From 8fcd8d1e63c05c48b3ac16d0c3e2cd6a7a5c8ec4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 26 Jul 2024 04:23:14 +0900 Subject: [PATCH 001/385] kbuild: clean up code duplication in cmd_fdtoverlay When resolving a merge conflict, Linus noticed the fdtoverlay command duplication introduced by commit 49636c5680b9 ("kbuild: verify dtoverlay files against schema"). He suggested a clean-up. I eliminated the duplication and refactored the code a little further. No functional changes are intended, except for the short logs. The log will look as follows: $ make ARCH=arm64 defconfig dtbs_check [ snip ] DTC [C] arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxca.dtb DTC [C] arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dtb DTC [C] arch/arm64/boot/dts/freescale/imx93-var-som-symphony.dtb DTC [C] arch/arm64/boot/dts/freescale/imx95-19x19-evk.dtb DTC arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-imx219.dtbo OVL [C] arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-imx219.dtb The tag [C] indicates that the schema check is executed. Link: https://lore.kernel.org/lkml/CAHk-=wiF3yeWehcvqY-4X7WNb8n4yw_5t0H1CpEpKi7JMjaMfw@mail.gmail.com/#t Requested-by: Linus Torvalds Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Schier --- scripts/Makefile.lib | 28 ++++++++++------------------ 1 file changed, 10 insertions(+), 18 deletions(-) diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index fe3668dc4954b..207325eaf1d1c 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -400,26 +400,23 @@ $(obj)/%.dtb.S: $(obj)/%.dtb FORCE $(obj)/%.dtbo.S: $(obj)/%.dtbo FORCE $(call if_changed,wrap_S_dtb) -quiet_cmd_dtc = DTC $@ +quiet_dtb_check_tag = $(if $(dtb-check-enabled),[C], ) +cmd_dtb_check = $(if $(dtb-check-enabled),; $(DT_CHECKER) $(DT_CHECKER_FLAGS) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) $@ || true) + +quiet_cmd_dtc = DTC $(quiet_dtb_check_tag) $@ cmd_dtc = $(HOSTCC) -E $(dtc_cpp_flags) -x assembler-with-cpp -o $(dtc-tmp) $< ; \ $(DTC) -o $@ -b 0 \ $(addprefix -i,$(dir $<) $(DTC_INCLUDE)) $(DTC_FLAGS) \ -d $(depfile).dtc.tmp $(dtc-tmp) ; \ - cat $(depfile).pre.tmp $(depfile).dtc.tmp > $(depfile) - -DT_CHECK_CMD = $(DT_CHECKER) $(DT_CHECKER_FLAGS) -u $(srctree)/$(DT_BINDING_DIR) -p $(DT_TMP_SCHEMA) + cat $(depfile).pre.tmp $(depfile).dtc.tmp > $(depfile) \ + $(cmd_dtb_check) # NOTE: # Do not replace $(filter %.dtb %.dtbo, $^) with $(real-prereqs). When a single # DTB is turned into a multi-blob DTB, $^ will contain header file dependencies # recorded in the .*.cmd file. -ifneq ($(CHECK_DTBS),) -quiet_cmd_fdtoverlay = DTOVLCH $@ - cmd_fdtoverlay = $(objtree)/scripts/dtc/fdtoverlay -o $@ -i $(filter %.dtb %.dtbo, $^) ; $(DT_CHECK_CMD) $@ || true -else -quiet_cmd_fdtoverlay = DTOVL $@ - cmd_fdtoverlay = $(objtree)/scripts/dtc/fdtoverlay -o $@ -i $(filter %.dtb %.dtbo, $^) -endif +quiet_cmd_fdtoverlay = OVL $(quiet_dtb_check_tag) $@ + cmd_fdtoverlay = $(objtree)/scripts/dtc/fdtoverlay -o $@ -i $(filter %.dtb %.dtbo, $^) $(cmd_dtb_check) $(multi-dtb-y): FORCE $(call if_changed,fdtoverlay) @@ -430,16 +427,11 @@ DT_CHECKER ?= dt-validate DT_CHECKER_FLAGS ?= $(if $(DT_SCHEMA_FILES),-l $(DT_SCHEMA_FILES),-m) DT_BINDING_DIR := Documentation/devicetree/bindings DT_TMP_SCHEMA := $(objtree)/$(DT_BINDING_DIR)/processed-schema.json - -quiet_cmd_dtb = DTC_CHK $@ - cmd_dtb = $(cmd_dtc) ; $(DT_CHECK_CMD) $@ || true -else -quiet_cmd_dtb = $(quiet_cmd_dtc) - cmd_dtb = $(cmd_dtc) +dtb-check-enabled = $(if $(filter %.dtb, $@),y) endif $(obj)/%.dtb: $(obj)/%.dts $(DTC) $(DT_TMP_SCHEMA) FORCE - $(call if_changed_dep,dtb) + $(call if_changed_dep,dtc) $(obj)/%.dtbo: $(src)/%.dtso $(DTC) FORCE $(call if_changed_dep,dtc) From 6fc9aacad49e3fbecd270c266850d50c453d52ef Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Sun, 4 Aug 2024 14:50:57 +0900 Subject: [PATCH 002/385] Makefile: add $(srctree) to dependency of compile_commands.json target When trying to build compile_commands.json for an external module against the kernel built in a separate output directory, the following error is displayed: make[1]: *** No rule to make target 'scripts/clang-tools/gen_compile_commands.py', needed by 'compile_commands.json'. Stop. This is because gen_compile_commands.py was previously looked up using a relative path to $(srctree), but commit b1992c3772e6 ("kbuild: use $(src) instead of $(srctree)/$(src) for source directory") stopped defining VPATH for external module builds. Prefixing gen_compile_commands.py with $(srctree) fixes the problem. Fixes: b1992c3772e6 ("kbuild: use $(src) instead of $(srctree)/$(src) for source directory") Signed-off-by: Alexandre Courbot Reviewed-by: Nicolas Schier Signed-off-by: Masahiro Yamada --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 44c02a6f60a14..44c33de28e933 100644 --- a/Makefile +++ b/Makefile @@ -1980,7 +1980,7 @@ nsdeps: modules quiet_cmd_gen_compile_commands = GEN $@ cmd_gen_compile_commands = $(PYTHON3) $< -a $(AR) -o $@ $(filter-out $<, $(real-prereqs)) -$(extmod_prefix)compile_commands.json: scripts/clang-tools/gen_compile_commands.py \ +$(extmod_prefix)compile_commands.json: $(srctree)/scripts/clang-tools/gen_compile_commands.py \ $(if $(KBUILD_EXTMOD),, vmlinux.a $(KBUILD_VMLINUX_LIBS)) \ $(if $(CONFIG_MODULES), $(MODORDER)) FORCE $(call if_changed,gen_compile_commands) From 33330bcf031818e60a816db0cfd3add9eecc3b28 Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Mon, 5 Aug 2024 11:22:34 +0200 Subject: [PATCH 003/385] scripts: kconfig: merge_config: config files: add a trailing newline When merging files without trailing newlines at the end of the file, two config fragments end up at the same row if file1.config doens't have a trailing newline at the end of the file. file1.config "CONFIG_1=y" file2.config "CONFIG_2=y" ./scripts/kconfig/merge_config.sh -m .config file1.config file2.config This will generate a .config looking like this. cat .config ... CONFIG_1=yCONFIG_2=y" Making sure so we add a newline at the end of every config file that is passed into the script. Signed-off-by: Anders Roxell Signed-off-by: Masahiro Yamada --- scripts/kconfig/merge_config.sh | 2 ++ 1 file changed, 2 insertions(+) diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh index 902eb429b9dbd..0b7952471c18f 100755 --- a/scripts/kconfig/merge_config.sh +++ b/scripts/kconfig/merge_config.sh @@ -167,6 +167,8 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do sed -i "/$CFG[ =]/d" $MERGE_FILE fi done + # In case the previous file lacks a new line at the end + echo >> $TMP_FILE cat $MERGE_FILE >> $TMP_FILE done From a39036847fa3a0cc09895e1693ef3ab5b74dce1e Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 6 Aug 2024 11:56:01 +0100 Subject: [PATCH 004/385] bnx2x: Provide declaration of dmae_reg_go_c in header Provide declaration of dmae_reg_go_c in header. This symbol is defined in bnx2x_main.c. And used in that file and bnx2x_stats.c. However, Sparse complains that there is no declaration of the symbol in dmae_reg_go_c nor is the symbol static. .../bnx2x_main.c:291:11: warning: symbol 'dmae_reg_go_c' was not declared. Should it be static? Address this by moving the declaration from bnx2x_stats.c to bnx2x_reg.h. No functional change intended. Compile tested only. Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240806-bnx2x-dec-v1-1-ae844ec785e4@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h | 2 ++ drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h index 4e9215bce4ad4..a018f251d1986 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h @@ -868,6 +868,8 @@ #define DORQ_REG_VF_TYPE_VALUE_0 0x170258 #define DORQ_REG_VF_USAGE_CT_LIMIT 0x170340 +extern const u32 dmae_reg_go_c[]; + /* [RW 4] Initial activity counter value on the load request; when the shortcut is done. */ #define DORQ_REG_SHRT_ACT_CNT 0x170070 diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c index 2bb133ae61c39..ba6729f2f9c0f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c @@ -23,8 +23,6 @@ #include "bnx2x_cmn.h" #include "bnx2x_sriov.h" -extern const u32 dmae_reg_go_c[]; - /* Statistics */ /* From df665ab188cdca8b8b3e0cca84a6511c395f9ece Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Wed, 7 Aug 2024 12:02:53 -0700 Subject: [PATCH 005/385] net: atlantic: use ethtool_sprintf Allows simplifying get_strings and avoids manual pointer manipulation. Signed-off-by: Rosen Penev Reviewed-by: Joe Damato Link: https://patch.msgid.link/20240807190303.6143-1-rosenp@gmail.com Signed-off-by: Jakub Kicinski --- .../ethernet/aquantia/atlantic/aq_ethtool.c | 21 +++++++------------ 1 file changed, 7 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index d0aecd1d73573..38f22918c699f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -279,18 +279,16 @@ static void aq_ethtool_get_strings(struct net_device *ndev, for (i = 0; i < cfg->vecs; i++) { for (si = 0; si < rx_stat_cnt; si++) { - snprintf(p, ETH_GSTRING_LEN, + ethtool_sprintf(&p, aq_ethtool_queue_rx_stat_names[si], tc_string, AQ_NIC_CFG_TCVEC2RING(cfg, tc, i)); - p += ETH_GSTRING_LEN; } for (si = 0; si < tx_stat_cnt; si++) { - snprintf(p, ETH_GSTRING_LEN, + ethtool_sprintf(&p, aq_ethtool_queue_tx_stat_names[si], tc_string, AQ_NIC_CFG_TCVEC2RING(cfg, tc, i)); - p += ETH_GSTRING_LEN; } } } @@ -305,20 +303,18 @@ static void aq_ethtool_get_strings(struct net_device *ndev, for (i = 0; i < max(rx_ring_cnt, tx_ring_cnt); i++) { for (si = 0; si < rx_stat_cnt; si++) { - snprintf(p, ETH_GSTRING_LEN, + ethtool_sprintf(&p, aq_ethtool_queue_rx_stat_names[si], tc_string, i ? PTP_HWST_RING_IDX : ptp_ring_idx); - p += ETH_GSTRING_LEN; } if (i >= tx_ring_cnt) continue; for (si = 0; si < tx_stat_cnt; si++) { - snprintf(p, ETH_GSTRING_LEN, + ethtool_sprintf(&p, aq_ethtool_queue_tx_stat_names[si], tc_string, i ? PTP_HWST_RING_IDX : ptp_ring_idx); - p += ETH_GSTRING_LEN; } } } @@ -338,9 +334,8 @@ static void aq_ethtool_get_strings(struct net_device *ndev, for (si = 0; si < ARRAY_SIZE(aq_macsec_txsc_stat_names); si++) { - snprintf(p, ETH_GSTRING_LEN, + ethtool_sprintf(&p, aq_macsec_txsc_stat_names[si], i); - p += ETH_GSTRING_LEN; } aq_txsc = &nic->macsec_cfg->aq_txsc[i]; for (sa = 0; sa < MACSEC_NUM_AN; sa++) { @@ -349,10 +344,9 @@ static void aq_ethtool_get_strings(struct net_device *ndev, for (si = 0; si < ARRAY_SIZE(aq_macsec_txsa_stat_names); si++) { - snprintf(p, ETH_GSTRING_LEN, + ethtool_sprintf(&p, aq_macsec_txsa_stat_names[si], i, sa); - p += ETH_GSTRING_LEN; } } } @@ -369,10 +363,9 @@ static void aq_ethtool_get_strings(struct net_device *ndev, for (si = 0; si < ARRAY_SIZE(aq_macsec_rxsa_stat_names); si++) { - snprintf(p, ETH_GSTRING_LEN, + ethtool_sprintf(&p, aq_macsec_rxsa_stat_names[si], i, sa); - p += ETH_GSTRING_LEN; } } } From ceb627435b00fe3bcee5957aeb3e5282a1f06eb6 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Wed, 7 Aug 2024 17:06:13 +0100 Subject: [PATCH 006/385] net: ethtool: check rxfh_max_num_contexts != 1 at register time A value of 1 doesn't make sense, as it implies the only allowed context ID is 0, which is reserved for the default context - in which case the driver should just not claim to support custom RSS contexts at all. Suggested-by: Jakub Kicinski Signed-off-by: Edward Cree Link: https://lore.kernel.org/c07725b3a3d0b0a63b85e230f9c77af59d4d07f8.1723045898.git.ecree.xilinx@gmail.com Signed-off-by: Jakub Kicinski --- net/ethtool/common.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 07032babd1b69..5f714bbbef195 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -654,6 +654,8 @@ int ethtool_check_ops(const struct ethtool_ops *ops) { if (WARN_ON(ops->set_coalesce && !ops->supported_coalesce_params)) return -EINVAL; + if (WARN_ON(ops->rxfh_max_num_contexts == 1)) + return -EINVAL; /* NOTE: sufficiently insane drivers may swap ethtool_ops at runtime, * the fact that ops are checked at registration time does not * mean the ops attached to a netdev later on are sane. From 09612576046a3cd29bd2b2b88c5813b1dfe96775 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 7 Aug 2024 14:22:26 +0200 Subject: [PATCH 007/385] net: sungem_phy: Constify struct mii_phy_def 'struct mii_phy_def' are not modified in this driver. Constifying these structures moves some data to a read-only section, so increase overall security. While at it fix the checkpatch warning related to this patch (some missing newlines and spaces around *) On a x86_64, with allmodconfig: Before: ====== 27709 928 0 28637 6fdd drivers/net/sungem_phy.o After: ===== text data bss dec hex filename 28157 476 0 28633 6fd9 drivers/net/sungem_phy.o Signed-off-by: Christophe JAILLET Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/54c3b30930f80f4895e6fa2f4234714fdea4ef4e.1723033266.git.christophe.jaillet@wanadoo.fr Signed-off-by: Jakub Kicinski --- drivers/net/sungem_phy.c | 35 +++++++++++++++++++---------------- include/linux/sungem_phy.h | 2 +- 2 files changed, 20 insertions(+), 17 deletions(-) diff --git a/drivers/net/sungem_phy.c b/drivers/net/sungem_phy.c index d591e33268e5f..55aa8d0c8e1f2 100644 --- a/drivers/net/sungem_phy.c +++ b/drivers/net/sungem_phy.c @@ -893,7 +893,7 @@ static const struct mii_phy_ops bcm5201_phy_ops = { .read_link = genmii_read_link, }; -static struct mii_phy_def bcm5201_phy_def = { +static const struct mii_phy_def bcm5201_phy_def = { .phy_id = 0x00406210, .phy_id_mask = 0xfffffff0, .name = "BCM5201", @@ -912,7 +912,7 @@ static const struct mii_phy_ops bcm5221_phy_ops = { .read_link = genmii_read_link, }; -static struct mii_phy_def bcm5221_phy_def = { +static const struct mii_phy_def bcm5221_phy_def = { .phy_id = 0x004061e0, .phy_id_mask = 0xfffffff0, .name = "BCM5221", @@ -930,7 +930,8 @@ static const struct mii_phy_ops bcm5241_phy_ops = { .poll_link = genmii_poll_link, .read_link = genmii_read_link, }; -static struct mii_phy_def bcm5241_phy_def = { + +static const struct mii_phy_def bcm5241_phy_def = { .phy_id = 0x0143bc30, .phy_id_mask = 0xfffffff0, .name = "BCM5241", @@ -949,7 +950,7 @@ static const struct mii_phy_ops bcm5400_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5400_phy_def = { +static const struct mii_phy_def bcm5400_phy_def = { .phy_id = 0x00206040, .phy_id_mask = 0xfffffff0, .name = "BCM5400", @@ -968,7 +969,7 @@ static const struct mii_phy_ops bcm5401_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5401_phy_def = { +static const struct mii_phy_def bcm5401_phy_def = { .phy_id = 0x00206050, .phy_id_mask = 0xfffffff0, .name = "BCM5401", @@ -987,7 +988,7 @@ static const struct mii_phy_ops bcm5411_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5411_phy_def = { +static const struct mii_phy_def bcm5411_phy_def = { .phy_id = 0x00206070, .phy_id_mask = 0xfffffff0, .name = "BCM5411", @@ -1007,7 +1008,7 @@ static const struct mii_phy_ops bcm5421_phy_ops = { .enable_fiber = bcm5421_enable_fiber, }; -static struct mii_phy_def bcm5421_phy_def = { +static const struct mii_phy_def bcm5421_phy_def = { .phy_id = 0x002060e0, .phy_id_mask = 0xfffffff0, .name = "BCM5421", @@ -1026,7 +1027,7 @@ static const struct mii_phy_ops bcm5421k2_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5421k2_phy_def = { +static const struct mii_phy_def bcm5421k2_phy_def = { .phy_id = 0x002062e0, .phy_id_mask = 0xfffffff0, .name = "BCM5421-K2", @@ -1045,7 +1046,7 @@ static const struct mii_phy_ops bcm5461_phy_ops = { .enable_fiber = bcm5461_enable_fiber, }; -static struct mii_phy_def bcm5461_phy_def = { +static const struct mii_phy_def bcm5461_phy_def = { .phy_id = 0x002060c0, .phy_id_mask = 0xfffffff0, .name = "BCM5461", @@ -1064,7 +1065,7 @@ static const struct mii_phy_ops bcm5462V_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5462V_phy_def = { +static const struct mii_phy_def bcm5462V_phy_def = { .phy_id = 0x002060d0, .phy_id_mask = 0xfffffff0, .name = "BCM5462-Vesta", @@ -1094,7 +1095,7 @@ static const struct mii_phy_ops marvell88e1111_phy_ops = { /* two revs in darwin for the 88e1101 ... I could use a datasheet * to get the proper names... */ -static struct mii_phy_def marvell88e1101v1_phy_def = { +static const struct mii_phy_def marvell88e1101v1_phy_def = { .phy_id = 0x01410c20, .phy_id_mask = 0xfffffff0, .name = "Marvell 88E1101v1", @@ -1102,7 +1103,8 @@ static struct mii_phy_def marvell88e1101v1_phy_def = { .magic_aneg = 1, .ops = &marvell88e1101_phy_ops }; -static struct mii_phy_def marvell88e1101v2_phy_def = { + +static const struct mii_phy_def marvell88e1101v2_phy_def = { .phy_id = 0x01410c60, .phy_id_mask = 0xfffffff0, .name = "Marvell 88E1101v2", @@ -1110,7 +1112,8 @@ static struct mii_phy_def marvell88e1101v2_phy_def = { .magic_aneg = 1, .ops = &marvell88e1101_phy_ops }; -static struct mii_phy_def marvell88e1111_phy_def = { + +static const struct mii_phy_def marvell88e1111_phy_def = { .phy_id = 0x01410cc0, .phy_id_mask = 0xfffffff0, .name = "Marvell 88E1111", @@ -1127,7 +1130,7 @@ static const struct mii_phy_ops generic_phy_ops = { .read_link = genmii_read_link }; -static struct mii_phy_def genmii_phy_def = { +static const struct mii_phy_def genmii_phy_def = { .phy_id = 0x00000000, .phy_id_mask = 0x00000000, .name = "Generic MII", @@ -1136,7 +1139,7 @@ static struct mii_phy_def genmii_phy_def = { .ops = &generic_phy_ops }; -static struct mii_phy_def* mii_phy_table[] = { +static const struct mii_phy_def *mii_phy_table[] = { &bcm5201_phy_def, &bcm5221_phy_def, &bcm5241_phy_def, @@ -1156,9 +1159,9 @@ static struct mii_phy_def* mii_phy_table[] = { int sungem_phy_probe(struct mii_phy *phy, int mii_id) { + const struct mii_phy_def *def; int rc; u32 id; - struct mii_phy_def* def; int i; /* We do not reset the mii_phy structure as the driver diff --git a/include/linux/sungem_phy.h b/include/linux/sungem_phy.h index c505f30e8b685..eecc7eb63bfb7 100644 --- a/include/linux/sungem_phy.h +++ b/include/linux/sungem_phy.h @@ -40,7 +40,7 @@ enum { /* An instance of a PHY, partially borrowed from mii_if_info */ struct mii_phy { - struct mii_phy_def* def; + const struct mii_phy_def *def; u32 advertising; int mii_id; From eb3ab13d997a2f12ec9d557b6ae2aea4e28e2bc3 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Wed, 7 Aug 2024 14:12:15 +0200 Subject: [PATCH 008/385] net: ti: icssg_prueth: populate netdev of_node Allow of_find_net_device_by_node() to find icssg_prueth ports and make the individual ports' of_nodes available in sysfs. Signed-off-by: Matthias Schiffer Reviewed-by: MD Danish Anwar Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20240807121215.3178964-1-matthias.schiffer@ew.tq-group.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ti/icssg/icssg_prueth.c | 1 + drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 9dc9de39bb8f0..53a3e44b99a20 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -857,6 +857,7 @@ static int prueth_netdev_init(struct prueth *prueth, } ether_addr_copy(emac->mac_addr, ndev->dev_addr); + ndev->dev.of_node = eth_node; ndev->min_mtu = PRUETH_MIN_PKT_SIZE; ndev->max_mtu = PRUETH_MAX_MTU; ndev->netdev_ops = &emac_netdev_ops; diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c index 54b7e27608ce8..292f04d29f4f7 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c @@ -847,6 +847,7 @@ static int prueth_netdev_init(struct prueth *prueth, } ether_addr_copy(emac->mac_addr, ndev->dev_addr); + ndev->dev.of_node = eth_node; ndev->min_mtu = PRUETH_MIN_PKT_SIZE; ndev->max_mtu = PRUETH_MAX_MTU; ndev->netdev_ops = &emac_netdev_ops; From 2524d6c28bdcb114372e86354c88d2e47eb1019d Mon Sep 17 00:00:00 2001 From: Pawel Dembicki Date: Mon, 5 Aug 2024 23:23:22 +0200 Subject: [PATCH 009/385] net: dsa: vsc73xx: use defined values in phy operations This commit changes magic numbers in phy operations. Some shifted registers was replaced with bitfield macros. No functional changes done. Reviewed-by: Linus Walleij Reviewed-by: Florian Fainelli Signed-off-by: Pawel Dembicki Signed-off-by: David S. Miller --- drivers/net/dsa/vitesse-vsc73xx-core.c | 45 +++++++++++++++++++------- 1 file changed, 33 insertions(+), 12 deletions(-) diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index 1711e780e65b6..a82b550a9e40f 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -41,7 +42,8 @@ #define VSC73XX_BLOCK_SYSTEM 0x7 /* Only subblock 0 */ /* MII Block subblock */ -#define VSC73XX_BLOCK_MII_INTERNAL 0x0 /* Internal MDIO subblock */ +#define VSC73XX_BLOCK_MII_INTERNAL 0x0 /* Internal MDIO subblock */ +#define VSC73XX_BLOCK_MII_EXTERNAL 0x1 /* External MDIO subblock */ #define CPU_PORT 6 /* CPU port */ @@ -224,10 +226,23 @@ #define VSC73XX_VLANACCESS_VLAN_TBL_CMD_CLEAR_TABLE 3 /* MII block 3 registers */ -#define VSC73XX_MII_STAT 0x0 -#define VSC73XX_MII_CMD 0x1 -#define VSC73XX_MII_DATA 0x2 -#define VSC73XX_MII_MPRES 0x3 +#define VSC73XX_MII_STAT 0x0 +#define VSC73XX_MII_CMD 0x1 +#define VSC73XX_MII_DATA 0x2 +#define VSC73XX_MII_MPRES 0x3 + +#define VSC73XX_MII_STAT_BUSY BIT(3) +#define VSC73XX_MII_STAT_READ BIT(2) +#define VSC73XX_MII_STAT_WRITE BIT(1) + +#define VSC73XX_MII_CMD_SCAN BIT(27) +#define VSC73XX_MII_CMD_OPERATION BIT(26) +#define VSC73XX_MII_CMD_PHY_ADDR GENMASK(25, 21) +#define VSC73XX_MII_CMD_PHY_REG GENMASK(20, 16) +#define VSC73XX_MII_CMD_WRITE_DATA GENMASK(15, 0) + +#define VSC73XX_MII_DATA_FAILURE BIT(16) +#define VSC73XX_MII_DATA_READ_DATA GENMASK(15, 0) #define VSC73XX_MII_MPRES_NOPREAMBLE BIT(6) #define VSC73XX_MII_MPRES_PRESCALEVAL GENMASK(5, 0) @@ -543,20 +558,24 @@ static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum) int ret; /* Setting bit 26 means "read" */ - cmd = BIT(26) | (phy << 21) | (regnum << 16); - ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd); + cmd = VSC73XX_MII_CMD_OPERATION | + FIELD_PREP(VSC73XX_MII_CMD_PHY_ADDR, phy) | + FIELD_PREP(VSC73XX_MII_CMD_PHY_REG, regnum); + ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL, + VSC73XX_MII_CMD, cmd); if (ret) return ret; msleep(2); - ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, 0, 2, &val); + ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL, + VSC73XX_MII_DATA, &val); if (ret) return ret; - if (val & BIT(16)) { + if (val & VSC73XX_MII_DATA_FAILURE) { dev_err(vsc->dev, "reading reg %02x from phy%d failed\n", regnum, phy); return -EIO; } - val &= 0xFFFFU; + val &= VSC73XX_MII_DATA_READ_DATA; dev_dbg(vsc->dev, "read reg %02x from phy%d = %04x\n", regnum, phy, val); @@ -582,8 +601,10 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum, return 0; } - cmd = (phy << 21) | (regnum << 16); - ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd); + cmd = FIELD_PREP(VSC73XX_MII_CMD_PHY_ADDR, phy) | + FIELD_PREP(VSC73XX_MII_CMD_PHY_REG, regnum); + ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL, + VSC73XX_MII_CMD, cmd); if (ret) return ret; From 36fb51479e3c1112013f60f01e3b9725f8f9baf7 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 6 Aug 2024 11:52:01 +0100 Subject: [PATCH 010/385] net: stmmac: xgmac: use const char arrays for string constants Jiri Slaby advises me that the preferred mechanism for declaring string constants is static char arrays, so use that here. This mostly reverts commit 1692b9775e74 ("net: stmmac: xgmac: use #define for string constants") That commit was a fix for commit 46eba193d04f ("net: stmmac: xgmac: fix handling of DPP safety error for DMA channels"). The fix being replacing const char * with #defines in order to address compilation failures observed on GCC 6 through 10. Compile tested only. No functional change intended. Suggested-by: Jiri Slaby Link: https://lore.kernel.org/netdev/485dbc5a-a04b-40c2-9481-955eaa5ce2e2@kernel.org/ Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- .../ethernet/stmicro/stmmac/dwxgmac2_core.c | 69 +++++++++---------- 1 file changed, 34 insertions(+), 35 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index f196cd99d5104..cbf2dd976ab1d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -846,42 +846,41 @@ static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= { { false, "UNKNOWN", "Unknown Error" }, /* 31 */ }; -#define DPP_RX_ERR "Read Rx Descriptor Parity checker Error" -#define DPP_TX_ERR "Read Tx Descriptor Parity checker Error" - +static const char dpp_rx_err[] = "Read Rx Descriptor Parity checker Error"; +static const char dpp_tx_err[] = "Read Tx Descriptor Parity checker Error"; static const struct dwxgmac3_error_desc dwxgmac3_dma_dpp_errors[32] = { - { true, "TDPES0", DPP_TX_ERR }, - { true, "TDPES1", DPP_TX_ERR }, - { true, "TDPES2", DPP_TX_ERR }, - { true, "TDPES3", DPP_TX_ERR }, - { true, "TDPES4", DPP_TX_ERR }, - { true, "TDPES5", DPP_TX_ERR }, - { true, "TDPES6", DPP_TX_ERR }, - { true, "TDPES7", DPP_TX_ERR }, - { true, "TDPES8", DPP_TX_ERR }, - { true, "TDPES9", DPP_TX_ERR }, - { true, "TDPES10", DPP_TX_ERR }, - { true, "TDPES11", DPP_TX_ERR }, - { true, "TDPES12", DPP_TX_ERR }, - { true, "TDPES13", DPP_TX_ERR }, - { true, "TDPES14", DPP_TX_ERR }, - { true, "TDPES15", DPP_TX_ERR }, - { true, "RDPES0", DPP_RX_ERR }, - { true, "RDPES1", DPP_RX_ERR }, - { true, "RDPES2", DPP_RX_ERR }, - { true, "RDPES3", DPP_RX_ERR }, - { true, "RDPES4", DPP_RX_ERR }, - { true, "RDPES5", DPP_RX_ERR }, - { true, "RDPES6", DPP_RX_ERR }, - { true, "RDPES7", DPP_RX_ERR }, - { true, "RDPES8", DPP_RX_ERR }, - { true, "RDPES9", DPP_RX_ERR }, - { true, "RDPES10", DPP_RX_ERR }, - { true, "RDPES11", DPP_RX_ERR }, - { true, "RDPES12", DPP_RX_ERR }, - { true, "RDPES13", DPP_RX_ERR }, - { true, "RDPES14", DPP_RX_ERR }, - { true, "RDPES15", DPP_RX_ERR }, + { true, "TDPES0", dpp_tx_err }, + { true, "TDPES1", dpp_tx_err }, + { true, "TDPES2", dpp_tx_err }, + { true, "TDPES3", dpp_tx_err }, + { true, "TDPES4", dpp_tx_err }, + { true, "TDPES5", dpp_tx_err }, + { true, "TDPES6", dpp_tx_err }, + { true, "TDPES7", dpp_tx_err }, + { true, "TDPES8", dpp_tx_err }, + { true, "TDPES9", dpp_tx_err }, + { true, "TDPES10", dpp_tx_err }, + { true, "TDPES11", dpp_tx_err }, + { true, "TDPES12", dpp_tx_err }, + { true, "TDPES13", dpp_tx_err }, + { true, "TDPES14", dpp_tx_err }, + { true, "TDPES15", dpp_tx_err }, + { true, "RDPES0", dpp_rx_err }, + { true, "RDPES1", dpp_rx_err }, + { true, "RDPES2", dpp_rx_err }, + { true, "RDPES3", dpp_rx_err }, + { true, "RDPES4", dpp_rx_err }, + { true, "RDPES5", dpp_rx_err }, + { true, "RDPES6", dpp_rx_err }, + { true, "RDPES7", dpp_rx_err }, + { true, "RDPES8", dpp_rx_err }, + { true, "RDPES9", dpp_rx_err }, + { true, "RDPES10", dpp_rx_err }, + { true, "RDPES11", dpp_rx_err }, + { true, "RDPES12", dpp_rx_err }, + { true, "RDPES13", dpp_rx_err }, + { true, "RDPES14", dpp_rx_err }, + { true, "RDPES15", dpp_rx_err }, }; static void dwxgmac3_handle_dma_err(struct net_device *ndev, From a0f6e5e9f1f8a0837a9e3ccc5a1f98cbfd2a6cf4 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Tue, 6 Aug 2024 08:38:07 -0700 Subject: [PATCH 011/385] .gitignore: add .gcda files These files contain the runtime coverage data generated by gcov. Signed-off-by: Vegard Nossum Signed-off-by: Chuck Lever Signed-off-by: Allison Henderson Signed-off-by: David S. Miller --- .gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/.gitignore b/.gitignore index 7902adf4f7f1a..38b7ab9e7dc4f 100644 --- a/.gitignore +++ b/.gitignore @@ -24,6 +24,7 @@ *.dwo *.elf *.gcno +*.gcda *.gz *.i *.ko From bc75dcc3cea797974913c6ccdbe17ed470be3da6 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Tue, 6 Aug 2024 08:38:08 -0700 Subject: [PATCH 012/385] net: rds: add option for GCOV profiling To better our unit tests we need code coverage to be part of the kernel. This patch borrows heavily from how CONFIG_GCOV_PROFILE_FTRACE is implemented Reviewed-by: Chuck Lever Signed-off-by: Vegard Nossum Signed-off-by: Allison Henderson Signed-off-by: David S. Miller --- net/rds/Kconfig | 9 +++++++++ net/rds/Makefile | 5 +++++ 2 files changed, 14 insertions(+) diff --git a/net/rds/Kconfig b/net/rds/Kconfig index 75cd696963b28..f007730aa2bb6 100644 --- a/net/rds/Kconfig +++ b/net/rds/Kconfig @@ -26,3 +26,12 @@ config RDS_DEBUG bool "RDS debugging messages" depends on RDS default n + +config GCOV_PROFILE_RDS + bool "Enable GCOV profiling on RDS" + depends on GCOV_KERNEL + help + Enable GCOV profiling on RDS for checking which functions/lines + are executed. + + If unsure, say N. diff --git a/net/rds/Makefile b/net/rds/Makefile index 8fdc118e29275..3af1ca1d965ce 100644 --- a/net/rds/Makefile +++ b/net/rds/Makefile @@ -15,3 +15,8 @@ rds_tcp-y := tcp.o tcp_connect.o tcp_listen.o tcp_recv.o \ tcp_send.o tcp_stats.o ccflags-$(CONFIG_RDS_DEBUG) := -DRDS_DEBUG + +# for GCOV coverage profiling +ifdef CONFIG_GCOV_PROFILE_RDS +GCOV_PROFILE := y +endif From 3ade6ce1255e6e97f91b8ba77408dce9d2292df2 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Tue, 6 Aug 2024 08:38:09 -0700 Subject: [PATCH 013/385] selftests: rds: add testing infrastructure This adds some basic self-testing infrastructure for RDS-TCP. Signed-off-by: Vegard Nossum Signed-off-by: Chuck Lever Signed-off-by: Allison Henderson Signed-off-by: David S. Miller --- Documentation/dev-tools/gcov.rst | 11 + MAINTAINERS | 1 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/net/rds/Makefile | 12 + tools/testing/selftests/net/rds/README.txt | 41 ++++ tools/testing/selftests/net/rds/config.sh | 53 +++++ tools/testing/selftests/net/rds/run.sh | 224 ++++++++++++++++++ tools/testing/selftests/net/rds/test.py | 262 +++++++++++++++++++++ 8 files changed, 605 insertions(+) create mode 100644 tools/testing/selftests/net/rds/Makefile create mode 100644 tools/testing/selftests/net/rds/README.txt create mode 100755 tools/testing/selftests/net/rds/config.sh create mode 100755 tools/testing/selftests/net/rds/run.sh create mode 100644 tools/testing/selftests/net/rds/test.py diff --git a/Documentation/dev-tools/gcov.rst b/Documentation/dev-tools/gcov.rst index 5fce2b06f2295..dbd26b02ff3c9 100644 --- a/Documentation/dev-tools/gcov.rst +++ b/Documentation/dev-tools/gcov.rst @@ -75,6 +75,17 @@ Only files which are linked to the main kernel image or are compiled as kernel modules are supported by this mechanism. +Module specific configs +----------------------- + +Gcov kernel configs for specific modules are described below: + +CONFIG_GCOV_PROFILE_RDS: + Enables GCOV profiling on RDS for checking which functions or + lines are executed. This config is used by the rds selftest to + generate coverage reports. If left unset the report is omitted. + + Files ----- diff --git a/MAINTAINERS b/MAINTAINERS index 1a7ea5c7c7100..7b291c3a9aa4a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19197,6 +19197,7 @@ S: Supported W: https://oss.oracle.com/projects/rds/ F: Documentation/networking/rds.rst F: net/rds/ +F: tools/testing/selftests/net/rds/ RDT - RESOURCE ALLOCATION M: Fenghua Yu diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index bc8fe9e8f7f20..a5f1c0c27dff9 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -68,6 +68,7 @@ TARGETS += net/mptcp TARGETS += net/openvswitch TARGETS += net/tcp_ao TARGETS += net/netfilter +TARGETS += net/rds TARGETS += nsfs TARGETS += perf_events TARGETS += pidfd diff --git a/tools/testing/selftests/net/rds/Makefile b/tools/testing/selftests/net/rds/Makefile new file mode 100644 index 0000000000000..da9714bc7aad3 --- /dev/null +++ b/tools/testing/selftests/net/rds/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 + +all: + @echo mk_build_dir="$(shell pwd)" > include.sh + +TEST_PROGS := run.sh \ + include.sh \ + test.py + +EXTRA_CLEAN := /tmp/rds_logs + +include ../../lib.mk diff --git a/tools/testing/selftests/net/rds/README.txt b/tools/testing/selftests/net/rds/README.txt new file mode 100644 index 0000000000000..cbde2951ab13b --- /dev/null +++ b/tools/testing/selftests/net/rds/README.txt @@ -0,0 +1,41 @@ +RDS self-tests +============== + +These scripts provide a coverage test for RDS-TCP by creating two +network namespaces and running rds packets between them. A loopback +network is provisioned with optional probability of packet loss or +corruption. A workload of 50000 hashes, each 64 characters in size, +are passed over an RDS socket on this test network. A passing test means +the RDS-TCP stack was able to recover properly. The provided config.sh +can be used to compile the kernel with the necessary gcov options. The +kernel may optionally be configured to omit the coverage report as well. + +USAGE: + run.sh [-d logdir] [-l packet_loss] [-c packet_corruption] + [-u packet_duplcate] + +OPTIONS: + -d Log directory. Defaults to tools/testing/selftests/net/rds/rds_logs + + -l Simulates a percentage of packet loss + + -c Simulates a percentage of packet corruption + + -u Simulates a percentage of packet duplication. + +EXAMPLE: + + # Create a suitable gcov enabled .config + tools/testing/selftests/net/rds/config.sh -g + + # Alternatly create a gcov disabled .config + tools/testing/selftests/net/rds/config.sh + + # build the kernel + vng --build --config tools/testing/selftests/net/config + + # launch the tests in a VM + vng -v --rwdir ./ --run . --user root --cpus 4 -- \ + "export PYTHONPATH=tools/testing/selftests/net/; tools/testing/selftests/net/rds/run.sh" + +An HTML coverage report will be output in tools/testing/selftests/net/rds/rds_logs/coverage/. diff --git a/tools/testing/selftests/net/rds/config.sh b/tools/testing/selftests/net/rds/config.sh new file mode 100755 index 0000000000000..791c8dbe1095e --- /dev/null +++ b/tools/testing/selftests/net/rds/config.sh @@ -0,0 +1,53 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 + +set -e +set -u +set -x + +unset KBUILD_OUTPUT + +GENERATE_GCOV_REPORT=0 +while getopts "g" opt; do + case ${opt} in + g) + GENERATE_GCOV_REPORT=1 + ;; + :) + echo "USAGE: config.sh [-g]" + exit 1 + ;; + ?) + echo "Invalid option: -${OPTARG}." + exit 1 + ;; + esac +done + +CONF_FILE="tools/testing/selftests/net/config" + +# no modules +scripts/config --file "$CONF_FILE" --disable CONFIG_MODULES + +# enable RDS +scripts/config --file "$CONF_FILE" --enable CONFIG_RDS +scripts/config --file "$CONF_FILE" --enable CONFIG_RDS_TCP + +if [ "$GENERATE_GCOV_REPORT" -eq 1 ]; then + # instrument RDS and only RDS + scripts/config --file "$CONF_FILE" --enable CONFIG_GCOV_KERNEL + scripts/config --file "$CONF_FILE" --disable GCOV_PROFILE_ALL + scripts/config --file "$CONF_FILE" --enable GCOV_PROFILE_RDS +else + scripts/config --file "$CONF_FILE" --disable CONFIG_GCOV_KERNEL + scripts/config --file "$CONF_FILE" --disable GCOV_PROFILE_ALL + scripts/config --file "$CONF_FILE" --disable GCOV_PROFILE_RDS +fi + +# need network namespaces to run tests with veth network interfaces +scripts/config --file "$CONF_FILE" --enable CONFIG_NET_NS +scripts/config --file "$CONF_FILE" --enable CONFIG_VETH + +# simulate packet loss +scripts/config --file "$CONF_FILE" --enable CONFIG_NET_SCH_NETEM + diff --git a/tools/testing/selftests/net/rds/run.sh b/tools/testing/selftests/net/rds/run.sh new file mode 100755 index 0000000000000..8aee244f582a3 --- /dev/null +++ b/tools/testing/selftests/net/rds/run.sh @@ -0,0 +1,224 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 + +set -e +set -u + +unset KBUILD_OUTPUT + +current_dir="$(realpath "$(dirname "$0")")" +build_dir="$current_dir" + +build_include="$current_dir/include.sh" +if test -f "$build_include"; then + # this include will define "$mk_build_dir" as the location the test was + # built. We will need this if the tests are installed in a location + # other than the kernel source + + source "$build_include" + build_dir="$mk_build_dir" +fi + +# This test requires kernel source and the *.gcda data therein +# Locate the top level of the kernel source, and the net/rds +# subfolder with the appropriate *.gcno object files +ksrc_dir="$(realpath "$build_dir"/../../../../../)" +kconfig="$ksrc_dir/.config" +obj_dir="$ksrc_dir/net/rds" + +GCOV_CMD=gcov + +#check to see if the host has the required packages to generate a gcov report +check_gcov_env() +{ + if ! which "$GCOV_CMD" > /dev/null 2>&1; then + echo "Warning: Could not find gcov. " + GENERATE_GCOV_REPORT=0 + return + fi + + # the gcov version must match the gcc version + GCC_VER=$(gcc -dumpfullversion) + GCOV_VER=$($GCOV_CMD -v | grep gcov | awk '{print $3}'| awk 'BEGIN {FS="-"}{print $1}') + if [ "$GCOV_VER" != "$GCC_VER" ]; then + #attempt to find a matching gcov version + GCOV_CMD=gcov-$(gcc -dumpversion) + + if ! which "$GCOV_CMD" > /dev/null 2>&1; then + echo "Warning: Could not find an appropriate gcov installation. \ + gcov version must match gcc version" + GENERATE_GCOV_REPORT=0 + return + fi + + #recheck version number of found gcov executable + GCOV_VER=$($GCOV_CMD -v | grep gcov | awk '{print $3}'| \ + awk 'BEGIN {FS="-"}{print $1}') + if [ "$GCOV_VER" != "$GCC_VER" ]; then + echo "Warning: Could not find an appropriate gcov installation. \ + gcov version must match gcc version" + GENERATE_GCOV_REPORT=0 + else + echo "Warning: Mismatched gcc and gcov detected. Using $GCOV_CMD" + fi + fi +} + +# Check to see if the kconfig has the required configs to generate a coverage report +check_gcov_conf() +{ + if ! grep -x "CONFIG_GCOV_PROFILE_RDS=y" "$kconfig" > /dev/null 2>&1; then + echo "INFO: CONFIG_GCOV_PROFILE_RDS should be enabled for coverage reports" + GENERATE_GCOV_REPORT=0 + fi + if ! grep -x "CONFIG_GCOV_KERNEL=y" "$kconfig" > /dev/null 2>&1; then + echo "INFO: CONFIG_GCOV_KERNEL should be enabled for coverage reports" + GENERATE_GCOV_REPORT=0 + fi + if grep -x "CONFIG_GCOV_PROFILE_ALL=y" "$kconfig" > /dev/null 2>&1; then + echo "INFO: CONFIG_GCOV_PROFILE_ALL should be disabled for coverage reports" + GENERATE_GCOV_REPORT=0 + fi + + if [ "$GENERATE_GCOV_REPORT" -eq 0 ]; then + echo "To enable gcov reports, please run "\ + "\"tools/testing/selftests/net/rds/config.sh -g\" and rebuild the kernel" + else + # if we have the required kernel configs, proceed to check the environment to + # ensure we have the required gcov packages + check_gcov_env + fi +} + +# Kselftest framework requirement - SKIP code is 4. +check_conf_enabled() { + if ! grep -x "$1=y" "$kconfig" > /dev/null 2>&1; then + echo "selftests: [SKIP] This test requires $1 enabled" + echo "Please run tools/testing/selftests/net/rds/config.sh and rebuild the kernel" + exit 4 + fi +} +check_conf_disabled() { + if grep -x "$1=y" "$kconfig" > /dev/null 2>&1; then + echo "selftests: [SKIP] This test requires $1 disabled" + echo "Please run tools/testing/selftests/net/rds/config.sh and rebuild the kernel" + exit 4 + fi +} +check_conf() { + check_conf_enabled CONFIG_NET_SCH_NETEM + check_conf_enabled CONFIG_VETH + check_conf_enabled CONFIG_NET_NS + check_conf_enabled CONFIG_RDS_TCP + check_conf_enabled CONFIG_RDS + check_conf_disabled CONFIG_MODULES +} + +check_env() +{ + if ! test -d "$obj_dir"; then + echo "selftests: [SKIP] This test requires a kernel source tree" + exit 4 + fi + if ! test -e "$kconfig"; then + echo "selftests: [SKIP] This test requires a configured kernel source tree" + exit 4 + fi + if ! which strace > /dev/null 2>&1; then + echo "selftests: [SKIP] Could not run test without strace" + exit 4 + fi + if ! which tcpdump > /dev/null 2>&1; then + echo "selftests: [SKIP] Could not run test without tcpdump" + exit 4 + fi + + if ! which python3 > /dev/null 2>&1; then + echo "selftests: [SKIP] Could not run test without python3" + exit 4 + fi + + python_major=$(python3 -c "import sys; print(sys.version_info[0])") + python_minor=$(python3 -c "import sys; print(sys.version_info[1])") + if [[ python_major -lt 3 || ( python_major -eq 3 && python_minor -lt 9 ) ]] ; then + echo "selftests: [SKIP] Could not run test without at least python3.9" + python3 -V + exit 4 + fi +} + +LOG_DIR="$current_dir"/rds_logs +PLOSS=0 +PCORRUPT=0 +PDUP=0 +GENERATE_GCOV_REPORT=1 +while getopts "d:l:c:u:" opt; do + case ${opt} in + d) + LOG_DIR=${OPTARG} + ;; + l) + PLOSS=${OPTARG} + ;; + c) + PCORRUPT=${OPTARG} + ;; + u) + PDUP=${OPTARG} + ;; + :) + echo "USAGE: run.sh [-d logdir] [-l packet_loss] [-c packet_corruption]" \ + "[-u packet_duplcate] [-g]" + exit 1 + ;; + ?) + echo "Invalid option: -${OPTARG}." + exit 1 + ;; + esac +done + + +check_env +check_conf +check_gcov_conf + + +rm -fr "$LOG_DIR" +TRACE_FILE="${LOG_DIR}/rds-strace.txt" +COVR_DIR="${LOG_DIR}/coverage/" +mkdir -p "$LOG_DIR" +mkdir -p "$COVR_DIR" + +set +e +echo running RDS tests... +echo Traces will be logged to "$TRACE_FILE" +rm -f "$TRACE_FILE" +strace -T -tt -o "$TRACE_FILE" python3 "$(dirname "$0")/test.py" --timeout 400 -d "$LOG_DIR" \ + -l "$PLOSS" -c "$PCORRUPT" -u "$PDUP" + +test_rc=$? +dmesg > "${LOG_DIR}/dmesg.out" + +if [ "$GENERATE_GCOV_REPORT" -eq 1 ]; then + echo saving coverage data... + (set +x; cd /sys/kernel/debug/gcov; find ./* -name '*.gcda' | \ + while read -r f + do + cat < "/sys/kernel/debug/gcov/$f" > "/$f" + done) + + echo running gcovr... + gcovr -s --html-details --gcov-executable "$GCOV_CMD" --gcov-ignore-parse-errors \ + -o "${COVR_DIR}/gcovr" "${ksrc_dir}/net/rds/" +else + echo "Coverage report will be skipped" +fi + +if [ "$test_rc" -eq 0 ]; then + echo "PASS: Test completed successfully" +else + echo "FAIL: Test failed" +fi + +exit "$test_rc" diff --git a/tools/testing/selftests/net/rds/test.py b/tools/testing/selftests/net/rds/test.py new file mode 100644 index 0000000000000..e6bb109bcead3 --- /dev/null +++ b/tools/testing/selftests/net/rds/test.py @@ -0,0 +1,262 @@ +#! /usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import argparse +import ctypes +import errno +import hashlib +import os +import select +import signal +import socket +import subprocess +import sys +import atexit +from pwd import getpwuid +from os import stat +from lib.py import ip + + +libc = ctypes.cdll.LoadLibrary('libc.so.6') +setns = libc.setns + +net0 = 'net0' +net1 = 'net1' + +veth0 = 'veth0' +veth1 = 'veth1' + +# Helper function for creating a socket inside a network namespace. +# We need this because otherwise RDS will detect that the two TCP +# sockets are on the same interface and use the loop transport instead +# of the TCP transport. +def netns_socket(netns, *args): + u0, u1 = socket.socketpair(socket.AF_UNIX, socket.SOCK_SEQPACKET) + + child = os.fork() + if child == 0: + # change network namespace + with open(f'/var/run/netns/{netns}') as f: + try: + ret = setns(f.fileno(), 0) + except IOError as e: + print(e.errno) + print(e) + + # create socket in target namespace + s = socket.socket(*args) + + # send resulting socket to parent + socket.send_fds(u0, [], [s.fileno()]) + + sys.exit(0) + + # receive socket from child + _, s, _, _ = socket.recv_fds(u1, 0, 1) + os.waitpid(child, 0) + u0.close() + u1.close() + return socket.fromfd(s[0], *args) + +def signal_handler(sig, frame): + print('Test timed out') + sys.exit(1) + +#Parse out command line arguments. We take an optional +# timeout parameter and an optional log output folder +parser = argparse.ArgumentParser(description="init script args", + formatter_class=argparse.ArgumentDefaultsHelpFormatter) +parser.add_argument("-d", "--logdir", action="store", + help="directory to store logs", default="/tmp") +parser.add_argument('--timeout', help="timeout to terminate hung test", + type=int, default=0) +parser.add_argument('-l', '--loss', help="Simulate tcp packet loss", + type=int, default=0) +parser.add_argument('-c', '--corruption', help="Simulate tcp packet corruption", + type=int, default=0) +parser.add_argument('-u', '--duplicate', help="Simulate tcp packet duplication", + type=int, default=0) +args = parser.parse_args() +logdir=args.logdir +packet_loss=str(args.loss)+'%' +packet_corruption=str(args.corruption)+'%' +packet_duplicate=str(args.duplicate)+'%' + +ip(f"netns add {net0}") +ip(f"netns add {net1}") +ip(f"link add type veth") + +addrs = [ + # we technically don't need different port numbers, but this will + # help identify traffic in the network analyzer + ('10.0.0.1', 10000), + ('10.0.0.2', 20000), +] + +# move interfaces to separate namespaces so they can no longer be +# bound directly; this prevents rds from switching over from the tcp +# transport to the loop transport. +ip(f"link set {veth0} netns {net0} up") +ip(f"link set {veth1} netns {net1} up") + + + +# add addresses +ip(f"-n {net0} addr add {addrs[0][0]}/32 dev {veth0}") +ip(f"-n {net1} addr add {addrs[1][0]}/32 dev {veth1}") + +# add routes +ip(f"-n {net0} route add {addrs[1][0]}/32 dev {veth0}") +ip(f"-n {net1} route add {addrs[0][0]}/32 dev {veth1}") + +# sanity check that our two interfaces/addresses are correctly set up +# and communicating by doing a single ping +ip(f"netns exec {net0} ping -c 1 {addrs[1][0]}") + +# Start a packet capture on each network +for net in [net0, net1]: + tcpdump_pid = os.fork() + if tcpdump_pid == 0: + pcap = logdir+'/'+net+'.pcap' + subprocess.check_call(['touch', pcap]) + user = getpwuid(stat(pcap).st_uid).pw_name + ip(f"netns exec {net} /usr/sbin/tcpdump -Z {user} -i any -w {pcap}") + sys.exit(0) + +# simulate packet loss, duplication and corruption +for net, iface in [(net0, veth0), (net1, veth1)]: + ip(f"netns exec {net} /usr/sbin/tc qdisc add dev {iface} root netem \ + corrupt {packet_corruption} loss {packet_loss} duplicate \ + {packet_duplicate}") + +# add a timeout +if args.timeout > 0: + signal.alarm(args.timeout) + signal.signal(signal.SIGALRM, signal_handler) + +sockets = [ + netns_socket(net0, socket.AF_RDS, socket.SOCK_SEQPACKET), + netns_socket(net1, socket.AF_RDS, socket.SOCK_SEQPACKET), +] + +for s, addr in zip(sockets, addrs): + s.bind(addr) + s.setblocking(0) + +fileno_to_socket = { + s.fileno(): s for s in sockets +} + +addr_to_socket = { + addr: s for addr, s in zip(addrs, sockets) +} + +socket_to_addr = { + s: addr for addr, s in zip(addrs, sockets) +} + +send_hashes = {} +recv_hashes = {} + +ep = select.epoll() + +for s in sockets: + ep.register(s, select.EPOLLRDNORM) + +n = 50000 +nr_send = 0 +nr_recv = 0 + +while nr_send < n: + # Send as much as we can without blocking + print("sending...", nr_send, nr_recv) + while nr_send < n: + send_data = hashlib.sha256( + f'packet {nr_send}'.encode('utf-8')).hexdigest().encode('utf-8') + + # pseudo-random send/receive pattern + sender = sockets[nr_send % 2] + receiver = sockets[1 - (nr_send % 3) % 2] + + try: + sender.sendto(send_data, socket_to_addr[receiver]) + send_hashes.setdefault((sender.fileno(), receiver.fileno()), + hashlib.sha256()).update(f'<{send_data}>'.encode('utf-8')) + nr_send = nr_send + 1 + except BlockingIOError as e: + break + except OSError as e: + if e.errno in [errno.ENOBUFS, errno.ECONNRESET, errno.EPIPE]: + break + raise + + # Receive as much as we can without blocking + print("receiving...", nr_send, nr_recv) + while nr_recv < nr_send: + for fileno, eventmask in ep.poll(): + receiver = fileno_to_socket[fileno] + + if eventmask & select.EPOLLRDNORM: + while True: + try: + recv_data, address = receiver.recvfrom(1024) + sender = addr_to_socket[address] + recv_hashes.setdefault((sender.fileno(), + receiver.fileno()), hashlib.sha256()).update( + f'<{recv_data}>'.encode('utf-8')) + nr_recv = nr_recv + 1 + except BlockingIOError as e: + break + + # exercise net/rds/tcp.c:rds_tcp_sysctl_reset() + for net in [net0, net1]: + ip(f"netns exec {net} /usr/sbin/sysctl net.rds.tcp.rds_tcp_rcvbuf=10000") + ip(f"netns exec {net} /usr/sbin/sysctl net.rds.tcp.rds_tcp_sndbuf=10000") + +print("done", nr_send, nr_recv) + +# the Python socket module doesn't know these +RDS_INFO_FIRST = 10000 +RDS_INFO_LAST = 10017 + +nr_success = 0 +nr_error = 0 + +for s in sockets: + for optname in range(RDS_INFO_FIRST, RDS_INFO_LAST + 1): + # Sigh, the Python socket module doesn't allow us to pass + # buffer lengths greater than 1024 for some reason. RDS + # wants multiple pages. + try: + s.getsockopt(socket.SOL_RDS, optname, 1024) + nr_success = nr_success + 1 + except OSError as e: + nr_error = nr_error + 1 + if e.errno == errno.ENOSPC: + # ignore + pass + +print(f"getsockopt(): {nr_success}/{nr_error}") + +print("Stopping network packet captures") +subprocess.check_call(['killall', '-q', 'tcpdump']) + +# We're done sending and receiving stuff, now let's check if what +# we received is what we sent. +for (sender, receiver), send_hash in send_hashes.items(): + recv_hash = recv_hashes.get((sender, receiver)) + + if recv_hash is None: + print("FAIL: No data received") + sys.exit(1) + + if send_hash.hexdigest() != recv_hash.hexdigest(): + print("FAIL: Send/recv mismatch") + print("hash expected:", send_hash.hexdigest()) + print("hash received:", recv_hash.hexdigest()) + sys.exit(1) + + print(f"{sender}/{receiver}: ok") + +print("Success") +sys.exit(0) From 916b7d31f7eef81fe20f86ef52c36938fa971872 Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Thu, 8 Aug 2024 20:53:45 +0000 Subject: [PATCH 014/385] ethtool: refactor checking max channels Currently ethtool_set_channel calls separate functions to check whether the new channel number violates rss configuration or flow steering configuration. Very soon we need to check whether the new channel number violates memory provider configuration as well. To do all 3 checks cleanly, add a wrapper around ethtool_get_max_rxnfc_channel() and ethtool_get_max_rxfh_channel(), which does both checks. We can later extend this wrapper to add the memory provider check in one place. Note that in the current code, we put a descriptive genl error message when we run into issues. To preserve the error message, we pass the genl_info* to the common helper. The ioctl calls can pass NULL instead. Suggested-by: Jakub Kicinski Signed-off-by: Mina Almasry Link: https://patch.msgid.link/20240808205345.2141858-1-almasrymina@google.com Signed-off-by: Jakub Kicinski --- net/ethtool/channels.c | 20 ++++---------------- net/ethtool/common.c | 32 ++++++++++++++++++++++++++++++-- net/ethtool/common.h | 7 +++++-- net/ethtool/ioctl.c | 13 +++---------- 4 files changed, 42 insertions(+), 30 deletions(-) diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index cee188da54f85..ca4f80282448b 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -114,8 +114,7 @@ ethnl_set_channels(struct ethnl_req_info *req_info, struct genl_info *info) struct net_device *dev = req_info->dev; struct ethtool_channels channels = {}; struct nlattr **tb = info->attrs; - u32 err_attr, max_rxfh_in_use; - u64 max_rxnfc_in_use; + u32 err_attr; int ret; dev->ethtool_ops->get_channels(dev, &channels); @@ -166,20 +165,9 @@ ethnl_set_channels(struct ethnl_req_info *req_info, struct genl_info *info) return -EINVAL; } - /* ensure the new Rx count fits within the configured Rx flow - * indirection table/rxnfc settings - */ - if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) - max_rxnfc_in_use = 0; - max_rxfh_in_use = ethtool_get_max_rxfh_channel(dev); - if (channels.combined_count + channels.rx_count <= max_rxfh_in_use) { - GENL_SET_ERR_MSG_FMT(info, "requested channel counts are too low for existing indirection table (%d)", max_rxfh_in_use); - return -EINVAL; - } - if (channels.combined_count + channels.rx_count <= max_rxnfc_in_use) { - GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing ntuple filter settings"); - return -EINVAL; - } + ret = ethtool_check_max_channel(dev, channels, info); + if (ret) + return ret; /* Disabling channels, query zero-copy AF_XDP sockets */ from_channel = channels.combined_count + diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 5f714bbbef195..7257ae272296f 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -6,6 +6,7 @@ #include #include +#include "netlink.h" #include "common.h" const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { @@ -539,7 +540,7 @@ static int ethtool_get_rxnfc_rule_count(struct net_device *dev) return info.rule_cnt; } -int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max) +static int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max) { const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_rxnfc *info; @@ -609,7 +610,7 @@ static u32 ethtool_get_max_rss_ctx_channel(struct net_device *dev) return max_ring; } -u32 ethtool_get_max_rxfh_channel(struct net_device *dev) +static u32 ethtool_get_max_rxfh_channel(struct net_device *dev) { struct ethtool_rxfh_param rxfh = {}; u32 dev_size, current_max; @@ -650,6 +651,33 @@ u32 ethtool_get_max_rxfh_channel(struct net_device *dev) return current_max; } +int ethtool_check_max_channel(struct net_device *dev, + struct ethtool_channels channels, + struct genl_info *info) +{ + u64 max_rxnfc_in_use; + u32 max_rxfh_in_use; + + /* ensure the new Rx count fits within the configured Rx flow + * indirection table/rxnfc settings + */ + if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) + max_rxnfc_in_use = 0; + max_rxfh_in_use = ethtool_get_max_rxfh_channel(dev); + if (channels.combined_count + channels.rx_count <= max_rxfh_in_use) { + if (info) + GENL_SET_ERR_MSG_FMT(info, "requested channel counts are too low for existing indirection table (%d)", max_rxfh_in_use); + return -EINVAL; + } + if (channels.combined_count + channels.rx_count <= max_rxnfc_in_use) { + if (info) + GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing ntuple filter settings"); + return -EINVAL; + } + + return 0; +} + int ethtool_check_ops(const struct ethtool_ops *ops) { if (WARN_ON(ops->set_coalesce && !ops->supported_coalesce_params)) diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 863806fcf01ae..d55d5201b085d 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -20,6 +20,8 @@ struct link_mode_info { u8 duplex; }; +struct genl_info; + extern const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]; extern const char @@ -42,8 +44,9 @@ int __ethtool_get_link(struct net_device *dev); bool convert_legacy_settings_to_link_ksettings( struct ethtool_link_ksettings *link_ksettings, const struct ethtool_cmd *legacy_settings); -u32 ethtool_get_max_rxfh_channel(struct net_device *dev); -int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max); +int ethtool_check_max_channel(struct net_device *dev, + struct ethtool_channels channels, + struct genl_info *info); int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info); extern const struct ethtool_phy_ops *ethtool_phy_ops; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index e18823bf23306..ba8630eb02efe 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -2069,8 +2069,6 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, { struct ethtool_channels channels, curr = { .cmd = ETHTOOL_GCHANNELS }; u16 from_channel, to_channel; - u64 max_rxnfc_in_use; - u32 max_rxfh_in_use; unsigned int i; int ret; @@ -2100,14 +2098,9 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, (!channels.rx_count || !channels.tx_count)) return -EINVAL; - /* ensure the new Rx count fits within the configured Rx flow - * indirection table/rxnfc settings */ - if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) - max_rxnfc_in_use = 0; - max_rxfh_in_use = ethtool_get_max_rxfh_channel(dev); - if (channels.combined_count + channels.rx_count <= - max_t(u64, max_rxnfc_in_use, max_rxfh_in_use)) - return -EINVAL; + ret = ethtool_check_max_channel(dev, channels, NULL); + if (ret) + return ret; /* Disabling channels, query zero-copy AF_XDP sockets */ from_channel = channels.combined_count + From 2d5c9dd2cde33150f9dbb8ee091eff05eb6c7df3 Mon Sep 17 00:00:00 2001 From: zhangxiangqian Date: Thu, 8 Aug 2024 17:39:45 +0800 Subject: [PATCH 015/385] net: usb: cdc_ether: don't spew notifications The usbnet_link_change function is not called, if the link has not changed. ... [16913.807393][ 3] cdc_ether 1-2:2.0 enx00e0995fd1ac: kevent 12 may have been dropped [16913.822266][ 2] cdc_ether 1-2:2.0 enx00e0995fd1ac: kevent 12 may have been dropped [16913.826296][ 2] cdc_ether 1-2:2.0 enx00e0995fd1ac: kevent 11 may have been dropped ... kevent 11 is scheduled too frequently and may affect other event schedules. Signed-off-by: zhangxiangqian Acked-by: Oliver Neukum Link: https://patch.msgid.link/1723109985-11996-1-git-send-email-zhangxiangqian@kylinos.cn Signed-off-by: Jakub Kicinski --- drivers/net/usb/cdc_ether.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 6d61052353f07..a6469235d904e 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -418,7 +418,8 @@ void usbnet_cdc_status(struct usbnet *dev, struct urb *urb) case USB_CDC_NOTIFY_NETWORK_CONNECTION: netif_dbg(dev, timer, dev->net, "CDC: carrier %s\n", event->wValue ? "on" : "off"); - usbnet_link_change(dev, !!event->wValue, 0); + if (netif_carrier_ok(dev->net) != !!event->wValue) + usbnet_link_change(dev, !!event->wValue, 0); break; case USB_CDC_NOTIFY_SPEED_CHANGE: /* tx/rx rates */ netif_dbg(dev, timer, dev->net, "CDC: speed change (len %d)\n", From c146f3d191147a12d6c9ac61c4e48ac2dc53edc0 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 8 Aug 2024 09:16:48 +0200 Subject: [PATCH 016/385] net: fs_enet: Fix warning due to wrong type Building fs_enet on powerpc e500 leads to following warning: CC drivers/net/ethernet/freescale/fs_enet/mac-scc.o In file included from ./include/linux/build_bug.h:5, from ./include/linux/container_of.h:5, from ./include/linux/list.h:5, from ./include/linux/module.h:12, from drivers/net/ethernet/freescale/fs_enet/mac-scc.c:15: drivers/net/ethernet/freescale/fs_enet/mac-scc.c: In function 'allocate_bd': ./include/linux/err.h:28:49: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] 28 | #define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO) | ^ ./include/linux/compiler.h:77:45: note: in definition of macro 'unlikely' 77 | # define unlikely(x) __builtin_expect(!!(x), 0) | ^ drivers/net/ethernet/freescale/fs_enet/mac-scc.c:138:13: note: in expansion of macro 'IS_ERR_VALUE' 138 | if (IS_ERR_VALUE(fep->ring_mem_addr)) | ^~~~~~~~~~~~ This is due to fep->ring_mem_addr not being a pointer but a DMA address which is 64 bits on that platform while pointers are 32 bits as this is a 32 bits platform with wider physical bus. However, using fep->ring_mem_addr is just wrong because cpm_muram_alloc() returns an offset within the muram and not a physical address directly. So use fpi->dpram_offset instead. Signed-off-by: Christophe Leroy Reviewed-by: Simon Horman Link: https://patch.msgid.link/ec67ea3a3bef7e58b8dc959f7c17d405af0d27e4.1723101144.git.christophe.leroy@csgroup.eu Signed-off-by: Jakub Kicinski --- .../net/ethernet/freescale/fs_enet/mac-scc.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c index a64cb6270515a..9e89ac2b6ce3e 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c @@ -131,15 +131,14 @@ static int setup_data(struct net_device *dev) static int allocate_bd(struct net_device *dev) { struct fs_enet_private *fep = netdev_priv(dev); - const struct fs_platform_info *fpi = fep->fpi; + struct fs_platform_info *fpi = fep->fpi; - fep->ring_mem_addr = cpm_muram_alloc((fpi->tx_ring + fpi->rx_ring) * - sizeof(cbd_t), 8); - if (IS_ERR_VALUE(fep->ring_mem_addr)) + fpi->dpram_offset = cpm_muram_alloc((fpi->tx_ring + fpi->rx_ring) * + sizeof(cbd_t), 8); + if (IS_ERR_VALUE(fpi->dpram_offset)) return -ENOMEM; - fep->ring_base = (void __iomem __force*) - cpm_muram_addr(fep->ring_mem_addr); + fep->ring_base = cpm_muram_addr(fpi->dpram_offset); return 0; } @@ -147,9 +146,10 @@ static int allocate_bd(struct net_device *dev) static void free_bd(struct net_device *dev) { struct fs_enet_private *fep = netdev_priv(dev); + const struct fs_platform_info *fpi = fep->fpi; if (fep->ring_base) - cpm_muram_free(fep->ring_mem_addr); + cpm_muram_free(fpi->dpram_offset); } static void cleanup_data(struct net_device *dev) @@ -247,9 +247,9 @@ static void restart(struct net_device *dev) __fs_out8((u8 __iomem *)ep + i, 0); /* point to bds */ - W16(ep, sen_genscc.scc_rbase, fep->ring_mem_addr); + W16(ep, sen_genscc.scc_rbase, fpi->dpram_offset); W16(ep, sen_genscc.scc_tbase, - fep->ring_mem_addr + sizeof(cbd_t) * fpi->rx_ring); + fpi->dpram_offset + sizeof(cbd_t) * fpi->rx_ring); /* Initialize function code registers for big-endian. */ From dda10fc801a9d81829e624ef75ecdfc94f39b310 Mon Sep 17 00:00:00 2001 From: Nick Child Date: Wed, 7 Aug 2024 16:18:03 -0500 Subject: [PATCH 017/385] ibmvnic: Only replenish rx pool when resources are getting low Previously, the driver would replenish the rx pool if the polling function consumed less than the budget. The logic being that the driver did not exhaust its budget so that must mean that the driver is not busy and has cycles to spare for replenishing the pool. So pool replenishment happens on every poll which did not consume the budget. This can very costly during request-response tests. In fact, an extra ~100pps can be seen in TCP_RR_150 tests when we remove this conditional. Trace results (ftrace, graph-time=1) for the poll function are below: Previous results: ibmvnic_poll = 64951846.0 us / 4167628.0 hits = AVG 15.58 replenish_rx_pool = 17602846.0 us / 4710437.0 hits = AVG 3.74 Now: ibmvnic_poll = 57673941.0 us / 4791737.0 hits = AVG 12.04 replenish_rx_pool = 3938171.6 us / 4314.0 hits = AVG 912.88 While the replenish function takes longer, it is hit less frequently meaning the ibmvnic_poll function, on average, is faster. Furthermore, this change does not have a negative effect on performance bandwidth/latency measurements. Signed-off-by: Nick Child Link: https://patch.msgid.link/20240807211809.1259563-2-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 23ebeb143987f..857d585bd2297 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3527,9 +3527,8 @@ static int ibmvnic_poll(struct napi_struct *napi, int budget) } if (adapter->state != VNIC_CLOSING && - ((atomic_read(&adapter->rx_pool[scrq_num].available) < - adapter->req_rx_add_entries_per_subcrq / 2) || - frames_processed < budget)) + (atomic_read(&adapter->rx_pool[scrq_num].available) < + adapter->req_rx_add_entries_per_subcrq / 2)) replenish_rx_pool(adapter, &adapter->rx_pool[scrq_num]); if (frames_processed < budget) { if (napi_complete_done(napi, frames_processed)) { From b41b45ecee6ba74bd590b113be9f349c6b818b46 Mon Sep 17 00:00:00 2001 From: Nick Child Date: Wed, 7 Aug 2024 16:18:04 -0500 Subject: [PATCH 018/385] ibmvnic: Use header len helper functions on tx Use the header length helper functions rather than trying to calculate it within the driver. There are defined functions for mac and network headers (skb_mac_header_len and skb_network_header_len) but no such function exists for the transport header length. Also, hdr_data was memset during allocation to all 0's so no need to memset again. Signed-off-by: Nick Child Link: https://patch.msgid.link/20240807211809.1259563-3-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 857d585bd2297..7d552d4bbe15f 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2156,36 +2156,28 @@ static int build_hdr_data(u8 hdr_field, struct sk_buff *skb, int len = 0; u8 *hdr; - if (skb_vlan_tagged(skb) && !skb_vlan_tag_present(skb)) - hdr_len[0] = sizeof(struct vlan_ethhdr); - else - hdr_len[0] = sizeof(struct ethhdr); if (skb->protocol == htons(ETH_P_IP)) { - hdr_len[1] = ip_hdr(skb)->ihl * 4; if (ip_hdr(skb)->protocol == IPPROTO_TCP) hdr_len[2] = tcp_hdrlen(skb); else if (ip_hdr(skb)->protocol == IPPROTO_UDP) hdr_len[2] = sizeof(struct udphdr); } else if (skb->protocol == htons(ETH_P_IPV6)) { - hdr_len[1] = sizeof(struct ipv6hdr); if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP) hdr_len[2] = tcp_hdrlen(skb); else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP) hdr_len[2] = sizeof(struct udphdr); - } else if (skb->protocol == htons(ETH_P_ARP)) { - hdr_len[1] = arp_hdr_len(skb->dev); - hdr_len[2] = 0; } - memset(hdr_data, 0, 120); if ((hdr_field >> 6) & 1) { + hdr_len[0] = skb_mac_header_len(skb); hdr = skb_mac_header(skb); memcpy(hdr_data, hdr, hdr_len[0]); len += hdr_len[0]; } if ((hdr_field >> 5) & 1) { + hdr_len[1] = skb_network_header_len(skb); hdr = skb_network_header(skb); memcpy(hdr_data + len, hdr, hdr_len[1]); len += hdr_len[1]; @@ -2196,6 +2188,7 @@ static int build_hdr_data(u8 hdr_field, struct sk_buff *skb, memcpy(hdr_data + len, hdr, hdr_len[2]); len += hdr_len[2]; } + return len; } From d95f749a0b5e42a30d7025d19c15a11c1a570e72 Mon Sep 17 00:00:00 2001 From: Nick Child Date: Wed, 7 Aug 2024 16:18:05 -0500 Subject: [PATCH 019/385] ibmvnic: Reduce memcpys in tx descriptor generation Previously when creating the header descriptors, the driver would: 1. allocate a temporary buffer on the stack (in build_hdr_descs_arr) 2. memcpy the header info into the temporary buffer (in build_hdr_data) 3. memcpy the temp buffer into a local variable (in create_hdr_descs) 4. copy the local variable into the return buffer (in create_hdr_descs) Since, there is no opportunity for errors during this process, the temp buffer is not needed and work can be done on the return buffer directly. Repurpose build_hdr_data() to only calculate the header lengths. Rename it to get_hdr_lens(). Edit create_hdr_descs() to read from the skb directly and copy directly into the returned useful buffer. The process now involves less memory and write operations while also being more readable. Signed-off-by: Nick Child Link: https://patch.msgid.link/20240807211809.1259563-4-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 89 ++++++++++++++---------------- 1 file changed, 40 insertions(+), 49 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 7d552d4bbe15f..58a517ecbda39 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2140,56 +2140,49 @@ static int ibmvnic_close(struct net_device *netdev) } /** - * build_hdr_data - creates L2/L3/L4 header data buffer + * get_hdr_lens - fills list of L2/L3/L4 hdr lens * @hdr_field: bitfield determining needed headers * @skb: socket buffer - * @hdr_len: array of header lengths - * @hdr_data: buffer to write the header to + * @hdr_len: array of header lengths to be filled * * Reads hdr_field to determine which headers are needed by firmware. * Builds a buffer containing these headers. Saves individual header * lengths and total buffer length to be used to build descriptors. + * + * Return: total len of all headers */ -static int build_hdr_data(u8 hdr_field, struct sk_buff *skb, - int *hdr_len, u8 *hdr_data) +static int get_hdr_lens(u8 hdr_field, struct sk_buff *skb, + int *hdr_len) { int len = 0; - u8 *hdr; - - if (skb->protocol == htons(ETH_P_IP)) { - if (ip_hdr(skb)->protocol == IPPROTO_TCP) - hdr_len[2] = tcp_hdrlen(skb); - else if (ip_hdr(skb)->protocol == IPPROTO_UDP) - hdr_len[2] = sizeof(struct udphdr); - } else if (skb->protocol == htons(ETH_P_IPV6)) { - if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP) - hdr_len[2] = tcp_hdrlen(skb); - else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP) - hdr_len[2] = sizeof(struct udphdr); - } if ((hdr_field >> 6) & 1) { hdr_len[0] = skb_mac_header_len(skb); - hdr = skb_mac_header(skb); - memcpy(hdr_data, hdr, hdr_len[0]); len += hdr_len[0]; } if ((hdr_field >> 5) & 1) { hdr_len[1] = skb_network_header_len(skb); - hdr = skb_network_header(skb); - memcpy(hdr_data + len, hdr, hdr_len[1]); len += hdr_len[1]; } - if ((hdr_field >> 4) & 1) { - hdr = skb_transport_header(skb); - memcpy(hdr_data + len, hdr, hdr_len[2]); - len += hdr_len[2]; + if (!((hdr_field >> 4) & 1)) + return len; + + if (skb->protocol == htons(ETH_P_IP)) { + if (ip_hdr(skb)->protocol == IPPROTO_TCP) + hdr_len[2] = tcp_hdrlen(skb); + else if (ip_hdr(skb)->protocol == IPPROTO_UDP) + hdr_len[2] = sizeof(struct udphdr); + } else if (skb->protocol == htons(ETH_P_IPV6)) { + if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP) + hdr_len[2] = tcp_hdrlen(skb); + else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP) + hdr_len[2] = sizeof(struct udphdr); } - return len; + return len + hdr_len[2]; } /** @@ -2202,12 +2195,14 @@ static int build_hdr_data(u8 hdr_field, struct sk_buff *skb, * * Creates header and, if needed, header extension descriptors and * places them in a descriptor array, scrq_arr + * + * Return: Number of header descs */ static int create_hdr_descs(u8 hdr_field, u8 *hdr_data, int len, int *hdr_len, union sub_crq *scrq_arr) { - union sub_crq hdr_desc; + union sub_crq *hdr_desc; int tmp_len = len; int num_descs = 0; u8 *data, *cur; @@ -2216,28 +2211,26 @@ static int create_hdr_descs(u8 hdr_field, u8 *hdr_data, int len, int *hdr_len, while (tmp_len > 0) { cur = hdr_data + len - tmp_len; - memset(&hdr_desc, 0, sizeof(hdr_desc)); - if (cur != hdr_data) { - data = hdr_desc.hdr_ext.data; + hdr_desc = &scrq_arr[num_descs]; + if (num_descs) { + data = hdr_desc->hdr_ext.data; tmp = tmp_len > 29 ? 29 : tmp_len; - hdr_desc.hdr_ext.first = IBMVNIC_CRQ_CMD; - hdr_desc.hdr_ext.type = IBMVNIC_HDR_EXT_DESC; - hdr_desc.hdr_ext.len = tmp; + hdr_desc->hdr_ext.first = IBMVNIC_CRQ_CMD; + hdr_desc->hdr_ext.type = IBMVNIC_HDR_EXT_DESC; + hdr_desc->hdr_ext.len = tmp; } else { - data = hdr_desc.hdr.data; + data = hdr_desc->hdr.data; tmp = tmp_len > 24 ? 24 : tmp_len; - hdr_desc.hdr.first = IBMVNIC_CRQ_CMD; - hdr_desc.hdr.type = IBMVNIC_HDR_DESC; - hdr_desc.hdr.len = tmp; - hdr_desc.hdr.l2_len = (u8)hdr_len[0]; - hdr_desc.hdr.l3_len = cpu_to_be16((u16)hdr_len[1]); - hdr_desc.hdr.l4_len = (u8)hdr_len[2]; - hdr_desc.hdr.flag = hdr_field << 1; + hdr_desc->hdr.first = IBMVNIC_CRQ_CMD; + hdr_desc->hdr.type = IBMVNIC_HDR_DESC; + hdr_desc->hdr.len = tmp; + hdr_desc->hdr.l2_len = (u8)hdr_len[0]; + hdr_desc->hdr.l3_len = cpu_to_be16((u16)hdr_len[1]); + hdr_desc->hdr.l4_len = (u8)hdr_len[2]; + hdr_desc->hdr.flag = hdr_field << 1; } memcpy(data, cur, tmp); tmp_len -= tmp; - *scrq_arr = hdr_desc; - scrq_arr++; num_descs++; } @@ -2260,13 +2253,11 @@ static void build_hdr_descs_arr(struct sk_buff *skb, int *num_entries, u8 hdr_field) { int hdr_len[3] = {0, 0, 0}; - u8 hdr_data[140] = {0}; int tot_len; - tot_len = build_hdr_data(hdr_field, skb, hdr_len, - hdr_data); - *num_entries += create_hdr_descs(hdr_field, hdr_data, tot_len, hdr_len, - indir_arr + 1); + tot_len = get_hdr_lens(hdr_field, skb, hdr_len); + *num_entries += create_hdr_descs(hdr_field, skb_mac_header(skb), + tot_len, hdr_len, indir_arr + 1); } static int ibmvnic_xmit_workarounds(struct sk_buff *skb, From 6e7a57581abea5335cbf29d738724d25d3c302d7 Mon Sep 17 00:00:00 2001 From: Nick Child Date: Wed, 7 Aug 2024 16:18:06 -0500 Subject: [PATCH 020/385] ibmvnic: Remove duplicate memory barriers in tx send_subcrq_[in]direct() already has a dma memory barrier. Remove the earlier one. Signed-off-by: Nick Child Link: https://patch.msgid.link/20240807211809.1259563-5-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 58a517ecbda39..256feac588ef7 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2459,9 +2459,6 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) skb_copy_from_linear_data(skb, dst, skb->len); } - /* post changes to long_term_buff *dst before VIOS accessing it */ - dma_wmb(); - tx_pool->consumer_index = (tx_pool->consumer_index + 1) % tx_pool->num_buffers; From 74839f7a82689bf5a21a5447cae8e3a7b7a606d2 Mon Sep 17 00:00:00 2001 From: Nick Child Date: Wed, 7 Aug 2024 16:18:07 -0500 Subject: [PATCH 021/385] ibmvnic: Introduce send sub-crq direct Firmware supports two hcalls to send a sub-crq request: H_SEND_SUB_CRQ_INDIRECT and H_SEND_SUB_CRQ. The indirect hcall allows for submission of batched messages while the other hcall is limited to only one message. This protocol is defined in PAPR section 17.2.3.3. Previously, the ibmvnic xmit function only used the indirect hcall. This allowed the driver to batch it's skbs. A single skb can occupy a few entries per hcall depending on if FW requires skb header information or not. The FW only needs header information if the packet is segmented. By this logic, if an skb is not GSO then it can fit in one sub-crq message and therefore is a candidate for H_SEND_SUB_CRQ. Batching skb transmission is only useful when there are more packets coming down the line (ie netdev_xmit_more is true). As it turns out, H_SEND_SUB_CRQ induces less latency than H_SEND_SUB_CRQ_INDIRECT. Therefore, use H_SEND_SUB_CRQ where appropriate. Small latency gains seen when doing TCP_RR_150 (request/response workload). Ftrace results (graph-time=1): Previous: ibmvnic_xmit = 29618270.83 us / 8860058.0 hits = AVG 3.34 ibmvnic_tx_scrq_flush = 21972231.02 us / 6553972.0 hits = AVG 3.35 Now: ibmvnic_xmit = 22153350.96 us / 8438942.0 hits = AVG 2.63 ibmvnic_tx_scrq_flush = 15858922.4 us / 6244076.0 hits = AVG 2.54 Signed-off-by: Nick Child Link: https://patch.msgid.link/20240807211809.1259563-6-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 52 ++++++++++++++++++++++++++---- 1 file changed, 46 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 256feac588ef7..d7262674eab7a 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -117,6 +117,7 @@ static void free_long_term_buff(struct ibmvnic_adapter *adapter, struct ibmvnic_long_term_buff *ltb); static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter); static void flush_reset_queue(struct ibmvnic_adapter *adapter); +static void print_subcrq_error(struct device *dev, int rc, const char *func); struct ibmvnic_stat { char name[ETH_GSTRING_LEN]; @@ -2334,8 +2335,29 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter, } } +static int send_subcrq_direct(struct ibmvnic_adapter *adapter, + u64 remote_handle, u64 *entry) +{ + unsigned int ua = adapter->vdev->unit_address; + struct device *dev = &adapter->vdev->dev; + int rc; + + /* Make sure the hypervisor sees the complete request */ + dma_wmb(); + rc = plpar_hcall_norets(H_SEND_SUB_CRQ, ua, + cpu_to_be64(remote_handle), + cpu_to_be64(entry[0]), cpu_to_be64(entry[1]), + cpu_to_be64(entry[2]), cpu_to_be64(entry[3])); + + if (rc) + print_subcrq_error(dev, rc, __func__); + + return rc; +} + static int ibmvnic_tx_scrq_flush(struct ibmvnic_adapter *adapter, - struct ibmvnic_sub_crq_queue *tx_scrq) + struct ibmvnic_sub_crq_queue *tx_scrq, + bool indirect) { struct ibmvnic_ind_xmit_queue *ind_bufp; u64 dma_addr; @@ -2350,7 +2372,13 @@ static int ibmvnic_tx_scrq_flush(struct ibmvnic_adapter *adapter, if (!entries) return 0; - rc = send_subcrq_indirect(adapter, handle, dma_addr, entries); + + if (indirect) + rc = send_subcrq_indirect(adapter, handle, dma_addr, entries); + else + rc = send_subcrq_direct(adapter, handle, + (u64 *)ind_bufp->indir_arr); + if (rc) ibmvnic_tx_scrq_clean_buffer(adapter, tx_scrq); else @@ -2408,7 +2436,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_dropped++; tx_send_failed++; ret = NETDEV_TX_OK; - lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq); + lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true); if (lpar_rc != H_SUCCESS) goto tx_err; goto out; @@ -2426,7 +2454,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_send_failed++; tx_dropped++; ret = NETDEV_TX_OK; - lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq); + lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true); if (lpar_rc != H_SUCCESS) goto tx_err; goto out; @@ -2521,6 +2549,16 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_crq.v1.flags1 |= IBMVNIC_TX_LSO; tx_crq.v1.mss = cpu_to_be16(skb_shinfo(skb)->gso_size); hdrs += 2; + } else if (!ind_bufp->index && !netdev_xmit_more()) { + ind_bufp->indir_arr[0] = tx_crq; + ind_bufp->index = 1; + tx_buff->num_entries = 1; + netdev_tx_sent_queue(txq, skb->len); + lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, false); + if (lpar_rc != H_SUCCESS) + goto tx_err; + + goto early_exit; } if ((*hdrs >> 7) & 1) @@ -2530,7 +2568,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_buff->num_entries = num_entries; /* flush buffer if current entry can not fit */ if (num_entries + ind_bufp->index > IBMVNIC_MAX_IND_DESCS) { - lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq); + lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true); if (lpar_rc != H_SUCCESS) goto tx_flush_err; } @@ -2538,15 +2576,17 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) indir_arr[0] = tx_crq; memcpy(&ind_bufp->indir_arr[ind_bufp->index], &indir_arr[0], num_entries * sizeof(struct ibmvnic_generic_scrq)); + ind_bufp->index += num_entries; if (__netdev_tx_sent_queue(txq, skb->len, netdev_xmit_more() && ind_bufp->index < IBMVNIC_MAX_IND_DESCS)) { - lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq); + lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true); if (lpar_rc != H_SUCCESS) goto tx_err; } +early_exit: if (atomic_add_return(num_entries, &tx_scrq->used) >= adapter->req_tx_entries_per_subcrq) { netdev_dbg(netdev, "Stopping queue %d\n", queue_num); From 1c33e29245ccb1182876eb57319777456f9e509c Mon Sep 17 00:00:00 2001 From: Nick Child Date: Wed, 7 Aug 2024 16:18:08 -0500 Subject: [PATCH 022/385] ibmvnic: Only record tx completed bytes once per handler Byte Queue Limits depends on dql_completed being called once per tx completion round in order to adjust its algorithm appropriately. The dql->limit value is an approximation of the amount of bytes that the NIC can consume per irq interval. If this approximation is too high then the NIC will become over-saturated. Too low and the NIC will starve. The dql->limit depends on dql->prev-* stats to calculate an optimal value. If dql_completed() is called more than once per irq handler then those prev-* values become unreliable (because they are not an accurate representation of the previous state of the NIC) resulting in a sub-optimal limit value. Therefore, move the call to netdev_tx_completed_queue() to the end of ibmvnic_complete_tx(). When performing 150 sessions of TCP rr (request-response 1 byte packets) workloads, one could observe: PREVIOUSLY: - limit and inflight values hovering around 130 - transaction rate of around 750k pps. NOW: - limit rises and falls in response to inflight (130-900) - transaction rate of around 1M pps (33% improvement) Signed-off-by: Nick Child Link: https://patch.msgid.link/20240807211809.1259563-7-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index d7262674eab7a..b687e5396e110 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -4189,20 +4189,17 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter, struct ibmvnic_sub_crq_queue *scrq) { struct device *dev = &adapter->vdev->dev; + int num_packets = 0, total_bytes = 0; struct ibmvnic_tx_pool *tx_pool; struct ibmvnic_tx_buff *txbuff; struct netdev_queue *txq; union sub_crq *next; - int index; - int i; + int index, i; restart_loop: while (pending_scrq(adapter, scrq)) { unsigned int pool = scrq->pool_index; int num_entries = 0; - int total_bytes = 0; - int num_packets = 0; - next = ibmvnic_next_scrq(adapter, scrq); for (i = 0; i < next->tx_comp.num_comps; i++) { index = be32_to_cpu(next->tx_comp.correlators[i]); @@ -4238,8 +4235,6 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter, /* remove tx_comp scrq*/ next->tx_comp.first = 0; - txq = netdev_get_tx_queue(adapter->netdev, scrq->pool_index); - netdev_tx_completed_queue(txq, num_packets, total_bytes); if (atomic_sub_return(num_entries, &scrq->used) <= (adapter->req_tx_entries_per_subcrq / 2) && @@ -4264,6 +4259,9 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter, goto restart_loop; } + txq = netdev_get_tx_queue(adapter->netdev, scrq->pool_index); + netdev_tx_completed_queue(txq, num_packets, total_bytes); + return 0; } From e633e32b60fd6701bed73599b273a2a03621ea54 Mon Sep 17 00:00:00 2001 From: Nick Child Date: Wed, 7 Aug 2024 16:18:09 -0500 Subject: [PATCH 023/385] ibmvnic: Perform tx CSO during send scrq direct During initialization with the vnic server, a bitstring is communicated to the client regarding header info needed during CSO (See "VNIC Capabilities" in PAPR). Most of the time, to be safe, vnic server requests header info for CSO. When header info is needed, multiple TX descriptors are required per skb; This limits the driver to use send_subcrq_indirect instead of send_subcrq_direct. Previously, the vnic server request for header info was ignored. This allowed the use of send_sub_crq_direct. Transmissions were successful because the bitstring returned by vnic server is broad and over cautionary. It was observed that mlx backing devices could actually transmit and handle CSO packets without the vnic server receiving header info (despite the fact that the bitstring requested it). There was a trust issue: The bitstring was overcautionary. This extra precaution (requesting header info when the backing device may not use it) comes at the cost of performance (using direct vs indirect hcalls has a 30% delta in small packet RR transaction rate). So it has been requested that the vnic server team tries to ensure that the bitstring is more exact. In the meantime, disable CSO when it is possible to use the skb in the send_subcrq_direct path. In other words, calculate the checksum before handing the packet to FW when the packet is not segmented and xmit_more is false. Since the code path is only possible if the skb is non GSO and xmit_more is false, the cost of doing checksum in the send_subcrq_direct path is minimal. Any large segmented skb will have xmit_more set to true more frequently and it is inexpensive to do checksumming on a small skb. The worst-case workload would be a 9000 MTU TCP_RR test with close to MTU sized packets (and TSO off). This allows xmit_more to be false more frequently and open the code path up to use send_subcrq_direct. Observing trace data (graph-time = 1) and packet rate with this workload shows minimal performance degradation: 1. NIC does checksum w headers, safely use send_subcrq_indirect: - Packet rate: 631k txs - Trace data: ibmvnic_xmit = 44344685.87 us / 6234576 hits = AVG 7.11 us skb_checksum_help = 4.07 us / 2 hits = AVG 2.04 us ^ Notice hits, tracing this just for reassurance ibmvnic_tx_scrq_flush = 33040649.69 us / 5638441 hits = AVG 5.86 us send_subcrq_indirect = 37438922.24 us / 6030859 hits = AVG 6.21 us 2. NIC does checksum w/o headers, dangerously use send_subcrq_direct: - Packet rate: 831k txs - Trace data: ibmvnic_xmit = 48940092.29 us / 8187630 hits = AVG 5.98 us skb_checksum_help = 2.03 us / 1 hits = AVG 2.03 ibmvnic_tx_scrq_flush = 31141879.57 us / 7948960 hits = AVG 3.92 us send_subcrq_indirect = 8412506.03 us / 728781 hits = AVG 11.54 ^ notice hits is much lower b/c send_subcrq_direct was called ^ wasn't traceable 3. driver does checksum, safely use send_subcrq_direct (THIS PATCH): - Packet rate: 829k txs - Trace data: ibmvnic_xmit = 56696077.63 us / 8066168 hits = AVG 7.03 us skb_checksum_help = 8587456.16 us / 7526072 hits = AVG 1.14 us ibmvnic_tx_scrq_flush = 30219545.55 us / 7782409 hits = AVG 3.88 us send_subcrq_indirect = 8638326.44 us / 763693 hits = AVG 11.31 us When the bitstring ever specifies that CSO does not require headers (dependent on VIOS vnic server changes), then this patch should be removed and replaced with one that investigates the bitstring before using send_subcrq_direct. Signed-off-by: Nick Child Link: https://patch.msgid.link/20240807211809.1259563-8-nnac123@linux.ibm.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ibm/ibmvnic.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index b687e5396e110..87e693a814331 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2409,6 +2409,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) unsigned long lpar_rc; union sub_crq tx_crq; unsigned int offset; + bool use_scrq_send_direct = false; int num_entries = 1; unsigned char *dst; int bufidx = 0; @@ -2468,6 +2469,18 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) memset(dst, 0, tx_pool->buf_size); data_dma_addr = ltb->addr + offset; + /* if we are going to send_subcrq_direct this then we need to + * update the checksum before copying the data into ltb. Essentially + * these packets force disable CSO so that we can guarantee that + * FW does not need header info and we can send direct. + */ + if (!skb_is_gso(skb) && !ind_bufp->index && !netdev_xmit_more()) { + use_scrq_send_direct = true; + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_help(skb)) + use_scrq_send_direct = false; + } + if (skb_shinfo(skb)->nr_frags) { int cur, i; @@ -2549,11 +2562,13 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_crq.v1.flags1 |= IBMVNIC_TX_LSO; tx_crq.v1.mss = cpu_to_be16(skb_shinfo(skb)->gso_size); hdrs += 2; - } else if (!ind_bufp->index && !netdev_xmit_more()) { - ind_bufp->indir_arr[0] = tx_crq; + } else if (use_scrq_send_direct) { + /* See above comment, CSO disabled with direct xmit */ + tx_crq.v1.flags1 &= ~(IBMVNIC_TX_CHKSUM_OFFLOAD); ind_bufp->index = 1; tx_buff->num_entries = 1; netdev_tx_sent_queue(txq, skb->len); + ind_bufp->indir_arr[0] = tx_crq; lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, false); if (lpar_rc != H_SUCCESS) goto tx_err; From 1862923bf6ae9d023826abf79d9795a06aecb350 Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Wed, 7 Aug 2024 14:58:27 -0700 Subject: [PATCH 024/385] net: ag71xx: use phylink_mii_ioctl f1294617d2f38bd2b9f6cce516b0326858b61182 removed the custom function for ndo_eth_ioctl and used the standard phy_do_ioctl which calls phy_mii_ioctl. However since then, this driver was ported to phylink where it makes more sense to call phylink_mii_ioctl. Bring back custom function that calls phylink_mii_ioctl. Signed-off-by: Rosen Penev Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20240807215834.33980-1-rosenp@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/atheros/ag71xx.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index a38be924cdaa0..2916fdb1970be 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -447,6 +447,13 @@ static void ag71xx_int_disable(struct ag71xx *ag, u32 ints) ag71xx_cb(ag, AG71XX_REG_INT_ENABLE, ints); } +static int ag71xx_do_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd) +{ + struct ag71xx *ag = netdev_priv(ndev); + + return phylink_mii_ioctl(ag->phylink, ifr, cmd); +} + static void ag71xx_get_drvinfo(struct net_device *ndev, struct ethtool_drvinfo *info) { @@ -1799,7 +1806,7 @@ static const struct net_device_ops ag71xx_netdev_ops = { .ndo_open = ag71xx_open, .ndo_stop = ag71xx_stop, .ndo_start_xmit = ag71xx_hard_start_xmit, - .ndo_eth_ioctl = phy_do_ioctl, + .ndo_eth_ioctl = ag71xx_do_ioctl, .ndo_tx_timeout = ag71xx_tx_timeout, .ndo_change_mtu = ag71xx_change_mtu, .ndo_set_mac_address = eth_mac_addr, From 6e20d538fb1dfb9c477a8e991da1fca3064ce0f7 Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Thu, 8 Aug 2024 08:59:17 +0300 Subject: [PATCH 025/385] net/mlx5: E-Switch, Increase max int port number for offload Currently MLX5E_TC_MAX_INT_PORT_NUM is 8. Usually int port has one ingress and one egress rules. But sometimes, a temporary rule can be offloaded as well, eg: recirc_id(0),in_port(br-phy),eth(src=10:70:fd:87:57:c0,dst=33:33:00:00:00:16), eth_type(0x86dd),ipv6(frag=no), packets:2, bytes:180, used:0.060s, actions:enp8s0f0 If one int port device offloads 3 rules, only 2 devices can offload. Other devices will hit the limit and fail to offload. Actually it is insufficient for customers. So increase the number to 32. Signed-off-by: Chris Mi Reviewed-by: Roi Dayan Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240808055927.2059700-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index c24bda56b2b5d..b982e648ea482 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -139,7 +139,7 @@ struct mlx5_rx_tun_attr { #define MLX5E_TC_TABLE_CHAIN_TAG_BITS 16 #define MLX5E_TC_TABLE_CHAIN_TAG_MASK GENMASK(MLX5E_TC_TABLE_CHAIN_TAG_BITS - 1, 0) -#define MLX5E_TC_MAX_INT_PORT_NUM (8) +#define MLX5E_TC_MAX_INT_PORT_NUM (32) #if IS_ENABLED(CONFIG_MLX5_CLS_ACT) From 88c46f6103e232e819b35ca811e96454d70a7138 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Thu, 8 Aug 2024 08:59:18 +0300 Subject: [PATCH 026/385] net/mlx5e: Enable remove flow for hard packet limit In the commit a2a73ea14b1a ("net/mlx5e: Don't listen to remove flows event"), remove_flow_enable event is removed, and the hard limit usually relies on software mechanism added in commit b2f7b01d36a9 ("net/mlx5e: Simulate missing IPsec TX limits hardware functionality"). But the delayed work is rescheduled every one second, which is slow for fast traffic. As a result, traffic can't be blocked even reaches the hard limit, which usually happens when soft and hard limits are very close. In reality it won't happen because soft limit is much lower than hard limit. But, as an optimization for RX to block traffic when reaching hard limit, need to set remove_flow_enable. When remove flow is enabled, IPSEC HARD_LIFETIME ASO syndrome will be set in the metadata defined in the ASO return register if packets reach hard lifetime threshold. And those packets are dropped immediately by the steering table. Signed-off-by: Jianbo Liu Reviewed-by: Leon Romanovsky Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240808055927.2059700-3-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index 797db853de363..53cfa39188cb0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -127,6 +127,7 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn, MLX5_SET(ipsec_aso, aso_ctx, remove_flow_pkt_cnt, attrs->lft.hard_packet_limit); MLX5_SET(ipsec_aso, aso_ctx, hard_lft_arm, 1); + MLX5_SET(ipsec_aso, aso_ctx, remove_flow_enable, 1); } if (attrs->lft.soft_packet_limit != XFRM_INF) { From 16bb8c613379e20d4adabc639ea6aecdaeba2ff1 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Thu, 8 Aug 2024 08:59:19 +0300 Subject: [PATCH 027/385] net/mlx5e: TC, Offload rewrite and mirror on tunnel over ovs internal port To offload the encap rule when the tunnel IP is configured on an openvswitch internal port, driver need to overwrite vport metadata in reg_c0 to the value assigned to the internal port, then forward packets to root table to be processed again by the rules matching on the metadata for such internal port. When such rule is combined with header rewrite and mirror, openvswitch generates the rule like the following, because it resets mirror after packets are modified. in_port(enp8s0f0npf0sf1),.., actions:enp8s0f0npf0sf2,set(tunnel(...)),set(ipv4(...)),vxlan_sys_4789,enp8s0f0npf0sf2 The split_count was introduced before to support rewrite and mirror. Driver splits the rule into two different hardware rules in order to offload it. But it's not enough to offload the above complicated rule because of the limitations, in both driver and firmware. To resolve this issue, the destination array is split again after the destination indexed by split_count. An extra rule is added for the leftover destinations (in the above example, it is enp8s0f0npf0sf2), and is inserted to post_act table. And the extra destination is added in the original rule to forward to post_act table, so the extra mirror is done there. Signed-off-by: Jianbo Liu Reviewed-by: Cosmin Ratiu Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240808055927.2059700-4-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../ethernet/mellanox/mlx5/core/en/tc_priv.h | 1 + .../net/ethernet/mellanox/mlx5/core/en_tc.c | 103 ++++++++++++++++++ .../net/ethernet/mellanox/mlx5/core/en_tc.h | 1 + .../mellanox/mlx5/core/eswitch_offloads.c | 7 ++ 4 files changed, 112 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index 6cc23af66b5be..efb34de4cb7ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -109,6 +109,7 @@ struct mlx5e_tc_flow { struct completion init_done; struct completion del_hw_done; struct mlx5_flow_attr *attr; + struct mlx5_flow_attr *extra_split_attr; struct list_head attrs; u32 chain_mapping; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 30673292e15fe..a28bf05d98f17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1739,11 +1739,102 @@ has_encap_dests(struct mlx5_flow_attr *attr) return false; } +static int +extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) +{ + struct mlx5_esw_flow_attr *esw_attr; + + if (flow->attr != attr || + !list_is_first(&attr->list, &flow->attrs)) + return 0; + + esw_attr = attr->esw_attr; + if (!esw_attr->split_count || + esw_attr->split_count == esw_attr->out_count - 1) + return 0; + + if (esw_attr->dest_int_port && + (esw_attr->dests[esw_attr->split_count].flags & + MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE)) + return esw_attr->split_count + 1; + + return 0; +} + +static int +extra_split_attr_dests(struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, int split_count) +{ + struct mlx5e_post_act *post_act = get_post_action(flow->priv); + struct mlx5e_tc_flow_parse_attr *parse_attr, *parse_attr2; + struct mlx5_esw_flow_attr *esw_attr, *esw_attr2; + struct mlx5e_post_act_handle *handle; + struct mlx5_flow_attr *attr2; + int i, j, err; + + if (IS_ERR(post_act)) + return PTR_ERR(post_act); + + attr2 = mlx5_alloc_flow_attr(mlx5e_get_flow_namespace(flow)); + parse_attr2 = kvzalloc(sizeof(*parse_attr), GFP_KERNEL); + if (!attr2 || !parse_attr2) { + err = -ENOMEM; + goto err_free; + } + attr2->parse_attr = parse_attr2; + + handle = mlx5e_tc_post_act_add(post_act, attr2); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto err_free; + } + + esw_attr = attr->esw_attr; + esw_attr2 = attr2->esw_attr; + esw_attr2->in_rep = esw_attr->in_rep; + + parse_attr = attr->parse_attr; + parse_attr2->filter_dev = parse_attr->filter_dev; + + for (i = split_count, j = 0; i < esw_attr->out_count; i++, j++) + esw_attr2->dests[j] = esw_attr->dests[i]; + + esw_attr2->out_count = j; + attr2->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + + err = mlx5e_tc_post_act_offload(post_act, handle); + if (err) + goto err_post_act_offload; + + err = mlx5e_tc_post_act_set_handle(flow->priv->mdev, handle, + &parse_attr->mod_hdr_acts); + if (err) + goto err_post_act_set_handle; + + esw_attr->out_count = split_count; + attr->extra_split_ft = mlx5e_tc_post_act_get_ft(post_act); + flow->extra_split_attr = attr2; + + attr2->post_act_handle = handle; + + return 0; + +err_post_act_set_handle: + mlx5e_tc_post_act_unoffload(post_act, handle); +err_post_act_offload: + mlx5e_tc_post_act_del(post_act, handle); +err_free: + kvfree(parse_attr2); + kfree(attr2); + return err; +} + static int post_process_attr(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr, struct netlink_ext_ack *extack) { + int extra_split; bool vf_tun; int err = 0; @@ -1757,6 +1848,13 @@ post_process_attr(struct mlx5e_tc_flow *flow, goto err_out; } + extra_split = extra_split_attr_dests_needed(flow, attr); + if (extra_split > 0) { + err = extra_split_attr_dests(flow, attr, extra_split); + if (err) + goto err_out; + } + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { err = mlx5e_tc_attach_mod_hdr(flow->priv, flow, attr); if (err) @@ -1971,6 +2069,11 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5e_tc_act_stats_del_flow(get_act_stats_handle(priv), flow); free_flow_post_acts(flow); + if (flow->extra_split_attr) { + mlx5_free_flow_attr_actions(flow, flow->extra_split_attr); + kvfree(flow->extra_split_attr->parse_attr); + kfree(flow->extra_split_attr); + } mlx5_free_flow_attr_actions(flow, attr); kvfree(attr->esw_attr->rx_tun_attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index b982e648ea482..e1b8cb78369f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -86,6 +86,7 @@ struct mlx5_flow_attr { u32 dest_chain; struct mlx5_flow_table *ft; struct mlx5_flow_table *dest_ft; + struct mlx5_flow_table *extra_split_ft; u8 inner_match_level; u8 outer_match_level; u8 tun_ip_version; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 768199d2255a1..f24f91d213f24 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -613,6 +613,13 @@ esw_setup_dests(struct mlx5_flow_destination *dest, } } + if (attr->extra_split_ft) { + flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; + dest[*i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest[*i].ft = attr->extra_split_ft; + (*i)++; + } + out: return err; } From b11bde56246ee85a67364efa0e181b479543dfef Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Thu, 8 Aug 2024 08:59:20 +0300 Subject: [PATCH 028/385] net/mlx5e: TC, Offload rewrite and mirror to both internal and external dests Firmware has the limitation that it cannot offload a rule with rewrite and mirror to internal and external destinations simultaneously. This patch adds a workaround to this issue. Here the destination array is split again, just like what's done in previous commit, but after the action indexed by split_count - 1. An extra rule is added for the leftover destinations. Such rule can be offloaded, even there are destinations to both internal and external destinations, because the header rewrite is left in the original FTE. Signed-off-by: Jianbo Liu Reviewed-by: Cosmin Ratiu Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240808055927.2059700-5-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index a28bf05d98f17..6b3b1afe83121 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1742,12 +1742,17 @@ has_encap_dests(struct mlx5_flow_attr *attr) static int extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) { + bool int_dest = false, ext_dest = false; struct mlx5_esw_flow_attr *esw_attr; + int i; if (flow->attr != attr || !list_is_first(&attr->list, &flow->attrs)) return 0; + if (flow_flag_test(flow, SLOW)) + return 0; + esw_attr = attr->esw_attr; if (!esw_attr->split_count || esw_attr->split_count == esw_attr->out_count - 1) @@ -1758,6 +1763,18 @@ extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE)) return esw_attr->split_count + 1; + for (i = esw_attr->split_count; i < esw_attr->out_count; i++) { + /* external dest with encap is considered as internal by firmware */ + if (esw_attr->dests[i].vport == MLX5_VPORT_UPLINK && + !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP_VALID)) + ext_dest = true; + else + int_dest = true; + + if (ext_dest && int_dest) + return esw_attr->split_count; + } + return 0; } From 4384bcff035e3699ab97286875d190f3661acc15 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 8 Aug 2024 08:59:21 +0300 Subject: [PATCH 029/385] net/mlx5e: Be consistent with bitmap handling of link modes Use the bitmap operations when accessing the advertised/supported link modes and remove places that access them as arrays of unsigned longs (underlying implementation of the bitmap), this makes the code much more readable and clear. Signed-off-by: Gal Pressman Reviewed-by: Carolina Jubran Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240808055927.2059700-6-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../ethernet/mellanox/mlx5/core/en_ethtool.c | 23 +++++++++---------- 1 file changed, 11 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 36845872ae94e..5fd81253d6b9d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -83,17 +83,15 @@ struct ptys2ethtool_config ptys2ext_ethtool_table[MLX5E_EXT_LINK_MODES_NUMBER]; ({ \ struct ptys2ethtool_config *cfg; \ const unsigned int modes[] = { __VA_ARGS__ }; \ - unsigned int i, bit, idx; \ + unsigned int i; \ cfg = &ptys2##table##_ethtool_table[reg_]; \ bitmap_zero(cfg->supported, \ __ETHTOOL_LINK_MODE_MASK_NBITS); \ bitmap_zero(cfg->advertised, \ __ETHTOOL_LINK_MODE_MASK_NBITS); \ for (i = 0 ; i < ARRAY_SIZE(modes) ; ++i) { \ - bit = modes[i] % 64; \ - idx = modes[i] / 64; \ - __set_bit(bit, &cfg->supported[idx]); \ - __set_bit(bit, &cfg->advertised[idx]); \ + bitmap_set(cfg->supported, modes[i], 1); \ + bitmap_set(cfg->advertised, modes[i], 1); \ } \ }) @@ -1299,7 +1297,8 @@ static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes) u32 i, ptys_modes = 0; for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) { - if (*ptys2legacy_ethtool_table[i].advertised == 0) + if (bitmap_empty(ptys2legacy_ethtool_table[i].advertised, + __ETHTOOL_LINK_MODE_MASK_NBITS)) continue; if (bitmap_intersects(ptys2legacy_ethtool_table[i].advertised, link_modes, @@ -1313,18 +1312,18 @@ static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes) static u32 mlx5e_ethtool2ptys_ext_adver_link(const unsigned long *link_modes) { u32 i, ptys_modes = 0; - unsigned long modes[2]; + __ETHTOOL_DECLARE_LINK_MODE_MASK(modes); for (i = 0; i < MLX5E_EXT_LINK_MODES_NUMBER; ++i) { - if (ptys2ext_ethtool_table[i].advertised[0] == 0 && - ptys2ext_ethtool_table[i].advertised[1] == 0) + if (bitmap_empty(ptys2ext_ethtool_table[i].advertised, + __ETHTOOL_LINK_MODE_MASK_NBITS)) continue; - memset(modes, 0, sizeof(modes)); + bitmap_zero(modes, __ETHTOOL_LINK_MODE_MASK_NBITS); bitmap_and(modes, ptys2ext_ethtool_table[i].advertised, link_modes, __ETHTOOL_LINK_MODE_MASK_NBITS); - if (modes[0] == ptys2ext_ethtool_table[i].advertised[0] && - modes[1] == ptys2ext_ethtool_table[i].advertised[1]) + if (bitmap_equal(modes, ptys2ext_ethtool_table[i].advertised, + __ETHTOOL_LINK_MODE_MASK_NBITS)) ptys_modes |= MLX5E_PROT_MASK(i); } return ptys_modes; From ab666b5287e898fcafc0ad1f2d4506cc3a1bfd23 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 8 Aug 2024 08:59:22 +0300 Subject: [PATCH 030/385] net/mlx5e: Use extack in set ringparams callback In case of errors in set ringparams, reflect it through extack instead of a dmesg print. While at it, make the messages more human friendly and remove two redundant checks that are already validated by the core. Signed-off-by: Gal Pressman Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240808055927.2059700-7-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 3 +- .../ethernet/mellanox/mlx5/core/en_ethtool.c | 28 ++++++------------- .../net/ethernet/mellanox/mlx5/core/en_rep.c | 2 +- .../mellanox/mlx5/core/ipoib/ethtool.c | 2 +- 4 files changed, 13 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 5fd82c67b6ab7..01781b70434cf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -1172,7 +1172,8 @@ void mlx5e_ethtool_get_ringparam(struct mlx5e_priv *priv, struct ethtool_ringparam *param, struct kernel_ethtool_ringparam *kernel_param); int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv, - struct ethtool_ringparam *param); + struct ethtool_ringparam *param, + struct netlink_ext_ack *extack); void mlx5e_ethtool_get_channels(struct mlx5e_priv *priv, struct ethtool_channels *ch); int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 5fd81253d6b9d..51624053722aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -352,35 +352,25 @@ static void mlx5e_get_ringparam(struct net_device *dev, } int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv, - struct ethtool_ringparam *param) + struct ethtool_ringparam *param, + struct netlink_ext_ack *extack) { struct mlx5e_params new_params; u8 log_rq_size; u8 log_sq_size; int err = 0; - if (param->rx_jumbo_pending) { - netdev_info(priv->netdev, "%s: rx_jumbo_pending not supported\n", - __func__); - return -EINVAL; - } - if (param->rx_mini_pending) { - netdev_info(priv->netdev, "%s: rx_mini_pending not supported\n", - __func__); - return -EINVAL; - } - if (param->rx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE)) { - netdev_info(priv->netdev, "%s: rx_pending (%d) < min (%d)\n", - __func__, param->rx_pending, - 1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE); + NL_SET_ERR_MSG_FMT_MOD(extack, "rx (%d) < min (%d)", + param->rx_pending, + 1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE); return -EINVAL; } if (param->tx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)) { - netdev_info(priv->netdev, "%s: tx_pending (%d) < min (%d)\n", - __func__, param->tx_pending, - 1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE); + NL_SET_ERR_MSG_FMT_MOD(extack, "tx (%d) < min (%d)", + param->tx_pending, + 1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE); return -EINVAL; } @@ -416,7 +406,7 @@ static int mlx5e_set_ringparam(struct net_device *dev, { struct mlx5e_priv *priv = netdev_priv(dev); - return mlx5e_ethtool_set_ringparam(priv, param); + return mlx5e_ethtool_set_ringparam(priv, param, extack); } void mlx5e_ethtool_get_channels(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 8790d57dc6dbf..916ba0db29f2f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -360,7 +360,7 @@ mlx5e_rep_set_ringparam(struct net_device *dev, { struct mlx5e_priv *priv = netdev_priv(dev); - return mlx5e_ethtool_set_ringparam(priv, param); + return mlx5e_ethtool_set_ringparam(priv, param, extack); } static void mlx5e_rep_get_channels(struct net_device *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index 26f8a11b89068..424ff39db28d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -74,7 +74,7 @@ static int mlx5i_set_ringparam(struct net_device *dev, { struct mlx5e_priv *priv = mlx5i_epriv(dev); - return mlx5e_ethtool_set_ringparam(priv, param); + return mlx5e_ethtool_set_ringparam(priv, param, extack); } static void mlx5i_get_ringparam(struct net_device *dev, From 29a943d71d231e2df81fd3834e75264904a77535 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 8 Aug 2024 08:59:23 +0300 Subject: [PATCH 031/385] net/mlx5e: Use extack in get coalesce callback In case of errors in get coalesce, reflect it through extack instead of a dmesg print. Signed-off-by: Gal Pressman Reviewed-by: Cosmin Ratiu Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240808055927.2059700-8-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 9 ++++++--- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c | 2 +- 4 files changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 01781b70434cf..7832f6b6c8a82 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -1180,7 +1180,8 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, struct ethtool_channels *ch); int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal, - struct kernel_ethtool_coalesce *kernel_coal); + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack); int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal, struct kernel_ethtool_coalesce *kernel_coal, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 51624053722aa..9760215926db5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -545,12 +545,15 @@ static int mlx5e_set_channels(struct net_device *dev, int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal, - struct kernel_ethtool_coalesce *kernel_coal) + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct dim_cq_moder *rx_moder, *tx_moder; - if (!MLX5_CAP_GEN(priv->mdev, cq_moderation)) + if (!MLX5_CAP_GEN(priv->mdev, cq_moderation)) { + NL_SET_ERR_MSG_MOD(extack, "CQ moderation not supported"); return -EOPNOTSUPP; + } rx_moder = &priv->channels.params.rx_cq_moderation; coal->rx_coalesce_usecs = rx_moder->usec; @@ -574,7 +577,7 @@ static int mlx5e_get_coalesce(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); - return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal); + return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal, extack); } static int mlx5e_ethtool_get_per_queue_coalesce(struct mlx5e_priv *priv, u32 queue, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 916ba0db29f2f..b885042eef142 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -386,7 +386,7 @@ static int mlx5e_rep_get_coalesce(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); - return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal); + return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal, extack); } static int mlx5e_rep_set_coalesce(struct net_device *netdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index 424ff39db28d0..9772327d51246 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -132,7 +132,7 @@ static int mlx5i_get_coalesce(struct net_device *netdev, { struct mlx5e_priv *priv = mlx5i_epriv(netdev); - return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal); + return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal, extack); } static int mlx5i_get_ts_info(struct net_device *netdev, From 9c4298b466b19651203c8c8847fcbfe3e37ef6b7 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 8 Aug 2024 08:59:24 +0300 Subject: [PATCH 032/385] net/mlx5e: Use extack in set coalesce callback In case of errors in set coalesce, reflect it through extack instead of a dmesg print. While at it, make the messages more human friendly. Signed-off-by: Gal Pressman Reviewed-by: Cosmin Ratiu Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240808055927.2059700-9-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../ethernet/mellanox/mlx5/core/en_ethtool.c | 20 +++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 9760215926db5..c14a5542ae9c9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -699,26 +699,34 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, int err = 0; if (!MLX5_CAP_GEN(mdev, cq_moderation) || - !MLX5_CAP_GEN(mdev, cq_period_mode_modify)) + !MLX5_CAP_GEN(mdev, cq_period_mode_modify)) { + NL_SET_ERR_MSG_MOD(extack, "CQ moderation not supported"); return -EOPNOTSUPP; + } if (coal->tx_coalesce_usecs > MLX5E_MAX_COAL_TIME || coal->rx_coalesce_usecs > MLX5E_MAX_COAL_TIME) { - netdev_info(priv->netdev, "%s: maximum coalesce time supported is %lu usecs\n", - __func__, MLX5E_MAX_COAL_TIME); + NL_SET_ERR_MSG_FMT_MOD( + extack, + "Max coalesce time %lu usecs, tx-usecs (%u) rx-usecs (%u)", + MLX5E_MAX_COAL_TIME, coal->tx_coalesce_usecs, + coal->rx_coalesce_usecs); return -ERANGE; } if (coal->tx_max_coalesced_frames > MLX5E_MAX_COAL_FRAMES || coal->rx_max_coalesced_frames > MLX5E_MAX_COAL_FRAMES) { - netdev_info(priv->netdev, "%s: maximum coalesced frames supported is %lu\n", - __func__, MLX5E_MAX_COAL_FRAMES); + NL_SET_ERR_MSG_FMT_MOD( + extack, + "Max coalesce frames %lu, tx-frames (%u) rx-frames (%u)", + MLX5E_MAX_COAL_FRAMES, coal->tx_max_coalesced_frames, + coal->rx_max_coalesced_frames); return -ERANGE; } if ((kernel_coal->use_cqe_mode_rx || kernel_coal->use_cqe_mode_tx) && !MLX5_CAP_GEN(priv->mdev, cq_period_start_from_cqe)) { - NL_SET_ERR_MSG_MOD(extack, "cqe_mode_rx/tx is not supported on this device"); + NL_SET_ERR_MSG_MOD(extack, "cqe-mode-rx/tx is not supported on this device"); return -EOPNOTSUPP; } From b5100b72da688282558b28255c03a2d72241a729 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 8 Aug 2024 08:59:25 +0300 Subject: [PATCH 033/385] net/mlx5e: Use extack in get module eeprom by page callback In case of errors in get module eeprom by page, reflect it through extack instead of a dmesg print. While at it, make the messages more human friendly. Signed-off-by: Gal Pressman Reviewed-by: Cosmin Ratiu Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240808055927.2059700-10-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index c14a5542ae9c9..56bdb4d07b7ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -2015,8 +2015,10 @@ static int mlx5e_get_module_eeprom_by_page(struct net_device *netdev, if (size_read == -EINVAL) return -EINVAL; if (size_read < 0) { - netdev_err(priv->netdev, "%s: mlx5_query_module_eeprom_by_page failed:0x%x\n", - __func__, size_read); + NL_SET_ERR_MSG_FMT_MOD( + extack, + "Query module eeprom by page failed, read %u bytes, err %d\n", + i, size_read); return i; } From 486aeb2db55b4509039f2e6017b2d06836893ee2 Mon Sep 17 00:00:00 2001 From: Cosmin Ratiu Date: Thu, 8 Aug 2024 08:59:26 +0300 Subject: [PATCH 034/385] net/mlx5e: CT: 'update' rules instead of 'replace' Offloaded rules can be updated with a new modify header action containing a changed restore cookie. This was done using the verb 'replace', while in some configurations 'update' is a better fit. This commit renames the functions used to reflect that. Signed-off-by: Cosmin Ratiu Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240808055927.2059700-11-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../ethernet/mellanox/mlx5/core/en/tc_ct.c | 34 +++++++++---------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 71a168746ebe2..ccee07d6ba1de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -876,10 +876,10 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, } static int -mlx5_tc_ct_entry_replace_rule(struct mlx5_tc_ct_priv *ct_priv, - struct flow_rule *flow_rule, - struct mlx5_ct_entry *entry, - bool nat, u8 zone_restore_id) +mlx5_tc_ct_entry_update_rule(struct mlx5_tc_ct_priv *ct_priv, + struct flow_rule *flow_rule, + struct mlx5_ct_entry *entry, + bool nat, u8 zone_restore_id) { struct mlx5_ct_zone_rule *zone_rule = &entry->zone_rules[nat]; struct mlx5_flow_attr *attr = zone_rule->attr, *old_attr; @@ -924,7 +924,7 @@ mlx5_tc_ct_entry_replace_rule(struct mlx5_tc_ct_priv *ct_priv, kfree(old_attr); kvfree(spec); - ct_dbg("Replaced ct entry rule in zone %d", entry->tuple.zone); + ct_dbg("Updated ct entry rule in zone %d", entry->tuple.zone); return 0; @@ -1141,23 +1141,23 @@ mlx5_tc_ct_entry_add_rules(struct mlx5_tc_ct_priv *ct_priv, } static int -mlx5_tc_ct_entry_replace_rules(struct mlx5_tc_ct_priv *ct_priv, - struct flow_rule *flow_rule, - struct mlx5_ct_entry *entry, - u8 zone_restore_id) +mlx5_tc_ct_entry_update_rules(struct mlx5_tc_ct_priv *ct_priv, + struct flow_rule *flow_rule, + struct mlx5_ct_entry *entry, + u8 zone_restore_id) { int err = 0; if (mlx5_tc_ct_entry_in_ct_table(entry)) { - err = mlx5_tc_ct_entry_replace_rule(ct_priv, flow_rule, entry, false, - zone_restore_id); + err = mlx5_tc_ct_entry_update_rule(ct_priv, flow_rule, entry, false, + zone_restore_id); if (err) return err; } if (mlx5_tc_ct_entry_in_ct_nat_table(entry)) { - err = mlx5_tc_ct_entry_replace_rule(ct_priv, flow_rule, entry, true, - zone_restore_id); + err = mlx5_tc_ct_entry_update_rule(ct_priv, flow_rule, entry, true, + zone_restore_id); if (err && mlx5_tc_ct_entry_in_ct_table(entry)) mlx5_tc_ct_entry_del_rule(ct_priv, entry, false); } @@ -1165,13 +1165,13 @@ mlx5_tc_ct_entry_replace_rules(struct mlx5_tc_ct_priv *ct_priv, } static int -mlx5_tc_ct_block_flow_offload_replace(struct mlx5_ct_ft *ft, struct flow_rule *flow_rule, - struct mlx5_ct_entry *entry, unsigned long cookie) +mlx5_tc_ct_block_flow_offload_update(struct mlx5_ct_ft *ft, struct flow_rule *flow_rule, + struct mlx5_ct_entry *entry, unsigned long cookie) { struct mlx5_tc_ct_priv *ct_priv = ft->ct_priv; int err; - err = mlx5_tc_ct_entry_replace_rules(ct_priv, flow_rule, entry, ft->zone_restore_id); + err = mlx5_tc_ct_entry_update_rules(ct_priv, flow_rule, entry, ft->zone_restore_id); if (!err) return 0; @@ -1216,7 +1216,7 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft, entry->restore_cookie = meta_action->ct_metadata.cookie; spin_unlock_bh(&ct_priv->ht_lock); - err = mlx5_tc_ct_block_flow_offload_replace(ft, flow_rule, entry, cookie); + err = mlx5_tc_ct_block_flow_offload_update(ft, flow_rule, entry, cookie); mlx5_tc_ct_entry_put(entry); return err; } From 6b5662b75960b38cee4930284c93bd645b8e03ab Mon Sep 17 00:00:00 2001 From: Cosmin Ratiu Date: Thu, 8 Aug 2024 08:59:27 +0300 Subject: [PATCH 035/385] net/mlx5e: CT: Update connection tracking steering entries Previously, replacing a connection tracking steering entry was done by adding a new rule (with the same tag but possibly different mod hdr actions/labels) then removing the old rule. This approach doesn't work in hardware steering because two steering entries with the same tag cannot coexist in a hardware steering table. This commit prepares for that by adding a new ct_rule_update operation on the ct_fs_ops struct which is used instead of add+delete. Implementations for both dmfs (firmware steering) and smfs (software steering) are provided, which simply add the new rule and delete the old one. Signed-off-by: Cosmin Ratiu Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240808055927.2059700-12-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- .../ethernet/mellanox/mlx5/core/en/tc/ct_fs.h | 2 ++ .../mellanox/mlx5/core/en/tc/ct_fs_dmfs.c | 21 +++++++++++++++ .../mellanox/mlx5/core/en/tc/ct_fs_smfs.c | 26 +++++++++++++++++++ .../ethernet/mellanox/mlx5/core/en/tc_ct.c | 12 +++------ 4 files changed, 53 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h index bb6b1a979ba13..62b3f7ff55621 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h @@ -25,6 +25,8 @@ struct mlx5_ct_fs_ops { struct mlx5_flow_attr *attr, struct flow_rule *flow_rule); void (*ct_rule_del)(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule); + int (*ct_rule_update)(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule, + struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr); size_t priv_size; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_dmfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_dmfs.c index ae4f55be48cec..64a82aafaacaf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_dmfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_dmfs.c @@ -65,9 +65,30 @@ mlx5_ct_fs_dmfs_ct_rule_del(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_ru kfree(dmfs_rule); } +static int mlx5_ct_fs_dmfs_ct_rule_update(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule, + struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr) +{ + struct mlx5_ct_fs_dmfs_rule *dmfs_rule = container_of(fs_rule, + struct mlx5_ct_fs_dmfs_rule, + fs_rule); + struct mlx5e_priv *priv = netdev_priv(fs->netdev); + struct mlx5_flow_handle *rule; + + rule = mlx5_tc_rule_insert(priv, spec, attr); + if (IS_ERR(rule)) + return PTR_ERR(rule); + mlx5_tc_rule_delete(priv, dmfs_rule->rule, dmfs_rule->attr); + + dmfs_rule->rule = rule; + dmfs_rule->attr = attr; + + return 0; +} + static struct mlx5_ct_fs_ops dmfs_ops = { .ct_rule_add = mlx5_ct_fs_dmfs_ct_rule_add, .ct_rule_del = mlx5_ct_fs_dmfs_ct_rule_del, + .ct_rule_update = mlx5_ct_fs_dmfs_ct_rule_update, .init = mlx5_ct_fs_dmfs_init, .destroy = mlx5_ct_fs_dmfs_destroy, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c index 8c531f4ec9129..1c062a2e8996e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c @@ -368,9 +368,35 @@ mlx5_ct_fs_smfs_ct_rule_del(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_ru kfree(smfs_rule); } +static int mlx5_ct_fs_smfs_ct_rule_update(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule, + struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr) +{ + struct mlx5_ct_fs_smfs_rule *smfs_rule = container_of(fs_rule, + struct mlx5_ct_fs_smfs_rule, + fs_rule); + struct mlx5_ct_fs_smfs *fs_smfs = mlx5_ct_fs_priv(fs); + struct mlx5dr_action *actions[3]; /* We only need to create 3 actions, see below. */ + struct mlx5dr_rule *rule; + + actions[0] = smfs_rule->count_action; + actions[1] = attr->modify_hdr->action.dr_action; + actions[2] = fs_smfs->fwd_action; + + rule = mlx5_smfs_rule_create(smfs_rule->smfs_matcher->dr_matcher, spec, + ARRAY_SIZE(actions), actions, spec->flow_context.flow_source); + if (!rule) + return -EINVAL; + + mlx5_smfs_rule_destroy(smfs_rule->rule); + smfs_rule->rule = rule; + + return 0; +} + static struct mlx5_ct_fs_ops fs_smfs_ops = { .ct_rule_add = mlx5_ct_fs_smfs_ct_rule_add, .ct_rule_del = mlx5_ct_fs_smfs_ct_rule_del, + .ct_rule_update = mlx5_ct_fs_smfs_ct_rule_update, .init = mlx5_ct_fs_smfs_init, .destroy = mlx5_ct_fs_smfs_destroy, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index ccee07d6ba1de..dcfccaaa8d917 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -884,7 +884,6 @@ mlx5_tc_ct_entry_update_rule(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_zone_rule *zone_rule = &entry->zone_rules[nat]; struct mlx5_flow_attr *attr = zone_rule->attr, *old_attr; struct mlx5e_mod_hdr_handle *mh; - struct mlx5_ct_fs_rule *rule; struct mlx5_flow_spec *spec; int err; @@ -902,22 +901,19 @@ mlx5_tc_ct_entry_update_rule(struct mlx5_tc_ct_priv *ct_priv, err = mlx5_tc_ct_entry_create_mod_hdr(ct_priv, attr, flow_rule, &mh, zone_restore_id, nat, mlx5_tc_ct_entry_in_ct_nat_table(entry)); if (err) { - ct_dbg("Failed to create ct entry mod hdr"); + ct_dbg("Failed to create ct entry mod hdr, err: %d", err); goto err_mod_hdr; } mlx5_tc_ct_set_tuple_match(ct_priv, spec, flow_rule); mlx5e_tc_match_to_reg_match(spec, ZONE_TO_REG, entry->tuple.zone, MLX5_CT_ZONE_MASK); - rule = ct_priv->fs_ops->ct_rule_add(ct_priv->fs, spec, attr, flow_rule); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - ct_dbg("Failed to add replacement ct entry rule, nat: %d", nat); + err = ct_priv->fs_ops->ct_rule_update(ct_priv->fs, zone_rule->rule, spec, attr); + if (err) { + ct_dbg("Failed to update ct entry rule, nat: %d, err: %d", nat, err); goto err_rule; } - ct_priv->fs_ops->ct_rule_del(ct_priv->fs, zone_rule->rule); - zone_rule->rule = rule; mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, old_attr, zone_rule->mh); zone_rule->mh = mh; mlx5_put_label_mapping(ct_priv, old_attr->ct_attr.ct_labels_id); From e2b1762cf32fb9be1e662ec1e8f3b8b36a9b293d Mon Sep 17 00:00:00 2001 From: James Chapman Date: Wed, 7 Aug 2024 07:54:44 +0100 Subject: [PATCH 036/385] documentation/networking: update l2tp docs l2tp no longer uses sk_user_data in tunnel sockets and now manages tunnel/session lifetimes slightly differently. Update docs to cover this. CC: linux-doc@vger.kernel.org CC: corbet@lwn.net Signed-off-by: James Chapman Signed-off-by: Tom Parkin Signed-off-by: David S. Miller --- Documentation/networking/l2tp.rst | 54 ++++++++++++------------------- 1 file changed, 20 insertions(+), 34 deletions(-) diff --git a/Documentation/networking/l2tp.rst b/Documentation/networking/l2tp.rst index 8496b467dea49..e8cf8b3e60ac9 100644 --- a/Documentation/networking/l2tp.rst +++ b/Documentation/networking/l2tp.rst @@ -638,9 +638,8 @@ Tunnels are identified by a unique tunnel id. The id is 16-bit for L2TPv2 and 32-bit for L2TPv3. Internally, the id is stored as a 32-bit value. -Tunnels are kept in a per-net list, indexed by tunnel id. The tunnel -id namespace is shared by L2TPv2 and L2TPv3. The tunnel context can be -derived from the socket's sk_user_data. +Tunnels are kept in a per-net list, indexed by tunnel id. The +tunnel id namespace is shared by L2TPv2 and L2TPv3. Handling tunnel socket close is perhaps the most tricky part of the L2TP implementation. If userspace closes a tunnel socket, the L2TP @@ -652,9 +651,7 @@ socket's encap_destroy handler is invoked, which L2TP uses to initiate its tunnel close actions. For L2TPIP sockets, the socket's close handler initiates the same tunnel close actions. All sessions are first closed. Each session drops its tunnel ref. When the tunnel ref -reaches zero, the tunnel puts its socket ref. When the socket is -eventually destroyed, its sk_destruct finally frees the L2TP tunnel -context. +reaches zero, the tunnel drops its socket ref. Sessions -------- @@ -667,10 +664,7 @@ pseudowire) or other data types such as PPP, ATM, HDLC or Frame Relay. Linux currently implements only Ethernet and PPP session types. Some L2TP session types also have a socket (PPP pseudowires) while -others do not (Ethernet pseudowires). We can't therefore use the -socket reference count as the reference count for session -contexts. The L2TP implementation therefore has its own internal -reference counts on the session contexts. +others do not (Ethernet pseudowires). Like tunnels, L2TP sessions are identified by a unique session id. Just as with tunnel ids, the session id is 16-bit for @@ -680,21 +674,19 @@ value. Sessions hold a ref on their parent tunnel to ensure that the tunnel stays extant while one or more sessions references it. -Sessions are kept in a per-tunnel list, indexed by session id. L2TPv3 -sessions are also kept in a per-net list indexed by session id, -because L2TPv3 session ids are unique across all tunnels and L2TPv3 -data packets do not contain a tunnel id in the header. This list is -therefore needed to find the session context associated with a -received data packet when the tunnel context cannot be derived from -the tunnel socket. +Sessions are kept in a per-net list. L2TPv2 sessions and L2TPv3 +sessions are stored in separate lists. L2TPv2 sessions are keyed +by a 32-bit key made up of the 16-bit tunnel ID and 16-bit +session ID. L2TPv3 sessions are keyed by the 32-bit session ID, since +L2TPv3 session ids are unique across all tunnels. Although the L2TPv3 RFC specifies that L2TPv3 session ids are not -scoped by the tunnel, the kernel does not police this for L2TPv3 UDP -tunnels and does not add sessions of L2TPv3 UDP tunnels into the -per-net session list. In the UDP receive code, we must trust that the -tunnel can be identified using the tunnel socket's sk_user_data and -lookup the session in the tunnel's session list instead of the per-net -session list. +scoped by the tunnel, the Linux implementation has historically +allowed this. Such session id collisions are supported using a per-net +hash table keyed by sk and session ID. When looking up L2TPv3 +sessions, the list entry may link to multiple sessions with that +session ID, in which case the session matching the given sk (tunnel) +is used. PPP --- @@ -714,10 +706,9 @@ The L2TP PPP implementation handles the closing of a PPPoL2TP socket by closing its corresponding L2TP session. This is complicated because it must consider racing with netlink session create/destroy requests and pppol2tp_connect trying to reconnect with a session that is in the -process of being closed. Unlike tunnels, PPP sessions do not hold a -ref on their associated socket, so code must be careful to sock_hold -the socket where necessary. For all the details, see commit -3d609342cc04129ff7568e19316ce3d7451a27e8. +process of being closed. PPP sessions hold a ref on their associated +socket in order that the socket remains extants while the session +references it. Ethernet -------- @@ -761,15 +752,10 @@ Limitations The current implementation has a number of limitations: - 1) Multiple UDP sockets with the same 5-tuple address cannot be - used. The kernel's tunnel context is identified using private - data associated with the socket so it is important that each - socket is uniquely identified by its address. - - 2) Interfacing with openvswitch is not yet implemented. It may be + 1) Interfacing with openvswitch is not yet implemented. It may be useful to map OVS Ethernet and VLAN ports into L2TPv3 tunnels. - 3) VLAN pseudowires are implemented using an ``l2tpethN`` interface + 2) VLAN pseudowires are implemented using an ``l2tpethN`` interface configured with a VLAN sub-interface. Since L2TPv3 VLAN pseudowires carry one and only one VLAN, it may be better to use a single netdevice rather than an ``l2tpethN`` and ``l2tpethN``:M From 168464c19e1ab7ddc5fb80d9c9560cfbcce6211d Mon Sep 17 00:00:00 2001 From: James Chapman Date: Wed, 7 Aug 2024 07:54:45 +0100 Subject: [PATCH 037/385] l2tp: remove inline from functions in c sources Update l2tp to remove the inline keyword from several functions in C sources, since this is now discouraged. Signed-off-by: James Chapman Signed-off-by: Tom Parkin Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 6 +++--- net/l2tp/l2tp_ip.c | 2 +- net/l2tp/l2tp_ip6.c | 2 +- net/l2tp/l2tp_ppp.c | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index ce3b316e2327e..70c231fcaa2e0 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -117,12 +117,12 @@ struct l2tp_net { struct hlist_head l2tp_v3_session_htable[16]; }; -static inline u32 l2tp_v2_session_key(u16 tunnel_id, u16 session_id) +static u32 l2tp_v2_session_key(u16 tunnel_id, u16 session_id) { return ((u32)tunnel_id) << 16 | session_id; } -static inline unsigned long l2tp_v3_session_hashkey(struct sock *sk, u32 session_id) +static unsigned long l2tp_v3_session_hashkey(struct sock *sk, u32 session_id) { return ((unsigned long)sk) + session_id; } @@ -135,7 +135,7 @@ static bool l2tp_sk_is_v6(struct sock *sk) } #endif -static inline struct l2tp_net *l2tp_pernet(const struct net *net) +static struct l2tp_net *l2tp_pernet(const struct net *net) { return net_generic(net, l2tp_net_id); } diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index f21dcbf3efd57..9bd29667ae344 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -37,7 +37,7 @@ static DEFINE_RWLOCK(l2tp_ip_lock); static struct hlist_head l2tp_ip_table; static struct hlist_head l2tp_ip_bind_table; -static inline struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk) +static struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk) { return (struct l2tp_ip_sock *)sk; } diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 3b0465f2d60d2..a7b7626ca2c6e 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -43,7 +43,7 @@ static DEFINE_RWLOCK(l2tp_ip6_lock); static struct hlist_head l2tp_ip6_table; static struct hlist_head l2tp_ip6_bind_table; -static inline struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk) +static struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk) { return (struct l2tp_ip6_sock *)sk; } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 9b4273fd518a7..c25dd8e360740 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -149,7 +149,7 @@ static struct sock *pppol2tp_session_get_sock(struct l2tp_session *session) /* Helpers to obtain tunnel/session contexts from sockets. */ -static inline struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk) +static struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk) { struct l2tp_session *session; From ebed6606b95954b94df6229db806978b32f3fa23 Mon Sep 17 00:00:00 2001 From: James Chapman Date: Wed, 7 Aug 2024 07:54:46 +0100 Subject: [PATCH 038/385] l2tp: move l2tp_ip and l2tp_ip6 data to pernet l2tp_ip[6] have always used global socket tables. It is therefore not possible to create l2tpip sockets in different namespaces with the same socket address. To support this, move l2tpip socket tables to pernet data. Signed-off-by: James Chapman Signed-off-by: Tom Parkin Signed-off-by: David S. Miller --- net/l2tp/l2tp_ip.c | 108 +++++++++++++++++++++++++++++++++---------- net/l2tp/l2tp_ip6.c | 110 ++++++++++++++++++++++++++++++++++---------- 2 files changed, 168 insertions(+), 50 deletions(-) diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 9bd29667ae344..f563c8afd8f39 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -22,9 +22,19 @@ #include #include #include +#include +#include #include "l2tp_core.h" +/* per-net private data for this module */ +static unsigned int l2tp_ip_net_id; +struct l2tp_ip_net { + rwlock_t l2tp_ip_lock; + struct hlist_head l2tp_ip_table; + struct hlist_head l2tp_ip_bind_table; +}; + struct l2tp_ip_sock { /* inet_sock has to be the first member of l2tp_ip_sock */ struct inet_sock inet; @@ -33,21 +43,23 @@ struct l2tp_ip_sock { u32 peer_conn_id; }; -static DEFINE_RWLOCK(l2tp_ip_lock); -static struct hlist_head l2tp_ip_table; -static struct hlist_head l2tp_ip_bind_table; - static struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk) { return (struct l2tp_ip_sock *)sk; } +static struct l2tp_ip_net *l2tp_ip_pernet(const struct net *net) +{ + return net_generic(net, l2tp_ip_net_id); +} + static struct sock *__l2tp_ip_bind_lookup(const struct net *net, __be32 laddr, __be32 raddr, int dif, u32 tunnel_id) { + struct l2tp_ip_net *pn = l2tp_ip_pernet(net); struct sock *sk; - sk_for_each_bound(sk, &l2tp_ip_bind_table) { + sk_for_each_bound(sk, &pn->l2tp_ip_bind_table) { const struct l2tp_ip_sock *l2tp = l2tp_ip_sk(sk); const struct inet_sock *inet = inet_sk(sk); int bound_dev_if; @@ -113,6 +125,7 @@ static struct sock *__l2tp_ip_bind_lookup(const struct net *net, __be32 laddr, static int l2tp_ip_recv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); + struct l2tp_ip_net *pn; struct sock *sk; u32 session_id; u32 tunnel_id; @@ -121,6 +134,8 @@ static int l2tp_ip_recv(struct sk_buff *skb) struct l2tp_tunnel *tunnel = NULL; struct iphdr *iph; + pn = l2tp_ip_pernet(net); + if (!pskb_may_pull(skb, 4)) goto discard; @@ -167,15 +182,15 @@ static int l2tp_ip_recv(struct sk_buff *skb) tunnel_id = ntohl(*(__be32 *)&skb->data[4]); iph = (struct iphdr *)skb_network_header(skb); - read_lock_bh(&l2tp_ip_lock); + read_lock_bh(&pn->l2tp_ip_lock); sk = __l2tp_ip_bind_lookup(net, iph->daddr, iph->saddr, inet_iif(skb), tunnel_id); if (!sk) { - read_unlock_bh(&l2tp_ip_lock); + read_unlock_bh(&pn->l2tp_ip_lock); goto discard; } sock_hold(sk); - read_unlock_bh(&l2tp_ip_lock); + read_unlock_bh(&pn->l2tp_ip_lock); if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; @@ -198,21 +213,25 @@ static int l2tp_ip_recv(struct sk_buff *skb) static int l2tp_ip_hash(struct sock *sk) { + struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); + if (sk_unhashed(sk)) { - write_lock_bh(&l2tp_ip_lock); - sk_add_node(sk, &l2tp_ip_table); - write_unlock_bh(&l2tp_ip_lock); + write_lock_bh(&pn->l2tp_ip_lock); + sk_add_node(sk, &pn->l2tp_ip_table); + write_unlock_bh(&pn->l2tp_ip_lock); } return 0; } static void l2tp_ip_unhash(struct sock *sk) { + struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); + if (sk_unhashed(sk)) return; - write_lock_bh(&l2tp_ip_lock); + write_lock_bh(&pn->l2tp_ip_lock); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip_lock); + write_unlock_bh(&pn->l2tp_ip_lock); } static int l2tp_ip_open(struct sock *sk) @@ -226,10 +245,12 @@ static int l2tp_ip_open(struct sock *sk) static void l2tp_ip_close(struct sock *sk, long timeout) { - write_lock_bh(&l2tp_ip_lock); + struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); + + write_lock_bh(&pn->l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip_lock); + write_unlock_bh(&pn->l2tp_ip_lock); sk_common_release(sk); } @@ -253,6 +274,7 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct inet_sock *inet = inet_sk(sk); struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *)uaddr; struct net *net = sock_net(sk); + struct l2tp_ip_net *pn; int ret; int chk_addr_ret; @@ -283,10 +305,11 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ - write_lock_bh(&l2tp_ip_lock); + pn = l2tp_ip_pernet(net); + write_lock_bh(&pn->l2tp_ip_lock); if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, 0, sk->sk_bound_dev_if, addr->l2tp_conn_id)) { - write_unlock_bh(&l2tp_ip_lock); + write_unlock_bh(&pn->l2tp_ip_lock); ret = -EADDRINUSE; goto out; } @@ -294,9 +317,9 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) sk_dst_reset(sk); l2tp_ip_sk(sk)->conn_id = addr->l2tp_conn_id; - sk_add_bind_node(sk, &l2tp_ip_bind_table); + sk_add_bind_node(sk, &pn->l2tp_ip_bind_table); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip_lock); + write_unlock_bh(&pn->l2tp_ip_lock); ret = 0; sock_reset_flag(sk, SOCK_ZAPPED); @@ -310,6 +333,7 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr; + struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); int rc; if (addr_len < sizeof(*lsa)) @@ -332,10 +356,10 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; - write_lock_bh(&l2tp_ip_lock); + write_lock_bh(&pn->l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); - sk_add_bind_node(sk, &l2tp_ip_bind_table); - write_unlock_bh(&l2tp_ip_lock); + sk_add_bind_node(sk, &pn->l2tp_ip_bind_table); + write_unlock_bh(&pn->l2tp_ip_lock); out_sk: release_sock(sk); @@ -640,25 +664,58 @@ static struct net_protocol l2tp_ip_protocol __read_mostly = { .handler = l2tp_ip_recv, }; +static __net_init int l2tp_ip_init_net(struct net *net) +{ + struct l2tp_ip_net *pn = net_generic(net, l2tp_ip_net_id); + + rwlock_init(&pn->l2tp_ip_lock); + INIT_HLIST_HEAD(&pn->l2tp_ip_table); + INIT_HLIST_HEAD(&pn->l2tp_ip_bind_table); + return 0; +} + +static __net_exit void l2tp_ip_exit_net(struct net *net) +{ + struct l2tp_ip_net *pn = l2tp_ip_pernet(net); + + write_lock_bh(&pn->l2tp_ip_lock); + WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip_table) != 0); + WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip_bind_table) != 0); + write_unlock_bh(&pn->l2tp_ip_lock); +} + +static struct pernet_operations l2tp_ip_net_ops = { + .init = l2tp_ip_init_net, + .exit = l2tp_ip_exit_net, + .id = &l2tp_ip_net_id, + .size = sizeof(struct l2tp_ip_net), +}; + static int __init l2tp_ip_init(void) { int err; pr_info("L2TP IP encapsulation support (L2TPv3)\n"); + err = register_pernet_device(&l2tp_ip_net_ops); + if (err) + goto out; + err = proto_register(&l2tp_ip_prot, 1); if (err != 0) - goto out; + goto out1; err = inet_add_protocol(&l2tp_ip_protocol, IPPROTO_L2TP); if (err) - goto out1; + goto out2; inet_register_protosw(&l2tp_ip_protosw); return 0; -out1: +out2: proto_unregister(&l2tp_ip_prot); +out1: + unregister_pernet_device(&l2tp_ip_net_ops); out: return err; } @@ -668,6 +725,7 @@ static void __exit l2tp_ip_exit(void) inet_unregister_protosw(&l2tp_ip_protosw); inet_del_protocol(&l2tp_ip_protocol, IPPROTO_L2TP); proto_unregister(&l2tp_ip_prot); + unregister_pernet_device(&l2tp_ip_net_ops); } module_init(l2tp_ip_init); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index a7b7626ca2c6e..dcec1de2898e9 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -22,6 +22,8 @@ #include #include #include +#include +#include #include #include @@ -29,6 +31,14 @@ #include "l2tp_core.h" +/* per-net private data for this module */ +static unsigned int l2tp_ip6_net_id; +struct l2tp_ip6_net { + rwlock_t l2tp_ip6_lock; + struct hlist_head l2tp_ip6_table; + struct hlist_head l2tp_ip6_bind_table; +}; + struct l2tp_ip6_sock { /* inet_sock has to be the first member of l2tp_ip6_sock */ struct inet_sock inet; @@ -39,23 +49,25 @@ struct l2tp_ip6_sock { struct ipv6_pinfo inet6; }; -static DEFINE_RWLOCK(l2tp_ip6_lock); -static struct hlist_head l2tp_ip6_table; -static struct hlist_head l2tp_ip6_bind_table; - static struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk) { return (struct l2tp_ip6_sock *)sk; } +static struct l2tp_ip6_net *l2tp_ip6_pernet(const struct net *net) +{ + return net_generic(net, l2tp_ip6_net_id); +} + static struct sock *__l2tp_ip6_bind_lookup(const struct net *net, const struct in6_addr *laddr, const struct in6_addr *raddr, int dif, u32 tunnel_id) { + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(net); struct sock *sk; - sk_for_each_bound(sk, &l2tp_ip6_bind_table) { + sk_for_each_bound(sk, &pn->l2tp_ip6_bind_table) { const struct in6_addr *sk_laddr = inet6_rcv_saddr(sk); const struct in6_addr *sk_raddr = &sk->sk_v6_daddr; const struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk); @@ -123,6 +135,7 @@ static struct sock *__l2tp_ip6_bind_lookup(const struct net *net, static int l2tp_ip6_recv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); + struct l2tp_ip6_net *pn; struct sock *sk; u32 session_id; u32 tunnel_id; @@ -131,6 +144,8 @@ static int l2tp_ip6_recv(struct sk_buff *skb) struct l2tp_tunnel *tunnel = NULL; struct ipv6hdr *iph; + pn = l2tp_ip6_pernet(net); + if (!pskb_may_pull(skb, 4)) goto discard; @@ -177,15 +192,15 @@ static int l2tp_ip6_recv(struct sk_buff *skb) tunnel_id = ntohl(*(__be32 *)&skb->data[4]); iph = ipv6_hdr(skb); - read_lock_bh(&l2tp_ip6_lock); + read_lock_bh(&pn->l2tp_ip6_lock); sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, &iph->saddr, inet6_iif(skb), tunnel_id); if (!sk) { - read_unlock_bh(&l2tp_ip6_lock); + read_unlock_bh(&pn->l2tp_ip6_lock); goto discard; } sock_hold(sk); - read_unlock_bh(&l2tp_ip6_lock); + read_unlock_bh(&pn->l2tp_ip6_lock); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; @@ -208,21 +223,25 @@ static int l2tp_ip6_recv(struct sk_buff *skb) static int l2tp_ip6_hash(struct sock *sk) { + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk)); + if (sk_unhashed(sk)) { - write_lock_bh(&l2tp_ip6_lock); - sk_add_node(sk, &l2tp_ip6_table); - write_unlock_bh(&l2tp_ip6_lock); + write_lock_bh(&pn->l2tp_ip6_lock); + sk_add_node(sk, &pn->l2tp_ip6_table); + write_unlock_bh(&pn->l2tp_ip6_lock); } return 0; } static void l2tp_ip6_unhash(struct sock *sk) { + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk)); + if (sk_unhashed(sk)) return; - write_lock_bh(&l2tp_ip6_lock); + write_lock_bh(&pn->l2tp_ip6_lock); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip6_lock); + write_unlock_bh(&pn->l2tp_ip6_lock); } static int l2tp_ip6_open(struct sock *sk) @@ -236,10 +255,12 @@ static int l2tp_ip6_open(struct sock *sk) static void l2tp_ip6_close(struct sock *sk, long timeout) { - write_lock_bh(&l2tp_ip6_lock); + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk)); + + write_lock_bh(&pn->l2tp_ip6_lock); hlist_del_init(&sk->sk_bind_node); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip6_lock); + write_unlock_bh(&pn->l2tp_ip6_lock); sk_common_release(sk); } @@ -265,11 +286,14 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *)uaddr; struct net *net = sock_net(sk); + struct l2tp_ip6_net *pn; __be32 v4addr = 0; int bound_dev_if; int addr_type; int err; + pn = l2tp_ip6_pernet(net); + if (addr->l2tp_family != AF_INET6) return -EINVAL; if (addr_len < sizeof(*addr)) @@ -327,10 +351,10 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) } rcu_read_unlock(); - write_lock_bh(&l2tp_ip6_lock); + write_lock_bh(&pn->l2tp_ip6_lock); if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, NULL, bound_dev_if, addr->l2tp_conn_id)) { - write_unlock_bh(&l2tp_ip6_lock); + write_unlock_bh(&pn->l2tp_ip6_lock); err = -EADDRINUSE; goto out_unlock; } @@ -343,9 +367,9 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id; - sk_add_bind_node(sk, &l2tp_ip6_bind_table); + sk_add_bind_node(sk, &pn->l2tp_ip6_bind_table); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip6_lock); + write_unlock_bh(&pn->l2tp_ip6_lock); sock_reset_flag(sk, SOCK_ZAPPED); release_sock(sk); @@ -367,6 +391,7 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, struct in6_addr *daddr; int addr_type; int rc; + struct l2tp_ip6_net *pn; if (addr_len < sizeof(*lsa)) return -EINVAL; @@ -398,10 +423,11 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, l2tp_ip6_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; - write_lock_bh(&l2tp_ip6_lock); + pn = l2tp_ip6_pernet(sock_net(sk)); + write_lock_bh(&pn->l2tp_ip6_lock); hlist_del_init(&sk->sk_bind_node); - sk_add_bind_node(sk, &l2tp_ip6_bind_table); - write_unlock_bh(&l2tp_ip6_lock); + sk_add_bind_node(sk, &pn->l2tp_ip6_bind_table); + write_unlock_bh(&pn->l2tp_ip6_lock); out_sk: release_sock(sk); @@ -768,25 +794,58 @@ static struct inet6_protocol l2tp_ip6_protocol __read_mostly = { .handler = l2tp_ip6_recv, }; +static __net_init int l2tp_ip6_init_net(struct net *net) +{ + struct l2tp_ip6_net *pn = net_generic(net, l2tp_ip6_net_id); + + rwlock_init(&pn->l2tp_ip6_lock); + INIT_HLIST_HEAD(&pn->l2tp_ip6_table); + INIT_HLIST_HEAD(&pn->l2tp_ip6_bind_table); + return 0; +} + +static __net_exit void l2tp_ip6_exit_net(struct net *net) +{ + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(net); + + write_lock_bh(&pn->l2tp_ip6_lock); + WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip6_table) != 0); + WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip6_bind_table) != 0); + write_unlock_bh(&pn->l2tp_ip6_lock); +} + +static struct pernet_operations l2tp_ip6_net_ops = { + .init = l2tp_ip6_init_net, + .exit = l2tp_ip6_exit_net, + .id = &l2tp_ip6_net_id, + .size = sizeof(struct l2tp_ip6_net), +}; + static int __init l2tp_ip6_init(void) { int err; pr_info("L2TP IP encapsulation support for IPv6 (L2TPv3)\n"); + err = register_pernet_device(&l2tp_ip6_net_ops); + if (err) + goto out; + err = proto_register(&l2tp_ip6_prot, 1); if (err != 0) - goto out; + goto out1; err = inet6_add_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP); if (err) - goto out1; + goto out2; inet6_register_protosw(&l2tp_ip6_protosw); return 0; -out1: +out2: proto_unregister(&l2tp_ip6_prot); +out1: + unregister_pernet_device(&l2tp_ip6_net_ops); out: return err; } @@ -796,6 +855,7 @@ static void __exit l2tp_ip6_exit(void) inet6_unregister_protosw(&l2tp_ip6_protosw); inet6_del_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP); proto_unregister(&l2tp_ip6_prot); + unregister_pernet_device(&l2tp_ip6_net_ops); } module_init(l2tp_ip6_init); From b0a8deda060d51ebe4614ed6e1829d933139ba1a Mon Sep 17 00:00:00 2001 From: James Chapman Date: Wed, 7 Aug 2024 07:54:47 +0100 Subject: [PATCH 039/385] l2tp: handle hash key collisions in l2tp_v3_session_get To handle colliding l2tpv3 session IDs, l2tp_v3_session_get searches a hashed list keyed by ID and sk. Although unlikely, if hash keys collide, it is possible that hash_for_each_possible loops over a session which doesn't have the ID that we are searching for. So check for session ID match when looping over possible hash key matches. Signed-off-by: James Chapman Signed-off-by: Tom Parkin Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 70c231fcaa2e0..3b34e549fb799 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -291,7 +291,8 @@ struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, */ struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); - if (tunnel && tunnel->sock == sk && + if (session->session_id == session_id && + tunnel && tunnel->sock == sk && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; From aa92c1cec92b146fe499fb693688d6d3d6bafad9 Mon Sep 17 00:00:00 2001 From: James Chapman Date: Wed, 7 Aug 2024 07:54:48 +0100 Subject: [PATCH 040/385] l2tp: add tunnel/session get_next helpers l2tp management APIs and procfs/debugfs iterate over l2tp tunnel and session lists. Since these lists are now implemented using IDR, we can use IDR get_next APIs to iterate them. Add tunnel/session get_next functions to do so. The session get_next functions get the next session in a given tunnel and need to account for l2tpv2 and l2tpv3 differences: * l2tpv2 sessions are keyed by tunnel ID / session ID. Iteration for a given tunnel ID, TID, can therefore start with a key given by TID/0 and finish when the next entry's tunnel ID is not TID. This is possible only because the tunnel ID part of the key is the upper 16 bits and the session ID part the lower 16 bits; when idr_next increments the key value, it therefore finds the next sessions of the current tunnel before those of the next tunnel. Entries with session ID 0 are always skipped because they are used internally by pppol2tp. * l2tpv3 sessions are keyed by session ID. Iteration starts at the first IDR entry and skips entries where the tunnel does not match. Iteration must also consider session ID collisions and walk the list of colliding sessions (if any) for one which matches the supplied tunnel. Signed-off-by: James Chapman Signed-off-by: Tom Parkin Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 126 +++++++++++++++++++++++++++++++++++++++++++ net/l2tp/l2tp_core.h | 3 ++ 2 files changed, 129 insertions(+) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 3b34e549fb799..5e36f45e906b9 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -262,6 +262,28 @@ struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth) } EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth); +struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key) +{ + struct l2tp_net *pn = l2tp_pernet(net); + struct l2tp_tunnel *tunnel = NULL; + + rcu_read_lock_bh(); +again: + tunnel = idr_get_next_ul(&pn->l2tp_tunnel_idr, key); + if (tunnel) { + if (refcount_inc_not_zero(&tunnel->ref_count)) { + rcu_read_unlock_bh(); + return tunnel; + } + (*key)++; + goto again; + } + rcu_read_unlock_bh(); + + return NULL; +} +EXPORT_SYMBOL_GPL(l2tp_tunnel_get_next); + struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id) { const struct l2tp_net *pn = l2tp_pernet(net); @@ -352,6 +374,110 @@ struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth) } EXPORT_SYMBOL_GPL(l2tp_session_get_nth); +static struct l2tp_session *l2tp_v2_session_get_next(const struct net *net, + u16 tid, + unsigned long *key) +{ + struct l2tp_net *pn = l2tp_pernet(net); + struct l2tp_session *session = NULL; + + /* Start searching within the range of the tid */ + if (*key == 0) + *key = l2tp_v2_session_key(tid, 0); + + rcu_read_lock_bh(); +again: + session = idr_get_next_ul(&pn->l2tp_v2_session_idr, key); + if (session) { + struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); + + /* ignore sessions with id 0 as they are internal for pppol2tp */ + if (session->session_id == 0) { + (*key)++; + goto again; + } + + if (tunnel && tunnel->tunnel_id == tid && + refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } + + (*key)++; + if (tunnel->tunnel_id == tid) + goto again; + } + rcu_read_unlock_bh(); + + return NULL; +} + +static struct l2tp_session *l2tp_v3_session_get_next(const struct net *net, + u32 tid, struct sock *sk, + unsigned long *key) +{ + struct l2tp_net *pn = l2tp_pernet(net); + struct l2tp_session *session = NULL; + + rcu_read_lock_bh(); +again: + session = idr_get_next_ul(&pn->l2tp_v3_session_idr, key); + if (session && !hash_hashed(&session->hlist)) { + struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); + + if (tunnel && tunnel->tunnel_id == tid && + refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } + + (*key)++; + goto again; + } + + /* If we get here and session is non-NULL, the IDR entry may be one + * where the session_id collides with one in another tunnel. Check + * session_htable for a match. There can only be one session of a given + * ID per tunnel so we can return as soon as a match is found. + */ + if (session && hash_hashed(&session->hlist)) { + unsigned long hkey = l2tp_v3_session_hashkey(sk, session->session_id); + u32 sid = session->session_id; + + hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session, + hlist, hkey) { + struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); + + if (session->session_id == sid && + tunnel && tunnel->tunnel_id == tid && + refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } + } + + /* If no match found, the colliding session ID isn't in our + * tunnel so try the next session ID. + */ + (*key)++; + goto again; + } + + rcu_read_unlock_bh(); + + return NULL; +} + +struct l2tp_session *l2tp_session_get_next(const struct net *net, struct sock *sk, int pver, + u32 tunnel_id, unsigned long *key) +{ + if (pver == L2TP_HDR_VER_2) + return l2tp_v2_session_get_next(net, tunnel_id, key); + else + return l2tp_v3_session_get_next(net, tunnel_id, sk, key); +} +EXPORT_SYMBOL_GPL(l2tp_session_get_next); + /* Lookup a session by interface name. * This is very inefficient but is only used by management interfaces. */ diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index c907687705b98..cc464982a7d97 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -220,12 +220,15 @@ void l2tp_session_dec_refcount(struct l2tp_session *session); */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth); +struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key); struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id); struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id); struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver, u32 tunnel_id, u32 session_id); struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth); +struct l2tp_session *l2tp_session_get_next(const struct net *net, struct sock *sk, int pver, + u32 tunnel_id, unsigned long *key); struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname); From 1f4c3dce9112d23145b4f8bbfd3793a1c4c517ab Mon Sep 17 00:00:00 2001 From: James Chapman Date: Wed, 7 Aug 2024 07:54:49 +0100 Subject: [PATCH 041/385] l2tp: use get_next APIs for management requests and procfs/debugfs l2tp netlink and procfs/debugfs iterate over tunnel and session lists to obtain data. They currently use very inefficient get_nth functions to do so. Replace these with get_next. For netlink, use nl cb->ctx[] for passing state instead of the obsolete cb->args[]. l2tp_tunnel_get_nth and l2tp_session_get_nth are no longer used so they can be removed. Signed-off-by: James Chapman Signed-off-by: Tom Parkin Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 40 ---------------------------------------- net/l2tp/l2tp_core.h | 2 -- net/l2tp/l2tp_debugfs.c | 16 +++++++++------- net/l2tp/l2tp_netlink.c | 34 +++++++++++++++++++++------------- net/l2tp/l2tp_ppp.c | 16 +++++++++------- 5 files changed, 39 insertions(+), 69 deletions(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 5e36f45e906b9..2e60957ee8211 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -241,27 +241,6 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) } EXPORT_SYMBOL_GPL(l2tp_tunnel_get); -struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth) -{ - struct l2tp_net *pn = l2tp_pernet(net); - unsigned long tunnel_id, tmp; - struct l2tp_tunnel *tunnel; - int count = 0; - - rcu_read_lock_bh(); - idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { - if (tunnel && ++count > nth && - refcount_inc_not_zero(&tunnel->ref_count)) { - rcu_read_unlock_bh(); - return tunnel; - } - } - rcu_read_unlock_bh(); - - return NULL; -} -EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth); - struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key) { struct l2tp_net *pn = l2tp_pernet(net); @@ -355,25 +334,6 @@ struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, in } EXPORT_SYMBOL_GPL(l2tp_session_get); -struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth) -{ - struct l2tp_session *session; - int count = 0; - - rcu_read_lock_bh(); - list_for_each_entry_rcu(session, &tunnel->session_list, list) { - if (++count > nth) { - l2tp_session_inc_refcount(session); - rcu_read_unlock_bh(); - return session; - } - } - rcu_read_unlock_bh(); - - return NULL; -} -EXPORT_SYMBOL_GPL(l2tp_session_get_nth); - static struct l2tp_session *l2tp_v2_session_get_next(const struct net *net, u16 tid, unsigned long *key) diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index cc464982a7d97..0fabacffc3f38 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -219,14 +219,12 @@ void l2tp_session_dec_refcount(struct l2tp_session *session); * the caller must ensure that the reference is dropped appropriately. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); -struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth); struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key); struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id); struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id); struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver, u32 tunnel_id, u32 session_id); -struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth); struct l2tp_session *l2tp_session_get_next(const struct net *net, struct sock *sk, int pver, u32 tunnel_id, unsigned long *key); struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 8755ae521154d..b2134b57ed18c 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -34,8 +34,8 @@ static struct dentry *rootdir; struct l2tp_dfs_seq_data { struct net *net; netns_tracker ns_tracker; - int tunnel_idx; /* current tunnel */ - int session_idx; /* index of session within current tunnel */ + unsigned long tkey; /* lookup key of current tunnel */ + unsigned long skey; /* lookup key of current session */ struct l2tp_tunnel *tunnel; struct l2tp_session *session; /* NULL means get next tunnel */ }; @@ -46,8 +46,8 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd) if (pd->tunnel) l2tp_tunnel_dec_refcount(pd->tunnel); - pd->tunnel = l2tp_tunnel_get_nth(pd->net, pd->tunnel_idx); - pd->tunnel_idx++; + pd->tunnel = l2tp_tunnel_get_next(pd->net, &pd->tkey); + pd->tkey++; } static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd) @@ -56,11 +56,13 @@ static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd) if (pd->session) l2tp_session_dec_refcount(pd->session); - pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx); - pd->session_idx++; + pd->session = l2tp_session_get_next(pd->net, pd->tunnel->sock, + pd->tunnel->version, + pd->tunnel->tunnel_id, &pd->skey); + pd->skey++; if (!pd->session) { - pd->session_idx = 0; + pd->skey = 0; l2tp_dfs_next_tunnel(pd); } } diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index fc43ecbd128cc..0598b97a0bcae 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -491,14 +491,20 @@ static int l2tp_nl_cmd_tunnel_get(struct sk_buff *skb, struct genl_info *info) return ret; } +struct l2tp_nl_cb_data { + unsigned long tkey; + unsigned long skey; +}; + static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback *cb) { - int ti = cb->args[0]; + struct l2tp_nl_cb_data *cbd = (void *)&cb->ctx[0]; + unsigned long key = cbd->tkey; struct l2tp_tunnel *tunnel; struct net *net = sock_net(skb->sk); for (;;) { - tunnel = l2tp_tunnel_get_nth(net, ti); + tunnel = l2tp_tunnel_get_next(net, &key); if (!tunnel) goto out; @@ -510,11 +516,11 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback } l2tp_tunnel_dec_refcount(tunnel); - ti++; + key++; } out: - cb->args[0] = ti; + cbd->tkey = key; return skb->len; } @@ -832,25 +838,27 @@ static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info) static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback *cb) { + struct l2tp_nl_cb_data *cbd = (void *)&cb->ctx[0]; struct net *net = sock_net(skb->sk); struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; - int ti = cb->args[0]; - int si = cb->args[1]; + unsigned long tkey = cbd->tkey; + unsigned long skey = cbd->skey; for (;;) { if (!tunnel) { - tunnel = l2tp_tunnel_get_nth(net, ti); + tunnel = l2tp_tunnel_get_next(net, &tkey); if (!tunnel) goto out; } - session = l2tp_session_get_nth(tunnel, si); + session = l2tp_session_get_next(net, tunnel->sock, tunnel->version, + tunnel->tunnel_id, &skey); if (!session) { - ti++; + tkey++; l2tp_tunnel_dec_refcount(tunnel); tunnel = NULL; - si = 0; + skey = 0; continue; } @@ -863,12 +871,12 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback } l2tp_session_dec_refcount(session); - si++; + skey++; } out: - cb->args[0] = ti; - cb->args[1] = si; + cbd->tkey = tkey; + cbd->skey = skey; return skb->len; } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index c25dd8e360740..8459e5159430a 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1397,8 +1397,8 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, struct pppol2tp_seq_data { struct seq_net_private p; - int tunnel_idx; /* current tunnel */ - int session_idx; /* index of session within current tunnel */ + unsigned long tkey; /* lookup key of current tunnel */ + unsigned long skey; /* lookup key of current session */ struct l2tp_tunnel *tunnel; struct l2tp_session *session; /* NULL means get next tunnel */ }; @@ -1410,8 +1410,8 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd) l2tp_tunnel_dec_refcount(pd->tunnel); for (;;) { - pd->tunnel = l2tp_tunnel_get_nth(net, pd->tunnel_idx); - pd->tunnel_idx++; + pd->tunnel = l2tp_tunnel_get_next(net, &pd->tkey); + pd->tkey++; /* Only accept L2TPv2 tunnels */ if (!pd->tunnel || pd->tunnel->version == 2) @@ -1427,11 +1427,13 @@ static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd) if (pd->session) l2tp_session_dec_refcount(pd->session); - pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx); - pd->session_idx++; + pd->session = l2tp_session_get_next(net, pd->tunnel->sock, + pd->tunnel->version, + pd->tunnel->tunnel_id, &pd->skey); + pd->skey++; if (!pd->session) { - pd->session_idx = 0; + pd->skey = 0; pppol2tp_next_tunnel(net, pd); } } From abe7a1a7d0b69e63b1bca5f9531023a52336784f Mon Sep 17 00:00:00 2001 From: James Chapman Date: Wed, 7 Aug 2024 07:54:50 +0100 Subject: [PATCH 042/385] l2tp: improve tunnel/session refcount helpers l2tp_tunnel_inc_refcount and l2tp_session_inc_refcount wrap refcount_inc. They add no value so just use the refcount APIs directly and drop l2tp's helpers. l2tp already uses refcount_inc_not_zero anyway. Rename l2tp_tunnel_dec_refcount and l2tp_session_dec_refcount to l2tp_tunnel_put and l2tp_session_put to better match their use pairing various _get getters. Signed-off-by: James Chapman Signed-off-by: Tom Parkin Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 52 ++++++++++++++++------------------------- net/l2tp/l2tp_core.h | 6 ++--- net/l2tp/l2tp_debugfs.c | 8 +++---- net/l2tp/l2tp_eth.c | 10 ++++---- net/l2tp/l2tp_ip.c | 6 ++--- net/l2tp/l2tp_ip6.c | 6 ++--- net/l2tp/l2tp_netlink.c | 38 +++++++++++++++--------------- net/l2tp/l2tp_ppp.c | 46 ++++++++++++++++++------------------ 8 files changed, 79 insertions(+), 93 deletions(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 2e60957ee8211..b0bf0ae08e85e 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -170,7 +170,7 @@ static void l2tp_session_free(struct l2tp_session *session) { trace_free_session(session); if (session->tunnel) - l2tp_tunnel_dec_refcount(session->tunnel); + l2tp_tunnel_put(session->tunnel); kfree_rcu(session, rcu); } @@ -197,31 +197,19 @@ struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk) } EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel); -void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) -{ - refcount_inc(&tunnel->ref_count); -} -EXPORT_SYMBOL_GPL(l2tp_tunnel_inc_refcount); - -void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel) +void l2tp_tunnel_put(struct l2tp_tunnel *tunnel) { if (refcount_dec_and_test(&tunnel->ref_count)) l2tp_tunnel_free(tunnel); } -EXPORT_SYMBOL_GPL(l2tp_tunnel_dec_refcount); - -void l2tp_session_inc_refcount(struct l2tp_session *session) -{ - refcount_inc(&session->ref_count); -} -EXPORT_SYMBOL_GPL(l2tp_session_inc_refcount); +EXPORT_SYMBOL_GPL(l2tp_tunnel_put); -void l2tp_session_dec_refcount(struct l2tp_session *session) +void l2tp_session_put(struct l2tp_session *session) { if (refcount_dec_and_test(&session->ref_count)) l2tp_session_free(session); } -EXPORT_SYMBOL_GPL(l2tp_session_dec_refcount); +EXPORT_SYMBOL_GPL(l2tp_session_put); /* Lookup a tunnel. A new reference is held on the returned tunnel. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) @@ -454,7 +442,7 @@ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, if (tunnel) { list_for_each_entry_rcu(session, &tunnel->session_list, list) { if (!strcmp(session->ifname, ifname)) { - l2tp_session_inc_refcount(session); + refcount_inc(&session->ref_count); rcu_read_unlock_bh(); return session; @@ -471,7 +459,7 @@ EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname); static void l2tp_session_coll_list_add(struct l2tp_session_coll_list *clist, struct l2tp_session *session) { - l2tp_session_inc_refcount(session); + refcount_inc(&session->ref_count); WARN_ON_ONCE(session->coll_list); session->coll_list = clist; spin_lock(&clist->lock); @@ -557,7 +545,7 @@ static void l2tp_session_collision_del(struct l2tp_net *pn, spin_unlock(&clist->lock); if (refcount_dec_and_test(&clist->ref_count)) kfree(clist); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); } } @@ -606,7 +594,7 @@ int l2tp_session_register(struct l2tp_session *session, goto out; } - l2tp_tunnel_inc_refcount(tunnel); + refcount_inc(&tunnel->ref_count); WRITE_ONCE(session->tunnel, tunnel); list_add_rcu(&session->list, &tunnel->session_list); @@ -1089,7 +1077,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (!session || !session->recv_skb) { if (session) - l2tp_session_dec_refcount(session); + l2tp_session_put(session); /* Not found? Pass to userspace to deal with */ goto pass; @@ -1103,12 +1091,12 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { - l2tp_session_dec_refcount(session); + l2tp_session_put(session); goto invalid; } l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return 0; @@ -1408,7 +1396,7 @@ static void l2tp_udp_encap_destroy(struct sock *sk) tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) { l2tp_tunnel_delete(tunnel); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); } } @@ -1443,10 +1431,10 @@ static void l2tp_tunnel_del_work(struct work_struct *work) l2tp_tunnel_remove(tunnel->l2tp_net, tunnel); /* drop initial ref */ - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); /* drop workqueue ref */ - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); } /* Create a socket for the tunnel, if one isn't set up by @@ -1634,7 +1622,7 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net, tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) { - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); return -EBUSY; } @@ -1726,7 +1714,7 @@ void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { if (!test_and_set_bit(0, &tunnel->dead)) { trace_delete_tunnel(tunnel); - l2tp_tunnel_inc_refcount(tunnel); + refcount_inc(&tunnel->ref_count); queue_work(l2tp_wq, &tunnel->del_work); } } @@ -1736,7 +1724,7 @@ void l2tp_session_delete(struct l2tp_session *session) { if (!test_and_set_bit(0, &session->dead)) { trace_delete_session(session); - l2tp_session_inc_refcount(session); + refcount_inc(&session->ref_count); queue_work(l2tp_wq, &session->del_work); } } @@ -1754,10 +1742,10 @@ static void l2tp_session_del_work(struct work_struct *work) (*session->session_close)(session); /* drop initial ref */ - l2tp_session_dec_refcount(session); + l2tp_session_put(session); /* drop workqueue ref */ - l2tp_session_dec_refcount(session); + l2tp_session_put(session); } /* We come here whenever a session's send_seq, cookie_len or diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 0fabacffc3f38..ffd8ced3a51ff 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -209,10 +209,8 @@ static inline void *l2tp_session_priv(struct l2tp_session *session) } /* Tunnel and session refcounts */ -void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel); -void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel); -void l2tp_session_inc_refcount(struct l2tp_session *session); -void l2tp_session_dec_refcount(struct l2tp_session *session); +void l2tp_tunnel_put(struct l2tp_tunnel *tunnel); +void l2tp_session_put(struct l2tp_session *session); /* Tunnel and session lookup. * These functions take a reference on the instances they return, so diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index b2134b57ed18c..2d0c8275a3a82 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -44,7 +44,7 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd) { /* Drop reference taken during previous invocation */ if (pd->tunnel) - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); pd->tunnel = l2tp_tunnel_get_next(pd->net, &pd->tkey); pd->tkey++; @@ -54,7 +54,7 @@ static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd) { /* Drop reference taken during previous invocation */ if (pd->session) - l2tp_session_dec_refcount(pd->session); + l2tp_session_put(pd->session); pd->session = l2tp_session_get_next(pd->net, pd->tunnel->sock, pd->tunnel->version, @@ -111,11 +111,11 @@ static void l2tp_dfs_seq_stop(struct seq_file *p, void *v) * or l2tp_dfs_next_tunnel(). */ if (pd->session) { - l2tp_session_dec_refcount(pd->session); + l2tp_session_put(pd->session); pd->session = NULL; } if (pd->tunnel) { - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); pd->tunnel = NULL; } } diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index cc8a3ce716e94..e94549668e104 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -283,7 +283,7 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, spriv = l2tp_session_priv(session); - l2tp_session_inc_refcount(session); + refcount_inc(&session->ref_count); rtnl_lock(); @@ -301,7 +301,7 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, if (rc < 0) { rtnl_unlock(); l2tp_session_delete(session); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); free_netdev(dev); return rc; @@ -312,17 +312,17 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, rtnl_unlock(); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); __module_get(THIS_MODULE); return 0; err_sess_dev: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); free_netdev(dev); err_sess: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); err: return rc; } diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index f563c8afd8f39..39f3f1334c4aa 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -167,7 +167,7 @@ static int l2tp_ip_recv(struct sk_buff *skb) goto discard_sess; l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return 0; @@ -200,7 +200,7 @@ static int l2tp_ip_recv(struct sk_buff *skb) return sk_receive_skb(sk, skb, 1); discard_sess: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); goto discard; discard_put: @@ -265,7 +265,7 @@ static void l2tp_ip_destroy_sock(struct sock *sk) tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) { l2tp_tunnel_delete(tunnel); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); } } diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index dcec1de2898e9..f4c1da0708269 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -177,7 +177,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb) goto discard_sess; l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return 0; @@ -210,7 +210,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb) return sk_receive_skb(sk, skb, 1); discard_sess: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); goto discard; discard_put: @@ -276,7 +276,7 @@ static void l2tp_ip6_destroy_sock(struct sock *sk) tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) { l2tp_tunnel_delete(tunnel); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); } } diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 0598b97a0bcae..284f1dec1b56d 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -63,7 +63,7 @@ static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info) if (tunnel) { session = l2tp_session_get(net, tunnel->sock, tunnel->version, tunnel_id, session_id); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); } } @@ -242,7 +242,7 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info if (ret < 0) goto out; - l2tp_tunnel_inc_refcount(tunnel); + refcount_inc(&tunnel->ref_count); ret = l2tp_tunnel_register(tunnel, net, &cfg); if (ret < 0) { kfree(tunnel); @@ -250,7 +250,7 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info } ret = l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel, L2TP_CMD_TUNNEL_CREATE); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); out: return ret; @@ -280,7 +280,7 @@ static int l2tp_nl_cmd_tunnel_delete(struct sk_buff *skb, struct genl_info *info l2tp_tunnel_delete(tunnel); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); out: return ret; @@ -308,7 +308,7 @@ static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info ret = l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel, L2TP_CMD_TUNNEL_MODIFY); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); out: return ret; @@ -479,12 +479,12 @@ static int l2tp_nl_cmd_tunnel_get(struct sk_buff *skb, struct genl_info *info) if (ret < 0) goto err_nlmsg_tunnel; - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); return genlmsg_unicast(net, msg, info->snd_portid); err_nlmsg_tunnel: - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); err_nlmsg: nlmsg_free(msg); err: @@ -511,10 +511,10 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, tunnel, L2TP_CMD_TUNNEL_GET) < 0) { - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); goto out; } - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); key++; } @@ -647,12 +647,12 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf if (session) { ret = l2tp_session_notify(&l2tp_nl_family, info, session, L2TP_CMD_SESSION_CREATE); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); } } out_tunnel: - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); out: return ret; } @@ -677,7 +677,7 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete) l2tp_nl_cmd_ops[pw_type]->session_delete(session); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); out: return ret; @@ -713,7 +713,7 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf ret = l2tp_session_notify(&l2tp_nl_family, info, session, L2TP_CMD_SESSION_MODIFY); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); out: return ret; @@ -824,14 +824,14 @@ static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info) ret = genlmsg_unicast(genl_info_net(info), msg, info->snd_portid); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return ret; err_ref_msg: nlmsg_free(msg); err_ref: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); err: return ret; } @@ -856,7 +856,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback tunnel->tunnel_id, &skey); if (!session) { tkey++; - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); tunnel = NULL; skey = 0; continue; @@ -865,11 +865,11 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, session, L2TP_CMD_SESSION_GET) < 0) { - l2tp_session_dec_refcount(session); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_session_put(session); + l2tp_tunnel_put(tunnel); break; } - l2tp_session_dec_refcount(session); + l2tp_session_put(session); skey++; } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 8459e5159430a..53baf2dd5d5da 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -313,12 +313,12 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m, l2tp_xmit_skb(session, skb); local_bh_enable(); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return total_len; error_put_sess: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); error: return error; } @@ -372,12 +372,12 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) l2tp_xmit_skb(session, skb); local_bh_enable(); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return 1; abort_put_sess: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); abort: /* Free the original skb */ kfree_skb(skb); @@ -413,7 +413,7 @@ static void pppol2tp_session_close(struct l2tp_session *session) sock_put(ps->__sk); /* drop ref taken when we referenced socket via sk_user_data */ - l2tp_session_dec_refcount(session); + l2tp_session_put(session); } } @@ -444,7 +444,7 @@ static int pppol2tp_release(struct socket *sock) if (session) { l2tp_session_delete(session); /* drop ref taken by pppol2tp_sock_to_session */ - l2tp_session_dec_refcount(session); + l2tp_session_put(session); } release_sock(sk); @@ -668,7 +668,7 @@ static struct l2tp_tunnel *pppol2tp_tunnel_get(struct net *net, if (error < 0) return ERR_PTR(error); - l2tp_tunnel_inc_refcount(tunnel); + refcount_inc(&tunnel->ref_count); error = l2tp_tunnel_register(tunnel, net, &tcfg); if (error < 0) { kfree(tunnel); @@ -684,7 +684,7 @@ static struct l2tp_tunnel *pppol2tp_tunnel_get(struct net *net, /* Error if socket is not prepped */ if (!tunnel->sock) { - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); return ERR_PTR(-ENOENT); } } @@ -774,13 +774,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, pppol2tp_session_init(session); ps = l2tp_session_priv(session); - l2tp_session_inc_refcount(session); + refcount_inc(&session->ref_count); mutex_lock(&ps->sk_lock); error = l2tp_session_register(session, tunnel); if (error < 0) { mutex_unlock(&ps->sk_lock); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); goto end; } @@ -836,8 +836,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, l2tp_tunnel_delete(tunnel); } if (drop_refcnt) - l2tp_session_dec_refcount(session); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_session_put(session); + l2tp_tunnel_put(tunnel); release_sock(sk); return error; @@ -877,7 +877,7 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel, return 0; err_sess: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); err: return error; } @@ -988,7 +988,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, error = len; - l2tp_session_dec_refcount(session); + l2tp_session_put(session); end: return error; } @@ -1038,12 +1038,12 @@ static int pppol2tp_tunnel_copy_stats(struct pppol2tp_ioc_stats *stats, return -EBADR; if (session->pwtype != L2TP_PWTYPE_PPP) { - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return -EBADR; } pppol2tp_copy_stats(stats, &session->stats); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return 0; } @@ -1261,7 +1261,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname, err = pppol2tp_session_setsockopt(sk, session, optname, val); } - l2tp_session_dec_refcount(session); + l2tp_session_put(session); end: return err; } @@ -1382,7 +1382,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, err = 0; end_put_sess: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); end: return err; } @@ -1407,7 +1407,7 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd) { /* Drop reference taken during previous invocation */ if (pd->tunnel) - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); for (;;) { pd->tunnel = l2tp_tunnel_get_next(net, &pd->tkey); @@ -1417,7 +1417,7 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd) if (!pd->tunnel || pd->tunnel->version == 2) return; - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); } } @@ -1425,7 +1425,7 @@ static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd) { /* Drop reference taken during previous invocation */ if (pd->session) - l2tp_session_dec_refcount(pd->session); + l2tp_session_put(pd->session); pd->session = l2tp_session_get_next(net, pd->tunnel->sock, pd->tunnel->version, @@ -1485,11 +1485,11 @@ static void pppol2tp_seq_stop(struct seq_file *p, void *v) * or pppol2tp_next_tunnel(). */ if (pd->session) { - l2tp_session_dec_refcount(pd->session); + l2tp_session_put(pd->session); pd->session = NULL; } if (pd->tunnel) { - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); pd->tunnel = NULL; } } From dcc59d3e328e3afe54df4f395796042735b1c420 Mon Sep 17 00:00:00 2001 From: James Chapman Date: Wed, 7 Aug 2024 07:54:51 +0100 Subject: [PATCH 043/385] l2tp: l2tp_eth: use per-cpu counters from dev->tstats l2tp_eth uses old-style dev->stats for fastpath packet/byte counters. Convert it to use dev->tstats per-cpu counters. Signed-off-by: James Chapman Signed-off-by: Tom Parkin Signed-off-by: David S. Miller --- net/l2tp/l2tp_eth.c | 32 ++++++++++---------------------- 1 file changed, 10 insertions(+), 22 deletions(-) diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index e94549668e104..15a862f33f76c 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -72,31 +72,19 @@ static netdev_tx_t l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev unsigned int len = skb->len; int ret = l2tp_xmit_skb(session, skb); - if (likely(ret == NET_XMIT_SUCCESS)) { - DEV_STATS_ADD(dev, tx_bytes, len); - DEV_STATS_INC(dev, tx_packets); - } else { + if (likely(ret == NET_XMIT_SUCCESS)) + dev_sw_netstats_tx_add(dev, 1, len); + else DEV_STATS_INC(dev, tx_dropped); - } - return NETDEV_TX_OK; -} -static void l2tp_eth_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *stats) -{ - stats->tx_bytes = DEV_STATS_READ(dev, tx_bytes); - stats->tx_packets = DEV_STATS_READ(dev, tx_packets); - stats->tx_dropped = DEV_STATS_READ(dev, tx_dropped); - stats->rx_bytes = DEV_STATS_READ(dev, rx_bytes); - stats->rx_packets = DEV_STATS_READ(dev, rx_packets); - stats->rx_errors = DEV_STATS_READ(dev, rx_errors); + return NETDEV_TX_OK; } static const struct net_device_ops l2tp_eth_netdev_ops = { .ndo_init = l2tp_eth_dev_init, .ndo_uninit = l2tp_eth_dev_uninit, .ndo_start_xmit = l2tp_eth_dev_xmit, - .ndo_get_stats64 = l2tp_eth_get_stats64, + .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = eth_mac_addr, }; @@ -112,6 +100,7 @@ static void l2tp_eth_dev_setup(struct net_device *dev) dev->features |= NETIF_F_LLTX; dev->netdev_ops = &l2tp_eth_netdev_ops; dev->needs_free_netdev = true; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; } static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len) @@ -138,12 +127,11 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, if (!dev) goto error_rcu; - if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) { - DEV_STATS_INC(dev, rx_packets); - DEV_STATS_ADD(dev, rx_bytes, data_len); - } else { + if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) + dev_sw_netstats_rx_add(dev, data_len); + else DEV_STATS_INC(dev, rx_errors); - } + rcu_read_unlock(); return; From c1b2e36b8776a20a1fbdeb9d3be0637c00d671b0 Mon Sep 17 00:00:00 2001 From: James Chapman Date: Wed, 7 Aug 2024 07:54:52 +0100 Subject: [PATCH 044/385] l2tp: flush workqueue before draining it syzbot exposes a race where a net used by l2tp is removed while an existing pppol2tp socket is closed. In l2tp_pre_exit_net, l2tp queues TUNNEL_DELETE work items to close each tunnel in the net. When these are run, new SESSION_DELETE work items are queued to delete each session in the tunnel. This all happens in drain_workqueue. However, drain_workqueue allows only new work items if they are queued by other work items which are already in the queue. If pppol2tp_release runs after drain_workqueue has started, it may queue a SESSION_DELETE work item, which results in the warning below in drain_workqueue. Address this by flushing the workqueue before drain_workqueue such that all queued TUNNEL_DELETE work items run before drain_workqueue is started. This will queue SESSION_DELETE work items for each session in the tunnel, hence pppol2tp_release or other API requests won't queue SESSION_DELETE requests once drain_workqueue is started. WARNING: CPU: 1 PID: 5467 at kernel/workqueue.c:2259 __queue_work+0xcd3/0xf50 kernel/workqueue.c:2258 Modules linked in: CPU: 1 UID: 0 PID: 5467 Comm: syz.3.43 Not tainted 6.11.0-rc1-syzkaller-00247-g3608d6aca5e7 #0 Hardware name: Google Compute Engine/Google Compute Engine, BIOS Google 06/27/2024 RIP: 0010:__queue_work+0xcd3/0xf50 kernel/workqueue.c:2258 Code: ff e8 11 84 36 00 90 0f 0b 90 e9 1e fd ff ff e8 03 84 36 00 eb 13 e8 fc 83 36 00 eb 0c e8 f5 83 36 00 eb 05 e8 ee 83 36 00 90 <0f> 0b 90 48 83 c4 60 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc RSP: 0018:ffffc90004607b48 EFLAGS: 00010093 RAX: ffffffff815ce274 RBX: ffff8880661fda00 RCX: ffff8880661fda00 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: 0000000000000000 R08: ffffffff815cd6d4 R09: 0000000000000000 R10: ffffc90004607c20 R11: fffff520008c0f85 R12: ffff88802ac33800 R13: ffff88802ac339c0 R14: dffffc0000000000 R15: 0000000000000008 FS: 00005555713eb500(0000) GS:ffff8880b9300000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 000000001eda6000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: queue_work_on+0x1c2/0x380 kernel/workqueue.c:2392 pppol2tp_release+0x163/0x230 net/l2tp/l2tp_ppp.c:445 __sock_release net/socket.c:659 [inline] sock_close+0xbc/0x240 net/socket.c:1421 __fput+0x24a/0x8a0 fs/file_table.c:422 task_work_run+0x24f/0x310 kernel/task_work.c:228 resume_user_mode_work include/linux/resume_user_mode.h:50 [inline] exit_to_user_mode_loop kernel/entry/common.c:114 [inline] exit_to_user_mode_prepare include/linux/entry-common.h:328 [inline] __syscall_exit_to_user_mode_work kernel/entry/common.c:207 [inline] syscall_exit_to_user_mode+0x168/0x370 kernel/entry/common.c:218 do_syscall_64+0x100/0x230 arch/x86/entry/common.c:89 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f061e9779f9 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffff1c1fce8 EFLAGS: 00000246 ORIG_RAX: 00000000000001b4 RAX: 0000000000000000 RBX: 000000000001017d RCX: 00007f061e9779f9 RDX: 0000000000000000 RSI: 000000000000001e RDI: 0000000000000003 RBP: 00007ffff1c1fdc0 R08: 0000000000000001 R09: 00007ffff1c1ffcf R10: 00007f061e800000 R11: 0000000000000246 R12: 0000000000000032 R13: 00007ffff1c1fde0 R14: 00007ffff1c1fe00 R15: ffffffffffffffff Fixes: fc7ec7f554d7 ("l2tp: delete sessions using work queue") Reported-by: syzbot+0e85b10481d2f5478053@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=0e85b10481d2f5478053 Signed-off-by: James Chapman Signed-off-by: Tom Parkin Signed-off-by: David S. Miller --- net/l2tp/l2tp_core.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index b0bf0ae08e85e..af87c781d6a66 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1855,8 +1855,16 @@ static __net_exit void l2tp_pre_exit_net(struct net *net) } rcu_read_unlock_bh(); - if (l2tp_wq) + if (l2tp_wq) { + /* ensure that all TUNNEL_DELETE work items are run before + * draining the work queue since TUNNEL_DELETE requests may + * queue SESSION_DELETE work items for each session in the + * tunnel. drain_workqueue may otherwise warn if SESSION_DELETE + * requests are queued while the work queue is being drained. + */ + __flush_workqueue(l2tp_wq); drain_workqueue(l2tp_wq); + } } static __net_exit void l2tp_exit_net(struct net *net) From fbda8ee64b7404a6a48af8481ed788f9d7946284 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Wed, 7 Aug 2024 22:15:13 -0700 Subject: [PATCH 045/385] bnxt_en: Update firmware interface to 1.10.3.68 The main changes are: 1. HWRM_VNIC_UPDATE used to safely disable and enable an RX ring within the VNIC. 2. New flag in HWRM_VNIC_QCAPS to indicate FW will do the proper flush during HWRM_VNIC_UPDATE. 3. New flag in HWRM_FUNC_QCAPS to indicate that reservations for some resources such as VNIC can be reduced. 4. New backing store memory types not used by the driver yet. Signed-off-by: Michael Chan Signed-off-by: David Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h | 389 +++++++++++------- 1 file changed, 249 insertions(+), 140 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index f219709f95635..f8ef6f1a1964e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -403,6 +403,9 @@ struct cmd_nums { #define HWRM_FUNC_LAG_UPDATE 0x1b1UL #define HWRM_FUNC_LAG_FREE 0x1b2UL #define HWRM_FUNC_LAG_QCFG 0x1b3UL + #define HWRM_FUNC_TIMEDTX_PACING_RATE_ADD 0x1c2UL + #define HWRM_FUNC_TIMEDTX_PACING_RATE_DELETE 0x1c3UL + #define HWRM_FUNC_TIMEDTX_PACING_RATE_QUERY 0x1c4UL #define HWRM_SELFTEST_QLIST 0x200UL #define HWRM_SELFTEST_EXEC 0x201UL #define HWRM_SELFTEST_IRQ 0x202UL @@ -430,6 +433,9 @@ struct cmd_nums { #define HWRM_STAT_GENERIC_QSTATS 0x218UL #define HWRM_MFG_PRVSN_EXPORT_CERT 0x219UL #define HWRM_STAT_DB_ERROR_QSTATS 0x21aUL + #define HWRM_MFG_TESTS 0x21bUL + #define HWRM_PORT_POE_CFG 0x230UL + #define HWRM_PORT_POE_QCFG 0x231UL #define HWRM_UDCC_QCAPS 0x258UL #define HWRM_UDCC_CFG 0x259UL #define HWRM_UDCC_QCFG 0x25aUL @@ -439,6 +445,9 @@ struct cmd_nums { #define HWRM_UDCC_COMP_CFG 0x25eUL #define HWRM_UDCC_COMP_QCFG 0x25fUL #define HWRM_UDCC_COMP_QUERY 0x260UL + #define HWRM_QUEUE_PFCWD_TIMEOUT_QCAPS 0x261UL + #define HWRM_QUEUE_PFCWD_TIMEOUT_CFG 0x262UL + #define HWRM_QUEUE_PFCWD_TIMEOUT_QCFG 0x263UL #define HWRM_TF 0x2bcUL #define HWRM_TF_VERSION_GET 0x2bdUL #define HWRM_TF_SESSION_OPEN 0x2c6UL @@ -500,10 +509,8 @@ struct cmd_nums { #define HWRM_TFC_IF_TBL_GET 0x399UL #define HWRM_TFC_TBL_SCOPE_CONFIG_GET 0x39aUL #define HWRM_TFC_RESC_USAGE_QUERY 0x39bUL - #define HWRM_QUEUE_PFCWD_TIMEOUT_QCAPS 0x39cUL - #define HWRM_QUEUE_PFCWD_TIMEOUT_CFG 0x39dUL - #define HWRM_QUEUE_PFCWD_TIMEOUT_QCFG 0x39eUL #define HWRM_SV 0x400UL + #define HWRM_DBG_SERDES_TEST 0xff0eUL #define HWRM_DBG_LOG_BUFFER_FLUSH 0xff0fUL #define HWRM_DBG_READ_DIRECT 0xff10UL #define HWRM_DBG_READ_INDIRECT 0xff11UL @@ -533,6 +540,9 @@ struct cmd_nums { #define HWRM_DBG_USEQ_RUN 0xff29UL #define HWRM_DBG_USEQ_DELIVERY_REQ 0xff2aUL #define HWRM_DBG_USEQ_RESP_HDR 0xff2bUL + #define HWRM_DBG_COREDUMP_CAPTURE 0xff2cUL + #define HWRM_DBG_PTRACE 0xff2dUL + #define HWRM_DBG_SIM_CABLE_STATE 0xff2eUL #define HWRM_NVM_GET_VPD_FIELD_INFO 0xffeaUL #define HWRM_NVM_SET_VPD_FIELD_INFO 0xffebUL #define HWRM_NVM_DEFRAG 0xffecUL @@ -582,6 +592,7 @@ struct ret_codes { #define HWRM_ERR_CODE_RESOURCE_LOCKED 0x11UL #define HWRM_ERR_CODE_PF_UNAVAILABLE 0x12UL #define HWRM_ERR_CODE_ENTITY_NOT_PRESENT 0x13UL + #define HWRM_ERR_CODE_SECURE_SOC_ERROR 0x14UL #define HWRM_ERR_CODE_TLV_ENCAPSULATED_RESPONSE 0x8000UL #define HWRM_ERR_CODE_UNKNOWN_ERR 0xfffeUL #define HWRM_ERR_CODE_CMD_NOT_SUPPORTED 0xffffUL @@ -613,8 +624,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 3 -#define HWRM_VERSION_RSVD 44 -#define HWRM_VERSION_STR "1.10.3.44" +#define HWRM_VERSION_RSVD 68 +#define HWRM_VERSION_STR "1.10.3.68" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -850,7 +861,10 @@ struct hwrm_async_event_cmpl { #define ASYNC_EVENT_CMPL_EVENT_ID_UDCC_SESSION_CHANGE 0x4bUL #define ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER 0x4cUL #define ASYNC_EVENT_CMPL_EVENT_ID_PEER_MMAP_CHANGE 0x4dUL - #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x4eUL + #define ASYNC_EVENT_CMPL_EVENT_ID_REPRESENTOR_PAIR_CHANGE 0x4eUL + #define ASYNC_EVENT_CMPL_EVENT_ID_VF_STAT_CHANGE 0x4fUL + #define ASYNC_EVENT_CMPL_EVENT_ID_HOST_COREDUMP 0x50UL + #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x51UL #define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG 0xfeUL #define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR 0xffUL #define ASYNC_EVENT_CMPL_EVENT_ID_LAST ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR @@ -1691,7 +1705,7 @@ struct hwrm_func_qcaps_input { u8 unused_0[6]; }; -/* hwrm_func_qcaps_output (size:1088b/136B) */ +/* hwrm_func_qcaps_output (size:1152b/144B) */ struct hwrm_func_qcaps_output { __le16 error_code; __le16 req_type; @@ -1824,6 +1838,9 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_EGRESS_NIC_FLOW_SUPPORTED 0x4000000UL #define FUNC_QCAPS_RESP_FLAGS_EXT2_MULTI_LOSSLESS_QUEUES_SUPPORTED 0x8000000UL #define FUNC_QCAPS_RESP_FLAGS_EXT2_PEER_MMAP_SUPPORTED 0x10000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_TIMED_TX_PACING_SUPPORTED 0x20000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_VF_STAT_EJECTION_SUPPORTED 0x40000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_HOST_COREDUMP_SUPPORTED 0x80000000UL __le16 tunnel_disable_flag; #define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_VXLAN 0x1UL #define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NGE 0x2UL @@ -1845,7 +1862,9 @@ struct hwrm_func_qcaps_output { __le32 roce_vf_max_qp; __le32 roce_vf_max_srq; __le32 roce_vf_max_gid; - u8 unused_3[3]; + __le32 flags_ext3; + #define FUNC_QCAPS_RESP_FLAGS_EXT3_RM_RSV_WHILE_ALLOC_CAP 0x1UL + u8 unused_3[7]; u8 valid; }; @@ -2021,7 +2040,8 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100 (0x1UL << 29) #define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100 __le16 host_mtu; - u8 unused_3[2]; + __le16 flags2; + #define FUNC_QCFG_RESP_FLAGS2_SRIOV_DSCP_INSERT_ENABLED 0x1UL u8 unused_4[2]; u8 port_kdnet_mode; #define FUNC_QCFG_RESP_PORT_KDNET_MODE_DISABLED 0x0UL @@ -3671,33 +3691,38 @@ struct hwrm_func_backing_store_cfg_v2_input { __le16 target_id; __le64 resp_addr; __le16 type; - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TX_CK 0x13UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RX_CK 0x14UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION 0x1dUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT_TRACE 0x1eUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT2_TRACE 0x1fUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT_TRACE 0x20UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT2_TRACE 0x21UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP0_TRACE 0x22UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_L2_HWRM_TRACE 0x23UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_ROCE_HWRM_TRACE 0x24UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID 0xffffUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT_TRACE 0x1eUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT2_TRACE 0x1fUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT_TRACE 0x20UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT2_TRACE 0x21UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP0_TRACE 0x22UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_L2_HWRM_TRACE 0x23UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_ROCE_HWRM_TRACE 0x24UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA0_TRACE 0x26UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA1_TRACE 0x27UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA2_TRACE 0x28UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP1_TRACE 0x29UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID __le16 instance; __le32 flags; #define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_PREBOOT_MODE 0x1UL @@ -3772,6 +3797,11 @@ struct hwrm_func_backing_store_qcfg_v2_input { #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP0_TRACE 0x22UL #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_L2_HWRM_TRACE 0x23UL #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_ROCE_HWRM_TRACE 0x24UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA0_TRACE 0x26UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA1_TRACE 0x27UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA2_TRACE 0x28UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP1_TRACE 0x29UL #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID 0xffffUL #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID __le16 instance; @@ -3785,29 +3815,34 @@ struct hwrm_func_backing_store_qcfg_v2_output { __le16 seq_id; __le16 resp_len; __le16 type; - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TX_CK 0x13UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RX_CK 0x14UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION 0x1dUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT_TRACE 0x1eUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT2_TRACE 0x1fUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT_TRACE 0x20UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT2_TRACE 0x21UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP0_TRACE 0x22UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_L2_HWRM_TRACE 0x23UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_ROCE_HWRM_TRACE 0x24UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID 0xffffUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT_TRACE 0x1eUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT2_TRACE 0x1fUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT_TRACE 0x20UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT2_TRACE 0x21UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP0_TRACE 0x22UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_L2_HWRM_TRACE 0x23UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_ROCE_HWRM_TRACE 0x24UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TTX_PACING_TQM_RING 0x25UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA0_TRACE 0x26UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA1_TRACE 0x27UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA2_TRACE 0x28UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP1_TRACE 0x29UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID __le16 instance; __le32 flags; __le64 page_dir; @@ -3883,6 +3918,13 @@ struct ts_split_entries { __le32 rsvd2[2]; }; +/* ck_split_entries (size:128b/16B) */ +struct ck_split_entries { + __le32 num_quic_entries; + __le32 rsvd; + __le32 rsvd2[2]; +}; + /* hwrm_func_backing_store_qcaps_v2_input (size:192b/24B) */ struct hwrm_func_backing_store_qcaps_v2_input { __le16 req_type; @@ -3891,33 +3933,38 @@ struct hwrm_func_backing_store_qcaps_v2_input { __le16 target_id; __le64 resp_addr; __le16 type; - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TX_CK 0x13UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RX_CK 0x14UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION 0x1dUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT_TRACE 0x1eUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT2_TRACE 0x1fUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT_TRACE 0x20UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT2_TRACE 0x21UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP0_TRACE 0x22UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_L2_HWRM_TRACE 0x23UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ROCE_HWRM_TRACE 0x24UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID 0xffffUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT_TRACE 0x1eUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT2_TRACE 0x1fUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT_TRACE 0x20UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT2_TRACE 0x21UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP0_TRACE 0x22UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_L2_HWRM_TRACE 0x23UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ROCE_HWRM_TRACE 0x24UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA0_TRACE 0x26UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA1_TRACE 0x27UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA2_TRACE 0x28UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP1_TRACE 0x29UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID u8 rsvd[6]; }; @@ -3928,39 +3975,45 @@ struct hwrm_func_backing_store_qcaps_v2_output { __le16 seq_id; __le16 resp_len; __le16 type; - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TX_CK 0x13UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RX_CK 0x14UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW 0x16UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW 0x17UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW 0x18UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW 0x19UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION 0x1dUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT_TRACE 0x1eUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT2_TRACE 0x1fUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT_TRACE 0x20UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT2_TRACE 0x21UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP0_TRACE 0x22UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_L2_HWRM_TRACE 0x23UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_ROCE_HWRM_TRACE 0x24UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID 0xffffUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW 0x16UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW 0x17UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW 0x18UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW 0x19UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT_TRACE 0x1eUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT2_TRACE 0x1fUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT_TRACE 0x20UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT2_TRACE 0x21UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP0_TRACE 0x22UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_L2_HWRM_TRACE 0x23UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_ROCE_HWRM_TRACE 0x24UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TTX_PACING_TQM_RING 0x25UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA0_TRACE 0x26UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA1_TRACE 0x27UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA2_TRACE 0x28UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP1_TRACE 0x29UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID __le16 entry_size; __le32 flags; #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ENABLE_CTX_KIND_INIT 0x1UL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID 0x2UL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_DRIVER_MANAGED_MEMORY 0x4UL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ROCE_QP_PSEUDO_STATIC_ALLOC 0x8UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_FW_DBG_TRACE 0x10UL __le32 instance_bit_map; u8 ctx_init_value; u8 ctx_init_offset; @@ -4410,6 +4463,7 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_MODULE_STATUS_PWRDOWN 0x3UL #define PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTINSERTED 0x4UL #define PORT_PHY_QCFG_RESP_MODULE_STATUS_CURRENTFAULT 0x5UL + #define PORT_PHY_QCFG_RESP_MODULE_STATUS_OVERHEATED 0x6UL #define PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTAPPLICABLE 0xffUL #define PORT_PHY_QCFG_RESP_MODULE_STATUS_LAST PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTAPPLICABLE __le32 preemphasis; @@ -4941,7 +4995,9 @@ struct hwrm_port_qstats_output { __le16 resp_len; __le16 tx_stat_size; __le16 rx_stat_size; - u8 unused_0[3]; + u8 flags; + #define PORT_QSTATS_RESP_FLAGS_CLEARED 0x1UL + u8 unused_0[2]; u8 valid; }; @@ -5074,6 +5130,7 @@ struct hwrm_port_qstats_ext_output { __le16 total_active_cos_queues; u8 flags; #define PORT_QSTATS_EXT_RESP_FLAGS_CLEAR_ROCE_COUNTERS_SUPPORTED 0x1UL + #define PORT_QSTATS_EXT_RESP_FLAGS_CLEARED 0x2UL u8 valid; }; @@ -6510,6 +6567,43 @@ struct hwrm_vnic_alloc_output { u8 valid; }; +/* hwrm_vnic_update_input (size:256b/32B) */ +struct hwrm_vnic_update_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le32 vnic_id; + __le32 enables; + #define VNIC_UPDATE_REQ_ENABLES_VNIC_STATE_VALID 0x1UL + #define VNIC_UPDATE_REQ_ENABLES_MRU_VALID 0x2UL + #define VNIC_UPDATE_REQ_ENABLES_METADATA_FORMAT_TYPE_VALID 0x4UL + u8 vnic_state; + #define VNIC_UPDATE_REQ_VNIC_STATE_NORMAL 0x0UL + #define VNIC_UPDATE_REQ_VNIC_STATE_DROP 0x1UL + #define VNIC_UPDATE_REQ_VNIC_STATE_LAST VNIC_UPDATE_REQ_VNIC_STATE_DROP + u8 metadata_format_type; + #define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_0 0x0UL + #define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_1 0x1UL + #define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_2 0x2UL + #define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_3 0x3UL + #define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_4 0x4UL + #define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_LAST VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_4 + __le16 mru; + u8 unused_1[4]; +}; + +/* hwrm_vnic_update_output (size:128b/16B) */ +struct hwrm_vnic_update_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 unused_0[7]; + u8 valid; +}; + /* hwrm_vnic_free_input (size:192b/24B) */ struct hwrm_vnic_free_input { __le16 req_type; @@ -6640,6 +6734,7 @@ struct hwrm_vnic_qcaps_output { #define VNIC_QCAPS_RESP_FLAGS_RSS_PROF_TCAM_MODE_ENABLED 0x8000000UL #define VNIC_QCAPS_RESP_FLAGS_VNIC_RSS_HASH_MODE_CAP 0x10000000UL #define VNIC_QCAPS_RESP_FLAGS_HW_TUNNEL_TPA_CAP 0x20000000UL + #define VNIC_QCAPS_RESP_FLAGS_RE_FLUSH_CAP 0x40000000UL __le16 max_aggs_supported; u8 unused_1[5]; u8 valid; @@ -7484,23 +7579,24 @@ struct hwrm_cfa_l2_filter_cfg_input { __le16 target_id; __le64 resp_addr; __le32 flags; - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH 0x1UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_TX 0x0UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX 0x1UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX - #define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP 0x2UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_MASK 0xcUL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_SFT 2 - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_NO_ROCE_L2 (0x0UL << 2) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2 (0x1UL << 2) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE (0x2UL << 2) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE - #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_MASK 0x30UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_SFT 4 - #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_NO_UPDATE (0x0UL << 4) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_BYPASS_LKUP (0x1UL << 4) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP (0x2UL << 4) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH 0x1UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_TX 0x0UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX 0x1UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX + #define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP 0x2UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_MASK 0xcUL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_SFT 2 + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_NO_ROCE_L2 (0x0UL << 2) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2 (0x1UL << 2) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE (0x2UL << 2) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE + #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_MASK 0x30UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_SFT 4 + #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_NO_UPDATE (0x0UL << 4) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_BYPASS_LKUP (0x1UL << 4) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP (0x2UL << 4) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_RESTORE_FW_OP (0x3UL << 4) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_RESTORE_FW_OP __le32 enables; #define CFA_L2_FILTER_CFG_REQ_ENABLES_DST_ID 0x1UL #define CFA_L2_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID 0x2UL @@ -8766,7 +8862,7 @@ struct ctx_hw_stats_ext { __le64 rx_tpa_events; }; -/* hwrm_stat_ctx_alloc_input (size:320b/40B) */ +/* hwrm_stat_ctx_alloc_input (size:384b/48B) */ struct hwrm_stat_ctx_alloc_input { __le16 req_type; __le16 cmpl_ring; @@ -8776,13 +8872,16 @@ struct hwrm_stat_ctx_alloc_input { __le64 stats_dma_addr; __le32 update_period_ms; u8 stat_ctx_flags; - #define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE 0x1UL + #define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE 0x1UL + #define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_DUP_HOST_BUF 0x2UL u8 unused_0; __le16 stats_dma_length; __le16 flags; #define STAT_CTX_ALLOC_REQ_FLAGS_STEERING_TAG_VALID 0x1UL __le16 steering_tag; - __le32 unused_1; + __le32 stat_ctx_id; + __le16 alloc_seq_id; + u8 unused_1[6]; }; /* hwrm_stat_ctx_alloc_output (size:128b/16B) */ @@ -9650,10 +9749,13 @@ struct hwrm_dbg_qcaps_output { __le32 coredump_component_disable_caps; #define DBG_QCAPS_RESP_COREDUMP_COMPONENT_DISABLE_CAPS_NVRAM 0x1UL __le32 flags; - #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_NVM 0x1UL - #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR 0x2UL - #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR 0x4UL - #define DBG_QCAPS_RESP_FLAGS_USEQ 0x8UL + #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_NVM 0x1UL + #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR 0x2UL + #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR 0x4UL + #define DBG_QCAPS_RESP_FLAGS_USEQ 0x8UL + #define DBG_QCAPS_RESP_FLAGS_COREDUMP_HOST_DDR 0x10UL + #define DBG_QCAPS_RESP_FLAGS_COREDUMP_HOST_CAPTURE 0x20UL + #define DBG_QCAPS_RESP_FLAGS_PTRACE 0x40UL u8 unused_1[3]; u8 valid; }; @@ -10092,16 +10194,19 @@ struct hwrm_nvm_erase_dir_entry_output { u8 valid; }; -/* hwrm_nvm_get_dev_info_input (size:128b/16B) */ +/* hwrm_nvm_get_dev_info_input (size:192b/24B) */ struct hwrm_nvm_get_dev_info_input { __le16 req_type; __le16 cmpl_ring; __le16 seq_id; __le16 target_id; __le64 resp_addr; + u8 flags; + #define NVM_GET_DEV_INFO_REQ_FLAGS_SECURITY_SOC_NVM 0x1UL + u8 unused_0[7]; }; -/* hwrm_nvm_get_dev_info_output (size:704b/88B) */ +/* hwrm_nvm_get_dev_info_output (size:768b/96B) */ struct hwrm_nvm_get_dev_info_output { __le16 error_code; __le16 req_type; @@ -10135,6 +10240,10 @@ struct hwrm_nvm_get_dev_info_output { __le16 netctrl_fw_minor; __le16 netctrl_fw_build; __le16 netctrl_fw_patch; + __le16 srt2_fw_major; + __le16 srt2_fw_minor; + __le16 srt2_fw_build; + __le16 srt2_fw_patch; u8 unused_0[7]; u8 valid; }; From f2878cdeb7549437c7c47029b4020e535735c5c9 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Wed, 7 Aug 2024 22:15:14 -0700 Subject: [PATCH 046/385] bnxt_en: Add support to call FW to update a VNIC Add the function bnxt_hwrm_vnic_update() to call FW to update a VNIC. This call can be used when disabling and enabling a receive ring within a VNIC. The mru which is the maximum receive size of packets received by the VNIC can be updated. Signed-off-by: Michael Chan Signed-off-by: David Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 20 ++++++++++++++++++++ drivers/net/ethernet/broadcom/bnxt/bnxt.h | 3 +++ 2 files changed, 23 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index e27e1082ee33a..6c0c65bed604b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -10089,6 +10089,26 @@ static int __bnxt_setup_vnic(struct bnxt *bp, struct bnxt_vnic_info *vnic) return rc; } +int bnxt_hwrm_vnic_update(struct bnxt *bp, struct bnxt_vnic_info *vnic, + u8 valid) +{ + struct hwrm_vnic_update_input *req; + int rc; + + rc = hwrm_req_init(bp, req, HWRM_VNIC_UPDATE); + if (rc) + return rc; + + req->vnic_id = cpu_to_le32(vnic->fw_vnic_id); + + if (valid & VNIC_UPDATE_REQ_ENABLES_MRU_VALID) + req->mru = cpu_to_le16(vnic->mru); + + req->enables = cpu_to_le32(valid); + + return hwrm_req_send(bp, req); +} + int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic) { int rc; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 6bbdc718c3a70..5de67f7189935 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1250,6 +1250,7 @@ struct bnxt_vnic_info { #define BNXT_MAX_CTX_PER_VNIC 8 u16 fw_rss_cos_lb_ctx[BNXT_MAX_CTX_PER_VNIC]; u16 fw_l2_ctx_id; + u16 mru; #define BNXT_MAX_UC_ADDRS 4 struct bnxt_l2_filter *l2_filters[BNXT_MAX_UC_ADDRS]; /* index 0 always dev_addr */ @@ -2838,6 +2839,8 @@ int bnxt_hwrm_free_wol_fltr(struct bnxt *bp); int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all); int bnxt_hwrm_func_qcaps(struct bnxt *bp); int bnxt_hwrm_fw_set_time(struct bnxt *); +int bnxt_hwrm_vnic_update(struct bnxt *bp, struct bnxt_vnic_info *vnic, + u8 valid); int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic); int __bnxt_setup_vnic_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic); void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx, From 6e360862c08756b13f3eb4b1dcbf0b9b9e4d7382 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Wed, 7 Aug 2024 22:15:15 -0700 Subject: [PATCH 047/385] bnxt_en: Check the FW's VNIC flush capability Check the HWRM_VNIC_QCAPS FW response for the receive engine flush capability. This capability indicates that we can reliably support RX ring restart when calling HWRM_VNIC_UPDATE with MRU set to 0. Signed-off-by: Michael Chan Signed-off-by: David Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 ++ drivers/net/ethernet/broadcom/bnxt/bnxt.h | 1 + 2 files changed, 3 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6c0c65bed604b..599ca00e0be30 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6715,6 +6715,8 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp) bp->rss_cap |= BNXT_RSS_CAP_ESP_V4_RSS_CAP; if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV6_CAP) bp->rss_cap |= BNXT_RSS_CAP_ESP_V6_RSS_CAP; + if (flags & VNIC_QCAPS_RESP_FLAGS_RE_FLUSH_CAP) + bp->fw_cap |= BNXT_FW_CAP_VNIC_RE_FLUSH; } hwrm_req_drop(bp, req); return rc; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 5de67f7189935..a2233b2d9329d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2438,6 +2438,7 @@ struct bnxt { #define BNXT_FW_CAP_VNIC_TUNNEL_TPA BIT_ULL(37) #define BNXT_FW_CAP_CFA_NTUPLE_RX_EXT_IP_PROTO BIT_ULL(38) #define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V3 BIT_ULL(39) + #define BNXT_FW_CAP_VNIC_RE_FLUSH BIT_ULL(40) u32 fw_dbg_cap; From d41575f76a6d870b386b2aa75143c5cf9543fb45 Mon Sep 17 00:00:00 2001 From: David Wei Date: Wed, 7 Aug 2024 22:15:16 -0700 Subject: [PATCH 048/385] bnxt_en: set vnic->mru in bnxt_hwrm_vnic_cfg() Set the newly added vnic->mru field in bnxt_hwrm_vnic_cfg(). Signed-off-by: David Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 599ca00e0be30..10ca0edc4aab6 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6579,7 +6579,8 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic) req->dflt_ring_grp = cpu_to_le16(bp->grp_info[grp_idx].fw_grp_id); req->lb_rule = cpu_to_le16(0xffff); vnic_mru: - req->mru = cpu_to_le16(bp->dev->mtu + ETH_HLEN + VLAN_HLEN); + vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN; + req->mru = cpu_to_le16(vnic->mru); req->vnic_id = cpu_to_le16(vnic->fw_vnic_id); #ifdef CONFIG_BNXT_SRIOV From b9d2956e869c78bb356a71dd0a75346da9fd191f Mon Sep 17 00:00:00 2001 From: David Wei Date: Wed, 7 Aug 2024 22:15:17 -0700 Subject: [PATCH 049/385] bnxt_en: stop packet flow during bnxt_queue_stop/start The current implementation when resetting a queue while packets are flowing puts the queue into an inconsistent state. There needs to be some synchronisation with the FW. Add calls to bnxt_hwrm_vnic_update() to set the MRU for both the default and ntuple vnic during queue start/stop. When the MRU is set to 0, flow is stopped. Each Rx queue belongs to either the default or the ntuple vnic. With calling bnxt_hwrm_vnic_update() the calls to napi_enable() and napi_disable() must be removed for reset to work on a queue that has active traffic flowing e.g. iperf3. Co-developed-by: Somnath Kotur Signed-off-by: Somnath Kotur Signed-off-by: David Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 10ca0edc4aab6..e1eadab82261a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -15177,7 +15177,8 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) struct bnxt *bp = netdev_priv(dev); struct bnxt_rx_ring_info *rxr, *clone; struct bnxt_cp_ring_info *cpr; - int rc; + struct bnxt_vnic_info *vnic; + int i, rc; rxr = &bp->rx_ring[idx]; clone = qmem; @@ -15202,11 +15203,16 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) if (bp->flags & BNXT_FLAG_AGG_RINGS) bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod); - napi_enable(&rxr->bnapi->napi); - cpr = &rxr->bnapi->cp_ring; cpr->sw_stats->rx.rx_resets++; + for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) { + vnic = &bp->vnic_info[i]; + vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN; + bnxt_hwrm_vnic_update(bp, vnic, + VNIC_UPDATE_REQ_ENABLES_MRU_VALID); + } + return 0; err_free_hwrm_rx_ring: @@ -15218,9 +15224,17 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx) { struct bnxt *bp = netdev_priv(dev); struct bnxt_rx_ring_info *rxr; + struct bnxt_vnic_info *vnic; + int i; + + for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) { + vnic = &bp->vnic_info[i]; + vnic->mru = 0; + bnxt_hwrm_vnic_update(bp, vnic, + VNIC_UPDATE_REQ_ENABLES_MRU_VALID); + } rxr = &bp->rx_ring[idx]; - napi_disable(&rxr->bnapi->napi); bnxt_hwrm_rx_ring_free(bp, rxr, false); bnxt_hwrm_rx_agg_ring_free(bp, rxr, false); rxr->rx_next_cons = 0; From 97cbf3d0accce0f29db0be3ac1b50d9d561d3206 Mon Sep 17 00:00:00 2001 From: David Wei Date: Wed, 7 Aug 2024 22:15:18 -0700 Subject: [PATCH 050/385] bnxt_en: only set dev->queue_mgmt_ops if supported by FW The queue API calls bnxt_hwrm_vnic_update() to stop/start the flow of packets, which can only properly flush the pipeline if FW indicates support. Add a macro BNXT_SUPPORTS_QUEUE_API that checks for the required flags and only set queue_mgmt_ops if true. Signed-off-by: David Wei Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 3 +++ 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index e1eadab82261a..75e2cfed57696 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -15718,7 +15718,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->stat_ops = &bnxt_stat_ops; dev->watchdog_timeo = BNXT_TX_TIMEOUT; dev->ethtool_ops = &bnxt_ethtool_ops; - dev->queue_mgmt_ops = &bnxt_queue_mgmt_ops; pci_set_drvdata(pdev, dev); rc = bnxt_alloc_hwrm_resources(bp); @@ -15899,6 +15898,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (BNXT_SUPPORTS_NTUPLE_VNIC(bp)) bp->rss_cap |= BNXT_RSS_CAP_MULTI_RSS_CTX; + if (BNXT_SUPPORTS_QUEUE_API(bp)) + dev->queue_mgmt_ops = &bnxt_queue_mgmt_ops; rc = register_netdev(dev); if (rc) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index a2233b2d9329d..62e637c5be31a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2451,6 +2451,9 @@ struct bnxt { #define BNXT_SUPPORTS_MULTI_RSS_CTX(bp) \ (BNXT_PF(bp) && BNXT_SUPPORTS_NTUPLE_VNIC(bp) && \ ((bp)->rss_cap & BNXT_RSS_CAP_MULTI_RSS_CTX)) +#define BNXT_SUPPORTS_QUEUE_API(bp) \ + (BNXT_PF(bp) && BNXT_SUPPORTS_NTUPLE_VNIC(bp) && \ + ((bp)->fw_cap & BNXT_FW_CAP_VNIC_RE_FLUSH)) u32 hwrm_spec_code; u16 hwrm_cmd_seq; From e81d00a6b3b7d619060223d0754ca02e7d4ba90f Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Thu, 8 Aug 2024 11:47:32 +0200 Subject: [PATCH 051/385] net: mvpp2: use port_count to remove ports As discussed in [1], there is no need to iterate over child nodes to remove the list of ports. Instead, a loop up to `port_count` ports can be used, and is in fact more reliable in case the child node availability changes. The suggested approach removes the need for the `fwnode` and `port_fwnode` variables in mvpp2_remove() as well. Link: https://lore.kernel.org/all/ZqdRgDkK1PzoI2Pf@shell.armlinux.org.uk/ [1] Suggested-by: Russell King Signed-off-by: Javier Carrasco Signed-off-by: David S. Miller --- .../net/ethernet/marvell/mvpp2/mvpp2_main.c | 23 ++++++------------- 1 file changed, 7 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 0d62a33afa80c..0b5b2425de12f 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -7655,12 +7655,8 @@ static int mvpp2_probe(struct platform_device *pdev) err_port_probe: fwnode_handle_put(port_fwnode); - i = 0; - fwnode_for_each_available_child_node(fwnode, port_fwnode) { - if (priv->port_list[i]) - mvpp2_port_remove(priv->port_list[i]); - i++; - } + for (i = 0; i < priv->port_count; i++) + mvpp2_port_remove(priv->port_list[i]); err_axi_clk: clk_disable_unprepare(priv->axi_clk); err_mg_core_clk: @@ -7677,18 +7673,13 @@ static int mvpp2_probe(struct platform_device *pdev) static void mvpp2_remove(struct platform_device *pdev) { struct mvpp2 *priv = platform_get_drvdata(pdev); - struct fwnode_handle *fwnode = pdev->dev.fwnode; - int i = 0, poolnum = MVPP2_BM_POOLS_NUM; - struct fwnode_handle *port_fwnode; + int i, poolnum = MVPP2_BM_POOLS_NUM; mvpp2_dbgfs_cleanup(priv); - fwnode_for_each_available_child_node(fwnode, port_fwnode) { - if (priv->port_list[i]) { - mutex_destroy(&priv->port_list[i]->gather_stats_lock); - mvpp2_port_remove(priv->port_list[i]); - } - i++; + for (i = 0; i < priv->port_count; i++) { + mutex_destroy(&priv->port_list[i]->gather_stats_lock); + mvpp2_port_remove(priv->port_list[i]); } destroy_workqueue(priv->stats_queue); @@ -7711,7 +7702,7 @@ static void mvpp2_remove(struct platform_device *pdev) aggr_txq->descs_dma); } - if (is_acpi_node(port_fwnode)) + if (!dev_of_node(&pdev->dev)) return; clk_disable_unprepare(priv->axi_clk); From a7b32744475cb774b4fce599f58394f4ef0acb68 Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Thu, 8 Aug 2024 11:47:33 +0200 Subject: [PATCH 052/385] net: mvpp2: use device_for_each_child_node() to access device child nodes The iterated nodes are direct children of the device node, and the `device_for_each_child_node()` macro accounts for child node availability. `fwnode_for_each_available_child_node()` is meant to access the child nodes of an fwnode, and therefore not direct child nodes of the device node. The child nodes within mvpp2_probe are not accessed outside the loops, and the scoped version of the macro can be used to automatically decrement the refcount on early exits. Use `device_for_each_child_node()` and its scoped variant to indicate device's direct child nodes. Reviewed-by: Jonathan Cameron Signed-off-by: Javier Carrasco Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 0b5b2425de12f..216cc7b860d6d 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -7417,8 +7417,6 @@ static int mvpp2_get_sram(struct platform_device *pdev, static int mvpp2_probe(struct platform_device *pdev) { - struct fwnode_handle *fwnode = pdev->dev.fwnode; - struct fwnode_handle *port_fwnode; struct mvpp2 *priv; struct resource *res; void __iomem *base; @@ -7591,7 +7589,7 @@ static int mvpp2_probe(struct platform_device *pdev) } /* Map DTS-active ports. Should be done before FIFO mvpp2_init */ - fwnode_for_each_available_child_node(fwnode, port_fwnode) { + device_for_each_child_node_scoped(&pdev->dev, port_fwnode) { if (!fwnode_property_read_u32(port_fwnode, "port-id", &i)) priv->port_map |= BIT(i); } @@ -7614,7 +7612,7 @@ static int mvpp2_probe(struct platform_device *pdev) goto err_axi_clk; /* Initialize ports */ - fwnode_for_each_available_child_node(fwnode, port_fwnode) { + device_for_each_child_node_scoped(&pdev->dev, port_fwnode) { err = mvpp2_port_probe(pdev, port_fwnode, priv); if (err < 0) goto err_port_probe; @@ -7653,8 +7651,6 @@ static int mvpp2_probe(struct platform_device *pdev) return 0; err_port_probe: - fwnode_handle_put(port_fwnode); - for (i = 0; i < priv->port_count; i++) mvpp2_port_remove(priv->port_list[i]); err_axi_clk: From aa9fbc5dd9da9e095a8b1a58540cf20cb06f595f Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 8 Aug 2024 12:41:17 +0100 Subject: [PATCH 053/385] net: mii: constify advertising mask Constify the advertising mask to linkmode functions that only read from the advertising mask. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/linux/mii.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/include/linux/mii.h b/include/linux/mii.h index d5a959ce48778..b8f26d4513c3f 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -140,7 +140,7 @@ static inline u32 ethtool_adv_to_mii_adv_t(u32 ethadv) * settings to phy autonegotiation advertisements for the * MII_ADVERTISE register. */ -static inline u32 linkmode_adv_to_mii_adv_t(unsigned long *advertising) +static inline u32 linkmode_adv_to_mii_adv_t(const unsigned long *advertising) { u32 result = 0; @@ -215,7 +215,8 @@ static inline u32 ethtool_adv_to_mii_ctrl1000_t(u32 ethadv) * settings to phy autonegotiation advertisements for the * MII_CTRL1000 register when in 1000T mode. */ -static inline u32 linkmode_adv_to_mii_ctrl1000_t(unsigned long *advertising) +static inline u32 +linkmode_adv_to_mii_ctrl1000_t(const unsigned long *advertising) { u32 result = 0; @@ -453,7 +454,7 @@ static inline void mii_ctrl1000_mod_linkmode_adv_t(unsigned long *advertising, * A small helper function that translates linkmode advertising to LVL * pause capabilities. */ -static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising) +static inline u32 linkmode_adv_to_lcl_adv_t(const unsigned long *advertising) { u32 lcl_adv = 0; From 6ff3cddc365beae1fbe185fd470cc0b86e895574 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 8 Aug 2024 12:41:22 +0100 Subject: [PATCH 054/385] net: phylib: do not disable autoneg for fixed speeds >= 1G We have an increasing number of drivers that are forcing auto-negotiation to be enabled for speeds of 1G or faster. It would appear that auto-negotiation is mandatory for speeds above 100M. In 802.3, Annex 40C's state diagrams seems to imply that mr_autoneg_enable (BMCR AN ENABLE) doesn't affect whether or not the AN state machines work for 1000base-T, and some PHY datasheets (e.g. Marvell Alaska) state that disabling mr_autoneg_enable leaves AN enabled but forced to 1G full duplex. Other PHY datasheets imply that BMCR AN ENABLE should not be cleared for >= 1G. Thus, this should be handled in phylib rather than in each driver. Rather than erroring out, arrange to implement the Marvell Alaska solution but in software for all PHYs: generate an appropriate single-speed advertisement for the requested speed, and keep AN enabled to the PHY driver. However, to avoid userspace API breakage, continue to report to userspace that we have AN disabled. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 34 +++++++++++++++++++++++++--------- 1 file changed, 25 insertions(+), 9 deletions(-) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 34752a87f98f7..159e71c1c9726 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2108,22 +2108,20 @@ EXPORT_SYMBOL(phy_reset_after_clk_enable); /** * genphy_config_advert - sanitize and advertise auto-negotiation parameters * @phydev: target phy_device struct + * @advert: auto-negotiation parameters to advertise * * Description: Writes MII_ADVERTISE with the appropriate values, * after sanitizing the values to make sure we only advertise * what is supported. Returns < 0 on error, 0 if the PHY's advertisement * hasn't changed, and > 0 if it has changed. */ -static int genphy_config_advert(struct phy_device *phydev) +static int genphy_config_advert(struct phy_device *phydev, + const unsigned long *advert) { int err, bmsr, changed = 0; u32 adv; - /* Only allow advertising what this PHY supports */ - linkmode_and(phydev->advertising, phydev->advertising, - phydev->supported); - - adv = linkmode_adv_to_mii_adv_t(phydev->advertising); + adv = linkmode_adv_to_mii_adv_t(advert); /* Setup standard advertisement */ err = phy_modify_changed(phydev, MII_ADVERTISE, @@ -2146,7 +2144,7 @@ static int genphy_config_advert(struct phy_device *phydev) if (!(bmsr & BMSR_ESTATEN)) return changed; - adv = linkmode_adv_to_mii_ctrl1000_t(phydev->advertising); + adv = linkmode_adv_to_mii_ctrl1000_t(advert); err = phy_modify_changed(phydev, MII_CTRL1000, ADVERTISE_1000FULL | ADVERTISE_1000HALF, @@ -2370,6 +2368,9 @@ EXPORT_SYMBOL(genphy_check_and_restart_aneg); */ int __genphy_config_aneg(struct phy_device *phydev, bool changed) { + __ETHTOOL_DECLARE_LINK_MODE_MASK(fixed_advert); + const struct phy_setting *set; + unsigned long *advert; int err; err = genphy_c45_an_config_eee_aneg(phydev); @@ -2384,10 +2385,25 @@ int __genphy_config_aneg(struct phy_device *phydev, bool changed) else if (err) changed = true; - if (AUTONEG_ENABLE != phydev->autoneg) + if (phydev->autoneg == AUTONEG_ENABLE) { + /* Only allow advertising what this PHY supports */ + linkmode_and(phydev->advertising, phydev->advertising, + phydev->supported); + advert = phydev->advertising; + } else if (phydev->speed < SPEED_1000) { return genphy_setup_forced(phydev); + } else { + linkmode_zero(fixed_advert); + + set = phy_lookup_setting(phydev->speed, phydev->duplex, + phydev->supported, true); + if (set) + linkmode_set_bit(set->bit, fixed_advert); + + advert = fixed_advert; + } - err = genphy_config_advert(phydev); + err = genphy_config_advert(phydev, advert); if (err < 0) /* error */ return err; else if (err) From c4e82c025b3f2561823b4ba7c5f112a2005f442b Mon Sep 17 00:00:00 2001 From: Enguerrand de Ribaucourt Date: Thu, 8 Aug 2024 15:14:21 +0000 Subject: [PATCH 055/385] net: dsa: microchip: ksz9477: split half-duplex monitoring function In order to respect the 80 columns limit, split the half-duplex monitoring function in two. This is just a styling change, no functional change. Signed-off-by: Enguerrand de Ribaucourt Acked-by: Arun Ramadoss Signed-off-by: David S. Miller --- drivers/net/dsa/microchip/ksz9477.c | 91 +++++++++++++++++------------ 1 file changed, 54 insertions(+), 37 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 425e20daf1e92..1e2293aa00dc9 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -427,54 +427,71 @@ void ksz9477_freeze_mib(struct ksz_device *dev, int port, bool freeze) mutex_unlock(&p->mib.cnt_mutex); } -int ksz9477_errata_monitor(struct ksz_device *dev, int port, - u64 tx_late_col) +static int ksz9477_half_duplex_monitor(struct ksz_device *dev, int port, + u64 tx_late_col) { + u8 lue_ctrl; u32 pmavbc; - u8 status; u16 pqm; int ret; - ret = ksz_pread8(dev, port, REG_PORT_STATUS_0, &status); + /* Errata DS80000754 recommends monitoring potential faults in + * half-duplex mode. The switch might not be able to communicate anymore + * in these states. If you see this message, please read the + * errata-sheet for more information: + * https://ww1.microchip.com/downloads/aemDocuments/documents + * /UNG/ProductDocuments/Errata/KSZ9477S-Errata-DS80000754.pdf + * To workaround this issue, half-duplex mode should be avoided. + * A software reset could be implemented to recover from this state. + */ + dev_warn_once(dev->dev, + "Half-duplex detected on port %d, transmission halt may occur\n", + port); + if (tx_late_col != 0) { + /* Transmission halt with late collisions */ + dev_crit_once(dev->dev, + "TX late collisions detected, transmission may be halted on port %d\n", + port); + } + ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &lue_ctrl); if (ret) return ret; - if (!(FIELD_GET(PORT_INTF_SPEED_MASK, status) == PORT_INTF_SPEED_NONE) && - !(status & PORT_INTF_FULL_DUPLEX)) { - /* Errata DS80000754 recommends monitoring potential faults in - * half-duplex mode. The switch might not be able to communicate anymore - * in these states. - * If you see this message, please read the errata-sheet for more information: - * https://ww1.microchip.com/downloads/aemDocuments/documents/UNG/ProductDocuments/Errata/KSZ9477S-Errata-DS80000754.pdf - * To workaround this issue, half-duplex mode should be avoided. - * A software reset could be implemented to recover from this state. - */ - dev_warn_once(dev->dev, - "Half-duplex detected on port %d, transmission halt may occur\n", - port); - if (tx_late_col != 0) { - /* Transmission halt with late collisions */ - dev_crit_once(dev->dev, - "TX late collisions detected, transmission may be halted on port %d\n", - port); - } - ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &status); + if (lue_ctrl & SW_VLAN_ENABLE) { + ret = ksz_pread16(dev, port, REG_PORT_QM_TX_CNT_0__4, &pqm); if (ret) return ret; - if (status & SW_VLAN_ENABLE) { - ret = ksz_pread16(dev, port, REG_PORT_QM_TX_CNT_0__4, &pqm); - if (ret) - return ret; - ret = ksz_read32(dev, REG_PMAVBC, &pmavbc); - if (ret) - return ret; - if ((FIELD_GET(PMAVBC_MASK, pmavbc) <= PMAVBC_MIN) || - (FIELD_GET(PORT_QM_TX_CNT_M, pqm) >= PORT_QM_TX_CNT_MAX)) { - /* Transmission halt with Half-Duplex and VLAN */ - dev_crit_once(dev->dev, - "resources out of limits, transmission may be halted\n"); - } + + ret = ksz_read32(dev, REG_PMAVBC, &pmavbc); + if (ret) + return ret; + + if ((FIELD_GET(PMAVBC_MASK, pmavbc) <= PMAVBC_MIN) || + (FIELD_GET(PORT_QM_TX_CNT_M, pqm) >= PORT_QM_TX_CNT_MAX)) { + /* Transmission halt with Half-Duplex and VLAN */ + dev_crit_once(dev->dev, + "resources out of limits, transmission may be halted\n"); } } + + return ret; +} + +int ksz9477_errata_monitor(struct ksz_device *dev, int port, + u64 tx_late_col) +{ + u8 status; + int ret; + + ret = ksz_pread8(dev, port, REG_PORT_STATUS_0, &status); + if (ret) + return ret; + + if (!(FIELD_GET(PORT_INTF_SPEED_MASK, status) + == PORT_INTF_SPEED_NONE) && + !(status & PORT_INTF_FULL_DUPLEX)) { + ret = ksz9477_half_duplex_monitor(dev, port, tx_late_col); + } + return ret; } From e332a5aba83500e8d422c90d2a84d8a5f888673e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 8 Aug 2024 02:47:28 +0900 Subject: [PATCH 056/385] treewide: remove unnecessary inclusion These files do not use any macros defined in . Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Schier --- drivers/accessibility/speakup/genmap.c | 1 - drivers/accessibility/speakup/makemapdata.c | 1 - drivers/staging/media/atomisp/include/linux/atomisp.h | 1 - samples/trace_events/trace_custom_sched.c | 1 - sound/soc/codecs/cs42l42.c | 1 - 5 files changed, 5 deletions(-) diff --git a/drivers/accessibility/speakup/genmap.c b/drivers/accessibility/speakup/genmap.c index 0125000e00d9a..0882bab10fb87 100644 --- a/drivers/accessibility/speakup/genmap.c +++ b/drivers/accessibility/speakup/genmap.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include "utils.h" diff --git a/drivers/accessibility/speakup/makemapdata.c b/drivers/accessibility/speakup/makemapdata.c index d7d41bb9b05fb..55e4ef8a93dc9 100644 --- a/drivers/accessibility/speakup/makemapdata.c +++ b/drivers/accessibility/speakup/makemapdata.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include "utils.h" diff --git a/drivers/staging/media/atomisp/include/linux/atomisp.h b/drivers/staging/media/atomisp/include/linux/atomisp.h index 16c9da172c031..fefbe3cd08f33 100644 --- a/drivers/staging/media/atomisp/include/linux/atomisp.h +++ b/drivers/staging/media/atomisp/include/linux/atomisp.h @@ -20,7 +20,6 @@ #define _ATOM_ISP_H #include -#include /* struct media_device_info.hw_revision */ #define ATOMISP_HW_REVISION_MASK 0x0000ff00 diff --git a/samples/trace_events/trace_custom_sched.c b/samples/trace_events/trace_custom_sched.c index b99d9ab7db858..dd409b704b35b 100644 --- a/samples/trace_events/trace_custom_sched.c +++ b/samples/trace_events/trace_custom_sched.c @@ -8,7 +8,6 @@ #define pr_fmt(fmt) fmt #include -#include #include #include diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c index 60d366e53526f..6400ac875e6f6 100644 --- a/sound/soc/codecs/cs42l42.c +++ b/sound/soc/codecs/cs42l42.c @@ -11,7 +11,6 @@ #include #include -#include #include #include #include From 1472464c6248575bf2d01c7f076b94704bb32c95 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 8 Aug 2024 03:03:00 +0900 Subject: [PATCH 057/385] kbuild: avoid scripts/kallsyms parsing /dev/null On macOS, as reported by Daniel Gomez, getline() sets ENOTTY to errno if it is requested to read from /dev/null. If this is worth fixing, I would rather pass an empty file to scripts/kallsyms instead of adding the ugly #ifdef __APPLE__. Fixes: c442db3f49f2 ("kbuild: remove PROVIDE() for kallsyms symbols") Reported-by: Daniel Gomez Closes: https://lore.kernel.org/all/20240807-macos-build-support-v1-12-4cd1ded85694@samsung.com/ Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Schier Reviewed-by: Daniel Gomez --- scripts/link-vmlinux.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index f7b2503cdba95..41c68ae3415d5 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -219,7 +219,8 @@ kallsymso= strip_debug= if is_enabled CONFIG_KALLSYMS; then - kallsyms /dev/null .tmp_vmlinux0.kallsyms + truncate -s0 .tmp_vmlinux.kallsyms0.syms + kallsyms .tmp_vmlinux.kallsyms0.syms .tmp_vmlinux0.kallsyms fi if is_enabled CONFIG_KALLSYMS || is_enabled CONFIG_DEBUG_INFO_BTF; then From f547e956dd84a585c6b75d3f52e1a1bb9c36c0e2 Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Fri, 9 Aug 2024 13:55:18 -0700 Subject: [PATCH 058/385] net: sunvnet: use ethtool_sprintf/puts Simpler and allows avoiding manual pointer addition. Signed-off-by: Rosen Penev Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/sunvnet.c | 34 +++++++++--------------------- 1 file changed, 10 insertions(+), 24 deletions(-) diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 2f30715e9b67f..1e887d951a041 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -114,37 +114,23 @@ static void vnet_get_strings(struct net_device *dev, u32 stringset, u8 *buf) { struct vnet *vp = (struct vnet *)netdev_priv(dev); struct vnet_port *port; - char *p = (char *)buf; switch (stringset) { case ETH_SS_STATS: memcpy(buf, ðtool_stats_keys, sizeof(ethtool_stats_keys)); - p += sizeof(ethtool_stats_keys); + buf += sizeof(ethtool_stats_keys); rcu_read_lock(); list_for_each_entry_rcu(port, &vp->port_list, list) { - snprintf(p, ETH_GSTRING_LEN, "p%u.%s-%pM", - port->q_index, port->switch_port ? "s" : "q", - port->raddr); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "p%u.rx_packets", - port->q_index); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "p%u.tx_packets", - port->q_index); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "p%u.rx_bytes", - port->q_index); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "p%u.tx_bytes", - port->q_index); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "p%u.event_up", - port->q_index); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "p%u.event_reset", - port->q_index); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&buf, "p%u.%s-%pM", port->q_index, + port->switch_port ? "s" : "q", + port->raddr); + ethtool_sprintf(&buf, "p%u.rx_packets", port->q_index); + ethtool_sprintf(&buf, "p%u.tx_packets", port->q_index); + ethtool_sprintf(&buf, "p%u.rx_bytes", port->q_index); + ethtool_sprintf(&buf, "p%u.tx_bytes", port->q_index); + ethtool_sprintf(&buf, "p%u.event_up", port->q_index); + ethtool_sprintf(&buf, "p%u.event_reset", port->q_index); } rcu_read_unlock(); break; From 6b8a024d25ebf7535eb4a3e926309aa693cfe1bd Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sat, 10 Aug 2024 10:06:32 +0800 Subject: [PATCH 059/385] net: vxlan: remove duplicated initialization in vxlan_xmit The variable "did_rsc" is initialized twice, which is unnecessary. Just remove one of them. Signed-off-by: Menglong Dong Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/vxlan/vxlan_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index ba59e92ab941d..8983e75e9881d 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2690,11 +2690,11 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *rdst, *fdst = NULL; const struct ip_tunnel_info *info; - bool did_rsc = false; struct vxlan_fdb *f; struct ethhdr *eth; __be32 vni = 0; u32 nhid = 0; + bool did_rsc; info = skb_tunnel_info(skb); From 10fbe8c082fdde74b1f0814bc30e194cf330cdf7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:37:17 -0700 Subject: [PATCH 060/385] selftests: drv-net: rss_ctx: add identifier to traffic comments Include the "name" of the context in the comment for traffic checks. Makes it easier to reason about which context failed when we loop over 32 contexts (it may matter if we failed in first vs last, for example). Reviewed-by: Gal Pressman Reviewed-by: Joe Damato Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- tools/testing/selftests/drivers/net/hw/rss_ctx.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index 011508ca604b0..1da6b214f4fe4 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -90,10 +90,10 @@ def _send_traffic_check(cfg, port, name, params): ksft_ge(directed, 20000, f"traffic on {name}: " + str(cnts)) if params.get('noise'): ksft_lt(sum(cnts[i] for i in params['noise']), directed / 2, - "traffic on other queues:" + str(cnts)) + f"traffic on other queues ({name})':" + str(cnts)) if params.get('empty'): ksft_eq(sum(cnts[i] for i in params['empty']), 0, - "traffic on inactive queues: " + str(cnts)) + f"traffic on inactive queues ({name}): " + str(cnts)) def test_rss_key_indir(cfg): From f203fd85e6669d72fb3bfa3ce485a9642a4a9583 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:37:18 -0700 Subject: [PATCH 061/385] eth: mvpp2: implement new RSS context API Implement the separate create/modify/delete ops for RSS. No problems with IDs - even tho RSS tables are per device the driver already seems to allocate IDs linearly per port. There's a translation table from per-port context ID to device context ID. mvpp2 doesn't have a key for the hash, it defaults to an empty/previous indir table. Note that there is no key at all, so we don't have to be concerned with reporting the wrong one (which is addressed by a patch later in the series). Compile-tested only. Reviewed-by: Edward Cree Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- .../net/ethernet/marvell/mvpp2/mvpp2_cls.c | 18 +--- .../net/ethernet/marvell/mvpp2/mvpp2_cls.h | 2 +- .../net/ethernet/marvell/mvpp2/mvpp2_main.c | 82 +++++++++++++++---- 3 files changed, 69 insertions(+), 33 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c index 40aeaa7bd739f..1641791a2d5b4 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c @@ -1522,29 +1522,19 @@ static int mvpp22_rss_context_create(struct mvpp2_port *port, u32 *rss_ctx) return 0; } -int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 *port_ctx) +int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 port_ctx) { u32 rss_ctx; - int ret, i; + int ret; ret = mvpp22_rss_context_create(port, &rss_ctx); if (ret) return ret; - /* Find the first available context number in the port, starting from 1. - * Context 0 on each port is reserved for the default context. - */ - for (i = 1; i < MVPP22_N_RSS_TABLES; i++) { - if (port->rss_ctx[i] < 0) - break; - } - - if (i == MVPP22_N_RSS_TABLES) + if (WARN_ON_ONCE(port->rss_ctx[port_ctx] >= 0)) return -EINVAL; - port->rss_ctx[i] = rss_ctx; - *port_ctx = i; - + port->rss_ctx[port_ctx] = rss_ctx; return 0; } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h index 663157dc8062b..85c9c6e806789 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h @@ -264,7 +264,7 @@ int mvpp22_port_rss_init(struct mvpp2_port *port); int mvpp22_port_rss_enable(struct mvpp2_port *port); int mvpp22_port_rss_disable(struct mvpp2_port *port); -int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 *rss_ctx); +int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 rss_ctx); int mvpp22_port_rss_ctx_delete(struct mvpp2_port *port, u32 rss_ctx); int mvpp22_port_rss_ctx_indir_set(struct mvpp2_port *port, u32 rss_ctx, diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 216cc7b860d6d..4a7098f5681c1 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5696,40 +5696,82 @@ static int mvpp2_ethtool_get_rxfh(struct net_device *dev, return ret; } -static int mvpp2_ethtool_set_rxfh(struct net_device *dev, - struct ethtool_rxfh_param *rxfh, - struct netlink_ext_ack *extack) +static bool mvpp2_ethtool_rxfh_okay(struct mvpp2_port *port, + const struct ethtool_rxfh_param *rxfh) { - struct mvpp2_port *port = netdev_priv(dev); - u32 *rss_context = &rxfh->rss_context; - int ret = 0; - if (!mvpp22_rss_is_supported(port)) - return -EOPNOTSUPP; + return false; if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE && rxfh->hfunc != ETH_RSS_HASH_CRC32) - return -EOPNOTSUPP; + return false; if (rxfh->key) + return false; + + return true; +} + +static int mvpp2_create_rxfh_context(struct net_device *dev, + struct ethtool_rxfh_context *ctx, + const struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack) +{ + struct mvpp2_port *port = netdev_priv(dev); + int ret = 0; + + if (!mvpp2_ethtool_rxfh_okay(port, rxfh)) return -EOPNOTSUPP; - if (*rss_context && rxfh->rss_delete) - return mvpp22_port_rss_ctx_delete(port, *rss_context); + ctx->hfunc = ETH_RSS_HASH_CRC32; - if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) { - ret = mvpp22_port_rss_ctx_create(port, rss_context); - if (ret) - return ret; - } + ret = mvpp22_port_rss_ctx_create(port, rxfh->rss_context); + if (ret) + return ret; - if (rxfh->indir) - ret = mvpp22_port_rss_ctx_indir_set(port, *rss_context, + if (!rxfh->indir) + ret = mvpp22_port_rss_ctx_indir_get(port, rxfh->rss_context, + ethtool_rxfh_context_indir(ctx)); + else + ret = mvpp22_port_rss_ctx_indir_set(port, rxfh->rss_context, rxfh->indir); + return ret; +} + +static int mvpp2_modify_rxfh_context(struct net_device *dev, + struct ethtool_rxfh_context *ctx, + const struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack) +{ + struct mvpp2_port *port = netdev_priv(dev); + int ret = 0; + + if (!mvpp2_ethtool_rxfh_okay(port, rxfh)) + return -EOPNOTSUPP; + if (rxfh->indir) + ret = mvpp22_port_rss_ctx_indir_set(port, rxfh->rss_context, + rxfh->indir); return ret; } +static int mvpp2_remove_rxfh_context(struct net_device *dev, + struct ethtool_rxfh_context *ctx, + u32 rss_context, + struct netlink_ext_ack *extack) +{ + struct mvpp2_port *port = netdev_priv(dev); + + return mvpp22_port_rss_ctx_delete(port, rss_context); +} + +static int mvpp2_ethtool_set_rxfh(struct net_device *dev, + struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack) +{ + return mvpp2_modify_rxfh_context(dev, NULL, rxfh, extack); +} + /* Device ops */ static const struct net_device_ops mvpp2_netdev_ops = { @@ -5750,6 +5792,7 @@ static const struct net_device_ops mvpp2_netdev_ops = { static const struct ethtool_ops mvpp2_eth_tool_ops = { .cap_rss_ctx_supported = true, + .rxfh_max_num_contexts = MVPP22_N_RSS_TABLES, .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES, .nway_reset = mvpp2_ethtool_nway_reset, @@ -5772,6 +5815,9 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = { .get_rxfh_indir_size = mvpp2_ethtool_get_rxfh_indir_size, .get_rxfh = mvpp2_ethtool_get_rxfh, .set_rxfh = mvpp2_ethtool_set_rxfh, + .create_rxfh_context = mvpp2_create_rxfh_context, + .modify_rxfh_context = mvpp2_modify_rxfh_context, + .remove_rxfh_context = mvpp2_remove_rxfh_context, }; /* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that From a7f6f56f604a396f91d891321edb29f286a80069 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:37:19 -0700 Subject: [PATCH 062/385] eth: mlx5: allow disabling queues when RSS contexts exist Since commit 24ac7e544081 ("ethtool: use the rss context XArray in ring deactivation safety-check") core will prevent queues from being disabled while being used by additional RSS contexts. The safety check is no longer necessary, and core will do a more accurate job of only rejecting changes which can actually break things. Reviewed-by: Gal Pressman Reviewed-by: Joe Damato Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 56bdb4d07b7ad..8af509397f630 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -433,7 +433,6 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, unsigned int count = ch->combined_count; struct mlx5e_params new_params; bool arfs_enabled; - int rss_cnt; bool opened; int err = 0; @@ -487,17 +486,6 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, goto out; } - /* Don't allow changing the number of channels if non-default RSS contexts exist, - * the kernel doesn't protect against set_channels operations that break them. - */ - rss_cnt = mlx5e_rx_res_rss_cnt(priv->rx_res) - 1; - if (rss_cnt) { - err = -EINVAL; - netdev_err(priv->netdev, "%s: Non-default RSS contexts exist (%d), cannot change the number of channels\n", - __func__, rss_cnt); - goto out; - } - /* Don't allow changing the number of channels if MQPRIO mode channel offload is active, * because it defines a partition over the channels queues. */ From ce056504e2e53b22c1f789cff2ad6a0a135dc24d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:37:20 -0700 Subject: [PATCH 063/385] ethtool: make ethtool_ops::cap_rss_ctx_supported optional cap_rss_ctx_supported was created because the API for creating and configuring additional contexts is mux'ed with the normal RSS API. Presence of ops does not imply driver can actually support rss_context != 0 (in fact drivers mostly ignore that field). cap_rss_ctx_supported lets core check that the driver is context-aware before calling it. Now that we have .create_rxfh_context, there is no such ambiguity. We can depend on presence of the op. Make setting the bit optional. Reviewed-by: Gal Pressman Reviewed-by: Edward Cree Reviewed-by: Joe Damato Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/ethtool.h | 3 ++- net/ethtool/ioctl.c | 6 ++++-- net/ethtool/rss.c | 3 ++- 3 files changed, 8 insertions(+), 4 deletions(-) diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 989c94eddb2b4..a149485904d8f 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -727,7 +727,8 @@ struct kernel_ethtool_ts_info { * @cap_link_lanes_supported: indicates if the driver supports lanes * parameter. * @cap_rss_ctx_supported: indicates if the driver supports RSS - * contexts. + * contexts via legacy API, drivers implementing @create_rxfh_context + * do not have to set this bit. * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor * RSS. * @rxfh_indir_space: max size of RSS indirection tables, if indirection table diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index ba8630eb02efe..1698b73812cee 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1227,7 +1227,8 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32) return -EINVAL; /* Most drivers don't handle rss_context, check it's 0 as well */ - if (rxfh.rss_context && !ops->cap_rss_ctx_supported) + if (rxfh.rss_context && !(ops->cap_rss_ctx_supported || + ops->create_rxfh_context)) return -EOPNOTSUPP; rxfh.indir_size = rxfh_dev.indir_size; @@ -1357,7 +1358,8 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32) return -EINVAL; /* Most drivers don't handle rss_context, check it's 0 as well */ - if (rxfh.rss_context && !ops->cap_rss_ctx_supported) + if (rxfh.rss_context && !(ops->cap_rss_ctx_supported || + ops->create_rxfh_context)) return -EOPNOTSUPP; /* Check input data transformation capabilities */ if (rxfh.input_xfrm && rxfh.input_xfrm != RXH_XFRM_SYM_XOR && diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 5c4c4505ab9a4..a06bdac8b8a2a 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -60,7 +60,8 @@ rss_prepare_data(const struct ethnl_req_info *req_base, return -EOPNOTSUPP; /* Some drivers don't handle rss_context */ - if (request->rss_context && !ops->cap_rss_ctx_supported) + if (request->rss_context && !(ops->cap_rss_ctx_supported || + ops->create_rxfh_context)) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); From fb770fe7584fb855620216193a34c6fb81830aa6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:37:21 -0700 Subject: [PATCH 064/385] eth: remove .cap_rss_ctx_supported from updated drivers Remove .cap_rss_ctx_supported from drivers which moved to the new API. This makes it easy to grep for drivers which still need to be converted. Reviewed-by: Gal Pressman Reviewed-by: Edward Cree Reviewed-by: Joe Damato Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 1 - drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 1 - drivers/net/ethernet/sfc/ef100_ethtool.c | 1 - drivers/net/ethernet/sfc/ethtool.c | 1 - 4 files changed, 4 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 9dadc89378f02..44076e4ebf1a7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -5289,7 +5289,6 @@ void bnxt_ethtool_free(struct bnxt *bp) const struct ethtool_ops bnxt_ethtool_ops = { .cap_link_lanes_supported = 1, - .cap_rss_ctx_supported = 1, .rxfh_max_num_contexts = BNXT_MAX_ETH_RSS_CTX + 1, .rxfh_indir_space = BNXT_MAX_RSS_TABLE_ENTRIES_P5, .rxfh_priv_size = sizeof(struct bnxt_rss_ctx), diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 4a7098f5681c1..2fe8bae4eb3c0 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5791,7 +5791,6 @@ static const struct net_device_ops mvpp2_netdev_ops = { }; static const struct ethtool_ops mvpp2_eth_tool_ops = { - .cap_rss_ctx_supported = true, .rxfh_max_num_contexts = MVPP22_N_RSS_TABLES, .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES, diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.c b/drivers/net/ethernet/sfc/ef100_ethtool.c index 896ffca4aee2b..746b5314acb54 100644 --- a/drivers/net/ethernet/sfc/ef100_ethtool.c +++ b/drivers/net/ethernet/sfc/ef100_ethtool.c @@ -37,7 +37,6 @@ ef100_ethtool_get_ringparam(struct net_device *net_dev, /* Ethtool options available */ const struct ethtool_ops ef100_ethtool_ops = { - .cap_rss_ctx_supported = true, .get_drvinfo = efx_ethtool_get_drvinfo, .get_msglevel = efx_ethtool_get_msglevel, .set_msglevel = efx_ethtool_set_msglevel, diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index 7c887160e2ef8..15245720c9496 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -240,7 +240,6 @@ static int efx_ethtool_get_ts_info(struct net_device *net_dev, } const struct ethtool_ops efx_ethtool_ops = { - .cap_rss_ctx_supported = true, .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USECS_IRQ | ETHTOOL_COALESCE_USE_ADAPTIVE_RX, From ec6e57beaf8bc64ea0c2dc0cc360afcc7f504425 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:37:22 -0700 Subject: [PATCH 065/385] ethtool: rss: don't report key if device doesn't support it marvell/otx2 and mvpp2 do not support setting different keys for different RSS contexts. Contexts have separate indirection tables but key is shared with all other contexts. This is likely fine, indirection table is the most important piece. Don't report the key-related parameters from such drivers. This prevents driver-errors, e.g. otx2 always writes the main key, even when user asks to change per-context key. The second reason is that without this change tracking the keys by the core gets complicated. Even if the driver correctly reject setting key with rss_context != 0, change of the main key would have to be reflected in the XArray for all additional contexts. Since the additional contexts don't have their own keys not including the attributes (in Netlink speak) seems intuitive. ethtool CLI seems to deal with it just fine. Having to set the flag in majority of the drivers is a bit tedious but not reporting the key is a safer default. Reviewed-by: Edward Cree Reviewed-by: Joe Damato Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 1 + drivers/net/ethernet/intel/ice/ice_ethtool.c | 1 + .../ethernet/mellanox/mlx5/core/en_ethtool.c | 1 + drivers/net/ethernet/sfc/ef100_ethtool.c | 1 + drivers/net/ethernet/sfc/ethtool.c | 1 + include/linux/ethtool.h | 4 +++ net/ethtool/ioctl.c | 25 ++++++++++++++++--- net/ethtool/rss.c | 21 +++++++++++----- 8 files changed, 45 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 44076e4ebf1a7..61d6afc3cacb7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -5289,6 +5289,7 @@ void bnxt_ethtool_free(struct bnxt *bp) const struct ethtool_ops bnxt_ethtool_ops = { .cap_link_lanes_supported = 1, + .rxfh_per_ctx_key = 1, .rxfh_max_num_contexts = BNXT_MAX_ETH_RSS_CTX + 1, .rxfh_indir_space = BNXT_MAX_RSS_TABLE_ENTRIES_P5, .rxfh_priv_size = sizeof(struct bnxt_rss_ctx), diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index bc79ba974e495..c7641d326ba54 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -4725,6 +4725,7 @@ static const struct ethtool_ops ice_ethtool_ops = { ETHTOOL_COALESCE_USE_ADAPTIVE | ETHTOOL_COALESCE_RX_USECS_HIGH, .cap_rss_sym_xor_supported = true, + .rxfh_per_ctx_key = true, .get_link_ksettings = ice_get_link_ksettings, .set_link_ksettings = ice_set_link_ksettings, .get_fec_stats = ice_get_fec_stats, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 8af509397f630..4d123dae912c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -2595,6 +2595,7 @@ static void mlx5e_get_ts_stats(struct net_device *netdev, const struct ethtool_ops mlx5e_ethtool_ops = { .cap_rss_ctx_supported = true, + .rxfh_per_ctx_key = true, .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES | ETHTOOL_COALESCE_USE_ADAPTIVE | diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.c b/drivers/net/ethernet/sfc/ef100_ethtool.c index 746b5314acb54..5c2551369812c 100644 --- a/drivers/net/ethernet/sfc/ef100_ethtool.c +++ b/drivers/net/ethernet/sfc/ef100_ethtool.c @@ -58,6 +58,7 @@ const struct ethtool_ops ef100_ethtool_ops = { .get_rxfh_indir_size = efx_ethtool_get_rxfh_indir_size, .get_rxfh_key_size = efx_ethtool_get_rxfh_key_size, + .rxfh_per_ctx_key = true, .rxfh_priv_size = sizeof(struct efx_rss_context_priv), .get_rxfh = efx_ethtool_get_rxfh, .set_rxfh = efx_ethtool_set_rxfh, diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index 15245720c9496..848b1923133a7 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -267,6 +267,7 @@ const struct ethtool_ops efx_ethtool_ops = { .set_rxnfc = efx_ethtool_set_rxnfc, .get_rxfh_indir_size = efx_ethtool_get_rxfh_indir_size, .get_rxfh_key_size = efx_ethtool_get_rxfh_key_size, + .rxfh_per_ctx_key = true, .rxfh_priv_size = sizeof(struct efx_rss_context_priv), .get_rxfh = efx_ethtool_get_rxfh, .set_rxfh = efx_ethtool_set_rxfh, diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index a149485904d8f..12f6dc5675987 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -731,6 +731,9 @@ struct kernel_ethtool_ts_info { * do not have to set this bit. * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor * RSS. + * @rxfh_per_ctx_key: device supports setting different RSS key for each + * additional context. Netlink API should report hfunc, key, and input_xfrm + * for every context, not just context 0. * @rxfh_indir_space: max size of RSS indirection tables, if indirection table * size as returned by @get_rxfh_indir_size may change during lifetime * of the device. Leave as 0 if the table size is constant. @@ -952,6 +955,7 @@ struct ethtool_ops { u32 cap_link_lanes_supported:1; u32 cap_rss_ctx_supported:1; u32 cap_rss_sym_xor_supported:1; + u32 rxfh_per_ctx_key:1; u32 rxfh_indir_space; u16 rxfh_key_space; u16 rxfh_priv_size; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 1698b73812cee..18cf9fa32ae3d 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1261,10 +1261,15 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, if (rxfh_dev.indir) memcpy(rxfh_dev.indir, ethtool_rxfh_context_indir(ctx), indir_bytes); - if (rxfh_dev.key) - memcpy(rxfh_dev.key, ethtool_rxfh_context_key(ctx), - user_key_size); - rxfh_dev.hfunc = ctx->hfunc; + if (!ops->rxfh_per_ctx_key) { + rxfh_dev.key_size = 0; + } else { + if (rxfh_dev.key) + memcpy(rxfh_dev.key, + ethtool_rxfh_context_key(ctx), + user_key_size); + rxfh_dev.hfunc = ctx->hfunc; + } rxfh_dev.input_xfrm = ctx->input_xfrm; ret = 0; } else { @@ -1281,6 +1286,11 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, &rxfh_dev.input_xfrm, sizeof(rxfh.input_xfrm))) { ret = -EFAULT; + } else if (copy_to_user(useraddr + + offsetof(struct ethtool_rxfh, key_size), + &rxfh_dev.key_size, + sizeof(rxfh.key_size))) { + ret = -EFAULT; } else if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, rss_config[0]), rss_config, total_size)) { @@ -1389,6 +1399,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]); + /* Check settings which may be global rather than per RSS-context */ + if (rxfh.rss_context && !ops->rxfh_per_ctx_key) + if (rxfh.key_size || + (rxfh.hfunc && rxfh.hfunc != ETH_RSS_HASH_NO_CHANGE) || + (rxfh.input_xfrm && rxfh.input_xfrm != RXH_XFRM_NO_CHANGE)) + return -EOPNOTSUPP; + rss_config = kzalloc(indir_bytes + dev_key_size, GFP_USER); if (!rss_config) return -ENOMEM; diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index a06bdac8b8a2a..cd8100d819196 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -10,6 +10,7 @@ struct rss_req_info { struct rss_reply_data { struct ethnl_reply_data base; + bool no_key_fields; u32 indir_size; u32 hkey_size; u32 hfunc; @@ -60,9 +61,12 @@ rss_prepare_data(const struct ethnl_req_info *req_base, return -EOPNOTSUPP; /* Some drivers don't handle rss_context */ - if (request->rss_context && !(ops->cap_rss_ctx_supported || - ops->create_rxfh_context)) - return -EOPNOTSUPP; + if (request->rss_context) { + if (!ops->cap_rss_ctx_supported && !ops->create_rxfh_context) + return -EOPNOTSUPP; + + data->no_key_fields = !ops->rxfh_per_ctx_key; + } ret = ethnl_ops_begin(dev); if (ret < 0) @@ -132,13 +136,18 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, nla_put_u32(skb, ETHTOOL_A_RSS_CONTEXT, request->rss_context)) return -EMSGSIZE; + if ((data->indir_size && + nla_put(skb, ETHTOOL_A_RSS_INDIR, + sizeof(u32) * data->indir_size, data->indir_table))) + return -EMSGSIZE; + + if (data->no_key_fields) + return 0; + if ((data->hfunc && nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) || (data->input_xfrm && nla_put_u32(skb, ETHTOOL_A_RSS_INPUT_XFRM, data->input_xfrm)) || - (data->indir_size && - nla_put(skb, ETHTOOL_A_RSS_INDIR, - sizeof(u32) * data->indir_size, data->indir_table)) || (data->hkey_size && nla_put(skb, ETHTOOL_A_RSS_HKEY, data->hkey_size, data->hkey))) return -EMSGSIZE; From a7ddfd5d57036caaaf2e1e896ff7aeed6530a0ca Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:37:23 -0700 Subject: [PATCH 066/385] ethtool: rss: move the device op invocation out of rss_prepare_data() Factor calling device ops out of rss_prepare_data(). Next patch will add alternative path using xarray. No functional changes. Reviewed-by: Joe Damato Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- net/ethtool/rss.c | 43 +++++++++++++++++++++++++++---------------- 1 file changed, 27 insertions(+), 16 deletions(-) diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index cd8100d819196..5c477cc36251e 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -43,13 +43,9 @@ rss_parse_request(struct ethnl_req_info *req_info, struct nlattr **tb, } static int -rss_prepare_data(const struct ethnl_req_info *req_base, - struct ethnl_reply_data *reply_base, - const struct genl_info *info) +rss_prepare_get(const struct rss_req_info *request, struct net_device *dev, + struct rss_reply_data *data, const struct genl_info *info) { - struct rss_reply_data *data = RSS_REPDATA(reply_base); - struct rss_req_info *request = RSS_REQINFO(req_base); - struct net_device *dev = reply_base->dev; struct ethtool_rxfh_param rxfh = {}; const struct ethtool_ops *ops; u32 total_size, indir_bytes; @@ -57,16 +53,6 @@ rss_prepare_data(const struct ethnl_req_info *req_base, int ret; ops = dev->ethtool_ops; - if (!ops->get_rxfh) - return -EOPNOTSUPP; - - /* Some drivers don't handle rss_context */ - if (request->rss_context) { - if (!ops->cap_rss_ctx_supported && !ops->create_rxfh_context) - return -EOPNOTSUPP; - - data->no_key_fields = !ops->rxfh_per_ctx_key; - } ret = ethnl_ops_begin(dev); if (ret < 0) @@ -109,6 +95,31 @@ rss_prepare_data(const struct ethnl_req_info *req_base, return ret; } +static int +rss_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + const struct genl_info *info) +{ + struct rss_reply_data *data = RSS_REPDATA(reply_base); + struct rss_req_info *request = RSS_REQINFO(req_base); + struct net_device *dev = reply_base->dev; + const struct ethtool_ops *ops; + + ops = dev->ethtool_ops; + if (!ops->get_rxfh) + return -EOPNOTSUPP; + + /* Some drivers don't handle rss_context */ + if (request->rss_context) { + if (!ops->cap_rss_ctx_supported && !ops->create_rxfh_context) + return -EOPNOTSUPP; + + data->no_key_fields = !ops->rxfh_per_ctx_key; + } + + return rss_prepare_get(request, dev, data, info); +} + static int rss_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) From bb87f2c7968eaebafa130f0618dea554700bb74b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:37:24 -0700 Subject: [PATCH 067/385] ethtool: rss: report info about additional contexts from XArray IOCTL already uses the XArray when reporting info about additional contexts. Do the same thing in netlink code. Reviewed-by: Edward Cree Reviewed-by: Joe Damato Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- net/ethtool/rss.c | 37 ++++++++++++++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-) diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 5c477cc36251e..023782ca1230d 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -82,7 +82,6 @@ rss_prepare_get(const struct rss_req_info *request, struct net_device *dev, rxfh.indir = data->indir_table; rxfh.key_size = data->hkey_size; rxfh.key = data->hkey; - rxfh.rss_context = request->rss_context; ret = ops->get_rxfh(dev, &rxfh); if (ret) @@ -95,6 +94,41 @@ rss_prepare_get(const struct rss_req_info *request, struct net_device *dev, return ret; } +static int +rss_prepare_ctx(const struct rss_req_info *request, struct net_device *dev, + struct rss_reply_data *data, const struct genl_info *info) +{ + struct ethtool_rxfh_context *ctx; + u32 total_size, indir_bytes; + u8 *rss_config; + + ctx = xa_load(&dev->ethtool->rss_ctx, request->rss_context); + if (!ctx) + return -ENOENT; + + data->indir_size = ctx->indir_size; + data->hkey_size = ctx->key_size; + data->hfunc = ctx->hfunc; + data->input_xfrm = ctx->input_xfrm; + + indir_bytes = data->indir_size * sizeof(u32); + total_size = indir_bytes + data->hkey_size; + rss_config = kzalloc(total_size, GFP_KERNEL); + if (!rss_config) + return -ENOMEM; + + data->indir_table = (u32 *)rss_config; + memcpy(data->indir_table, ethtool_rxfh_context_indir(ctx), indir_bytes); + + if (data->hkey_size) { + data->hkey = rss_config + indir_bytes; + memcpy(data->hkey, ethtool_rxfh_context_key(ctx), + data->hkey_size); + } + + return 0; +} + static int rss_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, @@ -115,6 +149,7 @@ rss_prepare_data(const struct ethnl_req_info *req_base, return -EOPNOTSUPP; data->no_key_fields = !ops->rxfh_per_ctx_key; + return rss_prepare_ctx(request, dev, data, info); } return rss_prepare_get(request, dev, data, info); From f6122900f4e28bfcb8abc76e1f7b83a1e0d8afd3 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:37:25 -0700 Subject: [PATCH 068/385] ethtool: rss: support dumping RSS contexts Now that we track RSS contexts in the core we can easily dump them. This is a major introspection improvement, as previously the only way to find all contexts would be to try all ids (of which there may be 2^32 - 1). Don't use the XArray iterators (like xa_for_each_start()) as they do not move the index past the end of the array once done, which caused multiple bugs in Netlink dumps in the past. Reviewed-by: Edward Cree Reviewed-by: Joe Damato Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- Documentation/netlink/specs/ethtool.yaml | 9 +- net/ethtool/netlink.c | 2 + net/ethtool/netlink.h | 2 + net/ethtool/rss.c | 135 +++++++++++++++++++++++ 4 files changed, 146 insertions(+), 2 deletions(-) diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index ea21fe135b97e..cf69eedae51d2 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -1749,12 +1749,12 @@ operations: attribute-set: rss - do: &rss-get-op + do: request: attributes: - header - context - reply: + reply: &rss-reply attributes: - header - context @@ -1762,6 +1762,11 @@ operations: - indir - hkey - input_xfrm + dump: + request: + attributes: + - header + reply: *rss-reply - name: plca-get-cfg doc: Get PLCA params. diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index cb1eea00e3498..041548e5f5e64 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -1128,6 +1128,8 @@ static const struct genl_ops ethtool_genl_ops[] = { { .cmd = ETHTOOL_MSG_RSS_GET, .doit = ethnl_default_doit, + .start = ethnl_rss_dump_start, + .dumpit = ethnl_rss_dumpit, .policy = ethnl_rss_get_policy, .maxattr = ARRAY_SIZE(ethnl_rss_get_policy) - 1, }, diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 46ec273a87c5c..919371383b235 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -464,6 +464,8 @@ int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_start(struct netlink_callback *cb); int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int ethnl_act_module_fw_flash(struct sk_buff *skb, struct genl_info *info); +int ethnl_rss_dump_start(struct netlink_callback *cb); +int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 023782ca1230d..2865720ff583d 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -208,6 +208,141 @@ static void rss_cleanup_data(struct ethnl_reply_data *reply_base) kfree(data->indir_table); } +struct rss_nl_dump_ctx { + unsigned long ifindex; + unsigned long ctx_idx; + + /* User wants to only dump contexts from given ifindex */ + unsigned int match_ifindex; +}; + +static struct rss_nl_dump_ctx *rss_dump_ctx(struct netlink_callback *cb) +{ + NL_ASSERT_DUMP_CTX_FITS(struct rss_nl_dump_ctx); + + return (struct rss_nl_dump_ctx *)cb->ctx; +} + +int ethnl_rss_dump_start(struct netlink_callback *cb) +{ + const struct genl_info *info = genl_info_dump(cb); + struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb); + struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; + int ret; + + /* Filtering by context not supported */ + if (tb[ETHTOOL_A_RSS_CONTEXT]) { + NL_SET_BAD_ATTR(info->extack, tb[ETHTOOL_A_RSS_CONTEXT]); + return -EINVAL; + } + + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_RSS_HEADER], + sock_net(cb->skb->sk), cb->extack, + false); + if (req_info.dev) { + ctx->match_ifindex = req_info.dev->ifindex; + ctx->ifindex = ctx->match_ifindex; + ethnl_parse_header_dev_put(&req_info); + req_info.dev = NULL; + } + + return ret; +} + +static int +rss_dump_one_ctx(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev, u32 rss_context) +{ + const struct genl_info *info = genl_info_dump(cb); + struct rss_reply_data data = {}; + struct rss_req_info req = {}; + void *ehdr; + int ret; + + req.rss_context = rss_context; + + ehdr = ethnl_dump_put(skb, cb, ETHTOOL_MSG_RSS_GET_REPLY); + if (!ehdr) + return -EMSGSIZE; + + ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_RSS_HEADER); + if (ret < 0) + goto err_cancel; + + /* Context 0 is not currently storred or cached in the XArray */ + if (!rss_context) + ret = rss_prepare_get(&req, dev, &data, info); + else + ret = rss_prepare_ctx(&req, dev, &data, info); + if (ret) + goto err_cancel; + + ret = rss_fill_reply(skb, &req.base, &data.base); + if (ret) + goto err_cleanup; + genlmsg_end(skb, ehdr); + + rss_cleanup_data(&data.base); + return 0; + +err_cleanup: + rss_cleanup_data(&data.base); +err_cancel: + genlmsg_cancel(skb, ehdr); + return ret; +} + +static int +rss_dump_one_dev(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev) +{ + struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb); + int ret; + + if (!dev->ethtool_ops->get_rxfh) + return 0; + + if (!ctx->ctx_idx) { + ret = rss_dump_one_ctx(skb, cb, dev, 0); + if (ret) + return ret; + ctx->ctx_idx++; + } + + for (; xa_find(&dev->ethtool->rss_ctx, &ctx->ctx_idx, + ULONG_MAX, XA_PRESENT); ctx->ctx_idx++) { + ret = rss_dump_one_ctx(skb, cb, dev, ctx->ctx_idx); + if (ret) + return ret; + } + ctx->ctx_idx = 0; + + return 0; +} + +int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb); + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + for_each_netdev_dump(net, dev, ctx->ifindex) { + if (ctx->match_ifindex && ctx->match_ifindex != ctx->ifindex) + break; + + ret = rss_dump_one_dev(skb, cb, dev); + if (ret) + break; + } + rtnl_unlock(); + + return ret; +} + const struct ethnl_request_ops ethnl_rss_request_ops = { .request_cmd = ETHTOOL_MSG_RSS_GET, .reply_cmd = ETHTOOL_MSG_RSS_GET_REPLY, From 3d50c66c0609c8b64fb22e9c188fca88f34e7c98 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:37:26 -0700 Subject: [PATCH 069/385] ethtool: rss: support skipping contexts during dump Applications may want to deal with dynamic RSS contexts only. So dumping context 0 will be counter-productive for them. Support starting the dump from a given context ID. Alternative would be to implement a dump flag to skip just context 0, not sure which is better... Reviewed-by: Edward Cree Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- Documentation/netlink/specs/ethtool.yaml | 4 ++++ Documentation/networking/ethtool-netlink.rst | 12 ++++++++++-- include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/netlink.h | 2 +- net/ethtool/rss.c | 12 +++++++++++- 5 files changed, 27 insertions(+), 4 deletions(-) diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index cf69eedae51d2..4c2334c213b00 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -1028,6 +1028,9 @@ attribute-sets: - name: input_xfrm type: u32 + - + name: start-context + type: u32 - name: plca attributes: @@ -1766,6 +1769,7 @@ operations: request: attributes: - header + - start-context reply: *rss-reply - name: plca-get-cfg diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d5f246aceb9f4..82c5542c80ce3 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1866,10 +1866,18 @@ RSS context of an interface similar to ``ETHTOOL_GRSSH`` ioctl request. Request contents: -===================================== ====== ========================== +===================================== ====== ============================ ``ETHTOOL_A_RSS_HEADER`` nested request header ``ETHTOOL_A_RSS_CONTEXT`` u32 context number -===================================== ====== ========================== + ``ETHTOOL_A_RSS_START_CONTEXT`` u32 start context number (dumps) +===================================== ====== ============================ + +``ETHTOOL_A_RSS_CONTEXT`` specifies which RSS context number to query, +if not set context 0 (the main context) is queried. Dumps can be filtered +by device (only listing contexts of a given netdev). Filtering single +context number is not supported but ``ETHTOOL_A_RSS_START_CONTEXT`` +can be used to start dumping context from the given number (primarily +used to ignore context 0s and only dump additional contexts). Kernel response contents: diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 6d5bdcc67631a..93c57525a9753 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -965,6 +965,7 @@ enum { ETHTOOL_A_RSS_INDIR, /* binary */ ETHTOOL_A_RSS_HKEY, /* binary */ ETHTOOL_A_RSS_INPUT_XFRM, /* u32 */ + ETHTOOL_A_RSS_START_CONTEXT, /* u32 */ __ETHTOOL_A_RSS_CNT, ETHTOOL_A_RSS_MAX = (__ETHTOOL_A_RSS_CNT - 1), diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 919371383b235..236c189fc9688 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -449,7 +449,7 @@ extern const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + extern const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1]; extern const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1]; extern const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1]; -extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_CONTEXT + 1]; +extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_START_CONTEXT + 1]; extern const struct nla_policy ethnl_plca_get_cfg_policy[ETHTOOL_A_PLCA_HEADER + 1]; extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1]; extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1]; diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 2865720ff583d..e07386275e142 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -28,6 +28,7 @@ struct rss_reply_data { const struct nla_policy ethnl_rss_get_policy[] = { [ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_RSS_CONTEXT] = { .type = NLA_U32 }, + [ETHTOOL_A_RSS_START_CONTEXT] = { .type = NLA_U32 }, }; static int @@ -38,6 +39,10 @@ rss_parse_request(struct ethnl_req_info *req_info, struct nlattr **tb, if (tb[ETHTOOL_A_RSS_CONTEXT]) request->rss_context = nla_get_u32(tb[ETHTOOL_A_RSS_CONTEXT]); + if (tb[ETHTOOL_A_RSS_START_CONTEXT]) { + NL_SET_BAD_ATTR(extack, tb[ETHTOOL_A_RSS_START_CONTEXT]); + return -EINVAL; + } return 0; } @@ -214,6 +219,7 @@ struct rss_nl_dump_ctx { /* User wants to only dump contexts from given ifindex */ unsigned int match_ifindex; + unsigned int start_ctx; }; static struct rss_nl_dump_ctx *rss_dump_ctx(struct netlink_callback *cb) @@ -236,6 +242,10 @@ int ethnl_rss_dump_start(struct netlink_callback *cb) NL_SET_BAD_ATTR(info->extack, tb[ETHTOOL_A_RSS_CONTEXT]); return -EINVAL; } + if (tb[ETHTOOL_A_RSS_START_CONTEXT]) { + ctx->start_ctx = nla_get_u32(tb[ETHTOOL_A_RSS_START_CONTEXT]); + ctx->ctx_idx = ctx->start_ctx; + } ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_RSS_HEADER], @@ -317,7 +327,7 @@ rss_dump_one_dev(struct sk_buff *skb, struct netlink_callback *cb, if (ret) return ret; } - ctx->ctx_idx = 0; + ctx->ctx_idx = ctx->start_ctx; return 0; } From 8ad3be135212a99fe16961de0e6d7d0ddd8268a2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:37:27 -0700 Subject: [PATCH 070/385] netlink: specs: decode indirection table as u32 array Indirection table is dumped as a raw u32 array, decode it. It's tempting to decode hash key, too, but it is an actual bitstream, so leave it be for now. Signed-off-by: Jakub Kicinski Reviewed-by: Donald Hunter Signed-off-by: David S. Miller --- Documentation/netlink/specs/ethtool.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 4c2334c213b00..1bbeaba5c6442 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -1022,6 +1022,7 @@ attribute-sets: - name: indir type: binary + sub-type: u32 - name: hkey type: binary From c1ad8ef804e40fc1ef3cb008e0113d76f4acc1a0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:37:28 -0700 Subject: [PATCH 071/385] selftests: drv-net: rss_ctx: test dumping RSS contexts Add a test for dumping RSS contexts. Make sure indir table and key are sane when contexts are created with various combination of inputs. Test the dump filtering by ifname and start-context. Reviewed-by: Petr Machata Reviewed-by: Edward Cree Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- .../selftests/drivers/net/hw/rss_ctx.py | 76 ++++++++++++++++++- tools/testing/selftests/net/lib/py/ksft.py | 6 ++ 2 files changed, 80 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index 1da6b214f4fe4..9d7adb3cf33b9 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -3,7 +3,7 @@ import datetime import random -from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ge, ksft_lt +from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ne, ksft_ge, ksft_lt from lib.py import NetDrvEpEnv from lib.py import EthtoolFamily, NetdevFamily from lib.py import KsftSkipEx @@ -302,6 +302,78 @@ def test_hitless_key_update(cfg): ksft_eq(carrier1 - carrier0, 0) +def test_rss_context_dump(cfg): + """ + Test dumping RSS contexts. This tests mostly exercises the kernel APIs. + """ + + # Get a random key of the right size + data = get_rss(cfg) + if 'rss-hash-key' in data: + key_data = _rss_key_rand(len(data['rss-hash-key'])) + key = _rss_key_str(key_data) + else: + key_data = [] + key = "ba:ad" + + ids = [] + try: + ids.append(ethtool_create(cfg, "-X", f"context new")) + defer(ethtool, f"-X {cfg.ifname} context {ids[-1]} delete") + + ids.append(ethtool_create(cfg, "-X", f"context new weight 1 1")) + defer(ethtool, f"-X {cfg.ifname} context {ids[-1]} delete") + + ids.append(ethtool_create(cfg, "-X", f"context new hkey {key}")) + defer(ethtool, f"-X {cfg.ifname} context {ids[-1]} delete") + except CmdExitFailure: + if not ids: + raise KsftSkipEx("Unable to add any contexts") + ksft_pr(f"Added only {len(ids)} out of 3 contexts") + + expect_tuples = set([(cfg.ifname, -1)] + [(cfg.ifname, ctx_id) for ctx_id in ids]) + + # Dump all + ctxs = cfg.ethnl.rss_get({}, dump=True) + tuples = [(c['header']['dev-name'], c.get('context', -1)) for c in ctxs] + ksft_eq(len(tuples), len(set(tuples)), "duplicates in context dump") + ctx_tuples = set([ctx for ctx in tuples if ctx[0] == cfg.ifname]) + ksft_eq(expect_tuples, ctx_tuples) + + # Sanity-check the results + for data in ctxs: + ksft_ne(set(data['indir']), {0}, "indir table is all zero") + ksft_ne(set(data.get('hkey', [1])), {0}, "key is all zero") + + # More specific checks + if len(ids) > 1 and data.get('context') == ids[1]: + ksft_eq(set(data['indir']), {0, 1}, + "ctx1 - indir table mismatch") + if len(ids) > 2 and data.get('context') == ids[2]: + ksft_eq(data['hkey'], bytes(key_data), "ctx2 - key mismatch") + + # Ifindex filter + ctxs = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}}, dump=True) + tuples = [(c['header']['dev-name'], c.get('context', -1)) for c in ctxs] + ctx_tuples = set(tuples) + ksft_eq(len(tuples), len(ctx_tuples), "duplicates in context dump") + ksft_eq(expect_tuples, ctx_tuples) + + # Skip ctx 0 + expect_tuples.remove((cfg.ifname, -1)) + + ctxs = cfg.ethnl.rss_get({'start-context': 1}, dump=True) + tuples = [(c['header']['dev-name'], c.get('context', -1)) for c in ctxs] + ksft_eq(len(tuples), len(set(tuples)), "duplicates in context dump") + ctx_tuples = set([ctx for ctx in tuples if ctx[0] == cfg.ifname]) + ksft_eq(expect_tuples, ctx_tuples) + + # And finally both with ifindex and skip main + ctxs = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}, 'start-context': 1}, dump=True) + ctx_tuples = set([(c['header']['dev-name'], c.get('context', -1)) for c in ctxs]) + ksft_eq(expect_tuples, ctx_tuples) + + def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None): """ Test separating traffic into RSS contexts. @@ -542,7 +614,7 @@ def main() -> None: ksft_run([test_rss_key_indir, test_rss_queue_reconfigure, test_rss_resize, test_hitless_key_update, test_rss_context, test_rss_context4, test_rss_context32, - test_rss_context_queue_reconfigure, + test_rss_context_dump, test_rss_context_queue_reconfigure, test_rss_context_overlap, test_rss_context_overlap2, test_rss_context_out_of_order, test_rss_context4_create_with_cfg], args=(cfg, )) diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index f663e0daec0db..477ae76de93de 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -55,6 +55,12 @@ def ksft_eq(a, b, comment=""): _fail("Check failed", a, "!=", b, comment) +def ksft_ne(a, b, comment=""): + global KSFT_RESULT + if a == b: + _fail("Check failed", a, "==", b, comment) + + def ksft_true(a, comment=""): if not a: _fail("Check failed", a, "does not eval to True", comment) From 45d84008ccbe2592206c110bd526c7dc140f7bd8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 9 Aug 2024 22:43:21 -0700 Subject: [PATCH 072/385] eth: fbnic: add basic rtnl stats Count packets, bytes and drop on the datapath, and report to the user. Since queues are completely freed when the device is down - accumulate the stats in the main netdev struct. This means that per-queue stats will only report values since last reset (per qstat recommendation). Reviewed-by: Joe Damato Link: https://patch.msgid.link/20240810054322.2766421-2-kuba@kernel.org Signed-off-by: Jakub Kicinski --- .../net/ethernet/meta/fbnic/fbnic_netdev.c | 69 +++++++++++++++++++ .../net/ethernet/meta/fbnic/fbnic_netdev.h | 3 + drivers/net/ethernet/meta/fbnic/fbnic_txrx.c | 51 +++++++++++++- drivers/net/ethernet/meta/fbnic/fbnic_txrx.h | 10 +++ 4 files changed, 132 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c index b7ce6da685433..a048e4a617eb8 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c @@ -316,6 +316,74 @@ void fbnic_clear_rx_mode(struct net_device *netdev) __dev_mc_unsync(netdev, NULL); } +static void fbnic_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats64) +{ + u64 tx_bytes, tx_packets, tx_dropped = 0; + u64 rx_bytes, rx_packets, rx_dropped = 0; + struct fbnic_net *fbn = netdev_priv(dev); + struct fbnic_queue_stats *stats; + unsigned int start, i; + + stats = &fbn->tx_stats; + + tx_bytes = stats->bytes; + tx_packets = stats->packets; + tx_dropped = stats->dropped; + + stats64->tx_bytes = tx_bytes; + stats64->tx_packets = tx_packets; + stats64->tx_dropped = tx_dropped; + + for (i = 0; i < fbn->num_tx_queues; i++) { + struct fbnic_ring *txr = fbn->tx[i]; + + if (!txr) + continue; + + stats = &txr->stats; + do { + start = u64_stats_fetch_begin(&stats->syncp); + tx_bytes = stats->bytes; + tx_packets = stats->packets; + tx_dropped = stats->dropped; + } while (u64_stats_fetch_retry(&stats->syncp, start)); + + stats64->tx_bytes += tx_bytes; + stats64->tx_packets += tx_packets; + stats64->tx_dropped += tx_dropped; + } + + stats = &fbn->rx_stats; + + rx_bytes = stats->bytes; + rx_packets = stats->packets; + rx_dropped = stats->dropped; + + stats64->rx_bytes = rx_bytes; + stats64->rx_packets = rx_packets; + stats64->rx_dropped = rx_dropped; + + for (i = 0; i < fbn->num_rx_queues; i++) { + struct fbnic_ring *rxr = fbn->rx[i]; + + if (!rxr) + continue; + + stats = &rxr->stats; + do { + start = u64_stats_fetch_begin(&stats->syncp); + rx_bytes = stats->bytes; + rx_packets = stats->packets; + rx_dropped = stats->dropped; + } while (u64_stats_fetch_retry(&stats->syncp, start)); + + stats64->rx_bytes += rx_bytes; + stats64->rx_packets += rx_packets; + stats64->rx_dropped += rx_dropped; + } +} + static const struct net_device_ops fbnic_netdev_ops = { .ndo_open = fbnic_open, .ndo_stop = fbnic_stop, @@ -324,6 +392,7 @@ static const struct net_device_ops fbnic_netdev_ops = { .ndo_features_check = fbnic_features_check, .ndo_set_mac_address = fbnic_set_mac, .ndo_set_rx_mode = fbnic_set_rx_mode, + .ndo_get_stats64 = fbnic_get_stats64, }; void fbnic_reset_queues(struct fbnic_net *fbn, diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h index 6bc0ebeb81826..60199e634468d 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h @@ -40,6 +40,9 @@ struct fbnic_net { u32 rss_key[FBNIC_RPC_RSS_KEY_DWORD_LEN]; u32 rss_flow_hash[FBNIC_NUM_HASH_OPT]; + /* Storage for stats after ring destruction */ + struct fbnic_queue_stats tx_stats; + struct fbnic_queue_stats rx_stats; u64 link_down_events; struct list_head napis; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c index 0ed4c9fff5d80..4d0406af297fd 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c @@ -273,6 +273,9 @@ fbnic_xmit_frame_ring(struct sk_buff *skb, struct fbnic_ring *ring) err_free: dev_kfree_skb_any(skb); err_count: + u64_stats_update_begin(&ring->stats.syncp); + ring->stats.dropped++; + u64_stats_update_end(&ring->stats.syncp); return NETDEV_TX_OK; } @@ -363,10 +366,19 @@ static void fbnic_clean_twq0(struct fbnic_napi_vector *nv, int napi_budget, txq = txring_txq(nv->napi.dev, ring); if (unlikely(discard)) { + u64_stats_update_begin(&ring->stats.syncp); + ring->stats.dropped += total_packets; + u64_stats_update_end(&ring->stats.syncp); + netdev_tx_completed_queue(txq, total_packets, total_bytes); return; } + u64_stats_update_begin(&ring->stats.syncp); + ring->stats.bytes += total_bytes; + ring->stats.packets += total_packets; + u64_stats_update_end(&ring->stats.syncp); + netif_txq_completed_wake(txq, total_packets, total_bytes, fbnic_desc_unused(ring), FBNIC_TX_DESC_WAKEUP); @@ -730,12 +742,12 @@ static bool fbnic_rcd_metadata_err(u64 rcd) static int fbnic_clean_rcq(struct fbnic_napi_vector *nv, struct fbnic_q_triad *qt, int budget) { + unsigned int packets = 0, bytes = 0, dropped = 0; struct fbnic_ring *rcq = &qt->cmpl; struct fbnic_pkt_buff *pkt; s32 head0 = -1, head1 = -1; __le64 *raw_rcd, done; u32 head = rcq->head; - u64 packets = 0; done = (head & (rcq->size_mask + 1)) ? cpu_to_le64(FBNIC_RCD_DONE) : 0; raw_rcd = &rcq->desc[head & rcq->size_mask]; @@ -780,9 +792,11 @@ static int fbnic_clean_rcq(struct fbnic_napi_vector *nv, fbnic_populate_skb_fields(nv, rcd, skb, qt); packets++; + bytes += skb->len; napi_gro_receive(&nv->napi, skb); } else { + dropped++; fbnic_put_pkt_buff(nv, pkt, 1); } @@ -799,6 +813,14 @@ static int fbnic_clean_rcq(struct fbnic_napi_vector *nv, } } + u64_stats_update_begin(&rcq->stats.syncp); + rcq->stats.packets += packets; + rcq->stats.bytes += bytes; + /* Re-add ethernet header length (removed in fbnic_build_skb) */ + rcq->stats.bytes += ETH_HLEN * packets; + rcq->stats.dropped += dropped; + u64_stats_update_end(&rcq->stats.syncp); + /* Unmap and free processed buffers */ if (head0 >= 0) fbnic_clean_bdq(nv, budget, &qt->sub0, head0); @@ -865,12 +887,36 @@ static irqreturn_t fbnic_msix_clean_rings(int __always_unused irq, void *data) return IRQ_HANDLED; } +static void fbnic_aggregate_ring_rx_counters(struct fbnic_net *fbn, + struct fbnic_ring *rxr) +{ + struct fbnic_queue_stats *stats = &rxr->stats; + + /* Capture stats from queues before dissasociating them */ + fbn->rx_stats.bytes += stats->bytes; + fbn->rx_stats.packets += stats->packets; + fbn->rx_stats.dropped += stats->dropped; +} + +static void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn, + struct fbnic_ring *txr) +{ + struct fbnic_queue_stats *stats = &txr->stats; + + /* Capture stats from queues before dissasociating them */ + fbn->tx_stats.bytes += stats->bytes; + fbn->tx_stats.packets += stats->packets; + fbn->tx_stats.dropped += stats->dropped; +} + static void fbnic_remove_tx_ring(struct fbnic_net *fbn, struct fbnic_ring *txr) { if (!(txr->flags & FBNIC_RING_F_STATS)) return; + fbnic_aggregate_ring_tx_counters(fbn, txr); + /* Remove pointer to the Tx ring */ WARN_ON(fbn->tx[txr->q_idx] && fbn->tx[txr->q_idx] != txr); fbn->tx[txr->q_idx] = NULL; @@ -882,6 +928,8 @@ static void fbnic_remove_rx_ring(struct fbnic_net *fbn, if (!(rxr->flags & FBNIC_RING_F_STATS)) return; + fbnic_aggregate_ring_rx_counters(fbn, rxr); + /* Remove pointer to the Rx ring */ WARN_ON(fbn->rx[rxr->q_idx] && fbn->rx[rxr->q_idx] != rxr); fbn->rx[rxr->q_idx] = NULL; @@ -974,6 +1022,7 @@ static int fbnic_alloc_nv_page_pool(struct fbnic_net *fbn, static void fbnic_ring_init(struct fbnic_ring *ring, u32 __iomem *doorbell, int q_idx, u8 flags) { + u64_stats_init(&ring->stats.syncp); ring->doorbell = doorbell; ring->q_idx = q_idx; ring->flags = flags; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h index 4a206c0e71924..2f91f68d11d57 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h @@ -7,6 +7,7 @@ #include #include #include +#include #include struct fbnic_net; @@ -51,6 +52,13 @@ struct fbnic_pkt_buff { u16 nr_frags; }; +struct fbnic_queue_stats { + u64 packets; + u64 bytes; + u64 dropped; + struct u64_stats_sync syncp; +}; + /* Pagecnt bias is long max to reserve the last bit to catch overflow * cases where if we overcharge the bias it will flip over to be negative. */ @@ -77,6 +85,8 @@ struct fbnic_ring { u32 head, tail; /* Head/Tail of ring */ + struct fbnic_queue_stats stats; + /* Slow path fields follow */ dma_addr_t dma; /* Phys addr of descriptor memory */ size_t size; /* Size of descriptor ring in memory */ From 8be1bd91db71fb52be17890586f34cf9403ace89 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Fri, 9 Aug 2024 22:43:22 -0700 Subject: [PATCH 073/385] eth: fbnic: add support for basic qstats Implement netdev_stat_ops and export the basic per-queue stats. This interface expect users to set the values that are used either to zero or to some other preserved value (they are 0xff by default). So here we export bytes/packets/drops from tx and rx_stats plus set some of the values that are exposed by queue stats to zero. $ cd tools/testing/selftests/drivers/net && ./stats.py [...] Totals: pass:4 fail:0 xfail:0 xpass:0 skip:0 error:0 Reviewed-by: Joe Damato Signed-off-by: Stanislav Fomichev Link: https://patch.msgid.link/20240810054322.2766421-3-kuba@kernel.org Signed-off-by: Jakub Kicinski --- .../net/ethernet/meta/fbnic/fbnic_netdev.c | 67 +++++++++++++++++++ 1 file changed, 67 insertions(+) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c index a048e4a617eb8..5713743612599 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c @@ -4,6 +4,7 @@ #include #include #include +#include #include "fbnic.h" #include "fbnic_netdev.h" @@ -395,6 +396,71 @@ static const struct net_device_ops fbnic_netdev_ops = { .ndo_get_stats64 = fbnic_get_stats64, }; +static void fbnic_get_queue_stats_rx(struct net_device *dev, int idx, + struct netdev_queue_stats_rx *rx) +{ + struct fbnic_net *fbn = netdev_priv(dev); + struct fbnic_ring *rxr = fbn->rx[idx]; + struct fbnic_queue_stats *stats; + unsigned int start; + u64 bytes, packets; + + if (!rxr) + return; + + stats = &rxr->stats; + do { + start = u64_stats_fetch_begin(&stats->syncp); + bytes = stats->bytes; + packets = stats->packets; + } while (u64_stats_fetch_retry(&stats->syncp, start)); + + rx->bytes = bytes; + rx->packets = packets; +} + +static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx, + struct netdev_queue_stats_tx *tx) +{ + struct fbnic_net *fbn = netdev_priv(dev); + struct fbnic_ring *txr = fbn->tx[idx]; + struct fbnic_queue_stats *stats; + unsigned int start; + u64 bytes, packets; + + if (!txr) + return; + + stats = &txr->stats; + do { + start = u64_stats_fetch_begin(&stats->syncp); + bytes = stats->bytes; + packets = stats->packets; + } while (u64_stats_fetch_retry(&stats->syncp, start)); + + tx->bytes = bytes; + tx->packets = packets; +} + +static void fbnic_get_base_stats(struct net_device *dev, + struct netdev_queue_stats_rx *rx, + struct netdev_queue_stats_tx *tx) +{ + struct fbnic_net *fbn = netdev_priv(dev); + + tx->bytes = fbn->tx_stats.bytes; + tx->packets = fbn->tx_stats.packets; + + rx->bytes = fbn->rx_stats.bytes; + rx->packets = fbn->rx_stats.packets; +} + +static const struct netdev_stat_ops fbnic_stat_ops = { + .get_queue_stats_rx = fbnic_get_queue_stats_rx, + .get_queue_stats_tx = fbnic_get_queue_stats_tx, + .get_base_stats = fbnic_get_base_stats, +}; + void fbnic_reset_queues(struct fbnic_net *fbn, unsigned int tx, unsigned int rx) { @@ -453,6 +519,7 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd) fbd->netdev = netdev; netdev->netdev_ops = &fbnic_netdev_ops; + netdev->stat_ops = &fbnic_stat_ops; fbn = netdev_priv(netdev); From 246ef40670b71fef0c3e2cd11404279bc6d6468e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Mon, 29 Jul 2024 17:30:10 -0700 Subject: [PATCH 074/385] ipv6: eliminate ndisc_ops_is_useropt() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit as it doesn't seem to offer anything of value. There's only 1 trivial user: int lowpan_ndisc_is_useropt(u8 nd_opt_type) { return nd_opt_type == ND_OPT_6CO; } but there's no harm to always treating that as a useropt... Cc: David Ahern Cc: YOSHIFUJI Hideaki / 吉藤英明 Signed-off-by: Maciej Żenczykowski Link: https://patch.msgid.link/20240730003010.156977-1-maze@google.com Signed-off-by: Jakub Kicinski --- include/net/ndisc.h | 15 --------------- net/6lowpan/ndisc.c | 6 ------ net/ipv6/ndisc.c | 4 ++-- 3 files changed, 2 insertions(+), 23 deletions(-) diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 7a533d5b1d59f..3c88d5bc5eed5 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -147,11 +147,6 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, * The following hooks can be defined; unless noted otherwise, they are * optional and can be filled with a null pointer. * - * int (*is_useropt)(u8 nd_opt_type): - * This function is called when IPv6 decide RA userspace options. if - * this function returns 1 then the option given by nd_opt_type will - * be handled as userspace option additional to the IPv6 options. - * * int (*parse_options)(const struct net_device *dev, * struct nd_opt_hdr *nd_opt, * struct ndisc_options *ndopts): @@ -200,7 +195,6 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, * addresses. E.g. 802.15.4 6LoWPAN. */ struct ndisc_ops { - int (*is_useropt)(u8 nd_opt_type); int (*parse_options)(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts); @@ -224,15 +218,6 @@ struct ndisc_ops { }; #if IS_ENABLED(CONFIG_IPV6) -static inline int ndisc_ops_is_useropt(const struct net_device *dev, - u8 nd_opt_type) -{ - if (dev->ndisc_ops && dev->ndisc_ops->is_useropt) - return dev->ndisc_ops->is_useropt(nd_opt_type); - else - return 0; -} - static inline int ndisc_ops_parse_options(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts) diff --git a/net/6lowpan/ndisc.c b/net/6lowpan/ndisc.c index 16be8f8b2f8ca..c40b98f7743cd 100644 --- a/net/6lowpan/ndisc.c +++ b/net/6lowpan/ndisc.c @@ -11,11 +11,6 @@ #include "6lowpan_i.h" -static int lowpan_ndisc_is_useropt(u8 nd_opt_type) -{ - return nd_opt_type == ND_OPT_6CO; -} - #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) #define NDISC_802154_SHORT_ADDR_LENGTH 1 static int lowpan_ndisc_parse_802154_options(const struct net_device *dev, @@ -222,7 +217,6 @@ static void lowpan_ndisc_prefix_rcv_add_addr(struct net *net, #endif const struct ndisc_ops lowpan_ndisc_ops = { - .is_useropt = lowpan_ndisc_is_useropt, #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) .parse_options = lowpan_ndisc_parse_options, .update = lowpan_ndisc_update, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index b8eec1b6cc2c8..1e42e40fb379c 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -200,9 +200,9 @@ static inline int ndisc_is_useropt(const struct net_device *dev, return opt->nd_opt_type == ND_OPT_PREFIX_INFO || opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || + opt->nd_opt_type == ND_OPT_6CO || opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || - opt->nd_opt_type == ND_OPT_PREF64 || - ndisc_ops_is_useropt(dev, opt->nd_opt_type); + opt->nd_opt_type == ND_OPT_PREF64; } static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev, From 75bab45e6b2da379fe2ebda48ed35f8ce371a2ef Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 7 Aug 2024 16:13:46 +0200 Subject: [PATCH 075/385] net: nexthop: Add flag to assert that NHGRP reserved fields are zero There are many unpatched kernel versions out there that do not initialize the reserved fields of struct nexthop_grp. The issue with that is that if those fields were to be used for some end (i.e. stop being reserved), old kernels would still keep sending random data through the field, and a new userspace could not rely on the value. In this patch, use the existing NHA_OP_FLAGS, which is currently inbound only, to carry flags back to the userspace. Add a flag to indicate that the reserved fields in struct nexthop_grp are zeroed before dumping. This is reliant on the actual fix from commit 6d745cd0e972 ("net: nexthop: Initialize all fields in dumped nexthops"). Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Link: https://patch.msgid.link/21037748d4f9d8ff486151f4c09083bcf12d5df8.1723036486.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/nexthop.h | 3 +++ net/ipv4/nexthop.c | 12 +++++++++--- 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h index dd8787f9cf39a..f4f060a87cc29 100644 --- a/include/uapi/linux/nexthop.h +++ b/include/uapi/linux/nexthop.h @@ -33,6 +33,9 @@ enum { #define NHA_OP_FLAG_DUMP_STATS BIT(0) #define NHA_OP_FLAG_DUMP_HW_STATS BIT(1) +/* Response OP_FLAGS. */ +#define NHA_OP_FLAG_RESP_GRP_RESVD_0 BIT(31) /* Dump clears resvd fields. */ + enum { NHA_UNSPEC, NHA_ID, /* u32; id for nexthop. id == 0 means auto-assign */ diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 6b9787ee86017..23caa13bf24dd 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -865,7 +865,7 @@ static int nla_put_nh_group_stats(struct sk_buff *skb, struct nexthop *nh, } static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, - u32 op_flags) + u32 op_flags, u32 *resp_op_flags) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nexthop_grp *p; @@ -874,6 +874,8 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, u16 group_type = 0; int i; + *resp_op_flags |= NHA_OP_FLAG_RESP_GRP_RESVD_0; + if (nhg->hash_threshold) group_type = NEXTHOP_GRP_TYPE_MPATH; else if (nhg->resilient) @@ -934,10 +936,12 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + u32 resp_op_flags = 0; if (nhg->fdb_nh && nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; - if (nla_put_nh_group(skb, nh, op_flags)) + if (nla_put_nh_group(skb, nh, op_flags, &resp_op_flags) || + nla_put_u32(skb, NHA_OP_FLAGS, resp_op_flags)) goto nla_put_failure; goto out; } @@ -1050,7 +1054,9 @@ static size_t nh_nlmsg_size(struct nexthop *nh) sz += nla_total_size(4); /* NHA_ID */ if (nh->is_group) - sz += nh_nlmsg_size_grp(nh); + sz += nh_nlmsg_size_grp(nh) + + nla_total_size(4) + /* NHA_OP_FLAGS */ + 0; else sz += nh_nlmsg_size_single(nh); From b72a6a7ab9573e06d5c2fcb92eaa28614a735bfd Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 7 Aug 2024 16:13:47 +0200 Subject: [PATCH 076/385] net: nexthop: Increase weight to u16 In CLOS networks, as link failures occur at various points in the network, ECMP weights of the involved nodes are adjusted to compensate. With high fan-out of the involved nodes, and overall high number of nodes, a (non-)ECMP weight ratio that we would like to configure does not fit into 8 bits. Instead of, say, 255:254, we might like to configure something like 1000:999. For these deployments, the 8-bit weight may not be enough. To that end, in this patch increase the next hop weight from u8 to u16. Increasing the width of an integral type can be tricky, because while the code still compiles, the types may not check out anymore, and numerical errors come up. To prevent this, the conversion was done in two steps. First the type was changed from u8 to a single-member structure, which invalidated all uses of the field. This allowed going through them one by one and audit for type correctness. Then the structure was replaced with a vanilla u16 again. This should ensure that no place was missed. The UAPI for configuring nexthop group members is that an attribute NHA_GROUP carries an array of struct nexthop_grp entries: struct nexthop_grp { __u32 id; /* nexthop id - must exist */ __u8 weight; /* weight of this nexthop */ __u8 resvd1; __u16 resvd2; }; The field resvd1 is currently validated and required to be zero. We can lift this requirement and carry high-order bits of the weight in the reserved field: struct nexthop_grp { __u32 id; /* nexthop id - must exist */ __u8 weight; /* weight of this nexthop */ __u8 weight_high; __u16 resvd2; }; Keeping the fields split this way was chosen in case an existing userspace makes assumptions about the width of the weight field, and to sidestep any endianness issues. The weight field is currently encoded as the weight value minus one, because weight of 0 is invalid. This same trick is impossible for the new weight_high field, because zero must mean actual zero. With this in place: - Old userspace is guaranteed to carry weight_high of 0, therefore configuring 8-bit weights as appropriate. When dumping nexthops with 16-bit weight, it would only show the lower 8 bits. But configuring such nexthops implies existence of userspace aware of the extension in the first place. - New userspace talking to an old kernel will work as long as it only attempts to configure 8-bit weights, where the high-order bits are zero. Old kernel will bounce attempts at configuring >8-bit weights. Renaming reserved fields as they are allocated for some purpose is commonly done in Linux. Whoever touches a reserved field is doing so at their own risk. nexthop_grp::resvd1 in particular is currently used by at least strace, however they carry an own copy of UAPI headers, and the conversion should be trivial. A helper is provided for decoding the weight out of the two fields. Forcing a conversion seems preferable to bending backwards and introducing anonymous unions or whatever. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Reviewed-by: Przemek Kitszel Link: https://patch.msgid.link/483e2fcf4beb0d9135d62e7d27b46fa2685479d4.1723036486.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- include/net/nexthop.h | 4 ++-- include/uapi/linux/nexthop.h | 7 ++++++- net/ipv4/nexthop.c | 37 ++++++++++++++++++++++-------------- 3 files changed, 31 insertions(+), 17 deletions(-) diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 68463aebcc059..d9fb44e8b3219 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -105,7 +105,7 @@ struct nh_grp_entry_stats { struct nh_grp_entry { struct nexthop *nh; struct nh_grp_entry_stats __percpu *stats; - u8 weight; + u16 weight; union { struct { @@ -192,7 +192,7 @@ struct nh_notifier_single_info { }; struct nh_notifier_grp_entry_info { - u8 weight; + u16 weight; struct nh_notifier_single_info nh; }; diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h index f4f060a87cc29..bc49baf4a267f 100644 --- a/include/uapi/linux/nexthop.h +++ b/include/uapi/linux/nexthop.h @@ -16,10 +16,15 @@ struct nhmsg { struct nexthop_grp { __u32 id; /* nexthop id - must exist */ __u8 weight; /* weight of this nexthop */ - __u8 resvd1; + __u8 weight_high; /* high order bits of weight */ __u16 resvd2; }; +static inline __u16 nexthop_grp_weight(const struct nexthop_grp *entry) +{ + return ((entry->weight_high << 8) | entry->weight) + 1; +} + enum { NEXTHOP_GRP_TYPE_MPATH, /* hash-threshold nexthop group * default type if not specified diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 23caa13bf24dd..9db10d409074e 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -872,6 +872,7 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, size_t len = nhg->num_nh * sizeof(*p); struct nlattr *nla; u16 group_type = 0; + u16 weight; int i; *resp_op_flags |= NHA_OP_FLAG_RESP_GRP_RESVD_0; @@ -890,9 +891,12 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, p = nla_data(nla); for (i = 0; i < nhg->num_nh; ++i) { + weight = nhg->nh_entries[i].weight - 1; + *p++ = (struct nexthop_grp) { .id = nhg->nh_entries[i].nh->id, - .weight = nhg->nh_entries[i].weight - 1, + .weight = weight, + .weight_high = weight >> 8, }; } @@ -1286,11 +1290,14 @@ static int nh_check_attr_group(struct net *net, nhg = nla_data(tb[NHA_GROUP]); for (i = 0; i < len; ++i) { - if (nhg[i].resvd1 || nhg[i].resvd2) { - NL_SET_ERR_MSG(extack, "Reserved fields in nexthop_grp must be 0"); + if (nhg[i].resvd2) { + NL_SET_ERR_MSG(extack, "Reserved field in nexthop_grp must be 0"); return -EINVAL; } - if (nhg[i].weight > 254) { + if (nexthop_grp_weight(&nhg[i]) == 0) { + /* 0xffff got passed in, representing weight of 0x10000, + * which is too heavy. + */ NL_SET_ERR_MSG(extack, "Invalid value for weight"); return -EINVAL; } @@ -1886,9 +1893,9 @@ static void nh_res_table_cancel_upkeep(struct nh_res_table *res_table) static void nh_res_group_rebalance(struct nh_group *nhg, struct nh_res_table *res_table) { - int prev_upper_bound = 0; - int total = 0; - int w = 0; + u16 prev_upper_bound = 0; + u32 total = 0; + u32 w = 0; int i; INIT_LIST_HEAD(&res_table->uw_nh_entries); @@ -1898,11 +1905,12 @@ static void nh_res_group_rebalance(struct nh_group *nhg, for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; - int upper_bound; + u16 upper_bound; + u64 btw; w += nhge->weight; - upper_bound = DIV_ROUND_CLOSEST(res_table->num_nh_buckets * w, - total); + btw = ((u64)res_table->num_nh_buckets) * w; + upper_bound = DIV_ROUND_CLOSEST_ULL(btw, total); nhge->res.wants_buckets = upper_bound - prev_upper_bound; prev_upper_bound = upper_bound; @@ -1968,8 +1976,8 @@ static void replace_nexthop_grp_res(struct nh_group *oldg, static void nh_hthr_group_rebalance(struct nh_group *nhg) { - int total = 0; - int w = 0; + u32 total = 0; + u32 w = 0; int i; for (i = 0; i < nhg->num_nh; ++i) @@ -1977,7 +1985,7 @@ static void nh_hthr_group_rebalance(struct nh_group *nhg) for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; - int upper_bound; + u32 upper_bound; w += nhge->weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1; @@ -2719,7 +2727,8 @@ static struct nexthop *nexthop_create_group(struct net *net, goto out_no_nh; } nhg->nh_entries[i].nh = nhe; - nhg->nh_entries[i].weight = entry[i].weight + 1; + nhg->nh_entries[i].weight = nexthop_grp_weight(&entry[i]); + list_add(&nhg->nh_entries[i].nh_list, &nhe->grp_list); nhg->nh_entries[i].nh_parent = nh; } From 110d3ffe9d2b42c04faaf92c3fc627004e3328c6 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 7 Aug 2024 16:13:48 +0200 Subject: [PATCH 077/385] selftests: router_mpath: Sleep after MZ In the context of an offloaded datapath, it may take a while for the ip link stats to be updated. This causes the test to fail when MZ_DELAY is too low. Sleep after the packets are sent for the link stats to get up to date. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Link: https://patch.msgid.link/8b1971d948273afd7de2da3d6a2ba35200540e55.1723036486.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/router_mpath_nh.sh | 2 ++ tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh | 2 ++ tools/testing/selftests/net/forwarding/router_multipath.sh | 2 ++ 3 files changed, 6 insertions(+) diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh index 2ba44247c60ae..c5a30f8f55b52 100755 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh @@ -243,6 +243,7 @@ multipath4_test() ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) @@ -276,6 +277,7 @@ multipath6_test() $MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh index cd9e346436fcf..bd35fe8be9aab 100755 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh @@ -244,6 +244,7 @@ multipath4_test() ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) @@ -274,6 +275,7 @@ multipath6_l4_test() $MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh index e2be354167a1c..46f365b557b76 100755 --- a/tools/testing/selftests/net/forwarding/router_multipath.sh +++ b/tools/testing/selftests/net/forwarding/router_multipath.sh @@ -180,6 +180,7 @@ multipath4_test() ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) @@ -217,6 +218,7 @@ multipath6_test() $MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) From bb89fdacf99ccbec4dfe2d04f76f870f1483d3ea Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 7 Aug 2024 16:13:49 +0200 Subject: [PATCH 078/385] selftests: router_mpath_nh: Test 16-bit next hop weights Add tests that exercise full 16 bits of NH weight. To test the 255:65535, it is necessary to run more packets than for the other tests. On a debug kernel, the test can take up to a minute, therefore avoid the test when KSFT_MACHINE_SLOW. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Link: https://patch.msgid.link/c0c257c00ad30b07afc3fa5e2afd135925405544.1723036486.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/forwarding/lib.sh | 7 ++++ .../net/forwarding/router_mpath_nh.sh | 38 +++++++++++++++---- .../net/forwarding/router_mpath_nh_lib.sh | 13 +++++++ 3 files changed, 50 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index ff96bb7535ff0..cb0fcd6f02931 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -509,6 +509,13 @@ xfail_on_slow() fi } +omit_on_slow() +{ + if [[ $KSFT_MACHINE_SLOW != yes ]]; then + "$@" + fi +} + xfail_on_veth() { local dev=$1; shift diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh index c5a30f8f55b52..a7d8399c8d4fc 100755 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh @@ -40,6 +40,7 @@ ALL_TESTS=" ping_ipv4 ping_ipv6 multipath_test + multipath16_test ping_ipv4_blackhole ping_ipv6_blackhole nh_stats_test_v4 @@ -226,9 +227,11 @@ routing_nh_obj() multipath4_test() { - local desc="$1" - local weight_rp12=$2 - local weight_rp13=$3 + local desc=$1; shift + local weight_rp12=$1; shift + local weight_rp13=$1; shift + local ports=${1-sp=1024,dp=0-32768}; shift + local t0_rp12 t0_rp13 t1_rp12 t1_rp13 local packets_rp12 packets_rp13 @@ -242,7 +245,7 @@ multipath4_test() t0_rp13=$(link_stats_tx_packets_get $rp13) ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ - -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "$ports" sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) @@ -259,9 +262,11 @@ multipath4_test() multipath6_test() { - local desc="$1" - local weight_rp12=$2 - local weight_rp13=$3 + local desc=$1; shift + local weight_rp12=$1; shift + local weight_rp13=$1; shift + local ports=${1-sp=1024,dp=0-32768}; shift + local t0_rp12 t0_rp13 t1_rp12 t1_rp13 local packets_rp12 packets_rp13 @@ -276,7 +281,7 @@ multipath6_test() t0_rp13=$(link_stats_tx_packets_get $rp13) $MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ - -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "$ports" sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) @@ -315,6 +320,23 @@ multipath_test() multipath6_test "Weighted MP 11:45" 11 45 } +multipath16_test() +{ + check_nhgw16 104 || return + + log_info "Running 16-bit IPv4 multipath tests" + multipath4_test "65535:65535" 65535 65535 + multipath4_test "128:512" 128 512 + omit_on_slow \ + multipath4_test "255:65535" 255 65535 sp=1024-1026,dp=0-65535 + + log_info "Running 16-bit IPv6 multipath tests" + multipath6_test "65535:65535" 65535 65535 + multipath6_test "128:512" 128 512 + omit_on_slow \ + multipath6_test "255:65535" 255 65535 sp=1024-1026,dp=0-65535 +} + ping_ipv4_blackhole() { RET=0 diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh index 2903294d8bca0..507b2852dabea 100644 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh @@ -117,3 +117,16 @@ __nh_stats_test_v6() $MZ -6 $h1 -A 2001:db8:1::2 -B 2001:db8:2::2 sysctl_restore net.ipv6.fib_multipath_hash_policy } + +check_nhgw16() +{ + local nhid=$1; shift + + ip nexthop replace id 9999 group "$nhid,65535" &>/dev/null + if (( $? )); then + log_test_skip "16-bit multipath tests" \ + "iproute2 or the kernel do not support 16-bit next hop weights" + return 1 + fi + ip nexthop del id 9999 ||: +} From dce0765c1d5bf810bf3cd8e66cf7f6e73d14d7e2 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 7 Aug 2024 16:13:50 +0200 Subject: [PATCH 079/385] selftests: router_mpath_nh_res: Test 16-bit next hop weights Add tests that exercise full 16 bits of NH weight. Like in the previous patch, omit the 255:65535 test when KSFT_MACHINE_SLOW. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Link: https://patch.msgid.link/a91d6ead9d1b1b4b7e276ca58a71ef814f42b7dd.1723036486.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- .../net/forwarding/router_mpath_nh_res.sh | 56 ++++++++++++++++--- 1 file changed, 48 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh index bd35fe8be9aab..88ddae05b39db 100755 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh @@ -40,6 +40,7 @@ ALL_TESTS=" ping_ipv4 ping_ipv6 multipath_test + multipath16_test nh_stats_test_v4 nh_stats_test_v6 " @@ -228,9 +229,11 @@ routing_nh_obj() multipath4_test() { - local desc="$1" - local weight_rp12=$2 - local weight_rp13=$3 + local desc=$1; shift + local weight_rp12=$1; shift + local weight_rp13=$1; shift + local ports=${1-sp=1024,dp=0-32768}; shift + local t0_rp12 t0_rp13 t1_rp12 t1_rp13 local packets_rp12 packets_rp13 @@ -243,7 +246,7 @@ multipath4_test() t0_rp13=$(link_stats_tx_packets_get $rp13) ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ - -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "$ports" sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) @@ -259,9 +262,11 @@ multipath4_test() multipath6_l4_test() { - local desc="$1" - local weight_rp12=$2 - local weight_rp13=$3 + local desc=$1; shift + local weight_rp12=$1; shift + local weight_rp13=$1; shift + local ports=${1-sp=1024,dp=0-32768}; shift + local t0_rp12 t0_rp13 t1_rp12 t1_rp13 local packets_rp12 packets_rp13 @@ -274,7 +279,7 @@ multipath6_l4_test() t0_rp13=$(link_stats_tx_packets_get $rp13) $MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ - -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "$ports" sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) @@ -373,6 +378,41 @@ multipath_test() ip nexthop replace id 106 group 104,1/105,1 type resilient } +multipath16_test() +{ + check_nhgw16 104 || return + + log_info "Running 16-bit IPv4 multipath tests" + ip nexthop replace id 103 group 101/102 type resilient idle_timer 0 + + ip nexthop replace id 103 group 101,65535/102,65535 type resilient + multipath4_test "65535:65535" 65535 65535 + + ip nexthop replace id 103 group 101,128/102,512 type resilient + multipath4_test "128:512" 128 512 + + ip nexthop replace id 103 group 101,255/102,65535 type resilient + omit_on_slow \ + multipath4_test "255:65535" 255 65535 sp=1024-1026,dp=0-65535 + + ip nexthop replace id 103 group 101,1/102,1 type resilient + + log_info "Running 16-bit IPv6 L4 hash multipath tests" + ip nexthop replace id 106 group 104/105 type resilient idle_timer 0 + + ip nexthop replace id 106 group 104,65535/105,65535 type resilient + multipath6_l4_test "65535:65535" 65535 65535 + + ip nexthop replace id 106 group 104,128/105,512 type resilient + multipath6_l4_test "128:512" 128 512 + + ip nexthop replace id 106 group 104,255/105,65535 type resilient + omit_on_slow \ + multipath6_l4_test "255:65535" 255 65535 sp=1024-1026,dp=0-65535 + + ip nexthop replace id 106 group 104,1/105,1 type resilient +} + nh_stats_test_v4() { __nh_stats_test_v4 resilient From 4b808f44733243f981ae04046ef93a65ecc631a9 Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Wed, 7 Aug 2024 16:13:51 +0200 Subject: [PATCH 080/385] selftests: fib_nexthops: Test 16-bit next hop weights Add tests that attempt to create NH groups that use full 16 bits of NH weight. Signed-off-by: Petr Machata Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Link: https://patch.msgid.link/101cdd3f2bfd9511c9bec95f909d20ff56f70ba5.1723036486.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/fib_nexthops.sh | 55 ++++++++++++++++++++- 1 file changed, 54 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index ac0b2c6a5761b..77c83d9508d3b 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -78,7 +78,12 @@ log_test() else ret=1 nfail=$((nfail+1)) - printf "TEST: %-60s [FAIL]\n" "${msg}" + if [[ $rc -eq $ksft_skip ]]; then + printf "TEST: %-60s [SKIP]\n" "${msg}" + else + printf "TEST: %-60s [FAIL]\n" "${msg}" + fi + if [ "$VERBOSE" = "1" ]; then echo " rc=$rc, expected $expected" fi @@ -923,6 +928,29 @@ ipv6_grp_fcnal() ipv6_grp_refs log_test $? 0 "Nexthop group replace refcounts" + + # + # 16-bit weights. + # + run_cmd "$IP nexthop add id 62 via 2001:db8:91::2 dev veth1" + run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1" + run_cmd "$IP nexthop add id 64 via 2001:db8:91::4 dev veth1" + run_cmd "$IP nexthop add id 65 via 2001:db8:91::5 dev veth1" + run_cmd "$IP nexthop add id 66 dev veth1" + + run_cmd "$IP nexthop add id 103 group 62,1000" + if [[ $? == 0 ]]; then + local GRP="id 103 group 62,254/63,255/64,256/65,257/66,65535" + run_cmd "$IP nexthop replace $GRP" + check_nexthop "id 103" "$GRP" + rc=$? + else + rc=$ksft_skip + fi + + $IP nexthop flush >/dev/null 2>&1 + + log_test $rc 0 "16-bit weights" } ipv6_res_grp_fcnal() @@ -987,6 +1015,31 @@ ipv6_res_grp_fcnal() check_nexthop_bucket "list id 102" \ "id 102 index 0 nhid 63 id 102 index 1 nhid 62 id 102 index 2 nhid 62 id 102 index 3 nhid 62" log_test $? 0 "Nexthop buckets updated after replace - nECMP" + + # + # 16-bit weights. + # + run_cmd "$IP nexthop add id 62 via 2001:db8:91::2 dev veth1" + run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1" + run_cmd "$IP nexthop add id 64 via 2001:db8:91::4 dev veth1" + run_cmd "$IP nexthop add id 65 via 2001:db8:91::5 dev veth1" + run_cmd "$IP nexthop add id 66 dev veth1" + + run_cmd "$IP nexthop add id 103 group 62,1000 type resilient buckets 32" + if [[ $? == 0 ]]; then + local GRP="id 103 group 62,254/63,255/64,256/65,257/66,65535 $(: + )type resilient buckets 32 idle_timer 0 $(: + )unbalanced_timer 0" + run_cmd "$IP nexthop replace $GRP" + check_nexthop "id 103" "$GRP unbalanced_time 0" + rc=$? + else + rc=$ksft_skip + fi + + $IP nexthop flush >/dev/null 2>&1 + + log_test $rc 0 "16-bit weights" } ipv6_fcnal_runtime() From e2d0fadd703c3a3a6ebe318ec82ea64c08d709c2 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 9 Aug 2024 09:22:12 -0600 Subject: [PATCH 081/385] sched: act_ct: avoid -Wflex-array-member-not-at-end warning -Wflex-array-member-not-at-end was introduced in GCC-14, and we are getting ready to enable it, globally. Remove unnecessary flex-array member `pad[]` and refactor the related code a bit. Fix the following warning: net/sched/act_ct.c:57:29: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end] Signed-off-by: Gustavo A. R. Silva Link: https://patch.msgid.link/ZrY0JMVsImbDbx6r@cute Signed-off-by: Jakub Kicinski --- net/sched/act_ct.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 3ba8e7e739b58..2197eb6256580 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -44,8 +44,6 @@ static DEFINE_MUTEX(zones_mutex); struct zones_ht_key { struct net *net; u16 zone; - /* Note : pad[] must be the last field. */ - u8 pad[]; }; struct tcf_ct_flow_table { @@ -62,7 +60,7 @@ struct tcf_ct_flow_table { static const struct rhashtable_params zones_params = { .head_offset = offsetof(struct tcf_ct_flow_table, node), .key_offset = offsetof(struct tcf_ct_flow_table, key), - .key_len = offsetof(struct zones_ht_key, pad), + .key_len = offsetofend(struct zones_ht_key, zone), .automatic_shrinking = true, }; From 46dd90fe51f3556deaf5af47aafcee10536a3978 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 8 Aug 2024 16:08:35 -0600 Subject: [PATCH 082/385] nfp: Use static_assert() to check struct sizes Commit d88cabfd9abc ("nfp: Avoid -Wflex-array-member-not-at-end warnings") introduced tagged `struct nfp_dump_tl_hdr`. We want to ensure that when new members need to be added to the flexible structure, they are always included within this tagged struct. So, we use `static_assert()` to ensure that the memory layout for both the flexible structure and the tagged struct is the same after any changes. Signed-off-by: Gustavo A. R. Silva Reviewed-by: Simon Horman Link: https://patch.msgid.link/ZrVB43Hen0H5WQFP@cute Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c index 2dd37557185e9..7276e44a21d09 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c @@ -41,6 +41,8 @@ struct nfp_dump_tl { ); char data[]; }; +static_assert(offsetof(struct nfp_dump_tl, data) == sizeof(struct nfp_dump_tl_hdr), + "struct member likely outside of struct_group_tagged()"); /* NFP CPP parameters */ struct nfp_dumpspec_cpp_isl_id { From 0a3e6939d4b33d68bce89477b9db01d68b744749 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 8 Aug 2024 16:07:54 -0600 Subject: [PATCH 083/385] net/smc: Use static_assert() to check struct sizes Commit 9748dbc9f265 ("net/smc: Avoid -Wflex-array-member-not-at-end warnings") introduced tagged `struct smc_clc_v2_extension_fixed` and `struct smc_clc_smcd_v2_extension_fixed`. We want to ensure that when new members need to be added to the flexible structures, they are always included within these tagged structs. So, we use `static_assert()` to ensure that the memory layout for both the flexible structure and the tagged struct is the same after any changes. Signed-off-by: Gustavo A. R. Silva Reviewed-by: Jan Karcher Link: https://patch.msgid.link/ZrVBuiqFHAORpFxE@cute Signed-off-by: Jakub Kicinski --- net/smc/smc_clc.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 467effb50cd65..5625fda2960b0 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -145,6 +145,8 @@ struct smc_clc_v2_extension { ); u8 user_eids[][SMC_MAX_EID_LEN]; }; +static_assert(offsetof(struct smc_clc_v2_extension, user_eids) == sizeof(struct smc_clc_v2_extension_fixed), + "struct member likely outside of struct_group_tagged()"); struct smc_clc_msg_proposal_prefix { /* prefix part of clc proposal message*/ __be32 outgoing_subnet; /* subnet mask */ @@ -169,6 +171,8 @@ struct smc_clc_smcd_v2_extension { ); struct smc_clc_smcd_gid_chid gidchid[]; }; +static_assert(offsetof(struct smc_clc_smcd_v2_extension, gidchid) == sizeof(struct smc_clc_smcd_v2_extension_fixed), + "struct member likely outside of struct_group_tagged()"); struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */ struct smc_clc_msg_hdr hdr; From 12dbc67c3b0bcd7414b511fd8a42ba4e388705bc Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:45:28 +0800 Subject: [PATCH 084/385] net: stmmac: Move the atds flag to the stmmac_dma_cfg structure ATDS (Alternate Descriptor Size) is a part of the DMA Bus Mode configs (together with PBL, ALL, EME, etc) of the DW GMAC controllers. Seeing it's not changed at runtime but is activated as long as the IP-core has it supported (at least due to the Type 2 Full Checksum Offload Engine feature), move the respective parameter from the stmmac_dma_ops::init() callback argument to the stmmac_dma_cfg structure, which already have the rest of the DMA-related configs defined. Besides the being added in the next commit DW GMAC multi-channels support will require to add the stmmac_dma_ops::init_chan() callback and have the ATDS flag set/cleared for each channel in there. Having the atds-flag in the stmmac_dma_cfg structure will make the parameter accessible from stmmac_dma_ops::init_chan() callback too. Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Reviewed-by: Serge Semin Acked-by: Huacai Chen Signed-off-by: Yanteng Si Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c | 4 ++-- drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 2 +- drivers/net/ethernet/stmicro/stmmac/hwif.h | 3 +-- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 5 ++--- include/linux/stmmac.h | 1 + 8 files changed, 10 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index e1b761dcfa1dd..d870790169524 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -299,7 +299,7 @@ static int sun8i_dwmac_dma_reset(void __iomem *ioaddr) * Called from stmmac via stmmac_dma_ops->init */ static void sun8i_dwmac_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) + struct stmmac_dma_cfg *dma_cfg) { writel(EMAC_RX_INT | EMAC_TX_INT, ioaddr + EMAC_INT_EN); writel(0x1FFFFFF, ioaddr + EMAC_INT_STA); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c index adccdd816ea91..984b809105afa 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c @@ -71,7 +71,7 @@ static void dwmac1000_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) } static void dwmac1000_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) + struct stmmac_dma_cfg *dma_cfg) { u32 value = readl(ioaddr + DMA_BUS_MODE); int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl; @@ -98,7 +98,7 @@ static void dwmac1000_dma_init(void __iomem *ioaddr, if (dma_cfg->mixed_burst) value |= DMA_BUS_MODE_MB; - if (atds) + if (dma_cfg->atds) value |= DMA_BUS_MODE_ATDS; if (dma_cfg->aal) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c index b402fb54f6131..82957db47c991 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c @@ -19,7 +19,7 @@ #include "dwmac_dma.h" static void dwmac100_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) + struct stmmac_dma_cfg *dma_cfg) { /* Enable Application Access by writing to DMA CSR0 */ writel(DMA_BUS_MODE_DEFAULT | (dma_cfg->pbl << DMA_BUS_MODE_PBL_SHIFT), diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 84d3a8551b032..e0165358c4ac8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -153,7 +153,7 @@ static void dwmac410_dma_init_channel(struct stmmac_priv *priv, } static void dwmac4_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) + struct stmmac_dma_cfg *dma_cfg) { u32 value = readl(ioaddr + DMA_SYS_BUS_MODE); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index dd2ab6185c40e..7840bc403788e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -20,7 +20,7 @@ static int dwxgmac2_dma_reset(void __iomem *ioaddr) } static void dwxgmac2_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) + struct stmmac_dma_cfg *dma_cfg) { u32 value = readl(ioaddr + XGMAC_DMA_SYSBUS_MODE); diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index e53c323627749..1c99c99f46279 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -175,8 +175,7 @@ struct dma_features; struct stmmac_dma_ops { /* DMA core initialization */ int (*reset)(void __iomem *ioaddr); - void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg, - int atds); + void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg); void (*init_chan)(struct stmmac_priv *priv, void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg, u32 chan); void (*init_rx_chan)(struct stmmac_priv *priv, void __iomem *ioaddr, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f3a1b179aaeac..9f1286835550e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3003,7 +3003,6 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) struct stmmac_rx_queue *rx_q; struct stmmac_tx_queue *tx_q; u32 chan = 0; - int atds = 0; int ret = 0; if (!priv->plat->dma_cfg || !priv->plat->dma_cfg->pbl) { @@ -3012,7 +3011,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) } if (priv->extend_desc && (priv->mode == STMMAC_RING_MODE)) - atds = 1; + priv->plat->dma_cfg->atds = 1; ret = stmmac_reset(priv, priv->ioaddr); if (ret) { @@ -3021,7 +3020,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) } /* DMA Configuration */ - stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg, atds); + stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg); if (priv->plat->axi) stmmac_axi(priv, priv->ioaddr, priv->plat->axi); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 84e13bd5df284..338991c08f007 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -100,6 +100,7 @@ struct stmmac_dma_cfg { bool eame; bool multi_msi_en; bool dche; + bool atds; }; #define AXI_BLEN 7 From ad72f783de06827a1f20d7df57ca52ee102a6faf Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:45:29 +0800 Subject: [PATCH 085/385] net: stmmac: Add multi-channel support DW GMAC v3.73 can be equipped with the Audio Video (AV) feature which enables transmission of time-sensitive traffic over bridged local area networks (DWC Ethernet QoS Product). In that case there can be up to two additional DMA-channels available with no Tx COE support (unless there is vendor-specific IP-core alterations). Each channel is implemented as a separate Control and Status register (CSR) for managing the transmit and receive functions, descriptor handling, and interrupt handling. Add the multi-channels DW GMAC controllers support just by making sure the already implemented DMA-configs are performed on the per-channel basis. Note the only currently known instance of the multi-channel DW GMAC IP-core is the LS2K2000 GNET controller, which has been released with the vendor-specific feature extension of having eight DMA-channels. The device support will be added in one of the following up commits. Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Reviewed-by: Serge Semin Acked-by: Huacai Chen Signed-off-by: Yanteng Si Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- .../net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 2 +- .../ethernet/stmicro/stmmac/dwmac1000_dma.c | 32 ++++++++++--------- .../net/ethernet/stmicro/stmmac/dwmac_dma.h | 27 +++++++++++++++- .../net/ethernet/stmicro/stmmac/dwmac_lib.c | 30 ++++++++--------- drivers/net/ethernet/stmicro/stmmac/hwif.h | 2 +- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 14 ++++---- 6 files changed, 68 insertions(+), 39 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index d870790169524..cc93f73a380e5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -395,7 +395,7 @@ static void sun8i_dwmac_dma_start_tx(struct stmmac_priv *priv, writel(v, ioaddr + EMAC_TX_CTL1); } -static void sun8i_dwmac_enable_dma_transmission(void __iomem *ioaddr) +static void sun8i_dwmac_enable_dma_transmission(void __iomem *ioaddr, u32 chan) { u32 v; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c index 984b809105afa..b3d7eff53b180 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c @@ -70,15 +70,17 @@ static void dwmac1000_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) writel(value, ioaddr + DMA_AXI_BUS_MODE); } -static void dwmac1000_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg) +static void dwmac1000_dma_init_channel(struct stmmac_priv *priv, + void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, u32 chan) { - u32 value = readl(ioaddr + DMA_BUS_MODE); int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl; int rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl; + u32 value; - /* - * Set the DMA PBL (Programmable Burst Length) mode. + value = readl(ioaddr + DMA_CHAN_BUS_MODE(chan)); + + /* Set the DMA PBL (Programmable Burst Length) mode. * * Note: before stmmac core 3.50 this mode bit was 4xPBL, and * post 3.5 mode bit acts as 8*PBL. @@ -104,10 +106,10 @@ static void dwmac1000_dma_init(void __iomem *ioaddr, if (dma_cfg->aal) value |= DMA_BUS_MODE_AAL; - writel(value, ioaddr + DMA_BUS_MODE); + writel(value, ioaddr + DMA_CHAN_BUS_MODE(chan)); /* Mask interrupts by writing to CSR7 */ - writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA); + writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_CHAN_INTR_ENA(chan)); } static void dwmac1000_dma_init_rx(struct stmmac_priv *priv, @@ -116,7 +118,7 @@ static void dwmac1000_dma_init_rx(struct stmmac_priv *priv, dma_addr_t dma_rx_phy, u32 chan) { /* RX descriptor base address list must be written into DMA CSR3 */ - writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_RCV_BASE_ADDR); + writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_CHAN_RCV_BASE_ADDR(chan)); } static void dwmac1000_dma_init_tx(struct stmmac_priv *priv, @@ -125,7 +127,7 @@ static void dwmac1000_dma_init_tx(struct stmmac_priv *priv, dma_addr_t dma_tx_phy, u32 chan) { /* TX descriptor base address list must be written into DMA CSR4 */ - writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_TX_BASE_ADDR); + writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_CHAN_TX_BASE_ADDR(chan)); } static u32 dwmac1000_configure_fc(u32 csr6, int rxfifosz) @@ -153,7 +155,7 @@ static void dwmac1000_dma_operation_mode_rx(struct stmmac_priv *priv, void __iomem *ioaddr, int mode, u32 channel, int fifosz, u8 qmode) { - u32 csr6 = readl(ioaddr + DMA_CONTROL); + u32 csr6 = readl(ioaddr + DMA_CHAN_CONTROL(channel)); if (mode == SF_DMA_MODE) { pr_debug("GMAC: enable RX store and forward mode\n"); @@ -175,14 +177,14 @@ static void dwmac1000_dma_operation_mode_rx(struct stmmac_priv *priv, /* Configure flow control based on rx fifo size */ csr6 = dwmac1000_configure_fc(csr6, fifosz); - writel(csr6, ioaddr + DMA_CONTROL); + writel(csr6, ioaddr + DMA_CHAN_CONTROL(channel)); } static void dwmac1000_dma_operation_mode_tx(struct stmmac_priv *priv, void __iomem *ioaddr, int mode, u32 channel, int fifosz, u8 qmode) { - u32 csr6 = readl(ioaddr + DMA_CONTROL); + u32 csr6 = readl(ioaddr + DMA_CHAN_CONTROL(channel)); if (mode == SF_DMA_MODE) { pr_debug("GMAC: enable TX store and forward mode\n"); @@ -209,7 +211,7 @@ static void dwmac1000_dma_operation_mode_tx(struct stmmac_priv *priv, csr6 |= DMA_CONTROL_TTC_256; } - writel(csr6, ioaddr + DMA_CONTROL); + writel(csr6, ioaddr + DMA_CHAN_CONTROL(channel)); } static void dwmac1000_dump_dma_regs(struct stmmac_priv *priv, @@ -271,12 +273,12 @@ static int dwmac1000_get_hw_feature(void __iomem *ioaddr, static void dwmac1000_rx_watchdog(struct stmmac_priv *priv, void __iomem *ioaddr, u32 riwt, u32 queue) { - writel(riwt, ioaddr + DMA_RX_WATCHDOG); + writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(queue)); } const struct stmmac_dma_ops dwmac1000_dma_ops = { .reset = dwmac_dma_reset, - .init = dwmac1000_dma_init, + .init_chan = dwmac1000_dma_init_channel, .init_rx_chan = dwmac1000_dma_init_rx, .init_tx_chan = dwmac1000_dma_init_tx, .axi = dwmac1000_dma_axi, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h index 72672391675f6..5d9c18f5bbf58 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h @@ -22,6 +22,31 @@ #define DMA_INTR_ENA 0x0000101c /* Interrupt Enable */ #define DMA_MISSED_FRAME_CTR 0x00001020 /* Missed Frame Counter */ +/* Following DMA defines are channels oriented */ +#define DMA_CHAN_BASE_OFFSET 0x100 + +static inline u32 dma_chan_base_addr(u32 base, u32 chan) +{ + return base + chan * DMA_CHAN_BASE_OFFSET; +} + +#define DMA_CHAN_BUS_MODE(chan) dma_chan_base_addr(DMA_BUS_MODE, chan) +#define DMA_CHAN_XMT_POLL_DEMAND(chan) \ + dma_chan_base_addr(DMA_XMT_POLL_DEMAND, chan) +#define DMA_CHAN_RCV_POLL_DEMAND(chan) \ + dma_chan_base_addr(DMA_RCV_POLL_DEMAND, chan) +#define DMA_CHAN_RCV_BASE_ADDR(chan) \ + dma_chan_base_addr(DMA_RCV_BASE_ADDR, chan) +#define DMA_CHAN_TX_BASE_ADDR(chan) \ + dma_chan_base_addr(DMA_TX_BASE_ADDR, chan) +#define DMA_CHAN_STATUS(chan) dma_chan_base_addr(DMA_STATUS, chan) +#define DMA_CHAN_CONTROL(chan) dma_chan_base_addr(DMA_CONTROL, chan) +#define DMA_CHAN_INTR_ENA(chan) dma_chan_base_addr(DMA_INTR_ENA, chan) +#define DMA_CHAN_MISSED_FRAME_CTR(chan) \ + dma_chan_base_addr(DMA_MISSED_FRAME_CTR, chan) +#define DMA_CHAN_RX_WATCHDOG(chan) \ + dma_chan_base_addr(DMA_RX_WATCHDOG, chan) + /* SW Reset */ #define DMA_BUS_MODE_SFT_RESET 0x00000001 /* Software Reset */ @@ -152,7 +177,7 @@ #define NUM_DWMAC1000_DMA_REGS 23 #define NUM_DWMAC4_DMA_REGS 27 -void dwmac_enable_dma_transmission(void __iomem *ioaddr); +void dwmac_enable_dma_transmission(void __iomem *ioaddr, u32 chan); void dwmac_enable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan, bool rx, bool tx); void dwmac_disable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index 85e18f9a22f92..4846bf49c576a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -28,65 +28,65 @@ int dwmac_dma_reset(void __iomem *ioaddr) } /* CSR1 enables the transmit DMA to check for new descriptor */ -void dwmac_enable_dma_transmission(void __iomem *ioaddr) +void dwmac_enable_dma_transmission(void __iomem *ioaddr, u32 chan) { - writel(1, ioaddr + DMA_XMT_POLL_DEMAND); + writel(1, ioaddr + DMA_CHAN_XMT_POLL_DEMAND(chan)); } void dwmac_enable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan, bool rx, bool tx) { - u32 value = readl(ioaddr + DMA_INTR_ENA); + u32 value = readl(ioaddr + DMA_CHAN_INTR_ENA(chan)); if (rx) value |= DMA_INTR_DEFAULT_RX; if (tx) value |= DMA_INTR_DEFAULT_TX; - writel(value, ioaddr + DMA_INTR_ENA); + writel(value, ioaddr + DMA_CHAN_INTR_ENA(chan)); } void dwmac_disable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan, bool rx, bool tx) { - u32 value = readl(ioaddr + DMA_INTR_ENA); + u32 value = readl(ioaddr + DMA_CHAN_INTR_ENA(chan)); if (rx) value &= ~DMA_INTR_DEFAULT_RX; if (tx) value &= ~DMA_INTR_DEFAULT_TX; - writel(value, ioaddr + DMA_INTR_ENA); + writel(value, ioaddr + DMA_CHAN_INTR_ENA(chan)); } void dwmac_dma_start_tx(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CONTROL); + u32 value = readl(ioaddr + DMA_CHAN_CONTROL(chan)); value |= DMA_CONTROL_ST; - writel(value, ioaddr + DMA_CONTROL); + writel(value, ioaddr + DMA_CHAN_CONTROL(chan)); } void dwmac_dma_stop_tx(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CONTROL); + u32 value = readl(ioaddr + DMA_CHAN_CONTROL(chan)); value &= ~DMA_CONTROL_ST; - writel(value, ioaddr + DMA_CONTROL); + writel(value, ioaddr + DMA_CHAN_CONTROL(chan)); } void dwmac_dma_start_rx(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CONTROL); + u32 value = readl(ioaddr + DMA_CHAN_CONTROL(chan)); value |= DMA_CONTROL_SR; - writel(value, ioaddr + DMA_CONTROL); + writel(value, ioaddr + DMA_CHAN_CONTROL(chan)); } void dwmac_dma_stop_rx(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CONTROL); + u32 value = readl(ioaddr + DMA_CHAN_CONTROL(chan)); value &= ~DMA_CONTROL_SR; - writel(value, ioaddr + DMA_CONTROL); + writel(value, ioaddr + DMA_CHAN_CONTROL(chan)); } #ifdef DWMAC_DMA_DEBUG @@ -165,7 +165,7 @@ int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats); int ret = 0; /* read the status register (CSR5) */ - u32 intr_status = readl(ioaddr + DMA_STATUS); + u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan)); #ifdef DWMAC_DMA_DEBUG /* Enable it to monitor DMA rx/tx status in case of critical problems */ diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 1c99c99f46279..7e90f34b8c882 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -197,7 +197,7 @@ struct stmmac_dma_ops { /* To track extra statistic (if supported) */ void (*dma_diagnostic_fr)(struct stmmac_extra_stats *x, void __iomem *ioaddr); - void (*enable_dma_transmission) (void __iomem *ioaddr); + void (*enable_dma_transmission)(void __iomem *ioaddr, u32 chan); void (*enable_dma_irq)(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan, bool rx, bool tx); void (*disable_dma_irq)(struct stmmac_priv *priv, void __iomem *ioaddr, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 9f1286835550e..d9fca8d1227c5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2367,9 +2367,11 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) if (txfifosz == 0) txfifosz = priv->dma_cap.tx_fifo_size; - /* Adjust for real per queue fifo size */ - rxfifosz /= rx_channels_count; - txfifosz /= tx_channels_count; + /* Split up the shared Tx/Rx FIFO memory on DW QoS Eth and DW XGMAC */ + if (priv->plat->has_gmac4 || priv->plat->has_xgmac) { + rxfifosz /= rx_channels_count; + txfifosz /= tx_channels_count; + } if (priv->plat->force_thresh_dma_mode) { txmode = tc; @@ -2553,7 +2555,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) true, priv->mode, true, true, xdp_desc.len); - stmmac_enable_dma_transmission(priv, priv->ioaddr); + stmmac_enable_dma_transmission(priv, priv->ioaddr, queue); xsk_tx_metadata_to_compl(meta, &tx_q->tx_skbuff_dma[entry].xsk_meta); @@ -4753,7 +4755,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len); - stmmac_enable_dma_transmission(priv, priv->ioaddr); + stmmac_enable_dma_transmission(priv, priv->ioaddr, queue); stmmac_flush_tx_descriptors(priv, queue); stmmac_tx_timer_arm(priv, queue); @@ -4980,7 +4982,7 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue, u64_stats_update_end(&txq_stats->q_syncp); } - stmmac_enable_dma_transmission(priv, priv->ioaddr); + stmmac_enable_dma_transmission(priv, priv->ioaddr, queue); entry = STMMAC_GET_ENTRY(entry, priv->dma_conf.dma_tx_size); tx_q->cur_tx = entry; From 005c0f071bc1db6a6972d598a265c0e45bca4038 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:45:30 +0800 Subject: [PATCH 086/385] net: stmmac: Export dwmac1000_dma_ops Export the DW GMAC DMA-ops descriptor so one could be available in the low-level platform drivers. It will be utilized to override some callbacks in order to handle the LS2K2000 GNET device specifics. The GNET controller support is being added in one of the following up commits. Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Reviewed-by: Serge Semin Acked-by: Huacai Chen Signed-off-by: Yanteng Si Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c index b3d7eff53b180..118a22406a2e9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c @@ -296,3 +296,4 @@ const struct stmmac_dma_ops dwmac1000_dma_ops = { .get_hw_feature = dwmac1000_get_hw_feature, .rx_watchdog = dwmac1000_rx_watchdog, }; +EXPORT_SYMBOL_GPL(dwmac1000_dma_ops); From 393ea68bf154a53a108bde4bd387fa85b3662181 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:47:07 +0800 Subject: [PATCH 087/385] net: stmmac: dwmac-loongson: Drop duplicated hash-based filter size init The plat_stmmacenet_data::multicast_filter_bins field is twice initialized in the loongson_default_data() method. Drop the redundant initialization, but for the readability sake keep the filters init statements defined in the same place of the method. Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Reviewed-by: Serge Semin Acked-by: Huacai Chen Signed-off-by: Yanteng Si Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 9e40c28d453ab..9dbd117663645 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -16,7 +16,7 @@ static int loongson_default_data(struct plat_stmmacenet_data *plat) plat->force_sf_dma_mode = 1; /* Set default value for multicast hash bins */ - plat->multicast_filter_bins = HASH_TABLE_SIZE; + plat->multicast_filter_bins = 256; /* Set default value for unicast filter entries */ plat->unicast_filter_entries = 1; @@ -41,7 +41,6 @@ static int loongson_default_data(struct plat_stmmacenet_data *plat) plat->dma_cfg->pbl = 32; plat->dma_cfg->pblx8 = true; - plat->multicast_filter_bins = 256; return 0; } From 0c979e6b55f99f939bb8158f3d8f8d2072b04e9c Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:47:08 +0800 Subject: [PATCH 088/385] net: stmmac: dwmac-loongson: Drop pci_enable/disable_msi calls The Loongson GMAC driver currently doesn't utilize the MSI IRQs, but retrieves the IRQs specified in the device DT-node. Let's drop the direct pci_enable_msi()/pci_disable_msi() calls then as redundant Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Reviewed-by: Serge Semin Acked-by: Huacai Chen Signed-off-by: Yanteng Si Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 9dbd117663645..32814afdf3216 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -114,7 +114,6 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id pci_set_master(pdev); loongson_default_data(plat); - pci_enable_msi(pdev); memset(&res, 0, sizeof(res)); res.addr = pcim_iomap_table(pdev)[0]; @@ -122,7 +121,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id if (res.irq < 0) { dev_err(&pdev->dev, "IRQ macirq not found\n"); ret = -ENODEV; - goto err_disable_msi; + goto err_disable_device; } res.wol_irq = of_irq_get_byname(np, "eth_wake_irq"); @@ -135,17 +134,15 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id if (res.lpi_irq < 0) { dev_err(&pdev->dev, "IRQ eth_lpi not found\n"); ret = -ENODEV; - goto err_disable_msi; + goto err_disable_device; } ret = stmmac_dvr_probe(&pdev->dev, plat, &res); if (ret) - goto err_disable_msi; + goto err_disable_device; return ret; -err_disable_msi: - pci_disable_msi(pdev); err_disable_device: pci_disable_device(pdev); err_put_node: @@ -169,7 +166,6 @@ static void loongson_dwmac_remove(struct pci_dev *pdev) break; } - pci_disable_msi(pdev); pci_disable_device(pdev); } From 324d96b46520f1476f25deaad0e49d8df71377c1 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:47:09 +0800 Subject: [PATCH 089/385] net: stmmac: dwmac-loongson: Use PCI_DEVICE_DATA() macro for device identification For the readability sake convert the hard-coded Loongson GMAC PCI ID to the respective macro and use the PCI_DEVICE_DATA() macro-function to create the pci_device_id array entry. The later change will be specifically useful in order to assign the device-specific data for the currently supported device and for about to be added Loongson GNET controller. Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Reviewed-by: Serge Semin Acked-by: Huacai Chen Signed-off-by: Yanteng Si Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 32814afdf3216..f39c13a74bb57 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -9,6 +9,8 @@ #include #include "stmmac.h" +#define PCI_DEVICE_ID_LOONGSON_GMAC 0x7a03 + static int loongson_default_data(struct plat_stmmacenet_data *plat) { plat->clk_csr = 2; /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */ @@ -208,7 +210,7 @@ static SIMPLE_DEV_PM_OPS(loongson_dwmac_pm_ops, loongson_dwmac_suspend, loongson_dwmac_resume); static const struct pci_device_id loongson_dwmac_id_table[] = { - { PCI_VDEVICE(LOONGSON, 0x7a03) }, + { PCI_DEVICE_DATA(LOONGSON, GMAC, NULL) }, {} }; MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table); From 79afc70002c20753aaed41a5083cf936148832b1 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:47:10 +0800 Subject: [PATCH 090/385] net: stmmac: dwmac-loongson: Detach GMAC-specific platform data init Loongson delivers two types of the network devices: Loongson GMAC and Loongson GNET in the framework of four SOC/Chipsets revisions: Chip Network PCI Dev ID Synopys Version DMA-channel LS2K1000 SOC GMAC 0x7a03 v3.50a/v3.73a 1 LS7A1000 Chipset GMAC 0x7a03 v3.50a/v3.73a 1 LS2K2000 SOC GMAC 0x7a03 v3.73a 8 LS2K2000 SOC GNET 0x7a13 v3.73a 8 LS7A2000 Chipset GNET 0x7a13 v3.73a 1 The driver currently supports the chips with the Loongson GMAC network device synthesized with a single DMA-channel available. As a preparation before adding the Loongson GNET support detach the Loongson GMAC-specific platform data initializations to the loongson_gmac_data() method and preserve the common settings in the loongson_default_data(). While at it drop the return value statement from the loongson_default_data() method as redundant. Note there is no intermediate vendor-specific PCS in between the MAC and PHY on Loongson GMAC and GNET. So the plat->mac_interface field can be freely initialized with the PHY_INTERFACE_MODE_NA value. Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Reviewed-by: Serge Semin Acked-by: Huacai Chen Signed-off-by: Yanteng Si Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- .../ethernet/stmicro/stmmac/dwmac-loongson.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index f39c13a74bb57..9b2e4bdf7cc76 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -11,7 +11,7 @@ #define PCI_DEVICE_ID_LOONGSON_GMAC 0x7a03 -static int loongson_default_data(struct plat_stmmacenet_data *plat) +static void loongson_default_data(struct plat_stmmacenet_data *plat) { plat->clk_csr = 2; /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */ plat->has_gmac = 1; @@ -20,16 +20,14 @@ static int loongson_default_data(struct plat_stmmacenet_data *plat) /* Set default value for multicast hash bins */ plat->multicast_filter_bins = 256; + plat->mac_interface = PHY_INTERFACE_MODE_NA; + /* Set default value for unicast filter entries */ plat->unicast_filter_entries = 1; /* Set the maxmtu to a default of JUMBO_LEN */ plat->maxmtu = JUMBO_LEN; - /* Set default number of RX and TX queues to use */ - plat->tx_queues_to_use = 1; - plat->rx_queues_to_use = 1; - /* Disable Priority config by default */ plat->tx_queues_cfg[0].use_prio = false; plat->rx_queues_cfg[0].use_prio = false; @@ -42,6 +40,14 @@ static int loongson_default_data(struct plat_stmmacenet_data *plat) plat->dma_cfg->pbl = 32; plat->dma_cfg->pblx8 = true; +} + +static int loongson_gmac_data(struct plat_stmmacenet_data *plat) +{ + loongson_default_data(plat); + + plat->tx_queues_to_use = 1; + plat->rx_queues_to_use = 1; return 0; } @@ -111,11 +117,10 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id } plat->phy_interface = phy_mode; - plat->mac_interface = PHY_INTERFACE_MODE_GMII; pci_set_master(pdev); - loongson_default_data(plat); + loongson_gmac_data(plat); memset(&res, 0, sizeof(res)); res.addr = pcim_iomap_table(pdev)[0]; From c70f3163681381c15686bdd2fe56bf4af9b8aaaa Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:48:02 +0800 Subject: [PATCH 091/385] net: stmmac: dwmac-loongson: Init ref and PTP clocks rate Reference and PTP clocks rate of the Loongson GMAC devices is 125MHz. (So is in the GNET devices which support is about to be added.) Set the respective plat_stmmacenet_data field up in accordance with that so to have the coalesce command and timestamping work correctly. Fixes: 30bba69d7db4 ("stmmac: pci: Add dwmac support for Loongson") Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Reviewed-by: Serge Semin Acked-by: Huacai Chen Signed-off-by: Yanteng Si Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 9b2e4bdf7cc76..327275b28dc2c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -35,6 +35,9 @@ static void loongson_default_data(struct plat_stmmacenet_data *plat) /* Disable RX queues routing by default */ plat->rx_queues_cfg[0].pkt_route = 0x0; + plat->clk_ref_rate = 125000000; + plat->clk_ptp_rate = 125000000; + /* Default to phy auto-detection */ plat->phy_addr = -1; From 849dc7341d1f48dacdeadb86eb09f6d7777b1e5e Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:48:03 +0800 Subject: [PATCH 092/385] net: stmmac: dwmac-loongson: Add phy_interface for Loongson GMAC PHY-interface of the Loongson GMAC device is RGMII with no internal delays added to the data lines signal. So to comply with that let's pre-initialize the platform-data field with the respective enum constant. Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Reviewed-by: Serge Semin Acked-by: Huacai Chen Signed-off-by: Yanteng Si Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 327275b28dc2c..7d3f284b9176c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -52,6 +52,8 @@ static int loongson_gmac_data(struct plat_stmmacenet_data *plat) plat->tx_queues_to_use = 1; plat->rx_queues_to_use = 1; + plat->phy_interface = PHY_INTERFACE_MODE_RGMII_ID; + return 0; } From 0ec04d32b5e7f03f1a18713a4958a056240763c8 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:48:04 +0800 Subject: [PATCH 093/385] net: stmmac: dwmac-loongson: Introduce PCI device info data The Loongson GNET device support is about to be added in one of the next commits. As another preparation for that introduce the PCI device info data with a setup() callback performing the device-specific platform data initializations. Currently it is utilized for the already supported Loongson GMAC device only. Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Reviewed-by: Serge Semin Acked-by: Huacai Chen Signed-off-by: Yanteng Si Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- .../ethernet/stmicro/stmmac/dwmac-loongson.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 7d3f284b9176c..10b49bea8e3cd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -11,6 +11,10 @@ #define PCI_DEVICE_ID_LOONGSON_GMAC 0x7a03 +struct stmmac_pci_info { + int (*setup)(struct plat_stmmacenet_data *plat); +}; + static void loongson_default_data(struct plat_stmmacenet_data *plat) { plat->clk_csr = 2; /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */ @@ -57,9 +61,14 @@ static int loongson_gmac_data(struct plat_stmmacenet_data *plat) return 0; } +static struct stmmac_pci_info loongson_gmac_pci_info = { + .setup = loongson_gmac_data, +}; + static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct plat_stmmacenet_data *plat; + struct stmmac_pci_info *info; struct stmmac_resources res; struct device_node *np; int ret, i, phy_mode; @@ -125,10 +134,14 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id pci_set_master(pdev); - loongson_gmac_data(plat); memset(&res, 0, sizeof(res)); res.addr = pcim_iomap_table(pdev)[0]; + info = (struct stmmac_pci_info *)id->driver_data; + ret = info->setup(plat); + if (ret) + goto err_disable_device; + res.irq = of_irq_get_byname(np, "macirq"); if (res.irq < 0) { dev_err(&pdev->dev, "IRQ macirq not found\n"); @@ -220,7 +233,7 @@ static SIMPLE_DEV_PM_OPS(loongson_dwmac_pm_ops, loongson_dwmac_suspend, loongson_dwmac_resume); static const struct pci_device_id loongson_dwmac_id_table[] = { - { PCI_DEVICE_DATA(LOONGSON, GMAC, NULL) }, + { PCI_DEVICE_DATA(LOONGSON, GMAC, &loongson_gmac_pci_info) }, {} }; MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table); From 126f4f96c41d2efe9ea1b949ff3e6d997010991e Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:48:05 +0800 Subject: [PATCH 094/385] net: stmmac: dwmac-loongson: Add DT-less GMAC PCI-device support The Loongson GMAC driver currently supports the network controllers installed on the LS2K1000 SoC and LS7A1000 chipset, for which the GMAC devices are required to be defined in the platform device tree source. But Loongson machines may have UEFI (implies ACPI) or PMON/UBOOT (implies FDT) as the system bootloaders. In order to have both system configurations support let's extend the driver functionality with the case of having the Loongson GMAC probed on the PCI bus with no device tree node defined for it. That requires to make the device DT-node optional, to rely on the IRQ line detected by the PCI core and to have the MDIO bus ID calculated using the PCIe Domain+BDF numbers. In order to have the device probe() and remove() methods less complicated let's move the DT- and ACPI-specific code to the respective sub-functions. Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Acked-by: Huacai Chen Signed-off-by: Yanteng Si Reviewed-by: Serge Semin Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- .../ethernet/stmicro/stmmac/dwmac-loongson.c | 165 +++++++++++------- 1 file changed, 102 insertions(+), 63 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 10b49bea8e3cd..c0740a41025bd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -12,11 +12,15 @@ #define PCI_DEVICE_ID_LOONGSON_GMAC 0x7a03 struct stmmac_pci_info { - int (*setup)(struct plat_stmmacenet_data *plat); + int (*setup)(struct pci_dev *pdev, struct plat_stmmacenet_data *plat); }; -static void loongson_default_data(struct plat_stmmacenet_data *plat) +static void loongson_default_data(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) { + /* Get bus_id, this can be overwritten later */ + plat->bus_id = pci_dev_id(pdev); + plat->clk_csr = 2; /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */ plat->has_gmac = 1; plat->force_sf_dma_mode = 1; @@ -49,9 +53,10 @@ static void loongson_default_data(struct plat_stmmacenet_data *plat) plat->dma_cfg->pblx8 = true; } -static int loongson_gmac_data(struct plat_stmmacenet_data *plat) +static int loongson_gmac_data(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) { - loongson_default_data(plat); + loongson_default_data(pdev, plat); plat->tx_queues_to_use = 1; plat->rx_queues_to_use = 1; @@ -65,20 +70,85 @@ static struct stmmac_pci_info loongson_gmac_pci_info = { .setup = loongson_gmac_data, }; +static int loongson_dwmac_dt_config(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat, + struct stmmac_resources *res) +{ + struct device_node *np = dev_of_node(&pdev->dev); + int ret; + + plat->mdio_node = of_get_child_by_name(np, "mdio"); + if (plat->mdio_node) { + dev_info(&pdev->dev, "Found MDIO subnode\n"); + plat->mdio_bus_data->needs_reset = true; + } + + ret = of_alias_get_id(np, "ethernet"); + if (ret >= 0) + plat->bus_id = ret; + + res->irq = of_irq_get_byname(np, "macirq"); + if (res->irq < 0) { + dev_err(&pdev->dev, "IRQ macirq not found\n"); + ret = -ENODEV; + goto err_put_node; + } + + res->wol_irq = of_irq_get_byname(np, "eth_wake_irq"); + if (res->wol_irq < 0) { + dev_info(&pdev->dev, + "IRQ eth_wake_irq not found, using macirq\n"); + res->wol_irq = res->irq; + } + + res->lpi_irq = of_irq_get_byname(np, "eth_lpi"); + if (res->lpi_irq < 0) { + dev_err(&pdev->dev, "IRQ eth_lpi not found\n"); + ret = -ENODEV; + goto err_put_node; + } + + ret = device_get_phy_mode(&pdev->dev); + if (ret < 0) { + dev_err(&pdev->dev, "phy_mode not found\n"); + ret = -ENODEV; + goto err_put_node; + } + + plat->phy_interface = ret; + + return 0; + +err_put_node: + of_node_put(plat->mdio_node); + + return ret; +} + +static void loongson_dwmac_dt_clear(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) +{ + of_node_put(plat->mdio_node); +} + +static int loongson_dwmac_acpi_config(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat, + struct stmmac_resources *res) +{ + if (!pdev->irq) + return -EINVAL; + + res->irq = pdev->irq; + + return 0; +} + static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct plat_stmmacenet_data *plat; struct stmmac_pci_info *info; struct stmmac_resources res; - struct device_node *np; - int ret, i, phy_mode; - - np = dev_of_node(&pdev->dev); - - if (!np) { - pr_info("dwmac_loongson_pci: No OF node\n"); - return -ENODEV; - } + int ret, i; plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); if (!plat) @@ -90,25 +160,19 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id if (!plat->mdio_bus_data) return -ENOMEM; - plat->mdio_node = of_get_child_by_name(np, "mdio"); - if (plat->mdio_node) { - dev_info(&pdev->dev, "Found MDIO subnode\n"); - plat->mdio_bus_data->needs_reset = true; - } - plat->dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*plat->dma_cfg), GFP_KERNEL); - if (!plat->dma_cfg) { - ret = -ENOMEM; - goto err_put_node; - } + if (!plat->dma_cfg) + return -ENOMEM; /* Enable pci device */ ret = pci_enable_device(pdev); if (ret) { dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n", __func__); - goto err_put_node; + return ret; } + pci_set_master(pdev); + /* Get the base address of device */ for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pdev, i) == 0) @@ -119,59 +183,32 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id break; } - plat->bus_id = of_alias_get_id(np, "ethernet"); - if (plat->bus_id < 0) - plat->bus_id = pci_dev_id(pdev); - - phy_mode = device_get_phy_mode(&pdev->dev); - if (phy_mode < 0) { - dev_err(&pdev->dev, "phy_mode not found\n"); - ret = phy_mode; - goto err_disable_device; - } - - plat->phy_interface = phy_mode; - - pci_set_master(pdev); - memset(&res, 0, sizeof(res)); res.addr = pcim_iomap_table(pdev)[0]; info = (struct stmmac_pci_info *)id->driver_data; - ret = info->setup(plat); + ret = info->setup(pdev, plat); if (ret) goto err_disable_device; - res.irq = of_irq_get_byname(np, "macirq"); - if (res.irq < 0) { - dev_err(&pdev->dev, "IRQ macirq not found\n"); - ret = -ENODEV; - goto err_disable_device; - } - - res.wol_irq = of_irq_get_byname(np, "eth_wake_irq"); - if (res.wol_irq < 0) { - dev_info(&pdev->dev, "IRQ eth_wake_irq not found, using macirq\n"); - res.wol_irq = res.irq; - } - - res.lpi_irq = of_irq_get_byname(np, "eth_lpi"); - if (res.lpi_irq < 0) { - dev_err(&pdev->dev, "IRQ eth_lpi not found\n"); - ret = -ENODEV; + if (dev_of_node(&pdev->dev)) + ret = loongson_dwmac_dt_config(pdev, plat, &res); + else + ret = loongson_dwmac_acpi_config(pdev, plat, &res); + if (ret) goto err_disable_device; - } ret = stmmac_dvr_probe(&pdev->dev, plat, &res); if (ret) - goto err_disable_device; + goto err_plat_clear; - return ret; + return 0; +err_plat_clear: + if (dev_of_node(&pdev->dev)) + loongson_dwmac_dt_clear(pdev, plat); err_disable_device: pci_disable_device(pdev); -err_put_node: - of_node_put(plat->mdio_node); return ret; } @@ -181,9 +218,11 @@ static void loongson_dwmac_remove(struct pci_dev *pdev) struct stmmac_priv *priv = netdev_priv(ndev); int i; - of_node_put(priv->plat->mdio_node); stmmac_dvr_remove(&pdev->dev); + if (dev_of_node(&pdev->dev)) + loongson_dwmac_dt_clear(pdev, priv->plat); + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pdev, i) == 0) continue; From 803fc61df261dee7dc71fb4f7000c0569e2afff6 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:48:54 +0800 Subject: [PATCH 095/385] net: stmmac: dwmac-loongson: Add Loongson Multi-channels GMAC support The Loongson DWMAC driver currently supports the Loongson GMAC devices (based on the DW GMAC v3.50a/v3.73a IP-core) installed to the LS2K1000 SoC and LS7A1000 chipset. But recently a new generation LS2K2000 SoC was released with the new version of the Loongson GMAC synthesized in. The new controller is based on the DW GMAC v3.73a IP-core with the AV-feature enabled, which implies the multi DMA-channels support. The multi DMA-channels feature has the next vendor-specific peculiarities: 1. Split up Tx and Rx DMA IRQ status/mask bits: Name Tx Rx DMA_INTR_ENA_NIE = 0x00040000 | 0x00020000; DMA_INTR_ENA_AIE = 0x00010000 | 0x00008000; DMA_STATUS_NIS = 0x00040000 | 0x00020000; DMA_STATUS_AIS = 0x00010000 | 0x00008000; DMA_STATUS_FBI = 0x00002000 | 0x00001000; 2. Custom Synopsys ID hardwired into the GMAC_VERSION.SNPSVER register field. It's 0x10 while it should have been 0x37 in accordance with the actual DW GMAC IP-core version. 3. There are eight DMA-channels available meanwhile the Synopsys DW GMAC IP-core supports up to three DMA-channels. 4. It's possible to have each DMA-channel IRQ independently delivered. The MSI IRQs must be utilized for that. Thus in order to have the multi-channels Loongson GMAC controllers supported let's modify the Loongson DWMAC driver in accordance with all the peculiarities described above: 1. Create the multi-channels Loongson GMAC-specific stmmac_dma_ops::dma_interrupt() stmmac_dma_ops::init_chan() callbacks due to the non-standard DMA IRQ CSR flags layout. 2. Create the Loongson DWMAC-specific platform setup() method which gets to initialize the DMA-ops with the dwmac1000_dma_ops instance and overrides the callbacks described in 1. The method also overrides the custom Synopsys ID with the real one in order to have the rest of the HW-specific callbacks correctly detected by the driver core. 3. Make sure the platform setup() method enables the flow control and duplex modes supported by the controller. Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Acked-by: Huacai Chen Signed-off-by: Yanteng Si Reviewed-by: Serge Semin Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- drivers/net/ethernet/stmicro/stmmac/common.h | 1 + .../ethernet/stmicro/stmmac/dwmac-loongson.c | 328 +++++++++++++++++- 2 files changed, 327 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index cd36ff4da68c6..684489156dcee 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -29,6 +29,7 @@ /* Synopsys Core versions */ #define DWMAC_CORE_3_40 0x34 #define DWMAC_CORE_3_50 0x35 +#define DWMAC_CORE_3_70 0x37 #define DWMAC_CORE_4_00 0x40 #define DWMAC_CORE_4_10 0x41 #define DWMAC_CORE_5_00 0x50 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index c0740a41025bd..48c92ba826d9e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -8,8 +8,69 @@ #include #include #include "stmmac.h" +#include "dwmac_dma.h" +#include "dwmac1000.h" + +/* Normal Loongson Tx Summary */ +#define DMA_INTR_ENA_NIE_TX_LOONGSON 0x00040000 +/* Normal Loongson Rx Summary */ +#define DMA_INTR_ENA_NIE_RX_LOONGSON 0x00020000 + +#define DMA_INTR_NORMAL_LOONGSON (DMA_INTR_ENA_NIE_TX_LOONGSON | \ + DMA_INTR_ENA_NIE_RX_LOONGSON | \ + DMA_INTR_ENA_RIE | DMA_INTR_ENA_TIE) + +/* Abnormal Loongson Tx Summary */ +#define DMA_INTR_ENA_AIE_TX_LOONGSON 0x00010000 +/* Abnormal Loongson Rx Summary */ +#define DMA_INTR_ENA_AIE_RX_LOONGSON 0x00008000 + +#define DMA_INTR_ABNORMAL_LOONGSON (DMA_INTR_ENA_AIE_TX_LOONGSON | \ + DMA_INTR_ENA_AIE_RX_LOONGSON | \ + DMA_INTR_ENA_FBE | DMA_INTR_ENA_UNE) + +#define DMA_INTR_DEFAULT_MASK_LOONGSON (DMA_INTR_NORMAL_LOONGSON | \ + DMA_INTR_ABNORMAL_LOONGSON) + +/* Normal Loongson Tx Interrupt Summary */ +#define DMA_STATUS_NIS_TX_LOONGSON 0x00040000 +/* Normal Loongson Rx Interrupt Summary */ +#define DMA_STATUS_NIS_RX_LOONGSON 0x00020000 + +/* Abnormal Loongson Tx Interrupt Summary */ +#define DMA_STATUS_AIS_TX_LOONGSON 0x00010000 +/* Abnormal Loongson Rx Interrupt Summary */ +#define DMA_STATUS_AIS_RX_LOONGSON 0x00008000 + +/* Fatal Loongson Tx Bus Error Interrupt */ +#define DMA_STATUS_FBI_TX_LOONGSON 0x00002000 +/* Fatal Loongson Rx Bus Error Interrupt */ +#define DMA_STATUS_FBI_RX_LOONGSON 0x00001000 + +#define DMA_STATUS_MSK_COMMON_LOONGSON (DMA_STATUS_NIS_TX_LOONGSON | \ + DMA_STATUS_NIS_RX_LOONGSON | \ + DMA_STATUS_AIS_TX_LOONGSON | \ + DMA_STATUS_AIS_RX_LOONGSON | \ + DMA_STATUS_FBI_TX_LOONGSON | \ + DMA_STATUS_FBI_RX_LOONGSON) + +#define DMA_STATUS_MSK_RX_LOONGSON (DMA_STATUS_ERI | DMA_STATUS_RWT | \ + DMA_STATUS_RPS | DMA_STATUS_RU | \ + DMA_STATUS_RI | DMA_STATUS_OVF | \ + DMA_STATUS_MSK_COMMON_LOONGSON) + +#define DMA_STATUS_MSK_TX_LOONGSON (DMA_STATUS_ETI | DMA_STATUS_UNF | \ + DMA_STATUS_TJT | DMA_STATUS_TU | \ + DMA_STATUS_TPS | DMA_STATUS_TI | \ + DMA_STATUS_MSK_COMMON_LOONGSON) #define PCI_DEVICE_ID_LOONGSON_GMAC 0x7a03 +#define DWMAC_CORE_LS_MULTICHAN 0x10 /* Loongson custom ID */ +#define CHANNEL_NUM 8 + +struct loongson_data { + u32 loongson_id; +}; struct stmmac_pci_info { int (*setup)(struct pci_dev *pdev, struct plat_stmmacenet_data *plat); @@ -56,10 +117,26 @@ static void loongson_default_data(struct pci_dev *pdev, static int loongson_gmac_data(struct pci_dev *pdev, struct plat_stmmacenet_data *plat) { + struct loongson_data *ld; + int i; + + ld = plat->bsp_priv; + loongson_default_data(pdev, plat); - plat->tx_queues_to_use = 1; - plat->rx_queues_to_use = 1; + if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) { + plat->rx_queues_to_use = CHANNEL_NUM; + plat->tx_queues_to_use = CHANNEL_NUM; + + /* Only channel 0 supports checksum, + * so turn off checksum to enable multiple channels. + */ + for (i = 1; i < CHANNEL_NUM; i++) + plat->tx_queues_cfg[i].coe_unsupported = 1; + } else { + plat->tx_queues_to_use = 1; + plat->rx_queues_to_use = 1; + } plat->phy_interface = PHY_INTERFACE_MODE_RGMII_ID; @@ -70,6 +147,233 @@ static struct stmmac_pci_info loongson_gmac_pci_info = { .setup = loongson_gmac_data, }; +static void loongson_dwmac_dma_init_channel(struct stmmac_priv *priv, + void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, + u32 chan) +{ + int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl; + int rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl; + u32 value; + + value = readl(ioaddr + DMA_CHAN_BUS_MODE(chan)); + + if (dma_cfg->pblx8) + value |= DMA_BUS_MODE_MAXPBL; + + value |= DMA_BUS_MODE_USP; + value &= ~(DMA_BUS_MODE_PBL_MASK | DMA_BUS_MODE_RPBL_MASK); + value |= (txpbl << DMA_BUS_MODE_PBL_SHIFT); + value |= (rxpbl << DMA_BUS_MODE_RPBL_SHIFT); + + /* Set the Fixed burst mode */ + if (dma_cfg->fixed_burst) + value |= DMA_BUS_MODE_FB; + + /* Mixed Burst has no effect when fb is set */ + if (dma_cfg->mixed_burst) + value |= DMA_BUS_MODE_MB; + + if (dma_cfg->atds) + value |= DMA_BUS_MODE_ATDS; + + if (dma_cfg->aal) + value |= DMA_BUS_MODE_AAL; + + writel(value, ioaddr + DMA_CHAN_BUS_MODE(chan)); + + /* Mask interrupts by writing to CSR7 */ + writel(DMA_INTR_DEFAULT_MASK_LOONGSON, ioaddr + + DMA_CHAN_INTR_ENA(chan)); +} + +static int loongson_dwmac_dma_interrupt(struct stmmac_priv *priv, + void __iomem *ioaddr, + struct stmmac_extra_stats *x, + u32 chan, u32 dir) +{ + struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats); + u32 abnor_intr_status; + u32 nor_intr_status; + u32 fb_intr_status; + u32 intr_status; + int ret = 0; + + /* read the status register (CSR5) */ + intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan)); + + if (dir == DMA_DIR_RX) + intr_status &= DMA_STATUS_MSK_RX_LOONGSON; + else if (dir == DMA_DIR_TX) + intr_status &= DMA_STATUS_MSK_TX_LOONGSON; + + nor_intr_status = intr_status & (DMA_STATUS_NIS_TX_LOONGSON | + DMA_STATUS_NIS_RX_LOONGSON); + abnor_intr_status = intr_status & (DMA_STATUS_AIS_TX_LOONGSON | + DMA_STATUS_AIS_RX_LOONGSON); + fb_intr_status = intr_status & (DMA_STATUS_FBI_TX_LOONGSON | + DMA_STATUS_FBI_RX_LOONGSON); + + /* ABNORMAL interrupts */ + if (unlikely(abnor_intr_status)) { + if (unlikely(intr_status & DMA_STATUS_UNF)) { + ret = tx_hard_error_bump_tc; + x->tx_undeflow_irq++; + } + if (unlikely(intr_status & DMA_STATUS_TJT)) + x->tx_jabber_irq++; + if (unlikely(intr_status & DMA_STATUS_OVF)) + x->rx_overflow_irq++; + if (unlikely(intr_status & DMA_STATUS_RU)) + x->rx_buf_unav_irq++; + if (unlikely(intr_status & DMA_STATUS_RPS)) + x->rx_process_stopped_irq++; + if (unlikely(intr_status & DMA_STATUS_RWT)) + x->rx_watchdog_irq++; + if (unlikely(intr_status & DMA_STATUS_ETI)) + x->tx_early_irq++; + if (unlikely(intr_status & DMA_STATUS_TPS)) { + x->tx_process_stopped_irq++; + ret = tx_hard_error; + } + if (unlikely(fb_intr_status)) { + x->fatal_bus_error_irq++; + ret = tx_hard_error; + } + } + /* TX/RX NORMAL interrupts */ + if (likely(nor_intr_status)) { + if (likely(intr_status & DMA_STATUS_RI)) { + u32 value = readl(ioaddr + DMA_INTR_ENA); + /* to schedule NAPI on real RIE event. */ + if (likely(value & DMA_INTR_ENA_RIE)) { + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->rx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); + ret |= handle_rx; + } + } + if (likely(intr_status & DMA_STATUS_TI)) { + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->tx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); + ret |= handle_tx; + } + if (unlikely(intr_status & DMA_STATUS_ERI)) + x->rx_early_irq++; + } + /* Optional hardware blocks, interrupts should be disabled */ + if (unlikely(intr_status & + (DMA_STATUS_GPI | DMA_STATUS_GMI | DMA_STATUS_GLI))) + pr_warn("%s: unexpected status %08x\n", __func__, intr_status); + + /* Clear the interrupt by writing a logic 1 to the CSR5[19-0] */ + writel((intr_status & 0x7ffff), ioaddr + DMA_CHAN_STATUS(chan)); + + return ret; +} + +static struct mac_device_info *loongson_dwmac_setup(void *apriv) +{ + struct stmmac_priv *priv = apriv; + struct mac_device_info *mac; + struct stmmac_dma_ops *dma; + struct loongson_data *ld; + + ld = priv->plat->bsp_priv; + + mac = devm_kzalloc(priv->device, sizeof(*mac), GFP_KERNEL); + if (!mac) + return NULL; + + dma = devm_kzalloc(priv->device, sizeof(*dma), GFP_KERNEL); + if (!dma) + return NULL; + + /* The Loongson GMAC devices are based on the DW GMAC + * v3.50a and v3.73a IP-cores. But the HW designers have changed the + * GMAC_VERSION.SNPSVER field to the custom 0x10 value on the + * network controllers with the multi-channels feature + * available to emphasize the differences: multiple DMA-channels, + * AV feature and GMAC_INT_STATUS CSR flags layout. Get back the + * original value so the correct HW-interface would be selected. + */ + if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) { + priv->synopsys_id = DWMAC_CORE_3_70; + *dma = dwmac1000_dma_ops; + dma->init_chan = loongson_dwmac_dma_init_channel; + dma->dma_interrupt = loongson_dwmac_dma_interrupt; + mac->dma = dma; + } + + priv->dev->priv_flags |= IFF_UNICAST_FLT; + + /* Pre-initialize the respective "mac" fields as it's done in + * dwmac1000_setup() + */ + mac->pcsr = priv->ioaddr; + mac->multicast_filter_bins = priv->plat->multicast_filter_bins; + mac->unicast_filter_entries = priv->plat->unicast_filter_entries; + mac->mcast_bits_log2 = 0; + + if (mac->multicast_filter_bins) + mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + + /* Loongson GMAC doesn't support the flow control. */ + mac->link.caps = MAC_10 | MAC_100 | MAC_1000; + + mac->link.duplex = GMAC_CONTROL_DM; + mac->link.speed10 = GMAC_CONTROL_PS; + mac->link.speed100 = GMAC_CONTROL_PS | GMAC_CONTROL_FES; + mac->link.speed1000 = 0; + mac->link.speed_mask = GMAC_CONTROL_PS | GMAC_CONTROL_FES; + mac->mii.addr = GMAC_MII_ADDR; + mac->mii.data = GMAC_MII_DATA; + mac->mii.addr_shift = 11; + mac->mii.addr_mask = 0x0000F800; + mac->mii.reg_shift = 6; + mac->mii.reg_mask = 0x000007C0; + mac->mii.clk_csr_shift = 2; + mac->mii.clk_csr_mask = GENMASK(5, 2); + + return mac; +} + +static int loongson_dwmac_msi_config(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat, + struct stmmac_resources *res) +{ + int i, ret, vecs; + + vecs = roundup_pow_of_two(CHANNEL_NUM * 2 + 1); + ret = pci_alloc_irq_vectors(pdev, vecs, vecs, PCI_IRQ_MSI); + if (ret < 0) { + dev_warn(&pdev->dev, "Failed to allocate MSI IRQs\n"); + return ret; + } + + res->irq = pci_irq_vector(pdev, 0); + + for (i = 0; i < plat->rx_queues_to_use; i++) { + res->rx_irq[CHANNEL_NUM - 1 - i] = + pci_irq_vector(pdev, 1 + i * 2); + } + + for (i = 0; i < plat->tx_queues_to_use; i++) { + res->tx_irq[CHANNEL_NUM - 1 - i] = + pci_irq_vector(pdev, 2 + i * 2); + } + + plat->flags |= STMMAC_FLAG_MULTI_MSI_EN; + + return 0; +} + +static void loongson_dwmac_msi_clear(struct pci_dev *pdev) +{ + pci_free_irq_vectors(pdev); +} + static int loongson_dwmac_dt_config(struct pci_dev *pdev, struct plat_stmmacenet_data *plat, struct stmmac_resources *res) @@ -148,6 +452,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id struct plat_stmmacenet_data *plat; struct stmmac_pci_info *info; struct stmmac_resources res; + struct loongson_data *ld; int ret, i; plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); @@ -164,6 +469,10 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id if (!plat->dma_cfg) return -ENOMEM; + ld = devm_kzalloc(&pdev->dev, sizeof(*ld), GFP_KERNEL); + if (!ld) + return -ENOMEM; + /* Enable pci device */ ret = pci_enable_device(pdev); if (ret) { @@ -186,6 +495,10 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id memset(&res, 0, sizeof(res)); res.addr = pcim_iomap_table(pdev)[0]; + plat->bsp_priv = ld; + plat->setup = loongson_dwmac_setup; + ld->loongson_id = readl(res.addr + GMAC_VERSION) & 0xff; + info = (struct stmmac_pci_info *)id->driver_data; ret = info->setup(pdev, plat); if (ret) @@ -198,6 +511,10 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id if (ret) goto err_disable_device; + /* Use the common MAC IRQ if per-channel MSIs allocation failed */ + if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) + loongson_dwmac_msi_config(pdev, plat, &res); + ret = stmmac_dvr_probe(&pdev->dev, plat, &res); if (ret) goto err_plat_clear; @@ -207,6 +524,8 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id err_plat_clear: if (dev_of_node(&pdev->dev)) loongson_dwmac_dt_clear(pdev, plat); + if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) + loongson_dwmac_msi_clear(pdev); err_disable_device: pci_disable_device(pdev); return ret; @@ -216,13 +535,18 @@ static void loongson_dwmac_remove(struct pci_dev *pdev) { struct net_device *ndev = dev_get_drvdata(&pdev->dev); struct stmmac_priv *priv = netdev_priv(ndev); + struct loongson_data *ld; int i; + ld = priv->plat->bsp_priv; stmmac_dvr_remove(&pdev->dev); if (dev_of_node(&pdev->dev)) loongson_dwmac_dt_clear(pdev, priv->plat); + if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) + loongson_dwmac_msi_clear(pdev); + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pdev, i) == 0) continue; From 56dbe2c290bc580ac0774e163133c2ed84ecb8f0 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:48:55 +0800 Subject: [PATCH 096/385] net: stmmac: dwmac-loongson: Add Loongson GNET support The new generation Loongson LS2K2000 SoC and LS7A2000 chipset are equipped with the network controllers called Loongson GNET. It's the single and multi DMA-channels Loongson GMAC but with a PHY attached. Here is the summary of the DW GMAC features the controller has: DW GMAC IP-core: v3.73a Speeds: 10/100/1000Mbps Duplex: Full (both versions), Half (LS2K2000 GNET only) DMA-descriptors type: enhanced L3/L4 filters availability: Y VLAN hash table filter: Y PHY-interface: GMII (PHY is integrated into the chips) Remote Wake-up support: Y Mac Management Counters (MMC): Y Number of additional MAC addresses: 5 MAC Hash-based filter: Y Hash Table Size: 256 AV feature: Y (LS2K2000 GNET only) DMA channels: 8 (LS2K2000 GNET), 1 (LS7A2000 GNET) Let's update the Loongson DWMAC driver to supporting the new Loongson GNET controller. The change is mainly trivial: the driver shall be bound to the PCIe device with DID 0x7a13, and the device-specific setup() method shall be called for it. The only peculiarity concerns the integrated PHY speed change procedure. The PHY has a weird problem with switching from the low speeds to 1000Mbps mode. The speedup procedure requires the PHY-link re-negotiation. So the suggested change provide the device-specific fix_mac_speed() method to overcome the problem. Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Acked-by: Huacai Chen Reviewed-by: Serge Semin Signed-off-by: Yanteng Si Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- .../ethernet/stmicro/stmmac/dwmac-loongson.c | 77 ++++++++++++++++++- 1 file changed, 74 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 48c92ba826d9e..949e349ef8568 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -65,11 +65,13 @@ DMA_STATUS_MSK_COMMON_LOONGSON) #define PCI_DEVICE_ID_LOONGSON_GMAC 0x7a03 +#define PCI_DEVICE_ID_LOONGSON_GNET 0x7a13 #define DWMAC_CORE_LS_MULTICHAN 0x10 /* Loongson custom ID */ #define CHANNEL_NUM 8 struct loongson_data { u32 loongson_id; + struct device *dev; }; struct stmmac_pci_info { @@ -147,6 +149,60 @@ static struct stmmac_pci_info loongson_gmac_pci_info = { .setup = loongson_gmac_data, }; +static void loongson_gnet_fix_speed(void *priv, unsigned int speed, + unsigned int mode) +{ + struct loongson_data *ld = (struct loongson_data *)priv; + struct net_device *ndev = dev_get_drvdata(ld->dev); + struct stmmac_priv *ptr = netdev_priv(ndev); + + /* The integrated PHY has a weird problem with switching from the low + * speeds to 1000Mbps mode. The speedup procedure requires the PHY-link + * re-negotiation. + */ + if (speed == SPEED_1000) { + if (readl(ptr->ioaddr + MAC_CTRL_REG) & + GMAC_CONTROL_PS) + /* Word around hardware bug, restart autoneg */ + phy_restart_aneg(ndev->phydev); + } +} + +static int loongson_gnet_data(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) +{ + struct loongson_data *ld; + int i; + + ld = plat->bsp_priv; + + loongson_default_data(pdev, plat); + + if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) { + plat->rx_queues_to_use = CHANNEL_NUM; + plat->tx_queues_to_use = CHANNEL_NUM; + + /* Only channel 0 supports checksum, + * so turn off checksum to enable multiple channels. + */ + for (i = 1; i < CHANNEL_NUM; i++) + plat->tx_queues_cfg[i].coe_unsupported = 1; + } else { + plat->tx_queues_to_use = 1; + plat->rx_queues_to_use = 1; + } + + plat->phy_interface = PHY_INTERFACE_MODE_GMII; + plat->mdio_bus_data->phy_mask = ~(u32)BIT(2); + plat->fix_mac_speed = loongson_gnet_fix_speed; + + return 0; +} + +static struct stmmac_pci_info loongson_gnet_pci_info = { + .setup = loongson_gnet_data, +}; + static void loongson_dwmac_dma_init_channel(struct stmmac_priv *priv, void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg, @@ -279,8 +335,10 @@ static struct mac_device_info *loongson_dwmac_setup(void *apriv) struct mac_device_info *mac; struct stmmac_dma_ops *dma; struct loongson_data *ld; + struct pci_dev *pdev; ld = priv->plat->bsp_priv; + pdev = to_pci_dev(priv->device); mac = devm_kzalloc(priv->device, sizeof(*mac), GFP_KERNEL); if (!mac) @@ -290,7 +348,7 @@ static struct mac_device_info *loongson_dwmac_setup(void *apriv) if (!dma) return NULL; - /* The Loongson GMAC devices are based on the DW GMAC + /* The Loongson GMAC and GNET devices are based on the DW GMAC * v3.50a and v3.73a IP-cores. But the HW designers have changed the * GMAC_VERSION.SNPSVER field to the custom 0x10 value on the * network controllers with the multi-channels feature @@ -319,8 +377,19 @@ static struct mac_device_info *loongson_dwmac_setup(void *apriv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); - /* Loongson GMAC doesn't support the flow control. */ - mac->link.caps = MAC_10 | MAC_100 | MAC_1000; + /* Loongson GMAC doesn't support the flow control. LS2K2000 + * GNET doesn't support the half-duplex link mode. + */ + if (pdev->device == PCI_DEVICE_ID_LOONGSON_GMAC) { + mac->link.caps = MAC_10 | MAC_100 | MAC_1000; + } else { + if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000; + else + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10FD | MAC_100FD | MAC_1000FD; + } mac->link.duplex = GMAC_CONTROL_DM; mac->link.speed10 = GMAC_CONTROL_PS; @@ -497,6 +566,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id plat->bsp_priv = ld; plat->setup = loongson_dwmac_setup; + ld->dev = &pdev->dev; ld->loongson_id = readl(res.addr + GMAC_VERSION) & 0xff; info = (struct stmmac_pci_info *)id->driver_data; @@ -597,6 +667,7 @@ static SIMPLE_DEV_PM_OPS(loongson_dwmac_pm_ops, loongson_dwmac_suspend, static const struct pci_device_id loongson_dwmac_id_table[] = { { PCI_DEVICE_DATA(LOONGSON, GMAC, &loongson_gmac_pci_info) }, + { PCI_DEVICE_DATA(LOONGSON, GNET, &loongson_gnet_pci_info) }, {} }; MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table); From 930df0990d06244c3baf43f295e3f3abbc075036 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 7 Aug 2024 21:48:56 +0800 Subject: [PATCH 097/385] net: stmmac: dwmac-loongson: Add loongson module author Add Yanteng Si as MODULE_AUTHOR of Loongson DWMAC PCI driver. Signed-off-by: Feiyang Chen Signed-off-by: Yinggang Gu Acked-by: Huacai Chen Reviewed-by: Serge Semin Signed-off-by: Yanteng Si Tested-by: Serge Semin Signed-off-by: Paolo Abeni --- drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 949e349ef8568..bfe6e2d631bdf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -686,4 +686,5 @@ module_pci_driver(loongson_dwmac_driver); MODULE_DESCRIPTION("Loongson DWMAC PCI driver"); MODULE_AUTHOR("Qing Zhang "); +MODULE_AUTHOR("Yanteng Si "); MODULE_LICENSE("GPL v2"); From 1ef33652d22c69a2a7519d003cd6c79b8e514f44 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Aug 2024 05:25:07 -0700 Subject: [PATCH 098/385] net: netpoll: extract core of netpoll_cleanup Extract the core part of netpoll_cleanup(), so, it could be called from a caller that has the rtnl lock already. Netconsole uses this in a weird way right now: __netpoll_cleanup(&nt->np); spin_lock_irqsave(&target_list_lock, flags); netdev_put(nt->np.dev, &nt->np.dev_tracker); nt->np.dev = NULL; nt->enabled = false; This will be replaced by do_netpoll_cleanup() as the locking situation is overhauled. Signed-off-by: Breno Leitao Reviewed-by: Rik van Riel Signed-off-by: Paolo Abeni --- include/linux/netpoll.h | 1 + net/core/netpoll.c | 12 +++++++++--- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index bd19c4b91e312..cd4e28db0cbd7 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -64,6 +64,7 @@ int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); void __netpoll_free(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); +void do_netpoll_cleanup(struct netpoll *np); netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb); #ifdef CONFIG_NETPOLL diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 55bcacf67df3b..a58ea724790ce 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -853,14 +853,20 @@ void __netpoll_free(struct netpoll *np) } EXPORT_SYMBOL_GPL(__netpoll_free); +void do_netpoll_cleanup(struct netpoll *np) +{ + __netpoll_cleanup(np); + netdev_put(np->dev, &np->dev_tracker); + np->dev = NULL; +} +EXPORT_SYMBOL(do_netpoll_cleanup); + void netpoll_cleanup(struct netpoll *np) { rtnl_lock(); if (!np->dev) goto out; - __netpoll_cleanup(np); - netdev_put(np->dev, &np->dev_tracker); - np->dev = NULL; + do_netpoll_cleanup(np); out: rtnl_unlock(); } From e0a2b7e4a0f926948e7ade15cea5a43038dd790c Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Aug 2024 05:25:08 -0700 Subject: [PATCH 099/385] net: netconsole: Correct mismatched return types netconsole incorrectly mixes int and ssize_t types by using int for return variables in functions that should return ssize_t. This is fixed by updating the return variables to the appropriate ssize_t type, ensuring consistency across the function definitions. Signed-off-by: Breno Leitao Signed-off-by: Paolo Abeni --- drivers/net/netconsole.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index ffedf7648bedf..b4d2ef109e31c 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -336,7 +336,7 @@ static ssize_t enabled_store(struct config_item *item, struct netconsole_target *nt = to_target(item); unsigned long flags; bool enabled; - int err; + ssize_t err; mutex_lock(&dynamic_netconsole_mutex); err = kstrtobool(buf, &enabled); @@ -394,7 +394,7 @@ static ssize_t release_store(struct config_item *item, const char *buf, { struct netconsole_target *nt = to_target(item); bool release; - int err; + ssize_t err; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -422,7 +422,7 @@ static ssize_t extended_store(struct config_item *item, const char *buf, { struct netconsole_target *nt = to_target(item); bool extended; - int err; + ssize_t err; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -469,7 +469,7 @@ static ssize_t local_port_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); - int rv = -EINVAL; + ssize_t rv = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -492,7 +492,7 @@ static ssize_t remote_port_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); - int rv = -EINVAL; + ssize_t rv = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -685,7 +685,7 @@ static ssize_t userdatum_value_store(struct config_item *item, const char *buf, struct userdatum *udm = to_userdatum(item); struct netconsole_target *nt; struct userdata *ud; - int ret; + ssize_t ret; if (count > MAX_USERDATA_VALUE_LENGTH) return -EMSGSIZE; From 5c4a39e8a608a0f0afa2710f469432e5bfce4562 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Aug 2024 05:25:09 -0700 Subject: [PATCH 100/385] net: netconsole: Standardize variable naming Update variable names from err to ret in cases where the variable may return non-error values. This change facilitates a forthcoming patch that relies on ret being used consistently to handle return values, regardless of whether they indicate an error or not. Signed-off-by: Breno Leitao Signed-off-by: Paolo Abeni --- drivers/net/netconsole.c | 50 ++++++++++++++++++++-------------------- 1 file changed, 25 insertions(+), 25 deletions(-) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index b4d2ef109e31c..0e43b5088bbb7 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -336,14 +336,14 @@ static ssize_t enabled_store(struct config_item *item, struct netconsole_target *nt = to_target(item); unsigned long flags; bool enabled; - ssize_t err; + ssize_t ret; mutex_lock(&dynamic_netconsole_mutex); - err = kstrtobool(buf, &enabled); - if (err) + ret = kstrtobool(buf, &enabled); + if (ret) goto out_unlock; - err = -EINVAL; + ret = -EINVAL; if (enabled == nt->enabled) { pr_info("network logging has already %s\n", nt->enabled ? "started" : "stopped"); @@ -365,8 +365,8 @@ static ssize_t enabled_store(struct config_item *item, */ netpoll_print_options(&nt->np); - err = netpoll_setup(&nt->np); - if (err) + ret = netpoll_setup(&nt->np); + if (ret) goto out_unlock; nt->enabled = true; @@ -386,7 +386,7 @@ static ssize_t enabled_store(struct config_item *item, return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return err; + return ret; } static ssize_t release_store(struct config_item *item, const char *buf, @@ -394,18 +394,18 @@ static ssize_t release_store(struct config_item *item, const char *buf, { struct netconsole_target *nt = to_target(item); bool release; - ssize_t err; + ssize_t ret; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); - err = -EINVAL; + ret = -EINVAL; goto out_unlock; } - err = kstrtobool(buf, &release); - if (err) + ret = kstrtobool(buf, &release); + if (ret) goto out_unlock; nt->release = release; @@ -414,7 +414,7 @@ static ssize_t release_store(struct config_item *item, const char *buf, return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return err; + return ret; } static ssize_t extended_store(struct config_item *item, const char *buf, @@ -422,18 +422,18 @@ static ssize_t extended_store(struct config_item *item, const char *buf, { struct netconsole_target *nt = to_target(item); bool extended; - ssize_t err; + ssize_t ret; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); - err = -EINVAL; + ret = -EINVAL; goto out_unlock; } - err = kstrtobool(buf, &extended); - if (err) + ret = kstrtobool(buf, &extended); + if (ret) goto out_unlock; nt->extended = extended; @@ -442,7 +442,7 @@ static ssize_t extended_store(struct config_item *item, const char *buf, return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return err; + return ret; } static ssize_t dev_name_store(struct config_item *item, const char *buf, @@ -469,7 +469,7 @@ static ssize_t local_port_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); - ssize_t rv = -EINVAL; + ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -478,21 +478,21 @@ static ssize_t local_port_store(struct config_item *item, const char *buf, goto out_unlock; } - rv = kstrtou16(buf, 10, &nt->np.local_port); - if (rv < 0) + ret = kstrtou16(buf, 10, &nt->np.local_port); + if (ret < 0) goto out_unlock; mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return rv; + return ret; } static ssize_t remote_port_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); - ssize_t rv = -EINVAL; + ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -501,14 +501,14 @@ static ssize_t remote_port_store(struct config_item *item, goto out_unlock; } - rv = kstrtou16(buf, 10, &nt->np.remote_port); - if (rv < 0) + ret = kstrtou16(buf, 10, &nt->np.remote_port); + if (ret < 0) goto out_unlock; mutex_unlock(&dynamic_netconsole_mutex); return strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return rv; + return ret; } static ssize_t local_ip_store(struct config_item *item, const char *buf, From f2ab4c1a9288774b1f9c102f0cb1b478965169bb Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Aug 2024 05:25:10 -0700 Subject: [PATCH 101/385] net: netconsole: Unify Function Return Paths The return flow in netconsole's dynamic functions is currently inconsistent. This patch aims to streamline and standardize the process by ensuring that the mutex is unlocked before returning the ret value. Additionally, this update includes a minor functional change where certain strnlen() operations are performed with the dynamic_netconsole_mutex locked. This adjustment is not anticipated to cause any issues, however, it is crucial to document this change for clarity. Signed-off-by: Breno Leitao Signed-off-by: Paolo Abeni --- drivers/net/netconsole.c | 38 +++++++++++++++----------------------- 1 file changed, 15 insertions(+), 23 deletions(-) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 0e43b5088bbb7..69eeab4a1e26d 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -382,8 +382,7 @@ static ssize_t enabled_store(struct config_item *item, netpoll_cleanup(&nt->np); } - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; @@ -410,8 +409,7 @@ static ssize_t release_store(struct config_item *item, const char *buf, nt->release = release; - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; @@ -437,9 +435,7 @@ static ssize_t extended_store(struct config_item *item, const char *buf, goto out_unlock; nt->extended = extended; - - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; @@ -481,8 +477,7 @@ static ssize_t local_port_store(struct config_item *item, const char *buf, ret = kstrtou16(buf, 10, &nt->np.local_port); if (ret < 0) goto out_unlock; - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; @@ -504,8 +499,7 @@ static ssize_t remote_port_store(struct config_item *item, ret = kstrtou16(buf, 10, &nt->np.remote_port); if (ret < 0) goto out_unlock; - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; @@ -515,6 +509,7 @@ static ssize_t local_ip_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); + ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -541,17 +536,17 @@ static ssize_t local_ip_store(struct config_item *item, const char *buf, goto out_unlock; } - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return -EINVAL; + return ret; } static ssize_t remote_ip_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); + ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -578,11 +573,10 @@ static ssize_t remote_ip_store(struct config_item *item, const char *buf, goto out_unlock; } - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return -EINVAL; + return ret; } static ssize_t remote_mac_store(struct config_item *item, const char *buf, @@ -590,6 +584,7 @@ static ssize_t remote_mac_store(struct config_item *item, const char *buf, { struct netconsole_target *nt = to_target(item); u8 remote_mac[ETH_ALEN]; + ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -604,11 +599,10 @@ static ssize_t remote_mac_store(struct config_item *item, const char *buf, goto out_unlock; memcpy(nt->np.remote_mac, remote_mac, ETH_ALEN); - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return -EINVAL; + return ret; } struct userdatum { @@ -700,9 +694,7 @@ static ssize_t userdatum_value_store(struct config_item *item, const char *buf, ud = to_userdata(item->ci_parent); nt = userdata_to_target(ud); update_userdata(nt); - - mutex_unlock(&dynamic_netconsole_mutex); - return count; + ret = count; out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; From 97714695ef904a4bdba75ca2f339215c0ae2b1fa Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 8 Aug 2024 05:25:11 -0700 Subject: [PATCH 102/385] net: netconsole: Defer netpoll cleanup to avoid lock release during list traversal Current issue: - The `target_list_lock` spinlock is held while iterating over target_list() entries. - Mid-loop, the lock is released to call __netpoll_cleanup(), then reacquired. - This practice compromises the protection provided by `target_list_lock`. Reason for current design: 1. __netpoll_cleanup() may sleep, incompatible with holding a spinlock. 2. target_list_lock must be a spinlock because write_msg() cannot sleep. (See commit b5427c27173e ("[NET] netconsole: Support multiple logging targets")) Defer the cleanup of the netpoll structure to outside the target_list_lock() protected area. Create another list (target_cleanup_list) to hold the entries that need to be cleaned up, and clean them using a mutex (target_cleanup_list_lock). Signed-off-by: Breno Leitao Signed-off-by: Paolo Abeni --- drivers/net/netconsole.c | 83 ++++++++++++++++++++++++++++++++-------- 1 file changed, 67 insertions(+), 16 deletions(-) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 69eeab4a1e26d..43c29b15adbfa 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -37,6 +37,7 @@ #include #include #include +#include MODULE_AUTHOR("Matt Mackall "); MODULE_DESCRIPTION("Console driver for network interfaces"); @@ -72,9 +73,16 @@ __setup("netconsole=", option_setup); /* Linked list of all configured targets */ static LIST_HEAD(target_list); +/* target_cleanup_list is used to track targets that need to be cleaned outside + * of target_list_lock. It should be cleaned in the same function it is + * populated. + */ +static LIST_HEAD(target_cleanup_list); /* This needs to be a spinlock because write_msg() cannot sleep */ static DEFINE_SPINLOCK(target_list_lock); +/* This needs to be a mutex because netpoll_cleanup might sleep */ +static DEFINE_MUTEX(target_cleanup_list_lock); /* * Console driver for extended netconsoles. Registered on the first use to @@ -210,6 +218,33 @@ static struct netconsole_target *alloc_and_init(void) return nt; } +/* Clean up every target in the cleanup_list and move the clean targets back to + * the main target_list. + */ +static void netconsole_process_cleanups_core(void) +{ + struct netconsole_target *nt, *tmp; + unsigned long flags; + + /* The cleanup needs RTNL locked */ + ASSERT_RTNL(); + + mutex_lock(&target_cleanup_list_lock); + list_for_each_entry_safe(nt, tmp, &target_cleanup_list, list) { + /* all entries in the cleanup_list needs to be disabled */ + WARN_ON_ONCE(nt->enabled); + do_netpoll_cleanup(&nt->np); + /* moved the cleaned target to target_list. Need to hold both + * locks + */ + spin_lock_irqsave(&target_list_lock, flags); + list_move(&nt->list, &target_list); + spin_unlock_irqrestore(&target_list_lock, flags); + } + WARN_ON_ONCE(!list_empty(&target_cleanup_list)); + mutex_unlock(&target_cleanup_list_lock); +} + #ifdef CONFIG_NETCONSOLE_DYNAMIC /* @@ -246,6 +281,19 @@ static struct netconsole_target *to_target(struct config_item *item) struct netconsole_target, group); } +/* Do the list cleanup with the rtnl lock hold. rtnl lock is necessary because + * netdev might be cleaned-up by calling __netpoll_cleanup(), + */ +static void netconsole_process_cleanups(void) +{ + /* rtnl lock is called here, because it has precedence over + * target_cleanup_list_lock mutex and target_cleanup_list + */ + rtnl_lock(); + netconsole_process_cleanups_core(); + rtnl_unlock(); +} + /* Get rid of possible trailing newline, returning the new length */ static void trim_newline(char *s, size_t maxlen) { @@ -376,13 +424,20 @@ static ssize_t enabled_store(struct config_item *item, * otherwise we might end up in write_msg() with * nt->np.dev == NULL and nt->enabled == true */ + mutex_lock(&target_cleanup_list_lock); spin_lock_irqsave(&target_list_lock, flags); nt->enabled = false; + /* Remove the target from the list, while holding + * target_list_lock + */ + list_move(&nt->list, &target_cleanup_list); spin_unlock_irqrestore(&target_list_lock, flags); - netpoll_cleanup(&nt->np); + mutex_unlock(&target_cleanup_list_lock); } ret = strnlen(buf, count); + /* Deferred cleanup */ + netconsole_process_cleanups(); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; @@ -942,7 +997,7 @@ static int netconsole_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { unsigned long flags; - struct netconsole_target *nt; + struct netconsole_target *nt, *tmp; struct net_device *dev = netdev_notifier_info_to_dev(ptr); bool stopped = false; @@ -950,9 +1005,9 @@ static int netconsole_netdev_event(struct notifier_block *this, event == NETDEV_RELEASE || event == NETDEV_JOIN)) goto done; + mutex_lock(&target_cleanup_list_lock); spin_lock_irqsave(&target_list_lock, flags); -restart: - list_for_each_entry(nt, &target_list, list) { + list_for_each_entry_safe(nt, tmp, &target_list, list) { netconsole_target_get(nt); if (nt->np.dev == dev) { switch (event) { @@ -962,25 +1017,16 @@ static int netconsole_netdev_event(struct notifier_block *this, case NETDEV_RELEASE: case NETDEV_JOIN: case NETDEV_UNREGISTER: - /* rtnl_lock already held - * we might sleep in __netpoll_cleanup() - */ nt->enabled = false; - spin_unlock_irqrestore(&target_list_lock, flags); - - __netpoll_cleanup(&nt->np); - - spin_lock_irqsave(&target_list_lock, flags); - netdev_put(nt->np.dev, &nt->np.dev_tracker); - nt->np.dev = NULL; + list_move(&nt->list, &target_cleanup_list); stopped = true; - netconsole_target_put(nt); - goto restart; } } netconsole_target_put(nt); } spin_unlock_irqrestore(&target_list_lock, flags); + mutex_unlock(&target_cleanup_list_lock); + if (stopped) { const char *msg = "had an event"; @@ -999,6 +1045,11 @@ static int netconsole_netdev_event(struct notifier_block *this, dev->name, msg); } + /* Process target_cleanup_list entries. By the end, target_cleanup_list + * should be empty + */ + netconsole_process_cleanups_core(); + done: return NOTIFY_DONE; } From dd1bf9f9df156b43e5122f90d97ac3f59a1a5621 Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Thu, 8 Aug 2024 21:49:51 -0700 Subject: [PATCH 103/385] net: hinic: use ethtool_sprintf/puts Simpler and avoids manual pointer addition. Signed-off-by: Rosen Penev Link: https://patch.msgid.link/20240809044957.4534-1-rosenp@gmail.com Signed-off-by: Paolo Abeni --- .../net/ethernet/huawei/hinic/hinic_ethtool.c | 33 ++++++------------- 1 file changed, 10 insertions(+), 23 deletions(-) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c index 0304f03d40936..c559dd4291d30 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c @@ -1471,7 +1471,6 @@ static void hinic_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { struct hinic_dev *nic_dev = netdev_priv(netdev); - char *p = (char *)data; u16 i, j; switch (stringset) { @@ -1479,31 +1478,19 @@ static void hinic_get_strings(struct net_device *netdev, memcpy(data, *hinic_test_strings, sizeof(hinic_test_strings)); return; case ETH_SS_STATS: - for (i = 0; i < ARRAY_SIZE(hinic_function_stats); i++) { - memcpy(p, hinic_function_stats[i].name, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < ARRAY_SIZE(hinic_function_stats); i++) + ethtool_puts(&data, hinic_function_stats[i].name); - for (i = 0; i < ARRAY_SIZE(hinic_port_stats); i++) { - memcpy(p, hinic_port_stats[i].name, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < ARRAY_SIZE(hinic_port_stats); i++) + ethtool_puts(&data, hinic_port_stats[i].name); - for (i = 0; i < nic_dev->num_qps; i++) { - for (j = 0; j < ARRAY_SIZE(hinic_tx_queue_stats); j++) { - sprintf(p, hinic_tx_queue_stats[j].name, i); - p += ETH_GSTRING_LEN; - } - } + for (i = 0; i < nic_dev->num_qps; i++) + for (j = 0; j < ARRAY_SIZE(hinic_tx_queue_stats); j++) + ethtool_sprintf(&data, hinic_tx_queue_stats[j].name, i); - for (i = 0; i < nic_dev->num_qps; i++) { - for (j = 0; j < ARRAY_SIZE(hinic_rx_queue_stats); j++) { - sprintf(p, hinic_rx_queue_stats[j].name, i); - p += ETH_GSTRING_LEN; - } - } + for (i = 0; i < nic_dev->num_qps; i++) + for (j = 0; j < ARRAY_SIZE(hinic_rx_queue_stats); j++) + ethtool_sprintf(&data, hinic_rx_queue_stats[j].name, i); return; default: From 86ff3d79a0ee72b7662ef1cc712ba85336b77c30 Mon Sep 17 00:00:00 2001 From: Junfeng Guo Date: Thu, 25 Jul 2024 16:07:57 -0600 Subject: [PATCH 104/385] ice: add parser create and destroy skeleton Add new parser module which can parse a packet in binary and generate information like ptype, protocol/offset pairs and flags which can be later used to feed the FXP profile creation directly. Add skeleton of the create and destroy APIs: ice_parser_create() ice_parser_destroy() Reviewed-by: Simon Horman Reviewed-by: Marcin Szycik Reviewed-by: Wojciech Drewek Signed-off-by: Qi Zhang Signed-off-by: Junfeng Guo Co-developed-by: Ahmed Zaki Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/Makefile | 1 + drivers/net/ethernet/intel/ice/ice_common.h | 1 + drivers/net/ethernet/intel/ice/ice_parser.c | 32 +++++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_parser.h | 13 +++++++++ 4 files changed, 47 insertions(+) create mode 100644 drivers/net/ethernet/intel/ice/ice_parser.c create mode 100644 drivers/net/ethernet/intel/ice/ice_parser.h diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 03500e28ac99c..23fa3f7f36ef5 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -28,6 +28,7 @@ ice-y := ice_main.o \ ice_vlan_mode.o \ ice_flex_pipe.o \ ice_flow.o \ + ice_parser.o \ ice_idc.o \ devlink/devlink.o \ devlink/devlink_port.o \ diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 66f29bac783a0..27208a60cece5 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -10,6 +10,7 @@ #include "ice_type.h" #include "ice_nvm.h" #include "ice_flex_pipe.h" +#include "ice_parser.h" #include #include "ice_switch.h" #include "ice_fdir.h" diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c new file mode 100644 index 0000000000000..6c50164efae00 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_parser.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2024 Intel Corporation */ + +#include "ice_common.h" + +/** + * ice_parser_create - create a parser instance + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated parser instance or ERR_PTR + * in case of error. + */ +struct ice_parser *ice_parser_create(struct ice_hw *hw) +{ + struct ice_parser *p; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return ERR_PTR(-ENOMEM); + + p->hw = hw; + return p; +} + +/** + * ice_parser_destroy - destroy a parser instance + * @psr: pointer to a parser instance + */ +void ice_parser_destroy(struct ice_parser *psr) +{ + kfree(psr); +} diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h new file mode 100644 index 0000000000000..09ed380eee320 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_parser.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef _ICE_PARSER_H_ +#define _ICE_PARSER_H_ + +struct ice_parser { + struct ice_hw *hw; /* pointer to the hardware structure */ +}; + +struct ice_parser *ice_parser_create(struct ice_hw *hw); +void ice_parser_destroy(struct ice_parser *psr); +#endif /* _ICE_PARSER_H_ */ From 75b4a938a947785cdda8908cb700c58e95f8ff69 Mon Sep 17 00:00:00 2001 From: Junfeng Guo Date: Thu, 25 Jul 2024 16:07:58 -0600 Subject: [PATCH 105/385] ice: parse and init various DDP parser sections Parse the following DDP sections: - ICE_SID_RXPARSER_IMEM into an array of struct ice_imem_item - ICE_SID_RXPARSER_METADATA_INIT into an array of struct ice_metainit_item - ICE_SID_RXPARSER_CAM or ICE_SID_RXPARSER_PG_SPILL into an array of struct ice_pg_cam_item - ICE_SID_RXPARSER_NOMATCH_CAM or ICE_SID_RXPARSER_NOMATCH_SPILL into an array of struct ice_pg_nm_cam_item - ICE_SID_RXPARSER_CAM into an array of ice_bst_tcam_item - ICE_SID_LBL_RXPARSER_TMEM into an array of ice_lbl_item - ICE_SID_RXPARSER_MARKER_PTYPE into an array of ice_ptype_mk_tcam_item - ICE_SID_RXPARSER_MARKER_GRP into an array of ice_mk_grp_item - ICE_SID_RXPARSER_PROTO_GRP into an array of ice_proto_grp_item - ICE_SID_RXPARSER_FLAG_REDIR into an array of ice_flg_rd_item - ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL, ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS into struct ice_xlt_kb Reviewed-by: Marcin Szycik Signed-off-by: Qi Zhang Signed-off-by: Junfeng Guo Co-developed-by: Ahmed Zaki Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Reviewed-by: Simon Horman Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_ddp.c | 10 +- drivers/net/ethernet/intel/ice/ice_ddp.h | 13 + drivers/net/ethernet/intel/ice/ice_parser.c | 1383 +++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_parser.h | 358 +++++ drivers/net/ethernet/intel/ice/ice_type.h | 1 + 5 files changed, 1760 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index f182179529b7d..953262b88a586 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -289,11 +289,11 @@ void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state, * indicates a base offset of 10, and the index for the entry is 2, then * section handler function should set the offset to 10 + 2 = 12. */ -static void *ice_pkg_enum_entry(struct ice_seg *ice_seg, - struct ice_pkg_enum *state, u32 sect_type, - u32 *offset, - void *(*handler)(u32 sect_type, void *section, - u32 index, u32 *offset)) +void *ice_pkg_enum_entry(struct ice_seg *ice_seg, + struct ice_pkg_enum *state, u32 sect_type, + u32 *offset, + void *(*handler)(u32 sect_type, void *section, + u32 index, u32 *offset)) { void *entry; diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.h b/drivers/net/ethernet/intel/ice/ice_ddp.h index 622543f08b431..97f2723174754 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.h +++ b/drivers/net/ethernet/intel/ice/ice_ddp.h @@ -261,10 +261,17 @@ struct ice_meta_sect { #define ICE_SID_CDID_KEY_BUILDER_RSS 47 #define ICE_SID_CDID_REDIR_RSS 48 +#define ICE_SID_RXPARSER_CAM 50 +#define ICE_SID_RXPARSER_NOMATCH_CAM 51 +#define ICE_SID_RXPARSER_IMEM 52 #define ICE_SID_RXPARSER_MARKER_PTYPE 55 #define ICE_SID_RXPARSER_BOOST_TCAM 56 +#define ICE_SID_RXPARSER_PROTO_GRP 57 #define ICE_SID_RXPARSER_METADATA_INIT 58 #define ICE_SID_TXPARSER_BOOST_TCAM 66 +#define ICE_SID_RXPARSER_MARKER_GRP 72 +#define ICE_SID_RXPARSER_PG_SPILL 76 +#define ICE_SID_RXPARSER_NOMATCH_SPILL 78 #define ICE_SID_XLT0_PE 80 #define ICE_SID_XLT_KEY_BUILDER_PE 81 @@ -276,6 +283,7 @@ struct ice_meta_sect { #define ICE_SID_CDID_KEY_BUILDER_PE 87 #define ICE_SID_CDID_REDIR_PE 88 +#define ICE_SID_RXPARSER_FLAG_REDIR 97 /* Label Metadata section IDs */ #define ICE_SID_LBL_FIRST 0x80000010 #define ICE_SID_LBL_RXPARSER_TMEM 0x80000018 @@ -451,6 +459,11 @@ int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count); int ice_pkg_buf_reserve_section(struct ice_buf_build *bld, u16 count); u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld); +void * +ice_pkg_enum_entry(struct ice_seg *ice_seg, struct ice_pkg_enum *state, + u32 sect_type, u32 *offset, + void *(*handler)(u32 sect_type, void *section, + u32 index, u32 *offset)); void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state, u32 sect_type); diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c index 6c50164efae00..5fdc87034fc69 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.c +++ b/drivers/net/ethernet/intel/ice/ice_parser.c @@ -3,6 +3,1271 @@ #include "ice_common.h" +struct ice_pkg_sect_hdr { + __le16 count; + __le16 offset; +}; + +/** + * ice_parser_sect_item_get - parse an item from a section + * @sect_type: section type + * @section: section object + * @index: index of the item to get + * @offset: dummy as prototype of ice_pkg_enum_entry's last parameter + * + * Return: a pointer to the item or NULL. + */ +static void *ice_parser_sect_item_get(u32 sect_type, void *section, + u32 index, u32 __maybe_unused *offset) +{ + size_t data_off = ICE_SEC_DATA_OFFSET; + struct ice_pkg_sect_hdr *hdr; + size_t size; + + if (!section) + return NULL; + + switch (sect_type) { + case ICE_SID_RXPARSER_IMEM: + size = ICE_SID_RXPARSER_IMEM_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_METADATA_INIT: + size = ICE_SID_RXPARSER_METADATA_INIT_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_CAM: + size = ICE_SID_RXPARSER_CAM_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_PG_SPILL: + size = ICE_SID_RXPARSER_PG_SPILL_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_NOMATCH_CAM: + size = ICE_SID_RXPARSER_NOMATCH_CAM_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_NOMATCH_SPILL: + size = ICE_SID_RXPARSER_NOMATCH_SPILL_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_BOOST_TCAM: + size = ICE_SID_RXPARSER_BOOST_TCAM_ENTRY_SIZE; + break; + case ICE_SID_LBL_RXPARSER_TMEM: + data_off = ICE_SEC_LBL_DATA_OFFSET; + size = ICE_SID_LBL_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_MARKER_PTYPE: + size = ICE_SID_RXPARSER_MARKER_TYPE_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_MARKER_GRP: + size = ICE_SID_RXPARSER_MARKER_GRP_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_PROTO_GRP: + size = ICE_SID_RXPARSER_PROTO_GRP_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_FLAG_REDIR: + size = ICE_SID_RXPARSER_FLAG_REDIR_ENTRY_SIZE; + break; + default: + return NULL; + } + + hdr = section; + if (index >= le16_to_cpu(hdr->count)) + return NULL; + + return section + data_off + index * size; +} + +/** + * ice_parser_create_table - create an item table from a section + * @hw: pointer to the hardware structure + * @sect_type: section type + * @item_size: item size in bytes + * @length: number of items in the table to create + * @parse_item: the function to parse the item + * @no_offset: ignore header offset, calculate index from 0 + * + * Return: a pointer to the allocated table or ERR_PTR. + */ +static void * +ice_parser_create_table(struct ice_hw *hw, u32 sect_type, + u32 item_size, u32 length, + void (*parse_item)(struct ice_hw *hw, u16 idx, + void *item, void *data, + int size), bool no_offset) +{ + struct ice_pkg_enum state = {}; + struct ice_seg *seg = hw->seg; + void *table, *data, *item; + u16 idx = 0; + + if (!seg) + return ERR_PTR(-EINVAL); + + table = kzalloc(item_size * length, GFP_KERNEL); + if (!table) + return ERR_PTR(-ENOMEM); + + do { + data = ice_pkg_enum_entry(seg, &state, sect_type, NULL, + ice_parser_sect_item_get); + seg = NULL; + if (data) { + struct ice_pkg_sect_hdr *hdr = state.sect; + + if (!no_offset) + idx = le16_to_cpu(hdr->offset) + + state.entry_idx; + + item = (void *)((uintptr_t)table + idx * item_size); + parse_item(hw, idx, item, data, item_size); + + if (no_offset) + idx++; + } + } while (data); + + return table; +} + +/*** ICE_SID_RXPARSER_IMEM section ***/ +#define ICE_IM_BM_ALU0 BIT(0) +#define ICE_IM_BM_ALU1 BIT(1) +#define ICE_IM_BM_ALU2 BIT(2) +#define ICE_IM_BM_PG BIT(3) + +/** + * ice_imem_bm_init - parse 4 bits of Boost Main + * @bm: pointer to the Boost Main structure + * @data: Boost Main data to be parsed + */ +static void ice_imem_bm_init(struct ice_bst_main *bm, u8 data) +{ + bm->alu0 = FIELD_GET(ICE_IM_BM_ALU0, data); + bm->alu1 = FIELD_GET(ICE_IM_BM_ALU1, data); + bm->alu2 = FIELD_GET(ICE_IM_BM_ALU2, data); + bm->pg = FIELD_GET(ICE_IM_BM_PG, data); +} + +#define ICE_IM_BKB_PRIO GENMASK(7, 0) +#define ICE_IM_BKB_TSR_CTRL BIT(8) + +/** + * ice_imem_bkb_init - parse 10 bits of Boost Main Build + * @bkb: pointer to the Boost Main Build structure + * @data: Boost Main Build data to be parsed + */ +static void ice_imem_bkb_init(struct ice_bst_keybuilder *bkb, u16 data) +{ + bkb->prio = FIELD_GET(ICE_IM_BKB_PRIO, data); + bkb->tsr_ctrl = FIELD_GET(ICE_IM_BKB_TSR_CTRL, data); +} + +#define ICE_IM_NPKB_OPC GENMASK(1, 0) +#define ICE_IM_NPKB_S_R0 GENMASK(9, 2) +#define ICE_IM_NPKB_L_R1 GENMASK(17, 10) + +/** + * ice_imem_npkb_init - parse 18 bits of Next Protocol Key Build + * @kb: pointer to the Next Protocol Key Build structure + * @data: Next Protocol Key Build data to be parsed + */ +static void ice_imem_npkb_init(struct ice_np_keybuilder *kb, u32 data) +{ + kb->opc = FIELD_GET(ICE_IM_NPKB_OPC, data); + kb->start_reg0 = FIELD_GET(ICE_IM_NPKB_S_R0, data); + kb->len_reg1 = FIELD_GET(ICE_IM_NPKB_L_R1, data); +} + +#define ICE_IM_PGKB_F0_ENA BIT_ULL(0) +#define ICE_IM_PGKB_F0_IDX GENMASK_ULL(6, 1) +#define ICE_IM_PGKB_F1_ENA BIT_ULL(7) +#define ICE_IM_PGKB_F1_IDX GENMASK_ULL(13, 8) +#define ICE_IM_PGKB_F2_ENA BIT_ULL(14) +#define ICE_IM_PGKB_F2_IDX GENMASK_ULL(20, 15) +#define ICE_IM_PGKB_F3_ENA BIT_ULL(21) +#define ICE_IM_PGKB_F3_IDX GENMASK_ULL(27, 22) +#define ICE_IM_PGKB_AR_IDX GENMASK_ULL(34, 28) + +/** + * ice_imem_pgkb_init - parse 35 bits of Parse Graph Key Build + * @kb: pointer to the Parse Graph Key Build structure + * @data: Parse Graph Key Build data to be parsed + */ +static void ice_imem_pgkb_init(struct ice_pg_keybuilder *kb, u64 data) +{ + kb->flag0_ena = FIELD_GET(ICE_IM_PGKB_F0_ENA, data); + kb->flag0_idx = FIELD_GET(ICE_IM_PGKB_F0_IDX, data); + kb->flag1_ena = FIELD_GET(ICE_IM_PGKB_F1_ENA, data); + kb->flag1_idx = FIELD_GET(ICE_IM_PGKB_F1_IDX, data); + kb->flag2_ena = FIELD_GET(ICE_IM_PGKB_F2_ENA, data); + kb->flag2_idx = FIELD_GET(ICE_IM_PGKB_F2_IDX, data); + kb->flag3_ena = FIELD_GET(ICE_IM_PGKB_F3_ENA, data); + kb->flag3_idx = FIELD_GET(ICE_IM_PGKB_F3_IDX, data); + kb->alu_reg_idx = FIELD_GET(ICE_IM_PGKB_AR_IDX, data); +} + +#define ICE_IM_ALU_OPC GENMASK_ULL(5, 0) +#define ICE_IM_ALU_SS GENMASK_ULL(13, 6) +#define ICE_IM_ALU_SL GENMASK_ULL(18, 14) +#define ICE_IM_ALU_SXS BIT_ULL(19) +#define ICE_IM_ALU_SXK GENMASK_ULL(23, 20) +#define ICE_IM_ALU_SRID GENMASK_ULL(30, 24) +#define ICE_IM_ALU_DRID GENMASK_ULL(37, 31) +#define ICE_IM_ALU_INC0 BIT_ULL(38) +#define ICE_IM_ALU_INC1 BIT_ULL(39) +#define ICE_IM_ALU_POO GENMASK_ULL(41, 40) +#define ICE_IM_ALU_PO GENMASK_ULL(49, 42) +#define ICE_IM_ALU_BA_S 50 /* offset for the 2nd 64-bits field */ +#define ICE_IM_ALU_BA GENMASK_ULL(57 - ICE_IM_ALU_BA_S, \ + 50 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_IMM GENMASK_ULL(73 - ICE_IM_ALU_BA_S, \ + 58 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_DFE BIT_ULL(74 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_DS GENMASK_ULL(80 - ICE_IM_ALU_BA_S, \ + 75 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_DL GENMASK_ULL(86 - ICE_IM_ALU_BA_S, \ + 81 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_FEI BIT_ULL(87 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_FSI GENMASK_ULL(95 - ICE_IM_ALU_BA_S, \ + 88 - ICE_IM_ALU_BA_S) + +/** + * ice_imem_alu_init - parse 96 bits of ALU entry + * @alu: pointer to the ALU entry structure + * @data: ALU entry data to be parsed + * @off: offset of the ALU entry data + */ +static void ice_imem_alu_init(struct ice_alu *alu, u8 *data, u8 off) +{ + u64 d64; + u8 idd; + + d64 = *((u64 *)data) >> off; + + alu->opc = FIELD_GET(ICE_IM_ALU_OPC, d64); + alu->src_start = FIELD_GET(ICE_IM_ALU_SS, d64); + alu->src_len = FIELD_GET(ICE_IM_ALU_SL, d64); + alu->shift_xlate_sel = FIELD_GET(ICE_IM_ALU_SXS, d64); + alu->shift_xlate_key = FIELD_GET(ICE_IM_ALU_SXK, d64); + alu->src_reg_id = FIELD_GET(ICE_IM_ALU_SRID, d64); + alu->dst_reg_id = FIELD_GET(ICE_IM_ALU_DRID, d64); + alu->inc0 = FIELD_GET(ICE_IM_ALU_INC0, d64); + alu->inc1 = FIELD_GET(ICE_IM_ALU_INC1, d64); + alu->proto_offset_opc = FIELD_GET(ICE_IM_ALU_POO, d64); + alu->proto_offset = FIELD_GET(ICE_IM_ALU_PO, d64); + + idd = (ICE_IM_ALU_BA_S + off) / BITS_PER_BYTE; + off = (ICE_IM_ALU_BA_S + off) % BITS_PER_BYTE; + d64 = *((u64 *)(&data[idd])) >> off; + + alu->branch_addr = FIELD_GET(ICE_IM_ALU_BA, d64); + alu->imm = FIELD_GET(ICE_IM_ALU_IMM, d64); + alu->dedicate_flags_ena = FIELD_GET(ICE_IM_ALU_DFE, d64); + alu->dst_start = FIELD_GET(ICE_IM_ALU_DS, d64); + alu->dst_len = FIELD_GET(ICE_IM_ALU_DL, d64); + alu->flags_extr_imm = FIELD_GET(ICE_IM_ALU_FEI, d64); + alu->flags_start_imm = FIELD_GET(ICE_IM_ALU_FSI, d64); +} + +#define ICE_IMEM_BM_S 0 +#define ICE_IMEM_BKB_S 4 +#define ICE_IMEM_BKB_IDD (ICE_IMEM_BKB_S / BITS_PER_BYTE) +#define ICE_IMEM_BKB_OFF (ICE_IMEM_BKB_S % BITS_PER_BYTE) +#define ICE_IMEM_PGP GENMASK(15, 14) +#define ICE_IMEM_NPKB_S 16 +#define ICE_IMEM_NPKB_IDD (ICE_IMEM_NPKB_S / BITS_PER_BYTE) +#define ICE_IMEM_NPKB_OFF (ICE_IMEM_NPKB_S % BITS_PER_BYTE) +#define ICE_IMEM_PGKB_S 34 +#define ICE_IMEM_PGKB_IDD (ICE_IMEM_PGKB_S / BITS_PER_BYTE) +#define ICE_IMEM_PGKB_OFF (ICE_IMEM_PGKB_S % BITS_PER_BYTE) +#define ICE_IMEM_ALU0_S 69 +#define ICE_IMEM_ALU0_IDD (ICE_IMEM_ALU0_S / BITS_PER_BYTE) +#define ICE_IMEM_ALU0_OFF (ICE_IMEM_ALU0_S % BITS_PER_BYTE) +#define ICE_IMEM_ALU1_S 165 +#define ICE_IMEM_ALU1_IDD (ICE_IMEM_ALU1_S / BITS_PER_BYTE) +#define ICE_IMEM_ALU1_OFF (ICE_IMEM_ALU1_S % BITS_PER_BYTE) +#define ICE_IMEM_ALU2_S 357 +#define ICE_IMEM_ALU2_IDD (ICE_IMEM_ALU2_S / BITS_PER_BYTE) +#define ICE_IMEM_ALU2_OFF (ICE_IMEM_ALU2_S % BITS_PER_BYTE) + +/** + * ice_imem_parse_item - parse 384 bits of IMEM entry + * @hw: pointer to the hardware structure + * @idx: index of IMEM entry + * @item: item of IMEM entry + * @data: IMEM entry data to be parsed + * @size: size of IMEM entry + */ +static void ice_imem_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_imem_item *ii = item; + u8 *buf = data; + + ii->idx = idx; + + ice_imem_bm_init(&ii->b_m, *(u8 *)buf); + ice_imem_bkb_init(&ii->b_kb, + *((u16 *)(&buf[ICE_IMEM_BKB_IDD])) >> + ICE_IMEM_BKB_OFF); + + ii->pg_prio = FIELD_GET(ICE_IMEM_PGP, *(u16 *)buf); + + ice_imem_npkb_init(&ii->np_kb, + *((u32 *)(&buf[ICE_IMEM_NPKB_IDD])) >> + ICE_IMEM_NPKB_OFF); + ice_imem_pgkb_init(&ii->pg_kb, + *((u64 *)(&buf[ICE_IMEM_PGKB_IDD])) >> + ICE_IMEM_PGKB_OFF); + + ice_imem_alu_init(&ii->alu0, + &buf[ICE_IMEM_ALU0_IDD], + ICE_IMEM_ALU0_OFF); + ice_imem_alu_init(&ii->alu1, + &buf[ICE_IMEM_ALU1_IDD], + ICE_IMEM_ALU1_OFF); + ice_imem_alu_init(&ii->alu2, + &buf[ICE_IMEM_ALU2_IDD], + ICE_IMEM_ALU2_OFF); +} + +/** + * ice_imem_table_get - create an imem table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated IMEM table. + */ +static struct ice_imem_item *ice_imem_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_IMEM, + sizeof(struct ice_imem_item), + ICE_IMEM_TABLE_SIZE, + ice_imem_parse_item, false); +} + +/*** ICE_SID_RXPARSER_METADATA_INIT section ***/ +#define ICE_MI_TSR GENMASK_ULL(7, 0) +#define ICE_MI_HO GENMASK_ULL(16, 8) +#define ICE_MI_PC GENMASK_ULL(24, 17) +#define ICE_MI_PGRN GENMASK_ULL(35, 25) +#define ICE_MI_CD GENMASK_ULL(38, 36) +#define ICE_MI_GAC BIT_ULL(39) +#define ICE_MI_GADM GENMASK_ULL(44, 40) +#define ICE_MI_GADS GENMASK_ULL(48, 45) +#define ICE_MI_GADL GENMASK_ULL(53, 49) +#define ICE_MI_GAI GENMASK_ULL(59, 56) +#define ICE_MI_GBC BIT_ULL(60) +#define ICE_MI_GBDM_S 61 /* offset for the 2nd 64-bits field */ +#define ICE_MI_GBDM_IDD (ICE_MI_GBDM_S / BITS_PER_BYTE) +#define ICE_MI_GBDM_OFF (ICE_MI_GBDM_S % BITS_PER_BYTE) + +#define ICE_MI_GBDM_GENMASK_ULL(high, low) \ + GENMASK_ULL((high) - ICE_MI_GBDM_S, (low) - ICE_MI_GBDM_S) +#define ICE_MI_GBDM ICE_MI_GBDM_GENMASK_ULL(65, 61) +#define ICE_MI_GBDS ICE_MI_GBDM_GENMASK_ULL(69, 66) +#define ICE_MI_GBDL ICE_MI_GBDM_GENMASK_ULL(74, 70) +#define ICE_MI_GBI ICE_MI_GBDM_GENMASK_ULL(80, 77) +#define ICE_MI_GCC BIT_ULL(81 - ICE_MI_GBDM_S) +#define ICE_MI_GCDM ICE_MI_GBDM_GENMASK_ULL(86, 82) +#define ICE_MI_GCDS ICE_MI_GBDM_GENMASK_ULL(90, 87) +#define ICE_MI_GCDL ICE_MI_GBDM_GENMASK_ULL(95, 91) +#define ICE_MI_GCI ICE_MI_GBDM_GENMASK_ULL(101, 98) +#define ICE_MI_GDC BIT_ULL(102 - ICE_MI_GBDM_S) +#define ICE_MI_GDDM ICE_MI_GBDM_GENMASK_ULL(107, 103) +#define ICE_MI_GDDS ICE_MI_GBDM_GENMASK_ULL(111, 108) +#define ICE_MI_GDDL ICE_MI_GBDM_GENMASK_ULL(116, 112) +#define ICE_MI_GDI ICE_MI_GBDM_GENMASK_ULL(122, 119) +#define ICE_MI_FLAG_S 123 /* offset for the 3rd 64-bits field */ +#define ICE_MI_FLAG_IDD (ICE_MI_FLAG_S / BITS_PER_BYTE) +#define ICE_MI_FLAG_OFF (ICE_MI_FLAG_S % BITS_PER_BYTE) +#define ICE_MI_FLAG GENMASK_ULL(186 - ICE_MI_FLAG_S, \ + 123 - ICE_MI_FLAG_S) + +/** + * ice_metainit_parse_item - parse 192 bits of Metadata Init entry + * @hw: pointer to the hardware structure + * @idx: index of Metadata Init entry + * @item: item of Metadata Init entry + * @data: Metadata Init entry data to be parsed + * @size: size of Metadata Init entry + */ +static void ice_metainit_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_metainit_item *mi = item; + u8 *buf = data; + u64 d64; + + mi->idx = idx; + + d64 = *(u64 *)buf; + + mi->tsr = FIELD_GET(ICE_MI_TSR, d64); + mi->ho = FIELD_GET(ICE_MI_HO, d64); + mi->pc = FIELD_GET(ICE_MI_PC, d64); + mi->pg_rn = FIELD_GET(ICE_MI_PGRN, d64); + mi->cd = FIELD_GET(ICE_MI_CD, d64); + + mi->gpr_a_ctrl = FIELD_GET(ICE_MI_GAC, d64); + mi->gpr_a_data_mdid = FIELD_GET(ICE_MI_GADM, d64); + mi->gpr_a_data_start = FIELD_GET(ICE_MI_GADS, d64); + mi->gpr_a_data_len = FIELD_GET(ICE_MI_GADL, d64); + mi->gpr_a_id = FIELD_GET(ICE_MI_GAI, d64); + + mi->gpr_b_ctrl = FIELD_GET(ICE_MI_GBC, d64); + + d64 = *((u64 *)&buf[ICE_MI_GBDM_IDD]) >> ICE_MI_GBDM_OFF; + + mi->gpr_b_data_mdid = FIELD_GET(ICE_MI_GBDM, d64); + mi->gpr_b_data_start = FIELD_GET(ICE_MI_GBDS, d64); + mi->gpr_b_data_len = FIELD_GET(ICE_MI_GBDL, d64); + mi->gpr_b_id = FIELD_GET(ICE_MI_GBI, d64); + + mi->gpr_c_ctrl = FIELD_GET(ICE_MI_GCC, d64); + mi->gpr_c_data_mdid = FIELD_GET(ICE_MI_GCDM, d64); + mi->gpr_c_data_start = FIELD_GET(ICE_MI_GCDS, d64); + mi->gpr_c_data_len = FIELD_GET(ICE_MI_GCDL, d64); + mi->gpr_c_id = FIELD_GET(ICE_MI_GCI, d64); + + mi->gpr_d_ctrl = FIELD_GET(ICE_MI_GDC, d64); + mi->gpr_d_data_mdid = FIELD_GET(ICE_MI_GDDM, d64); + mi->gpr_d_data_start = FIELD_GET(ICE_MI_GDDS, d64); + mi->gpr_d_data_len = FIELD_GET(ICE_MI_GDDL, d64); + mi->gpr_d_id = FIELD_GET(ICE_MI_GDI, d64); + + d64 = *((u64 *)&buf[ICE_MI_FLAG_IDD]) >> ICE_MI_FLAG_OFF; + + mi->flags = FIELD_GET(ICE_MI_FLAG, d64); +} + +/** + * ice_metainit_table_get - create a metainit table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Metadata initialization table. + */ +static struct ice_metainit_item *ice_metainit_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_METADATA_INIT, + sizeof(struct ice_metainit_item), + ICE_METAINIT_TABLE_SIZE, + ice_metainit_parse_item, false); +} + +/*** ICE_SID_RXPARSER_CAM, ICE_SID_RXPARSER_PG_SPILL, + * ICE_SID_RXPARSER_NOMATCH_CAM and ICE_SID_RXPARSER_NOMATCH_CAM + * sections ***/ +#define ICE_PGCA_NN GENMASK_ULL(10, 0) +#define ICE_PGCA_NPC GENMASK_ULL(18, 11) +#define ICE_PGCA_IPG BIT_ULL(19) +#define ICE_PGCA_PID GENMASK_ULL(30, 23) +#define ICE_PGCA_IMG BIT_ULL(31) +#define ICE_PGCA_MID GENMASK_ULL(39, 32) +#define ICE_PGCA_ILR BIT_ULL(40) +#define ICE_PGCA_HOP BIT_ULL(41) +#define ICE_PGCA_HOI GENMASK_ULL(50, 42) + +/** + * ice_pg_cam_action_init - parse 55 bits of Parse Graph CAM Action + * @action: pointer to the Parse Graph CAM Action structure + * @data: Parse Graph CAM Action data to be parsed + */ +static void ice_pg_cam_action_init(struct ice_pg_cam_action *action, u64 data) +{ + action->next_node = FIELD_GET(ICE_PGCA_NN, data); + action->next_pc = FIELD_GET(ICE_PGCA_NPC, data); + action->is_pg = FIELD_GET(ICE_PGCA_IPG, data); + action->proto_id = FIELD_GET(ICE_PGCA_PID, data); + action->is_mg = FIELD_GET(ICE_PGCA_IMG, data); + action->marker_id = FIELD_GET(ICE_PGCA_MID, data); + action->is_last_round = FIELD_GET(ICE_PGCA_ILR, data); + action->ho_polarity = FIELD_GET(ICE_PGCA_HOP, data); + action->ho_inc = FIELD_GET(ICE_PGCA_HOI, data); +} + +#define ICE_PGNCK_VLD BIT_ULL(0) +#define ICE_PGNCK_NID GENMASK_ULL(11, 1) +#define ICE_PGNCK_F0 BIT_ULL(12) +#define ICE_PGNCK_F1 BIT_ULL(13) +#define ICE_PGNCK_F2 BIT_ULL(14) +#define ICE_PGNCK_F3 BIT_ULL(15) +#define ICE_PGNCK_BH BIT_ULL(16) +#define ICE_PGNCK_BI GENMASK_ULL(24, 17) +#define ICE_PGNCK_AR GENMASK_ULL(40, 25) + +/** + * ice_pg_nm_cam_key_init - parse 41 bits of Parse Graph NoMatch CAM Key + * @key: pointer to the Parse Graph NoMatch CAM Key structure + * @data: Parse Graph NoMatch CAM Key data to be parsed + */ +static void ice_pg_nm_cam_key_init(struct ice_pg_nm_cam_key *key, u64 data) +{ + key->valid = FIELD_GET(ICE_PGNCK_VLD, data); + key->node_id = FIELD_GET(ICE_PGNCK_NID, data); + key->flag0 = FIELD_GET(ICE_PGNCK_F0, data); + key->flag1 = FIELD_GET(ICE_PGNCK_F1, data); + key->flag2 = FIELD_GET(ICE_PGNCK_F2, data); + key->flag3 = FIELD_GET(ICE_PGNCK_F3, data); + + if (FIELD_GET(ICE_PGNCK_BH, data)) + key->boost_idx = FIELD_GET(ICE_PGNCK_BI, data); + else + key->boost_idx = 0; + + key->alu_reg = FIELD_GET(ICE_PGNCK_AR, data); +} + +#define ICE_PGCK_VLD BIT_ULL(0) +#define ICE_PGCK_NID GENMASK_ULL(11, 1) +#define ICE_PGCK_F0 BIT_ULL(12) +#define ICE_PGCK_F1 BIT_ULL(13) +#define ICE_PGCK_F2 BIT_ULL(14) +#define ICE_PGCK_F3 BIT_ULL(15) +#define ICE_PGCK_BH BIT_ULL(16) +#define ICE_PGCK_BI GENMASK_ULL(24, 17) +#define ICE_PGCK_AR GENMASK_ULL(40, 25) +#define ICE_PGCK_NPK_S 41 /* offset for the 2nd 64-bits field */ +#define ICE_PGCK_NPK_IDD (ICE_PGCK_NPK_S / BITS_PER_BYTE) +#define ICE_PGCK_NPK_OFF (ICE_PGCK_NPK_S % BITS_PER_BYTE) +#define ICE_PGCK_NPK GENMASK_ULL(72 - ICE_PGCK_NPK_S, \ + 41 - ICE_PGCK_NPK_S) + +/** + * ice_pg_cam_key_init - parse 73 bits of Parse Graph CAM Key + * @key: pointer to the Parse Graph CAM Key structure + * @data: Parse Graph CAM Key data to be parsed + */ +static void ice_pg_cam_key_init(struct ice_pg_cam_key *key, u8 *data) +{ + u64 d64 = *(u64 *)data; + + key->valid = FIELD_GET(ICE_PGCK_VLD, d64); + key->node_id = FIELD_GET(ICE_PGCK_NID, d64); + key->flag0 = FIELD_GET(ICE_PGCK_F0, d64); + key->flag1 = FIELD_GET(ICE_PGCK_F1, d64); + key->flag2 = FIELD_GET(ICE_PGCK_F2, d64); + key->flag3 = FIELD_GET(ICE_PGCK_F3, d64); + + if (FIELD_GET(ICE_PGCK_BH, d64)) + key->boost_idx = FIELD_GET(ICE_PGCK_BI, d64); + else + key->boost_idx = 0; + + key->alu_reg = FIELD_GET(ICE_PGCK_AR, d64); + + d64 = *((u64 *)&data[ICE_PGCK_NPK_IDD]) >> ICE_PGCK_NPK_OFF; + + key->next_proto = FIELD_GET(ICE_PGCK_NPK, d64); +} + +#define ICE_PG_CAM_ACT_S 73 +#define ICE_PG_CAM_ACT_IDD (ICE_PG_CAM_ACT_S / BITS_PER_BYTE) +#define ICE_PG_CAM_ACT_OFF (ICE_PG_CAM_ACT_S % BITS_PER_BYTE) + +/** + * ice_pg_cam_parse_item - parse 128 bits of Parse Graph CAM Entry + * @hw: pointer to the hardware structure + * @idx: index of Parse Graph CAM Entry + * @item: item of Parse Graph CAM Entry + * @data: Parse Graph CAM Entry data to be parsed + * @size: size of Parse Graph CAM Entry + */ +static void ice_pg_cam_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_pg_cam_item *ci = item; + u8 *buf = data; + u64 d64; + + ci->idx = idx; + + ice_pg_cam_key_init(&ci->key, buf); + + d64 = *((u64 *)&buf[ICE_PG_CAM_ACT_IDD]) >> ICE_PG_CAM_ACT_OFF; + ice_pg_cam_action_init(&ci->action, d64); +} + +#define ICE_PG_SP_CAM_KEY_S 56 +#define ICE_PG_SP_CAM_KEY_IDD (ICE_PG_SP_CAM_KEY_S / BITS_PER_BYTE) + +/** + * ice_pg_sp_cam_parse_item - parse 136 bits of Parse Graph Spill CAM Entry + * @hw: pointer to the hardware structure + * @idx: index of Parse Graph Spill CAM Entry + * @item: item of Parse Graph Spill CAM Entry + * @data: Parse Graph Spill CAM Entry data to be parsed + * @size: size of Parse Graph Spill CAM Entry + */ +static void ice_pg_sp_cam_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_pg_cam_item *ci = item; + u8 *buf = data; + u64 d64; + + ci->idx = idx; + + d64 = *(u64 *)buf; + ice_pg_cam_action_init(&ci->action, d64); + + ice_pg_cam_key_init(&ci->key, &buf[ICE_PG_SP_CAM_KEY_IDD]); +} + +#define ICE_PG_NM_CAM_ACT_S 41 +#define ICE_PG_NM_CAM_ACT_IDD (ICE_PG_NM_CAM_ACT_S / BITS_PER_BYTE) +#define ICE_PG_NM_CAM_ACT_OFF (ICE_PG_NM_CAM_ACT_S % BITS_PER_BYTE) + +/** + * ice_pg_nm_cam_parse_item - parse 96 bits of Parse Graph NoMatch CAM Entry + * @hw: pointer to the hardware structure + * @idx: index of Parse Graph NoMatch CAM Entry + * @item: item of Parse Graph NoMatch CAM Entry + * @data: Parse Graph NoMatch CAM Entry data to be parsed + * @size: size of Parse Graph NoMatch CAM Entry + */ +static void ice_pg_nm_cam_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_pg_nm_cam_item *ci = item; + u8 *buf = data; + u64 d64; + + ci->idx = idx; + + d64 = *(u64 *)buf; + ice_pg_nm_cam_key_init(&ci->key, d64); + + d64 = *((u64 *)&buf[ICE_PG_NM_CAM_ACT_IDD]) >> ICE_PG_NM_CAM_ACT_OFF; + ice_pg_cam_action_init(&ci->action, d64); +} + +#define ICE_PG_NM_SP_CAM_ACT_S 56 +#define ICE_PG_NM_SP_CAM_ACT_IDD (ICE_PG_NM_SP_CAM_ACT_S / BITS_PER_BYTE) +#define ICE_PG_NM_SP_CAM_ACT_OFF (ICE_PG_NM_SP_CAM_ACT_S % BITS_PER_BYTE) + +/** + * ice_pg_nm_sp_cam_parse_item - parse 104 bits of Parse Graph NoMatch Spill + * CAM Entry + * @hw: pointer to the hardware structure + * @idx: index of Parse Graph NoMatch Spill CAM Entry + * @item: item of Parse Graph NoMatch Spill CAM Entry + * @data: Parse Graph NoMatch Spill CAM Entry data to be parsed + * @size: size of Parse Graph NoMatch Spill CAM Entry + */ +static void ice_pg_nm_sp_cam_parse_item(struct ice_hw *hw, u16 idx, + void *item, void *data, + int __maybe_unused size) +{ + struct ice_pg_nm_cam_item *ci = item; + u8 *buf = data; + u64 d64; + + ci->idx = idx; + + d64 = *(u64 *)buf; + ice_pg_cam_action_init(&ci->action, d64); + + d64 = *((u64 *)&buf[ICE_PG_NM_SP_CAM_ACT_IDD]) >> + ICE_PG_NM_SP_CAM_ACT_OFF; + ice_pg_nm_cam_key_init(&ci->key, d64); +} + +/** + * ice_pg_cam_table_get - create a parse graph cam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Parse Graph CAM table. + */ +static struct ice_pg_cam_item *ice_pg_cam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_CAM, + sizeof(struct ice_pg_cam_item), + ICE_PG_CAM_TABLE_SIZE, + ice_pg_cam_parse_item, false); +} + +/** + * ice_pg_sp_cam_table_get - create a parse graph spill cam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Parse Graph Spill CAM table. + */ +static struct ice_pg_cam_item *ice_pg_sp_cam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_PG_SPILL, + sizeof(struct ice_pg_cam_item), + ICE_PG_SP_CAM_TABLE_SIZE, + ice_pg_sp_cam_parse_item, false); +} + +/** + * ice_pg_nm_cam_table_get - create a parse graph no match cam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Parse Graph No Match CAM table. + */ +static struct ice_pg_nm_cam_item *ice_pg_nm_cam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_NOMATCH_CAM, + sizeof(struct ice_pg_nm_cam_item), + ICE_PG_NM_CAM_TABLE_SIZE, + ice_pg_nm_cam_parse_item, false); +} + +/** + * ice_pg_nm_sp_cam_table_get - create a parse graph no match spill cam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Parse Graph No Match Spill CAM table. + */ +static struct ice_pg_nm_cam_item *ice_pg_nm_sp_cam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_NOMATCH_SPILL, + sizeof(struct ice_pg_nm_cam_item), + ICE_PG_NM_SP_CAM_TABLE_SIZE, + ice_pg_nm_sp_cam_parse_item, false); +} + +/*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/ +#define ICE_BST_ALU_OPC GENMASK_ULL(5, 0) +#define ICE_BST_ALU_SS GENMASK_ULL(13, 6) +#define ICE_BST_ALU_SL GENMASK_ULL(18, 14) +#define ICE_BST_ALU_SXS BIT_ULL(19) +#define ICE_BST_ALU_SXK GENMASK_ULL(23, 20) +#define ICE_BST_ALU_SRID GENMASK_ULL(30, 24) +#define ICE_BST_ALU_DRID GENMASK_ULL(37, 31) +#define ICE_BST_ALU_INC0 BIT_ULL(38) +#define ICE_BST_ALU_INC1 BIT_ULL(39) +#define ICE_BST_ALU_POO GENMASK_ULL(41, 40) +#define ICE_BST_ALU_PO GENMASK_ULL(49, 42) +#define ICE_BST_ALU_BA_S 50 /* offset for the 2nd 64-bits field */ +#define ICE_BST_ALU_BA GENMASK_ULL(57 - ICE_BST_ALU_BA_S, \ + 50 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_IMM GENMASK_ULL(73 - ICE_BST_ALU_BA_S, \ + 58 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_DFE BIT_ULL(74 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_DS GENMASK_ULL(80 - ICE_BST_ALU_BA_S, \ + 75 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_DL GENMASK_ULL(86 - ICE_BST_ALU_BA_S, \ + 81 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_FEI BIT_ULL(87 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_FSI GENMASK_ULL(95 - ICE_BST_ALU_BA_S, \ + 88 - ICE_BST_ALU_BA_S) + +/** + * ice_bst_alu_init - parse 96 bits of ALU entry + * @alu: pointer to the ALU entry structure + * @data: ALU entry data to be parsed + * @off: offset of the ALU entry data + */ +static void ice_bst_alu_init(struct ice_alu *alu, u8 *data, u8 off) +{ + u64 d64; + u8 idd; + + d64 = *((u64 *)data) >> off; + + alu->opc = FIELD_GET(ICE_BST_ALU_OPC, d64); + alu->src_start = FIELD_GET(ICE_BST_ALU_SS, d64); + alu->src_len = FIELD_GET(ICE_BST_ALU_SL, d64); + alu->shift_xlate_sel = FIELD_GET(ICE_BST_ALU_SXS, d64); + alu->shift_xlate_key = FIELD_GET(ICE_BST_ALU_SXK, d64); + alu->src_reg_id = FIELD_GET(ICE_BST_ALU_SRID, d64); + alu->dst_reg_id = FIELD_GET(ICE_BST_ALU_DRID, d64); + alu->inc0 = FIELD_GET(ICE_BST_ALU_INC0, d64); + alu->inc1 = FIELD_GET(ICE_BST_ALU_INC1, d64); + alu->proto_offset_opc = FIELD_GET(ICE_BST_ALU_POO, d64); + alu->proto_offset = FIELD_GET(ICE_BST_ALU_PO, d64); + + idd = (ICE_BST_ALU_BA_S + off) / BITS_PER_BYTE; + off = (ICE_BST_ALU_BA_S + off) % BITS_PER_BYTE; + d64 = *((u64 *)(&data[idd])) >> off; + + alu->branch_addr = FIELD_GET(ICE_BST_ALU_BA, d64); + alu->imm = FIELD_GET(ICE_BST_ALU_IMM, d64); + alu->dedicate_flags_ena = FIELD_GET(ICE_BST_ALU_DFE, d64); + alu->dst_start = FIELD_GET(ICE_BST_ALU_DS, d64); + alu->dst_len = FIELD_GET(ICE_BST_ALU_DL, d64); + alu->flags_extr_imm = FIELD_GET(ICE_BST_ALU_FEI, d64); + alu->flags_start_imm = FIELD_GET(ICE_BST_ALU_FSI, d64); +} + +#define ICE_BST_PGKB_F0_ENA BIT_ULL(0) +#define ICE_BST_PGKB_F0_IDX GENMASK_ULL(6, 1) +#define ICE_BST_PGKB_F1_ENA BIT_ULL(7) +#define ICE_BST_PGKB_F1_IDX GENMASK_ULL(13, 8) +#define ICE_BST_PGKB_F2_ENA BIT_ULL(14) +#define ICE_BST_PGKB_F2_IDX GENMASK_ULL(20, 15) +#define ICE_BST_PGKB_F3_ENA BIT_ULL(21) +#define ICE_BST_PGKB_F3_IDX GENMASK_ULL(27, 22) +#define ICE_BST_PGKB_AR_IDX GENMASK_ULL(34, 28) + +/** + * ice_bst_pgkb_init - parse 35 bits of Parse Graph Key Build + * @kb: pointer to the Parse Graph Key Build structure + * @data: Parse Graph Key Build data to be parsed + */ +static void ice_bst_pgkb_init(struct ice_pg_keybuilder *kb, u64 data) +{ + kb->flag0_ena = FIELD_GET(ICE_BST_PGKB_F0_ENA, data); + kb->flag0_idx = FIELD_GET(ICE_BST_PGKB_F0_IDX, data); + kb->flag1_ena = FIELD_GET(ICE_BST_PGKB_F1_ENA, data); + kb->flag1_idx = FIELD_GET(ICE_BST_PGKB_F1_IDX, data); + kb->flag2_ena = FIELD_GET(ICE_BST_PGKB_F2_ENA, data); + kb->flag2_idx = FIELD_GET(ICE_BST_PGKB_F2_IDX, data); + kb->flag3_ena = FIELD_GET(ICE_BST_PGKB_F3_ENA, data); + kb->flag3_idx = FIELD_GET(ICE_BST_PGKB_F3_IDX, data); + kb->alu_reg_idx = FIELD_GET(ICE_BST_PGKB_AR_IDX, data); +} + +#define ICE_BST_NPKB_OPC GENMASK(1, 0) +#define ICE_BST_NPKB_S_R0 GENMASK(9, 2) +#define ICE_BST_NPKB_L_R1 GENMASK(17, 10) + +/** + * ice_bst_npkb_init - parse 18 bits of Next Protocol Key Build + * @kb: pointer to the Next Protocol Key Build structure + * @data: Next Protocol Key Build data to be parsed + */ +static void ice_bst_npkb_init(struct ice_np_keybuilder *kb, u32 data) +{ + kb->opc = FIELD_GET(ICE_BST_NPKB_OPC, data); + kb->start_reg0 = FIELD_GET(ICE_BST_NPKB_S_R0, data); + kb->len_reg1 = FIELD_GET(ICE_BST_NPKB_L_R1, data); +} + +#define ICE_BT_KEY_S 32 +#define ICE_BT_KEY_IDD (ICE_BT_KEY_S / BITS_PER_BYTE) +#define ICE_BT_KIV_S 192 +#define ICE_BT_KIV_IDD (ICE_BT_KIV_S / BITS_PER_BYTE) +#define ICE_BT_HIG_S 352 +#define ICE_BT_HIG_IDD (ICE_BT_HIG_S / BITS_PER_BYTE) +#define ICE_BT_PGP_S 360 +#define ICE_BT_PGP_IDD (ICE_BT_PGP_S / BITS_PER_BYTE) +#define ICE_BT_PGP_M GENMASK(361 - ICE_BT_PGP_S, 360 - ICE_BT_PGP_S) +#define ICE_BT_NPKB_S 362 +#define ICE_BT_NPKB_IDD (ICE_BT_NPKB_S / BITS_PER_BYTE) +#define ICE_BT_NPKB_OFF (ICE_BT_NPKB_S % BITS_PER_BYTE) +#define ICE_BT_PGKB_S 380 +#define ICE_BT_PGKB_IDD (ICE_BT_PGKB_S / BITS_PER_BYTE) +#define ICE_BT_PGKB_OFF (ICE_BT_PGKB_S % BITS_PER_BYTE) +#define ICE_BT_ALU0_S 415 +#define ICE_BT_ALU0_IDD (ICE_BT_ALU0_S / BITS_PER_BYTE) +#define ICE_BT_ALU0_OFF (ICE_BT_ALU0_S % BITS_PER_BYTE) +#define ICE_BT_ALU1_S 511 +#define ICE_BT_ALU1_IDD (ICE_BT_ALU1_S / BITS_PER_BYTE) +#define ICE_BT_ALU1_OFF (ICE_BT_ALU1_S % BITS_PER_BYTE) +#define ICE_BT_ALU2_S 607 +#define ICE_BT_ALU2_IDD (ICE_BT_ALU2_S / BITS_PER_BYTE) +#define ICE_BT_ALU2_OFF (ICE_BT_ALU2_S % BITS_PER_BYTE) + +/** + * ice_bst_parse_item - parse 704 bits of Boost TCAM entry + * @hw: pointer to the hardware structure + * @idx: index of Boost TCAM entry + * @item: item of Boost TCAM entry + * @data: Boost TCAM entry data to be parsed + * @size: size of Boost TCAM entry + */ +static void ice_bst_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_bst_tcam_item *ti = item; + u8 *buf = (u8 *)data; + int i; + + ti->addr = *(u16 *)buf; + + for (i = 0; i < ICE_BST_TCAM_KEY_SIZE; i++) { + ti->key[i] = buf[ICE_BT_KEY_IDD + i]; + ti->key_inv[i] = buf[ICE_BT_KIV_IDD + i]; + } + ti->hit_idx_grp = buf[ICE_BT_HIG_IDD]; + ti->pg_prio = buf[ICE_BT_PGP_IDD] & ICE_BT_PGP_M; + + ice_bst_npkb_init(&ti->np_kb, + *((u32 *)(&buf[ICE_BT_NPKB_IDD])) >> + ICE_BT_NPKB_OFF); + ice_bst_pgkb_init(&ti->pg_kb, + *((u64 *)(&buf[ICE_BT_PGKB_IDD])) >> + ICE_BT_PGKB_OFF); + + ice_bst_alu_init(&ti->alu0, &buf[ICE_BT_ALU0_IDD], ICE_BT_ALU0_OFF); + ice_bst_alu_init(&ti->alu1, &buf[ICE_BT_ALU1_IDD], ICE_BT_ALU1_OFF); + ice_bst_alu_init(&ti->alu2, &buf[ICE_BT_ALU2_IDD], ICE_BT_ALU2_OFF); +} + +/** + * ice_bst_tcam_table_get - create a boost tcam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Boost TCAM table. + */ +static struct ice_bst_tcam_item *ice_bst_tcam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_BOOST_TCAM, + sizeof(struct ice_bst_tcam_item), + ICE_BST_TCAM_TABLE_SIZE, + ice_bst_parse_item, true); +} + +static void ice_parse_lbl_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int size) +{ + memcpy(item, data, size); +} + +/** + * ice_bst_lbl_table_get - create a boost label table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Boost label table. + */ +static struct ice_lbl_item *ice_bst_lbl_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_LBL_RXPARSER_TMEM, + sizeof(struct ice_lbl_item), + ICE_BST_TCAM_TABLE_SIZE, + ice_parse_lbl_item, true); +} + +/*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/ +static void ice_parse_ptype_mk_tcam_item(struct ice_hw *hw, u16 idx, + void *item, void *data, int size) +{ + memcpy(item, data, size); +} + +/** + * ice_ptype_mk_tcam_table_get - create a ptype marker tcam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Marker PType TCAM table. + */ +static +struct ice_ptype_mk_tcam_item *ice_ptype_mk_tcam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_MARKER_PTYPE, + sizeof(struct ice_ptype_mk_tcam_item), + ICE_PTYPE_MK_TCAM_TABLE_SIZE, + ice_parse_ptype_mk_tcam_item, true); +} + +/*** ICE_SID_RXPARSER_MARKER_GRP section ***/ +static void ice_mk_grp_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_mk_grp_item *grp = item; + u8 *buf = data; + int i; + + grp->idx = idx; + + for (i = 0; i < ICE_MK_COUNT_PER_GRP; i++) + grp->markers[i] = buf[i]; +} + +/** + * ice_mk_grp_table_get - create a marker group table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Marker Group ID table. + */ +static struct ice_mk_grp_item *ice_mk_grp_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_MARKER_GRP, + sizeof(struct ice_mk_grp_item), + ICE_MK_GRP_TABLE_SIZE, + ice_mk_grp_parse_item, false); +} + +/*** ICE_SID_RXPARSER_PROTO_GRP section ***/ +#define ICE_PO_POL BIT(0) +#define ICE_PO_PID GENMASK(8, 1) +#define ICE_PO_OFF GENMASK(21, 12) + +/** + * ice_proto_off_parse - parse 22 bits of Protocol entry + * @po: pointer to the Protocol entry structure + * @data: Protocol entry data to be parsed + */ +static void ice_proto_off_parse(struct ice_proto_off *po, u32 data) +{ + po->polarity = FIELD_GET(ICE_PO_POL, data); + po->proto_id = FIELD_GET(ICE_PO_PID, data); + po->offset = FIELD_GET(ICE_PO_OFF, data); +} + +/** + * ice_proto_grp_parse_item - parse 192 bits of Protocol Group Table entry + * @hw: pointer to the hardware structure + * @idx: index of Protocol Group Table entry + * @item: item of Protocol Group Table entry + * @data: Protocol Group Table entry data to be parsed + * @size: size of Protocol Group Table entry + */ +static void ice_proto_grp_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_proto_grp_item *grp = item; + u8 *buf = (u8 *)data; + u8 idd, off; + u32 d32; + int i; + + grp->idx = idx; + + for (i = 0; i < ICE_PROTO_COUNT_PER_GRP; i++) { + idd = (ICE_PROTO_GRP_ITEM_SIZE * i) / BITS_PER_BYTE; + off = (ICE_PROTO_GRP_ITEM_SIZE * i) % BITS_PER_BYTE; + d32 = *((u32 *)&buf[idd]) >> off; + ice_proto_off_parse(&grp->po[i], d32); + } +} + +/** + * ice_proto_grp_table_get - create a proto group table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Protocol Group table. + */ +static struct ice_proto_grp_item *ice_proto_grp_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_PROTO_GRP, + sizeof(struct ice_proto_grp_item), + ICE_PROTO_GRP_TABLE_SIZE, + ice_proto_grp_parse_item, false); +} + +/*** ICE_SID_RXPARSER_FLAG_REDIR section ***/ +#define ICE_FRT_EXPO BIT(0) +#define ICE_FRT_IFID GENMASK(6, 1) + +/** + * ice_flg_rd_parse_item - parse 8 bits of Flag Redirect Table entry + * @hw: pointer to the hardware structure + * @idx: index of Flag Redirect Table entry + * @item: item of Flag Redirect Table entry + * @data: Flag Redirect Table entry data to be parsed + * @size: size of Flag Redirect Table entry + */ +static void ice_flg_rd_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_flg_rd_item *rdi = item; + u8 d8 = *(u8 *)data; + + rdi->idx = idx; + rdi->expose = FIELD_GET(ICE_FRT_EXPO, d8); + rdi->intr_flg_id = FIELD_GET(ICE_FRT_IFID, d8); +} + +/** + * ice_flg_rd_table_get - create a flag redirect table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Flags Redirection table. + */ +static struct ice_flg_rd_item *ice_flg_rd_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_FLAG_REDIR, + sizeof(struct ice_flg_rd_item), + ICE_FLG_RD_TABLE_SIZE, + ice_flg_rd_parse_item, false); +} + +/*** ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL, + * ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS + * sections ***/ +#define ICE_XLT_KB_X1AS_S 32 /* offset for the 1st 64-bits field */ +#define ICE_XLT_KB_X1AS_IDD (ICE_XLT_KB_X1AS_S / BITS_PER_BYTE) +#define ICE_XLT_KB_X1AS_OFF (ICE_XLT_KB_X1AS_S % BITS_PER_BYTE) +#define ICE_XLT_KB_X1AS GENMASK_ULL(34 - ICE_XLT_KB_X1AS_S, \ + 32 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_X2AS GENMASK_ULL(37 - ICE_XLT_KB_X1AS_S, \ + 35 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL00 GENMASK_ULL(46 - ICE_XLT_KB_X1AS_S, \ + 38 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL01 GENMASK_ULL(55 - ICE_XLT_KB_X1AS_S, \ + 47 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL02 GENMASK_ULL(64 - ICE_XLT_KB_X1AS_S, \ + 56 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL03 GENMASK_ULL(73 - ICE_XLT_KB_X1AS_S, \ + 65 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL04 GENMASK_ULL(82 - ICE_XLT_KB_X1AS_S, \ + 74 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL05 GENMASK_ULL(91 - ICE_XLT_KB_X1AS_S, \ + 83 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL06_S 92 /* offset for the 2nd 64-bits field */ +#define ICE_XLT_KB_FL06_IDD (ICE_XLT_KB_FL06_S / BITS_PER_BYTE) +#define ICE_XLT_KB_FL06_OFF (ICE_XLT_KB_FL06_S % BITS_PER_BYTE) +#define ICE_XLT_KB_FL06 GENMASK_ULL(100 - ICE_XLT_KB_FL06_S, \ + 92 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL07 GENMASK_ULL(109 - ICE_XLT_KB_FL06_S, \ + 101 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL08 GENMASK_ULL(118 - ICE_XLT_KB_FL06_S, \ + 110 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL09 GENMASK_ULL(127 - ICE_XLT_KB_FL06_S, \ + 119 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL10 GENMASK_ULL(136 - ICE_XLT_KB_FL06_S, \ + 128 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL11 GENMASK_ULL(145 - ICE_XLT_KB_FL06_S, \ + 137 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL12_S 146 /* offset for the 3rd 64-bits field */ +#define ICE_XLT_KB_FL12_IDD (ICE_XLT_KB_FL12_S / BITS_PER_BYTE) +#define ICE_XLT_KB_FL12_OFF (ICE_XLT_KB_FL12_S % BITS_PER_BYTE) +#define ICE_XLT_KB_FL12 GENMASK_ULL(154 - ICE_XLT_KB_FL12_S, \ + 146 - ICE_XLT_KB_FL12_S) +#define ICE_XLT_KB_FL13 GENMASK_ULL(163 - ICE_XLT_KB_FL12_S, \ + 155 - ICE_XLT_KB_FL12_S) +#define ICE_XLT_KB_FL14 GENMASK_ULL(181 - ICE_XLT_KB_FL12_S, \ + 164 - ICE_XLT_KB_FL12_S) +#define ICE_XLT_KB_X1MS GENMASK_ULL(186 - ICE_XLT_KB_FL12_S, \ + 182 - ICE_XLT_KB_FL12_S) +#define ICE_XLT_KB_X2MS GENMASK_ULL(191 - ICE_XLT_KB_FL12_S, \ + 187 - ICE_XLT_KB_FL12_S) + +/** + * ice_kb_entry_init - parse 192 bits of XLT Key Builder entry + * @entry: pointer to the XLT Key Builder entry structure + * @data: XLT Key Builder entry data to be parsed + */ +static void ice_kb_entry_init(struct ice_xlt_kb_entry *entry, u8 *data) +{ + u8 i = 0; + u64 d64; + + d64 = *((u64 *)&data[ICE_XLT_KB_X1AS_IDD]) >> ICE_XLT_KB_X1AS_OFF; + + entry->xlt1_ad_sel = FIELD_GET(ICE_XLT_KB_X1AS, d64); + entry->xlt2_ad_sel = FIELD_GET(ICE_XLT_KB_X2AS, d64); + + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL00, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL01, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL02, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL03, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL04, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL05, d64); + + d64 = *((u64 *)&data[ICE_XLT_KB_FL06_IDD]) >> ICE_XLT_KB_FL06_OFF; + + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL06, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL07, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL08, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL09, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL10, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL11, d64); + + d64 = *((u64 *)&data[ICE_XLT_KB_FL12_IDD]) >> ICE_XLT_KB_FL12_OFF; + + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL12, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL13, d64); + entry->flg0_14_sel[i] = FIELD_GET(ICE_XLT_KB_FL14, d64); + + entry->xlt1_md_sel = FIELD_GET(ICE_XLT_KB_X1MS, d64); + entry->xlt2_md_sel = FIELD_GET(ICE_XLT_KB_X2MS, d64); +} + +#define ICE_XLT_KB_X1PM_OFF 0 +#define ICE_XLT_KB_X2PM_OFF 1 +#define ICE_XLT_KB_PIPM_OFF 2 +#define ICE_XLT_KB_FL15_OFF 4 +#define ICE_XLT_KB_TBL_OFF 12 + +/** + * ice_parse_kb_data - parse 204 bits of XLT Key Build Table + * @hw: pointer to the hardware structure + * @kb: pointer to the XLT Key Build Table structure + * @data: XLT Key Build Table data to be parsed + */ +static void ice_parse_kb_data(struct ice_hw *hw, struct ice_xlt_kb *kb, + void *data) +{ + u8 *buf = data; + int i; + + kb->xlt1_pm = buf[ICE_XLT_KB_X1PM_OFF]; + kb->xlt2_pm = buf[ICE_XLT_KB_X2PM_OFF]; + kb->prof_id_pm = buf[ICE_XLT_KB_PIPM_OFF]; + + kb->flag15 = *(u64 *)&buf[ICE_XLT_KB_FL15_OFF]; + for (i = 0; i < ICE_XLT_KB_TBL_CNT; i++) + ice_kb_entry_init(&kb->entries[i], + &buf[ICE_XLT_KB_TBL_OFF + + i * ICE_XLT_KB_TBL_ENTRY_SIZE]); +} + +static struct ice_xlt_kb *ice_xlt_kb_get(struct ice_hw *hw, u32 sect_type) +{ + struct ice_pkg_enum state = {}; + struct ice_seg *seg = hw->seg; + struct ice_xlt_kb *kb; + void *data; + + if (!seg) + return ERR_PTR(-EINVAL); + + kb = kzalloc(sizeof(*kb), GFP_KERNEL); + if (!kb) + return ERR_PTR(-ENOMEM); + + data = ice_pkg_enum_section(seg, &state, sect_type); + if (!data) { + ice_debug(hw, ICE_DBG_PARSER, "failed to find section type %d.\n", + sect_type); + kfree(kb); + return ERR_PTR(-EINVAL); + } + + ice_parse_kb_data(hw, kb, data); + + return kb; +} + +/** + * ice_xlt_kb_get_sw - create switch xlt key build + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Key Builder table for Switch. + */ +static struct ice_xlt_kb *ice_xlt_kb_get_sw(struct ice_hw *hw) +{ + return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_SW); +} + +/** + * ice_xlt_kb_get_acl - create acl xlt key build + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Key Builder table for ACL. + */ +static struct ice_xlt_kb *ice_xlt_kb_get_acl(struct ice_hw *hw) +{ + return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_ACL); +} + +/** + * ice_xlt_kb_get_fd - create fdir xlt key build + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Key Builder table for Flow Director. + */ +static struct ice_xlt_kb *ice_xlt_kb_get_fd(struct ice_hw *hw) +{ + return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_FD); +} + +/** + * ice_xlt_kb_get_rss - create rss xlt key build + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Key Builder table for RSS. + */ +static struct ice_xlt_kb *ice_xlt_kb_get_rss(struct ice_hw *hw) +{ + return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_RSS); +} + +/*** Parser API ***/ /** * ice_parser_create - create a parser instance * @hw: pointer to the hardware structure @@ -13,13 +1278,114 @@ struct ice_parser *ice_parser_create(struct ice_hw *hw) { struct ice_parser *p; + void *err; p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); p->hw = hw; + + p->imem_table = ice_imem_table_get(hw); + if (IS_ERR(p->imem_table)) { + err = p->imem_table; + goto err; + } + + p->mi_table = ice_metainit_table_get(hw); + if (IS_ERR(p->mi_table)) { + err = p->mi_table; + goto err; + } + + p->pg_cam_table = ice_pg_cam_table_get(hw); + if (IS_ERR(p->pg_cam_table)) { + err = p->pg_cam_table; + goto err; + } + + p->pg_sp_cam_table = ice_pg_sp_cam_table_get(hw); + if (IS_ERR(p->pg_sp_cam_table)) { + err = p->pg_sp_cam_table; + goto err; + } + + p->pg_nm_cam_table = ice_pg_nm_cam_table_get(hw); + if (IS_ERR(p->pg_nm_cam_table)) { + err = p->pg_nm_cam_table; + goto err; + } + + p->pg_nm_sp_cam_table = ice_pg_nm_sp_cam_table_get(hw); + if (IS_ERR(p->pg_nm_sp_cam_table)) { + err = p->pg_nm_sp_cam_table; + goto err; + } + + p->bst_tcam_table = ice_bst_tcam_table_get(hw); + if (IS_ERR(p->bst_tcam_table)) { + err = p->bst_tcam_table; + goto err; + } + + p->bst_lbl_table = ice_bst_lbl_table_get(hw); + if (IS_ERR(p->bst_lbl_table)) { + err = p->bst_lbl_table; + goto err; + } + + p->ptype_mk_tcam_table = ice_ptype_mk_tcam_table_get(hw); + if (IS_ERR(p->ptype_mk_tcam_table)) { + err = p->ptype_mk_tcam_table; + goto err; + } + + p->mk_grp_table = ice_mk_grp_table_get(hw); + if (IS_ERR(p->mk_grp_table)) { + err = p->mk_grp_table; + goto err; + } + + p->proto_grp_table = ice_proto_grp_table_get(hw); + if (IS_ERR(p->proto_grp_table)) { + err = p->proto_grp_table; + goto err; + } + + p->flg_rd_table = ice_flg_rd_table_get(hw); + if (IS_ERR(p->flg_rd_table)) { + err = p->flg_rd_table; + goto err; + } + + p->xlt_kb_sw = ice_xlt_kb_get_sw(hw); + if (IS_ERR(p->xlt_kb_sw)) { + err = p->xlt_kb_sw; + goto err; + } + + p->xlt_kb_acl = ice_xlt_kb_get_acl(hw); + if (IS_ERR(p->xlt_kb_acl)) { + err = p->xlt_kb_acl; + goto err; + } + + p->xlt_kb_fd = ice_xlt_kb_get_fd(hw); + if (IS_ERR(p->xlt_kb_fd)) { + err = p->xlt_kb_fd; + goto err; + } + + p->xlt_kb_rss = ice_xlt_kb_get_rss(hw); + if (IS_ERR(p->xlt_kb_rss)) { + err = p->xlt_kb_rss; + goto err; + } + return p; +err: + ice_parser_destroy(p); + return err; } /** @@ -28,5 +1394,22 @@ struct ice_parser *ice_parser_create(struct ice_hw *hw) */ void ice_parser_destroy(struct ice_parser *psr) { + kfree(psr->imem_table); + kfree(psr->mi_table); + kfree(psr->pg_cam_table); + kfree(psr->pg_sp_cam_table); + kfree(psr->pg_nm_cam_table); + kfree(psr->pg_nm_sp_cam_table); + kfree(psr->bst_tcam_table); + kfree(psr->bst_lbl_table); + kfree(psr->ptype_mk_tcam_table); + kfree(psr->mk_grp_table); + kfree(psr->proto_grp_table); + kfree(psr->flg_rd_table); + kfree(psr->xlt_kb_sw); + kfree(psr->xlt_kb_acl); + kfree(psr->xlt_kb_fd); + kfree(psr->xlt_kb_rss); + kfree(psr); } diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h index 09ed380eee320..6e8054d596448 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.h +++ b/drivers/net/ethernet/intel/ice/ice_parser.h @@ -4,8 +4,366 @@ #ifndef _ICE_PARSER_H_ #define _ICE_PARSER_H_ +#define ICE_SEC_DATA_OFFSET 4 +#define ICE_SID_RXPARSER_IMEM_ENTRY_SIZE 48 +#define ICE_SID_RXPARSER_METADATA_INIT_ENTRY_SIZE 24 +#define ICE_SID_RXPARSER_CAM_ENTRY_SIZE 16 +#define ICE_SID_RXPARSER_PG_SPILL_ENTRY_SIZE 17 +#define ICE_SID_RXPARSER_NOMATCH_CAM_ENTRY_SIZE 12 +#define ICE_SID_RXPARSER_NOMATCH_SPILL_ENTRY_SIZE 13 +#define ICE_SID_RXPARSER_BOOST_TCAM_ENTRY_SIZE 88 +#define ICE_SID_RXPARSER_MARKER_TYPE_ENTRY_SIZE 24 +#define ICE_SID_RXPARSER_MARKER_GRP_ENTRY_SIZE 8 +#define ICE_SID_RXPARSER_PROTO_GRP_ENTRY_SIZE 24 +#define ICE_SID_RXPARSER_FLAG_REDIR_ENTRY_SIZE 1 + +#define ICE_SEC_LBL_DATA_OFFSET 2 +#define ICE_SID_LBL_ENTRY_SIZE 66 + +/*** ICE_SID_RXPARSER_IMEM section ***/ +#define ICE_IMEM_TABLE_SIZE 192 + +/* TCAM boost Master; if bit is set, and TCAM hit, TCAM output overrides iMEM + * output. + */ +struct ice_bst_main { + bool alu0; + bool alu1; + bool alu2; + bool pg; +}; + +struct ice_bst_keybuilder { + u8 prio; /* 0-3: PG precedence within ALUs (3 highest) */ + bool tsr_ctrl; /* TCAM Search Register control */ +}; + +/* Next protocol Key builder */ +struct ice_np_keybuilder { + u8 opc; + u8 start_reg0; + u8 len_reg1; +}; + +enum ice_np_keybuilder_opcode { + ICE_NPKB_OPC_EXTRACT = 0, + ICE_NPKB_OPC_BUILD = 1, + ICE_NPKB_OPC_BYPASS = 2, +}; + +/* Parse Graph Key builder */ +struct ice_pg_keybuilder { + bool flag0_ena; + bool flag1_ena; + bool flag2_ena; + bool flag3_ena; + u8 flag0_idx; + u8 flag1_idx; + u8 flag2_idx; + u8 flag3_idx; + u8 alu_reg_idx; +}; + +enum ice_alu_idx { + ICE_ALU0_IDX = 0, + ICE_ALU1_IDX = 1, + ICE_ALU2_IDX = 2, +}; + +enum ice_alu_opcode { + ICE_ALU_PARK = 0, + ICE_ALU_MOV_ADD = 1, + ICE_ALU_ADD = 2, + ICE_ALU_MOV_AND = 4, + ICE_ALU_AND = 5, + ICE_ALU_AND_IMM = 6, + ICE_ALU_MOV_OR = 7, + ICE_ALU_OR = 8, + ICE_ALU_MOV_XOR = 9, + ICE_ALU_XOR = 10, + ICE_ALU_NOP = 11, + ICE_ALU_BR = 12, + ICE_ALU_BREQ = 13, + ICE_ALU_BRNEQ = 14, + ICE_ALU_BRGT = 15, + ICE_ALU_BRLT = 16, + ICE_ALU_BRGEQ = 17, + ICE_ALU_BRLEG = 18, + ICE_ALU_SETEQ = 19, + ICE_ALU_ANDEQ = 20, + ICE_ALU_OREQ = 21, + ICE_ALU_SETNEQ = 22, + ICE_ALU_ANDNEQ = 23, + ICE_ALU_ORNEQ = 24, + ICE_ALU_SETGT = 25, + ICE_ALU_ANDGT = 26, + ICE_ALU_ORGT = 27, + ICE_ALU_SETLT = 28, + ICE_ALU_ANDLT = 29, + ICE_ALU_ORLT = 30, + ICE_ALU_MOV_SUB = 31, + ICE_ALU_SUB = 32, + ICE_ALU_INVALID = 64, +}; + +enum ice_proto_off_opcode { + ICE_PO_OFF_REMAIN = 0, + ICE_PO_OFF_HDR_ADD = 1, + ICE_PO_OFF_HDR_SUB = 2, +}; + +struct ice_alu { + enum ice_alu_opcode opc; + u8 src_start; + u8 src_len; + bool shift_xlate_sel; + u8 shift_xlate_key; + u8 src_reg_id; + u8 dst_reg_id; + bool inc0; + bool inc1; + u8 proto_offset_opc; + u8 proto_offset; + u8 branch_addr; + u16 imm; + bool dedicate_flags_ena; + u8 dst_start; + u8 dst_len; + bool flags_extr_imm; + u8 flags_start_imm; +}; + +/* Parser program code (iMEM) */ +struct ice_imem_item { + u16 idx; + struct ice_bst_main b_m; + struct ice_bst_keybuilder b_kb; + u8 pg_prio; + struct ice_np_keybuilder np_kb; + struct ice_pg_keybuilder pg_kb; + struct ice_alu alu0; + struct ice_alu alu1; + struct ice_alu alu2; +}; + +/*** ICE_SID_RXPARSER_METADATA_INIT section ***/ +#define ICE_METAINIT_TABLE_SIZE 16 + +/* Metadata Initialization item */ +struct ice_metainit_item { + u16 idx; + + u8 tsr; /* TCAM Search key Register */ + u16 ho; /* Header Offset register */ + u16 pc; /* Program Counter register */ + u16 pg_rn; /* Parse Graph Root Node */ + u8 cd; /* Control Domain ID */ + + /* General Purpose Registers */ + bool gpr_a_ctrl; + u8 gpr_a_data_mdid; + u8 gpr_a_data_start; + u8 gpr_a_data_len; + u8 gpr_a_id; + + bool gpr_b_ctrl; + u8 gpr_b_data_mdid; + u8 gpr_b_data_start; + u8 gpr_b_data_len; + u8 gpr_b_id; + + bool gpr_c_ctrl; + u8 gpr_c_data_mdid; + u8 gpr_c_data_start; + u8 gpr_c_data_len; + u8 gpr_c_id; + + bool gpr_d_ctrl; + u8 gpr_d_data_mdid; + u8 gpr_d_data_start; + u8 gpr_d_data_len; + u8 gpr_d_id; + + u64 flags; /* Initial value for all flags */ +}; + +/*** ICE_SID_RXPARSER_CAM, ICE_SID_RXPARSER_PG_SPILL, + * ICE_SID_RXPARSER_NOMATCH_CAM and ICE_SID_RXPARSER_NOMATCH_CAM + * sections ***/ +#define ICE_PG_CAM_TABLE_SIZE 2048 +#define ICE_PG_SP_CAM_TABLE_SIZE 128 +#define ICE_PG_NM_CAM_TABLE_SIZE 1024 +#define ICE_PG_NM_SP_CAM_TABLE_SIZE 64 + +struct ice_pg_cam_key { + bool valid; + u16 node_id; /* Node ID of protocol in parse graph */ + bool flag0; + bool flag1; + bool flag2; + bool flag3; + u8 boost_idx; /* Boost TCAM match index */ + u16 alu_reg; + u32 next_proto; /* next Protocol value */ +}; + +struct ice_pg_nm_cam_key { + bool valid; + u16 node_id; + bool flag0; + bool flag1; + bool flag2; + bool flag3; + u8 boost_idx; + u16 alu_reg; +}; + +struct ice_pg_cam_action { + u16 next_node; /* Parser Node ID for the next round */ + u8 next_pc; /* next Program Counter */ + bool is_pg; /* is protocol group */ + u8 proto_id; /* protocol ID or proto group ID */ + bool is_mg; /* is marker group */ + u8 marker_id; /* marker ID or marker group ID */ + bool is_last_round; + bool ho_polarity; /* header offset polarity */ + u16 ho_inc; +}; + +/* Parse Graph item */ +struct ice_pg_cam_item { + u16 idx; + struct ice_pg_cam_key key; + struct ice_pg_cam_action action; +}; + +/* Parse Graph No Match item */ +struct ice_pg_nm_cam_item { + u16 idx; + struct ice_pg_nm_cam_key key; + struct ice_pg_cam_action action; +}; + +/*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/ +#define ICE_BST_TCAM_TABLE_SIZE 256 +#define ICE_BST_TCAM_KEY_SIZE 20 +#define ICE_BST_KEY_TCAM_SIZE 19 + +/* Boost TCAM item */ +struct ice_bst_tcam_item { + u16 addr; + u8 key[ICE_BST_TCAM_KEY_SIZE]; + u8 key_inv[ICE_BST_TCAM_KEY_SIZE]; + u8 hit_idx_grp; + u8 pg_prio; + struct ice_np_keybuilder np_kb; + struct ice_pg_keybuilder pg_kb; + struct ice_alu alu0; + struct ice_alu alu1; + struct ice_alu alu2; +}; + +#define ICE_LBL_LEN 64 +struct ice_lbl_item { + u16 idx; + char label[ICE_LBL_LEN]; +}; + +/*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/ +#define ICE_PTYPE_MK_TCAM_TABLE_SIZE 1024 +#define ICE_PTYPE_MK_TCAM_KEY_SIZE 10 + +struct ice_ptype_mk_tcam_item { + u16 address; + u16 ptype; + u8 key[ICE_PTYPE_MK_TCAM_KEY_SIZE]; + u8 key_inv[ICE_PTYPE_MK_TCAM_KEY_SIZE]; +} __packed; + +/*** ICE_SID_RXPARSER_MARKER_GRP section ***/ +#define ICE_MK_GRP_TABLE_SIZE 128 +#define ICE_MK_COUNT_PER_GRP 8 + +/* Marker Group item */ +struct ice_mk_grp_item { + int idx; + u8 markers[ICE_MK_COUNT_PER_GRP]; +}; + +/*** ICE_SID_RXPARSER_PROTO_GRP section ***/ +#define ICE_PROTO_COUNT_PER_GRP 8 +#define ICE_PROTO_GRP_TABLE_SIZE 192 +#define ICE_PROTO_GRP_ITEM_SIZE 22 +struct ice_proto_off { + bool polarity; /* true: positive, false: negative */ + u8 proto_id; + u16 offset; /* 10 bit protocol offset */ +}; + +/* Protocol Group item */ +struct ice_proto_grp_item { + u16 idx; + struct ice_proto_off po[ICE_PROTO_COUNT_PER_GRP]; +}; + +/*** ICE_SID_RXPARSER_FLAG_REDIR section ***/ +#define ICE_FLG_RD_TABLE_SIZE 64 + +/* Flags Redirection item */ +struct ice_flg_rd_item { + u16 idx; + bool expose; + u8 intr_flg_id; /* Internal Flag ID */ +}; + +/*** ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL, + * ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS + * sections ***/ +#define ICE_XLT_KB_FLAG0_14_CNT 15 +#define ICE_XLT_KB_TBL_CNT 8 +#define ICE_XLT_KB_TBL_ENTRY_SIZE 24 + +struct ice_xlt_kb_entry { + u8 xlt1_ad_sel; + u8 xlt2_ad_sel; + u16 flg0_14_sel[ICE_XLT_KB_FLAG0_14_CNT]; + u8 xlt1_md_sel; + u8 xlt2_md_sel; +}; + +/* XLT Key Builder */ +struct ice_xlt_kb { + u8 xlt1_pm; /* XLT1 Partition Mode */ + u8 xlt2_pm; /* XLT2 Partition Mode */ + u8 prof_id_pm; /* Profile ID Partition Mode */ + u64 flag15; + + struct ice_xlt_kb_entry entries[ICE_XLT_KB_TBL_CNT]; +}; + +/*** Parser API ***/ struct ice_parser { struct ice_hw *hw; /* pointer to the hardware structure */ + + struct ice_imem_item *imem_table; + struct ice_metainit_item *mi_table; + + struct ice_pg_cam_item *pg_cam_table; + struct ice_pg_cam_item *pg_sp_cam_table; + struct ice_pg_nm_cam_item *pg_nm_cam_table; + struct ice_pg_nm_cam_item *pg_nm_sp_cam_table; + + struct ice_bst_tcam_item *bst_tcam_table; + struct ice_lbl_item *bst_lbl_table; + struct ice_ptype_mk_tcam_item *ptype_mk_tcam_table; + struct ice_mk_grp_item *mk_grp_table; + struct ice_proto_grp_item *proto_grp_table; + struct ice_flg_rd_item *flg_rd_table; + + struct ice_xlt_kb *xlt_kb_sw; + struct ice_xlt_kb *xlt_kb_acl; + struct ice_xlt_kb *xlt_kb_fd; + struct ice_xlt_kb *xlt_kb_rss; }; struct ice_parser *ice_parser_create(struct ice_hw *hw); diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 96037bef3e784..b9e4432323355 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -61,6 +61,7 @@ static inline u32 ice_round_to_num(u32 N, u32 R) ICE_DBG_AQ_DESC | \ ICE_DBG_AQ_DESC_BUF | \ ICE_DBG_AQ_CMD) +#define ICE_DBG_PARSER BIT_ULL(28) #define ICE_DBG_USER BIT_ULL(31) From 68add288189a5490868ccf8cbed273320568928d Mon Sep 17 00:00:00 2001 From: Junfeng Guo Date: Thu, 25 Jul 2024 16:07:59 -0600 Subject: [PATCH 106/385] ice: add debugging functions for the parser sections Add debug for all parser sections. Reviewed-by: Marcin Szycik Signed-off-by: Qi Zhang Signed-off-by: Junfeng Guo Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_parser.c | 470 ++++++++++++++++++++ 1 file changed, 470 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c index 5fdc87034fc69..23ba1a36742e6 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.c +++ b/drivers/net/ethernet/intel/ice/ice_parser.c @@ -129,6 +129,100 @@ ice_parser_create_table(struct ice_hw *hw, u32 sect_type, } /*** ICE_SID_RXPARSER_IMEM section ***/ +static void ice_imem_bst_bm_dump(struct ice_hw *hw, struct ice_bst_main *bm) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "boost main:\n"); + dev_info(dev, "\talu0 = %d\n", bm->alu0); + dev_info(dev, "\talu1 = %d\n", bm->alu1); + dev_info(dev, "\talu2 = %d\n", bm->alu2); + dev_info(dev, "\tpg = %d\n", bm->pg); +} + +static void ice_imem_bst_kb_dump(struct ice_hw *hw, + struct ice_bst_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "boost key builder:\n"); + dev_info(dev, "\tpriority = %d\n", kb->prio); + dev_info(dev, "\ttsr_ctrl = %d\n", kb->tsr_ctrl); +} + +static void ice_imem_np_kb_dump(struct ice_hw *hw, + struct ice_np_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "next proto key builder:\n"); + dev_info(dev, "\topc = %d\n", kb->opc); + dev_info(dev, "\tstart_or_reg0 = %d\n", kb->start_reg0); + dev_info(dev, "\tlen_or_reg1 = %d\n", kb->len_reg1); +} + +static void ice_imem_pg_kb_dump(struct ice_hw *hw, + struct ice_pg_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "parse graph key builder:\n"); + dev_info(dev, "\tflag0_ena = %d\n", kb->flag0_ena); + dev_info(dev, "\tflag1_ena = %d\n", kb->flag1_ena); + dev_info(dev, "\tflag2_ena = %d\n", kb->flag2_ena); + dev_info(dev, "\tflag3_ena = %d\n", kb->flag3_ena); + dev_info(dev, "\tflag0_idx = %d\n", kb->flag0_idx); + dev_info(dev, "\tflag1_idx = %d\n", kb->flag1_idx); + dev_info(dev, "\tflag2_idx = %d\n", kb->flag2_idx); + dev_info(dev, "\tflag3_idx = %d\n", kb->flag3_idx); + dev_info(dev, "\talu_reg_idx = %d\n", kb->alu_reg_idx); +} + +static void ice_imem_alu_dump(struct ice_hw *hw, + struct ice_alu *alu, int index) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "alu%d:\n", index); + dev_info(dev, "\topc = %d\n", alu->opc); + dev_info(dev, "\tsrc_start = %d\n", alu->src_start); + dev_info(dev, "\tsrc_len = %d\n", alu->src_len); + dev_info(dev, "\tshift_xlate_sel = %d\n", alu->shift_xlate_sel); + dev_info(dev, "\tshift_xlate_key = %d\n", alu->shift_xlate_key); + dev_info(dev, "\tsrc_reg_id = %d\n", alu->src_reg_id); + dev_info(dev, "\tdst_reg_id = %d\n", alu->dst_reg_id); + dev_info(dev, "\tinc0 = %d\n", alu->inc0); + dev_info(dev, "\tinc1 = %d\n", alu->inc1); + dev_info(dev, "\tproto_offset_opc = %d\n", alu->proto_offset_opc); + dev_info(dev, "\tproto_offset = %d\n", alu->proto_offset); + dev_info(dev, "\tbranch_addr = %d\n", alu->branch_addr); + dev_info(dev, "\timm = %d\n", alu->imm); + dev_info(dev, "\tdst_start = %d\n", alu->dst_start); + dev_info(dev, "\tdst_len = %d\n", alu->dst_len); + dev_info(dev, "\tflags_extr_imm = %d\n", alu->flags_extr_imm); + dev_info(dev, "\tflags_start_imm= %d\n", alu->flags_start_imm); +} + +/** + * ice_imem_dump - dump an imem item info + * @hw: pointer to the hardware structure + * @item: imem item to dump + */ +static void ice_imem_dump(struct ice_hw *hw, struct ice_imem_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "index = %d\n", item->idx); + ice_imem_bst_bm_dump(hw, &item->b_m); + ice_imem_bst_kb_dump(hw, &item->b_kb); + dev_info(dev, "pg priority = %d\n", item->pg_prio); + ice_imem_np_kb_dump(hw, &item->np_kb); + ice_imem_pg_kb_dump(hw, &item->pg_kb); + ice_imem_alu_dump(hw, &item->alu0, 0); + ice_imem_alu_dump(hw, &item->alu1, 1); + ice_imem_alu_dump(hw, &item->alu2, 2); +} + #define ICE_IM_BM_ALU0 BIT(0) #define ICE_IM_BM_ALU1 BIT(1) #define ICE_IM_BM_ALU2 BIT(2) @@ -328,6 +422,9 @@ static void ice_imem_parse_item(struct ice_hw *hw, u16 idx, void *item, ice_imem_alu_init(&ii->alu2, &buf[ICE_IMEM_ALU2_IDD], ICE_IMEM_ALU2_OFF); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_imem_dump(hw, ii); } /** @@ -345,6 +442,50 @@ static struct ice_imem_item *ice_imem_table_get(struct ice_hw *hw) } /*** ICE_SID_RXPARSER_METADATA_INIT section ***/ +/** + * ice_metainit_dump - dump an metainit item info + * @hw: pointer to the hardware structure + * @item: metainit item to dump + */ +static void ice_metainit_dump(struct ice_hw *hw, struct ice_metainit_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "index = %d\n", item->idx); + + dev_info(dev, "tsr = %d\n", item->tsr); + dev_info(dev, "ho = %d\n", item->ho); + dev_info(dev, "pc = %d\n", item->pc); + dev_info(dev, "pg_rn = %d\n", item->pg_rn); + dev_info(dev, "cd = %d\n", item->cd); + + dev_info(dev, "gpr_a_ctrl = %d\n", item->gpr_a_ctrl); + dev_info(dev, "gpr_a_data_mdid = %d\n", item->gpr_a_data_mdid); + dev_info(dev, "gpr_a_data_start = %d\n", item->gpr_a_data_start); + dev_info(dev, "gpr_a_data_len = %d\n", item->gpr_a_data_len); + dev_info(dev, "gpr_a_id = %d\n", item->gpr_a_id); + + dev_info(dev, "gpr_b_ctrl = %d\n", item->gpr_b_ctrl); + dev_info(dev, "gpr_b_data_mdid = %d\n", item->gpr_b_data_mdid); + dev_info(dev, "gpr_b_data_start = %d\n", item->gpr_b_data_start); + dev_info(dev, "gpr_b_data_len = %d\n", item->gpr_b_data_len); + dev_info(dev, "gpr_b_id = %d\n", item->gpr_b_id); + + dev_info(dev, "gpr_c_ctrl = %d\n", item->gpr_c_ctrl); + dev_info(dev, "gpr_c_data_mdid = %d\n", item->gpr_c_data_mdid); + dev_info(dev, "gpr_c_data_start = %d\n", item->gpr_c_data_start); + dev_info(dev, "gpr_c_data_len = %d\n", item->gpr_c_data_len); + dev_info(dev, "gpr_c_id = %d\n", item->gpr_c_id); + + dev_info(dev, "gpr_d_ctrl = %d\n", item->gpr_d_ctrl); + dev_info(dev, "gpr_d_data_mdid = %d\n", item->gpr_d_data_mdid); + dev_info(dev, "gpr_d_data_start = %d\n", item->gpr_d_data_start); + dev_info(dev, "gpr_d_data_len = %d\n", item->gpr_d_data_len); + dev_info(dev, "gpr_d_id = %d\n", item->gpr_d_id); + + dev_info(dev, "flags = 0x%llx\n", (unsigned long long)(item->flags)); +} + #define ICE_MI_TSR GENMASK_ULL(7, 0) #define ICE_MI_HO GENMASK_ULL(16, 8) #define ICE_MI_PC GENMASK_ULL(24, 17) @@ -437,6 +578,9 @@ static void ice_metainit_parse_item(struct ice_hw *hw, u16 idx, void *item, d64 = *((u64 *)&buf[ICE_MI_FLAG_IDD]) >> ICE_MI_FLAG_OFF; mi->flags = FIELD_GET(ICE_MI_FLAG, d64); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_metainit_dump(hw, mi); } /** @@ -456,6 +600,80 @@ static struct ice_metainit_item *ice_metainit_table_get(struct ice_hw *hw) /*** ICE_SID_RXPARSER_CAM, ICE_SID_RXPARSER_PG_SPILL, * ICE_SID_RXPARSER_NOMATCH_CAM and ICE_SID_RXPARSER_NOMATCH_CAM * sections ***/ +static void ice_pg_cam_key_dump(struct ice_hw *hw, struct ice_pg_cam_key *key) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "key:\n"); + dev_info(dev, "\tvalid = %d\n", key->valid); + dev_info(dev, "\tnode_id = %d\n", key->node_id); + dev_info(dev, "\tflag0 = %d\n", key->flag0); + dev_info(dev, "\tflag1 = %d\n", key->flag1); + dev_info(dev, "\tflag2 = %d\n", key->flag2); + dev_info(dev, "\tflag3 = %d\n", key->flag3); + dev_info(dev, "\tboost_idx = %d\n", key->boost_idx); + dev_info(dev, "\talu_reg = 0x%04x\n", key->alu_reg); + dev_info(dev, "\tnext_proto = 0x%08x\n", key->next_proto); +} + +static void ice_pg_nm_cam_key_dump(struct ice_hw *hw, + struct ice_pg_nm_cam_key *key) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "key:\n"); + dev_info(dev, "\tvalid = %d\n", key->valid); + dev_info(dev, "\tnode_id = %d\n", key->node_id); + dev_info(dev, "\tflag0 = %d\n", key->flag0); + dev_info(dev, "\tflag1 = %d\n", key->flag1); + dev_info(dev, "\tflag2 = %d\n", key->flag2); + dev_info(dev, "\tflag3 = %d\n", key->flag3); + dev_info(dev, "\tboost_idx = %d\n", key->boost_idx); + dev_info(dev, "\talu_reg = 0x%04x\n", key->alu_reg); +} + +static void ice_pg_cam_action_dump(struct ice_hw *hw, + struct ice_pg_cam_action *action) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "action:\n"); + dev_info(dev, "\tnext_node = %d\n", action->next_node); + dev_info(dev, "\tnext_pc = %d\n", action->next_pc); + dev_info(dev, "\tis_pg = %d\n", action->is_pg); + dev_info(dev, "\tproto_id = %d\n", action->proto_id); + dev_info(dev, "\tis_mg = %d\n", action->is_mg); + dev_info(dev, "\tmarker_id = %d\n", action->marker_id); + dev_info(dev, "\tis_last_round = %d\n", action->is_last_round); + dev_info(dev, "\tho_polarity = %d\n", action->ho_polarity); + dev_info(dev, "\tho_inc = %d\n", action->ho_inc); +} + +/** + * ice_pg_cam_dump - dump an parse graph cam info + * @hw: pointer to the hardware structure + * @item: parse graph cam to dump + */ +static void ice_pg_cam_dump(struct ice_hw *hw, struct ice_pg_cam_item *item) +{ + dev_info(ice_hw_to_dev(hw), "index = %d\n", item->idx); + ice_pg_cam_key_dump(hw, &item->key); + ice_pg_cam_action_dump(hw, &item->action); +} + +/** + * ice_pg_nm_cam_dump - dump an parse graph no match cam info + * @hw: pointer to the hardware structure + * @item: parse graph no match cam to dump + */ +static void ice_pg_nm_cam_dump(struct ice_hw *hw, + struct ice_pg_nm_cam_item *item) +{ + dev_info(ice_hw_to_dev(hw), "index = %d\n", item->idx); + ice_pg_nm_cam_key_dump(hw, &item->key); + ice_pg_cam_action_dump(hw, &item->action); +} + #define ICE_PGCA_NN GENMASK_ULL(10, 0) #define ICE_PGCA_NPC GENMASK_ULL(18, 11) #define ICE_PGCA_IPG BIT_ULL(19) @@ -584,6 +802,9 @@ static void ice_pg_cam_parse_item(struct ice_hw *hw, u16 idx, void *item, d64 = *((u64 *)&buf[ICE_PG_CAM_ACT_IDD]) >> ICE_PG_CAM_ACT_OFF; ice_pg_cam_action_init(&ci->action, d64); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_pg_cam_dump(hw, ci); } #define ICE_PG_SP_CAM_KEY_S 56 @@ -610,6 +831,9 @@ static void ice_pg_sp_cam_parse_item(struct ice_hw *hw, u16 idx, void *item, ice_pg_cam_action_init(&ci->action, d64); ice_pg_cam_key_init(&ci->key, &buf[ICE_PG_SP_CAM_KEY_IDD]); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_pg_cam_dump(hw, ci); } #define ICE_PG_NM_CAM_ACT_S 41 @@ -638,6 +862,9 @@ static void ice_pg_nm_cam_parse_item(struct ice_hw *hw, u16 idx, void *item, d64 = *((u64 *)&buf[ICE_PG_NM_CAM_ACT_IDD]) >> ICE_PG_NM_CAM_ACT_OFF; ice_pg_cam_action_init(&ci->action, d64); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_pg_nm_cam_dump(hw, ci); } #define ICE_PG_NM_SP_CAM_ACT_S 56 @@ -669,6 +896,9 @@ static void ice_pg_nm_sp_cam_parse_item(struct ice_hw *hw, u16 idx, d64 = *((u64 *)&buf[ICE_PG_NM_SP_CAM_ACT_IDD]) >> ICE_PG_NM_SP_CAM_ACT_OFF; ice_pg_nm_cam_key_init(&ci->key, d64); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_pg_nm_cam_dump(hw, ci); } /** @@ -728,6 +958,99 @@ static struct ice_pg_nm_cam_item *ice_pg_nm_sp_cam_table_get(struct ice_hw *hw) } /*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/ +static void ice_bst_np_kb_dump(struct ice_hw *hw, struct ice_np_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "next proto key builder:\n"); + dev_info(dev, "\topc = %d\n", kb->opc); + dev_info(dev, "\tstart_reg0 = %d\n", kb->start_reg0); + dev_info(dev, "\tlen_reg1 = %d\n", kb->len_reg1); +} + +static void ice_bst_pg_kb_dump(struct ice_hw *hw, struct ice_pg_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "parse graph key builder:\n"); + dev_info(dev, "\tflag0_ena = %d\n", kb->flag0_ena); + dev_info(dev, "\tflag1_ena = %d\n", kb->flag1_ena); + dev_info(dev, "\tflag2_ena = %d\n", kb->flag2_ena); + dev_info(dev, "\tflag3_ena = %d\n", kb->flag3_ena); + dev_info(dev, "\tflag0_idx = %d\n", kb->flag0_idx); + dev_info(dev, "\tflag1_idx = %d\n", kb->flag1_idx); + dev_info(dev, "\tflag2_idx = %d\n", kb->flag2_idx); + dev_info(dev, "\tflag3_idx = %d\n", kb->flag3_idx); + dev_info(dev, "\talu_reg_idx = %d\n", kb->alu_reg_idx); +} + +static void ice_bst_alu_dump(struct ice_hw *hw, struct ice_alu *alu, int idx) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "alu%d:\n", idx); + dev_info(dev, "\topc = %d\n", alu->opc); + dev_info(dev, "\tsrc_start = %d\n", alu->src_start); + dev_info(dev, "\tsrc_len = %d\n", alu->src_len); + dev_info(dev, "\tshift_xlate_sel = %d\n", alu->shift_xlate_sel); + dev_info(dev, "\tshift_xlate_key = %d\n", alu->shift_xlate_key); + dev_info(dev, "\tsrc_reg_id = %d\n", alu->src_reg_id); + dev_info(dev, "\tdst_reg_id = %d\n", alu->dst_reg_id); + dev_info(dev, "\tinc0 = %d\n", alu->inc0); + dev_info(dev, "\tinc1 = %d\n", alu->inc1); + dev_info(dev, "\tproto_offset_opc = %d\n", alu->proto_offset_opc); + dev_info(dev, "\tproto_offset = %d\n", alu->proto_offset); + dev_info(dev, "\tbranch_addr = %d\n", alu->branch_addr); + dev_info(dev, "\timm = %d\n", alu->imm); + dev_info(dev, "\tdst_start = %d\n", alu->dst_start); + dev_info(dev, "\tdst_len = %d\n", alu->dst_len); + dev_info(dev, "\tflags_extr_imm = %d\n", alu->flags_extr_imm); + dev_info(dev, "\tflags_start_imm= %d\n", alu->flags_start_imm); +} + +/** + * ice_bst_tcam_dump - dump a boost tcam info + * @hw: pointer to the hardware structure + * @item: boost tcam to dump + */ +static void ice_bst_tcam_dump(struct ice_hw *hw, struct ice_bst_tcam_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "addr = %d\n", item->addr); + + dev_info(dev, "key : "); + for (i = 0; i < ICE_BST_TCAM_KEY_SIZE; i++) + dev_info(dev, "%02x ", item->key[i]); + + dev_info(dev, "\n"); + + dev_info(dev, "key_inv: "); + for (i = 0; i < ICE_BST_TCAM_KEY_SIZE; i++) + dev_info(dev, "%02x ", item->key_inv[i]); + + dev_info(dev, "\n"); + + dev_info(dev, "hit_idx_grp = %d\n", item->hit_idx_grp); + dev_info(dev, "pg_prio = %d\n", item->pg_prio); + + ice_bst_np_kb_dump(hw, &item->np_kb); + ice_bst_pg_kb_dump(hw, &item->pg_kb); + + ice_bst_alu_dump(hw, &item->alu0, ICE_ALU0_IDX); + ice_bst_alu_dump(hw, &item->alu1, ICE_ALU1_IDX); + ice_bst_alu_dump(hw, &item->alu2, ICE_ALU2_IDX); +} + +static void ice_lbl_dump(struct ice_hw *hw, struct ice_lbl_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "index = %u\n", item->idx); + dev_info(dev, "label = %s\n", item->label); +} + #define ICE_BST_ALU_OPC GENMASK_ULL(5, 0) #define ICE_BST_ALU_SS GENMASK_ULL(13, 6) #define ICE_BST_ALU_SL GENMASK_ULL(18, 14) @@ -894,6 +1217,9 @@ static void ice_bst_parse_item(struct ice_hw *hw, u16 idx, void *item, ice_bst_alu_init(&ti->alu0, &buf[ICE_BT_ALU0_IDD], ICE_BT_ALU0_OFF); ice_bst_alu_init(&ti->alu1, &buf[ICE_BT_ALU1_IDD], ICE_BT_ALU1_OFF); ice_bst_alu_init(&ti->alu2, &buf[ICE_BT_ALU2_IDD], ICE_BT_ALU2_OFF); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_bst_tcam_dump(hw, ti); } /** @@ -914,6 +1240,9 @@ static void ice_parse_lbl_item(struct ice_hw *hw, u16 idx, void *item, void *data, int size) { memcpy(item, data, size); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_lbl_dump(hw, (struct ice_lbl_item *)item); } /** @@ -931,10 +1260,41 @@ static struct ice_lbl_item *ice_bst_lbl_table_get(struct ice_hw *hw) } /*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/ +/** + * ice_ptype_mk_tcam_dump - dump an ptype marker tcam info + * @hw: pointer to the hardware structure + * @item: ptype marker tcam to dump + */ +static void ice_ptype_mk_tcam_dump(struct ice_hw *hw, + struct ice_ptype_mk_tcam_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "address = %d\n", item->address); + dev_info(dev, "ptype = %d\n", item->ptype); + + dev_info(dev, "key :"); + for (i = 0; i < ICE_PTYPE_MK_TCAM_KEY_SIZE; i++) + dev_info(dev, "%02x ", item->key[i]); + + dev_info(dev, "\n"); + + dev_info(dev, "key_inv:"); + for (i = 0; i < ICE_PTYPE_MK_TCAM_KEY_SIZE; i++) + dev_info(dev, "%02x ", item->key_inv[i]); + + dev_info(dev, "\n"); +} + static void ice_parse_ptype_mk_tcam_item(struct ice_hw *hw, u16 idx, void *item, void *data, int size) { memcpy(item, data, size); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_ptype_mk_tcam_dump(hw, + (struct ice_ptype_mk_tcam_item *)item); } /** @@ -953,6 +1313,25 @@ struct ice_ptype_mk_tcam_item *ice_ptype_mk_tcam_table_get(struct ice_hw *hw) } /*** ICE_SID_RXPARSER_MARKER_GRP section ***/ +/** + * ice_mk_grp_dump - dump an marker group item info + * @hw: pointer to the hardware structure + * @item: marker group item to dump + */ +static void ice_mk_grp_dump(struct ice_hw *hw, struct ice_mk_grp_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "index = %d\n", item->idx); + + dev_info(dev, "markers: "); + for (i = 0; i < ICE_MK_COUNT_PER_GRP; i++) + dev_info(dev, "%d ", item->markers[i]); + + dev_info(dev, "\n"); +} + static void ice_mk_grp_parse_item(struct ice_hw *hw, u16 idx, void *item, void *data, int __maybe_unused size) { @@ -964,6 +1343,9 @@ static void ice_mk_grp_parse_item(struct ice_hw *hw, u16 idx, void *item, for (i = 0; i < ICE_MK_COUNT_PER_GRP; i++) grp->markers[i] = buf[i]; + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_mk_grp_dump(hw, grp); } /** @@ -981,6 +1363,33 @@ static struct ice_mk_grp_item *ice_mk_grp_table_get(struct ice_hw *hw) } /*** ICE_SID_RXPARSER_PROTO_GRP section ***/ +static void ice_proto_off_dump(struct ice_hw *hw, + struct ice_proto_off *po, int idx) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "proto %d\n", idx); + dev_info(dev, "\tpolarity = %d\n", po->polarity); + dev_info(dev, "\tproto_id = %d\n", po->proto_id); + dev_info(dev, "\toffset = %d\n", po->offset); +} + +/** + * ice_proto_grp_dump - dump a proto group item info + * @hw: pointer to the hardware structure + * @item: proto group item to dump + */ +static void ice_proto_grp_dump(struct ice_hw *hw, + struct ice_proto_grp_item *item) +{ + int i; + + dev_info(ice_hw_to_dev(hw), "index = %d\n", item->idx); + + for (i = 0; i < ICE_PROTO_COUNT_PER_GRP; i++) + ice_proto_off_dump(hw, &item->po[i], i); +} + #define ICE_PO_POL BIT(0) #define ICE_PO_PID GENMASK(8, 1) #define ICE_PO_OFF GENMASK(21, 12) @@ -1022,6 +1431,9 @@ static void ice_proto_grp_parse_item(struct ice_hw *hw, u16 idx, void *item, d32 = *((u32 *)&buf[idd]) >> off; ice_proto_off_parse(&grp->po[i], d32); } + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_proto_grp_dump(hw, grp); } /** @@ -1039,6 +1451,20 @@ static struct ice_proto_grp_item *ice_proto_grp_table_get(struct ice_hw *hw) } /*** ICE_SID_RXPARSER_FLAG_REDIR section ***/ +/** + * ice_flg_rd_dump - dump a flag redirect item info + * @hw: pointer to the hardware structure + * @item: flag redirect item to dump + */ +static void ice_flg_rd_dump(struct ice_hw *hw, struct ice_flg_rd_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "index = %d\n", item->idx); + dev_info(dev, "expose = %d\n", item->expose); + dev_info(dev, "intr_flg_id = %d\n", item->intr_flg_id); +} + #define ICE_FRT_EXPO BIT(0) #define ICE_FRT_IFID GENMASK(6, 1) @@ -1059,6 +1485,9 @@ static void ice_flg_rd_parse_item(struct ice_hw *hw, u16 idx, void *item, rdi->idx = idx; rdi->expose = FIELD_GET(ICE_FRT_EXPO, d8); rdi->intr_flg_id = FIELD_GET(ICE_FRT_IFID, d8); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_flg_rd_dump(hw, rdi); } /** @@ -1078,6 +1507,44 @@ static struct ice_flg_rd_item *ice_flg_rd_table_get(struct ice_hw *hw) /*** ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL, * ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS * sections ***/ +static void ice_xlt_kb_entry_dump(struct ice_hw *hw, + struct ice_xlt_kb_entry *entry, int idx) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "key builder entry %d\n", idx); + dev_info(dev, "\txlt1_ad_sel = %d\n", entry->xlt1_ad_sel); + dev_info(dev, "\txlt2_ad_sel = %d\n", entry->xlt2_ad_sel); + + for (i = 0; i < ICE_XLT_KB_FLAG0_14_CNT; i++) + dev_info(dev, "\tflg%d_sel = %d\n", i, entry->flg0_14_sel[i]); + + dev_info(dev, "\txlt1_md_sel = %d\n", entry->xlt1_md_sel); + dev_info(dev, "\txlt2_md_sel = %d\n", entry->xlt2_md_sel); +} + +/** + * ice_xlt_kb_dump - dump a xlt key build info + * @hw: pointer to the hardware structure + * @kb: key build to dump + */ +static void ice_xlt_kb_dump(struct ice_hw *hw, struct ice_xlt_kb *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "xlt1_pm = %d\n", kb->xlt1_pm); + dev_info(dev, "xlt2_pm = %d\n", kb->xlt2_pm); + dev_info(dev, "prof_id_pm = %d\n", kb->prof_id_pm); + dev_info(dev, "flag15 lo = 0x%08x\n", (u32)kb->flag15); + dev_info(dev, "flag15 hi = 0x%08x\n", + (u32)(kb->flag15 >> (sizeof(u32) * BITS_PER_BYTE))); + + for (i = 0; i < ICE_XLT_KB_TBL_CNT; i++) + ice_xlt_kb_entry_dump(hw, &kb->entries[i], i); +} + #define ICE_XLT_KB_X1AS_S 32 /* offset for the 1st 64-bits field */ #define ICE_XLT_KB_X1AS_IDD (ICE_XLT_KB_X1AS_S / BITS_PER_BYTE) #define ICE_XLT_KB_X1AS_OFF (ICE_XLT_KB_X1AS_S % BITS_PER_BYTE) @@ -1194,6 +1661,9 @@ static void ice_parse_kb_data(struct ice_hw *hw, struct ice_xlt_kb *kb, ice_kb_entry_init(&kb->entries[i], &buf[ICE_XLT_KB_TBL_OFF + i * ICE_XLT_KB_TBL_ENTRY_SIZE]); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_xlt_kb_dump(hw, kb); } static struct ice_xlt_kb *ice_xlt_kb_get(struct ice_hw *hw, u32 sect_type) From 4851f12c8d8a0dc89d1bf83ec9d7f34bd4f65572 Mon Sep 17 00:00:00 2001 From: Junfeng Guo Date: Thu, 25 Jul 2024 16:08:00 -0600 Subject: [PATCH 107/385] ice: add parser internal helper functions Add the following internal helper functions: - ice_bst_tcam_match(): to perform ternary match on boost TCAM. - ice_pg_cam_match(): to perform parse graph key match in cam table. - ice_pg_nm_cam_match(): to perform parse graph key no match in cam table. - ice_ptype_mk_tcam_match(): to perform ptype markers match in tcam table. - ice_flg_redirect(): to redirect parser flags to packet flags. - ice_xlt_kb_flag_get(): to aggregate 64 bit packet flag into 16 bit key builder flags. Reviewed-by: Simon Horman Reviewed-by: Aleksandr Loktionov Reviewed-by: Wojciech Drewek Reviewed-by: Marcin Szycik Signed-off-by: Qi Zhang Signed-off-by: Junfeng Guo Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_parser.c | 208 ++++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_parser.h | 51 +++-- 2 files changed, 244 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c index 23ba1a36742e6..f44310e941507 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.c +++ b/drivers/net/ethernet/intel/ice/ice_parser.c @@ -957,6 +957,109 @@ static struct ice_pg_nm_cam_item *ice_pg_nm_sp_cam_table_get(struct ice_hw *hw) ice_pg_nm_sp_cam_parse_item, false); } +static bool __ice_pg_cam_match(struct ice_pg_cam_item *item, + struct ice_pg_cam_key *key) +{ + return (item->key.valid && + !memcmp(&item->key.val, &key->val, sizeof(key->val))); +} + +static bool __ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *item, + struct ice_pg_cam_key *key) +{ + return (item->key.valid && + !memcmp(&item->key.val, &key->val, sizeof(item->key.val))); +} + +/** + * ice_pg_cam_match - search parse graph cam table by key + * @table: parse graph cam table to search + * @size: cam table size + * @key: search key + * + * Return: a pointer to the matching PG CAM item or NULL. + */ +struct ice_pg_cam_item *ice_pg_cam_match(struct ice_pg_cam_item *table, + int size, struct ice_pg_cam_key *key) +{ + int i; + + for (i = 0; i < size; i++) { + struct ice_pg_cam_item *item = &table[i]; + + if (__ice_pg_cam_match(item, key)) + return item; + } + + return NULL; +} + +/** + * ice_pg_nm_cam_match - search parse graph no match cam table by key + * @table: parse graph no match cam table to search + * @size: cam table size + * @key: search key + * + * Return: a pointer to the matching PG No Match CAM item or NULL. + */ +struct ice_pg_nm_cam_item * +ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size, + struct ice_pg_cam_key *key) +{ + int i; + + for (i = 0; i < size; i++) { + struct ice_pg_nm_cam_item *item = &table[i]; + + if (__ice_pg_nm_cam_match(item, key)) + return item; + } + + return NULL; +} + +/*** Ternary match ***/ +/* Perform a ternary match on a 1-byte pattern (@pat) given @key and @key_inv + * Rules (per bit): + * Key == 0 and Key_inv == 0 : Never match (Don't care) + * Key == 0 and Key_inv == 1 : Match on bit == 1 + * Key == 1 and Key_inv == 0 : Match on bit == 0 + * Key == 1 and Key_inv == 1 : Always match (Don't care) + * + * Return: true if all bits match, false otherwise. + */ +static bool ice_ternary_match_byte(u8 key, u8 key_inv, u8 pat) +{ + u8 bit_key, bit_key_inv, bit_pat; + int i; + + for (i = 0; i < BITS_PER_BYTE; i++) { + bit_key = key & BIT(i); + bit_key_inv = key_inv & BIT(i); + bit_pat = pat & BIT(i); + + if (bit_key != 0 && bit_key_inv != 0) + continue; + + if ((bit_key == 0 && bit_key_inv == 0) || bit_key == bit_pat) + return false; + } + + return true; +} + +static bool ice_ternary_match(const u8 *key, const u8 *key_inv, + const u8 *pat, int len) +{ + int i; + + for (i = 0; i < len; i++) + if (!ice_ternary_match_byte(key[i], key_inv[i], pat[i])) + return false; + + return true; +} + /*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/ static void ice_bst_np_kb_dump(struct ice_hw *hw, struct ice_np_keybuilder *kb) { @@ -1259,6 +1362,31 @@ static struct ice_lbl_item *ice_bst_lbl_table_get(struct ice_hw *hw) ice_parse_lbl_item, true); } +/** + * ice_bst_tcam_match - match a pattern on the boost tcam table + * @tcam_table: boost tcam table to search + * @pat: pattern to match + * + * Return: a pointer to the matching Boost TCAM item or NULL. + */ +struct ice_bst_tcam_item * +ice_bst_tcam_match(struct ice_bst_tcam_item *tcam_table, u8 *pat) +{ + int i; + + for (i = 0; i < ICE_BST_TCAM_TABLE_SIZE; i++) { + struct ice_bst_tcam_item *item = &tcam_table[i]; + + if (item->hit_idx_grp == 0) + continue; + if (ice_ternary_match(item->key, item->key_inv, pat, + ICE_BST_TCAM_KEY_SIZE)) + return item; + } + + return NULL; +} + /*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/ /** * ice_ptype_mk_tcam_dump - dump an ptype marker tcam info @@ -1312,6 +1440,30 @@ struct ice_ptype_mk_tcam_item *ice_ptype_mk_tcam_table_get(struct ice_hw *hw) ice_parse_ptype_mk_tcam_item, true); } +/** + * ice_ptype_mk_tcam_match - match a pattern on a ptype marker tcam table + * @table: ptype marker tcam table to search + * @pat: pattern to match + * @len: length of the pattern + * + * Return: a pointer to the matching Marker PType item or NULL. + */ +struct ice_ptype_mk_tcam_item * +ice_ptype_mk_tcam_match(struct ice_ptype_mk_tcam_item *table, + u8 *pat, int len) +{ + int i; + + for (i = 0; i < ICE_PTYPE_MK_TCAM_TABLE_SIZE; i++) { + struct ice_ptype_mk_tcam_item *item = &table[i]; + + if (ice_ternary_match(item->key, item->key_inv, pat, len)) + return item; + } + + return NULL; +} + /*** ICE_SID_RXPARSER_MARKER_GRP section ***/ /** * ice_mk_grp_dump - dump an marker group item info @@ -1504,6 +1656,31 @@ static struct ice_flg_rd_item *ice_flg_rd_table_get(struct ice_hw *hw) ice_flg_rd_parse_item, false); } +/** + * ice_flg_redirect - redirect a parser flag to packet flag + * @table: flag redirect table + * @psr_flg: parser flag to redirect + * + * Return: flag or 0 if @psr_flag = 0. + */ +u64 ice_flg_redirect(struct ice_flg_rd_item *table, u64 psr_flg) +{ + u64 flg = 0; + int i; + + for (i = 0; i < ICE_FLG_RDT_SIZE; i++) { + struct ice_flg_rd_item *item = &table[i]; + + if (!item->expose) + continue; + + if (psr_flg & BIT(item->intr_flg_id)) + flg |= BIT(i); + } + + return flg; +} + /*** ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL, * ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS * sections ***/ @@ -1737,6 +1914,37 @@ static struct ice_xlt_kb *ice_xlt_kb_get_rss(struct ice_hw *hw) return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_RSS); } +#define ICE_XLT_KB_MASK GENMASK_ULL(5, 0) + +/** + * ice_xlt_kb_flag_get - aggregate 64 bits packet flag into 16 bits xlt flag + * @kb: xlt key build + * @pkt_flag: 64 bits packet flag + * + * Return: XLT flag or 0 if @pkt_flag = 0. + */ +u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag) +{ + struct ice_xlt_kb_entry *entry = &kb->entries[0]; + u16 flag = 0; + int i; + + /* check flag 15 */ + if (kb->flag15 & pkt_flag) + flag = BIT(ICE_XLT_KB_FLAG0_14_CNT); + + /* check flag 0 - 14 */ + for (i = 0; i < ICE_XLT_KB_FLAG0_14_CNT; i++) { + /* only check first entry */ + u16 idx = entry->flg0_14_sel[i] & ICE_XLT_KB_MASK; + + if (pkt_flag & BIT(idx)) + flag |= (u16)BIT(i); + } + + return flag; +} + /*** Parser API ***/ /** * ice_parser_create - create a parser instance diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h index 6e8054d596448..1d2453890d8ec 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.h +++ b/drivers/net/ethernet/intel/ice/ice_parser.h @@ -197,25 +197,29 @@ struct ice_metainit_item { struct ice_pg_cam_key { bool valid; - u16 node_id; /* Node ID of protocol in parse graph */ - bool flag0; - bool flag1; - bool flag2; - bool flag3; - u8 boost_idx; /* Boost TCAM match index */ - u16 alu_reg; - u32 next_proto; /* next Protocol value */ + struct_group_attr(val, __packed, + u16 node_id; /* Node ID of protocol in parse graph */ + bool flag0; + bool flag1; + bool flag2; + bool flag3; + u8 boost_idx; /* Boost TCAM match index */ + u16 alu_reg; + u32 next_proto; /* next Protocol value (must be last) */ + ); }; struct ice_pg_nm_cam_key { bool valid; - u16 node_id; - bool flag0; - bool flag1; - bool flag2; - bool flag3; - u8 boost_idx; - u16 alu_reg; + struct_group_attr(val, __packed, + u16 node_id; + bool flag0; + bool flag1; + bool flag2; + bool flag3; + u8 boost_idx; + u16 alu_reg; + ); }; struct ice_pg_cam_action { @@ -244,6 +248,12 @@ struct ice_pg_nm_cam_item { struct ice_pg_cam_action action; }; +struct ice_pg_cam_item *ice_pg_cam_match(struct ice_pg_cam_item *table, + int size, struct ice_pg_cam_key *key); +struct ice_pg_nm_cam_item * +ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size, + struct ice_pg_cam_key *key); + /*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/ #define ICE_BST_TCAM_TABLE_SIZE 256 #define ICE_BST_TCAM_KEY_SIZE 20 @@ -269,6 +279,9 @@ struct ice_lbl_item { char label[ICE_LBL_LEN]; }; +struct ice_bst_tcam_item * +ice_bst_tcam_match(struct ice_bst_tcam_item *tcam_table, u8 *pat); + /*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/ #define ICE_PTYPE_MK_TCAM_TABLE_SIZE 1024 #define ICE_PTYPE_MK_TCAM_KEY_SIZE 10 @@ -280,6 +293,9 @@ struct ice_ptype_mk_tcam_item { u8 key_inv[ICE_PTYPE_MK_TCAM_KEY_SIZE]; } __packed; +struct ice_ptype_mk_tcam_item * +ice_ptype_mk_tcam_match(struct ice_ptype_mk_tcam_item *table, + u8 *pat, int len); /*** ICE_SID_RXPARSER_MARKER_GRP section ***/ #define ICE_MK_GRP_TABLE_SIZE 128 #define ICE_MK_COUNT_PER_GRP 8 @@ -308,6 +324,7 @@ struct ice_proto_grp_item { /*** ICE_SID_RXPARSER_FLAG_REDIR section ***/ #define ICE_FLG_RD_TABLE_SIZE 64 +#define ICE_FLG_RDT_SIZE 64 /* Flags Redirection item */ struct ice_flg_rd_item { @@ -316,6 +333,8 @@ struct ice_flg_rd_item { u8 intr_flg_id; /* Internal Flag ID */ }; +u64 ice_flg_redirect(struct ice_flg_rd_item *table, u64 psr_flg); + /*** ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL, * ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS * sections ***/ @@ -341,6 +360,8 @@ struct ice_xlt_kb { struct ice_xlt_kb_entry entries[ICE_XLT_KB_TBL_CNT]; }; +u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag); + /*** Parser API ***/ struct ice_parser { struct ice_hw *hw; /* pointer to the hardware structure */ From 9a4c07aaa0f54dd2ddd9e772be9b9ece27b229f0 Mon Sep 17 00:00:00 2001 From: Junfeng Guo Date: Thu, 25 Jul 2024 16:08:01 -0600 Subject: [PATCH 108/385] ice: add parser execution main loop Implement the core work of the runtime parser via: - ice_parser_rt_execute() - ice_parser_rt_reset() - ice_parser_rt_pkt_buf_set() Reviewed-by: Marcin Szycik Signed-off-by: Qi Zhang Signed-off-by: Junfeng Guo Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Reviewed-by: Simon Horman Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/Makefile | 1 + drivers/net/ethernet/intel/ice/ice_parser.c | 41 + drivers/net/ethernet/intel/ice/ice_parser.h | 91 ++ .../net/ethernet/intel/ice/ice_parser_rt.c | 861 ++++++++++++++++++ 4 files changed, 994 insertions(+) create mode 100644 drivers/net/ethernet/intel/ice/ice_parser_rt.c diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 23fa3f7f36ef5..b4f6fa4ba13d4 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -29,6 +29,7 @@ ice-y := ice_main.o \ ice_flex_pipe.o \ ice_flow.o \ ice_parser.o \ + ice_parser_rt.o \ ice_idc.o \ devlink/devlink.o \ devlink/devlink_port.o \ diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c index f44310e941507..e40dc31a56016 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.c +++ b/drivers/net/ethernet/intel/ice/ice_parser.c @@ -1963,6 +1963,7 @@ struct ice_parser *ice_parser_create(struct ice_hw *hw) return ERR_PTR(-ENOMEM); p->hw = hw; + p->rt.psr = p; p->imem_table = ice_imem_table_get(hw); if (IS_ERR(p->imem_table)) { @@ -2091,3 +2092,43 @@ void ice_parser_destroy(struct ice_parser *psr) kfree(psr); } + +/** + * ice_parser_run - parse on a packet in binary and return the result + * @psr: pointer to a parser instance + * @pkt_buf: packet data + * @pkt_len: packet length + * @rslt: input/output parameter to save parser result. + * + * Return: 0 on success or errno. + */ +int ice_parser_run(struct ice_parser *psr, const u8 *pkt_buf, + int pkt_len, struct ice_parser_result *rslt) +{ + ice_parser_rt_reset(&psr->rt); + ice_parser_rt_pktbuf_set(&psr->rt, pkt_buf, pkt_len); + + return ice_parser_rt_execute(&psr->rt, rslt); +} + +/** + * ice_parser_result_dump - dump a parser result info + * @hw: pointer to the hardware structure + * @rslt: parser result info to dump + */ +void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "ptype = %d\n", rslt->ptype); + for (i = 0; i < rslt->po_num; i++) + dev_info(dev, "proto = %d, offset = %d\n", + rslt->po[i].proto_id, rslt->po[i].offset); + + dev_info(dev, "flags_psr = 0x%016llx\n", rslt->flags_psr); + dev_info(dev, "flags_pkt = 0x%016llx\n", rslt->flags_pkt); + dev_info(dev, "flags_sw = 0x%04x\n", rslt->flags_sw); + dev_info(dev, "flags_fd = 0x%04x\n", rslt->flags_fd); + dev_info(dev, "flags_rss = 0x%04x\n", rslt->flags_rss); +} diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h index 1d2453890d8ec..ef08ccbe48746 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.h +++ b/drivers/net/ethernet/intel/ice/ice_parser.h @@ -363,6 +363,92 @@ struct ice_xlt_kb { u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag); /*** Parser API ***/ +#define ICE_GPR_HV_IDX 64 +#define ICE_GPR_HV_SIZE 32 +#define ICE_GPR_ERR_IDX 84 +#define ICE_GPR_FLG_IDX 104 +#define ICE_GPR_FLG_SIZE 16 + +#define ICE_GPR_TSR_IDX 108 /* TSR: TCAM Search Register */ +#define ICE_GPR_NN_IDX 109 /* NN: Next Parsing Cycle Node ID */ +#define ICE_GPR_HO_IDX 110 /* HO: Next Parsing Cycle hdr Offset */ +#define ICE_GPR_NP_IDX 111 /* NP: Next Parsing Cycle */ + +#define ICE_PARSER_MAX_PKT_LEN 504 +#define ICE_PARSER_PKT_REV 32 +#define ICE_PARSER_GPR_NUM 128 +#define ICE_PARSER_FLG_NUM 64 +#define ICE_PARSER_ERR_NUM 16 +#define ICE_BST_KEY_SIZE 10 +#define ICE_MARKER_ID_SIZE 9 +#define ICE_MARKER_MAX_SIZE \ + (ICE_MARKER_ID_SIZE * BITS_PER_BYTE - 1) +#define ICE_MARKER_ID_NUM 8 +#define ICE_PO_PAIR_SIZE 256 + +struct ice_gpr_pu { + /* array of flags to indicate if GRP needs to be updated */ + bool gpr_val_upd[ICE_PARSER_GPR_NUM]; + u16 gpr_val[ICE_PARSER_GPR_NUM]; + u64 flg_msk; + u64 flg_val; + u16 err_msk; + u16 err_val; +}; + +enum ice_pg_prio { + ICE_PG_P0 = 0, + ICE_PG_P1 = 1, + ICE_PG_P2 = 2, + ICE_PG_P3 = 3, +}; + +struct ice_parser_rt { + struct ice_parser *psr; + u16 gpr[ICE_PARSER_GPR_NUM]; + u8 pkt_buf[ICE_PARSER_MAX_PKT_LEN + ICE_PARSER_PKT_REV]; + u16 pkt_len; + u16 po; + u8 bst_key[ICE_BST_KEY_SIZE]; + struct ice_pg_cam_key pg_key; + struct ice_alu *alu0; + struct ice_alu *alu1; + struct ice_alu *alu2; + struct ice_pg_cam_action *action; + u8 pg_prio; + struct ice_gpr_pu pu; + u8 markers[ICE_MARKER_ID_SIZE]; + bool protocols[ICE_PO_PAIR_SIZE]; + u16 offsets[ICE_PO_PAIR_SIZE]; +}; + +struct ice_parser_proto_off { + u8 proto_id; /* hardware protocol ID */ + u16 offset; /* offset from the start of the protocol header */ +}; + +#define ICE_PARSER_PROTO_OFF_PAIR_SIZE 16 +#define ICE_PARSER_FLAG_PSR_SIZE 8 + +struct ice_parser_result { + u16 ptype; /* 16 bits hardware PTYPE */ + /* array of protocol and header offset pairs */ + struct ice_parser_proto_off po[ICE_PARSER_PROTO_OFF_PAIR_SIZE]; + int po_num; /* # of protocol-offset pairs must <= 16 */ + u64 flags_psr; /* parser flags */ + u64 flags_pkt; /* packet flags */ + u16 flags_sw; /* key builder flags for SW */ + u16 flags_acl; /* key builder flags for ACL */ + u16 flags_fd; /* key builder flags for FD */ + u16 flags_rss; /* key builder flags for RSS */ +}; + +void ice_parser_rt_reset(struct ice_parser_rt *rt); +void ice_parser_rt_pktbuf_set(struct ice_parser_rt *rt, const u8 *pkt_buf, + int pkt_len); +int ice_parser_rt_execute(struct ice_parser_rt *rt, + struct ice_parser_result *rslt); + struct ice_parser { struct ice_hw *hw; /* pointer to the hardware structure */ @@ -385,8 +471,13 @@ struct ice_parser { struct ice_xlt_kb *xlt_kb_acl; struct ice_xlt_kb *xlt_kb_fd; struct ice_xlt_kb *xlt_kb_rss; + + struct ice_parser_rt rt; }; struct ice_parser *ice_parser_create(struct ice_hw *hw); void ice_parser_destroy(struct ice_parser *psr); +int ice_parser_run(struct ice_parser *psr, const u8 *pkt_buf, + int pkt_len, struct ice_parser_result *rslt); +void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt); #endif /* _ICE_PARSER_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_parser_rt.c b/drivers/net/ethernet/intel/ice/ice_parser_rt.c new file mode 100644 index 0000000000000..d5bcc266b01ec --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_parser_rt.c @@ -0,0 +1,861 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2024 Intel Corporation */ + +#include "ice_common.h" + +static void ice_rt_tsr_set(struct ice_parser_rt *rt, u16 tsr) +{ + rt->gpr[ICE_GPR_TSR_IDX] = tsr; +} + +static void ice_rt_ho_set(struct ice_parser_rt *rt, u16 ho) +{ + rt->gpr[ICE_GPR_HO_IDX] = ho; + memcpy(&rt->gpr[ICE_GPR_HV_IDX], &rt->pkt_buf[ho], ICE_GPR_HV_SIZE); +} + +static void ice_rt_np_set(struct ice_parser_rt *rt, u16 pc) +{ + rt->gpr[ICE_GPR_NP_IDX] = pc; +} + +static void ice_rt_nn_set(struct ice_parser_rt *rt, u16 node) +{ + rt->gpr[ICE_GPR_NN_IDX] = node; +} + +static void +ice_rt_flag_set(struct ice_parser_rt *rt, unsigned int idx, bool set) +{ + struct ice_hw *hw = rt->psr->hw; + unsigned int word, id; + + word = idx / ICE_GPR_FLG_SIZE; + id = idx % ICE_GPR_FLG_SIZE; + + if (set) { + rt->gpr[ICE_GPR_FLG_IDX + word] |= (u16)BIT(id); + ice_debug(hw, ICE_DBG_PARSER, "Set parser flag %u\n", idx); + } else { + rt->gpr[ICE_GPR_FLG_IDX + word] &= ~(u16)BIT(id); + ice_debug(hw, ICE_DBG_PARSER, "Clear parser flag %u\n", idx); + } +} + +static void ice_rt_gpr_set(struct ice_parser_rt *rt, int idx, u16 val) +{ + struct ice_hw *hw = rt->psr->hw; + + if (idx == ICE_GPR_HO_IDX) + ice_rt_ho_set(rt, val); + else + rt->gpr[idx] = val; + + ice_debug(hw, ICE_DBG_PARSER, "Set GPR %d value %d\n", idx, val); +} + +static void ice_rt_err_set(struct ice_parser_rt *rt, unsigned int idx, bool set) +{ + struct ice_hw *hw = rt->psr->hw; + + if (set) { + rt->gpr[ICE_GPR_ERR_IDX] |= (u16)BIT(idx); + ice_debug(hw, ICE_DBG_PARSER, "Set parser error %u\n", idx); + } else { + rt->gpr[ICE_GPR_ERR_IDX] &= ~(u16)BIT(idx); + ice_debug(hw, ICE_DBG_PARSER, "Reset parser error %u\n", idx); + } +} + +/** + * ice_parser_rt_reset - reset the parser runtime + * @rt: pointer to the parser runtime + */ +void ice_parser_rt_reset(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + struct ice_metainit_item *mi; + unsigned int i; + + mi = &psr->mi_table[0]; + + memset(rt, 0, sizeof(*rt)); + rt->psr = psr; + + ice_rt_tsr_set(rt, mi->tsr); + ice_rt_ho_set(rt, mi->ho); + ice_rt_np_set(rt, mi->pc); + ice_rt_nn_set(rt, mi->pg_rn); + + for (i = 0; i < ICE_PARSER_FLG_NUM; i++) { + if (mi->flags & BIT(i)) + ice_rt_flag_set(rt, i, true); + } +} + +/** + * ice_parser_rt_pktbuf_set - set a packet into parser runtime + * @rt: pointer to the parser runtime + * @pkt_buf: buffer with packet data + * @pkt_len: packet buffer length + */ +void ice_parser_rt_pktbuf_set(struct ice_parser_rt *rt, const u8 *pkt_buf, + int pkt_len) +{ + int len = min(ICE_PARSER_MAX_PKT_LEN, pkt_len); + u16 ho = rt->gpr[ICE_GPR_HO_IDX]; + + memcpy(rt->pkt_buf, pkt_buf, len); + rt->pkt_len = pkt_len; + + memcpy(&rt->gpr[ICE_GPR_HV_IDX], &rt->pkt_buf[ho], ICE_GPR_HV_SIZE); +} + +static void ice_bst_key_init(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + u8 tsr = (u8)rt->gpr[ICE_GPR_TSR_IDX]; + u16 ho = rt->gpr[ICE_GPR_HO_IDX]; + u8 *key = rt->bst_key; + int idd, i; + + idd = ICE_BST_TCAM_KEY_SIZE - 1; + if (imem->b_kb.tsr_ctrl) + key[idd] = tsr; + else + key[idd] = imem->b_kb.prio; + + idd = ICE_BST_KEY_TCAM_SIZE - 1; + for (i = idd; i >= 0; i--) { + int j; + + j = ho + idd - i; + if (j < ICE_PARSER_MAX_PKT_LEN) + key[i] = rt->pkt_buf[ho + idd - i]; + else + key[i] = 0; + } + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generated Boost TCAM Key:\n"); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "%02X %02X %02X %02X %02X %02X %02X %02X %02X %02X\n", + key[0], key[1], key[2], key[3], key[4], + key[5], key[6], key[7], key[8], key[9]); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "\n"); +} + +static u16 ice_bit_rev_u16(u16 v, int len) +{ + return bitrev16(v) >> (BITS_PER_TYPE(v) - len); +} + +static u32 ice_bit_rev_u32(u32 v, int len) +{ + return bitrev32(v) >> (BITS_PER_TYPE(v) - len); +} + +static u32 ice_hv_bit_sel(struct ice_parser_rt *rt, int start, int len) +{ + int offset; + u32 buf[2]; + u64 val; + + offset = ICE_GPR_HV_IDX + (start / BITS_PER_TYPE(u16)); + + memcpy(buf, &rt->gpr[offset], sizeof(buf)); + + buf[0] = bitrev8x4(buf[0]); + buf[1] = bitrev8x4(buf[1]); + + val = *(u64 *)buf; + val >>= start % BITS_PER_TYPE(u16); + + return ice_bit_rev_u32(val, len); +} + +static u32 ice_pk_build(struct ice_parser_rt *rt, + struct ice_np_keybuilder *kb) +{ + if (kb->opc == ICE_NPKB_OPC_EXTRACT) + return ice_hv_bit_sel(rt, kb->start_reg0, kb->len_reg1); + else if (kb->opc == ICE_NPKB_OPC_BUILD) + return rt->gpr[kb->start_reg0] | + ((u32)rt->gpr[kb->len_reg1] << BITS_PER_TYPE(u16)); + else if (kb->opc == ICE_NPKB_OPC_BYPASS) + return 0; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Unsupported OP Code %u\n", + kb->opc); + return U32_MAX; +} + +static bool ice_flag_get(struct ice_parser_rt *rt, unsigned int index) +{ + int word = index / ICE_GPR_FLG_SIZE; + int id = index % ICE_GPR_FLG_SIZE; + + return !!(rt->gpr[ICE_GPR_FLG_IDX + word] & (u16)BIT(id)); +} + +static int ice_imem_pgk_init(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + memset(&rt->pg_key, 0, sizeof(rt->pg_key)); + rt->pg_key.next_proto = ice_pk_build(rt, &imem->np_kb); + if (rt->pg_key.next_proto == U32_MAX) + return -EINVAL; + + if (imem->pg_kb.flag0_ena) + rt->pg_key.flag0 = ice_flag_get(rt, imem->pg_kb.flag0_idx); + if (imem->pg_kb.flag1_ena) + rt->pg_key.flag1 = ice_flag_get(rt, imem->pg_kb.flag1_idx); + if (imem->pg_kb.flag2_ena) + rt->pg_key.flag2 = ice_flag_get(rt, imem->pg_kb.flag2_idx); + if (imem->pg_kb.flag3_ena) + rt->pg_key.flag3 = ice_flag_get(rt, imem->pg_kb.flag3_idx); + + rt->pg_key.alu_reg = rt->gpr[imem->pg_kb.alu_reg_idx]; + rt->pg_key.node_id = rt->gpr[ICE_GPR_NN_IDX]; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generate Parse Graph Key: node_id(%d), flag0-3(%d,%d,%d,%d), boost_idx(%d), alu_reg(0x%04x), next_proto(0x%08x)\n", + rt->pg_key.node_id, + rt->pg_key.flag0, + rt->pg_key.flag1, + rt->pg_key.flag2, + rt->pg_key.flag3, + rt->pg_key.boost_idx, + rt->pg_key.alu_reg, + rt->pg_key.next_proto); + + return 0; +} + +static void ice_imem_alu0_set(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + rt->alu0 = &imem->alu0; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU0 from imem pc %d\n", + imem->idx); +} + +static void ice_imem_alu1_set(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + rt->alu1 = &imem->alu1; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU1 from imem pc %d\n", + imem->idx); +} + +static void ice_imem_alu2_set(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + rt->alu2 = &imem->alu2; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU2 from imem pc %d\n", + imem->idx); +} + +static void ice_imem_pgp_set(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + rt->pg_prio = imem->pg_prio; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load PG priority %d from imem pc %d\n", + rt->pg_prio, imem->idx); +} + +static int ice_bst_pgk_init(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + memset(&rt->pg_key, 0, sizeof(rt->pg_key)); + rt->pg_key.boost_idx = bst->hit_idx_grp; + rt->pg_key.next_proto = ice_pk_build(rt, &bst->np_kb); + if (rt->pg_key.next_proto == U32_MAX) + return -EINVAL; + + if (bst->pg_kb.flag0_ena) + rt->pg_key.flag0 = ice_flag_get(rt, bst->pg_kb.flag0_idx); + if (bst->pg_kb.flag1_ena) + rt->pg_key.flag1 = ice_flag_get(rt, bst->pg_kb.flag1_idx); + if (bst->pg_kb.flag2_ena) + rt->pg_key.flag2 = ice_flag_get(rt, bst->pg_kb.flag2_idx); + if (bst->pg_kb.flag3_ena) + rt->pg_key.flag3 = ice_flag_get(rt, bst->pg_kb.flag3_idx); + + rt->pg_key.alu_reg = rt->gpr[bst->pg_kb.alu_reg_idx]; + rt->pg_key.node_id = rt->gpr[ICE_GPR_NN_IDX]; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generate Parse Graph Key: node_id(%d), flag0-3(%d,%d,%d,%d), boost_idx(%d), alu_reg(0x%04x), next_proto(0x%08x)\n", + rt->pg_key.node_id, + rt->pg_key.flag0, + rt->pg_key.flag1, + rt->pg_key.flag2, + rt->pg_key.flag3, + rt->pg_key.boost_idx, + rt->pg_key.alu_reg, + rt->pg_key.next_proto); + + return 0; +} + +static void ice_bst_alu0_set(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + rt->alu0 = &bst->alu0; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU0 from boost address %d\n", + bst->addr); +} + +static void ice_bst_alu1_set(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + rt->alu1 = &bst->alu1; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU1 from boost address %d\n", + bst->addr); +} + +static void ice_bst_alu2_set(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + rt->alu2 = &bst->alu2; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU2 from boost address %d\n", + bst->addr); +} + +static void ice_bst_pgp_set(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + rt->pg_prio = bst->pg_prio; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load PG priority %d from boost address %d\n", + rt->pg_prio, bst->addr); +} + +static struct ice_pg_cam_item *ice_rt_pg_cam_match(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + struct ice_pg_cam_item *item; + + item = ice_pg_cam_match(psr->pg_cam_table, ICE_PG_CAM_TABLE_SIZE, + &rt->pg_key); + if (!item) + item = ice_pg_cam_match(psr->pg_sp_cam_table, + ICE_PG_SP_CAM_TABLE_SIZE, &rt->pg_key); + return item; +} + +static +struct ice_pg_nm_cam_item *ice_rt_pg_nm_cam_match(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + struct ice_pg_nm_cam_item *item; + + item = ice_pg_nm_cam_match(psr->pg_nm_cam_table, + ICE_PG_NM_CAM_TABLE_SIZE, &rt->pg_key); + + if (!item) + item = ice_pg_nm_cam_match(psr->pg_nm_sp_cam_table, + ICE_PG_NM_SP_CAM_TABLE_SIZE, + &rt->pg_key); + return item; +} + +static void ice_gpr_add(struct ice_parser_rt *rt, int idx, u16 val) +{ + rt->pu.gpr_val_upd[idx] = true; + rt->pu.gpr_val[idx] = val; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Pending update for register %d value %d\n", + idx, val); +} + +static void ice_pg_exe(struct ice_parser_rt *rt) +{ + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ParseGraph action ...\n"); + + ice_gpr_add(rt, ICE_GPR_NP_IDX, rt->action->next_pc); + ice_gpr_add(rt, ICE_GPR_NN_IDX, rt->action->next_node); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ParseGraph action done.\n"); +} + +static void ice_flg_add(struct ice_parser_rt *rt, int idx, bool val) +{ + rt->pu.flg_msk |= BIT(idx); + if (val) + rt->pu.flg_val |= BIT(idx); + else + rt->pu.flg_val &= ~BIT(idx); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Pending update for flag %d value %d\n", + idx, val); +} + +static void ice_flg_update(struct ice_parser_rt *rt, struct ice_alu *alu) +{ + u32 hv_bit_sel; + int i; + + if (!alu->dedicate_flags_ena) + return; + + if (alu->flags_extr_imm) { + for (i = 0; i < alu->dst_len; i++) + ice_flg_add(rt, alu->dst_start + i, + !!(alu->flags_start_imm & BIT(i))); + } else { + for (i = 0; i < alu->dst_len; i++) { + hv_bit_sel = ice_hv_bit_sel(rt, + alu->flags_start_imm + i, + 1); + ice_flg_add(rt, alu->dst_start + i, !!hv_bit_sel); + } + } +} + +static void ice_po_update(struct ice_parser_rt *rt, struct ice_alu *alu) +{ + if (alu->proto_offset_opc == ICE_PO_OFF_HDR_ADD) + rt->po = (u16)(rt->gpr[ICE_GPR_HO_IDX] + alu->proto_offset); + else if (alu->proto_offset_opc == ICE_PO_OFF_HDR_SUB) + rt->po = (u16)(rt->gpr[ICE_GPR_HO_IDX] - alu->proto_offset); + else if (alu->proto_offset_opc == ICE_PO_OFF_REMAIN) + rt->po = rt->gpr[ICE_GPR_HO_IDX]; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Update Protocol Offset = %d\n", + rt->po); +} + +static u16 ice_reg_bit_sel(struct ice_parser_rt *rt, int reg_idx, + int start, int len) +{ + int offset; + u32 val; + + offset = ICE_GPR_HV_IDX + (start / BITS_PER_TYPE(u16)); + + memcpy(&val, &rt->gpr[offset], sizeof(val)); + + val = bitrev8x4(val); + val >>= start % BITS_PER_TYPE(u16); + + return ice_bit_rev_u16(val, len); +} + +static void ice_err_add(struct ice_parser_rt *rt, int idx, bool val) +{ + rt->pu.err_msk |= (u16)BIT(idx); + if (val) + rt->pu.flg_val |= (u64)BIT_ULL(idx); + else + rt->pu.flg_val &= ~(u64)BIT_ULL(idx); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Pending update for error %d value %d\n", + idx, val); +} + +static void ice_dst_reg_bit_set(struct ice_parser_rt *rt, struct ice_alu *alu, + bool val) +{ + u16 flg_idx; + + if (alu->dedicate_flags_ena) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "DedicatedFlagsEnable should not be enabled in opcode %d\n", + alu->opc); + return; + } + + if (alu->dst_reg_id == ICE_GPR_ERR_IDX) { + if (alu->dst_start >= ICE_PARSER_ERR_NUM) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Invalid error %d\n", + alu->dst_start); + return; + } + ice_err_add(rt, alu->dst_start, val); + } else if (alu->dst_reg_id >= ICE_GPR_FLG_IDX) { + flg_idx = (u16)(((alu->dst_reg_id - ICE_GPR_FLG_IDX) << 4) + + alu->dst_start); + + if (flg_idx >= ICE_PARSER_FLG_NUM) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Invalid flag %d\n", + flg_idx); + return; + } + ice_flg_add(rt, flg_idx, val); + } else { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Unexpected Dest Register Bit set, RegisterID %d Start %d\n", + alu->dst_reg_id, alu->dst_start); + } +} + +static void ice_alu_exe(struct ice_parser_rt *rt, struct ice_alu *alu) +{ + u16 dst, src, shift, imm; + + if (alu->shift_xlate_sel) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "shift_xlate_sel != 0 is not expected\n"); + return; + } + + ice_po_update(rt, alu); + ice_flg_update(rt, alu); + + dst = rt->gpr[alu->dst_reg_id]; + src = ice_reg_bit_sel(rt, alu->src_reg_id, + alu->src_start, alu->src_len); + shift = alu->shift_xlate_key; + imm = alu->imm; + + switch (alu->opc) { + case ICE_ALU_PARK: + break; + case ICE_ALU_MOV_ADD: + dst = (src << shift) + imm; + ice_gpr_add(rt, alu->dst_reg_id, dst); + break; + case ICE_ALU_ADD: + dst += (src << shift) + imm; + ice_gpr_add(rt, alu->dst_reg_id, dst); + break; + case ICE_ALU_ORLT: + if (src < imm) + ice_dst_reg_bit_set(rt, alu, true); + ice_gpr_add(rt, ICE_GPR_NP_IDX, alu->branch_addr); + break; + case ICE_ALU_OREQ: + if (src == imm) + ice_dst_reg_bit_set(rt, alu, true); + ice_gpr_add(rt, ICE_GPR_NP_IDX, alu->branch_addr); + break; + case ICE_ALU_SETEQ: + ice_dst_reg_bit_set(rt, alu, src == imm); + ice_gpr_add(rt, ICE_GPR_NP_IDX, alu->branch_addr); + break; + case ICE_ALU_MOV_XOR: + dst = (src << shift) ^ imm; + ice_gpr_add(rt, alu->dst_reg_id, dst); + break; + default: + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Unsupported ALU instruction %d\n", + alu->opc); + break; + } +} + +static void ice_alu0_exe(struct ice_parser_rt *rt) +{ + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU0 ...\n"); + ice_alu_exe(rt, rt->alu0); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU0 done.\n"); +} + +static void ice_alu1_exe(struct ice_parser_rt *rt) +{ + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU1 ...\n"); + ice_alu_exe(rt, rt->alu1); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU1 done.\n"); +} + +static void ice_alu2_exe(struct ice_parser_rt *rt) +{ + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU2 ...\n"); + ice_alu_exe(rt, rt->alu2); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU2 done.\n"); +} + +static void ice_pu_exe(struct ice_parser_rt *rt) +{ + struct ice_gpr_pu *pu = &rt->pu; + unsigned int i; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Updating Registers ...\n"); + + for (i = 0; i < ICE_PARSER_GPR_NUM; i++) { + if (pu->gpr_val_upd[i]) + ice_rt_gpr_set(rt, i, pu->gpr_val[i]); + } + + for (i = 0; i < ICE_PARSER_FLG_NUM; i++) { + if (pu->flg_msk & BIT(i)) + ice_rt_flag_set(rt, i, pu->flg_val & BIT(i)); + } + + for (i = 0; i < ICE_PARSER_ERR_NUM; i++) { + if (pu->err_msk & BIT(i)) + ice_rt_err_set(rt, i, pu->err_val & BIT(i)); + } + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Updating Registers done.\n"); +} + +static void ice_alu_pg_exe(struct ice_parser_rt *rt) +{ + memset(&rt->pu, 0, sizeof(rt->pu)); + + switch (rt->pg_prio) { + case (ICE_PG_P0): + ice_pg_exe(rt); + ice_alu0_exe(rt); + ice_alu1_exe(rt); + ice_alu2_exe(rt); + break; + case (ICE_PG_P1): + ice_alu0_exe(rt); + ice_pg_exe(rt); + ice_alu1_exe(rt); + ice_alu2_exe(rt); + break; + case (ICE_PG_P2): + ice_alu0_exe(rt); + ice_alu1_exe(rt); + ice_pg_exe(rt); + ice_alu2_exe(rt); + break; + case (ICE_PG_P3): + ice_alu0_exe(rt); + ice_alu1_exe(rt); + ice_alu2_exe(rt); + ice_pg_exe(rt); + break; + } + + ice_pu_exe(rt); + + if (rt->action->ho_inc == 0) + return; + + if (rt->action->ho_polarity) + ice_rt_ho_set(rt, rt->gpr[ICE_GPR_HO_IDX] + rt->action->ho_inc); + else + ice_rt_ho_set(rt, rt->gpr[ICE_GPR_HO_IDX] - rt->action->ho_inc); +} + +static void ice_proto_off_update(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + + if (rt->action->is_pg) { + struct ice_proto_grp_item *proto_grp = + &psr->proto_grp_table[rt->action->proto_id]; + u16 po; + int i; + + for (i = 0; i < ICE_PROTO_COUNT_PER_GRP; i++) { + struct ice_proto_off *entry = &proto_grp->po[i]; + + if (entry->proto_id == U8_MAX) + break; + + if (!entry->polarity) + po = rt->po + entry->offset; + else + po = rt->po - entry->offset; + + rt->protocols[entry->proto_id] = true; + rt->offsets[entry->proto_id] = po; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Protocol %d at offset %d\n", + entry->proto_id, po); + } + } else { + rt->protocols[rt->action->proto_id] = true; + rt->offsets[rt->action->proto_id] = rt->po; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Protocol %d at offset %d\n", + rt->action->proto_id, rt->po); + } +} + +static void ice_marker_set(struct ice_parser_rt *rt, int idx) +{ + unsigned int byte = idx / BITS_PER_BYTE; + unsigned int bit = idx % BITS_PER_BYTE; + + rt->markers[byte] |= (u8)BIT(bit); +} + +static void ice_marker_update(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + + if (rt->action->is_mg) { + struct ice_mk_grp_item *mk_grp = + &psr->mk_grp_table[rt->action->marker_id]; + int i; + + for (i = 0; i < ICE_MARKER_ID_NUM; i++) { + u8 marker = mk_grp->markers[i]; + + if (marker == ICE_MARKER_MAX_SIZE) + break; + + ice_marker_set(rt, marker); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Marker %d\n", + marker); + } + } else { + if (rt->action->marker_id != ICE_MARKER_MAX_SIZE) + ice_marker_set(rt, rt->action->marker_id); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Marker %d\n", + rt->action->marker_id); + } +} + +static u16 ice_ptype_resolve(struct ice_parser_rt *rt) +{ + struct ice_ptype_mk_tcam_item *item; + struct ice_parser *psr = rt->psr; + + item = ice_ptype_mk_tcam_match(psr->ptype_mk_tcam_table, + rt->markers, ICE_MARKER_ID_SIZE); + if (item) + return item->ptype; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Could not resolve PTYPE\n"); + return U16_MAX; +} + +static void ice_proto_off_resolve(struct ice_parser_rt *rt, + struct ice_parser_result *rslt) +{ + int i; + + for (i = 0; i < ICE_PO_PAIR_SIZE - 1; i++) { + if (rt->protocols[i]) { + rslt->po[rslt->po_num].proto_id = (u8)i; + rslt->po[rslt->po_num].offset = rt->offsets[i]; + rslt->po_num++; + } + } +} + +static void ice_result_resolve(struct ice_parser_rt *rt, + struct ice_parser_result *rslt) +{ + struct ice_parser *psr = rt->psr; + + memset(rslt, 0, sizeof(*rslt)); + + memcpy(&rslt->flags_psr, &rt->gpr[ICE_GPR_FLG_IDX], + ICE_PARSER_FLAG_PSR_SIZE); + rslt->flags_pkt = ice_flg_redirect(psr->flg_rd_table, rslt->flags_psr); + rslt->flags_sw = ice_xlt_kb_flag_get(psr->xlt_kb_sw, rslt->flags_pkt); + rslt->flags_fd = ice_xlt_kb_flag_get(psr->xlt_kb_fd, rslt->flags_pkt); + rslt->flags_rss = ice_xlt_kb_flag_get(psr->xlt_kb_rss, rslt->flags_pkt); + + ice_proto_off_resolve(rt, rslt); + rslt->ptype = ice_ptype_resolve(rt); +} + +/** + * ice_parser_rt_execute - parser execution routine + * @rt: pointer to the parser runtime + * @rslt: input/output parameter to save parser result + * + * Return: 0 on success or errno. + */ +int ice_parser_rt_execute(struct ice_parser_rt *rt, + struct ice_parser_result *rslt) +{ + struct ice_pg_nm_cam_item *pg_nm_cam; + struct ice_parser *psr = rt->psr; + struct ice_pg_cam_item *pg_cam; + int status = 0; + u16 node; + u16 pc; + + node = rt->gpr[ICE_GPR_NN_IDX]; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Start with Node: %u\n", node); + + while (true) { + struct ice_bst_tcam_item *bst; + struct ice_imem_item *imem; + + pc = rt->gpr[ICE_GPR_NP_IDX]; + imem = &psr->imem_table[pc]; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load imem at pc: %u\n", + pc); + + ice_bst_key_init(rt, imem); + bst = ice_bst_tcam_match(psr->bst_tcam_table, rt->bst_key); + if (!bst) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "No Boost TCAM Match\n"); + status = ice_imem_pgk_init(rt, imem); + if (status) + break; + ice_imem_alu0_set(rt, imem); + ice_imem_alu1_set(rt, imem); + ice_imem_alu2_set(rt, imem); + ice_imem_pgp_set(rt, imem); + } else { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Boost TCAM Match address: %u\n", + bst->addr); + if (imem->b_m.pg) { + status = ice_bst_pgk_init(rt, bst); + if (status) + break; + ice_bst_pgp_set(rt, bst); + } else { + status = ice_imem_pgk_init(rt, imem); + if (status) + break; + ice_imem_pgp_set(rt, imem); + } + + if (imem->b_m.alu0) + ice_bst_alu0_set(rt, bst); + else + ice_imem_alu0_set(rt, imem); + + if (imem->b_m.alu1) + ice_bst_alu1_set(rt, bst); + else + ice_imem_alu1_set(rt, imem); + + if (imem->b_m.alu2) + ice_bst_alu2_set(rt, bst); + else + ice_imem_alu2_set(rt, imem); + } + + rt->action = NULL; + pg_cam = ice_rt_pg_cam_match(rt); + if (!pg_cam) { + pg_nm_cam = ice_rt_pg_nm_cam_match(rt); + if (pg_nm_cam) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Match ParseGraph Nomatch CAM Address %u\n", + pg_nm_cam->idx); + rt->action = &pg_nm_cam->action; + } + } else { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Match ParseGraph CAM Address %u\n", + pg_cam->idx); + rt->action = &pg_cam->action; + } + + if (!rt->action) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Failed to match ParseGraph CAM, stop parsing.\n"); + status = -EINVAL; + break; + } + + ice_alu_pg_exe(rt); + ice_marker_update(rt); + ice_proto_off_update(rt); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Go to node %u\n", + rt->action->next_node); + + if (rt->action->is_last_round) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Last Round in ParseGraph Action, stop parsing.\n"); + break; + } + + if (rt->gpr[ICE_GPR_HO_IDX] >= rt->pkt_len) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Header Offset (%u) is larger than packet len (%u), stop parsing\n", + rt->gpr[ICE_GPR_HO_IDX], rt->pkt_len); + break; + } + } + + ice_result_resolve(rt, rslt); + + return status; +} From b2687653fe690569d48eb60343745fe436f7d532 Mon Sep 17 00:00:00 2001 From: Junfeng Guo Date: Thu, 25 Jul 2024 16:08:02 -0600 Subject: [PATCH 109/385] ice: support turning on/off the parser's double vlan mode Add API ice_parser_dvm_set() to support turning on/off the parser's double vlan mode. Reviewed-by: Marcin Szycik Signed-off-by: Qi Zhang Signed-off-by: Junfeng Guo Co-developed-by: Ahmed Zaki Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Reviewed-by: Simon Horman Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_parser.c | 78 ++++++++++++++++++++- drivers/net/ethernet/intel/ice/ice_parser.h | 18 +++++ 2 files changed, 93 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c index e40dc31a56016..f032b907ccd2c 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.c +++ b/drivers/net/ethernet/intel/ice/ice_parser.c @@ -597,6 +597,32 @@ static struct ice_metainit_item *ice_metainit_table_get(struct ice_hw *hw) ice_metainit_parse_item, false); } +/** + * ice_bst_tcam_search - find a TCAM item with specific type + * @tcam_table: the TCAM table + * @lbl_table: the lbl table to search + * @type: the type we need to match against + * @start: start searching from this index + * + * Return: a pointer to the matching BOOST TCAM item or NULL. + */ +struct ice_bst_tcam_item * +ice_bst_tcam_search(struct ice_bst_tcam_item *tcam_table, + struct ice_lbl_item *lbl_table, + enum ice_lbl_type type, u16 *start) +{ + u16 i = *start; + + for (; i < ICE_BST_TCAM_TABLE_SIZE; i++) { + if (lbl_table[i].type == type) { + *start = i; + return &tcam_table[lbl_table[i].idx]; + } + } + + return NULL; +} + /*** ICE_SID_RXPARSER_CAM, ICE_SID_RXPARSER_PG_SPILL, * ICE_SID_RXPARSER_NOMATCH_CAM and ICE_SID_RXPARSER_NOMATCH_CAM * sections ***/ @@ -1151,6 +1177,7 @@ static void ice_lbl_dump(struct ice_hw *hw, struct ice_lbl_item *item) struct device *dev = ice_hw_to_dev(hw); dev_info(dev, "index = %u\n", item->idx); + dev_info(dev, "type = %u\n", item->type); dev_info(dev, "label = %s\n", item->label); } @@ -1340,12 +1367,21 @@ static struct ice_bst_tcam_item *ice_bst_tcam_table_get(struct ice_hw *hw) } static void ice_parse_lbl_item(struct ice_hw *hw, u16 idx, void *item, - void *data, int size) + void *data, int __maybe_unused size) { - memcpy(item, data, size); + struct ice_lbl_item *lbl_item = item; + struct ice_lbl_item *lbl_data = data; + + lbl_item->idx = lbl_data->idx; + memcpy(lbl_item->label, lbl_data->label, sizeof(lbl_item->label)); + + if (strstarts(lbl_item->label, ICE_LBL_BST_DVM)) + lbl_item->type = ICE_LBL_BST_TYPE_DVM; + else if (strstarts(lbl_item->label, ICE_LBL_BST_SVM)) + lbl_item->type = ICE_LBL_BST_TYPE_SVM; if (hw->debug_mask & ICE_DBG_PARSER) - ice_lbl_dump(hw, (struct ice_lbl_item *)item); + ice_lbl_dump(hw, lbl_item); } /** @@ -2132,3 +2168,39 @@ void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt) dev_info(dev, "flags_fd = 0x%04x\n", rslt->flags_fd); dev_info(dev, "flags_rss = 0x%04x\n", rslt->flags_rss); } + +#define ICE_BT_VLD_KEY 0xFF +#define ICE_BT_INV_KEY 0xFE + +static void ice_bst_dvm_set(struct ice_parser *psr, enum ice_lbl_type type, + bool on) +{ + u16 i = 0; + + while (true) { + struct ice_bst_tcam_item *item; + u8 key; + + item = ice_bst_tcam_search(psr->bst_tcam_table, + psr->bst_lbl_table, + type, &i); + if (!item) + break; + + key = on ? ICE_BT_VLD_KEY : ICE_BT_INV_KEY; + item->key[ICE_BT_VM_OFF] = key; + item->key_inv[ICE_BT_VM_OFF] = key; + i++; + } +} + +/** + * ice_parser_dvm_set - configure double vlan mode for parser + * @psr: pointer to a parser instance + * @on: true to turn on; false to turn off + */ +void ice_parser_dvm_set(struct ice_parser *psr, bool on) +{ + ice_bst_dvm_set(psr, ICE_LBL_BST_TYPE_DVM, on); + ice_bst_dvm_set(psr, ICE_LBL_BST_TYPE_SVM, !on); +} diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h index ef08ccbe48746..92319c60b3881 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.h +++ b/drivers/net/ethernet/intel/ice/ice_parser.h @@ -274,13 +274,29 @@ struct ice_bst_tcam_item { }; #define ICE_LBL_LEN 64 +#define ICE_LBL_BST_DVM "BOOST_MAC_VLAN_DVM" +#define ICE_LBL_BST_SVM "BOOST_MAC_VLAN_SVM" + +enum ice_lbl_type { + ICE_LBL_BST_TYPE_UNKNOWN, + ICE_LBL_BST_TYPE_DVM, + ICE_LBL_BST_TYPE_SVM, +}; + struct ice_lbl_item { u16 idx; char label[ICE_LBL_LEN]; + + /* must be at the end, not part of the DDP section */ + enum ice_lbl_type type; }; struct ice_bst_tcam_item * ice_bst_tcam_match(struct ice_bst_tcam_item *tcam_table, u8 *pat); +struct ice_bst_tcam_item * +ice_bst_tcam_search(struct ice_bst_tcam_item *tcam_table, + struct ice_lbl_item *lbl_table, + enum ice_lbl_type type, u16 *start); /*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/ #define ICE_PTYPE_MK_TCAM_TABLE_SIZE 1024 @@ -429,6 +445,7 @@ struct ice_parser_proto_off { #define ICE_PARSER_PROTO_OFF_PAIR_SIZE 16 #define ICE_PARSER_FLAG_PSR_SIZE 8 +#define ICE_BT_VM_OFF 0 struct ice_parser_result { u16 ptype; /* 16 bits hardware PTYPE */ @@ -477,6 +494,7 @@ struct ice_parser { struct ice_parser *ice_parser_create(struct ice_hw *hw); void ice_parser_destroy(struct ice_parser *psr); +void ice_parser_dvm_set(struct ice_parser *psr, bool on); int ice_parser_run(struct ice_parser *psr, const u8 *pkt_buf, int pkt_len, struct ice_parser_result *rslt); void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt); From 80a480075911ec333a692e3108899a565b5f4bdc Mon Sep 17 00:00:00 2001 From: Junfeng Guo Date: Thu, 25 Jul 2024 16:08:03 -0600 Subject: [PATCH 110/385] ice: add UDP tunnels support to the parser Add support for the vxlan, geneve, ecpri UDP tunnels through the following APIs: - ice_parser_vxlan_tunnel_set() - ice_parser_geneve_tunnel_set() - ice_parser_ecpri_tunnel_set() Reviewed-by: Simon Horman Reviewed-by: Marcin Szycik Signed-off-by: Qi Zhang Signed-off-by: Junfeng Guo Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_parser.c | 98 +++++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_parser.h | 13 +++ 2 files changed, 111 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c index f032b907ccd2c..ee89208bf21d8 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.c +++ b/drivers/net/ethernet/intel/ice/ice_parser.c @@ -1379,6 +1379,12 @@ static void ice_parse_lbl_item(struct ice_hw *hw, u16 idx, void *item, lbl_item->type = ICE_LBL_BST_TYPE_DVM; else if (strstarts(lbl_item->label, ICE_LBL_BST_SVM)) lbl_item->type = ICE_LBL_BST_TYPE_SVM; + else if (strstarts(lbl_item->label, ICE_LBL_TNL_VXLAN)) + lbl_item->type = ICE_LBL_BST_TYPE_VXLAN; + else if (strstarts(lbl_item->label, ICE_LBL_TNL_GENEVE)) + lbl_item->type = ICE_LBL_BST_TYPE_GENEVE; + else if (strstarts(lbl_item->label, ICE_LBL_TNL_UDP_ECPRI)) + lbl_item->type = ICE_LBL_BST_TYPE_UDP_ECPRI; if (hw->debug_mask & ICE_DBG_PARSER) ice_lbl_dump(hw, lbl_item); @@ -2204,3 +2210,95 @@ void ice_parser_dvm_set(struct ice_parser *psr, bool on) ice_bst_dvm_set(psr, ICE_LBL_BST_TYPE_DVM, on); ice_bst_dvm_set(psr, ICE_LBL_BST_TYPE_SVM, !on); } + +static int ice_tunnel_port_set(struct ice_parser *psr, enum ice_lbl_type type, + u16 udp_port, bool on) +{ + u8 *buf = (u8 *)&udp_port; + u16 i = 0; + + while (true) { + struct ice_bst_tcam_item *item; + + item = ice_bst_tcam_search(psr->bst_tcam_table, + psr->bst_lbl_table, + type, &i); + if (!item) + break; + + /* found empty slot to add */ + if (on && item->key[ICE_BT_TUN_PORT_OFF_H] == ICE_BT_INV_KEY && + item->key_inv[ICE_BT_TUN_PORT_OFF_H] == ICE_BT_INV_KEY) { + item->key_inv[ICE_BT_TUN_PORT_OFF_L] = + buf[ICE_UDP_PORT_OFF_L]; + item->key_inv[ICE_BT_TUN_PORT_OFF_H] = + buf[ICE_UDP_PORT_OFF_H]; + + item->key[ICE_BT_TUN_PORT_OFF_L] = + ICE_BT_VLD_KEY - buf[ICE_UDP_PORT_OFF_L]; + item->key[ICE_BT_TUN_PORT_OFF_H] = + ICE_BT_VLD_KEY - buf[ICE_UDP_PORT_OFF_H]; + + return 0; + /* found a matched slot to delete */ + } else if (!on && + (item->key_inv[ICE_BT_TUN_PORT_OFF_L] == + buf[ICE_UDP_PORT_OFF_L] || + item->key_inv[ICE_BT_TUN_PORT_OFF_H] == + buf[ICE_UDP_PORT_OFF_H])) { + item->key_inv[ICE_BT_TUN_PORT_OFF_L] = ICE_BT_VLD_KEY; + item->key_inv[ICE_BT_TUN_PORT_OFF_H] = ICE_BT_INV_KEY; + + item->key[ICE_BT_TUN_PORT_OFF_L] = ICE_BT_VLD_KEY; + item->key[ICE_BT_TUN_PORT_OFF_H] = ICE_BT_INV_KEY; + + return 0; + } + i++; + } + + return -EINVAL; +} + +/** + * ice_parser_vxlan_tunnel_set - configure vxlan tunnel for parser + * @psr: pointer to a parser instance + * @udp_port: vxlan tunnel port in UDP header + * @on: true to turn on; false to turn off + * + * Return: 0 on success or errno on failure. + */ +int ice_parser_vxlan_tunnel_set(struct ice_parser *psr, + u16 udp_port, bool on) +{ + return ice_tunnel_port_set(psr, ICE_LBL_BST_TYPE_VXLAN, udp_port, on); +} + +/** + * ice_parser_geneve_tunnel_set - configure geneve tunnel for parser + * @psr: pointer to a parser instance + * @udp_port: geneve tunnel port in UDP header + * @on: true to turn on; false to turn off + * + * Return: 0 on success or errno on failure. + */ +int ice_parser_geneve_tunnel_set(struct ice_parser *psr, + u16 udp_port, bool on) +{ + return ice_tunnel_port_set(psr, ICE_LBL_BST_TYPE_GENEVE, udp_port, on); +} + +/** + * ice_parser_ecpri_tunnel_set - configure ecpri tunnel for parser + * @psr: pointer to a parser instance + * @udp_port: ecpri tunnel port in UDP header + * @on: true to turn on; false to turn off + * + * Return: 0 on success or errno on failure. + */ +int ice_parser_ecpri_tunnel_set(struct ice_parser *psr, + u16 udp_port, bool on) +{ + return ice_tunnel_port_set(psr, ICE_LBL_BST_TYPE_UDP_ECPRI, + udp_port, on); +} diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h index 92319c60b3881..f9500ddf15670 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.h +++ b/drivers/net/ethernet/intel/ice/ice_parser.h @@ -276,11 +276,17 @@ struct ice_bst_tcam_item { #define ICE_LBL_LEN 64 #define ICE_LBL_BST_DVM "BOOST_MAC_VLAN_DVM" #define ICE_LBL_BST_SVM "BOOST_MAC_VLAN_SVM" +#define ICE_LBL_TNL_VXLAN "TNL_VXLAN" +#define ICE_LBL_TNL_GENEVE "TNL_GENEVE" +#define ICE_LBL_TNL_UDP_ECPRI "TNL_UDP_ECPRI" enum ice_lbl_type { ICE_LBL_BST_TYPE_UNKNOWN, ICE_LBL_BST_TYPE_DVM, ICE_LBL_BST_TYPE_SVM, + ICE_LBL_BST_TYPE_VXLAN, + ICE_LBL_BST_TYPE_GENEVE, + ICE_LBL_BST_TYPE_UDP_ECPRI, }; struct ice_lbl_item { @@ -445,7 +451,11 @@ struct ice_parser_proto_off { #define ICE_PARSER_PROTO_OFF_PAIR_SIZE 16 #define ICE_PARSER_FLAG_PSR_SIZE 8 +#define ICE_BT_TUN_PORT_OFF_H 16 +#define ICE_BT_TUN_PORT_OFF_L 15 #define ICE_BT_VM_OFF 0 +#define ICE_UDP_PORT_OFF_H 1 +#define ICE_UDP_PORT_OFF_L 0 struct ice_parser_result { u16 ptype; /* 16 bits hardware PTYPE */ @@ -495,6 +505,9 @@ struct ice_parser { struct ice_parser *ice_parser_create(struct ice_hw *hw); void ice_parser_destroy(struct ice_parser *psr); void ice_parser_dvm_set(struct ice_parser *psr, bool on); +int ice_parser_vxlan_tunnel_set(struct ice_parser *psr, u16 udp_port, bool on); +int ice_parser_geneve_tunnel_set(struct ice_parser *psr, u16 udp_port, bool on); +int ice_parser_ecpri_tunnel_set(struct ice_parser *psr, u16 udp_port, bool on); int ice_parser_run(struct ice_parser *psr, const u8 *pkt_buf, int pkt_len, struct ice_parser_result *rslt); void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt); From e312b3a1e2092f612914dbc4fa5d96b4d8ff94ef Mon Sep 17 00:00:00 2001 From: Junfeng Guo Date: Thu, 25 Jul 2024 16:08:04 -0600 Subject: [PATCH 111/385] ice: add API for parser profile initialization Add API ice_parser_profile_init() to init a parser profile based on a parser result and a mask buffer. The ice_parser_profile struct is used by the low level FXP engine to create HW profile/field vectors. Reviewed-by: Marcin Szycik Signed-off-by: Qi Zhang Signed-off-by: Junfeng Guo Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Reviewed-by: Simon Horman Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_parser.c | 130 +++++++++++++++++++- drivers/net/ethernet/intel/ice/ice_parser.h | 26 ++++ 2 files changed, 154 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c index ee89208bf21d8..664beb64f5570 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.c +++ b/drivers/net/ethernet/intel/ice/ice_parser.c @@ -2243,9 +2243,9 @@ static int ice_tunnel_port_set(struct ice_parser *psr, enum ice_lbl_type type, /* found a matched slot to delete */ } else if (!on && (item->key_inv[ICE_BT_TUN_PORT_OFF_L] == - buf[ICE_UDP_PORT_OFF_L] || + buf[ICE_UDP_PORT_OFF_L] || item->key_inv[ICE_BT_TUN_PORT_OFF_H] == - buf[ICE_UDP_PORT_OFF_H])) { + buf[ICE_UDP_PORT_OFF_H])) { item->key_inv[ICE_BT_TUN_PORT_OFF_L] = ICE_BT_VLD_KEY; item->key_inv[ICE_BT_TUN_PORT_OFF_H] = ICE_BT_INV_KEY; @@ -2302,3 +2302,129 @@ int ice_parser_ecpri_tunnel_set(struct ice_parser *psr, return ice_tunnel_port_set(psr, ICE_LBL_BST_TYPE_UDP_ECPRI, udp_port, on); } + +/** + * ice_nearest_proto_id - find nearest protocol ID + * @rslt: pointer to a parser result instance + * @offset: a min value for the protocol offset + * @proto_id: the protocol ID (output) + * @proto_off: the protocol offset (output) + * + * From the protocols in @rslt, find the nearest protocol that has offset + * larger than @offset. + * + * Return: if true, the protocol's ID and offset + */ +static bool ice_nearest_proto_id(struct ice_parser_result *rslt, u16 offset, + u8 *proto_id, u16 *proto_off) +{ + u16 dist = U16_MAX; + u8 proto = 0; + int i; + + for (i = 0; i < rslt->po_num; i++) { + if (offset < rslt->po[i].offset) + continue; + if (offset - rslt->po[i].offset < dist) { + proto = rslt->po[i].proto_id; + dist = offset - rslt->po[i].offset; + } + } + + if (dist % 2) + return false; + + *proto_id = proto; + *proto_off = dist; + + return true; +} + +/* default flag mask to cover GTP_EH_PDU, GTP_EH_PDU_LINK and TUN2 + * In future, the flag masks should learn from DDP + */ +#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_SW 0x4002 +#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_ACL 0x0000 +#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_FD 0x6080 +#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_RSS 0x6010 + +/** + * ice_parser_profile_init - initialize a FXP profile based on parser result + * @rslt: a instance of a parser result + * @pkt_buf: packet data buffer + * @msk_buf: packet mask buffer + * @buf_len: packet length + * @blk: FXP pipeline stage + * @prof: input/output parameter to save the profile + * + * Return: 0 on success or errno on failure. + */ +int ice_parser_profile_init(struct ice_parser_result *rslt, + const u8 *pkt_buf, const u8 *msk_buf, + int buf_len, enum ice_block blk, + struct ice_parser_profile *prof) +{ + u8 proto_id = U8_MAX; + u16 proto_off = 0; + u16 off; + + memset(prof, 0, sizeof(*prof)); + set_bit(rslt->ptype, prof->ptypes); + if (blk == ICE_BLK_SW) { + prof->flags = rslt->flags_sw; + prof->flags_msk = ICE_KEYBUILD_FLAG_MASK_DEFAULT_SW; + } else if (blk == ICE_BLK_ACL) { + prof->flags = rslt->flags_acl; + prof->flags_msk = ICE_KEYBUILD_FLAG_MASK_DEFAULT_ACL; + } else if (blk == ICE_BLK_FD) { + prof->flags = rslt->flags_fd; + prof->flags_msk = ICE_KEYBUILD_FLAG_MASK_DEFAULT_FD; + } else if (blk == ICE_BLK_RSS) { + prof->flags = rslt->flags_rss; + prof->flags_msk = ICE_KEYBUILD_FLAG_MASK_DEFAULT_RSS; + } else { + return -EINVAL; + } + + for (off = 0; off < buf_len - 1; off++) { + if (msk_buf[off] == 0 && msk_buf[off + 1] == 0) + continue; + if (!ice_nearest_proto_id(rslt, off, &proto_id, &proto_off)) + continue; + if (prof->fv_num >= ICE_PARSER_FV_MAX) + return -EINVAL; + + prof->fv[prof->fv_num].proto_id = proto_id; + prof->fv[prof->fv_num].offset = proto_off; + prof->fv[prof->fv_num].spec = *(const u16 *)&pkt_buf[off]; + prof->fv[prof->fv_num].msk = *(const u16 *)&msk_buf[off]; + prof->fv_num++; + } + + return 0; +} + +/** + * ice_parser_profile_dump - dump an FXP profile info + * @hw: pointer to the hardware structure + * @prof: profile info to dump + */ +void ice_parser_profile_dump(struct ice_hw *hw, + struct ice_parser_profile *prof) +{ + struct device *dev = ice_hw_to_dev(hw); + u16 i; + + dev_info(dev, "ptypes:\n"); + for (i = 0; i < ICE_FLOW_PTYPE_MAX; i++) + if (test_bit(i, prof->ptypes)) + dev_info(dev, "\t%u\n", i); + + for (i = 0; i < prof->fv_num; i++) + dev_info(dev, "proto = %u, offset = %2u, spec = 0x%04x, mask = 0x%04x\n", + prof->fv[i].proto_id, prof->fv[i].offset, + prof->fv[i].spec, prof->fv[i].msk); + + dev_info(dev, "flags = 0x%04x\n", prof->flags); + dev_info(dev, "flags_msk = 0x%04x\n", prof->flags_msk); +} diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h index f9500ddf15670..6509d807627ce 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.h +++ b/drivers/net/ethernet/intel/ice/ice_parser.h @@ -451,6 +451,8 @@ struct ice_parser_proto_off { #define ICE_PARSER_PROTO_OFF_PAIR_SIZE 16 #define ICE_PARSER_FLAG_PSR_SIZE 8 +#define ICE_PARSER_FV_SIZE 48 +#define ICE_PARSER_FV_MAX 24 #define ICE_BT_TUN_PORT_OFF_H 16 #define ICE_BT_TUN_PORT_OFF_L 15 #define ICE_BT_VM_OFF 0 @@ -511,4 +513,28 @@ int ice_parser_ecpri_tunnel_set(struct ice_parser *psr, u16 udp_port, bool on); int ice_parser_run(struct ice_parser *psr, const u8 *pkt_buf, int pkt_len, struct ice_parser_result *rslt); void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt); + +struct ice_parser_fv { + u8 proto_id; /* hardware protocol ID */ + u16 offset; /* offset from the start of the protocol header */ + u16 spec; /* pattern to match */ + u16 msk; /* pattern mask */ +}; + +struct ice_parser_profile { + /* array of field vectors */ + struct ice_parser_fv fv[ICE_PARSER_FV_SIZE]; + int fv_num; /* # of field vectors must <= 48 */ + u16 flags; /* key builder flags */ + u16 flags_msk; /* key builder flag mask */ + + DECLARE_BITMAP(ptypes, ICE_FLOW_PTYPE_MAX); /* PTYPE bitmap */ +}; + +int ice_parser_profile_init(struct ice_parser_result *rslt, + const u8 *pkt_buf, const u8 *msk_buf, + int buf_len, enum ice_block blk, + struct ice_parser_profile *prof); +void ice_parser_profile_dump(struct ice_hw *hw, + struct ice_parser_profile *prof); #endif /* _ICE_PARSER_H_ */ From fb4dae4ca315fe48f1a8a452172f29196b2a7f3d Mon Sep 17 00:00:00 2001 From: Junfeng Guo Date: Thu, 25 Jul 2024 16:08:05 -0600 Subject: [PATCH 112/385] virtchnl: support raw packet in protocol header The patch extends existing virtchnl_proto_hdrs structure to allow VF to pass a pair of buffers as packet data and mask that describe a match pattern of a filter rule. Then the kernel PF driver is requested to parse the pair of buffer and figure out low level hardware metadata (ptype, profile, field vector.. ) to program the expected FDIR or RSS rules. Reviewed-by: Simon Horman Reviewed-by: Marcin Szycik Signed-off-by: Qi Zhang Signed-off-by: Junfeng Guo Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- include/linux/avf/virtchnl.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 8e177b67e82f4..4f78a65e33dca 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -1121,6 +1121,7 @@ enum virtchnl_vfr_states { }; #define VIRTCHNL_MAX_NUM_PROTO_HDRS 32 +#define VIRTCHNL_MAX_SIZE_RAW_PACKET 1024 #define PROTO_HDR_SHIFT 5 #define PROTO_HDR_FIELD_START(proto_hdr_type) ((proto_hdr_type) << PROTO_HDR_SHIFT) #define PROTO_HDR_FIELD_MASK ((1UL << PROTO_HDR_SHIFT) - 1) @@ -1266,13 +1267,22 @@ struct virtchnl_proto_hdrs { u8 pad[3]; /** * specify where protocol header start from. + * must be 0 when sending a raw packet request. * 0 - from the outer layer * 1 - from the first inner layer * 2 - from the second inner layer * .... **/ int count; /* the proto layers must < VIRTCHNL_MAX_NUM_PROTO_HDRS */ - struct virtchnl_proto_hdr proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS]; + union { + struct virtchnl_proto_hdr + proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS]; + struct { + u16 pkt_len; + u8 spec[VIRTCHNL_MAX_SIZE_RAW_PACKET]; + u8 mask[VIRTCHNL_MAX_SIZE_RAW_PACKET]; + } raw; + }; }; VIRTCHNL_CHECK_STRUCT_LEN(2312, virtchnl_proto_hdrs); From f217c187ea2eb31500fdea34f595f56433a164f1 Mon Sep 17 00:00:00 2001 From: Junfeng Guo Date: Thu, 25 Jul 2024 16:08:06 -0600 Subject: [PATCH 113/385] ice: add method to disable FDIR SWAP option The SWAP Flag in the FDIR Programming Descriptor doesn't work properly, it is always set and cannot be unset (hardware bug). Thus, add a method to effectively disable the FDIR SWAP option by setting the FDSWAP instead of FDINSET registers. Reviewed-by: Marcin Szycik Signed-off-by: Junfeng Guo Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Reviewed-by: Simon Horman Signed-off-by: Tony Nguyen --- .../net/ethernet/intel/ice/ice_flex_pipe.c | 51 ++++++++++++++++++- .../net/ethernet/intel/ice/ice_flex_pipe.h | 4 +- drivers/net/ethernet/intel/ice/ice_flow.c | 2 +- 3 files changed, 53 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 20d5db88c99fe..7f182a6f72aa7 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -2981,6 +2981,50 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, } /** + * ice_disable_fd_swap - set register appropriately to disable FD SWAP + * @hw: pointer to the HW struct + * @prof_id: profile ID + */ +static void +ice_disable_fd_swap(struct ice_hw *hw, u8 prof_id) +{ + u16 swap_val, fvw_num; + unsigned int i; + + swap_val = ICE_SWAP_VALID; + fvw_num = hw->blk[ICE_BLK_FD].es.fvw / ICE_FDIR_REG_SET_SIZE; + + /* Since the SWAP Flag in the Programming Desc doesn't work, + * here add method to disable the SWAP Option via setting + * certain SWAP and INSET register sets. + */ + for (i = 0; i < fvw_num ; i++) { + u32 raw_swap, raw_in; + unsigned int j; + + raw_swap = 0; + raw_in = 0; + + for (j = 0; j < ICE_FDIR_REG_SET_SIZE; j++) { + raw_swap |= (swap_val++) << (j * BITS_PER_BYTE); + raw_in |= ICE_INSET_DFLT << (j * BITS_PER_BYTE); + } + + /* write the FDIR swap register set */ + wr32(hw, GLQF_FDSWAP(prof_id, i), raw_swap); + + ice_debug(hw, ICE_DBG_INIT, "swap wr(%d, %d): 0x%x = 0x%08x\n", + prof_id, i, GLQF_FDSWAP(prof_id, i), raw_swap); + + /* write the FDIR inset register set */ + wr32(hw, GLQF_FDINSET(prof_id, i), raw_in); + + ice_debug(hw, ICE_DBG_INIT, "inset wr(%d, %d): 0x%x = 0x%08x\n", + prof_id, i, GLQF_FDINSET(prof_id, i), raw_in); + } +} + +/* * ice_add_prof - add profile * @hw: pointer to the HW struct * @blk: hardware block @@ -2991,6 +3035,7 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, * @es: extraction sequence (length of array is determined by the block) * @masks: mask for extraction sequence * @symm: symmetric setting for RSS profiles + * @fd_swap: enable/disable FDIR paired src/dst fields swap option * * This function registers a profile, which matches a set of PTYPES with a * particular extraction sequence. While the hardware profile is allocated @@ -3000,7 +3045,7 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, int ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], const struct ice_ptype_attributes *attr, u16 attr_cnt, - struct ice_fv_word *es, u16 *masks, bool symm) + struct ice_fv_word *es, u16 *masks, bool symm, bool fd_swap) { u32 bytes = DIV_ROUND_UP(ICE_FLOW_PTYPE_MAX, BITS_PER_BYTE); DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT); @@ -3020,7 +3065,7 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], status = ice_alloc_prof_id(hw, blk, &prof_id); if (status) goto err_ice_add_prof; - if (blk == ICE_BLK_FD) { + if (blk == ICE_BLK_FD && fd_swap) { /* For Flow Director block, the extraction sequence may * need to be altered in the case where there are paired * fields that have no match. This is necessary because @@ -3031,6 +3076,8 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], status = ice_update_fd_swap(hw, prof_id, es); if (status) goto err_ice_add_prof; + } else if (blk == ICE_BLK_FD) { + ice_disable_fd_swap(hw, prof_id); } status = ice_update_prof_masking(hw, blk, prof_id, masks); if (status) diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h index b39d7cdc381fa..7c66652dadd6c 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -6,6 +6,8 @@ #include "ice_type.h" +#define ICE_FDIR_REG_SET_SIZE 4 + int ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access); void ice_release_change_lock(struct ice_hw *hw); @@ -42,7 +44,7 @@ bool ice_hw_ptype_ena(struct ice_hw *hw, u16 ptype); int ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], const struct ice_ptype_attributes *attr, u16 attr_cnt, - struct ice_fv_word *es, u16 *masks, bool symm); + struct ice_fv_word *es, u16 *masks, bool symm, bool fd_swap); struct ice_prof_map * ice_search_prof_id(struct ice_hw *hw, enum ice_block blk, u64 id); int diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c index fc2b58f56279d..79106503194bf 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.c +++ b/drivers/net/ethernet/intel/ice/ice_flow.c @@ -1400,7 +1400,7 @@ ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk, /* Add a HW profile for this flow profile */ status = ice_add_prof(hw, blk, prof_id, (u8 *)params->ptypes, params->attr, params->attr_cnt, params->es, - params->mask, symm); + params->mask, symm, true); if (status) { ice_debug(hw, ICE_DBG_FLOW, "Error adding a HW flow profile\n"); goto out; From 99f419df8a5c5e1a58822203989f77712d01d410 Mon Sep 17 00:00:00 2001 From: Junfeng Guo Date: Thu, 25 Jul 2024 16:08:07 -0600 Subject: [PATCH 114/385] ice: enable FDIR filters from raw binary patterns for VFs Enable VFs to create FDIR filters from raw binary patterns. The corresponding processes for raw flow are added in the Parse / Create / Destroy stages. Reviewed-by: Marcin Szycik Signed-off-by: Junfeng Guo Co-developed-by: Ahmed Zaki Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Reviewed-by: Simon Horman Signed-off-by: Tony Nguyen --- .../net/ethernet/intel/ice/ice_flex_pipe.c | 48 +++ .../net/ethernet/intel/ice/ice_flex_pipe.h | 3 + drivers/net/ethernet/intel/ice/ice_flow.c | 107 +++++ drivers/net/ethernet/intel/ice/ice_flow.h | 5 + drivers/net/ethernet/intel/ice/ice_vf_lib.h | 8 + .../ethernet/intel/ice/ice_virtchnl_fdir.c | 403 +++++++++++++++++- 6 files changed, 566 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 7f182a6f72aa7..ed95072ca6e31 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -4145,6 +4145,54 @@ ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl) return status; } +/** + * ice_flow_assoc_fdir_prof - add an FDIR profile for main/ctrl VSI + * @hw: pointer to the HW struct + * @blk: HW block + * @dest_vsi: dest VSI + * @fdir_vsi: fdir programming VSI + * @hdl: profile handle + * + * Update the hardware tables to enable the FDIR profile indicated by @hdl for + * the VSI specified by @dest_vsi. On success, the flow will be enabled. + * + * Return: 0 on success or negative errno on failure. + */ +int +ice_flow_assoc_fdir_prof(struct ice_hw *hw, enum ice_block blk, + u16 dest_vsi, u16 fdir_vsi, u64 hdl) +{ + u16 vsi_num; + int status; + + if (blk != ICE_BLK_FD) + return -EINVAL; + + vsi_num = ice_get_hw_vsi_num(hw, dest_vsi); + status = ice_add_prof_id_flow(hw, blk, vsi_num, hdl); + if (status) { + ice_debug(hw, ICE_DBG_FLOW, "Adding HW profile failed for main VSI flow entry: %d\n", + status); + return status; + } + + vsi_num = ice_get_hw_vsi_num(hw, fdir_vsi); + status = ice_add_prof_id_flow(hw, blk, vsi_num, hdl); + if (status) { + ice_debug(hw, ICE_DBG_FLOW, "Adding HW profile failed for ctrl VSI flow entry: %d\n", + status); + goto err; + } + + return 0; + +err: + vsi_num = ice_get_hw_vsi_num(hw, dest_vsi); + ice_rem_prof_id_flow(hw, blk, vsi_num, hdl); + + return status; +} + /** * ice_rem_prof_from_list - remove a profile from list * @hw: pointer to the HW struct diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h index 7c66652dadd6c..90b9b09931221 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -51,6 +51,9 @@ int ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl); int ice_rem_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl); +int +ice_flow_assoc_fdir_prof(struct ice_hw *hw, enum ice_block blk, + u16 dest_vsi, u16 fdir_vsi, u64 hdl); enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buff, u32 len); enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len); diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c index 79106503194bf..d97b751052f22 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.c +++ b/drivers/net/ethernet/intel/ice/ice_flow.c @@ -409,6 +409,29 @@ static const u32 ice_ptypes_gtpc_tid[] = { }; /* Packet types for GTPU */ +static const struct ice_ptype_attributes ice_attr_gtpu_session[] = { + { ICE_MAC_IPV4_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV4_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV4_TCP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV4_ICMP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_TCP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_ICMP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_FRAG, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_TCP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_ICMPV6, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_FRAG, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_TCP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_ICMPV6, ICE_PTYPE_ATTR_GTP_SESSION }, +}; + static const struct ice_ptype_attributes ice_attr_gtpu_eh[] = { { ICE_MAC_IPV4_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_PDU_EH }, { ICE_MAC_IPV4_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_PDU_EH }, @@ -1523,6 +1546,90 @@ ice_flow_disassoc_prof(struct ice_hw *hw, enum ice_block blk, return status; } +#define FLAG_GTP_EH_PDU_LINK BIT_ULL(13) +#define FLAG_GTP_EH_PDU BIT_ULL(14) + +#define HI_BYTE_IN_WORD GENMASK(15, 8) +#define LO_BYTE_IN_WORD GENMASK(7, 0) + +#define FLAG_GTPU_MSK \ + (FLAG_GTP_EH_PDU | FLAG_GTP_EH_PDU_LINK) +#define FLAG_GTPU_UP \ + (FLAG_GTP_EH_PDU | FLAG_GTP_EH_PDU_LINK) +#define FLAG_GTPU_DW FLAG_GTP_EH_PDU + +/** + * ice_flow_set_parser_prof - Set flow profile based on the parsed profile info + * @hw: pointer to the HW struct + * @dest_vsi: dest VSI + * @fdir_vsi: fdir programming VSI + * @prof: stores parsed profile info from raw flow + * @blk: classification blk + * + * Return: 0 on success or negative errno on failure. + */ +int +ice_flow_set_parser_prof(struct ice_hw *hw, u16 dest_vsi, u16 fdir_vsi, + struct ice_parser_profile *prof, enum ice_block blk) +{ + u64 id = find_first_bit(prof->ptypes, ICE_FLOW_PTYPE_MAX); + struct ice_flow_prof_params *params __free(kfree); + u8 fv_words = hw->blk[blk].es.fvw; + int status; + int i, idx; + + params = kzalloc(sizeof(*params), GFP_KERNEL); + if (!params) + return -ENOMEM; + + for (i = 0; i < ICE_MAX_FV_WORDS; i++) { + params->es[i].prot_id = ICE_PROT_INVALID; + params->es[i].off = ICE_FV_OFFSET_INVAL; + } + + for (i = 0; i < prof->fv_num; i++) { + if (hw->blk[blk].es.reverse) + idx = fv_words - i - 1; + else + idx = i; + params->es[idx].prot_id = prof->fv[i].proto_id; + params->es[idx].off = prof->fv[i].offset; + params->mask[idx] = (((prof->fv[i].msk) << BITS_PER_BYTE) & + HI_BYTE_IN_WORD) | + (((prof->fv[i].msk) >> BITS_PER_BYTE) & + LO_BYTE_IN_WORD); + } + + switch (prof->flags) { + case FLAG_GTPU_DW: + params->attr = ice_attr_gtpu_down; + params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_down); + break; + case FLAG_GTPU_UP: + params->attr = ice_attr_gtpu_up; + params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_up); + break; + default: + if (prof->flags_msk & FLAG_GTPU_MSK) { + params->attr = ice_attr_gtpu_session; + params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_session); + } + break; + } + + status = ice_add_prof(hw, blk, id, (u8 *)prof->ptypes, + params->attr, params->attr_cnt, + params->es, params->mask, false, false); + if (status) + return status; + + status = ice_flow_assoc_fdir_prof(hw, blk, dest_vsi, fdir_vsi, id); + if (status) + ice_rem_prof(hw, blk, id); + + return status; +} + /** * ice_flow_add_prof - Add a flow profile for packet segments and matched fields * @hw: pointer to the HW struct diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h index 2fd2e0cb483d6..6cb7bb879c98e 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.h +++ b/drivers/net/ethernet/intel/ice/ice_flow.h @@ -5,6 +5,7 @@ #define _ICE_FLOW_H_ #include "ice_flex_type.h" +#include "ice_parser.h" #define ICE_FLOW_ENTRY_HANDLE_INVAL 0 #define ICE_FLOW_FLD_OFF_INVAL 0xffff @@ -326,6 +327,7 @@ enum ice_rss_cfg_hdr_type { ICE_RSS_ANY_HEADERS }; +struct ice_vsi; struct ice_rss_hash_cfg { u32 addl_hdrs; /* protocol header fields */ u64 hash_flds; /* hash bit field (ICE_FLOW_HASH_*) to configure */ @@ -445,6 +447,9 @@ ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir, bool symm, struct ice_flow_prof **prof); int ice_flow_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 prof_id); int +ice_flow_set_parser_prof(struct ice_hw *hw, u16 dest_vsi, u16 fdir_vsi, + struct ice_parser_profile *prof, enum ice_block blk); +int ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id, u64 entry_id, u16 vsi, enum ice_flow_priority prio, void *data, u64 *entry_h); diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index fec16919ec195..be4266899690a 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -12,6 +12,7 @@ #include #include #include "ice_type.h" +#include "ice_flow.h" #include "ice_virtchnl_fdir.h" #include "ice_vsi_vlan_ops.h" @@ -52,6 +53,12 @@ struct ice_mdd_vf_events { u16 last_printed; }; +/* Structure to store fdir fv entry */ +struct ice_fdir_prof_info { + struct ice_parser_profile prof; + u64 fdir_active_cnt; +}; + /* VF operations */ struct ice_vf_ops { enum ice_disq_rst_src reset_type; @@ -91,6 +98,7 @@ struct ice_vf { u16 lan_vsi_idx; /* index into PF struct */ u16 ctrl_vsi_idx; struct ice_vf_fdir fdir; + struct ice_fdir_prof_info fdir_prof_info[ICE_MAX_PTGS]; /* first vector index of this VF in the PF space */ int first_vector_idx; struct ice_sw *vf_sw_id; /* switch ID the VF VSIs connect to */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index b4feb09276870..14e3f0f89c78d 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -26,6 +26,15 @@ enum ice_fdir_tunnel_type { ICE_FDIR_TUNNEL_TYPE_NONE = 0, ICE_FDIR_TUNNEL_TYPE_GTPU, ICE_FDIR_TUNNEL_TYPE_GTPU_EH, + ICE_FDIR_TUNNEL_TYPE_ECPRI, + ICE_FDIR_TUNNEL_TYPE_GTPU_INNER, + ICE_FDIR_TUNNEL_TYPE_GTPU_EH_INNER, + ICE_FDIR_TUNNEL_TYPE_GRE, + ICE_FDIR_TUNNEL_TYPE_GTPOGRE, + ICE_FDIR_TUNNEL_TYPE_GTPOGRE_INNER, + ICE_FDIR_TUNNEL_TYPE_GRE_INNER, + ICE_FDIR_TUNNEL_TYPE_L2TPV2, + ICE_FDIR_TUNNEL_TYPE_L2TPV2_INNER, }; struct virtchnl_fdir_fltr_conf { @@ -33,6 +42,11 @@ struct virtchnl_fdir_fltr_conf { enum ice_fdir_tunnel_type ttype; u64 inset_flag; u32 flow_id; + + struct ice_parser_profile *prof; + bool parser_ena; + u8 *pkt_buf; + u8 pkt_len; }; struct virtchnl_fdir_inset_map { @@ -786,6 +800,107 @@ ice_vc_fdir_config_input_set(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, return ret; } +/** + * ice_vc_fdir_is_raw_flow - check if FDIR flow is raw (binary) + * @proto: virtchnl protocol headers + * + * Check if the FDIR rule is raw flow (protocol agnostic flow) or not. Note + * that common FDIR rule must have non-zero proto->count. Thus, we choose the + * tunnel_level and count of proto as the indicators. If both tunnel_level and + * count of proto are zero, this FDIR rule will be regarded as raw flow. + * + * Returns: true if headers describe raw flow, false otherwise. + */ +static bool +ice_vc_fdir_is_raw_flow(struct virtchnl_proto_hdrs *proto) +{ + return (proto->tunnel_level == 0 && proto->count == 0); +} + +/** + * ice_vc_fdir_parse_raw - parse a virtchnl raw FDIR rule + * @vf: pointer to the VF info + * @proto: virtchnl protocol headers + * @conf: FDIR configuration for each filter + * + * Parse the virtual channel filter's raw flow and store it in @conf + * + * Return: 0 on success or negative errno on failure. + */ +static int +ice_vc_fdir_parse_raw(struct ice_vf *vf, + struct virtchnl_proto_hdrs *proto, + struct virtchnl_fdir_fltr_conf *conf) +{ + u8 *pkt_buf, *msk_buf __free(kfree); + struct ice_parser_result rslt; + struct ice_pf *pf = vf->pf; + struct ice_parser *psr; + int status = -ENOMEM; + struct ice_hw *hw; + u16 udp_port = 0; + + pkt_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL); + msk_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL); + if (!pkt_buf || !msk_buf) + goto err_mem_alloc; + + memcpy(pkt_buf, proto->raw.spec, proto->raw.pkt_len); + memcpy(msk_buf, proto->raw.mask, proto->raw.pkt_len); + + hw = &pf->hw; + + /* Get raw profile info via Parser Lib */ + psr = ice_parser_create(hw); + if (IS_ERR(psr)) { + status = PTR_ERR(psr); + goto err_mem_alloc; + } + + ice_parser_dvm_set(psr, ice_is_dvm_ena(hw)); + + if (ice_get_open_tunnel_port(hw, &udp_port, TNL_VXLAN)) + ice_parser_vxlan_tunnel_set(psr, udp_port, true); + + status = ice_parser_run(psr, pkt_buf, proto->raw.pkt_len, &rslt); + if (status) + goto err_parser_destroy; + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_parser_result_dump(hw, &rslt); + + conf->prof = kzalloc(sizeof(*conf->prof), GFP_KERNEL); + if (!conf->prof) { + status = -ENOMEM; + goto err_parser_destroy; + } + + status = ice_parser_profile_init(&rslt, pkt_buf, msk_buf, + proto->raw.pkt_len, ICE_BLK_FD, + conf->prof); + if (status) + goto err_parser_profile_init; + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_parser_profile_dump(hw, conf->prof); + + /* Store raw flow info into @conf */ + conf->pkt_len = proto->raw.pkt_len; + conf->pkt_buf = pkt_buf; + conf->parser_ena = true; + + ice_parser_destroy(psr); + return 0; + +err_parser_profile_init: + kfree(conf->prof); +err_parser_destroy: + ice_parser_destroy(psr); +err_mem_alloc: + kfree(pkt_buf); + return status; +} + /** * ice_vc_fdir_parse_pattern * @vf: pointer to the VF info @@ -813,6 +928,10 @@ ice_vc_fdir_parse_pattern(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, return -EINVAL; } + /* For raw FDIR filters created by the parser */ + if (ice_vc_fdir_is_raw_flow(proto)) + return ice_vc_fdir_parse_raw(vf, proto, conf); + for (i = 0; i < proto->count; i++) { struct virtchnl_proto_hdr *hdr = &proto->proto_hdr[i]; struct ip_esp_hdr *esph; @@ -1101,8 +1220,10 @@ ice_vc_validate_fdir_fltr(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, struct virtchnl_proto_hdrs *proto = &fltr->rule_cfg.proto_hdrs; int ret; - if (!ice_vc_validate_pattern(vf, proto)) - return -EINVAL; + /* For raw FDIR filters created by the parser */ + if (!ice_vc_fdir_is_raw_flow(proto)) + if (!ice_vc_validate_pattern(vf, proto)) + return -EINVAL; ret = ice_vc_fdir_parse_pattern(vf, fltr, conf); if (ret) @@ -1295,11 +1416,15 @@ static int ice_vc_fdir_write_fltr(struct ice_vf *vf, return -ENOMEM; ice_fdir_get_prgm_desc(hw, input, &desc, add); - ret = ice_fdir_get_gen_prgm_pkt(hw, input, pkt, false, is_tun); - if (ret) { - dev_dbg(dev, "Gen training pkt for VF %d ptype %d failed\n", - vf->vf_id, input->flow_type); - goto err_free_pkt; + if (conf->parser_ena) { + memcpy(pkt, conf->pkt_buf, conf->pkt_len); + } else { + ret = ice_fdir_get_gen_prgm_pkt(hw, input, pkt, false, is_tun); + if (ret) { + dev_dbg(dev, "Gen training pkt for VF %d ptype %d failed\n", + vf->vf_id, input->flow_type); + goto err_free_pkt; + } } ret = ice_prgm_fdir_fltr(ctrl_vsi, &desc, pkt); @@ -1521,6 +1646,16 @@ ice_vf_verify_rx_desc(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx, return ret; } +static int ice_fdir_is_tunnel(enum ice_fdir_tunnel_type ttype) +{ + return (ttype == ICE_FDIR_TUNNEL_TYPE_GRE_INNER || + ttype == ICE_FDIR_TUNNEL_TYPE_GTPU_INNER || + ttype == ICE_FDIR_TUNNEL_TYPE_GTPU_EH_INNER || + ttype == ICE_FDIR_TUNNEL_TYPE_GTPOGRE_INNER || + ttype == ICE_FDIR_TUNNEL_TYPE_ECPRI || + ttype == ICE_FDIR_TUNNEL_TYPE_L2TPV2_INNER); +} + /** * ice_vc_add_fdir_fltr_post * @vf: pointer to the VF structure @@ -1781,6 +1916,158 @@ static void ice_vc_fdir_clear_irq_ctx(struct ice_vf *vf) spin_unlock_irqrestore(&vf->fdir.ctx_lock, flags); } +/** + * ice_vc_parser_fv_check_diff - check two parsed FDIR profile fv context + * @fv_a: struct of parsed FDIR profile field vector + * @fv_b: struct of parsed FDIR profile field vector + * + * Check if the two parsed FDIR profile field vector context are different, + * including proto_id, offset and mask. + * + * Return: true on different, false on otherwise. + */ +static bool ice_vc_parser_fv_check_diff(struct ice_parser_fv *fv_a, + struct ice_parser_fv *fv_b) +{ + return (fv_a->proto_id != fv_b->proto_id || + fv_a->offset != fv_b->offset || + fv_a->msk != fv_b->msk); +} + +/** + * ice_vc_parser_fv_save - save parsed FDIR profile fv context + * @fv: struct of parsed FDIR profile field vector + * @fv_src: parsed FDIR profile field vector context to save + * + * Save the parsed FDIR profile field vector context, including proto_id, + * offset and mask. + * + * Return: Void. + */ +static void ice_vc_parser_fv_save(struct ice_parser_fv *fv, + struct ice_parser_fv *fv_src) +{ + fv->proto_id = fv_src->proto_id; + fv->offset = fv_src->offset; + fv->msk = fv_src->msk; + fv->spec = 0; +} + +/** + * ice_vc_add_fdir_raw - add a raw FDIR filter for VF + * @vf: pointer to the VF info + * @conf: FDIR configuration for each filter + * @v_ret: the final VIRTCHNL code + * @stat: pointer to the VIRTCHNL_OP_ADD_FDIR_FILTER + * @len: length of the stat + * + * Return: 0 on success or negative errno on failure. + */ +static int +ice_vc_add_fdir_raw(struct ice_vf *vf, + struct virtchnl_fdir_fltr_conf *conf, + enum virtchnl_status_code *v_ret, + struct virtchnl_fdir_add *stat, int len) +{ + struct ice_vsi *vf_vsi, *ctrl_vsi; + struct ice_fdir_prof_info *pi; + struct ice_pf *pf = vf->pf; + int ret, ptg, id, i; + struct device *dev; + struct ice_hw *hw; + bool fv_found; + + dev = ice_pf_to_dev(pf); + hw = &pf->hw; + *v_ret = VIRTCHNL_STATUS_ERR_PARAM; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + + id = find_first_bit(conf->prof->ptypes, ICE_FLOW_PTYPE_MAX); + ptg = hw->blk[ICE_BLK_FD].xlt1.t[id]; + + vf_vsi = ice_get_vf_vsi(vf); + if (!vf_vsi) { + dev_err(dev, "Can not get FDIR vf_vsi for VF %d\n", vf->vf_id); + return -ENODEV; + } + + ctrl_vsi = pf->vsi[vf->ctrl_vsi_idx]; + if (!ctrl_vsi) { + dev_err(dev, "Can not get FDIR ctrl_vsi for VF %d\n", + vf->vf_id); + return -ENODEV; + } + + fv_found = false; + + /* Check if profile info already exists, then update the counter */ + pi = &vf->fdir_prof_info[ptg]; + if (pi->fdir_active_cnt != 0) { + for (i = 0; i < ICE_MAX_FV_WORDS; i++) + if (ice_vc_parser_fv_check_diff(&pi->prof.fv[i], + &conf->prof->fv[i])) + break; + if (i == ICE_MAX_FV_WORDS) { + fv_found = true; + pi->fdir_active_cnt++; + } + } + + /* HW profile setting is only required for the first time */ + if (!fv_found) { + ret = ice_flow_set_parser_prof(hw, vf_vsi->idx, + ctrl_vsi->idx, conf->prof, + ICE_BLK_FD); + + if (ret) { + *v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + dev_dbg(dev, "VF %d: insert hw prof failed\n", + vf->vf_id); + return ret; + } + } + + ret = ice_vc_fdir_insert_entry(vf, conf, &conf->flow_id); + if (ret) { + *v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + dev_dbg(dev, "VF %d: insert FDIR list failed\n", + vf->vf_id); + return ret; + } + + ret = ice_vc_fdir_set_irq_ctx(vf, conf, + VIRTCHNL_OP_ADD_FDIR_FILTER); + if (ret) { + dev_dbg(dev, "VF %d: set FDIR context failed\n", + vf->vf_id); + goto err_rem_entry; + } + + ret = ice_vc_fdir_write_fltr(vf, conf, true, false); + if (ret) { + dev_err(dev, "VF %d: adding FDIR raw flow rule failed, ret:%d\n", + vf->vf_id, ret); + goto err_clr_irq; + } + + /* Save parsed profile fv info of the FDIR rule for the first time */ + if (!fv_found) { + for (i = 0; i < conf->prof->fv_num; i++) + ice_vc_parser_fv_save(&pi->prof.fv[i], + &conf->prof->fv[i]); + pi->prof.fv_num = conf->prof->fv_num; + pi->fdir_active_cnt = 1; + } + + return 0; + +err_clr_irq: + ice_vc_fdir_clear_irq_ctx(vf); +err_rem_entry: + ice_vc_fdir_remove_entry(vf, conf, conf->flow_id); + return ret; +} + /** * ice_vc_add_fdir_fltr - add a FDIR filter for VF by the msg buffer * @vf: pointer to the VF info @@ -1846,7 +2133,7 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) len = sizeof(*stat); ret = ice_vc_validate_fdir_fltr(vf, fltr, conf); if (ret) { - v_ret = VIRTCHNL_STATUS_SUCCESS; + v_ret = VIRTCHNL_STATUS_ERR_PARAM; stat->status = VIRTCHNL_FDIR_FAILURE_RULE_INVALID; dev_dbg(dev, "Invalid FDIR filter from VF %d\n", vf->vf_id); goto err_free_conf; @@ -1861,6 +2148,15 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) goto exit; } + /* For raw FDIR filters created by the parser */ + if (conf->parser_ena) { + ret = ice_vc_add_fdir_raw(vf, conf, &v_ret, stat, len); + if (ret) + goto err_free_conf; + goto exit; + } + + is_tun = ice_fdir_is_tunnel(conf->ttype); ret = ice_vc_fdir_config_input_set(vf, fltr, conf, is_tun); if (ret) { v_ret = VIRTCHNL_STATUS_SUCCESS; @@ -1921,6 +2217,78 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) return ret; } +/** + * ice_vc_del_fdir_raw - delete a raw FDIR filter for VF + * @vf: pointer to the VF info + * @conf: FDIR configuration for each filter + * @v_ret: the final VIRTCHNL code + * @stat: pointer to the VIRTCHNL_OP_DEL_FDIR_FILTER + * @len: length of the stat + * + * Return: 0 on success or negative errno on failure. + */ +static int +ice_vc_del_fdir_raw(struct ice_vf *vf, + struct virtchnl_fdir_fltr_conf *conf, + enum virtchnl_status_code *v_ret, + struct virtchnl_fdir_del *stat, int len) +{ + struct ice_vsi *vf_vsi, *ctrl_vsi; + enum ice_block blk = ICE_BLK_FD; + struct ice_fdir_prof_info *pi; + struct ice_pf *pf = vf->pf; + struct device *dev; + struct ice_hw *hw; + unsigned long id; + u16 vsi_num; + int ptg; + int ret; + + dev = ice_pf_to_dev(pf); + hw = &pf->hw; + *v_ret = VIRTCHNL_STATUS_ERR_PARAM; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + + id = find_first_bit(conf->prof->ptypes, ICE_FLOW_PTYPE_MAX); + ptg = hw->blk[ICE_BLK_FD].xlt1.t[id]; + + ret = ice_vc_fdir_write_fltr(vf, conf, false, false); + if (ret) { + dev_err(dev, "VF %u: deleting FDIR raw flow rule failed: %d\n", + vf->vf_id, ret); + return ret; + } + + vf_vsi = ice_get_vf_vsi(vf); + if (!vf_vsi) { + dev_err(dev, "Can not get FDIR vf_vsi for VF %u\n", vf->vf_id); + return -ENODEV; + } + + ctrl_vsi = pf->vsi[vf->ctrl_vsi_idx]; + if (!ctrl_vsi) { + dev_err(dev, "Can not get FDIR ctrl_vsi for VF %u\n", + vf->vf_id); + return -ENODEV; + } + + pi = &vf->fdir_prof_info[ptg]; + if (pi->fdir_active_cnt != 0) { + pi->fdir_active_cnt--; + /* Remove the profile id flow if no active FDIR rule left */ + if (!pi->fdir_active_cnt) { + vsi_num = ice_get_hw_vsi_num(hw, ctrl_vsi->idx); + ice_rem_prof_id_flow(hw, blk, vsi_num, id); + + vsi_num = ice_get_hw_vsi_num(hw, vf_vsi->idx); + ice_rem_prof_id_flow(hw, blk, vsi_num, id); + } + } + + conf->parser_ena = false; + return 0; +} + /** * ice_vc_del_fdir_fltr - delete a FDIR filter for VF by the msg buffer * @vf: pointer to the VF info @@ -1933,7 +2301,10 @@ int ice_vc_del_fdir_fltr(struct ice_vf *vf, u8 *msg) struct virtchnl_fdir_del *fltr = (struct virtchnl_fdir_del *)msg; struct virtchnl_fdir_del *stat = NULL; struct virtchnl_fdir_fltr_conf *conf; + struct ice_vf_fdir *fdir = &vf->fdir; enum virtchnl_status_code v_ret; + struct ice_fdir_fltr *input; + enum ice_fltr_ptype flow; struct device *dev; struct ice_pf *pf; int is_tun = 0; @@ -1983,6 +2354,15 @@ int ice_vc_del_fdir_fltr(struct ice_vf *vf, u8 *msg) goto err_exit; } + /* For raw FDIR filters created by the parser */ + if (conf->parser_ena) { + ret = ice_vc_del_fdir_raw(vf, conf, &v_ret, stat, len); + if (ret) + goto err_del_tmr; + goto exit; + } + + is_tun = ice_fdir_is_tunnel(conf->ttype); ret = ice_vc_fdir_write_fltr(vf, conf, false, is_tun); if (ret) { v_ret = VIRTCHNL_STATUS_SUCCESS; @@ -1992,6 +2372,13 @@ int ice_vc_del_fdir_fltr(struct ice_vf *vf, u8 *msg) goto err_del_tmr; } + /* Remove unused profiles to avoid unexpected behaviors */ + input = &conf->input; + flow = input->flow_type; + if (fdir->fdir_fltr_cnt[flow][is_tun] == 1) + ice_vc_fdir_rem_prof(vf, flow, is_tun); + +exit: kfree(stat); return ret; From 995617dccc89643d8d8022bbec76e869643842bf Mon Sep 17 00:00:00 2001 From: Ahmed Zaki Date: Thu, 25 Jul 2024 16:08:08 -0600 Subject: [PATCH 115/385] iavf: refactor add/del FDIR filters In preparation for a second type of FDIR filters that can be added by tc-u32, move the add/del of the FDIR logic to be entirely contained in iavf_fdir.c. The iavf_find_fdir_fltr_by_loc() is renamed to iavf_find_fdir_fltr() to be more agnostic to the filter ID parameter (for now @loc, which is relevant only to current FDIR filters added via ethtool). The FDIR filter deletion is moved from iavf_del_fdir_ethtool() in ethtool.c to iavf_fdir_del_fltr(). While at it, fix a minor bug where the "fltr" is accessed out of the fdir_fltr_lock spinlock protection. Reviewed-by: Sridhar Samudrala Reviewed-by: Marcin Szycik Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Reviewed-by: Simon Horman Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf.h | 5 ++ .../net/ethernet/intel/iavf/iavf_ethtool.c | 56 ++------------- drivers/net/ethernet/intel/iavf/iavf_fdir.c | 72 +++++++++++++++++-- drivers/net/ethernet/intel/iavf/iavf_fdir.h | 7 +- 4 files changed, 83 insertions(+), 57 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 23a6557fc3db2..dfed22baebf8d 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -444,6 +444,11 @@ struct iavf_adapter { spinlock_t adv_rss_lock; /* protect the RSS management list */ }; +/* Must be called with fdir_fltr_lock lock held */ +static inline bool iavf_fdir_max_reached(struct iavf_adapter *adapter) +{ + return adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS; +} /* Ethtool Private Flags */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 52273f7eab2c4..7ab445eeee18c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -927,7 +927,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter, spin_lock_bh(&adapter->fdir_fltr_lock); - rule = iavf_find_fdir_fltr_by_loc(adapter, fsp->location); + rule = iavf_find_fdir_fltr(adapter, fsp->location); if (!rule) { ret = -EINVAL; goto release_lock; @@ -1263,15 +1263,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx return -EINVAL; spin_lock_bh(&adapter->fdir_fltr_lock); - if (adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS) { - spin_unlock_bh(&adapter->fdir_fltr_lock); - dev_err(&adapter->pdev->dev, - "Unable to add Flow Director filter because VF reached the limit of max allowed filters (%u)\n", - IAVF_MAX_FDIR_FILTERS); - return -ENOSPC; - } - - if (iavf_find_fdir_fltr_by_loc(adapter, fsp->location)) { + if (iavf_find_fdir_fltr(adapter, fsp->location)) { dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, it already exists\n"); spin_unlock_bh(&adapter->fdir_fltr_lock); return -EEXIST; @@ -1291,23 +1283,10 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx } err = iavf_add_fdir_fltr_info(adapter, fsp, fltr); - if (err) - goto ret; - - spin_lock_bh(&adapter->fdir_fltr_lock); - iavf_fdir_list_add_fltr(adapter, fltr); - adapter->fdir_active_fltr++; - - if (adapter->link_up) - fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; - else - fltr->state = IAVF_FDIR_FLTR_INACTIVE; - spin_unlock_bh(&adapter->fdir_fltr_lock); + if (!err) + err = iavf_fdir_add_fltr(adapter, fltr); - if (adapter->link_up) - iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_FDIR_FILTER); -ret: - if (err && fltr) + if (err) kfree(fltr); mutex_unlock(&adapter->crit_lock); @@ -1324,34 +1303,11 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd) { struct ethtool_rx_flow_spec *fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; - struct iavf_fdir_fltr *fltr = NULL; - int err = 0; if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; - spin_lock_bh(&adapter->fdir_fltr_lock); - fltr = iavf_find_fdir_fltr_by_loc(adapter, fsp->location); - if (fltr) { - if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { - fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; - } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) { - list_del(&fltr->list); - kfree(fltr); - adapter->fdir_active_fltr--; - fltr = NULL; - } else { - err = -EBUSY; - } - } else if (adapter->fdir_active_fltr) { - err = -EINVAL; - } - spin_unlock_bh(&adapter->fdir_fltr_lock); - - if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST) - iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_FDIR_FILTER); - - return err; + return iavf_fdir_del_fltr(adapter, fsp->location); } /** diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c index 2d47b0b4640e4..1e1daf71dfa04 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c @@ -815,13 +815,14 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * } /** - * iavf_find_fdir_fltr_by_loc - find filter with location + * iavf_find_fdir_fltr - find FDIR filter * @adapter: pointer to the VF adapter structure * @loc: location to find. * - * Returns pointer to Flow Director filter if found or null + * Returns: pointer to Flow Director filter if found or NULL. Lock must be held. */ -struct iavf_fdir_fltr *iavf_find_fdir_fltr_by_loc(struct iavf_adapter *adapter, u32 loc) +struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter, + u32 loc) { struct iavf_fdir_fltr *rule; @@ -833,14 +834,26 @@ struct iavf_fdir_fltr *iavf_find_fdir_fltr_by_loc(struct iavf_adapter *adapter, } /** - * iavf_fdir_list_add_fltr - add a new node to the flow director filter list + * iavf_fdir_add_fltr - add a new node to the flow director filter list * @adapter: pointer to the VF adapter structure * @fltr: filter node to add to structure + * + * Return: 0 on success or negative errno on failure. */ -void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr) +int iavf_fdir_add_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) { struct iavf_fdir_fltr *rule, *parent = NULL; + spin_lock_bh(&adapter->fdir_fltr_lock); + if (iavf_fdir_max_reached(adapter)) { + spin_unlock_bh(&adapter->fdir_fltr_lock); + dev_err(&adapter->pdev->dev, + "Unable to add Flow Director filter (limit (%u) reached)\n", + IAVF_MAX_FDIR_FILTERS); + return -ENOSPC; + } + list_for_each_entry(rule, &adapter->fdir_list_head, list) { if (rule->loc >= fltr->loc) break; @@ -851,4 +864,53 @@ void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr list_add(&fltr->list, &parent->list); else list_add(&fltr->list, &adapter->fdir_list_head); + adapter->fdir_active_fltr++; + + if (adapter->link_up) + fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; + else + fltr->state = IAVF_FDIR_FLTR_INACTIVE; + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (adapter->link_up) + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_FDIR_FILTER); + + return 0; +} + +/** + * iavf_fdir_del_fltr - delete a flow director filter from the list + * @adapter: pointer to the VF adapter structure + * @loc: location to delete. + * + * Return: 0 on success or negative errno on failure. + */ +int iavf_fdir_del_fltr(struct iavf_adapter *adapter, u32 loc) +{ + struct iavf_fdir_fltr *fltr = NULL; + int err = 0; + + spin_lock_bh(&adapter->fdir_fltr_lock); + fltr = iavf_find_fdir_fltr(adapter, loc); + + if (fltr) { + if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { + fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; + } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) { + list_del(&fltr->list); + kfree(fltr); + adapter->fdir_active_fltr--; + fltr = NULL; + } else { + err = -EBUSY; + } + } else if (adapter->fdir_active_fltr) { + err = -EINVAL; + } + + if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST) + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_FDIR_FILTER); + + spin_unlock_bh(&adapter->fdir_fltr_lock); + return err; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h index d31bd923ba8cb..5c85eb25fa2a8 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h @@ -128,6 +128,9 @@ int iavf_validate_fdir_fltr_masks(struct iavf_adapter *adapter, int iavf_fill_fdir_add_msg(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); -void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); -struct iavf_fdir_fltr *iavf_find_fdir_fltr_by_loc(struct iavf_adapter *adapter, u32 loc); +int iavf_fdir_add_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr); +int iavf_fdir_del_fltr(struct iavf_adapter *adapter, u32 loc); +struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter, + u32 loc); #endif /* _IAVF_FDIR_H_ */ From 623122ac1c4074791ea319df4676fb2875817fe4 Mon Sep 17 00:00:00 2001 From: Ahmed Zaki Date: Thu, 25 Jul 2024 16:08:09 -0600 Subject: [PATCH 116/385] iavf: add support for offloading tc U32 cls filters Add support for offloading cls U32 filters. Only "skbedit queue_mapping" and "drop" actions are supported. Also, only "ip" and "802_3" tc protocols are allowed. The PF must advertise the VIRTCHNL_VF_OFFLOAD_TC_U32 capability flag. Since the filters will be enabled via the FD stage at the PF, a new type of FDIR filters is added and the existing list and state machine are used. The new filters can be used to configure flow directors based on raw (binary) pattern in the rx packet. Examples: 0. # tc qdisc add dev enp175s0v0 ingress 1. Redirect UDP from src IP 192.168.2.1 to queue 12: # tc filter add dev protocol ip ingress u32 \ match u32 0x45000000 0xff000000 at 0 \ match u32 0x00110000 0x00ff0000 at 8 \ match u32 0xC0A80201 0xffffffff at 12 \ match u32 0x00000000 0x00000000 at 24 \ action skbedit queue_mapping 12 skip_sw 2. Drop all ICMP: # tc filter add dev protocol ip ingress u32 \ match u32 0x45000000 0xff000000 at 0 \ match u32 0x00010000 0x00ff0000 at 8 \ match u32 0x00000000 0x00000000 at 24 \ action drop skip_sw 3. Redirect ICMP traffic from MAC 3c:fd:fe:a5:47:e0 to queue 7 (note proto: 802_3): # tc filter add dev protocol 802_3 ingress u32 \ match u32 0x00003CFD 0x0000ffff at 4 \ match u32 0xFEA547E0 0xffffffff at 8 \ match u32 0x08004500 0xffffff00 at 12 \ match u32 0x00000001 0x000000ff at 20 \ match u32 0x0000 0x0000 at 40 \ action skbedit queue_mapping 7 skip_sw Notes on matches: 1 - All intermediate fields that are needed to parse the correct PTYPE must be provided (in e.g. 3: Ethernet Type 0x0800 in MAC, IP version and IP length: 0x45 and protocol: 0x01 (ICMP)). 2 - The last match must provide an offset that guarantees all required headers are accounted for, even if the last header is not matched. For example, in #2, the last match is 4 bytes at offset 24 starting from IP header, so the total is 14 (MAC) + 24 + 4 = 42, which is the sum of MAC+IP+ICMP headers. Reviewed-by: Sridhar Samudrala Reviewed-by: Marcin Szycik Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Reviewed-by: Simon Horman Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf.h | 27 ++- .../net/ethernet/intel/iavf/iavf_ethtool.c | 9 +- drivers/net/ethernet/intel/iavf/iavf_fdir.c | 29 +++- drivers/net/ethernet/intel/iavf/iavf_fdir.h | 10 +- drivers/net/ethernet/intel/iavf/iavf_main.c | 160 +++++++++++++++++- .../net/ethernet/intel/iavf/iavf_virtchnl.c | 25 ++- drivers/net/ethernet/intel/ice/ice_virtchnl.c | 4 + include/linux/avf/virtchnl.h | 1 + 8 files changed, 238 insertions(+), 27 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index dfed22baebf8d..48cd1d06761c8 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -33,6 +33,7 @@ #include #include #include +#include #include "iavf_type.h" #include @@ -393,6 +394,8 @@ struct iavf_adapter { VIRTCHNL_VF_OFFLOAD_VLAN_V2) #define CRC_OFFLOAD_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_CRC) +#define TC_U32_SUPPORT(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_TC_U32) #define VLAN_V2_FILTERING_ALLOWED(_a) \ (VLAN_V2_ALLOWED((_a)) && \ ((_a)->vlan_v2_caps.filtering.filtering_support.outer || \ @@ -437,6 +440,7 @@ struct iavf_adapter { #define IAVF_MAX_FDIR_FILTERS 128 /* max allowed Flow Director filters */ u16 fdir_active_fltr; + u16 raw_fdir_active_fltr; struct list_head fdir_list_head; spinlock_t fdir_fltr_lock; /* protect the Flow Director filter list */ @@ -447,7 +451,28 @@ struct iavf_adapter { /* Must be called with fdir_fltr_lock lock held */ static inline bool iavf_fdir_max_reached(struct iavf_adapter *adapter) { - return adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS; + return adapter->fdir_active_fltr + adapter->raw_fdir_active_fltr >= + IAVF_MAX_FDIR_FILTERS; +} + +static inline void +iavf_inc_fdir_active_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) +{ + if (iavf_is_raw_fdir(fltr)) + adapter->raw_fdir_active_fltr++; + else + adapter->fdir_active_fltr++; +} + +static inline void +iavf_dec_fdir_active_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) +{ + if (iavf_is_raw_fdir(fltr)) + adapter->raw_fdir_active_fltr--; + else + adapter->fdir_active_fltr--; } /* Ethtool Private Flags */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 7ab445eeee18c..74a1e9fe18212 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -927,7 +927,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter, spin_lock_bh(&adapter->fdir_fltr_lock); - rule = iavf_find_fdir_fltr(adapter, fsp->location); + rule = iavf_find_fdir_fltr(adapter, false, fsp->location); if (!rule) { ret = -EINVAL; goto release_lock; @@ -1072,6 +1072,9 @@ iavf_get_fdir_fltr_ids(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd, spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(fltr, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + continue; + if (cnt == cmd->rule_cnt) { val = -EMSGSIZE; goto release_lock; @@ -1263,7 +1266,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx return -EINVAL; spin_lock_bh(&adapter->fdir_fltr_lock); - if (iavf_find_fdir_fltr(adapter, fsp->location)) { + if (iavf_find_fdir_fltr(adapter, false, fsp->location)) { dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, it already exists\n"); spin_unlock_bh(&adapter->fdir_fltr_lock); return -EEXIST; @@ -1307,7 +1310,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; - return iavf_fdir_del_fltr(adapter, fsp->location); + return iavf_fdir_del_fltr(adapter, false, fsp->location); } /** diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c index 1e1daf71dfa04..a1b3b44cc14a1 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c @@ -796,6 +796,9 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(tmp, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + continue; + if (tmp->flow_type != fltr->flow_type) continue; @@ -817,18 +820,21 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * /** * iavf_find_fdir_fltr - find FDIR filter * @adapter: pointer to the VF adapter structure - * @loc: location to find. + * @is_raw: filter type, is raw (tc u32) or not (ethtool) + * @data: data to ID the filter, type dependent * * Returns: pointer to Flow Director filter if found or NULL. Lock must be held. */ struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter, - u32 loc) + bool is_raw, u32 data) { struct iavf_fdir_fltr *rule; - list_for_each_entry(rule, &adapter->fdir_list_head, list) - if (rule->loc == loc) + list_for_each_entry(rule, &adapter->fdir_list_head, list) { + if ((is_raw && rule->cls_u32_handle == data) || + (!is_raw && rule->loc == data)) return rule; + } return NULL; } @@ -855,6 +861,9 @@ int iavf_fdir_add_fltr(struct iavf_adapter *adapter, } list_for_each_entry(rule, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + break; + if (rule->loc >= fltr->loc) break; parent = rule; @@ -864,7 +873,8 @@ int iavf_fdir_add_fltr(struct iavf_adapter *adapter, list_add(&fltr->list, &parent->list); else list_add(&fltr->list, &adapter->fdir_list_head); - adapter->fdir_active_fltr++; + + iavf_inc_fdir_active_fltr(adapter, fltr); if (adapter->link_up) fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; @@ -881,25 +891,26 @@ int iavf_fdir_add_fltr(struct iavf_adapter *adapter, /** * iavf_fdir_del_fltr - delete a flow director filter from the list * @adapter: pointer to the VF adapter structure - * @loc: location to delete. + * @is_raw: filter type, is raw (tc u32) or not (ethtool) + * @data: data to ID the filter, type dependent * * Return: 0 on success or negative errno on failure. */ -int iavf_fdir_del_fltr(struct iavf_adapter *adapter, u32 loc) +int iavf_fdir_del_fltr(struct iavf_adapter *adapter, bool is_raw, u32 data) { struct iavf_fdir_fltr *fltr = NULL; int err = 0; spin_lock_bh(&adapter->fdir_fltr_lock); - fltr = iavf_find_fdir_fltr(adapter, loc); + fltr = iavf_find_fdir_fltr(adapter, is_raw, data); if (fltr) { if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) { list_del(&fltr->list); + iavf_dec_fdir_active_fltr(adapter, fltr); kfree(fltr); - adapter->fdir_active_fltr--; fltr = NULL; } else { err = -EBUSY; diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h index 5c85eb25fa2a8..e84a5351162f7 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h @@ -117,12 +117,18 @@ struct iavf_fdir_fltr { u32 flow_id; + u32 cls_u32_handle; /* for FDIR added via tc u32 */ u32 loc; /* Rule location inside the flow table */ u32 q_index; struct virtchnl_fdir_add vc_add_msg; }; +static inline bool iavf_is_raw_fdir(struct iavf_fdir_fltr *fltr) +{ + return !fltr->vc_add_msg.rule_cfg.proto_hdrs.count; +} + int iavf_validate_fdir_fltr_masks(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); int iavf_fill_fdir_add_msg(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); @@ -130,7 +136,7 @@ void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *f bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); int iavf_fdir_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); -int iavf_fdir_del_fltr(struct iavf_adapter *adapter, u32 loc); +int iavf_fdir_del_fltr(struct iavf_adapter *adapter, bool is_raw, u32 data); struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter, - u32 loc); + bool is_raw, u32 data); #endif /* _IAVF_FDIR_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index ff11bafb3b4fd..f782402cd7898 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -4013,7 +4013,7 @@ static int iavf_delete_clsflower(struct iavf_adapter *adapter, /** * iavf_setup_tc_cls_flower - flower classifier offloads - * @adapter: board private structure + * @adapter: pointer to iavf adapter structure * @cls_flower: pointer to flow_cls_offload struct with flow info */ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, @@ -4031,6 +4031,154 @@ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, } } +/** + * iavf_add_cls_u32 - Add U32 classifier offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_add_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + struct netlink_ext_ack *extack = cls_u32->common.extack; + struct virtchnl_fdir_rule *rule_cfg; + struct virtchnl_filter_action *vact; + struct virtchnl_proto_hdrs *hdrs; + struct ethhdr *spec_h, *mask_h; + const struct tc_action *act; + struct iavf_fdir_fltr *fltr; + struct tcf_exts *exts; + unsigned int q_index; + int i, status = 0; + int off_base = 0; + + if (cls_u32->knode.link_handle) { + NL_SET_ERR_MSG_MOD(extack, "Linking not supported"); + return -EOPNOTSUPP; + } + + fltr = kzalloc(sizeof(*fltr), GFP_KERNEL); + if (!fltr) + return -ENOMEM; + + rule_cfg = &fltr->vc_add_msg.rule_cfg; + hdrs = &rule_cfg->proto_hdrs; + hdrs->count = 0; + + /* The parser lib at the PF expects the packet starting with MAC hdr */ + switch (ntohs(cls_u32->common.protocol)) { + case ETH_P_802_3: + break; + case ETH_P_IP: + spec_h = (struct ethhdr *)hdrs->raw.spec; + mask_h = (struct ethhdr *)hdrs->raw.mask; + spec_h->h_proto = htons(ETH_P_IP); + mask_h->h_proto = htons(0xFFFF); + off_base += ETH_HLEN; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Only 802_3 and ip filter protocols are supported"); + status = -EOPNOTSUPP; + goto free_alloc; + } + + for (i = 0; i < cls_u32->knode.sel->nkeys; i++) { + __be32 val, mask; + int off; + + off = off_base + cls_u32->knode.sel->keys[i].off; + val = cls_u32->knode.sel->keys[i].val; + mask = cls_u32->knode.sel->keys[i].mask; + + if (off >= sizeof(hdrs->raw.spec)) { + NL_SET_ERR_MSG_MOD(extack, "Input exceeds maximum allowed."); + status = -EINVAL; + goto free_alloc; + } + + memcpy(&hdrs->raw.spec[off], &val, sizeof(val)); + memcpy(&hdrs->raw.mask[off], &mask, sizeof(mask)); + hdrs->raw.pkt_len = off + sizeof(val); + } + + /* Only one action is allowed */ + rule_cfg->action_set.count = 1; + vact = &rule_cfg->action_set.actions[0]; + exts = cls_u32->knode.exts; + + tcf_exts_for_each_action(i, act, exts) { + /* FDIR queue */ + if (is_tcf_skbedit_rx_queue_mapping(act)) { + q_index = tcf_skbedit_rx_queue_mapping(act); + if (q_index >= adapter->num_active_queues) { + status = -EINVAL; + goto free_alloc; + } + + vact->type = VIRTCHNL_ACTION_QUEUE; + vact->act_conf.queue.index = q_index; + break; + } + + /* Drop */ + if (is_tcf_gact_shot(act)) { + vact->type = VIRTCHNL_ACTION_DROP; + break; + } + + /* Unsupported action */ + NL_SET_ERR_MSG_MOD(extack, "Unsupported action."); + status = -EOPNOTSUPP; + goto free_alloc; + } + + fltr->vc_add_msg.vsi_id = adapter->vsi.id; + fltr->cls_u32_handle = cls_u32->knode.handle; + return iavf_fdir_add_fltr(adapter, fltr); + +free_alloc: + kfree(fltr); + return status; +} + +/** + * iavf_del_cls_u32 - Delete U32 classifier offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_del_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + return iavf_fdir_del_fltr(adapter, true, cls_u32->knode.handle); +} + +/** + * iavf_setup_tc_cls_u32 - U32 filter offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_setup_tc_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + if (!TC_U32_SUPPORT(adapter) || !FDIR_FLTR_SUPPORT(adapter)) + return -EOPNOTSUPP; + + switch (cls_u32->command) { + case TC_CLSU32_NEW_KNODE: + case TC_CLSU32_REPLACE_KNODE: + return iavf_add_cls_u32(adapter, cls_u32); + case TC_CLSU32_DELETE_KNODE: + return iavf_del_cls_u32(adapter, cls_u32); + default: + return -EOPNOTSUPP; + } +} + /** * iavf_setup_tc_block_cb - block callback for tc * @type: type of offload @@ -4050,6 +4198,8 @@ static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, switch (type) { case TC_SETUP_CLSFLOWER: return iavf_setup_tc_cls_flower(cb_priv, type_data); + case TC_SETUP_CLSU32: + return iavf_setup_tc_cls_u32(cb_priv, type_data); default: return -EOPNOTSUPP; } @@ -4332,8 +4482,8 @@ static void iavf_disable_fdir(struct iavf_adapter *adapter) fdir->state == IAVF_FDIR_FLTR_INACTIVE) { /* Delete filters not registered in PF */ list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING || fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST || fdir->state == IAVF_FDIR_FLTR_ACTIVE) { @@ -4843,9 +4993,11 @@ int iavf_process_config(struct iavf_adapter *adapter) /* get HW VLAN features that can be toggled */ hw_vlan_features = iavf_get_netdev_vlan_hw_features(adapter); - /* Enable cloud filter if ADQ is supported */ - if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) + /* Enable HW TC offload if ADQ or tc U32 is supported */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ || + TC_U32_SUPPORT(adapter)) hw_features |= NETIF_F_HW_TC; + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_USO) hw_features |= NETIF_F_GSO_UDP_L4; diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 1e543f6a7c303..7e810b65380ca 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -142,6 +142,7 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_WB_ON_ITR | VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 | VIRTCHNL_VF_OFFLOAD_ENCAP | + VIRTCHNL_VF_OFFLOAD_TC_U32 | VIRTCHNL_VF_OFFLOAD_VLAN_V2 | VIRTCHNL_VF_OFFLOAD_CRC | VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | @@ -1961,8 +1962,8 @@ static void iavf_activate_fdir_filters(struct iavf_adapter *adapter) * list on PF is already cleared after a reset */ list_del(&f->list); + iavf_dec_fdir_active_fltr(adapter, f); kfree(f); - adapter->fdir_active_fltr--; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -2135,8 +2136,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, dev_err(&adapter->pdev->dev, "%s\n", msg); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -2451,8 +2452,12 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list) { if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING) { if (add_fltr->status == VIRTCHNL_FDIR_SUCCESS) { - dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is added\n", - fdir->loc); + if (!iavf_is_raw_fdir(fdir)) + dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is added\n", + fdir->loc); + else + dev_info(&adapter->pdev->dev, "Flow Director filter (raw) for TC handle %x is added\n", + TC_U32_USERHTID(fdir->cls_u32_handle)); fdir->state = IAVF_FDIR_FLTR_ACTIVE; fdir->flow_id = add_fltr->flow_id; } else { @@ -2460,8 +2465,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, add_fltr->status); iavf_print_fdir_fltr(adapter, fdir); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } } } @@ -2479,11 +2484,15 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS || del_fltr->status == VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) { - dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n", - fdir->loc); + if (!iavf_is_raw_fdir(fdir)) + dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n", + fdir->loc); + else + dev_info(&adapter->pdev->dev, "Flow Director filter (raw) for TC handle %x is deleted\n", + TC_U32_USERHTID(fdir->cls_u32_handle)); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } else { fdir->state = IAVF_FDIR_FLTR_ACTIVE; dev_info(&adapter->pdev->dev, "Failed to delete Flow Director filter with status: %d\n", diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 1c6ce0c4ed4ee..59f62306b9cb0 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -461,6 +461,10 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_FDIR_PF; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_TC_U32 && + vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_FDIR_PF) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_TC_U32; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 4f78a65e33dca..f41395264dca1 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -247,6 +247,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); /* used to negotiate communicating link speeds in Mbps */ #define VIRTCHNL_VF_CAP_ADV_LINK_SPEED BIT(7) #define VIRTCHNL_VF_OFFLOAD_CRC BIT(10) +#define VIRTCHNL_VF_OFFLOAD_TC_U32 BIT(11) #define VIRTCHNL_VF_OFFLOAD_VLAN_V2 BIT(15) #define VIRTCHNL_VF_OFFLOAD_VLAN BIT(16) #define VIRTCHNL_VF_OFFLOAD_RX_POLLING BIT(17) From baae8b0ba8352f2b93346cc1e33ca115152cf22c Mon Sep 17 00:00:00 2001 From: Jing-Ping Jan Date: Tue, 13 Aug 2024 01:09:10 +0800 Subject: [PATCH 117/385] Documentation: networking: correct spelling Correct spelling problems for Documentation/networking/ as reported by ispell. Signed-off-by: Jing-Ping Jan Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240812170910.5760-1-zoo868e@gmail.com Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 82c5542c80ce3..3f6c6880e7c48 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -934,18 +934,18 @@ Request contents: ==================================== ====== =========================== Kernel checks that requested ring sizes do not exceed limits reported by -driver. Driver may impose additional constraints and may not suspport all +driver. Driver may impose additional constraints and may not support all attributes. ``ETHTOOL_A_RINGS_CQE_SIZE`` specifies the completion queue event size. -Completion queue events(CQE) are the events posted by NIC to indicate the -completion status of a packet when the packet is sent(like send success or -error) or received(like pointers to packet fragments). The CQE size parameter +Completion queue events (CQE) are the events posted by NIC to indicate the +completion status of a packet when the packet is sent (like send success or +error) or received (like pointers to packet fragments). The CQE size parameter enables to modify the CQE size other than default size if NIC supports it. -A bigger CQE can have more receive buffer pointers inturn NIC can transfer -a bigger frame from wire. Based on the NIC hardware, the overall completion -queue size can be adjusted in the driver if CQE size is modified. +A bigger CQE can have more receive buffer pointers, and in turn the NIC can +transfer a bigger frame from wire. Based on the NIC hardware, the overall +completion queue size can be adjusted in the driver if CQE size is modified. CHANNELS_GET ============ @@ -989,7 +989,7 @@ Request contents: ===================================== ====== ========================== Kernel checks that requested channel counts do not exceed limits reported by -driver. Driver may impose additional constraints and may not suspport all +driver. Driver may impose additional constraints and may not support all attributes. @@ -1935,7 +1935,7 @@ When set, the optional ``ETHTOOL_A_PLCA_VERSION`` attribute indicates which standard and version the PLCA management interface complies to. When not set, the interface is vendor-specific and (possibly) supplied by the driver. The OPEN Alliance SIG specifies a standard register map for 10BASE-T1S PHYs -embedding the PLCA Reconcialiation Sublayer. See "10BASE-T1S PLCA Management +embedding the PLCA Reconciliation Sublayer. See "10BASE-T1S PLCA Management Registers" at https://www.opensig.org/about/specifications/. When set, the optional ``ETHTOOL_A_PLCA_ENABLED`` attribute indicates the @@ -1997,7 +1997,7 @@ Request contents: ``ETHTOOL_A_PLCA_ENABLED`` u8 PLCA Admin State ``ETHTOOL_A_PLCA_NODE_ID`` u8 PLCA unique local node ID ``ETHTOOL_A_PLCA_NODE_CNT`` u8 Number of PLCA nodes on the - netkork, including the + network, including the coordinator ``ETHTOOL_A_PLCA_TO_TMR`` u8 Transmit Opportunity Timer value in bit-times (BT) From be034ee6c33dcd7c8dc7160266acb50c897cc2ea Mon Sep 17 00:00:00 2001 From: Frank Li Date: Sun, 11 Aug 2024 14:40:49 -0400 Subject: [PATCH 118/385] dt-bindings: net: fsl,qoriq-mc-dpmac: using unevaluatedProperties Replace additionalProperties with unevaluatedProperties because it have allOf: $ref: ethernet-controller.yaml#. Remove all properties, which already defined in ethernet-controller.yaml. Fixed below CHECK_DTBS warnings: arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dtb: fsl-mc@80c000000: dpmacs:ethernet@11: 'fixed-link' does not match any of the regexes: 'pinctrl-[0-9]+' from schema $id: http://devicetree.org/schemas/misc/fsl,qoriq-mc.yaml# Signed-off-by: Frank Li Reviewed-by: Krzysztof Kozlowski Link: https://patch.msgid.link/20240811184049.3759195-1-Frank.Li@nxp.com Signed-off-by: Jakub Kicinski --- .../devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml index a1b71b35319e7..f19c4fa66f18b 100644 --- a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml +++ b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml @@ -24,24 +24,16 @@ properties: maxItems: 1 description: The DPMAC number - phy-handle: true - - phy-connection-type: true - - phy-mode: true - pcs-handle: maxItems: 1 description: A reference to a node representing a PCS PHY device found on the internal MDIO bus. - managed: true - required: - reg -additionalProperties: false +unevaluatedProperties: false examples: - | From 58c98d0cd4f8899f517ba1f0255d2aac7666a002 Mon Sep 17 00:00:00 2001 From: Ziwei Xiao Date: Mon, 12 Aug 2024 15:20:12 -0700 Subject: [PATCH 119/385] gve: Add RSS device option Add a device option to inform the driver about the hash key size and hash table size used by the device. This information will be stored and made available for RSS ethtool operations. Signed-off-by: Ziwei Xiao Signed-off-by: Praveen Kaligineedi Reviewed-by: Praveen Kaligineedi Reviewed-by: Harshitha Ramamurthy Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20240812222013.1503584-2-pkaligineedi@google.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/google/gve/gve.h | 3 ++ drivers/net/ethernet/google/gve/gve_adminq.c | 36 ++++++++++++++++++-- drivers/net/ethernet/google/gve/gve_adminq.h | 15 +++++++- 3 files changed, 51 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 84ac004d39533..6c21f3c53619c 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -831,6 +831,9 @@ struct gve_priv { u32 num_flow_rules; struct gve_flow_rules_cache flow_rules_cache; + + u16 rss_key_size; + u16 rss_lut_size; }; enum gve_service_task_flags_bit { diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index c5bbc1b7524ed..b5c801d2f8b58 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -45,6 +45,7 @@ void gve_parse_device_option(struct gve_priv *priv, struct gve_device_option_dqo_qpl **dev_op_dqo_qpl, struct gve_device_option_buffer_sizes **dev_op_buffer_sizes, struct gve_device_option_flow_steering **dev_op_flow_steering, + struct gve_device_option_rss_config **dev_op_rss_config, struct gve_device_option_modify_ring **dev_op_modify_ring) { u32 req_feat_mask = be32_to_cpu(option->required_features_mask); @@ -207,6 +208,23 @@ void gve_parse_device_option(struct gve_priv *priv, "Flow Steering"); *dev_op_flow_steering = (void *)(option + 1); break; + case GVE_DEV_OPT_ID_RSS_CONFIG: + if (option_length < sizeof(**dev_op_rss_config) || + req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_RSS_CONFIG) { + dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT, + "RSS config", + (int)sizeof(**dev_op_rss_config), + GVE_DEV_OPT_REQ_FEAT_MASK_RSS_CONFIG, + option_length, req_feat_mask); + break; + } + + if (option_length > sizeof(**dev_op_rss_config)) + dev_warn(&priv->pdev->dev, + GVE_DEVICE_OPTION_TOO_BIG_FMT, + "RSS config"); + *dev_op_rss_config = (void *)(option + 1); + break; default: /* If we don't recognize the option just continue * without doing anything. @@ -227,6 +245,7 @@ gve_process_device_options(struct gve_priv *priv, struct gve_device_option_dqo_qpl **dev_op_dqo_qpl, struct gve_device_option_buffer_sizes **dev_op_buffer_sizes, struct gve_device_option_flow_steering **dev_op_flow_steering, + struct gve_device_option_rss_config **dev_op_rss_config, struct gve_device_option_modify_ring **dev_op_modify_ring) { const int num_options = be16_to_cpu(descriptor->num_device_options); @@ -249,7 +268,8 @@ gve_process_device_options(struct gve_priv *priv, dev_op_gqi_rda, dev_op_gqi_qpl, dev_op_dqo_rda, dev_op_jumbo_frames, dev_op_dqo_qpl, dev_op_buffer_sizes, - dev_op_flow_steering, dev_op_modify_ring); + dev_op_flow_steering, dev_op_rss_config, + dev_op_modify_ring); dev_opt = next_opt; } @@ -867,6 +887,8 @@ static void gve_enable_supported_features(struct gve_priv *priv, *dev_op_buffer_sizes, const struct gve_device_option_flow_steering *dev_op_flow_steering, + const struct gve_device_option_rss_config + *dev_op_rss_config, const struct gve_device_option_modify_ring *dev_op_modify_ring) { @@ -931,6 +953,14 @@ static void gve_enable_supported_features(struct gve_priv *priv, priv->max_flow_rules); } } + + if (dev_op_rss_config && + (supported_features_mask & GVE_SUP_RSS_CONFIG_MASK)) { + priv->rss_key_size = + be16_to_cpu(dev_op_rss_config->hash_key_size); + priv->rss_lut_size = + be16_to_cpu(dev_op_rss_config->hash_lut_size); + } } int gve_adminq_describe_device(struct gve_priv *priv) @@ -939,6 +969,7 @@ int gve_adminq_describe_device(struct gve_priv *priv) struct gve_device_option_buffer_sizes *dev_op_buffer_sizes = NULL; struct gve_device_option_jumbo_frames *dev_op_jumbo_frames = NULL; struct gve_device_option_modify_ring *dev_op_modify_ring = NULL; + struct gve_device_option_rss_config *dev_op_rss_config = NULL; struct gve_device_option_gqi_rda *dev_op_gqi_rda = NULL; struct gve_device_option_gqi_qpl *dev_op_gqi_qpl = NULL; struct gve_device_option_dqo_rda *dev_op_dqo_rda = NULL; @@ -973,6 +1004,7 @@ int gve_adminq_describe_device(struct gve_priv *priv) &dev_op_jumbo_frames, &dev_op_dqo_qpl, &dev_op_buffer_sizes, &dev_op_flow_steering, + &dev_op_rss_config, &dev_op_modify_ring); if (err) goto free_device_descriptor; @@ -1035,7 +1067,7 @@ int gve_adminq_describe_device(struct gve_priv *priv) gve_enable_supported_features(priv, supported_features_mask, dev_op_jumbo_frames, dev_op_dqo_qpl, dev_op_buffer_sizes, dev_op_flow_steering, - dev_op_modify_ring); + dev_op_rss_config, dev_op_modify_ring); free_device_descriptor: dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus); diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index ed1370c9b1971..7d9ef9a12fef7 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -164,6 +164,14 @@ struct gve_device_option_flow_steering { static_assert(sizeof(struct gve_device_option_flow_steering) == 12); +struct gve_device_option_rss_config { + __be32 supported_features_mask; + __be16 hash_key_size; + __be16 hash_lut_size; +}; + +static_assert(sizeof(struct gve_device_option_rss_config) == 8); + /* Terminology: * * RDA - Raw DMA Addressing - Buffers associated with SKBs are directly DMA @@ -182,6 +190,7 @@ enum gve_dev_opt_id { GVE_DEV_OPT_ID_JUMBO_FRAMES = 0x8, GVE_DEV_OPT_ID_BUFFER_SIZES = 0xa, GVE_DEV_OPT_ID_FLOW_STEERING = 0xb, + GVE_DEV_OPT_ID_RSS_CONFIG = 0xe, }; enum gve_dev_opt_req_feat_mask { @@ -194,6 +203,7 @@ enum gve_dev_opt_req_feat_mask { GVE_DEV_OPT_REQ_FEAT_MASK_BUFFER_SIZES = 0x0, GVE_DEV_OPT_REQ_FEAT_MASK_MODIFY_RING = 0x0, GVE_DEV_OPT_REQ_FEAT_MASK_FLOW_STEERING = 0x0, + GVE_DEV_OPT_REQ_FEAT_MASK_RSS_CONFIG = 0x0, }; enum gve_sup_feature_mask { @@ -201,6 +211,7 @@ enum gve_sup_feature_mask { GVE_SUP_JUMBO_FRAMES_MASK = 1 << 2, GVE_SUP_BUFFER_SIZES_MASK = 1 << 4, GVE_SUP_FLOW_STEERING_MASK = 1 << 5, + GVE_SUP_RSS_CONFIG_MASK = 1 << 7, }; #define GVE_DEV_OPT_LEN_GQI_RAW_ADDRESSING 0x0 @@ -214,6 +225,7 @@ enum gve_driver_capbility { gve_driver_capability_dqo_rda = 3, gve_driver_capability_alt_miss_compl = 4, gve_driver_capability_flexible_buffer_size = 5, + gve_driver_capability_flexible_rss_size = 6, }; #define GVE_CAP1(a) BIT((int)a) @@ -226,7 +238,8 @@ enum gve_driver_capbility { GVE_CAP1(gve_driver_capability_gqi_rda) | \ GVE_CAP1(gve_driver_capability_dqo_rda) | \ GVE_CAP1(gve_driver_capability_alt_miss_compl) | \ - GVE_CAP1(gve_driver_capability_flexible_buffer_size)) + GVE_CAP1(gve_driver_capability_flexible_buffer_size) | \ + GVE_CAP1(gve_driver_capability_flexible_rss_size)) #define GVE_DRIVER_CAPABILITY_FLAGS2 0x0 #define GVE_DRIVER_CAPABILITY_FLAGS3 0x0 From fa46c456fa6ecc409cec43ac534b1a156bcef7b2 Mon Sep 17 00:00:00 2001 From: Jeroen de Borst Date: Mon, 12 Aug 2024 15:20:13 -0700 Subject: [PATCH 120/385] gve: Add RSS adminq commands and ethtool support Introduce adminq commands to configure and retrieve RSS settings from the device. Implement corresponding ethtool ops for user-level management. Signed-off-by: Jeroen de Borst Co-developed-by: Ziwei Xiao Signed-off-by: Ziwei Xiao Signed-off-by: Praveen Kaligineedi Reviewed-by: Praveen Kaligineedi Reviewed-by: Harshitha Ramamurthy Reviewed-by: Willem de Bruijn Reviewed-by: Hariprasad Kelam Link: https://patch.msgid.link/20240812222013.1503584-3-pkaligineedi@google.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/google/gve/gve.h | 2 + drivers/net/ethernet/google/gve/gve_adminq.c | 146 ++++++++++++++++++ drivers/net/ethernet/google/gve/gve_adminq.h | 44 ++++++ drivers/net/ethernet/google/gve/gve_ethtool.c | 44 +++++- 4 files changed, 235 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 6c21f3c53619c..09a85ed591431 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -784,6 +784,8 @@ struct gve_priv { u32 adminq_verify_driver_compatibility_cnt; u32 adminq_query_flow_rules_cnt; u32 adminq_cfg_flow_rule_cnt; + u32 adminq_cfg_rss_cnt; + u32 adminq_query_rss_cnt; /* Global stats */ u32 interface_up_cnt; /* count of times interface turned up since last reset */ diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index b5c801d2f8b58..e44e8b139633f 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -309,6 +309,8 @@ int gve_adminq_alloc(struct device *dev, struct gve_priv *priv) priv->adminq_get_ptype_map_cnt = 0; priv->adminq_query_flow_rules_cnt = 0; priv->adminq_cfg_flow_rule_cnt = 0; + priv->adminq_cfg_rss_cnt = 0; + priv->adminq_query_rss_cnt = 0; /* Setup Admin queue with the device */ if (priv->pdev->revision < 0x1) { @@ -554,6 +556,12 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv, case GVE_ADMINQ_CONFIGURE_FLOW_RULE: priv->adminq_cfg_flow_rule_cnt++; break; + case GVE_ADMINQ_CONFIGURE_RSS: + priv->adminq_cfg_rss_cnt++; + break; + case GVE_ADMINQ_QUERY_RSS: + priv->adminq_query_rss_cnt++; + break; default: dev_err(&priv->pdev->dev, "unknown AQ command opcode %d\n", opcode); } @@ -1280,6 +1288,81 @@ int gve_adminq_reset_flow_rules(struct gve_priv *priv) return gve_adminq_configure_flow_rule(priv, &flow_rule_cmd); } +int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh) +{ + dma_addr_t lut_bus = 0, key_bus = 0; + u16 key_size = 0, lut_size = 0; + union gve_adminq_command cmd; + __be32 *lut = NULL; + u8 hash_alg = 0; + u8 *key = NULL; + int err = 0; + u16 i; + + switch (rxfh->hfunc) { + case ETH_RSS_HASH_NO_CHANGE: + break; + case ETH_RSS_HASH_TOP: + hash_alg = ETH_RSS_HASH_TOP; + break; + default: + return -EOPNOTSUPP; + } + + if (rxfh->indir) { + lut_size = priv->rss_lut_size; + lut = dma_alloc_coherent(&priv->pdev->dev, + lut_size * sizeof(*lut), + &lut_bus, GFP_KERNEL); + if (!lut) + return -ENOMEM; + + for (i = 0; i < priv->rss_lut_size; i++) + lut[i] = cpu_to_be32(rxfh->indir[i]); + } + + if (rxfh->key) { + key_size = priv->rss_key_size; + key = dma_alloc_coherent(&priv->pdev->dev, + key_size, &key_bus, GFP_KERNEL); + if (!key) { + err = -ENOMEM; + goto out; + } + + memcpy(key, rxfh->key, key_size); + } + + /* Zero-valued fields in the cmd.configure_rss instruct the device to + * not update those fields. + */ + memset(&cmd, 0, sizeof(cmd)); + cmd.opcode = cpu_to_be32(GVE_ADMINQ_CONFIGURE_RSS); + cmd.configure_rss = (struct gve_adminq_configure_rss) { + .hash_types = cpu_to_be16(BIT(GVE_RSS_HASH_TCPV4) | + BIT(GVE_RSS_HASH_UDPV4) | + BIT(GVE_RSS_HASH_TCPV6) | + BIT(GVE_RSS_HASH_UDPV6)), + .hash_alg = hash_alg, + .hash_key_size = cpu_to_be16(key_size), + .hash_lut_size = cpu_to_be16(lut_size), + .hash_key_addr = cpu_to_be64(key_bus), + .hash_lut_addr = cpu_to_be64(lut_bus), + }; + + err = gve_adminq_execute_cmd(priv, &cmd); + +out: + if (lut) + dma_free_coherent(&priv->pdev->dev, + lut_size * sizeof(*lut), + lut, lut_bus); + if (key) + dma_free_coherent(&priv->pdev->dev, + key_size, key, key_bus); + return err; +} + /* In the dma memory that the driver allocated for the device to query the flow rules, the device * will first write it with a struct of gve_query_flow_rules_descriptor. Next to it, the device * will write an array of rules or rule ids with the count that specified in the descriptor. @@ -1357,3 +1440,66 @@ int gve_adminq_query_flow_rules(struct gve_priv *priv, u16 query_opcode, u32 sta dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus); return err; } + +static int gve_adminq_process_rss_query(struct gve_priv *priv, + struct gve_query_rss_descriptor *descriptor, + struct ethtool_rxfh_param *rxfh) +{ + u32 total_memory_length; + u16 hash_lut_length; + void *rss_info_addr; + __be32 *lut; + u16 i; + + total_memory_length = be32_to_cpu(descriptor->total_length); + hash_lut_length = priv->rss_lut_size * sizeof(*rxfh->indir); + + if (sizeof(*descriptor) + priv->rss_key_size + hash_lut_length != total_memory_length) { + dev_err(&priv->dev->dev, + "rss query desc from device has invalid length parameter.\n"); + return -EINVAL; + } + + rxfh->hfunc = descriptor->hash_alg; + + rss_info_addr = (void *)(descriptor + 1); + if (rxfh->key) + memcpy(rxfh->key, rss_info_addr, priv->rss_key_size); + + rss_info_addr += priv->rss_key_size; + lut = (__be32 *)rss_info_addr; + if (rxfh->indir) { + for (i = 0; i < priv->rss_lut_size; i++) + rxfh->indir[i] = be32_to_cpu(lut[i]); + } + + return 0; +} + +int gve_adminq_query_rss_config(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh) +{ + struct gve_query_rss_descriptor *descriptor; + union gve_adminq_command cmd; + dma_addr_t descriptor_bus; + int err = 0; + + descriptor = dma_pool_alloc(priv->adminq_pool, GFP_KERNEL, &descriptor_bus); + if (!descriptor) + return -ENOMEM; + + memset(&cmd, 0, sizeof(cmd)); + cmd.opcode = cpu_to_be32(GVE_ADMINQ_QUERY_RSS); + cmd.query_rss = (struct gve_adminq_query_rss) { + .available_length = cpu_to_be64(GVE_ADMINQ_BUFFER_SIZE), + .rss_descriptor_addr = cpu_to_be64(descriptor_bus), + }; + err = gve_adminq_execute_cmd(priv, &cmd); + if (err) + goto out; + + err = gve_adminq_process_rss_query(priv, descriptor, rxfh); + +out: + dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus); + return err; +} diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index 7d9ef9a12fef7..863683de96942 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -20,12 +20,14 @@ enum gve_adminq_opcodes { GVE_ADMINQ_DESTROY_TX_QUEUE = 0x7, GVE_ADMINQ_DESTROY_RX_QUEUE = 0x8, GVE_ADMINQ_DECONFIGURE_DEVICE_RESOURCES = 0x9, + GVE_ADMINQ_CONFIGURE_RSS = 0xA, GVE_ADMINQ_SET_DRIVER_PARAMETER = 0xB, GVE_ADMINQ_REPORT_STATS = 0xC, GVE_ADMINQ_REPORT_LINK_SPEED = 0xD, GVE_ADMINQ_GET_PTYPE_MAP = 0xE, GVE_ADMINQ_VERIFY_DRIVER_COMPATIBILITY = 0xF, GVE_ADMINQ_QUERY_FLOW_RULES = 0x10, + GVE_ADMINQ_QUERY_RSS = 0x12, /* For commands that are larger than 56 bytes */ GVE_ADMINQ_EXTENDED_COMMAND = 0xFF, @@ -522,6 +524,44 @@ struct gve_adminq_query_flow_rules { static_assert(sizeof(struct gve_adminq_query_flow_rules) == 24); +enum gve_rss_hash_type { + GVE_RSS_HASH_IPV4, + GVE_RSS_HASH_TCPV4, + GVE_RSS_HASH_IPV6, + GVE_RSS_HASH_IPV6_EX, + GVE_RSS_HASH_TCPV6, + GVE_RSS_HASH_TCPV6_EX, + GVE_RSS_HASH_UDPV4, + GVE_RSS_HASH_UDPV6, + GVE_RSS_HASH_UDPV6_EX, +}; + +struct gve_adminq_configure_rss { + __be16 hash_types; + u8 hash_alg; + u8 reserved; + __be16 hash_key_size; + __be16 hash_lut_size; + __be64 hash_key_addr; + __be64 hash_lut_addr; +}; + +static_assert(sizeof(struct gve_adminq_configure_rss) == 24); + +struct gve_query_rss_descriptor { + __be32 total_length; + __be16 hash_types; + u8 hash_alg; + u8 reserved; +}; + +struct gve_adminq_query_rss { + __be64 available_length; + __be64 rss_descriptor_addr; +}; + +static_assert(sizeof(struct gve_adminq_query_rss) == 16); + union gve_adminq_command { struct { __be32 opcode; @@ -543,6 +583,8 @@ union gve_adminq_command { struct gve_adminq_verify_driver_compatibility verify_driver_compatibility; struct gve_adminq_query_flow_rules query_flow_rules; + struct gve_adminq_configure_rss configure_rss; + struct gve_adminq_query_rss query_rss; struct gve_adminq_extended_command extended_command; }; }; @@ -581,6 +623,8 @@ int gve_adminq_add_flow_rule(struct gve_priv *priv, struct gve_adminq_flow_rule int gve_adminq_del_flow_rule(struct gve_priv *priv, u32 loc); int gve_adminq_reset_flow_rules(struct gve_priv *priv); int gve_adminq_query_flow_rules(struct gve_priv *priv, u16 query_opcode, u32 starting_loc); +int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh); +int gve_adminq_query_rss_config(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh); struct gve_ptype_lut; int gve_adminq_get_ptype_map_dqo(struct gve_priv *priv, diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 5a8b490ab3ad0..bdfc6e77b2af5 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -75,7 +75,8 @@ static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = { "adminq_destroy_tx_queue_cnt", "adminq_destroy_rx_queue_cnt", "adminq_dcfg_device_resources_cnt", "adminq_set_driver_parameter_cnt", "adminq_report_stats_cnt", "adminq_report_link_speed_cnt", "adminq_get_ptype_map_cnt", - "adminq_query_flow_rules", "adminq_cfg_flow_rule", + "adminq_query_flow_rules", "adminq_cfg_flow_rule", "adminq_cfg_rss_cnt", + "adminq_query_rss_cnt", }; static const char gve_gstrings_priv_flags[][ETH_GSTRING_LEN] = { @@ -453,6 +454,8 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = priv->adminq_get_ptype_map_cnt; data[i++] = priv->adminq_query_flow_rules_cnt; data[i++] = priv->adminq_cfg_flow_rule_cnt; + data[i++] = priv->adminq_cfg_rss_cnt; + data[i++] = priv->adminq_query_rss_cnt; } static void gve_get_channels(struct net_device *netdev, @@ -838,6 +841,41 @@ static int gve_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, u return err; } +static u32 gve_get_rxfh_key_size(struct net_device *netdev) +{ + struct gve_priv *priv = netdev_priv(netdev); + + return priv->rss_key_size; +} + +static u32 gve_get_rxfh_indir_size(struct net_device *netdev) +{ + struct gve_priv *priv = netdev_priv(netdev); + + return priv->rss_lut_size; +} + +static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh) +{ + struct gve_priv *priv = netdev_priv(netdev); + + if (!priv->rss_key_size || !priv->rss_lut_size) + return -EOPNOTSUPP; + + return gve_adminq_query_rss_config(priv, rxfh); +} + +static int gve_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack) +{ + struct gve_priv *priv = netdev_priv(netdev); + + if (!priv->rss_key_size || !priv->rss_lut_size) + return -EOPNOTSUPP; + + return gve_adminq_configure_rss(priv, rxfh); +} + const struct ethtool_ops gve_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS, .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT, @@ -851,6 +889,10 @@ const struct ethtool_ops gve_ethtool_ops = { .get_channels = gve_get_channels, .set_rxnfc = gve_set_rxnfc, .get_rxnfc = gve_get_rxnfc, + .get_rxfh_indir_size = gve_get_rxfh_indir_size, + .get_rxfh_key_size = gve_get_rxfh_key_size, + .get_rxfh = gve_get_rxfh, + .set_rxfh = gve_set_rxfh, .get_link = ethtool_op_get_link, .get_coalesce = gve_get_coalesce, .set_coalesce = gve_set_coalesce, From ed4290f39f417793928630e85c26411db233d841 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 10 Aug 2024 23:39:04 +0200 Subject: [PATCH 121/385] net: netconsole: Constify struct config_item_type 'struct config_item_type' is not modified in this driver. This structure is only used with config_group_init_type_name() which takes a const struct config_item_type* as a 3rd argument. This also makes things consistent with 'netconsole_target_type' witch is already const. Constifying this structure moves some data to a read-only section, so increase overall security, especially when the structure holds some function pointers. On a x86_64, with allmodconfig: Before: ====== text data bss dec hex filename 33007 3952 1312 38271 957f drivers/net/netconsole.o After: ===== text data bss dec hex filename 33071 3888 1312 38271 957f drivers/net/netconsole.o Signed-off-by: Christophe JAILLET Reviewed-by: Breno Leitao Link: https://patch.msgid.link/9c205b2b4bdb09fc9e9d2cb2f2936ec053da1b1b.1723325900.git.christophe.jaillet@wanadoo.fr Signed-off-by: Jakub Kicinski --- drivers/net/netconsole.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 43c29b15adbfa..72384c1ecc5ce 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -825,7 +825,7 @@ static struct configfs_group_operations userdata_ops = { .drop_item = userdatum_drop, }; -static struct config_item_type userdata_type = { +static const struct config_item_type userdata_type = { .ct_item_ops = &userdatum_ops, .ct_group_ops = &userdata_ops, .ct_attrs = userdata_attrs, From 4374a1fe580a14f6152752390c678d90311df247 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cs=C3=B3k=C3=A1s=2C=20Bence?= Date: Mon, 12 Aug 2024 11:47:13 +0200 Subject: [PATCH 122/385] net: fec: Move `fec_ptp_read()` to the top of the file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This function is used in `fec_ptp_enable_pps()` through struct cyclecounter read(). Moving the declaration makes it clearer, what's happening. Suggested-by: Frank Li Link: https://lore.kernel.org/netdev/20240805144754.2384663-1-csokas.bence@prolan.hu/T/#ma6c21ad264016c24612048b1483769eaff8cdf20 Signed-off-by: Csókás, Bence Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20240812094713.2883476-1-csokas.bence@prolan.hu Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/fec_ptp.c | 50 ++++++++++++------------ 1 file changed, 25 insertions(+), 25 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 2e4f3e1782a25..7f4ccd1ade5b1 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -90,6 +90,30 @@ #define FEC_PTP_MAX_NSEC_PERIOD 4000000000ULL #define FEC_PTP_MAX_NSEC_COUNTER 0x80000000ULL +/** + * fec_ptp_read - read raw cycle counter (to be used by time counter) + * @cc: the cyclecounter structure + * + * this function reads the cyclecounter registers and is called by the + * cyclecounter structure used to construct a ns counter from the + * arbitrary fixed point registers + */ +static u64 fec_ptp_read(const struct cyclecounter *cc) +{ + struct fec_enet_private *fep = + container_of(cc, struct fec_enet_private, cc); + u32 tempval; + + tempval = readl(fep->hwp + FEC_ATIME_CTRL); + tempval |= FEC_T_CTRL_CAPTURE; + writel(tempval, fep->hwp + FEC_ATIME_CTRL); + + if (fep->quirks & FEC_QUIRK_BUG_CAPTURE) + udelay(1); + + return readl(fep->hwp + FEC_ATIME); +} + /** * fec_ptp_enable_pps * @fep: the fec_enet_private structure handle @@ -136,7 +160,7 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable) * NSEC_PER_SEC - ts.tv_nsec. Add the remaining nanoseconds * to current timer would be next second. */ - tempval = fep->cc.read(&fep->cc); + tempval = fec_ptp_read(&fep->cc); /* Convert the ptp local counter to 1588 timestamp */ ns = timecounter_cyc2time(&fep->tc, tempval); ts = ns_to_timespec64(ns); @@ -271,30 +295,6 @@ static enum hrtimer_restart fec_ptp_pps_perout_handler(struct hrtimer *timer) return HRTIMER_NORESTART; } -/** - * fec_ptp_read - read raw cycle counter (to be used by time counter) - * @cc: the cyclecounter structure - * - * this function reads the cyclecounter registers and is called by the - * cyclecounter structure used to construct a ns counter from the - * arbitrary fixed point registers - */ -static u64 fec_ptp_read(const struct cyclecounter *cc) -{ - struct fec_enet_private *fep = - container_of(cc, struct fec_enet_private, cc); - u32 tempval; - - tempval = readl(fep->hwp + FEC_ATIME_CTRL); - tempval |= FEC_T_CTRL_CAPTURE; - writel(tempval, fep->hwp + FEC_ATIME_CTRL); - - if (fep->quirks & FEC_QUIRK_BUG_CAPTURE) - udelay(1); - - return readl(fep->hwp + FEC_ATIME); -} - /** * fec_ptp_start_cyclecounter - create the cycle counter from hw * @ndev: network device From 713ebaed68d88121cbaf5e74104e2290a9ea74bd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cs=C3=B3k=C3=A1s=2C=20Bence?= Date: Mon, 12 Aug 2024 11:47:15 +0200 Subject: [PATCH 123/385] net: fec: Remove duplicated code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit `fec_ptp_pps_perout()` reimplements logic already in `fec_ptp_read()`. Replace with function call. Signed-off-by: Csókás, Bence Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20240812094713.2883476-2-csokas.bence@prolan.hu Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/fec_ptp.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 7f4ccd1ade5b1..4cffda363a148 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -235,13 +235,7 @@ static int fec_ptp_pps_perout(struct fec_enet_private *fep) timecounter_read(&fep->tc); /* Get the current ptp hardware time counter */ - temp_val = readl(fep->hwp + FEC_ATIME_CTRL); - temp_val |= FEC_T_CTRL_CAPTURE; - writel(temp_val, fep->hwp + FEC_ATIME_CTRL); - if (fep->quirks & FEC_QUIRK_BUG_CAPTURE) - udelay(1); - - ptp_hc = readl(fep->hwp + FEC_ATIME); + ptp_hc = fec_ptp_read(&fep->cc); /* Convert the ptp local counter to 1588 timestamp */ curr_time = timecounter_cyc2time(&fep->tc, ptp_hc); From 29cabacef1024b39506d3acd18cb2e558832bbaf Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Mon, 12 Aug 2024 12:24:13 +0100 Subject: [PATCH 124/385] net: mvneta: Use __be16 for l3_proto parameter of mvneta_txq_desc_csum() The value passed as the l3_proto argument of mvneta_txq_desc_csum() is __be16. And mvneta_txq_desc_csum uses this parameter as a __be16 value. So use __be16 as the type for the parameter, rather than type with host byte order. Flagged by Sparse as: .../mvneta.c:1796:25: warning: restricted __be16 degrades to integer .../mvneta.c:1979:45: warning: incorrect type in argument 2 (different base types) .../mvneta.c:1979:45: expected int l3_proto .../mvneta.c:1979:45: got restricted __be16 [usertype] l3_proto No functional change intended. Flagged by Sparse. Signed-off-by: Simon Horman Reviewed-by: Marcin Wojtas Link: https://patch.msgid.link/20240812-mvneta-be16-v1-1-e1ea12234230@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/marvell/mvneta.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 41894834fb53c..d72b2d5f96db8 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1781,7 +1781,7 @@ static int mvneta_txq_sent_desc_proc(struct mvneta_port *pp, } /* Set TXQ descriptors fields relevant for CSUM calculation */ -static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto, +static u32 mvneta_txq_desc_csum(int l3_offs, __be16 l3_proto, int ip_hdr_len, int l4_proto) { u32 command; From 712f585ab8b2cc2ff4e441b14a4907f764d78f2b Mon Sep 17 00:00:00 2001 From: Enguerrand de Ribaucourt Date: Mon, 12 Aug 2024 12:43:47 +0000 Subject: [PATCH 125/385] net: dsa: microchip: ksz9477: unwrap URL in comment Keep the URL in a single line for easier copy-pasting. Signed-off-by: Enguerrand de Ribaucourt Reviewed-by: Andrew Lunn Acked-by: Arun Ramadoss Link: https://patch.msgid.link/20240812124346.597702-1-enguerrand.de-ribaucourt@savoirfairelinux.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/microchip/ksz9477.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 1e2293aa00dc9..755de092b2c2c 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -439,8 +439,7 @@ static int ksz9477_half_duplex_monitor(struct ksz_device *dev, int port, * half-duplex mode. The switch might not be able to communicate anymore * in these states. If you see this message, please read the * errata-sheet for more information: - * https://ww1.microchip.com/downloads/aemDocuments/documents - * /UNG/ProductDocuments/Errata/KSZ9477S-Errata-DS80000754.pdf + * https://ww1.microchip.com/downloads/aemDocuments/documents/UNG/ProductDocuments/Errata/KSZ9477S-Errata-DS80000754.pdf * To workaround this issue, half-duplex mode should be avoided. * A software reset could be implemented to recover from this state. */ From 2984e69a24affc8e5624069b7bb44593e09037e8 Mon Sep 17 00:00:00 2001 From: Moon Yeounsu Date: Sat, 10 Aug 2024 23:15:02 +0900 Subject: [PATCH 126/385] net: ethernet: dlink: replace deprecated macro Macro `SIMPLE_DEV_PM_OPS()` is deprecated. This patch replaces `SIMPLE_DEV_PM_OPS()` with `DEFINE_SIMPLE_DEV_PM_OPS()` currently used. Expanded results are the same since remaining member is initialized as zero (NULL): static SIMPLE_DEV_PM_OPS(rio_pm_ops, rio_suspend, rio_resume); Expanded to: static const struct dev_pm_ops __attribute__((__unused__)) rio_pm_ops = { .suspend = ((1) ? ((rio_suspend)) : ((void *)0)), .resume = ((1) ? ((rio_resume)) : ((void *)0)), .freeze = ((1) ? ((rio_suspend)) : ((void *)0)), .thaw = ((1) ? ((rio_resume)) : ((void *)0)), .poweroff = ((1) ? ((rio_suspend)) : ((void *)0)), .restore = ((1) ? ((rio_resume)) : ((void *)0)), }; static DEFINE_SIMPLE_DEV_PM_OPS(rio_pm_ops, rio_suspend, rio_resume); Expanded to: static const struct dev_pm_ops rio_pm_ops = { .suspend = ((1) ? ((rio_suspend)) : ((void *)0)), .resume = ((1) ? ((rio_resume)) : ((void *)0)), .freeze = ((1) ? ((rio_suspend)) : ((void *)0)), .thaw = ((1) ? ((rio_resume)) : ((void *)0)), .poweroff = ((1) ? ((rio_suspend)) : ((void *)0)), .restore = ((1) ? ((rio_resume)) : ((void *)0)), .runtime_suspend = ((void *)0), .runtime_resume = ((void *)0), .runtime_idle = ((void *)0), }; Signed-off-by: Moon Yeounsu Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/dlink/dl2k.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index 7bfeae04b52ba..d0ea926078706 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -1842,7 +1842,7 @@ static int rio_resume(struct device *device) return 0; } -static SIMPLE_DEV_PM_OPS(rio_pm_ops, rio_suspend, rio_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(rio_pm_ops, rio_suspend, rio_resume); #define RIO_PM_OPS (&rio_pm_ops) #else From ffff7ee843c351ce71d6e0d52f0f20bea35e18c9 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 13 Aug 2024 15:32:55 +0100 Subject: [PATCH 127/385] bnxt_en: Extend maximum length of version string by 1 byte This corrects an out-by-one error in the maximum length of the package version string. The size argument of snprintf includes space for the trailing '\0' byte, so there is no need to allow extra space for it by reducing the value of the size argument by 1. Found by inspection. Compile tested only. Signed-off-by: Simon Horman Reviewed-by: Michael Chan Link: https://patch.msgid.link/20240813-bnxt-str-v2-1-872050a157e7@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 61d6afc3cacb7..39eed5831e3ab 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -4161,7 +4161,7 @@ static void bnxt_get_pkgver(struct net_device *dev) if (!bnxt_get_pkginfo(dev, buf, sizeof(buf))) { len = strlen(bp->fw_ver_str); - snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len - 1, + snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len, "/pkg %s", buf); } } From 1418e9ab3e2e2f3aad3b1f93e9e4472160132755 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 13 Aug 2024 15:32:56 +0100 Subject: [PATCH 128/385] bnxt_en: avoid truncation of per rx run debugfs filename Although it seems unlikely in practice - there would need to be rx ring indexes greater than 10^10 - it is theoretically possible for the filename of per rx ring debugfs files to be truncated. This is because although a 16 byte buffer is provided, the length of the filename is restricted to 10 bytes. Remove this restriction and allow the entire buffer to be used. Also reduce the buffer to 12 bytes, which is sufficient. Given that the range of rx ring indexes likely much smaller than the maximum range of a 32-bit signed integer, a smaller buffer could be used, with some further changes. But this change seems simple, robust, and has minimal stack overhead. Flagged by gcc-14: .../bnxt_debugfs.c: In function 'bnxt_debug_dev_init': drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c:69:30: warning: '%d' directive output may be truncated writing between 1 and 11 bytes into a region of size 10 [-Wformat-truncation=] 69 | snprintf(qname, 10, "%d", ring_idx); | ^~ In function 'debugfs_dim_ring_init', inlined from 'bnxt_debug_dev_init' at .../bnxt_debugfs.c:87:4: .../bnxt_debugfs.c:69:29: note: directive argument in the range [-2147483643, 2147483646] 69 | snprintf(qname, 10, "%d", ring_idx); | ^~~~ .../bnxt_debugfs.c:69:9: note: 'snprintf' output between 2 and 12 bytes into a destination of size 10 69 | snprintf(qname, 10, "%d", ring_idx); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Compile tested only Signed-off-by: Simon Horman Reviewed-by: Michael Chan Link: https://patch.msgid.link/20240813-bnxt-str-v2-2-872050a157e7@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c index 156c2404854fc..127b7015f6762 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c @@ -64,9 +64,9 @@ static const struct file_operations debugfs_dim_fops = { static void debugfs_dim_ring_init(struct dim *dim, int ring_idx, struct dentry *dd) { - static char qname[16]; + static char qname[12]; - snprintf(qname, 10, "%d", ring_idx); + snprintf(qname, sizeof(qname), "%d", ring_idx); debugfs_create_file(qname, 0600, dd, dim, &debugfs_dim_fops); } From 216203bdc2280d8fc5baf60707eee2051de1426e Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Aug 2024 16:15:02 -0600 Subject: [PATCH 129/385] UAPI: net/sched: Use __struct_group() in flex struct tc_u32_sel Use the `__struct_group()` helper to create a new tagged `struct tc_u32_sel_hdr`. This structure groups together all the members of the flexible `struct tc_u32_sel` except the flexible array. As a result, the array is effectively separated from the rest of the members without modifying the memory layout of the flexible structure. This new tagged struct will be used to fix problematic declarations of middle-flex-arrays in composite structs[1]. [1] https://git.kernel.org/linus/d88cabfd9abc Signed-off-by: Gustavo A. R. Silva Link: https://patch.msgid.link/e59fe833564ddc5b2cc83056a4c504be887d6193.1723586870.git.gustavoars@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/pkt_cls.h | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index d36d9cdf0c008..2c32080416b5a 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -246,16 +246,19 @@ struct tc_u32_key { }; struct tc_u32_sel { - unsigned char flags; - unsigned char offshift; - unsigned char nkeys; - - __be16 offmask; - __u16 off; - short offoff; - - short hoff; - __be32 hmask; + /* New members MUST be added within the __struct_group() macro below. */ + __struct_group(tc_u32_sel_hdr, hdr, /* no attrs */, + unsigned char flags; + unsigned char offshift; + unsigned char nkeys; + + __be16 offmask; + __u16 off; + short offoff; + + short hoff; + __be32 hmask; + ); struct tc_u32_key keys[]; }; From 6c5cdabb3ec325f1846dad72f520814bbda79dca Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 13 Aug 2024 16:15:31 -0600 Subject: [PATCH 130/385] cxgb4: Avoid -Wflex-array-member-not-at-end warning -Wflex-array-member-not-at-end was introduced in GCC-14, and we are getting ready to enable it, globally. Change the type of the middle struct member currently causing trouble from `struct tc_u32_sel` to `struct tc_u32_sel_hdr`. Fix the following warning: drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h:245:27: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end] Signed-off-by: Gustavo A. R. Silva Link: https://patch.msgid.link/97388e8a7990975aa56cf0ada211764c735c3432.1723586870.git.gustavoars@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h index 9050568a034cd..64663112cad8a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h @@ -242,7 +242,7 @@ struct cxgb4_next_header { * field's value to jump to next header such as IHL field * in IPv4 header. */ - struct tc_u32_sel sel; + struct tc_u32_sel_hdr sel; struct tc_u32_key key; /* location of jump to make */ const struct cxgb4_match_field *jump; From aae6b81260fd9a7224f7eb4fc440d625852245bb Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 12 Aug 2024 10:43:48 -0400 Subject: [PATCH 131/385] Bluetooth: HCI: Invert LE State quirk to be opt-out rather then opt-in This inverts the LE State quirk so by default we assume the controllers would report valid states rather than invalid which is how quirks normally behave, also this would result in HCI command failing it the LE States are really broken thus exposing the controllers that are really broken in this respect. Link: https://github.com/bluez/bluez/issues/584 Fixes: 220915857e29 ("Bluetooth: Adding driver and quirk defs for multi-role LE") Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btintel.c | 10 ---------- drivers/bluetooth/btintel_pcie.c | 3 --- drivers/bluetooth/btmtksdio.c | 3 --- drivers/bluetooth/btrtl.c | 1 - drivers/bluetooth/btusb.c | 4 ++-- drivers/bluetooth/hci_qca.c | 4 ++-- drivers/bluetooth/hci_vhci.c | 2 -- include/net/bluetooth/hci.h | 17 ++++++++++------- include/net/bluetooth/hci_core.h | 2 +- net/bluetooth/hci_event.c | 2 +- 10 files changed, 16 insertions(+), 32 deletions(-) diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 2ebc970e6573f..7d5e4de64e3ce 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -2945,9 +2945,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) INTEL_ROM_LEGACY_NO_WBS_SUPPORT)) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - if (ver.hw_variant == 0x08 && ver.fw_variant == 0x22) - set_bit(HCI_QUIRK_VALID_LE_STATES, - &hdev->quirks); err = btintel_legacy_rom_setup(hdev, &ver); break; @@ -2956,7 +2953,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) case 0x12: /* ThP */ case 0x13: /* HrP */ case 0x14: /* CcP */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); fallthrough; case 0x0c: /* WsP */ /* Apply the device specific HCI quirks @@ -3048,9 +3044,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) /* These variants don't seem to support LE Coded PHY */ set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks); - /* Set Valid LE States quirk */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, ver.hw_variant); @@ -3076,9 +3069,6 @@ static int btintel_setup_combined(struct hci_dev *hdev) */ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - /* Apply LE States quirk from solar onwards */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, INTEL_HW_VARIANT(ver_tlv.cnvi_bt)); diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index 0d1a0415557b2..1c7631f22c522 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -1180,9 +1180,6 @@ static int btintel_pcie_setup(struct hci_dev *hdev) */ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - /* Apply LE States quirk from solar onwards */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - /* Setup MSFT Extension support */ btintel_set_msft_opcode(hdev, INTEL_HW_VARIANT(ver_tlv.cnvi_bt)); diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c index 39d6898497a40..497e4c87f5be5 100644 --- a/drivers/bluetooth/btmtksdio.c +++ b/drivers/bluetooth/btmtksdio.c @@ -1148,9 +1148,6 @@ static int btmtksdio_setup(struct hci_dev *hdev) } } - /* Valid LE States quirk for MediaTek 7921 */ - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - break; case 0x7663: case 0x7668: diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index f2f37143c454d..fd7991ea76726 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -1287,7 +1287,6 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) case CHIP_ID_8852C: case CHIP_ID_8851B: case CHIP_ID_8852BT: - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); /* RTL8852C needs to transmit mSBC data continuously without diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index acdba5d77694f..51d9d4532dda4 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -3956,8 +3956,8 @@ static int btusb_probe(struct usb_interface *intf, if (id->driver_info & BTUSB_WIDEBAND_SPEECH) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - if (id->driver_info & BTUSB_VALID_LE_STATES) - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); + if (!(id->driver_info & BTUSB_VALID_LE_STATES)) + set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks); if (id->driver_info & BTUSB_DIGIANSWER) { data->cmdreq_type = USB_TYPE_VENDOR; diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 45adc1560d949..4b1ad7ea5b95a 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -2474,8 +2474,8 @@ static int qca_serdev_probe(struct serdev_device *serdev) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); - if (data->capabilities & QCA_CAP_VALID_LE_STATES) - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); + if (!(data->capabilities & QCA_CAP_VALID_LE_STATES)) + set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks); } return 0; diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index c4046f8f1985a..43e9ac5a3324e 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -425,8 +425,6 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) if (opcode & 0x80) set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks); - set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); - if (hci_register_dev(hdev) < 0) { BT_ERR("Can't register HCI device"); hci_free_dev(hdev); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index e372a88e8c3f6..d1d073089f384 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -206,14 +206,17 @@ enum { */ HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, - /* When this quirk is set, the controller has validated that - * LE states reported through the HCI_LE_READ_SUPPORTED_STATES are - * valid. This mechanism is necessary as many controllers have - * been seen has having trouble initiating a connectable - * advertisement despite the state combination being reported as - * supported. + /* When this quirk is set, the LE states reported through the + * HCI_LE_READ_SUPPORTED_STATES are invalid/broken. + * + * This mechanism is necessary as many controllers have been seen has + * having trouble initiating a connectable advertisement despite the + * state combination being reported as supported. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. */ - HCI_QUIRK_VALID_LE_STATES, + HCI_QUIRK_BROKEN_LE_STATES, /* When this quirk is set, then erroneous data reporting * is ignored. This is mainly due to the fact that the HCI diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 31020891fc68c..e449dba698f35 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -825,7 +825,7 @@ extern struct mutex hci_cb_list_lock; } while (0) #define hci_dev_le_state_simultaneous(hdev) \ - (test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) && \ + (!test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) && \ (hdev->le_states[4] & 0x08) && /* Central */ \ (hdev->le_states[4] & 0x40) && /* Peripheral */ \ (hdev->le_states[3] & 0x10)) /* Simultaneous */ diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index d0c118c47f6c9..1c82dcdf6e8fc 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5920,7 +5920,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, * while we have an existing one in peripheral role. */ if (hdev->conn_hash.le_num_peripheral > 0 && - (!test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) || + (test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) || !(hdev->le_states[3] & 0x10))) return NULL; From 932021a11805b9da4bd6abf66fe233cccd59fe0e Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 12 Aug 2024 11:22:08 -0400 Subject: [PATCH 132/385] Bluetooth: hci_core: Fix LE quote calculation Function hci_sched_le needs to update the respective counter variable inplace other the likes of hci_quote_sent would attempt to use the possible outdated value of conn->{le_cnt,acl_cnt}. Link: https://github.com/bluez/bluez/issues/915 Fixes: 73d80deb7bdf ("Bluetooth: prioritizing data over HCI") Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/hci_core.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 06da8ac13dca8..f25a21f532aa7 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -3664,19 +3664,19 @@ static void hci_sched_le(struct hci_dev *hdev) { struct hci_chan *chan; struct sk_buff *skb; - int quote, cnt, tmp; + int quote, *cnt, tmp; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, LE_LINK)) return; - cnt = hdev->le_pkts ? hdev->le_cnt : hdev->acl_cnt; + cnt = hdev->le_pkts ? &hdev->le_cnt : &hdev->acl_cnt; - __check_timeout(hdev, cnt, LE_LINK); + __check_timeout(hdev, *cnt, LE_LINK); - tmp = cnt; - while (cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { + tmp = *cnt; + while (*cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote-- && (skb = skb_peek(&chan->data_q))) { BT_DBG("chan %p skb %p len %d priority %u", chan, skb, @@ -3691,7 +3691,7 @@ static void hci_sched_le(struct hci_dev *hdev) hci_send_frame(hdev, skb); hdev->le_last_tx = jiffies; - cnt--; + (*cnt)--; chan->sent++; chan->conn->sent++; @@ -3701,12 +3701,7 @@ static void hci_sched_le(struct hci_dev *hdev) } } - if (hdev->le_pkts) - hdev->le_cnt = cnt; - else - hdev->acl_cnt = cnt; - - if (cnt != tmp) + if (*cnt != tmp) hci_prio_recalculate(hdev, LE_LINK); } From 28cd47f75185c4818b0fb1b46f2f02faaba96376 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Wed, 30 Aug 2023 15:08:06 -0700 Subject: [PATCH 133/385] Bluetooth: SMP: Fix assumption of Central always being Initiator SMP initiator role shall be considered the one that initiates the pairing procedure with SMP_CMD_PAIRING_REQ: BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 3, Part H page 1557: Figure 2.1: LE pairing phases Note that by sending SMP_CMD_SECURITY_REQ it doesn't change the role to be Initiator. Link: https://github.com/bluez/bluez/issues/567 Fixes: b28b4943660f ("Bluetooth: Add strict checks for allowed SMP PDUs") Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/smp.c | 144 ++++++++++++++++++++++---------------------- 1 file changed, 72 insertions(+), 72 deletions(-) diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 1e7ea3a4b7ef3..4f9fdf400584e 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -914,7 +914,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, * Confirms and the responder Enters the passkey. */ if (smp->method == OVERLAP) { - if (hcon->role == HCI_ROLE_MASTER) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp->method = CFM_PASSKEY; else smp->method = REQ_PASSKEY; @@ -964,7 +964,7 @@ static u8 smp_confirm(struct smp_chan *smp) smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp); - if (conn->hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM); else SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -980,7 +980,8 @@ static u8 smp_random(struct smp_chan *smp) int ret; bt_dev_dbg(conn->hcon->hdev, "conn %p %s", conn, - conn->hcon->out ? "initiator" : "responder"); + test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" : + "responder"); ret = smp_c1(smp->tk, smp->rrnd, smp->preq, smp->prsp, hcon->init_addr_type, &hcon->init_addr, @@ -994,7 +995,7 @@ static u8 smp_random(struct smp_chan *smp) return SMP_CONFIRM_FAILED; } - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { u8 stk[16]; __le64 rand = 0; __le16 ediv = 0; @@ -1256,14 +1257,15 @@ static void smp_distribute_keys(struct smp_chan *smp) rsp = (void *) &smp->prsp[1]; /* The responder sends its keys first */ - if (hcon->out && (smp->remote_key_dist & KEY_DIST_MASK)) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags) && + (smp->remote_key_dist & KEY_DIST_MASK)) { smp_allow_key_dist(smp); return; } req = (void *) &smp->preq[1]; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { keydist = &rsp->init_key_dist; *keydist &= req->init_key_dist; } else { @@ -1432,7 +1434,7 @@ static int sc_mackey_and_ltk(struct smp_chan *smp, u8 mackey[16], u8 ltk[16]) struct hci_conn *hcon = smp->conn->hcon; u8 *na, *nb, a[7], b[7]; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { na = smp->prnd; nb = smp->rrnd; } else { @@ -1460,7 +1462,7 @@ static void sc_dhkey_check(struct smp_chan *smp) a[6] = hcon->init_addr_type; b[6] = hcon->resp_addr_type; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local_addr = a; remote_addr = b; memcpy(io_cap, &smp->preq[1], 3); @@ -1539,7 +1541,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) /* The round is only complete when the initiator * receives pairing random. */ - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); if (smp->passkey_round == 20) @@ -1567,7 +1569,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); return 0; @@ -1578,7 +1580,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) case SMP_CMD_PUBLIC_KEY: default: /* Initiating device starts the round */ - if (!hcon->out) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return 0; bt_dev_dbg(hdev, "Starting passkey round %u", @@ -1623,7 +1625,7 @@ static int sc_user_reply(struct smp_chan *smp, u16 mgmt_op, __le32 passkey) } /* Initiator sends DHKey check first */ - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { sc_dhkey_check(smp); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); } else if (test_and_clear_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags)) { @@ -1746,7 +1748,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) struct smp_cmd_pairing rsp, *req = (void *) skb->data; struct l2cap_chan *chan = conn->smp; struct hci_dev *hdev = conn->hcon->hdev; - struct smp_chan *smp; + struct smp_chan *smp = chan->data; u8 key_size, auth, sec_level; int ret; @@ -1755,16 +1757,14 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*req)) return SMP_INVALID_PARAMS; - if (conn->hcon->role != HCI_ROLE_SLAVE) + if (smp && test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_CMD_NOTSUPP; - if (!chan->data) + if (!smp) { smp = smp_chan_create(conn); - else - smp = chan->data; - - if (!smp) - return SMP_UNSPECIFIED; + if (!smp) + return SMP_UNSPECIFIED; + } /* We didn't start the pairing, so match remote */ auth = req->auth_req & AUTH_REQ_MASK(hdev); @@ -1946,7 +1946,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*rsp)) return SMP_INVALID_PARAMS; - if (conn->hcon->role != HCI_ROLE_MASTER) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_CMD_NOTSUPP; skb_pull(skb, sizeof(*rsp)); @@ -2041,7 +2041,7 @@ static u8 sc_check_confirm(struct smp_chan *smp) if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY) return sc_passkey_round(smp, SMP_CMD_PAIRING_CONFIRM); - if (conn->hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -2063,7 +2063,7 @@ static int fixup_sc_false_positive(struct smp_chan *smp) u8 auth; /* The issue is only observed when we're in responder role */ - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_UNSPECIFIED; if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) { @@ -2099,7 +2099,8 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) struct hci_dev *hdev = hcon->hdev; bt_dev_dbg(hdev, "conn %p %s", conn, - hcon->out ? "initiator" : "responder"); + test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" : + "responder"); if (skb->len < sizeof(smp->pcnf)) return SMP_INVALID_PARAMS; @@ -2121,7 +2122,7 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) return ret; } - if (conn->hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -2156,7 +2157,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) if (!test_bit(SMP_FLAG_SC, &smp->flags)) return smp_random(smp); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { pkax = smp->local_pk; pkbx = smp->remote_pk; na = smp->prnd; @@ -2169,7 +2170,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) } if (smp->method == REQ_OOB) { - if (!hcon->out) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); @@ -2180,7 +2181,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY) return sc_passkey_round(smp, SMP_CMD_PAIRING_RANDOM); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { u8 cfm[16]; err = smp_f4(smp->tfm_cmac, smp->remote_pk, smp->local_pk, @@ -2221,7 +2222,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) return SMP_UNSPECIFIED; if (smp->method == REQ_OOB) { - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { sc_dhkey_check(smp); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); } @@ -2295,10 +2296,27 @@ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level, return false; } +static void smp_send_pairing_req(struct smp_chan *smp, __u8 auth) +{ + struct smp_cmd_pairing cp; + + if (smp->conn->hcon->type == ACL_LINK) + build_bredr_pairing_cmd(smp, &cp, NULL); + else + build_pairing_cmd(smp->conn, &cp, NULL, auth); + + smp->preq[0] = SMP_CMD_PAIRING_REQ; + memcpy(&smp->preq[1], &cp, sizeof(cp)); + + smp_send_cmd(smp->conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); + SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); + + set_bit(SMP_FLAG_INITIATOR, &smp->flags); +} + static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_cmd_security_req *rp = (void *) skb->data; - struct smp_cmd_pairing cp; struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; struct smp_chan *smp; @@ -2347,16 +2365,20 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) skb_pull(skb, sizeof(*rp)); - memset(&cp, 0, sizeof(cp)); - build_pairing_cmd(conn, &cp, NULL, auth); + smp_send_pairing_req(smp, auth); - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &cp, sizeof(cp)); + return 0; +} - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); +static void smp_send_security_req(struct smp_chan *smp, __u8 auth) +{ + struct smp_cmd_security_req cp; - return 0; + cp.auth_req = auth; + smp_send_cmd(smp->conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); + SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ); + + clear_bit(SMP_FLAG_INITIATOR, &smp->flags); } int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) @@ -2427,23 +2449,11 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) authreq |= SMP_AUTH_MITM; } - if (hcon->role == HCI_ROLE_MASTER) { - struct smp_cmd_pairing cp; - - build_pairing_cmd(conn, &cp, NULL, authreq); - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &cp, sizeof(cp)); - - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); - } else { - struct smp_cmd_security_req cp; - cp.auth_req = authreq; - smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ); - } + if (hcon->role == HCI_ROLE_MASTER) + smp_send_pairing_req(smp, authreq); + else + smp_send_security_req(smp, authreq); - set_bit(SMP_FLAG_INITIATOR, &smp->flags); ret = 0; unlock: @@ -2694,8 +2704,6 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb) static u8 sc_select_method(struct smp_chan *smp) { - struct l2cap_conn *conn = smp->conn; - struct hci_conn *hcon = conn->hcon; struct smp_cmd_pairing *local, *remote; u8 local_mitm, remote_mitm, local_io, remote_io, method; @@ -2708,7 +2716,7 @@ static u8 sc_select_method(struct smp_chan *smp) * the "struct smp_cmd_pairing" from them we need to skip the * first byte which contains the opcode. */ - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local = (void *) &smp->preq[1]; remote = (void *) &smp->prsp[1]; } else { @@ -2777,7 +2785,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) /* Non-initiating device sends its public key after receiving * the key from the initiating device. */ - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { err = sc_send_public_key(smp); if (err) return err; @@ -2839,7 +2847,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) } if (smp->method == REQ_OOB) { - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); @@ -2848,7 +2856,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) return 0; } - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM); if (smp->method == REQ_PASSKEY) { @@ -2863,7 +2871,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) /* The Initiating device waits for the non-initiating device to * send the confirm value. */ - if (conn->hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return 0; err = smp_f4(smp->tfm_cmac, smp->local_pk, smp->remote_pk, smp->prnd, @@ -2897,7 +2905,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) a[6] = hcon->init_addr_type; b[6] = hcon->resp_addr_type; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local_addr = a; remote_addr = b; memcpy(io_cap, &smp->prsp[1], 3); @@ -2922,7 +2930,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) if (crypto_memneq(check->e, e, 16)) return SMP_DHKEY_CHECK_FAILED; - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { if (test_bit(SMP_FLAG_WAIT_USER, &smp->flags)) { set_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags); return 0; @@ -2934,7 +2942,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) sc_add_ltk(smp); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { hci_le_start_enc(hcon, 0, 0, smp->tk, smp->enc_key_size); hcon->enc_key_size = smp->enc_key_size; } @@ -3083,7 +3091,6 @@ static void bredr_pairing(struct l2cap_chan *chan) struct l2cap_conn *conn = chan->conn; struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; - struct smp_cmd_pairing req; struct smp_chan *smp; bt_dev_dbg(hdev, "chan %p", chan); @@ -3135,14 +3142,7 @@ static void bredr_pairing(struct l2cap_chan *chan) bt_dev_dbg(hdev, "starting SMP over BR/EDR"); - /* Prepare and send the BR/EDR SMP Pairing Request */ - build_bredr_pairing_cmd(smp, &req, NULL); - - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &req, sizeof(req)); - - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(req), &req); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); + smp_send_pairing_req(smp, 0x00); } static void smp_resume_cb(struct l2cap_chan *chan) From 538fd3921afac97158d4177139a0ad39f056dbb2 Mon Sep 17 00:00:00 2001 From: Griffin Kroah-Hartman Date: Thu, 15 Aug 2024 13:51:00 +0200 Subject: [PATCH 134/385] Bluetooth: MGMT: Add error handling to pair_device() hci_conn_params_add() never checks for a NULL value and could lead to a NULL pointer dereference causing a crash. Fixed by adding error handling in the function. Cc: Stable Fixes: 5157b8a503fa ("Bluetooth: Fix initializing conn_params in scan phase") Signed-off-by: Griffin Kroah-Hartman Reported-by: Yiwei Zhang Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/mgmt.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 40d4887c7f791..25979f4283a6f 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -3456,6 +3456,10 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, * will be kept and this function does nothing. */ p = hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type); + if (!p) { + err = -EIO; + goto unlock; + } if (p->auto_connect == HCI_AUTO_CONN_EXPLICIT) p->auto_connect = HCI_AUTO_CONN_DISABLED; From e7d731326ef0622f103e5ed47d3405f71cdcd7f6 Mon Sep 17 00:00:00 2001 From: Abhash Jha Date: Wed, 14 Aug 2024 23:01:21 +0530 Subject: [PATCH 135/385] selftests/net/pmtu.sh: Fix typo in error message The word 'expected' was spelled as 'exepcted'. Fixed the typo in this patch. Signed-off-by: Abhash Jha Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240814173121.33590-1-abhashkumarjha123@gmail.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/pmtu.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 5175c0c83a238..24a50622406c2 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -1447,7 +1447,7 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { size=$(du -sb $tmpoutfile) size=${size%%/tmp/*} - [ $size -ne 1048576 ] && err "File size $size mismatches exepcted value in locally bridged vxlan test" && return 1 + [ $size -ne 1048576 ] && err "File size $size mismatches expected value in locally bridged vxlan test" && return 1 done rm -f "$tmpoutfile" From 7cb43579641dc437941782b473387c6f8bbc1d25 Mon Sep 17 00:00:00 2001 From: Pieter Van Trappen Date: Mon, 12 Aug 2024 11:06:55 +0200 Subject: [PATCH 136/385] net: macb: increase max_mtu for oversized frames Increase max_mtu from 1500 to 1518 bytes when not configured for jumbo frames. Use 1536 as a starting point as documented in macb.h for oversized (big) frames, which is the configuration applied in case jumbo frames capability is not configured; ref. macb_main.c. Signed-off-by: Pieter Van Trappen Link: https://patch.msgid.link/20240812090657.583821-1-vtpieter@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/cadence/macb_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 97b4cc5feb95b..127bb32080340 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -5119,12 +5119,12 @@ static int macb_probe(struct platform_device *pdev) goto err_out_free_netdev; } - /* MTU range: 68 - 1500 or 10240 */ + /* MTU range: 68 - 1518 or 10240 */ dev->min_mtu = GEM_MTU_MIN_SIZE; if ((bp->caps & MACB_CAPS_JUMBO) && bp->jumbo_max_len) dev->max_mtu = bp->jumbo_max_len - ETH_HLEN - ETH_FCS_LEN; else - dev->max_mtu = ETH_DATA_LEN; + dev->max_mtu = 1536 - ETH_HLEN - ETH_FCS_LEN; if (bp->caps & MACB_CAPS_BD_RD_PREFETCH) { val = GEM_BFEXT(RXBD_RDBUFF, gem_readl(bp, DCFG10)); From e3af3d3c5b26c33a7950e34e137584f6056c4319 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 9 Aug 2024 16:54:02 -0700 Subject: [PATCH 137/385] ipv4: Check !in_dev earlier for ioctl(SIOCSIFADDR). dev->ip_ptr could be NULL if we set an invalid MTU. Even then, if we issue ioctl(SIOCSIFADDR) for a new IPv4 address, devinet_ioctl() allocates struct in_ifaddr and fails later in inet_set_ifa() because in_dev is NULL. Let's move the check earlier. Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20240809235406.50187-2-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/ipv4/devinet.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index d96f3e452fef6..ddab151164542 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -574,10 +574,6 @@ static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) ASSERT_RTNL(); - if (!in_dev) { - inet_free_ifa(ifa); - return -ENOBUFS; - } ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); if (ifa->ifa_dev != in_dev) { @@ -1184,6 +1180,8 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) if (!ifa) { ret = -ENOBUFS; + if (!in_dev) + break; ifa = inet_alloc_ifa(); if (!ifa) break; From 6e701eb914124cf260a8b9a4350740f9a7407fc7 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 9 Aug 2024 16:54:03 -0700 Subject: [PATCH 138/385] ipv4: Set ifa->ifa_dev in inet_alloc_ifa(). When a new IPv4 address is assigned via ioctl(SIOCSIFADDR), inet_set_ifa() sets ifa->ifa_dev if it's different from in_dev passed as an argument. In this case, ifa is always a newly allocated object, and ifa->ifa_dev is NULL. inet_set_ifa() can be called for an existing reused ifa, then, this check is always false. Let's set ifa_dev in inet_alloc_ifa() and remove the check in inet_set_ifa(). Now, inet_alloc_ifa() is symmetric with inet_rcu_free_ifa(). Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20240809235406.50187-3-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/ipv4/devinet.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index ddab151164542..9f4add07e67d7 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -216,9 +216,18 @@ static void devinet_sysctl_unregister(struct in_device *idev) /* Locks all the inet devices. */ -static struct in_ifaddr *inet_alloc_ifa(void) +static struct in_ifaddr *inet_alloc_ifa(struct in_device *in_dev) { - return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL_ACCOUNT); + struct in_ifaddr *ifa; + + ifa = kzalloc(sizeof(*ifa), GFP_KERNEL_ACCOUNT); + if (!ifa) + return NULL; + + in_dev_hold(in_dev); + ifa->ifa_dev = in_dev; + + return ifa; } static void inet_rcu_free_ifa(struct rcu_head *head) @@ -576,11 +585,7 @@ static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); - if (ifa->ifa_dev != in_dev) { - WARN_ON(ifa->ifa_dev); - in_dev_hold(in_dev); - ifa->ifa_dev = in_dev; - } + if (ipv4_is_loopback(ifa->ifa_local)) ifa->ifa_scope = RT_SCOPE_HOST; return inet_insert_ifa(ifa); @@ -871,7 +876,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, if (!in_dev) goto errout; - ifa = inet_alloc_ifa(); + ifa = inet_alloc_ifa(in_dev); if (!ifa) /* * A potential indev allocation can be left alive, it stays @@ -881,7 +886,6 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); - in_dev_hold(in_dev); if (!tb[IFA_ADDRESS]) tb[IFA_ADDRESS] = tb[IFA_LOCAL]; @@ -892,8 +896,6 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags; ifa->ifa_scope = ifm->ifa_scope; - ifa->ifa_dev = in_dev; - ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]); ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]); @@ -1182,7 +1184,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) ret = -ENOBUFS; if (!in_dev) break; - ifa = inet_alloc_ifa(); + ifa = inet_alloc_ifa(in_dev); if (!ifa) break; INIT_HLIST_NODE(&ifa->hash); @@ -1584,7 +1586,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, if (!inetdev_valid_mtu(dev->mtu)) break; if (dev->flags & IFF_LOOPBACK) { - struct in_ifaddr *ifa = inet_alloc_ifa(); + struct in_ifaddr *ifa = inet_alloc_ifa(in_dev); if (ifa) { INIT_HLIST_NODE(&ifa->hash); @@ -1592,8 +1594,6 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, ifa->ifa_address = htonl(INADDR_LOOPBACK); ifa->ifa_prefixlen = 8; ifa->ifa_mask = inet_make_mask(8); - in_dev_hold(in_dev); - ifa->ifa_dev = in_dev; ifa->ifa_scope = RT_SCOPE_HOST; memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, From ecdae5168460f7260c0f8dad069aa06f9ba0706e Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 9 Aug 2024 16:54:04 -0700 Subject: [PATCH 139/385] ipv4: Remove redundant !ifa->ifa_dev check. Now, ifa_dev is only set in inet_alloc_ifa() and never NULL after ifa gets visible. Let's remove the unneeded NULL check for ifa->ifa_dev. Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20240809235406.50187-4-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c | 5 ++--- drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 2 +- net/ipv4/devinet.c | 3 +-- 3 files changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index ed24d6af7487b..9cff0a8ffb2c5 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -3185,8 +3185,7 @@ netxen_list_config_ip(struct netxen_adapter *adapter, struct list_head *head; bool ret = false; - dev = ifa->ifa_dev ? ifa->ifa_dev->dev : NULL; - + dev = ifa->ifa_dev->dev; if (dev == NULL) goto out; @@ -3379,7 +3378,7 @@ netxen_inetaddr_event(struct notifier_block *this, struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; unsigned long ip_event; - dev = ifa->ifa_dev ? ifa->ifa_dev->dev : NULL; + dev = ifa->ifa_dev->dev; ip_event = (event == NETDEV_UP) ? NX_IP_UP : NX_IP_DOWN; recheck: if (dev == NULL) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 90df4a0909fa2..b3588a1ebc25f 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -4146,7 +4146,7 @@ qlcnic_inetaddr_event(struct notifier_block *this, struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; - dev = ifa->ifa_dev ? ifa->ifa_dev->dev : NULL; + dev = ifa->ifa_dev->dev; recheck: if (dev == NULL) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 9f4add07e67d7..baf036bfad76e 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -234,8 +234,7 @@ static void inet_rcu_free_ifa(struct rcu_head *head) { struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head); - if (ifa->ifa_dev) - in_dev_put(ifa->ifa_dev); + in_dev_put(ifa->ifa_dev); kfree(ifa); } From 100465a91a900699db9c64fb55063affd15c4362 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 9 Aug 2024 16:54:05 -0700 Subject: [PATCH 140/385] ipv4: Initialise ifa->hash in inet_alloc_ifa(). Whenever ifa is allocated, we call INIT_HLIST_NODE(&ifa->hash). Let's move it to inet_alloc_ifa(). Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20240809235406.50187-5-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/ipv4/devinet.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index baf036bfad76e..b5d2a9fd46c70 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -227,6 +227,8 @@ static struct in_ifaddr *inet_alloc_ifa(struct in_device *in_dev) in_dev_hold(in_dev); ifa->ifa_dev = in_dev; + INIT_HLIST_NODE(&ifa->hash); + return ifa; } @@ -889,7 +891,6 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, if (!tb[IFA_ADDRESS]) tb[IFA_ADDRESS] = tb[IFA_LOCAL]; - INIT_HLIST_NODE(&ifa->hash); ifa->ifa_prefixlen = ifm->ifa_prefixlen; ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen); ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : @@ -1186,7 +1187,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) ifa = inet_alloc_ifa(in_dev); if (!ifa) break; - INIT_HLIST_NODE(&ifa->hash); + if (colon) memcpy(ifa->ifa_label, ifr->ifr_name, IFNAMSIZ); else @@ -1588,7 +1589,6 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, struct in_ifaddr *ifa = inet_alloc_ifa(in_dev); if (ifa) { - INIT_HLIST_NODE(&ifa->hash); ifa->ifa_local = ifa->ifa_address = htonl(INADDR_LOOPBACK); ifa->ifa_prefixlen = 8; From de67763cbdbba8149eeb5d45ad0c6834f7c7b352 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 9 Aug 2024 16:54:06 -0700 Subject: [PATCH 141/385] ip: Move INFINITY_LIFE_TIME to addrconf.h. INFINITY_LIFE_TIME is the common value used in IPv4 and IPv6 but defined in both .c files. Also, 0xffffffff used in addrconf_timeout_fixup() is INFINITY_LIFE_TIME. Let's move INFINITY_LIFE_TIME's definition to addrconf.h Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20240809235406.50187-6-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/addrconf.h | 4 +++- net/ipv4/devinet.c | 2 -- net/ipv6/addrconf.c | 2 -- 3 files changed, 3 insertions(+), 5 deletions(-) diff --git a/include/net/addrconf.h b/include/net/addrconf.h index b18e81f0c9e1a..c8ed31828db36 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -187,10 +187,12 @@ static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) return 0; } +#define INFINITY_LIFE_TIME 0xFFFFFFFF + static inline unsigned long addrconf_timeout_fixup(u32 timeout, unsigned int unit) { - if (timeout == 0xffffffff) + if (timeout == INFINITY_LIFE_TIME) return ~0UL; /* diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index b5d2a9fd46c70..61be85154dd19 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -703,8 +703,6 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, return err; } -#define INFINITY_LIFE_TIME 0xFFFFFFFF - static void check_lifetime(struct work_struct *work) { unsigned long now, next, next_sec, next_sched; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c87d008aefa4c..04ee75af2f6b7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -92,8 +92,6 @@ #include #include -#define INFINITY_LIFE_TIME 0xFFFFFFFF - #define IPV6_MAX_STRLEN \ sizeof("ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255") From e5efc2311cc437e2b565d164a3de884fa33f13e9 Mon Sep 17 00:00:00 2001 From: Erwan Velu Date: Mon, 12 Aug 2024 10:22:42 +0200 Subject: [PATCH 142/385] net/mlx5: Use cpumask_local_spread() instead of custom code Commit 2acda57736de ("net/mlx5e: Improve remote NUMA preferences used for the IRQ affinity hints") removed the usage of cpumask_local_spread(). The issue explained in this commit was fixed by commit 406d394abfcd ("cpumask: improve on cpumask_local_spread() locality"). Since this commit, mlx5_cpumask_default_spread() is having the same behavior as cpumask_local_spread(). This commit is about : - removing the specific logic and use cpumask_local_spread() instead - passing mlx5_core_dev as argument to more flexibility mlx5_cpumask_default_spread() is kept as it could be useful for some future specific quirks. Signed-off-by: Erwan Velu Acked-by: Yury Norov Reviewed-by: Tariq Toukan Link: https://patch.msgid.link/20240812082244.22810-1-e.velu@criteo.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 27 +++----------------- 1 file changed, 4 insertions(+), 23 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index cb7e7e4104aff..f15ecaef13313 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -835,28 +835,9 @@ static void comp_irq_release_pci(struct mlx5_core_dev *dev, u16 vecidx) mlx5_irq_release_vector(irq); } -static int mlx5_cpumask_default_spread(int numa_node, int index) +static int mlx5_cpumask_default_spread(struct mlx5_core_dev *dev, int index) { - const struct cpumask *prev = cpu_none_mask; - const struct cpumask *mask; - int found_cpu = 0; - int i = 0; - int cpu; - - rcu_read_lock(); - for_each_numa_hop_mask(mask, numa_node) { - for_each_cpu_andnot(cpu, mask, prev) { - if (i++ == index) { - found_cpu = cpu; - goto spread_done; - } - } - prev = mask; - } - -spread_done: - rcu_read_unlock(); - return found_cpu; + return cpumask_local_spread(index, dev->priv.numa_node); } static struct cpu_rmap *mlx5_eq_table_get_pci_rmap(struct mlx5_core_dev *dev) @@ -880,7 +861,7 @@ static int comp_irq_request_pci(struct mlx5_core_dev *dev, u16 vecidx) int cpu; rmap = mlx5_eq_table_get_pci_rmap(dev); - cpu = mlx5_cpumask_default_spread(dev->priv.numa_node, vecidx); + cpu = mlx5_cpumask_default_spread(dev, vecidx); irq = mlx5_irq_request_vector(dev, cpu, vecidx, &rmap); if (IS_ERR(irq)) return PTR_ERR(irq); @@ -1145,7 +1126,7 @@ int mlx5_comp_vector_get_cpu(struct mlx5_core_dev *dev, int vector) if (mask) cpu = cpumask_first(mask); else - cpu = mlx5_cpumask_default_spread(dev->priv.numa_node, vector); + cpu = mlx5_cpumask_default_spread(dev, vector); return cpu; } From fcb1aa5163b1ae4cf2864b688b08927aac51f51e Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 12 Aug 2024 13:17:53 -0400 Subject: [PATCH 143/385] openvswitch: switch to per-action label counting in conntrack Similar to commit 70f06c115bcc ("sched: act_ct: switch to per-action label counting"), we should also switch to per-action label counting in openvswitch conntrack, as Florian suggested. The difference is that nf_connlabels_get() is called unconditionally when creating an ct action in ovs_ct_copy_action(). As with these flows: table=0,ip,actions=ct(commit,table=1) table=1,ip,actions=ct(commit,exec(set_field:0xac->ct_label),table=2) it needs to make sure the label ext is created in the 1st flow before the ct is committed in ovs_ct_commit(). Otherwise, the warning in nf_ct_ext_add() when creating the label ext in the 2nd flow will be triggered: WARN_ON(nf_ct_is_confirmed(ct)); Signed-off-by: Xin Long Reviewed-by: Aaron Conole Acked-by: Florian Westphal Link: https://patch.msgid.link/6b9347d5c1a0b364e88d900b29a616c3f8e5b1ca.1723483073.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski --- net/openvswitch/conntrack.c | 30 ++++++++++++------------------ net/openvswitch/datapath.h | 3 --- 2 files changed, 12 insertions(+), 21 deletions(-) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 8eb1d644b741f..a3da5ee34f92d 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1368,11 +1368,8 @@ bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr) attr == OVS_KEY_ATTR_CT_MARK) return true; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - attr == OVS_KEY_ATTR_CT_LABELS) { - struct ovs_net *ovs_net = net_generic(net, ovs_net_id); - - return ovs_net->xt_label; - } + attr == OVS_KEY_ATTR_CT_LABELS) + return true; return false; } @@ -1381,6 +1378,7 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, bool log) { + unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; struct ovs_conntrack_info ct_info; const char *helper = NULL; u16 family; @@ -1409,6 +1407,12 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, return -ENOMEM; } + if (nf_connlabels_get(net, n_bits - 1)) { + nf_ct_tmpl_free(ct_info.ct); + OVS_NLERR(log, "Failed to set connlabel length"); + return -EOPNOTSUPP; + } + if (ct_info.timeout[0]) { if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto, ct_info.timeout)) @@ -1577,6 +1581,7 @@ static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info) if (ct_info->ct) { if (ct_info->timeout[0]) nf_ct_destroy_timeout(ct_info->ct); + nf_connlabels_put(nf_ct_net(ct_info->ct)); nf_ct_tmpl_free(ct_info->ct); } } @@ -2002,17 +2007,9 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = { int ovs_ct_init(struct net *net) { - unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) struct ovs_net *ovs_net = net_generic(net, ovs_net_id); - if (nf_connlabels_get(net, n_bits - 1)) { - ovs_net->xt_label = false; - OVS_NLERR(true, "Failed to set connlabel length"); - } else { - ovs_net->xt_label = true; - } - -#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) return ovs_ct_limit_init(net, ovs_net); #else return 0; @@ -2021,12 +2018,9 @@ int ovs_ct_init(struct net *net) void ovs_ct_exit(struct net *net) { +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) struct ovs_net *ovs_net = net_generic(net, ovs_net_id); -#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) ovs_ct_limit_exit(net, ovs_net); #endif - - if (ovs_net->xt_label) - nf_connlabels_put(net); } diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 9ca6231ea6470..365b9bb7f546e 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -160,9 +160,6 @@ struct ovs_net { #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) struct ovs_ct_limit_info *ct_limit_info; #endif - - /* Module reference for configuring conntrack. */ - bool xt_label; }; /** From d440af37ba6fa301144c6fce2186fe0ab5a8f283 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Wed, 14 Aug 2024 09:06:38 +0200 Subject: [PATCH 144/385] netdev: Add missing __percpu qualifier to a cast Add missing __percpu qualifier to a (void *) cast to fix dev.c:10863:45: warning: cast removes address space '__percpu' of expression sparse warning. Also remove now unneeded __force sparse directives. Found by GCC's named address space checks. There were no changes in the resulting object file. Signed-off-by: Uros Bizjak Link: https://patch.msgid.link/20240814070748.943671-1-ubizjak@gmail.com Signed-off-by: Jakub Kicinski --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index f66e614078832..e7260889d4cb0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10868,7 +10868,7 @@ noinline void netdev_core_stats_inc(struct net_device *dev, u32 offset) return; } - field = (__force unsigned long __percpu *)((__force void *)p + offset); + field = (unsigned long __percpu *)((void __percpu *)p + offset); this_cpu_inc(*field); } EXPORT_SYMBOL_GPL(netdev_core_stats_inc); From b96ed2c97c791954abc881ef384e773010945aec Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 14 Aug 2024 14:25:00 +0200 Subject: [PATCH 145/385] virtio_net: move netdev_tx_reset_queue() call before RX napi enable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit During suspend/resume the following BUG was hit: ------------[ cut here ]------------ kernel BUG at lib/dynamic_queue_limits.c:99! Internal error: Oops - BUG: 0 [#1] SMP ARM Modules linked in: bluetooth ecdh_generic ecc libaes CPU: 1 PID: 1282 Comm: rtcwake Not tainted 6.10.0-rc3-00732-gc8bd1f7f3e61 #15240 Hardware name: Generic DT based system PC is at dql_completed+0x270/0x2cc LR is at __free_old_xmit+0x120/0x198 pc : []    lr : []    psr: 80000013 ... Flags: Nzcv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none Control: 10c5387d  Table: 43a4406a  DAC: 00000051 ... Process rtcwake (pid: 1282, stack limit = 0xfbc21278) Stack: (0xe0805e80 to 0xe0806000) ... Call trace:  dql_completed from __free_old_xmit+0x120/0x198  __free_old_xmit from free_old_xmit+0x44/0xe4  free_old_xmit from virtnet_poll_tx+0x88/0x1b4  virtnet_poll_tx from __napi_poll+0x2c/0x1d4  __napi_poll from net_rx_action+0x140/0x2b4  net_rx_action from handle_softirqs+0x11c/0x350  handle_softirqs from call_with_stack+0x18/0x20  call_with_stack from do_softirq+0x48/0x50  do_softirq from __local_bh_enable_ip+0xa0/0xa4  __local_bh_enable_ip from virtnet_open+0xd4/0x21c  virtnet_open from virtnet_restore+0x94/0x120  virtnet_restore from virtio_device_restore+0x110/0x1f4  virtio_device_restore from dpm_run_callback+0x3c/0x100  dpm_run_callback from device_resume+0x12c/0x2a8  device_resume from dpm_resume+0x12c/0x1e0  dpm_resume from dpm_resume_end+0xc/0x18  dpm_resume_end from suspend_devices_and_enter+0x1f0/0x72c  suspend_devices_and_enter from pm_suspend+0x270/0x2a0  pm_suspend from state_store+0x68/0xc8  state_store from kernfs_fop_write_iter+0x10c/0x1cc  kernfs_fop_write_iter from vfs_write+0x2b0/0x3dc  vfs_write from ksys_write+0x5c/0xd4  ksys_write from ret_fast_syscall+0x0/0x54 Exception stack(0xe8bf1fa8 to 0xe8bf1ff0) ... ---[ end trace 0000000000000000 ]--- After virtnet_napi_enable() is called, the following path is hit: __napi_poll() -> virtnet_poll() -> virtnet_poll_cleantx() -> netif_tx_wake_queue() That wakes the TX queue and allows skbs to be submitted and accounted by BQL counters. Then netdev_tx_reset_queue() is called that resets BQL counters and eventually leads to the BUG in dql_completed(). Move virtnet_napi_tx_enable() what does BQL counters reset before RX napi enable to avoid the issue. Reported-by: Marek Szyprowski Closes: https://lore.kernel.org/netdev/e632e378-d019-4de7-8f13-07c572ab37a9@samsung.com/ Fixes: c8bd1f7f3e61 ("virtio_net: add support for Byte Queue Limits") Tested-by: Marek Szyprowski Signed-off-by: Jiri Pirko Acked-by: Michael S. Tsirkin Acked-by: Jason Wang Link: https://patch.msgid.link/20240814122500.1710279-1-jiri@resnulli.us Signed-off-by: Jakub Kicinski --- drivers/net/virtio_net.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 3f10c72743e94..c6af189480929 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2867,8 +2867,8 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) if (err < 0) goto err_xdp_reg_mem_model; - virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, qp_index)); + virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); return 0; From c948c0973df5db9314459da621342e1170bd9e8e Mon Sep 17 00:00:00 2001 From: Pavan Chebbi Date: Wed, 14 Aug 2024 15:54:29 -0700 Subject: [PATCH 146/385] bnxt_en: Don't clear ntuple filters and rss contexts during ethtool ops The driver currently blindly deletes its cache of RSS cotexts and ntuple filters when the ethtool channel count is changing. It also deletes the ntuple filters cache when the default indirection table is changing. The core will not allow ethtool channels to drop below any that have been configured as ntuple destinations since this commit from 2022: 47f3ecf4763d ("ethtool: Fail number of channels change when it conflicts with rxnfc") So there is absolutely no need to delete the ntuple filters and RSS contexts when changing ethtool channels. It is also unnecessary to delete ntuple filters when the default RSS indirection table is changing. Remove bnxt_clear_usr_fltrs() and bnxt_clear_rss_ctxis() from the ethtool ops and change them to static functions. This bug will cause confusion to the end user and causes failure when running the rss_ctx.py selftest. Fixes: 1018319f949c ("bnxt_en: Invalidate user filters when needed") Reported-by: Jakub Kicinski Closes: https://lore.kernel.org/netdev/20240725111912.7bc17cf6@kernel.org/ Reviewed-by: Andy Gospodarek Signed-off-by: Pavan Chebbi Signed-off-by: Michael Chan Link: https://patch.msgid.link/20240814225429.199280-1-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++-- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 2 -- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 4 ---- 3 files changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index e27e1082ee33a..04a623b3eee29 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -5056,7 +5056,7 @@ void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr) list_del_init(&fltr->list); } -void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all) +static void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all) { struct bnxt_filter_base *usr_fltr, *tmp; @@ -10248,7 +10248,7 @@ static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp) } } -void bnxt_clear_rss_ctxs(struct bnxt *bp) +static void bnxt_clear_rss_ctxs(struct bnxt *bp) { struct ethtool_rxfh_context *ctx; unsigned long context; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 6bbdc718c3a70..059a6f81c1a87 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2790,7 +2790,6 @@ void bnxt_set_ring_params(struct bnxt *); int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode); void bnxt_insert_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr); void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr); -void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all); int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size, bool async_only); int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp); @@ -2842,7 +2841,6 @@ int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic); int __bnxt_setup_vnic_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic); void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx, bool all); -void bnxt_clear_rss_ctxs(struct bnxt *bp); int bnxt_open_nic(struct bnxt *, bool, bool); int bnxt_half_open_nic(struct bnxt *bp); void bnxt_half_close_nic(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 9dadc89378f02..4cf9bf8b01b09 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -968,9 +968,6 @@ static int bnxt_set_channels(struct net_device *dev, return -EINVAL; } - bnxt_clear_usr_fltrs(bp, true); - if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp)) - bnxt_clear_rss_ctxs(bp); if (netif_running(dev)) { if (BNXT_PF(bp)) { /* TODO CHIMP_FW: Send message to all VF's @@ -2000,7 +1997,6 @@ static int bnxt_set_rxfh(struct net_device *dev, bnxt_modify_rss(bp, NULL, NULL, rxfh); - bnxt_clear_usr_fltrs(bp, false); if (netif_running(bp->dev)) { bnxt_close_nic(bp, false, false); rc = bnxt_open_nic(bp, false, false); From b153b3c747003e1ce312ba205e552db4bd9e8df7 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 14 Aug 2024 07:28:32 -0700 Subject: [PATCH 147/385] MAINTAINERS: add selftests to network drivers tools/testing/selftests/drivers/net/ is not listed under networking entries. Add it to NETWORKING DRIVERS. Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240814142832.3473685-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index f328373463b0d..a964a34651f56 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15886,6 +15886,7 @@ F: include/linux/netdevice.h F: include/uapi/linux/cn_proc.h F: include/uapi/linux/if_* F: include/uapi/linux/netdevice.h +F: tools/testing/selftests/drivers/net/ X: drivers/net/wireless/ NETWORKING DRIVERS (WIRELESS) From 0cb70ee4a6ee6b0a4b0e0f70a64a094c6fe05944 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 14 Aug 2024 13:22:25 +0800 Subject: [PATCH 148/385] virtio: rename virtio_config_enabled to virtio_config_core_enabled Following patch will allow the config interrupt to be disabled by a specific driver via another boolean. So this patch renames virtio_config_enabled and relevant helpers to virtio_config_core_enabled. Cc: Venkat Venkatsubra Cc: Gia-Khanh Nguyen Acked-by: Michael S. Tsirkin Signed-off-by: Jason Wang Link: https://patch.msgid.link/20240814052228.4654-2-jasowang@redhat.com Signed-off-by: Jakub Kicinski --- drivers/virtio/virtio.c | 22 +++++++++++----------- include/linux/virtio.h | 4 ++-- 2 files changed, 13 insertions(+), 13 deletions(-) diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index bc1f962e483b9..6b692b0fa578b 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -127,7 +127,7 @@ static void __virtio_config_changed(struct virtio_device *dev) { struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); - if (!dev->config_enabled) + if (!dev->config_core_enabled) dev->config_change_pending = true; else if (drv && drv->config_changed) drv->config_changed(dev); @@ -143,17 +143,17 @@ void virtio_config_changed(struct virtio_device *dev) } EXPORT_SYMBOL_GPL(virtio_config_changed); -static void virtio_config_disable(struct virtio_device *dev) +static void virtio_config_core_disable(struct virtio_device *dev) { spin_lock_irq(&dev->config_lock); - dev->config_enabled = false; + dev->config_core_enabled = false; spin_unlock_irq(&dev->config_lock); } -static void virtio_config_enable(struct virtio_device *dev) +static void virtio_config_core_enable(struct virtio_device *dev) { spin_lock_irq(&dev->config_lock); - dev->config_enabled = true; + dev->config_core_enabled = true; if (dev->config_change_pending) __virtio_config_changed(dev); dev->config_change_pending = false; @@ -316,7 +316,7 @@ static int virtio_dev_probe(struct device *_d) if (drv->scan) drv->scan(dev); - virtio_config_enable(dev); + virtio_config_core_enable(dev); return 0; @@ -331,7 +331,7 @@ static void virtio_dev_remove(struct device *_d) struct virtio_device *dev = dev_to_virtio(_d); struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); - virtio_config_disable(dev); + virtio_config_core_disable(dev); drv->remove(dev); @@ -443,7 +443,7 @@ int register_virtio_device(struct virtio_device *dev) goto out_ida_remove; spin_lock_init(&dev->config_lock); - dev->config_enabled = false; + dev->config_core_enabled = false; dev->config_change_pending = false; INIT_LIST_HEAD(&dev->vqs); @@ -500,14 +500,14 @@ int virtio_device_freeze(struct virtio_device *dev) struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); int ret; - virtio_config_disable(dev); + virtio_config_core_disable(dev); dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED; if (drv && drv->freeze) { ret = drv->freeze(dev); if (ret) { - virtio_config_enable(dev); + virtio_config_core_enable(dev); return ret; } } @@ -557,7 +557,7 @@ int virtio_device_restore(struct virtio_device *dev) if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK)) virtio_device_ready(dev); - virtio_config_enable(dev); + virtio_config_core_enable(dev); return 0; diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 4b16844c6bc29..de6d3cc176d96 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -118,7 +118,7 @@ struct virtio_admin_cmd { * struct virtio_device - representation of a device using virtio * @index: unique position on the virtio bus * @failed: saved value for VIRTIO_CONFIG_S_FAILED bit (for restore) - * @config_enabled: configuration change reporting enabled + * @config_core_enabled: configuration change reporting enabled by core * @config_change_pending: configuration change reported while disabled * @config_lock: protects configuration change reporting * @vqs_list_lock: protects @vqs. @@ -135,7 +135,7 @@ struct virtio_admin_cmd { struct virtio_device { int index; bool failed; - bool config_enabled; + bool config_core_enabled; bool config_change_pending; spinlock_t config_lock; spinlock_t vqs_list_lock; From 224de6f886f8184fd448700a6d78f216694de948 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 14 Aug 2024 13:22:26 +0800 Subject: [PATCH 149/385] virtio: allow driver to disable the configure change notification Sometime, it would be useful to disable the configure change notification from the driver. So this patch allows this by introducing a variable config_change_driver_disabled and only allow the configure change notification callback to be triggered when it is allowed by both the virtio core and the driver. It is set to false by default to hold the current semantic so we don't need to change any drivers. The first user for this would be virtio-net. Cc: Venkat Venkatsubra Cc: Gia-Khanh Nguyen Acked-by: Michael S. Tsirkin Signed-off-by: Jason Wang Link: https://patch.msgid.link/20240814052228.4654-3-jasowang@redhat.com Signed-off-by: Jakub Kicinski --- drivers/virtio/virtio.c | 39 ++++++++++++++++++++++++++++++++++++--- include/linux/virtio.h | 7 +++++++ 2 files changed, 43 insertions(+), 3 deletions(-) diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 6b692b0fa578b..b9095751e43bb 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -127,10 +127,12 @@ static void __virtio_config_changed(struct virtio_device *dev) { struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); - if (!dev->config_core_enabled) + if (!dev->config_core_enabled || dev->config_driver_disabled) dev->config_change_pending = true; - else if (drv && drv->config_changed) + else if (drv && drv->config_changed) { drv->config_changed(dev); + dev->config_change_pending = false; + } } void virtio_config_changed(struct virtio_device *dev) @@ -143,6 +145,38 @@ void virtio_config_changed(struct virtio_device *dev) } EXPORT_SYMBOL_GPL(virtio_config_changed); +/** + * virtio_config_driver_disable - disable config change reporting by drivers + * @dev: the device to reset + * + * This is only allowed to be called by a driver and disabling can't + * be nested. + */ +void virtio_config_driver_disable(struct virtio_device *dev) +{ + spin_lock_irq(&dev->config_lock); + dev->config_driver_disabled = true; + spin_unlock_irq(&dev->config_lock); +} +EXPORT_SYMBOL_GPL(virtio_config_driver_disable); + +/** + * virtio_config_driver_enable - enable config change reporting by drivers + * @dev: the device to reset + * + * This is only allowed to be called by a driver and enabling can't + * be nested. + */ +void virtio_config_driver_enable(struct virtio_device *dev) +{ + spin_lock_irq(&dev->config_lock); + dev->config_driver_disabled = false; + if (dev->config_change_pending) + __virtio_config_changed(dev); + spin_unlock_irq(&dev->config_lock); +} +EXPORT_SYMBOL_GPL(virtio_config_driver_enable); + static void virtio_config_core_disable(struct virtio_device *dev) { spin_lock_irq(&dev->config_lock); @@ -156,7 +190,6 @@ static void virtio_config_core_enable(struct virtio_device *dev) dev->config_core_enabled = true; if (dev->config_change_pending) __virtio_config_changed(dev); - dev->config_change_pending = false; spin_unlock_irq(&dev->config_lock); } diff --git a/include/linux/virtio.h b/include/linux/virtio.h index de6d3cc176d96..306137a15d075 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -119,6 +119,8 @@ struct virtio_admin_cmd { * @index: unique position on the virtio bus * @failed: saved value for VIRTIO_CONFIG_S_FAILED bit (for restore) * @config_core_enabled: configuration change reporting enabled by core + * @config_driver_disabled: configuration change reporting disabled by + * a driver * @config_change_pending: configuration change reported while disabled * @config_lock: protects configuration change reporting * @vqs_list_lock: protects @vqs. @@ -136,6 +138,7 @@ struct virtio_device { int index; bool failed; bool config_core_enabled; + bool config_driver_disabled; bool config_change_pending; spinlock_t config_lock; spinlock_t vqs_list_lock; @@ -166,6 +169,10 @@ void __virtqueue_break(struct virtqueue *_vq); void __virtqueue_unbreak(struct virtqueue *_vq); void virtio_config_changed(struct virtio_device *dev); + +void virtio_config_driver_disable(struct virtio_device *dev); +void virtio_config_driver_enable(struct virtio_device *dev); + #ifdef CONFIG_PM_SLEEP int virtio_device_freeze(struct virtio_device *dev); int virtio_device_restore(struct virtio_device *dev); From df28de7b00502761eba62490f413c65c9b175ed9 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 14 Aug 2024 13:22:27 +0800 Subject: [PATCH 150/385] virtio-net: synchronize operstate with admin state on up/down This patch synchronizes operstate with admin state per RFC2863. This is done by trying to toggle the carrier upon open/close and synchronize with the config change work. This allows to propagate status correctly to stacked devices like: ip link add link enp0s3 macvlan0 type macvlan ip link set link enp0s3 down ip link show Before this patch: 3: enp0s3: mtu 1500 qdisc pfifo_fast state DOWN mode DEFAULT group default qlen 1000 link/ether 00:00:05:00:00:09 brd ff:ff:ff:ff:ff:ff ...... 5: macvlan0@enp0s3: mtu 1500 qdisc noqueue state UP mode DEFAULT group default qlen 1000 link/ether b2:a9:c5:04:da:53 brd ff:ff:ff:ff:ff:ff After this patch: 3: enp0s3: mtu 1500 qdisc pfifo_fast state DOWN mode DEFAULT group default qlen 1000 link/ether 00:00:05:00:00:09 brd ff:ff:ff:ff:ff:ff ... 5: macvlan0@enp0s3: mtu 1500 qdisc noqueue state LOWERLAYERDOWN mode DEFAULT group default qlen 1000 link/ether b2:a9:c5:04:da:53 brd ff:ff:ff:ff:ff:ff Cc: Venkat Venkatsubra Cc: Gia-Khanh Nguyen Acked-by: Michael S. Tsirkin Signed-off-by: Jason Wang Link: https://patch.msgid.link/20240814052228.4654-4-jasowang@redhat.com Signed-off-by: Jakub Kicinski --- drivers/net/virtio_net.c | 78 +++++++++++++++++++++++++--------------- 1 file changed, 50 insertions(+), 28 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 3f10c72743e94..55b712a71e637 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2885,6 +2885,25 @@ static void virtnet_cancel_dim(struct virtnet_info *vi, struct dim *dim) net_dim_work_cancel(dim); } +static void virtnet_update_settings(struct virtnet_info *vi) +{ + u32 speed; + u8 duplex; + + if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX)) + return; + + virtio_cread_le(vi->vdev, struct virtio_net_config, speed, &speed); + + if (ethtool_validate_speed(speed)) + vi->speed = speed; + + virtio_cread_le(vi->vdev, struct virtio_net_config, duplex, &duplex); + + if (ethtool_validate_duplex(duplex)) + vi->duplex = duplex; +} + static int virtnet_open(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); @@ -2903,6 +2922,15 @@ static int virtnet_open(struct net_device *dev) goto err_enable_qp; } + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) { + if (vi->status & VIRTIO_NET_S_LINK_UP) + netif_carrier_on(vi->dev); + virtio_config_driver_enable(vi->vdev); + } else { + vi->status = VIRTIO_NET_S_LINK_UP; + netif_carrier_on(dev); + } + return 0; err_enable_qp: @@ -3381,12 +3409,22 @@ static int virtnet_close(struct net_device *dev) disable_delayed_refill(vi); /* Make sure refill_work doesn't re-enable napi! */ cancel_delayed_work_sync(&vi->refill); + /* Prevent the config change callback from changing carrier + * after close + */ + virtio_config_driver_disable(vi->vdev); + /* Stop getting status/speed updates: we don't care until next + * open + */ + cancel_work_sync(&vi->config_work); for (i = 0; i < vi->max_queue_pairs; i++) { virtnet_disable_queue_pair(vi, i); virtnet_cancel_dim(vi, &vi->rq[i].dim); } + netif_carrier_off(dev); + return 0; } @@ -5095,25 +5133,6 @@ static void virtnet_init_settings(struct net_device *dev) vi->duplex = DUPLEX_UNKNOWN; } -static void virtnet_update_settings(struct virtnet_info *vi) -{ - u32 speed; - u8 duplex; - - if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX)) - return; - - virtio_cread_le(vi->vdev, struct virtio_net_config, speed, &speed); - - if (ethtool_validate_speed(speed)) - vi->speed = speed; - - virtio_cread_le(vi->vdev, struct virtio_net_config, duplex, &duplex); - - if (ethtool_validate_duplex(duplex)) - vi->duplex = duplex; -} - static u32 virtnet_get_rxfh_key_size(struct net_device *dev) { return ((struct virtnet_info *)netdev_priv(dev))->rss_key_size; @@ -6524,6 +6543,9 @@ static int virtnet_probe(struct virtio_device *vdev) goto free_failover; } + /* Disable config change notification until ndo_open. */ + virtio_config_driver_disable(vi->vdev); + virtio_device_ready(vdev); virtnet_set_queues(vi, vi->curr_queue_pairs); @@ -6573,25 +6595,25 @@ static int virtnet_probe(struct virtio_device *vdev) vi->device_stats_cap = le64_to_cpu(v); } - rtnl_unlock(); - - err = virtnet_cpu_notif_add(vi); - if (err) { - pr_debug("virtio_net: registering cpu notifier failed\n"); - goto free_unregister_netdev; - } - /* Assume link up if device can't report link status, otherwise get link status from config. */ netif_carrier_off(dev); if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) { - schedule_work(&vi->config_work); + virtnet_config_changed_work(&vi->config_work); } else { vi->status = VIRTIO_NET_S_LINK_UP; virtnet_update_settings(vi); netif_carrier_on(dev); } + rtnl_unlock(); + + err = virtnet_cpu_notif_add(vi); + if (err) { + pr_debug("virtio_net: registering cpu notifier failed\n"); + goto free_unregister_netdev; + } + for (i = 0; i < ARRAY_SIZE(guest_offloads); i++) if (virtio_has_feature(vi->vdev, guest_offloads[i])) set_bit(guest_offloads[i], &vi->guest_offloads); From c392d6019398315526b0b508282f87c7b2318c72 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 14 Aug 2024 13:22:28 +0800 Subject: [PATCH 151/385] virtio-net: synchronize probe with ndo_set_features We calculate guest offloads during probe without the protection of rtnl_lock. This lead to race between probe and ndo_set_features. Fix this by moving the calculation under the rtnl_lock. Fixes: 3f93522ffab2 ("virtio-net: switch off offloads on demand if possible on XDP set") Acked-by: Michael S. Tsirkin Signed-off-by: Jason Wang Link: https://patch.msgid.link/20240814052228.4654-5-jasowang@redhat.com Signed-off-by: Jakub Kicinski --- drivers/net/virtio_net.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 55b712a71e637..6c79fc43fa31d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -6606,6 +6606,11 @@ static int virtnet_probe(struct virtio_device *vdev) netif_carrier_on(dev); } + for (i = 0; i < ARRAY_SIZE(guest_offloads); i++) + if (virtio_has_feature(vi->vdev, guest_offloads[i])) + set_bit(guest_offloads[i], &vi->guest_offloads); + vi->guest_offloads_capable = vi->guest_offloads; + rtnl_unlock(); err = virtnet_cpu_notif_add(vi); @@ -6614,11 +6619,6 @@ static int virtnet_probe(struct virtio_device *vdev) goto free_unregister_netdev; } - for (i = 0; i < ARRAY_SIZE(guest_offloads); i++) - if (virtio_has_feature(vi->vdev, guest_offloads[i])) - set_bit(guest_offloads[i], &vi->guest_offloads); - vi->guest_offloads_capable = vi->guest_offloads; - pr_debug("virtnet: registered device %s with %d RX and TX vq's\n", dev->name, max_queue_pairs); From 8d019b15ddd55d6dc5685b1f51902c4aa8e01939 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:06:54 +0300 Subject: [PATCH 152/385] selftests: net: local_termination: refactor macvlan creation/deletion This will be used in other subtests as well; make new macvlan_create() and macvlan_destroy() functions. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- .../net/forwarding/local_termination.sh | 30 +++++++++++-------- 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 4b364cdf3ef0c..36f3d577d0be8 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -247,19 +247,29 @@ bridge_destroy() ip link del br0 } -standalone() +macvlan_create() { - h1_create - h2_create + local lower=$1 - ip link add link $h2 name macvlan0 type macvlan mode private + ip link add link $lower name macvlan0 type macvlan mode private ip link set macvlan0 address $MACVLAN_ADDR ip link set macvlan0 up +} - run_test $h2 - +macvlan_destroy() +{ ip link del macvlan0 +} + +standalone() +{ + h1_create + h2_create + macvlan_create $h2 + + run_test $h2 + macvlan_destroy h2_destroy h1_destroy } @@ -268,15 +278,11 @@ bridge() { h1_create bridge_create - - ip link add link br0 name macvlan0 type macvlan mode private - ip link set macvlan0 address $MACVLAN_ADDR - ip link set macvlan0 up + macvlan_create br0 run_test br0 - ip link del macvlan0 - + macvlan_destroy bridge_destroy h1_destroy } From 4261fa35185c0112acca0496d3732c8fcfe1dcf2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:06:55 +0300 Subject: [PATCH 153/385] selftests: net: local_termination: parameterize sending interface In future changes we will want to subject the DUT, $h2, to additional VLAN-tagged traffic. For that, we need to run the tests using $h1.100 as a sending interface, rather than the currently hardcoded $h1. Add a parameter to run_test() and modify its 2 callers to explicitly pass $h1, as was implicit before. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- .../net/forwarding/local_termination.sh | 39 ++++++++++--------- 1 file changed, 20 insertions(+), 19 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 36f3d577d0be8..92f0e242d119d 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -104,44 +104,45 @@ mc_route_destroy() run_test() { - local rcv_if_name=$1 - local smac=$(mac_get $h1) + local send_if_name=$1; shift + local rcv_if_name=$1; shift + local smac=$(mac_get $send_if_name) local rcv_dmac=$(mac_get $rcv_if_name) tcpdump_start $rcv_if_name - mc_route_prepare $h1 + mc_route_prepare $send_if_name mc_route_prepare $rcv_if_name - send_uc_ipv4 $h1 $rcv_dmac - send_uc_ipv4 $h1 $MACVLAN_ADDR - send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR1 + send_uc_ipv4 $send_if_name $rcv_dmac + send_uc_ipv4 $send_if_name $MACVLAN_ADDR + send_uc_ipv4 $send_if_name $UNKNOWN_UC_ADDR1 ip link set dev $rcv_if_name promisc on - send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR2 - mc_send $h1 $UNKNOWN_IPV4_MC_ADDR2 - mc_send $h1 $UNKNOWN_IPV6_MC_ADDR2 + send_uc_ipv4 $send_if_name $UNKNOWN_UC_ADDR2 + mc_send $send_if_name $UNKNOWN_IPV4_MC_ADDR2 + mc_send $send_if_name $UNKNOWN_IPV6_MC_ADDR2 ip link set dev $rcv_if_name promisc off mc_join $rcv_if_name $JOINED_IPV4_MC_ADDR - mc_send $h1 $JOINED_IPV4_MC_ADDR + mc_send $send_if_name $JOINED_IPV4_MC_ADDR mc_leave mc_join $rcv_if_name $JOINED_IPV6_MC_ADDR - mc_send $h1 $JOINED_IPV6_MC_ADDR + mc_send $send_if_name $JOINED_IPV6_MC_ADDR mc_leave - mc_send $h1 $UNKNOWN_IPV4_MC_ADDR1 - mc_send $h1 $UNKNOWN_IPV6_MC_ADDR1 + mc_send $send_if_name $UNKNOWN_IPV4_MC_ADDR1 + mc_send $send_if_name $UNKNOWN_IPV6_MC_ADDR1 ip link set dev $rcv_if_name allmulticast on - send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR3 - mc_send $h1 $UNKNOWN_IPV4_MC_ADDR3 - mc_send $h1 $UNKNOWN_IPV6_MC_ADDR3 + send_uc_ipv4 $send_if_name $UNKNOWN_UC_ADDR3 + mc_send $send_if_name $UNKNOWN_IPV4_MC_ADDR3 + mc_send $send_if_name $UNKNOWN_IPV6_MC_ADDR3 ip link set dev $rcv_if_name allmulticast off mc_route_destroy $rcv_if_name - mc_route_destroy $h1 + mc_route_destroy $send_if_name sleep 1 @@ -267,7 +268,7 @@ standalone() h2_create macvlan_create $h2 - run_test $h2 + run_test $h1 $h2 macvlan_destroy h2_destroy @@ -280,7 +281,7 @@ bridge() bridge_create macvlan_create br0 - run_test br0 + run_test $h1 br0 macvlan_destroy bridge_destroy From df7cf5cc551c7c0a92520e91e1184993784c6386 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:06:56 +0300 Subject: [PATCH 154/385] selftests: net: local_termination: parameterize test name There are upcoming tests which verify the RX filtering of a bridge (or bridge port), but under differing vlan_filtering conditions. Since we currently print $h2 (the DUT) in the log_test() output, it becomes necessary to make a further distinction between tests, to not give the user the impression that the exact same thing is run twice. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- .../net/forwarding/local_termination.sh | 38 ++++++++++--------- 1 file changed, 20 insertions(+), 18 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 92f0e242d119d..af284edaf4014 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -68,10 +68,11 @@ send_uc_ipv4() check_rcv() { - local if_name=$1 - local type=$2 - local pattern=$3 - local should_receive=$4 + local if_name=$1; shift + local type=$1; shift + local pattern=$1; shift + local should_receive=$1; shift + local test_name="$1"; shift local should_fail= [ $should_receive = true ] && should_fail=0 || should_fail=1 @@ -81,7 +82,7 @@ check_rcv() check_err_fail "$should_fail" "$?" "reception" - log_test "$if_name: $type" + log_test "$test_name: $type" } mc_route_prepare() @@ -106,6 +107,7 @@ run_test() { local send_if_name=$1; shift local rcv_if_name=$1; shift + local test_name="$1"; shift local smac=$(mac_get $send_if_name) local rcv_dmac=$(mac_get $rcv_if_name) @@ -150,61 +152,61 @@ run_test() check_rcv $rcv_if_name "Unicast IPv4 to primary MAC address" \ "$smac > $rcv_dmac, ethertype IPv4 (0x0800)" \ - true + true "$test_name" check_rcv $rcv_if_name "Unicast IPv4 to macvlan MAC address" \ "$smac > $MACVLAN_ADDR, ethertype IPv4 (0x0800)" \ - true + true "$test_name" xfail_on_veth $h1 \ check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address" \ "$smac > $UNKNOWN_UC_ADDR1, ethertype IPv4 (0x0800)" \ - false + false "$test_name" check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address, promisc" \ "$smac > $UNKNOWN_UC_ADDR2, ethertype IPv4 (0x0800)" \ - true + true "$test_name" xfail_on_veth $h1 \ check_rcv $rcv_if_name \ "Unicast IPv4 to unknown MAC address, allmulti" \ "$smac > $UNKNOWN_UC_ADDR3, ethertype IPv4 (0x0800)" \ - false + false "$test_name" check_rcv $rcv_if_name "Multicast IPv4 to joined group" \ "$smac > $JOINED_MACV4_MC_ADDR, ethertype IPv4 (0x0800)" \ - true + true "$test_name" xfail_on_veth $h1 \ check_rcv $rcv_if_name \ "Multicast IPv4 to unknown group" \ "$smac > $UNKNOWN_MACV4_MC_ADDR1, ethertype IPv4 (0x0800)" \ - false + false "$test_name" check_rcv $rcv_if_name "Multicast IPv4 to unknown group, promisc" \ "$smac > $UNKNOWN_MACV4_MC_ADDR2, ethertype IPv4 (0x0800)" \ - true + true "$test_name" check_rcv $rcv_if_name "Multicast IPv4 to unknown group, allmulti" \ "$smac > $UNKNOWN_MACV4_MC_ADDR3, ethertype IPv4 (0x0800)" \ - true + true "$test_name" check_rcv $rcv_if_name "Multicast IPv6 to joined group" \ "$smac > $JOINED_MACV6_MC_ADDR, ethertype IPv6 (0x86dd)" \ - true + true "$test_name" xfail_on_veth $h1 \ check_rcv $rcv_if_name "Multicast IPv6 to unknown group" \ "$smac > $UNKNOWN_MACV6_MC_ADDR1, ethertype IPv6 (0x86dd)" \ - false + false "$test_name" check_rcv $rcv_if_name "Multicast IPv6 to unknown group, promisc" \ "$smac > $UNKNOWN_MACV6_MC_ADDR2, ethertype IPv6 (0x86dd)" \ - true + true "$test_name" check_rcv $rcv_if_name "Multicast IPv6 to unknown group, allmulti" \ "$smac > $UNKNOWN_MACV6_MC_ADDR3, ethertype IPv6 (0x86dd)" \ - true + true "$test_name" tcpdump_cleanup $rcv_if_name } From 5b8e74182ed3d4f1c38c626e6120275ca9d92bee Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:06:57 +0300 Subject: [PATCH 155/385] selftests: net: local_termination: add one more test for VLAN-aware bridges The current bridge() test is for packet reception on a VLAN-unaware bridge. Some things are different enough with VLAN-aware bridges that it's worth renaming this test into vlan_unaware_bridge(), and add a new vlan_aware_bridge() test. The two will share the same implementation: bridge() becomes a common function, which receives $vlan_filtering as an argument. Rename it to test_bridge() at the same time, because just bridge() pollutes the global namespace and we cannot invoke the binary with the same name from the iproute2 package currently. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- .../net/forwarding/local_termination.sh | 22 +++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index af284edaf4014..5aa364b40e335 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -1,7 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="standalone bridge" +ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge" NUM_NETIFS=2 PING_COUNT=1 REQUIRE_MTOOLS=yes @@ -233,7 +233,9 @@ h2_destroy() bridge_create() { - ip link add br0 type bridge + local vlan_filtering=$1 + + ip link add br0 type bridge vlan_filtering $vlan_filtering ip link set br0 address $BRIDGE_ADDR ip link set br0 up @@ -277,10 +279,12 @@ standalone() h1_destroy } -bridge() +test_bridge() { + local vlan_filtering=$1 + h1_create - bridge_create + bridge_create $vlan_filtering macvlan_create br0 run_test $h1 br0 @@ -290,6 +294,16 @@ bridge() h1_destroy } +vlan_unaware_bridge() +{ + test_bridge 0 +} + +vlan_aware_bridge() +{ + test_bridge 1 +} + cleanup() { pre_cleanup From 5fea8bb009744bbb90b3f6ca41c558429ee4c849 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:06:58 +0300 Subject: [PATCH 156/385] selftests: net: local_termination: introduce new tests which capture VLAN behavior Add more coverage to the local termination selftest as follows: - 8021q upper of $h2 - 8021q upper of $h2, where $h2 is a port of a VLAN-unaware bridge - 8021q upper of $h2, where $h2 is a port of a VLAN-aware bridge - 8021q upper of VLAN-unaware br0, which is the upper of $h2 - 8021q upper of VLAN-aware br0, which is the upper of $h2 Especially the cases with traffic sent through the VLAN upper of a VLAN-aware bridge port will be immediately relevant when we will start transmitting PTP packets as an additional kind of traffic. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- .../net/forwarding/local_termination.sh | 117 ++++++++++++++++-- 1 file changed, 110 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 5aa364b40e335..e22c6a693bef2 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -1,7 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge" +ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge test_vlan \ + vlan_over_vlan_unaware_bridged_port vlan_over_vlan_aware_bridged_port \ + vlan_over_vlan_unaware_bridge vlan_over_vlan_aware_bridge" NUM_NETIFS=2 PING_COUNT=1 REQUIRE_MTOOLS=yes @@ -231,6 +233,30 @@ h2_destroy() simple_if_fini $h2 $H2_IPV4/24 $H2_IPV6/64 } +h1_vlan_create() +{ + simple_if_init $h1 + vlan_create $h1 100 v$h1 $H1_IPV4/24 $H1_IPV6/64 +} + +h1_vlan_destroy() +{ + vlan_destroy $h1 100 + simple_if_fini $h1 +} + +h2_vlan_create() +{ + simple_if_init $h2 + vlan_create $h2 100 v$h2 $H2_IPV4/24 $H2_IPV6/64 +} + +h2_vlan_destroy() +{ + vlan_destroy $h2 100 + simple_if_fini $h2 +} + bridge_create() { local vlan_filtering=$1 @@ -241,14 +267,10 @@ bridge_create() ip link set $h2 master br0 ip link set $h2 up - - simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64 } bridge_destroy() { - simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64 - ip link del br0 } @@ -272,7 +294,7 @@ standalone() h2_create macvlan_create $h2 - run_test $h1 $h2 + run_test $h1 $h2 "$h2" macvlan_destroy h2_destroy @@ -285,11 +307,13 @@ test_bridge() h1_create bridge_create $vlan_filtering + simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64 macvlan_create br0 - run_test $h1 br0 + run_test $h1 br0 "vlan_filtering=$vlan_filtering bridge" macvlan_destroy + simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64 bridge_destroy h1_destroy } @@ -304,6 +328,85 @@ vlan_aware_bridge() test_bridge 1 } +test_vlan() +{ + h1_vlan_create + h2_vlan_create + macvlan_create $h2.100 + + run_test $h1.100 $h2.100 "VLAN upper" + + macvlan_destroy + h2_vlan_destroy + h1_vlan_destroy +} + +vlan_over_bridged_port() +{ + local vlan_filtering=$1 + + h1_vlan_create + h2_vlan_create + bridge_create $vlan_filtering + macvlan_create $h2.100 + + run_test $h1.100 $h2.100 "VLAN over vlan_filtering=$vlan_filtering bridged port" + + macvlan_destroy + bridge_destroy + h2_vlan_destroy + h1_vlan_destroy +} + +vlan_over_vlan_unaware_bridged_port() +{ + vlan_over_bridged_port 0 +} + +vlan_over_vlan_aware_bridged_port() +{ + vlan_over_bridged_port 1 +} + +vlan_over_bridge() +{ + local vlan_filtering=$1 + + h1_vlan_create + bridge_create $vlan_filtering + simple_if_init br0 + vlan_create br0 100 vbr0 $H2_IPV4/24 $H2_IPV6/64 + macvlan_create br0.100 + + if [ $vlan_filtering = 1 ]; then + bridge vlan add dev $h2 vid 100 master + bridge vlan add dev br0 vid 100 self + fi + + run_test $h1.100 br0.100 "VLAN over vlan_filtering=$vlan_filtering bridge" + + if [ $vlan_filtering = 1 ]; then + bridge vlan del dev br0 vid 100 self + bridge vlan del dev $h2 vid 100 master + fi + + macvlan_destroy + vlan_destroy br0 100 + simple_if_fini br0 + bridge_destroy + h1_vlan_destroy +} + +vlan_over_vlan_unaware_bridge() +{ + vlan_over_bridge 0 +} + +vlan_over_vlan_aware_bridge() +{ + vlan_over_bridge 1 +} + cleanup() { pre_cleanup From 9aa3749ca4a880c1a59720aab3eacf344ed8d68d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:06:59 +0300 Subject: [PATCH 157/385] selftests: net: local_termination: don't use xfail_on_veth() xfail_on_veth() for this test is an incorrect approximation which gives false positives and false negatives. When local_termination fails with "reception succeeded, but should have failed", it is because the DUT ($h2) accepts packets even when not configured as promiscuous. This is not something specific to veth; even the bridge behaves that way, but this is not captured by the xfail_on_veth test. The IFF_UNICAST_FLT flag is not explicitly exported to user space, but it can somewhat be determined from the interface's behavior. We have to create a macvlan upper with a different MAC address. This forces a dev_uc_add() call in the kernel. When the unicast filtering list is not empty, but the device doesn't support IFF_UNICAST_FLT, __dev_set_rx_mode() force-enables promiscuity on the interface, to ensure correct behavior (that the requested address is received). We can monitor the change in the promiscuity flag and infer from it whether the device supports unicast filtering. There is no equivalent thing for allmulti, unfortunately. We never know what's hiding behind a device which has allmulti=off. Whether it will actually perform RX multicast filtering of unknown traffic is a strong "maybe". The bridge driver, for example, completely ignores the flag. We'll have to keep the xfail behavior, but instead of XFAIL on just veth, always XFAIL. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- tools/testing/selftests/net/forwarding/lib.sh | 57 ++++++++++++++++++ .../net/forwarding/local_termination.sh | 58 ++++++++++++++----- 2 files changed, 99 insertions(+), 16 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index ff96bb7535ff0..718d04a4f72d0 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -500,6 +500,11 @@ check_err_fail() fi } +xfail() +{ + FAIL_TO_XFAIL=yes "$@" +} + xfail_on_slow() { if [[ $KSFT_MACHINE_SLOW = yes ]]; then @@ -1113,6 +1118,39 @@ mac_get() ip -j link show dev $if_name | jq -r '.[]["address"]' } +ether_addr_to_u64() +{ + local addr="$1" + local order="$((1 << 40))" + local val=0 + local byte + + addr="${addr//:/ }" + + for byte in $addr; do + byte="0x$byte" + val=$((val + order * byte)) + order=$((order >> 8)) + done + + printf "0x%x" $val +} + +u64_to_ether_addr() +{ + local val=$1 + local byte + local i + + for ((i = 40; i >= 0; i -= 8)); do + byte=$(((val & (0xff << i)) >> i)) + printf "%02x" $byte + if [ $i -ne 0 ]; then + printf ":" + fi + done +} + ipv6_lladdr_get() { local if_name=$1 @@ -2229,3 +2267,22 @@ absval() echo $((v > 0 ? v : -v)) } + +has_unicast_flt() +{ + local dev=$1; shift + local mac_addr=$(mac_get $dev) + local tmp=$(ether_addr_to_u64 $mac_addr) + local promisc + + ip link set $dev up + ip link add link $dev name macvlan-tmp type macvlan mode private + ip link set macvlan-tmp address $(u64_to_ether_addr $((tmp + 1))) + ip link set macvlan-tmp up + + promisc=$(ip -j -d link show dev $dev | jq -r '.[].promiscuity') + + ip link del macvlan-tmp + + [[ $promisc == 1 ]] && echo "no" || echo "yes" +} diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index e22c6a693bef2..80ea4c10d7649 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -109,9 +109,11 @@ run_test() { local send_if_name=$1; shift local rcv_if_name=$1; shift + local no_unicast_flt=$1; shift local test_name="$1"; shift local smac=$(mac_get $send_if_name) local rcv_dmac=$(mac_get $rcv_if_name) + local should_receive tcpdump_start $rcv_if_name @@ -160,26 +162,26 @@ run_test() "$smac > $MACVLAN_ADDR, ethertype IPv4 (0x0800)" \ true "$test_name" - xfail_on_veth $h1 \ - check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address" \ - "$smac > $UNKNOWN_UC_ADDR1, ethertype IPv4 (0x0800)" \ - false "$test_name" + [ $no_unicast_flt = true ] && should_receive=true || should_receive=false + check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address" \ + "$smac > $UNKNOWN_UC_ADDR1, ethertype IPv4 (0x0800)" \ + $should_receive "$test_name" check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address, promisc" \ "$smac > $UNKNOWN_UC_ADDR2, ethertype IPv4 (0x0800)" \ true "$test_name" - xfail_on_veth $h1 \ - check_rcv $rcv_if_name \ - "Unicast IPv4 to unknown MAC address, allmulti" \ - "$smac > $UNKNOWN_UC_ADDR3, ethertype IPv4 (0x0800)" \ - false "$test_name" + [ $no_unicast_flt = true ] && should_receive=true || should_receive=false + check_rcv $rcv_if_name \ + "Unicast IPv4 to unknown MAC address, allmulti" \ + "$smac > $UNKNOWN_UC_ADDR3, ethertype IPv4 (0x0800)" \ + $should_receive "$test_name" check_rcv $rcv_if_name "Multicast IPv4 to joined group" \ "$smac > $JOINED_MACV4_MC_ADDR, ethertype IPv4 (0x0800)" \ true "$test_name" - xfail_on_veth $h1 \ + xfail \ check_rcv $rcv_if_name \ "Multicast IPv4 to unknown group" \ "$smac > $UNKNOWN_MACV4_MC_ADDR1, ethertype IPv4 (0x0800)" \ @@ -197,7 +199,7 @@ run_test() "$smac > $JOINED_MACV6_MC_ADDR, ethertype IPv6 (0x86dd)" \ true "$test_name" - xfail_on_veth $h1 \ + xfail \ check_rcv $rcv_if_name "Multicast IPv6 to unknown group" \ "$smac > $UNKNOWN_MACV6_MC_ADDR1, ethertype IPv6 (0x86dd)" \ false "$test_name" @@ -290,11 +292,17 @@ macvlan_destroy() standalone() { + local no_unicast_flt=true + + if [ $(has_unicast_flt $h2) = yes ]; then + no_unicast_flt=false + fi + h1_create h2_create macvlan_create $h2 - run_test $h1 $h2 "$h2" + run_test $h1 $h2 $no_unicast_flt "$h2" macvlan_destroy h2_destroy @@ -303,6 +311,7 @@ standalone() test_bridge() { + local no_unicast_flt=true local vlan_filtering=$1 h1_create @@ -310,7 +319,7 @@ test_bridge() simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64 macvlan_create br0 - run_test $h1 br0 "vlan_filtering=$vlan_filtering bridge" + run_test $h1 br0 $no_unicast_flt "vlan_filtering=$vlan_filtering bridge" macvlan_destroy simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64 @@ -330,11 +339,17 @@ vlan_aware_bridge() test_vlan() { + local no_unicast_flt=true + + if [ $(has_unicast_flt $h2) = yes ]; then + no_unicast_flt=false + fi + h1_vlan_create h2_vlan_create macvlan_create $h2.100 - run_test $h1.100 $h2.100 "VLAN upper" + run_test $h1.100 $h2.100 $no_unicast_flt "VLAN upper" macvlan_destroy h2_vlan_destroy @@ -343,14 +358,23 @@ test_vlan() vlan_over_bridged_port() { + local no_unicast_flt=true local vlan_filtering=$1 + # br_manage_promisc() will not force a single vlan_filtering port to + # promiscuous mode, so we should still expect unicast filtering to take + # place if the device can do it. + if [ $(has_unicast_flt $h2) = yes ] && [ $vlan_filtering = 1 ]; then + no_unicast_flt=false + fi + h1_vlan_create h2_vlan_create bridge_create $vlan_filtering macvlan_create $h2.100 - run_test $h1.100 $h2.100 "VLAN over vlan_filtering=$vlan_filtering bridged port" + run_test $h1.100 $h2.100 $no_unicast_flt \ + "VLAN over vlan_filtering=$vlan_filtering bridged port" macvlan_destroy bridge_destroy @@ -370,6 +394,7 @@ vlan_over_vlan_aware_bridged_port() vlan_over_bridge() { + local no_unicast_flt=true local vlan_filtering=$1 h1_vlan_create @@ -383,7 +408,8 @@ vlan_over_bridge() bridge vlan add dev br0 vid 100 self fi - run_test $h1.100 br0.100 "VLAN over vlan_filtering=$vlan_filtering bridge" + run_test $h1.100 br0.100 $no_unicast_flt \ + "VLAN over vlan_filtering=$vlan_filtering bridge" if [ $vlan_filtering = 1 ]; then bridge vlan del dev br0 vid 100 self From 237979504264912a9797dabc0db35126e705fe0d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:00 +0300 Subject: [PATCH 158/385] selftests: net: local_termination: add PTP frames to the mix A breakage in the felix DSA driver shows we do not have enough test coverage. More generally, it is sufficiently special that it is likely drivers will treat it differently. This is not meant to be a full PTP test, it just makes sure that PTP packets sent to the different addresses corresponding to their profiles are received correctly. The local_termination selftest seemed like the most appropriate place for this addition. PTP RX/TX in some cases makes no sense (over a bridge) and this is why $skip_ptp exists. And in others - PTP over a bridge port - the IP stack needs convincing through the available bridge netfilter hooks to leave the PTP packets alone and not stolen by the bridge rx_handler. It is safe to assume that users have that figured out already. This is a driver level test, and by using tcpdump, all that extra setup is out of scope here. send_non_ip() was an unfinished idea; written but never used. Replace it with a more generic send_raw(), and send 3 PTP packet types times 3 transports. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- .../net/forwarding/local_termination.sh | 161 ++++++++++++++++-- 1 file changed, 148 insertions(+), 13 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index 80ea4c10d7649..648868f746044 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -39,9 +39,68 @@ UNKNOWN_MACV6_MC_ADDR1="33:33:01:02:03:05" UNKNOWN_MACV6_MC_ADDR2="33:33:01:02:03:06" UNKNOWN_MACV6_MC_ADDR3="33:33:01:02:03:07" -NON_IP_MC="01:02:03:04:05:06" -NON_IP_PKT="00:04 48:45:4c:4f" -BC="ff:ff:ff:ff:ff:ff" +PTP_1588_L2_SYNC=" \ +01:1b:19:00:00:00 00:00:de:ad:be:ef 88:f7 00 02 \ +00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 00 00 \ +00 00 00 00 00 00 00 00 00 00" +PTP_1588_L2_FOLLOW_UP=" \ +01:1b:19:00:00:00 00:00:de:ad:be:ef 88:f7 08 02 \ +00 2c 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 02 00 \ +00 00 66 83 c5 f1 17 97 ed f0" +PTP_1588_L2_PDELAY_REQ=" \ +01:80:c2:00:00:0e 00:00:de:ad:be:ef 88:f7 02 02 \ +00 36 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 06 05 7f \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 00 00" +PTP_1588_IPV4_SYNC=" \ +01:00:5e:00:01:81 00:00:de:ad:be:ef 08:00 45 00 \ +00 48 0a 9a 40 00 01 11 cb 88 c0 00 02 01 e0 00 \ +01 81 01 3f 01 3f 00 34 a3 c8 00 02 00 2c 00 00 \ +02 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \ +63 ff fe cf 17 0e 00 01 00 00 00 00 00 00 00 00 \ +00 00 00 00 00 00" +PTP_1588_IPV4_FOLLOW_UP=" +01:00:5e:00:01:81 00:00:de:ad:be:ef 08:00 45 00 \ +00 48 0a 9b 40 00 01 11 cb 87 c0 00 02 01 e0 00 \ +01 81 01 40 01 40 00 34 a3 c8 08 02 00 2c 00 00 \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \ +63 ff fe cf 17 0e 00 01 00 00 02 00 00 00 66 83 \ +c6 0f 1d 9a 61 87" +PTP_1588_IPV4_PDELAY_REQ=" \ +01:00:5e:00:00:6b 00:00:de:ad:be:ef 08:00 45 00 \ +00 52 35 a9 40 00 01 11 a1 85 c0 00 02 01 e0 00 \ +00 6b 01 3f 01 3f 00 3e a2 bc 02 02 00 36 00 00 \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \ +63 ff fe cf 17 0e 00 01 00 01 05 7f 00 00 00 00 \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00" +PTP_1588_IPV6_SYNC=" \ +33:33:00:00:01:81 00:00:de:ad:be:ef 86:dd 60 06 \ +7c 2f 00 36 11 01 20 01 0d b8 00 01 00 00 00 00 \ +00 00 00 00 00 01 ff 0e 00 00 00 00 00 00 00 00 \ +00 00 00 00 01 81 01 3f 01 3f 00 36 2e 92 00 02 \ +00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 00 00 \ +00 00 00 00 00 00 00 00 00 00 00 00" +PTP_1588_IPV6_FOLLOW_UP=" \ +33:33:00:00:01:81 00:00:de:ad:be:ef 86:dd 60 0a \ +00 bc 00 36 11 01 20 01 0d b8 00 01 00 00 00 00 \ +00 00 00 00 00 01 ff 0e 00 00 00 00 00 00 00 00 \ +00 00 00 00 01 81 01 40 01 40 00 36 2e 92 08 02 \ +00 2c 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 02 00 \ +00 00 66 83 c6 2a 32 09 bd 74 00 00" +PTP_1588_IPV6_PDELAY_REQ=" \ +33:33:00:00:00:6b 00:00:de:ad:be:ef 86:dd 60 0c \ +5c fd 00 40 11 01 fe 80 00 00 00 00 00 00 3c 37 \ +63 ff fe cf 17 0e ff 02 00 00 00 00 00 00 00 00 \ +00 00 00 00 00 6b 01 3f 01 3f 00 40 b4 54 02 02 \ +00 36 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 3e 37 63 ff fe cf 17 0e 00 01 00 01 05 7f \ +00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \ +00 00 00 00 00 00" # Disable promisc to ensure we don't receive unknown MAC DA packets export TCPDUMP_EXTRA_FLAGS="-pl" @@ -49,13 +108,15 @@ export TCPDUMP_EXTRA_FLAGS="-pl" h1=${NETIFS[p1]} h2=${NETIFS[p2]} -send_non_ip() +send_raw() { - local if_name=$1 - local smac=$2 - local dmac=$3 + local if_name=$1; shift + local pkt="$1"; shift + local smac=$(mac_get $if_name) - $MZ -q $if_name "$dmac $smac $NON_IP_PKT" + pkt="${pkt/00:00:de:ad:be:ef/$smac}" + + $MZ -q $if_name "$pkt" } send_uc_ipv4() @@ -109,6 +170,7 @@ run_test() { local send_if_name=$1; shift local rcv_if_name=$1; shift + local skip_ptp=$1; shift local no_unicast_flt=$1; shift local test_name="$1"; shift local smac=$(mac_get $send_if_name) @@ -150,6 +212,35 @@ run_test() mc_route_destroy $rcv_if_name mc_route_destroy $send_if_name + if [ $skip_ptp = false ]; then + ip maddress add 01:1b:19:00:00:00 dev $rcv_if_name + send_raw $send_if_name "$PTP_1588_L2_SYNC" + send_raw $send_if_name "$PTP_1588_L2_FOLLOW_UP" + ip maddress del 01:1b:19:00:00:00 dev $rcv_if_name + + ip maddress add 01:80:c2:00:00:0e dev $rcv_if_name + send_raw $send_if_name "$PTP_1588_L2_PDELAY_REQ" + ip maddress del 01:80:c2:00:00:0e dev $rcv_if_name + + mc_join $rcv_if_name 224.0.1.129 + send_raw $send_if_name "$PTP_1588_IPV4_SYNC" + send_raw $send_if_name "$PTP_1588_IPV4_FOLLOW_UP" + mc_leave + + mc_join $rcv_if_name 224.0.0.107 + send_raw $send_if_name "$PTP_1588_IPV4_PDELAY_REQ" + mc_leave + + mc_join $rcv_if_name ff0e::181 + send_raw $send_if_name "$PTP_1588_IPV6_SYNC" + send_raw $send_if_name "$PTP_1588_IPV6_FOLLOW_UP" + mc_leave + + mc_join $rcv_if_name ff02::6b + send_raw $send_if_name "$PTP_1588_IPV6_PDELAY_REQ" + mc_leave + fi + sleep 1 tcpdump_stop $rcv_if_name @@ -212,6 +303,44 @@ run_test() "$smac > $UNKNOWN_MACV6_MC_ADDR3, ethertype IPv6 (0x86dd)" \ true "$test_name" + if [ $skip_ptp = false ]; then + check_rcv $rcv_if_name "1588v2 over L2 transport, Sync" \ + "ethertype PTP (0x88f7).* PTPv2.* msg type : sync msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over L2 transport, Follow-Up" \ + "ethertype PTP (0x88f7).* PTPv2.* msg type : follow up msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over L2 transport, Peer Delay Request" \ + "ethertype PTP (0x88f7).* PTPv2.* msg type : peer delay req msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv4, Sync" \ + "ethertype IPv4 (0x0800).* PTPv2.* msg type : sync msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv4, Follow-Up" \ + "ethertype IPv4 (0x0800).* PTPv2.* msg type : follow up msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv4, Peer Delay Request" \ + "ethertype IPv4 (0x0800).* PTPv2.* msg type : peer delay req msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv6, Sync" \ + "ethertype IPv6 (0x86dd).* PTPv2.* msg type : sync msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv6, Follow-Up" \ + "ethertype IPv6 (0x86dd).* PTPv2.* msg type : follow up msg" \ + true "$test_name" + + check_rcv $rcv_if_name "1588v2 over IPv6, Peer Delay Request" \ + "ethertype IPv6 (0x86dd).* PTPv2.* msg type : peer delay req msg" \ + true "$test_name" + fi + tcpdump_cleanup $rcv_if_name } @@ -293,6 +422,7 @@ macvlan_destroy() standalone() { local no_unicast_flt=true + local skip_ptp=false if [ $(has_unicast_flt $h2) = yes ]; then no_unicast_flt=false @@ -302,7 +432,7 @@ standalone() h2_create macvlan_create $h2 - run_test $h1 $h2 $no_unicast_flt "$h2" + run_test $h1 $h2 $skip_ptp $no_unicast_flt "$h2" macvlan_destroy h2_destroy @@ -313,13 +443,15 @@ test_bridge() { local no_unicast_flt=true local vlan_filtering=$1 + local skip_ptp=true h1_create bridge_create $vlan_filtering simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64 macvlan_create br0 - run_test $h1 br0 $no_unicast_flt "vlan_filtering=$vlan_filtering bridge" + run_test $h1 br0 $skip_ptp $no_unicast_flt \ + "vlan_filtering=$vlan_filtering bridge" macvlan_destroy simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64 @@ -340,6 +472,7 @@ vlan_aware_bridge() test_vlan() { local no_unicast_flt=true + local skip_ptp=false if [ $(has_unicast_flt $h2) = yes ]; then no_unicast_flt=false @@ -349,7 +482,7 @@ test_vlan() h2_vlan_create macvlan_create $h2.100 - run_test $h1.100 $h2.100 $no_unicast_flt "VLAN upper" + run_test $h1.100 $h2.100 $skip_ptp $no_unicast_flt "VLAN upper" macvlan_destroy h2_vlan_destroy @@ -360,6 +493,7 @@ vlan_over_bridged_port() { local no_unicast_flt=true local vlan_filtering=$1 + local skip_ptp=false # br_manage_promisc() will not force a single vlan_filtering port to # promiscuous mode, so we should still expect unicast filtering to take @@ -373,7 +507,7 @@ vlan_over_bridged_port() bridge_create $vlan_filtering macvlan_create $h2.100 - run_test $h1.100 $h2.100 $no_unicast_flt \ + run_test $h1.100 $h2.100 $skip_ptp $no_unicast_flt \ "VLAN over vlan_filtering=$vlan_filtering bridged port" macvlan_destroy @@ -396,6 +530,7 @@ vlan_over_bridge() { local no_unicast_flt=true local vlan_filtering=$1 + local skip_ptp=true h1_vlan_create bridge_create $vlan_filtering @@ -408,7 +543,7 @@ vlan_over_bridge() bridge vlan add dev br0 vid 100 self fi - run_test $h1.100 br0.100 $no_unicast_flt \ + run_test $h1.100 br0.100 $skip_ptp $no_unicast_flt \ "VLAN over vlan_filtering=$vlan_filtering bridge" if [ $vlan_filtering = 1 ]; then From e29b82ef27616777e21c07dc263a8769cbdaa358 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:01 +0300 Subject: [PATCH 159/385] selftests: net: bridge_vlan_aware: test that other TPIDs are seen as untagged The bridge VLAN implementation w.r.t. VLAN protocol is described in merge commit 1a0b20b25732 ("Merge branch 'bridge-next'"). We are only sensitive to those VLAN tags whose TPID is equal to the bridge's vlan_protocol. Thus, an 802.1ad VLAN should be treated as 802.1Q-untagged. Add 3 tests which validate that: - 802.1ad-tagged traffic is learned into the PVID of an 802.1Q-aware bridge - Double-tagged traffic is forwarded when just the PVID of the port is present in the VLAN group of the ports - Double-tagged traffic is not forwarded when the PVID of the port is absent from the VLAN group of the ports The test passes with both veth and ocelot. Signed-off-by: Vladimir Oltean Reviewed-by: Ido Schimmel Tested-by: Ido Schimmel Signed-off-by: David S. Miller --- .../net/forwarding/bridge_vlan_aware.sh | 54 ++++++++++++++++++- 1 file changed, 53 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh index 64bd00fe9a4f8..90f8a244ea901 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh @@ -1,7 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn" +ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid" NUM_NETIFS=4 CHECK_TC="yes" source lib.sh @@ -142,6 +142,58 @@ extern_learn() bridge fdb del de:ad:be:ef:13:37 dev $swp1 master vlan 1 &> /dev/null } +other_tpid() +{ + local mac=de:ad:be:ef:13:37 + + # Test that packets with TPID 802.1ad VID 3 + TPID 802.1Q VID 5 are + # classified as untagged by a bridge with vlan_protocol 802.1Q, and + # are processed in the PVID of the ingress port (here 1). Not VID 3, + # and not VID 5. + RET=0 + + tc qdisc add dev $h2 clsact + tc filter add dev $h2 ingress protocol all pref 1 handle 101 \ + flower dst_mac $mac action drop + ip link set $h2 promisc on + ethtool -K $h2 rx-vlan-filter off rx-vlan-stag-filter off + + $MZ -q $h1 -c 1 -b $mac -a own "88:a8 00:03 81:00 00:05 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa" + sleep 1 + + # Match on 'self' addresses as well, for those drivers which + # do not push their learned addresses to the bridge software + # database + bridge -j fdb show $swp1 | \ + jq -e ".[] | select(.mac == \"$(mac_get $h1)\") | select(.vlan == 1)" &> /dev/null + check_err $? "FDB entry was not learned when it should" + + log_test "FDB entry in PVID for VLAN-tagged with other TPID" + + RET=0 + tc -j -s filter show dev $h2 ingress \ + | jq -e ".[] | select(.options.handle == 101) \ + | select(.options.actions[0].stats.packets == 1)" &> /dev/null + check_err $? "Packet was not forwarded when it should" + log_test "Reception of VLAN with other TPID as untagged" + + bridge vlan del dev $swp1 vid 1 + + $MZ -q $h1 -c 1 -b $mac -a own "88:a8 00:03 81:00 00:05 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa" + sleep 1 + + RET=0 + tc -j -s filter show dev $h2 ingress \ + | jq -e ".[] | select(.options.handle == 101) \ + | select(.options.actions[0].stats.packets == 1)" &> /dev/null + check_err $? "Packet was forwarded when should not" + log_test "Reception of VLAN with other TPID as untagged (no PVID)" + + bridge vlan add dev $swp1 vid 1 pvid untagged + ip link set $h2 promisc off + tc qdisc del dev $h2 clsact +} + trap cleanup EXIT setup_prepare From 67c3ca2c5cfe6a50772514e3349b5e7b3b0fac03 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:02 +0300 Subject: [PATCH 160/385] net: mscc: ocelot: use ocelot_xmit_get_vlan_info() also for FDMA and register injection Problem description ------------------- On an NXP LS1028A (felix DSA driver) with the following configuration: - ocelot-8021q tagging protocol - VLAN-aware bridge (with STP) spanning at least swp0 and swp1 - 8021q VLAN upper interfaces on swp0 and swp1: swp0.700, swp1.700 - ptp4l on swp0.700 and swp1.700 we see that the ptp4l instances do not see each other's traffic, and they all go to the grand master state due to the ANNOUNCE_RECEIPT_TIMEOUT_EXPIRES condition. Jumping to the conclusion for the impatient ------------------------------------------- There is a zero-day bug in the ocelot switchdev driver in the way it handles VLAN-tagged packet injection. The correct logic already exists in the source code, in function ocelot_xmit_get_vlan_info() added by commit 5ca721c54d86 ("net: dsa: tag_ocelot: set the classified VLAN during xmit"). But it is used only for normal NPI-based injection with the DSA "ocelot" tagging protocol. The other injection code paths (register-based and FDMA-based) roll their own wrong logic. This affects and was noticed on the DSA "ocelot-8021q" protocol because it uses register-based injection. By moving ocelot_xmit_get_vlan_info() to a place that's common for both the DSA tagger and the ocelot switch library, it can also be called from ocelot_port_inject_frame() in ocelot.c. We need to touch the lines with ocelot_ifh_port_set()'s prototype anyway, so let's rename it to something clearer regarding what it does, and add a kernel-doc. ocelot_ifh_set_basic() should do. Investigation notes ------------------- Debugging reveals that PTP event (aka those carrying timestamps, like Sync) frames injected into swp0.700 (but also swp1.700) hit the wire with two VLAN tags: 00000000: 01 1b 19 00 00 00 00 01 02 03 04 05 81 00 02 bc ~~~~~~~~~~~ 00000010: 81 00 02 bc 88 f7 00 12 00 2c 00 00 02 00 00 00 ~~~~~~~~~~~ 00000020: 00 00 00 00 00 00 00 00 00 00 00 01 02 ff fe 03 00000030: 04 05 00 01 00 04 00 00 00 00 00 00 00 00 00 00 00000040: 00 00 The second (unexpected) VLAN tag makes felix_check_xtr_pkt() -> ptp_classify_raw() fail to see these as PTP packets at the link partner's receiving end, and return PTP_CLASS_NONE (because the BPF classifier is not written to expect 2 VLAN tags). The reason why packets have 2 VLAN tags is because the transmission code treats VLAN incorrectly. Neither ocelot switchdev, nor felix DSA, declare the NETIF_F_HW_VLAN_CTAG_TX feature. Therefore, at xmit time, all VLANs should be in the skb head, and none should be in the hwaccel area. This is done by: static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tag_present(skb) && !vlan_hw_offload_capable(features, skb->vlan_proto)) skb = __vlan_hwaccel_push_inside(skb); return skb; } But ocelot_port_inject_frame() handles things incorrectly: ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); void ocelot_ifh_port_set(struct sk_buff *skb, void *ifh, int port, u32 rew_op) { (...) if (vlan_tag) ocelot_ifh_set_vlan_tci(ifh, vlan_tag); (...) } The way __vlan_hwaccel_push_inside() pushes the tag inside the skb head is by calling: static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) { skb->vlan_present = 0; } which does _not_ zero out skb->vlan_tci as seen by skb_vlan_tag_get(). This means that ocelot, when it calls skb_vlan_tag_get(), sees (and uses) a residual skb->vlan_tci, while the same VLAN tag is _already_ in the skb head. The trivial fix for double VLAN headers is to replace the content of ocelot_ifh_port_set() with: if (skb_vlan_tag_present(skb)) ocelot_ifh_set_vlan_tci(ifh, skb_vlan_tag_get(skb)); but this would not be correct either, because, as mentioned, vlan_hw_offload_capable() is false for us, so we'd be inserting dead code and we'd always transmit packets with VID=0 in the injection frame header. I can't actually test the ocelot switchdev driver and rely exclusively on code inspection, but I don't think traffic from 8021q uppers has ever been injected properly, and not double-tagged. Thus I'm blaming the introduction of VLAN fields in the injection header - early driver code. As hinted at in the early conclusion, what we _want_ to happen for VLAN transmission was already described once in commit 5ca721c54d86 ("net: dsa: tag_ocelot: set the classified VLAN during xmit"). ocelot_xmit_get_vlan_info() intends to ensure that if the port through which we're transmitting is under a VLAN-aware bridge, the outer VLAN tag from the skb head is stripped from there and inserted into the injection frame header (so that the packet is processed in hardware through that actual VLAN). And in all other cases, the packet is sent with VID=0 in the injection frame header, since the port is VLAN-unaware and has logic to strip this VID on egress (making it invisible to the wire). Fixes: 08d02364b12f ("net: mscc: fix the injection header") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 29 +++++++++++---- drivers/net/ethernet/mscc/ocelot_fdma.c | 2 +- include/linux/dsa/ocelot.h | 47 +++++++++++++++++++++++++ include/soc/mscc/ocelot.h | 3 +- net/dsa/tag_ocelot.c | 37 ++----------------- 5 files changed, 75 insertions(+), 43 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index ed2fb44500b0c..69a4e5a90475b 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1193,17 +1193,34 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp) } EXPORT_SYMBOL(ocelot_can_inject); -void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag) +/** + * ocelot_ifh_set_basic - Set basic information in Injection Frame Header + * @ifh: Pointer to Injection Frame Header memory + * @ocelot: Switch private data structure + * @port: Egress port number + * @rew_op: Egress rewriter operation for PTP + * @skb: Pointer to socket buffer (packet) + * + * Populate the Injection Frame Header with basic information for this skb: the + * analyzer bypass bit, destination port, VLAN info, egress rewriter info. + */ +void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, + u32 rew_op, struct sk_buff *skb) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + u64 vlan_tci, tag_type; + + ocelot_xmit_get_vlan_info(skb, ocelot_port->bridge, &vlan_tci, + &tag_type); + ocelot_ifh_set_bypass(ifh, 1); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); - ocelot_ifh_set_tag_type(ifh, IFH_TAG_TYPE_C); - if (vlan_tag) - ocelot_ifh_set_vlan_tci(ifh, vlan_tag); + ocelot_ifh_set_tag_type(ifh, tag_type); + ocelot_ifh_set_vlan_tci(ifh, vlan_tci); if (rew_op) ocelot_ifh_set_rew_op(ifh, rew_op); } -EXPORT_SYMBOL(ocelot_ifh_port_set); +EXPORT_SYMBOL(ocelot_ifh_set_basic); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb) @@ -1214,7 +1231,7 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) | QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp); - ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb); for (i = 0; i < OCELOT_TAG_LEN / 4; i++) ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp); diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c index 312a468321544..87b59cc5e4416 100644 --- a/drivers/net/ethernet/mscc/ocelot_fdma.c +++ b/drivers/net/ethernet/mscc/ocelot_fdma.c @@ -666,7 +666,7 @@ static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op, ifh = skb_push(skb, OCELOT_TAG_LEN); skb_put(skb, ETH_FCS_LEN); memset(ifh, 0, OCELOT_TAG_LEN); - ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb); return 0; } diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index dca2969015d80..6fbfbde68a37c 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -5,6 +5,8 @@ #ifndef _NET_DSA_TAG_OCELOT_H #define _NET_DSA_TAG_OCELOT_H +#include +#include #include #include #include @@ -273,4 +275,49 @@ static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb) return rew_op; } +/** + * ocelot_xmit_get_vlan_info: Determine VLAN_TCI and TAG_TYPE for injected frame + * @skb: Pointer to socket buffer + * @br: Pointer to bridge device that the port is under, if any + * @vlan_tci: + * @tag_type: + * + * If the port is under a VLAN-aware bridge, remove the VLAN header from the + * payload and move it into the DSA tag, which will make the switch classify + * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, + * which is the pvid of standalone ports (OCELOT_STANDALONE_PVID), although not + * of VLAN-unaware bridge ports (that would be ocelot_vlan_unaware_pvid()). + * Anyway, VID 0 is fine because it is stripped on egress for these port modes, + * and source address learning is not performed for packets injected from the + * CPU anyway, so it doesn't matter that the VID is "wrong". + */ +static inline void ocelot_xmit_get_vlan_info(struct sk_buff *skb, + struct net_device *br, + u64 *vlan_tci, u64 *tag_type) +{ + struct vlan_ethhdr *hdr; + u16 proto, tci; + + if (!br || !br_vlan_enabled(br)) { + *vlan_tci = 0; + *tag_type = IFH_TAG_TYPE_C; + return; + } + + hdr = (struct vlan_ethhdr *)skb_mac_header(skb); + br_vlan_get_proto(br, &proto); + + if (ntohs(hdr->h_vlan_proto) == proto) { + vlan_remove_tag(skb, &tci); + *vlan_tci = tci; + } else { + rcu_read_lock(); + br_vlan_get_pvid_rcu(br, &tci); + rcu_read_unlock(); + *vlan_tci = tci; + } + + *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; +} + #endif diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 6a37b29f4b4c7..ed18e6bafc8d0 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -969,7 +969,8 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb); -void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag); +void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, + u32 rew_op, struct sk_buff *skb); int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb); void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp); void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index e0e4300bfbd3f..bf6608fc6be70 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -8,40 +8,6 @@ #define OCELOT_NAME "ocelot" #define SEVILLE_NAME "seville" -/* If the port is under a VLAN-aware bridge, remove the VLAN header from the - * payload and move it into the DSA tag, which will make the switch classify - * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, - * which is the pvid of standalone and VLAN-unaware bridge ports. - */ -static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp, - u64 *vlan_tci, u64 *tag_type) -{ - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct vlan_ethhdr *hdr; - u16 proto, tci; - - if (!br || !br_vlan_enabled(br)) { - *vlan_tci = 0; - *tag_type = IFH_TAG_TYPE_C; - return; - } - - hdr = skb_vlan_eth_hdr(skb); - br_vlan_get_proto(br, &proto); - - if (ntohs(hdr->h_vlan_proto) == proto) { - vlan_remove_tag(skb, &tci); - *vlan_tci = tci; - } else { - rcu_read_lock(); - br_vlan_get_pvid_rcu(br, &tci); - rcu_read_unlock(); - *vlan_tci = tci; - } - - *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; -} - static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, __be32 ifh_prefix, void **ifh) { @@ -53,7 +19,8 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, u32 rew_op = 0; u64 qos_class; - ocelot_xmit_get_vlan_info(skb, dp, &vlan_tci, &tag_type); + ocelot_xmit_get_vlan_info(skb, dsa_port_bridge_dev_get(dp), &vlan_tci, + &tag_type); qos_class = netdev_get_num_tc(netdev) ? netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority; From e1b9e80236c540fa85d76e2d510d1b38e1968c5d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:03 +0300 Subject: [PATCH 161/385] net: mscc: ocelot: fix QoS class for injected packets with "ocelot-8021q" There are 2 distinct code paths (listed below) in the source code which set up an injection header for Ocelot(-like) switches. Code path (2) lacks the QoS class and source port being set correctly. Especially the improper QoS classification is a problem for the "ocelot-8021q" alternative DSA tagging protocol, because we support tc-taprio and each packet needs to be scheduled precisely through its time slot. This includes PTP, which is normally assigned to a traffic class other than 0, but would be sent through TC 0 nonetheless. The code paths are: (1) ocelot_xmit_common() from net/dsa/tag_ocelot.c - called only by the standard "ocelot" DSA tagging protocol which uses NPI-based injection - sets up bit fields in the tag manually to account for a small difference (destination port offset) between Ocelot and Seville. Namely, ocelot_ifh_set_dest() is omitted out of ocelot_xmit_common(), because there's also seville_ifh_set_dest(). (2) ocelot_ifh_set_basic(), called by: - ocelot_fdma_prepare_skb() for FDMA transmission of the ocelot switchdev driver - ocelot_port_xmit() -> ocelot_port_inject_frame() for register-based transmission of the ocelot switchdev driver - felix_port_deferred_xmit() -> ocelot_port_inject_frame() for the DSA tagger ocelot-8021q when it must transmit PTP frames (also through register-based injection). sets the bit fields according to its own logic. The problem is that (2) doesn't call ocelot_ifh_set_qos_class(). Copying that logic from ocelot_xmit_common() fixes that. Unfortunately, although desirable, it is not easily possible to de-duplicate code paths (1) and (2), and make net/dsa/tag_ocelot.c directly call ocelot_ifh_set_basic()), because of the ocelot/seville difference. This is the "minimal" fix with some logic duplicated (but at least more consolidated). Fixes: 0a6f17c6ae21 ("net: dsa: tag_ocelot_8021q: add support for PTP timestamping") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 10 +++++++++- drivers/net/ethernet/mscc/ocelot_fdma.c | 1 - 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 69a4e5a90475b..9301716e21d58 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1208,13 +1208,21 @@ void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, u32 rew_op, struct sk_buff *skb) { struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct net_device *dev = skb->dev; u64 vlan_tci, tag_type; + int qos_class; ocelot_xmit_get_vlan_info(skb, ocelot_port->bridge, &vlan_tci, &tag_type); + qos_class = netdev_get_num_tc(dev) ? + netdev_get_prio_tc_map(dev, skb->priority) : skb->priority; + + memset(ifh, 0, OCELOT_TAG_LEN); ocelot_ifh_set_bypass(ifh, 1); + ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports)); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); + ocelot_ifh_set_qos_class(ifh, qos_class); ocelot_ifh_set_tag_type(ifh, tag_type); ocelot_ifh_set_vlan_tci(ifh, vlan_tci); if (rew_op) @@ -1225,7 +1233,7 @@ EXPORT_SYMBOL(ocelot_ifh_set_basic); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb) { - u32 ifh[OCELOT_TAG_LEN / 4] = {0}; + u32 ifh[OCELOT_TAG_LEN / 4]; unsigned int i, count, last; ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) | diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c index 87b59cc5e4416..00326ae8c708b 100644 --- a/drivers/net/ethernet/mscc/ocelot_fdma.c +++ b/drivers/net/ethernet/mscc/ocelot_fdma.c @@ -665,7 +665,6 @@ static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op, ifh = skb_push(skb, OCELOT_TAG_LEN); skb_put(skb, ETH_FCS_LEN); - memset(ifh, 0, OCELOT_TAG_LEN); ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb); return 0; From c5e12ac3beb0dd3a718296b2d8af5528e9ab728e Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:04 +0300 Subject: [PATCH 162/385] net: mscc: ocelot: serialize access to the injection/extraction groups As explained by Horatiu Vultur in commit 603ead96582d ("net: sparx5: Add spinlock for frame transmission from CPU") which is for a similar hardware design, multiple CPUs can simultaneously perform injection or extraction. There are only 2 register groups for injection and 2 for extraction, and the driver only uses one of each. So we'd better serialize access using spin locks, otherwise frame corruption is possible. Note that unlike in sparx5, FDMA in ocelot does not have this issue because struct ocelot_fdma_tx_ring already contains an xmit_lock. I guess this is mostly a problem for NXP LS1028A, as that is dual core. I don't think VSC7514 is. So I'm blaming the commit where LS1028A (aka the felix DSA driver) started using register-based packet injection and extraction. Fixes: 0a6f17c6ae21 ("net: dsa: tag_ocelot_8021q: add support for PTP timestamping") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 11 +++++ drivers/net/ethernet/mscc/ocelot.c | 52 ++++++++++++++++++++++ drivers/net/ethernet/mscc/ocelot_vsc7514.c | 4 ++ include/soc/mscc/ocelot.h | 9 ++++ 4 files changed, 76 insertions(+) diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index e554699f06d41..8d31ff18c5c7e 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -528,7 +528,9 @@ static int felix_tag_8021q_setup(struct dsa_switch *ds) * so we need to be careful that there are no extra frames to be * dequeued over MMIO, since we would never know to discard them. */ + ocelot_lock_xtr_grp_bh(ocelot, 0); ocelot_drain_cpu_queue(ocelot, 0); + ocelot_unlock_xtr_grp_bh(ocelot, 0); return 0; } @@ -1518,6 +1520,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work) int port = xmit_work->dp->index; int retries = 10; + ocelot_lock_inj_grp(ocelot, 0); + do { if (ocelot_can_inject(ocelot, 0)) break; @@ -1526,6 +1530,7 @@ static void felix_port_deferred_xmit(struct kthread_work *work) } while (--retries); if (!retries) { + ocelot_unlock_inj_grp(ocelot, 0); dev_err(ocelot->dev, "port %d failed to inject skb\n", port); ocelot_port_purge_txtstamp_skb(ocelot, port, skb); @@ -1535,6 +1540,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work) ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); + ocelot_unlock_inj_grp(ocelot, 0); + consume_skb(skb); kfree(xmit_work); } @@ -1694,6 +1701,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot) if (!felix->info->quirk_no_xtr_irq) return false; + ocelot_lock_xtr_grp(ocelot, grp); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) { struct sk_buff *skb; unsigned int type; @@ -1730,6 +1739,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot) ocelot_drain_cpu_queue(ocelot, 0); } + ocelot_unlock_xtr_grp(ocelot, grp); + return true; } diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 9301716e21d58..f4e027a6fe955 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1099,6 +1099,48 @@ void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, } EXPORT_SYMBOL(ocelot_ptp_rx_timestamp); +void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp) + __acquires(&ocelot->inj_lock) +{ + spin_lock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_inj_grp); + +void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp) + __releases(&ocelot->inj_lock) +{ + spin_unlock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_inj_grp); + +void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp) + __acquires(&ocelot->inj_lock) +{ + spin_lock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp); + +void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp) + __releases(&ocelot->inj_lock) +{ + spin_unlock(&ocelot->inj_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp); + +void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp) + __acquires(&ocelot->xtr_lock) +{ + spin_lock_bh(&ocelot->xtr_lock); +} +EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp_bh); + +void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp) + __releases(&ocelot->xtr_lock) +{ + spin_unlock_bh(&ocelot->xtr_lock); +} +EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp_bh); + int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) { u64 timestamp, src_port, len; @@ -1109,6 +1151,8 @@ int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) u32 val, *buf; int err; + lockdep_assert_held(&ocelot->xtr_lock); + err = ocelot_xtr_poll_xfh(ocelot, grp, xfh); if (err) return err; @@ -1184,6 +1228,8 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp) { u32 val = ocelot_read(ocelot, QS_INJ_STATUS); + lockdep_assert_held(&ocelot->inj_lock); + if (!(val & QS_INJ_STATUS_FIFO_RDY(BIT(grp)))) return false; if (val & QS_INJ_STATUS_WMARK_REACHED(BIT(grp))) @@ -1236,6 +1282,8 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 ifh[OCELOT_TAG_LEN / 4]; unsigned int i, count, last; + lockdep_assert_held(&ocelot->inj_lock); + ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) | QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp); @@ -1272,6 +1320,8 @@ EXPORT_SYMBOL(ocelot_port_inject_frame); void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp) { + lockdep_assert_held(&ocelot->xtr_lock); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) ocelot_read_rix(ocelot, QS_XTR_RD, grp); } @@ -2954,6 +3004,8 @@ int ocelot_init(struct ocelot *ocelot) mutex_init(&ocelot->fwd_domain_lock); spin_lock_init(&ocelot->ptp_clock_lock); spin_lock_init(&ocelot->ts_id_lock); + spin_lock_init(&ocelot->inj_lock); + spin_lock_init(&ocelot->xtr_lock); ocelot->owq = alloc_ordered_workqueue("ocelot-owq", 0); if (!ocelot->owq) diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 993212c3a7da6..c09dd2e3343cb 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -51,6 +51,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) struct ocelot *ocelot = arg; int grp = 0, err; + ocelot_lock_xtr_grp(ocelot, grp); + while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) { struct sk_buff *skb; @@ -69,6 +71,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) if (err < 0) ocelot_drain_cpu_queue(ocelot, 0); + ocelot_unlock_xtr_grp(ocelot, grp); + return IRQ_HANDLED; } diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index ed18e6bafc8d0..462c653e10174 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -813,6 +813,9 @@ struct ocelot { const u32 *const *map; struct list_head stats_regions; + spinlock_t inj_lock; + spinlock_t xtr_lock; + u32 pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM]; int packet_buffer_size; int num_frame_refs; @@ -966,6 +969,12 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, u32 val, u32 reg, u32 offset); /* Packet I/O */ +void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp); +void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp); +void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp); +void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp); +void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp); +void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp); bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb); From 93e4649efa964201c73b0a03c35c04a0d6fc809f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:05 +0300 Subject: [PATCH 163/385] net: dsa: provide a software untagging function on RX for VLAN-aware bridges Through code analysis, I realized that the ds->untag_bridge_pvid logic is contradictory - see the newly added FIXME above the kernel-doc for dsa_software_untag_vlan_unaware_bridge(). Moreover, for the Felix driver, I need something very similar, but which is actually _not_ contradictory: untag the bridge PVID on RX, but for VLAN-aware bridges. The existing logic does it for VLAN-unaware bridges. Since I don't want to change the functionality of drivers which were supposedly properly tested with the ds->untag_bridge_pvid flag, I have introduced a new one: ds->untag_vlan_aware_bridge_pvid, and I have refactored the DSA reception code into a common path for both flags. TODO: both flags should be unified under a single ds->software_vlan_untag, which users of both current flags should set. This is not something that can be carried out right away. It needs very careful examination of all drivers which make use of this functionality, since some of them actually get this wrong in the first place. For example, commit 9130c2d30c17 ("net: dsa: microchip: ksz8795: Use software untagging on CPU port") uses this in a driver which has ds->configure_vlan_while_not_filtering = true. The latter mechanism has been known for many years to be broken by design: https://lore.kernel.org/netdev/CABumfLzJmXDN_W-8Z=p9KyKUVi_HhS7o_poBkeKHS2BkAiyYpw@mail.gmail.com/ and we have the situation of 2 bugs canceling each other. There is no private VLAN, and the port follows the PVID of the VLAN-unaware bridge. So, it's kinda ok for that driver to use the ds->untag_bridge_pvid mechanism, in a broken way. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 16 +++--- net/dsa/tag.c | 5 +- net/dsa/tag.h | 135 +++++++++++++++++++++++++++++++++++----------- 3 files changed, 118 insertions(+), 38 deletions(-) diff --git a/include/net/dsa.h b/include/net/dsa.h index b06f97ae3da1b..d7a6c2930277e 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -403,14 +403,18 @@ struct dsa_switch { */ u32 configure_vlan_while_not_filtering:1; - /* If the switch driver always programs the CPU port as egress tagged - * despite the VLAN configuration indicating otherwise, then setting - * @untag_bridge_pvid will force the DSA receive path to pop the - * bridge's default_pvid VLAN tagged frames to offer a consistent - * behavior between a vlan_filtering=0 and vlan_filtering=1 bridge - * device. + /* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames. + * DEPRECATED: Do NOT set this field in new drivers. Instead look at + * the dsa_software_vlan_untag() comments. */ u32 untag_bridge_pvid:1; + /* Pop the default_pvid of VLAN-aware bridge ports from tagged frames. + * Useful if the switch cannot preserve the VLAN tag as seen on the + * wire for user port ingress, and chooses to send all frames as + * VLAN-tagged to the CPU, including those which were originally + * untagged. + */ + u32 untag_vlan_aware_bridge_pvid:1; /* Let DSA manage the FDB entries towards the * CPU, based on the software bridge database. diff --git a/net/dsa/tag.c b/net/dsa/tag.c index 6e402d49afd3e..79ad105902d97 100644 --- a/net/dsa/tag.c +++ b/net/dsa/tag.c @@ -105,8 +105,9 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, p = netdev_priv(skb->dev); - if (unlikely(cpu_dp->ds->untag_bridge_pvid)) { - nskb = dsa_untag_bridge_pvid(skb); + if (unlikely(cpu_dp->ds->untag_bridge_pvid || + cpu_dp->ds->untag_vlan_aware_bridge_pvid)) { + nskb = dsa_software_vlan_untag(skb); if (!nskb) { kfree_skb(skb); return 0; diff --git a/net/dsa/tag.h b/net/dsa/tag.h index f6b9c73718dfa..d5707870906bc 100644 --- a/net/dsa/tag.h +++ b/net/dsa/tag.h @@ -44,46 +44,81 @@ static inline struct net_device *dsa_conduit_find_user(struct net_device *dev, return NULL; } -/* If under a bridge with vlan_filtering=0, make sure to send pvid-tagged - * frames as untagged, since the bridge will not untag them. +/** + * dsa_software_untag_vlan_aware_bridge: Software untagging for VLAN-aware bridge + * @skb: Pointer to received socket buffer (packet) + * @br: Pointer to bridge upper interface of ingress port + * @vid: Parsed VID from packet + * + * The bridge can process tagged packets. Software like STP/PTP may not. The + * bridge can also process untagged packets, to the same effect as if they were + * tagged with the PVID of the ingress port. So packets tagged with the PVID of + * the bridge port must be software-untagged, to support both use cases. */ -static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) +static inline void dsa_software_untag_vlan_aware_bridge(struct sk_buff *skb, + struct net_device *br, + u16 vid) { - struct dsa_port *dp = dsa_user_to_port(skb->dev); - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct net_device *dev = skb->dev; - struct net_device *upper_dev; - u16 vid, pvid, proto; + u16 pvid, proto; int err; - if (!br || br_vlan_enabled(br)) - return skb; - err = br_vlan_get_proto(br, &proto); if (err) - return skb; + return; - /* Move VLAN tag from data to hwaccel */ - if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) { - skb = skb_vlan_untag(skb); - if (!skb) - return NULL; - } + err = br_vlan_get_pvid_rcu(skb->dev, &pvid); + if (err) + return; - if (!skb_vlan_tag_present(skb)) - return skb; + if (vid == pvid && skb->vlan_proto == htons(proto)) + __vlan_hwaccel_clear_tag(skb); +} - vid = skb_vlan_tag_get_id(skb); +/** + * dsa_software_untag_vlan_unaware_bridge: Software untagging for VLAN-unaware bridge + * @skb: Pointer to received socket buffer (packet) + * @br: Pointer to bridge upper interface of ingress port + * @vid: Parsed VID from packet + * + * The bridge ignores all VLAN tags. Software like STP/PTP may not (it may run + * on the plain port, or on a VLAN upper interface). Maybe packets are coming + * to software as tagged with a driver-defined VID which is NOT equal to the + * PVID of the bridge port (since the bridge is VLAN-unaware, its configuration + * should NOT be committed to hardware). DSA needs a method for this private + * VID to be communicated by software to it, and if packets are tagged with it, + * software-untag them. Note: the private VID may be different per bridge, to + * support the FDB isolation use case. + * + * FIXME: this is currently implemented based on the broken assumption that + * the "private VID" used by the driver in VLAN-unaware mode is equal to the + * bridge PVID. It should not be, except for a coincidence; the bridge PVID is + * irrelevant to the data path in the VLAN-unaware mode. Thus, the VID that + * this function removes is wrong. + * + * All users of ds->untag_bridge_pvid should fix their drivers, if necessary, + * to make the two independent. Only then, if there still remains a need to + * strip the private VID from packets, then a new ds->ops->get_private_vid() + * API shall be introduced to communicate to DSA what this VID is, which needs + * to be stripped here. + */ +static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb, + struct net_device *br, + u16 vid) +{ + struct net_device *upper_dev; + u16 pvid, proto; + int err; - /* We already run under an RCU read-side critical section since - * we are called from netif_receive_skb_list_internal(). - */ - err = br_vlan_get_pvid_rcu(dev, &pvid); + err = br_vlan_get_proto(br, &proto); if (err) - return skb; + return; - if (vid != pvid) - return skb; + err = br_vlan_get_pvid_rcu(skb->dev, &pvid); + if (err) + return; + + if (vid != pvid || skb->vlan_proto != htons(proto)) + return; /* The sad part about attempting to untag from DSA is that we * don't know, unless we check, if the skb will end up in @@ -95,10 +130,50 @@ static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) * definitely keep the tag, to make sure it keeps working. */ upper_dev = __vlan_find_dev_deep_rcu(br, htons(proto), vid); - if (upper_dev) + if (!upper_dev) + __vlan_hwaccel_clear_tag(skb); +} + +/** + * dsa_software_vlan_untag: Software VLAN untagging in DSA receive path + * @skb: Pointer to socket buffer (packet) + * + * Receive path method for switches which cannot avoid tagging all packets + * towards the CPU port. Called when ds->untag_bridge_pvid (legacy) or + * ds->untag_vlan_aware_bridge_pvid is set to true. + * + * As a side effect of this method, any VLAN tag from the skb head is moved + * to hwaccel. + */ +static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb) +{ + struct dsa_port *dp = dsa_user_to_port(skb->dev); + struct net_device *br = dsa_port_bridge_dev_get(dp); + u16 vid; + + /* software untagging for standalone ports not yet necessary */ + if (!br) return skb; - __vlan_hwaccel_clear_tag(skb); + /* Move VLAN tag from data to hwaccel */ + if (!skb_vlan_tag_present(skb)) { + skb = skb_vlan_untag(skb); + if (!skb) + return NULL; + } + + if (!skb_vlan_tag_present(skb)) + return skb; + + vid = skb_vlan_tag_get_id(skb); + + if (br_vlan_enabled(br)) { + if (dp->ds->untag_vlan_aware_bridge_pvid) + dsa_software_untag_vlan_aware_bridge(skb, br, vid); + } else { + if (dp->ds->untag_bridge_pvid) + dsa_software_untag_vlan_unaware_bridge(skb, br, vid); + } return skb; } From f1288fd7293b91442ad7420394c252a252ecaa30 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:06 +0300 Subject: [PATCH 164/385] net: dsa: felix: fix VLAN tag loss on CPU reception with ocelot-8021q There is a major design bug with ocelot-8021q, which is that it expects more of the hardware than the hardware can actually do. The short summary of the issue is that when a port is under a VLAN-aware bridge and we use this tagging protocol, VLAN upper interfaces of this port do not see RX traffic. We use VCAP ES0 (egress rewriter) rules towards the tag_8021q CPU port to encapsulate packets with an outer tag, later stripped by software, that depends on the source user port. We do this so that packets can be identified in ocelot_rcv(). To be precise, we create rules with push_outer_tag = OCELOT_ES0_TAG and push_inner_tag = 0. With this configuration, we expect the switch to keep the inner tag configuration as found in the packet (if it was untagged on user port ingress, keep it untagged, otherwise preserve the VLAN tag unmodified as the inner tag towards the tag_8021q CPU port). But this is not what happens. Instead, table "Tagging Combinations" from the user manual suggests that when the ES0 action is "PUSH_OUTER_TAG=1 and PUSH_INNER_TAG=0", there will be "no inner tag". Experimentation further clarifies what this means. It appears that this "inner tag" which is not pushed into the packet on its egress towards the CPU is none other than the classified VLAN. When the ingress user port is standalone or under a VLAN-unaware bridge, the classified VLAN is a discardable quantity: it is a fixed value - the result of ocelot_vlan_unaware_pvid()'s configuration, and actually independent of the VID from any 802.1Q header that may be in the frame. It is actually preferable to discard the "inner tag" in this case. The problem is when the ingress port is under a VLAN-aware bridge. Then, the classified VLAN is taken from the frame's 802.1Q header, with a fallback on the bridge port's PVID. It would be very good to not discard the "inner tag" here, because if we do, we break communication with any 8021q VLAN uppers that the port might have. These have a processing path outside the bridge. There seems to be nothing else we can do except to change the configuration for VCAP ES0 rules, to actually push the inner VLAN into the frame. There are 2 options for that, first is to push a fixed value specified in the rule, and second is to push a fixed value, plus (aka arithmetic +) the classified VLAN. We choose the second option, and we select that fixed value as 0. Thus, what is pushed in the inner tag is just the classified VLAN. From there, we need to perform software untagging, in the receive path, of stuff that was untagged on the wire. Fixes: 7c83a7c539ab ("net: dsa: add a second tagger for Ocelot switches based on tag_8021q") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 115 +++++++++++++++++++++++++++++++-- 1 file changed, 109 insertions(+), 6 deletions(-) diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 8d31ff18c5c7e..4a705f7333f43 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -61,11 +61,46 @@ static int felix_cpu_port_for_conduit(struct dsa_switch *ds, return cpu_dp->index; } +/** + * felix_update_tag_8021q_rx_rule - Update VCAP ES0 tag_8021q rule after + * vlan_filtering change + * @outer_tagging_rule: Pointer to VCAP filter on which the update is performed + * @vlan_filtering: Current bridge VLAN filtering setting + * + * Source port identification for tag_8021q is done using VCAP ES0 rules on the + * CPU port(s). The ES0 tag B (inner tag from the packet) can be configured as + * either: + * - push_inner_tag=0: the inner tag is never pushed into the frame + * (and we lose info about the classified VLAN). This is + * good when the classified VLAN is a discardable quantity + * for the software RX path: it is either set to + * OCELOT_STANDALONE_PVID, or to + * ocelot_vlan_unaware_pvid(bridge). + * - push_inner_tag=1: the inner tag is always pushed. This is good when the + * classified VLAN is not a discardable quantity (the port + * is under a VLAN-aware bridge, and software needs to + * continue processing the packet in the same VLAN as the + * hardware). + * The point is that what is good for a VLAN-unaware port is not good for a + * VLAN-aware port, and vice versa. Thus, the RX tagging rules must be kept in + * sync with the VLAN filtering state of the port. + */ +static void +felix_update_tag_8021q_rx_rule(struct ocelot_vcap_filter *outer_tagging_rule, + bool vlan_filtering) +{ + if (vlan_filtering) + outer_tagging_rule->action.push_inner_tag = OCELOT_ES0_TAG; + else + outer_tagging_rule->action.push_inner_tag = OCELOT_NO_ES0_TAG; +} + /* Set up VCAP ES0 rules for pushing a tag_8021q VLAN towards the CPU such that * the tagger can perform RX source port identification. */ static int felix_tag_8021q_vlan_add_rx(struct dsa_switch *ds, int port, - int upstream, u16 vid) + int upstream, u16 vid, + bool vlan_filtering) { struct ocelot_vcap_filter *outer_tagging_rule; struct ocelot *ocelot = ds->priv; @@ -96,6 +131,14 @@ static int felix_tag_8021q_vlan_add_rx(struct dsa_switch *ds, int port, outer_tagging_rule->action.tag_a_tpid_sel = OCELOT_TAG_TPID_SEL_8021AD; outer_tagging_rule->action.tag_a_vid_sel = 1; outer_tagging_rule->action.vid_a_val = vid; + felix_update_tag_8021q_rx_rule(outer_tagging_rule, vlan_filtering); + outer_tagging_rule->action.tag_b_tpid_sel = OCELOT_TAG_TPID_SEL_8021Q; + /* Leave TAG_B_VID_SEL at 0 (Classified VID + VID_B_VAL). Since we also + * leave VID_B_VAL at 0, this makes ES0 tag B (the inner tag) equal to + * the classified VID, which we need to see in the DSA tagger's receive + * path. Note: the inner tag is only visible in the packet when pushed + * (push_inner_tag == OCELOT_ES0_TAG). + */ err = ocelot_vcap_filter_add(ocelot, outer_tagging_rule, NULL); if (err) @@ -227,6 +270,7 @@ static int felix_tag_8021q_vlan_del_tx(struct dsa_switch *ds, int port, u16 vid) static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid, u16 flags) { + struct dsa_port *dp = dsa_to_port(ds, port); struct dsa_port *cpu_dp; int err; @@ -234,11 +278,12 @@ static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid, * membership, which we aren't. So we don't need to add any VCAP filter * for the CPU port. */ - if (!dsa_is_user_port(ds, port)) + if (!dsa_port_is_user(dp)) return 0; dsa_switch_for_each_cpu_port(cpu_dp, ds) { - err = felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid); + err = felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid, + dsa_port_is_vlan_filtering(dp)); if (err) return err; } @@ -258,10 +303,11 @@ static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid, static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid) { + struct dsa_port *dp = dsa_to_port(ds, port); struct dsa_port *cpu_dp; int err; - if (!dsa_is_user_port(ds, port)) + if (!dsa_port_is_user(dp)) return 0; dsa_switch_for_each_cpu_port(cpu_dp, ds) { @@ -278,11 +324,41 @@ static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid) del_tx_failed: dsa_switch_for_each_cpu_port(cpu_dp, ds) - felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid); + felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid, + dsa_port_is_vlan_filtering(dp)); return err; } +static int felix_update_tag_8021q_rx_rules(struct dsa_switch *ds, int port, + bool vlan_filtering) +{ + struct ocelot_vcap_filter *outer_tagging_rule; + struct ocelot_vcap_block *block_vcap_es0; + struct ocelot *ocelot = ds->priv; + struct dsa_port *cpu_dp; + unsigned long cookie; + int err; + + block_vcap_es0 = &ocelot->block[VCAP_ES0]; + + dsa_switch_for_each_cpu_port(cpu_dp, ds) { + cookie = OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port, + cpu_dp->index); + + outer_tagging_rule = ocelot_vcap_block_find_filter_by_id(block_vcap_es0, + cookie, false); + + felix_update_tag_8021q_rx_rule(outer_tagging_rule, vlan_filtering); + + err = ocelot_vcap_filter_replace(ocelot, outer_tagging_rule); + if (err) + return err; + } + + return 0; +} + static int felix_trap_get_cpu_port(struct dsa_switch *ds, const struct ocelot_vcap_filter *trap) { @@ -532,6 +608,16 @@ static int felix_tag_8021q_setup(struct dsa_switch *ds) ocelot_drain_cpu_queue(ocelot, 0); ocelot_unlock_xtr_grp_bh(ocelot, 0); + /* Problem: when using push_inner_tag=1 for ES0 tag B, we lose info + * about whether the received packets were VLAN-tagged on the wire, + * since they are always tagged on egress towards the CPU port. + * + * Since using push_inner_tag=1 is unavoidable for VLAN-aware bridges, + * we must work around the fallout by untagging in software to make + * untagged reception work more or less as expected. + */ + ds->untag_vlan_aware_bridge_pvid = true; + return 0; } @@ -556,6 +642,8 @@ static void felix_tag_8021q_teardown(struct dsa_switch *ds) ocelot_port_teardown_dsa_8021q_cpu(ocelot, dp->index); dsa_tag_8021q_unregister(ds); + + ds->untag_vlan_aware_bridge_pvid = false; } static unsigned long felix_tag_8021q_get_host_fwd_mask(struct dsa_switch *ds) @@ -1010,8 +1098,23 @@ static int felix_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, struct netlink_ext_ack *extack) { struct ocelot *ocelot = ds->priv; + bool using_tag_8021q; + struct felix *felix; + int err; - return ocelot_port_vlan_filtering(ocelot, port, enabled, extack); + err = ocelot_port_vlan_filtering(ocelot, port, enabled, extack); + if (err) + return err; + + felix = ocelot_to_felix(ocelot); + using_tag_8021q = felix->tag_proto == DSA_TAG_PROTO_OCELOT_8021Q; + if (using_tag_8021q) { + err = felix_update_tag_8021q_rx_rules(ds, port, enabled); + if (err) + return err; + } + + return 0; } static int felix_vlan_add(struct dsa_switch *ds, int port, From 36dd1141be70b5966906919714dc504a24c65ddf Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 15 Aug 2024 03:07:07 +0300 Subject: [PATCH 165/385] net: mscc: ocelot: treat 802.1ad tagged traffic as 802.1Q-untagged I was revisiting the topic of 802.1ad treatment in the Ocelot switch [0] and realized that not only is its basic VLAN classification pipeline improper for offloading vlan_protocol 802.1ad bridges, but also improper for offloading regular 802.1Q bridges already. Namely, 802.1ad-tagged traffic should be treated as VLAN-untagged by bridged ports, but this switch treats it as if it was 802.1Q-tagged with the same VID as in the 802.1ad header. This is markedly different to what the Linux bridge expects; see the "other_tpid()" function in tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh. An idea came to me that the VCAP IS1 TCAM is more powerful than I'm giving it credit for, and that it actually overwrites the classified VID before the VLAN Table lookup takes place. In other words, it can be used even to save a packet from being dropped on ingress due to VLAN membership. Add a sophisticated TCAM rule hardcoded into the driver to force the switch to behave like a Linux bridge with vlan_filtering 1 vlan_protocol 802.1Q. Regarding the lifetime of the filter: eventually the bridge will disappear, and vlan_filtering on the port will be restored to 0 for standalone mode. Then the filter will be deleted. [0]: https://lore.kernel.org/netdev/20201009122947.nvhye4hvcha3tljh@skbuf/ Fixes: 7142529f1688 ("net: mscc: ocelot: add VLAN filtering") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 188 ++++++++++++++++++++++-- drivers/net/ethernet/mscc/ocelot_vcap.c | 1 + include/soc/mscc/ocelot_vcap.h | 2 + 3 files changed, 180 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index f4e027a6fe955..3d72aa7b13050 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -453,9 +453,158 @@ static u16 ocelot_vlan_unaware_pvid(struct ocelot *ocelot, return VLAN_N_VID - bridge_num - 1; } +/** + * ocelot_update_vlan_reclassify_rule() - Make switch aware only to bridge VLAN TPID + * + * @ocelot: Switch private data structure + * @port: Index of ingress port + * + * IEEE 802.1Q-2018 clauses "5.5 C-VLAN component conformance" and "5.6 S-VLAN + * component conformance" suggest that a C-VLAN component should only recognize + * and filter on C-Tags, and an S-VLAN component should only recognize and + * process based on C-Tags. + * + * In Linux, as per commit 1a0b20b25732 ("Merge branch 'bridge-next'"), C-VLAN + * components are largely represented by a bridge with vlan_protocol 802.1Q, + * and S-VLAN components by a bridge with vlan_protocol 802.1ad. + * + * Currently the driver only offloads vlan_protocol 802.1Q, but the hardware + * design is non-conformant, because the switch assigns each frame to a VLAN + * based on an entirely different question, as detailed in figure "Basic VLAN + * Classification Flow" from its manual and reproduced below. + * + * Set TAG_TYPE, PCP, DEI, VID to port-default values in VLAN_CFG register + * if VLAN_AWARE_ENA[port] and frame has outer tag then: + * if VLAN_INNER_TAG_ENA[port] and frame has inner tag then: + * TAG_TYPE = (Frame.InnerTPID <> 0x8100) + * Set PCP, DEI, VID to values from inner VLAN header + * else: + * TAG_TYPE = (Frame.OuterTPID <> 0x8100) + * Set PCP, DEI, VID to values from outer VLAN header + * if VID == 0 then: + * VID = VLAN_CFG.VLAN_VID + * + * Summarized, the switch will recognize both 802.1Q and 802.1ad TPIDs as VLAN + * "with equal rights", and just set the TAG_TYPE bit to 0 (if 802.1Q) or to 1 + * (if 802.1ad). It will classify based on whichever of the tags is "outer", no + * matter what TPID that may have (or "inner", if VLAN_INNER_TAG_ENA[port]). + * + * In the VLAN Table, the TAG_TYPE information is not accessible - just the + * classified VID is - so it is as if each VLAN Table entry is for 2 VLANs: + * C-VLAN X, and S-VLAN X. + * + * Whereas the Linux bridge behavior is to only filter on frames with a TPID + * equal to the vlan_protocol, and treat everything else as VLAN-untagged. + * + * Consider an ingress packet tagged with 802.1ad VID=3 and 802.1Q VID=5, + * received on a bridge vlan_filtering=1 vlan_protocol=802.1Q port. This frame + * should be treated as 802.1Q-untagged, and classified to the PVID of that + * bridge port. Not to VID=3, and not to VID=5. + * + * The VCAP IS1 TCAM has everything we need to overwrite the choices made in + * the basic VLAN classification pipeline: it can match on TAG_TYPE in the key, + * and it can modify the classified VID in the action. Thus, for each port + * under a vlan_filtering bridge, we can insert a rule in VCAP IS1 lookup 0 to + * match on 802.1ad tagged frames and modify their classified VID to the 802.1Q + * PVID of the port. This effectively makes it appear to the outside world as + * if those packets were processed as VLAN-untagged. + * + * The rule needs to be updated each time the bridge PVID changes, and needs + * to be deleted if the bridge PVID is deleted, or if the port becomes + * VLAN-unaware. + */ +static int ocelot_update_vlan_reclassify_rule(struct ocelot *ocelot, int port) +{ + unsigned long cookie = OCELOT_VCAP_IS1_VLAN_RECLASSIFY(ocelot, port); + struct ocelot_vcap_block *block_vcap_is1 = &ocelot->block[VCAP_IS1]; + struct ocelot_port *ocelot_port = ocelot->ports[port]; + const struct ocelot_bridge_vlan *pvid_vlan; + struct ocelot_vcap_filter *filter; + int err, val, pcp, dei; + bool vid_replace_ena; + u16 vid; + + pvid_vlan = ocelot_port->pvid_vlan; + vid_replace_ena = ocelot_port->vlan_aware && pvid_vlan; + + filter = ocelot_vcap_block_find_filter_by_id(block_vcap_is1, cookie, + false); + if (!vid_replace_ena) { + /* If the reclassification filter doesn't need to exist, delete + * it if it was previously installed, and exit doing nothing + * otherwise. + */ + if (filter) + return ocelot_vcap_filter_del(ocelot, filter); + + return 0; + } + + /* The reclassification rule must apply. See if it already exists + * or if it must be created. + */ + + /* Treating as VLAN-untagged means using as classified VID equal to + * the bridge PVID, and PCP/DEI set to the port default QoS values. + */ + vid = pvid_vlan->vid; + val = ocelot_read_gix(ocelot, ANA_PORT_QOS_CFG, port); + pcp = ANA_PORT_QOS_CFG_QOS_DEFAULT_VAL_X(val); + dei = !!(val & ANA_PORT_QOS_CFG_DP_DEFAULT_VAL); + + if (filter) { + bool changed = false; + + /* Filter exists, just update it */ + if (filter->action.vid != vid) { + filter->action.vid = vid; + changed = true; + } + if (filter->action.pcp != pcp) { + filter->action.pcp = pcp; + changed = true; + } + if (filter->action.dei != dei) { + filter->action.dei = dei; + changed = true; + } + + if (!changed) + return 0; + + return ocelot_vcap_filter_replace(ocelot, filter); + } + + /* Filter doesn't exist, create it */ + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) + return -ENOMEM; + + filter->key_type = OCELOT_VCAP_KEY_ANY; + filter->ingress_port_mask = BIT(port); + filter->vlan.tpid = OCELOT_VCAP_BIT_1; + filter->prio = 1; + filter->id.cookie = cookie; + filter->id.tc_offload = false; + filter->block_id = VCAP_IS1; + filter->type = OCELOT_VCAP_FILTER_OFFLOAD; + filter->lookup = 0; + filter->action.vid_replace_ena = true; + filter->action.pcp_dei_ena = true; + filter->action.vid = vid; + filter->action.pcp = pcp; + filter->action.dei = dei; + + err = ocelot_vcap_filter_add(ocelot, filter, NULL); + if (err) + kfree(filter); + + return err; +} + /* Default vlan to clasify for untagged frames (may be zero) */ -static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, - const struct ocelot_bridge_vlan *pvid_vlan) +static int ocelot_port_set_pvid(struct ocelot *ocelot, int port, + const struct ocelot_bridge_vlan *pvid_vlan) { struct ocelot_port *ocelot_port = ocelot->ports[port]; u16 pvid = ocelot_vlan_unaware_pvid(ocelot, ocelot_port->bridge); @@ -475,15 +624,23 @@ static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, * happens automatically), but also 802.1p traffic which gets * classified to VLAN 0, but that is always in our RX filter, so it * would get accepted were it not for this setting. + * + * Also, we only support the bridge 802.1Q VLAN protocol, so + * 802.1ad-tagged frames (carrying S-Tags) should be considered + * 802.1Q-untagged, and also dropped. */ if (!pvid_vlan && ocelot_port->vlan_aware) val = ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | - ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA; + ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA | + ANA_PORT_DROP_CFG_DROP_S_TAGGED_ENA; ocelot_rmw_gix(ocelot, val, ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | - ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA, + ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA | + ANA_PORT_DROP_CFG_DROP_S_TAGGED_ENA, ANA_PORT_DROP_CFG, port); + + return ocelot_update_vlan_reclassify_rule(ocelot, port); } static struct ocelot_bridge_vlan *ocelot_bridge_vlan_find(struct ocelot *ocelot, @@ -631,7 +788,10 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M, ANA_PORT_VLAN_CFG, port); - ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan); + err = ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan); + if (err) + return err; + ocelot_port_manage_port_tag(ocelot, port); return 0; @@ -684,9 +844,12 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, return err; /* Default ingress vlan classification */ - if (pvid) - ocelot_port_set_pvid(ocelot, port, - ocelot_bridge_vlan_find(ocelot, vid)); + if (pvid) { + err = ocelot_port_set_pvid(ocelot, port, + ocelot_bridge_vlan_find(ocelot, vid)); + if (err) + return err; + } /* Untagged egress vlan clasification */ ocelot_port_manage_port_tag(ocelot, port); @@ -712,8 +875,11 @@ int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid) return err; /* Ingress */ - if (del_pvid) - ocelot_port_set_pvid(ocelot, port, NULL); + if (del_pvid) { + err = ocelot_port_set_pvid(ocelot, port, NULL); + if (err) + return err; + } /* Egress */ ocelot_port_manage_port_tag(ocelot, port); @@ -2607,7 +2773,7 @@ int ocelot_port_set_default_prio(struct ocelot *ocelot, int port, u8 prio) ANA_PORT_QOS_CFG, port); - return 0; + return ocelot_update_vlan_reclassify_rule(ocelot, port); } EXPORT_SYMBOL_GPL(ocelot_port_set_default_prio); diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c index 73cdec5ca6a34..5734b86aed5b5 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.c +++ b/drivers/net/ethernet/mscc/ocelot_vcap.c @@ -695,6 +695,7 @@ static void is1_entry_set(struct ocelot *ocelot, int ix, vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_MC, filter->dmac_mc); vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_BC, filter->dmac_bc); vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_VLAN_TAGGED, tag->tagged); + vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_TPID, tag->tpid); vcap_key_set(vcap, &data, VCAP_IS1_HK_VID, tag->vid.value, tag->vid.mask); vcap_key_set(vcap, &data, VCAP_IS1_HK_PCP, diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index c601a4598b0da..eb19668a06db1 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -13,6 +13,7 @@ */ #define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port, upstream) ((upstream) << 16 | (port)) #define OCELOT_VCAP_IS1_TAG_8021Q_TXVLAN(ocelot, port) (port) +#define OCELOT_VCAP_IS1_VLAN_RECLASSIFY(ocelot, port) ((ocelot)->num_phys_ports + (port)) #define OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN(ocelot, port) (port) #define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port) ((ocelot)->num_phys_ports + (port)) #define OCELOT_VCAP_IS2_MRP_TRAP(ocelot) ((ocelot)->num_phys_ports * 2) @@ -499,6 +500,7 @@ struct ocelot_vcap_key_vlan { struct ocelot_vcap_u8 pcp; /* PCP (3 bit) */ enum ocelot_vcap_bit dei; /* DEI */ enum ocelot_vcap_bit tagged; /* Tagged/untagged frame */ + enum ocelot_vcap_bit tpid; }; struct ocelot_vcap_key_etype { From 145082ebfcf08f4fd254c467abf4aa58b4d38505 Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Mon, 12 Aug 2024 14:17:21 +0200 Subject: [PATCH 166/385] Documentation/llvm: turn make command for ccache into code block The command provided to use ccache with clang is not a literal code block. Once built, the documentation displays the '' symbols as a " character, which is wrong, and the command can not be applied as provided. Turn the command into a literal code block. Signed-off-by: Javier Carrasco Reviewed-by: Nathan Chancellor Signed-off-by: Masahiro Yamada --- Documentation/kbuild/llvm.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst index bb5c44f8bd1c4..6dc66b4f31a7b 100644 --- a/Documentation/kbuild/llvm.rst +++ b/Documentation/kbuild/llvm.rst @@ -126,7 +126,7 @@ Ccache ``ccache`` can be used with ``clang`` to improve subsequent builds, (though KBUILD_BUILD_TIMESTAMP_ should be set to a deterministic value between builds -in order to avoid 100% cache misses, see Reproducible_builds_ for more info): +in order to avoid 100% cache misses, see Reproducible_builds_ for more info):: KBUILD_BUILD_TIMESTAMP='' make LLVM=1 CC="ccache clang" From 2140e63cd87fa707acf514d594725097bed018fd Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Mon, 12 Aug 2024 09:30:44 +0200 Subject: [PATCH 167/385] ethtool: Add new result codes for TDR diagnostics Add new result codes to support TDR diagnostics in preparation for Open Alliance 1000BaseT1 TDR support: - ETHTOOL_A_CABLE_RESULT_CODE_NOISE: TDR not possible due to high noise level. - ETHTOOL_A_CABLE_RESULT_CODE_RESOLUTION_NOT_POSSIBLE: TDR resolution not possible / out of distance. Reviewed-by: Andrew Lunn Signed-off-by: Oleksij Rempel Link: https://patch.msgid.link/20240812073046.1728288-1-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- include/uapi/linux/ethtool_netlink.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 93c57525a9753..9074fa309bd6d 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -556,6 +556,10 @@ enum { * a regular 100 Ohm cable and a part with the abnormal impedance value */ ETHTOOL_A_CABLE_RESULT_CODE_IMPEDANCE_MISMATCH, + /* TDR not possible due to high noise level */ + ETHTOOL_A_CABLE_RESULT_CODE_NOISE, + /* TDR resolution not possible / out of distance */ + ETHTOOL_A_CABLE_RESULT_CODE_RESOLUTION_NOT_POSSIBLE, }; enum { From 9e7c1a9b90334d3c87467f0204bf2bcd9794c22c Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Mon, 12 Aug 2024 09:30:45 +0200 Subject: [PATCH 168/385] phy: Add Open Alliance helpers for the PHY framework Introduce helper functions specific to Open Alliance diagnostics, integrating them into the PHY framework. Currently, these helpers are limited to 1000BaseT1 specific TDR functionality. Signed-off-by: Oleksij Rempel Link: https://patch.msgid.link/20240812073046.1728288-2-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/phy/Kconfig | 3 + drivers/net/phy/Makefile | 1 + drivers/net/phy/open_alliance_helpers.c | 77 +++++++++++++++++++++++++ drivers/net/phy/open_alliance_helpers.h | 47 +++++++++++++++ 4 files changed, 128 insertions(+) create mode 100644 drivers/net/phy/open_alliance_helpers.c create mode 100644 drivers/net/phy/open_alliance_helpers.h diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 7fddc8306d822..874422e530ff0 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -44,6 +44,9 @@ config LED_TRIGGER_PHY Mbps OR Gbps OR link for any speed known to the PHY. +config OPEN_ALLIANCE_HELPERS + bool + config PHYLIB_LEDS def_bool OF depends on LEDS_CLASS=y || LEDS_CLASS=PHYLIB diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 202ed7f450da6..f086a606a87e9 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -22,6 +22,7 @@ endif obj-$(CONFIG_MDIO_DEVRES) += mdio_devres.o libphy-$(CONFIG_SWPHY) += swphy.o libphy-$(CONFIG_LED_TRIGGER_PHY) += phy_led_triggers.o +libphy-$(CONFIG_OPEN_ALLIANCE_HELPERS) += open_alliance_helpers.o obj-$(CONFIG_PHYLINK) += phylink.o obj-$(CONFIG_PHYLIB) += libphy.o diff --git a/drivers/net/phy/open_alliance_helpers.c b/drivers/net/phy/open_alliance_helpers.c new file mode 100644 index 0000000000000..36a70451d7da0 --- /dev/null +++ b/drivers/net/phy/open_alliance_helpers.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * open_alliance_helpers.c - OPEN Alliance specific PHY diagnostic helpers + * + * This file contains helper functions for implementing advanced diagnostic + * features as specified by the OPEN Alliance for automotive Ethernet PHYs. + * These helpers include functionality for Time Delay Reflection (TDR), dynamic + * channel quality assessment, and other PHY diagnostics. + * + * For more information on the specifications, refer to the OPEN Alliance + * documentation: https://opensig.org/automotive-ethernet-specifications/ + * Currently following specifications are partially or fully implemented: + * - Advanced diagnostic features for 1000BASE-T1 automotive Ethernet PHYs. + * TC12 - advanced PHY features. + * https://opensig.org/wp-content/uploads/2024/03/Advanced_PHY_features_for_automotive_Ethernet_v2.0_fin.pdf + */ + +#include +#include + +#include "open_alliance_helpers.h" + +/** + * oa_1000bt1_get_ethtool_cable_result_code - Convert TDR status to ethtool + * result code + * @reg_value: Value read from the TDR register + * + * This function takes a register value from the HDD.TDR register and converts + * the TDR status to the corresponding ethtool cable test result code. + * + * Return: The appropriate ethtool result code based on the TDR status + */ +int oa_1000bt1_get_ethtool_cable_result_code(u16 reg_value) +{ + u8 tdr_status = FIELD_GET(OA_1000BT1_HDD_TDR_STATUS_MASK, reg_value); + u8 dist_val = FIELD_GET(OA_1000BT1_HDD_TDR_DISTANCE_MASK, reg_value); + + switch (tdr_status) { + case OA_1000BT1_HDD_TDR_STATUS_CABLE_OK: + return ETHTOOL_A_CABLE_RESULT_CODE_OK; + case OA_1000BT1_HDD_TDR_STATUS_OPEN: + return ETHTOOL_A_CABLE_RESULT_CODE_OPEN; + case OA_1000BT1_HDD_TDR_STATUS_SHORT: + return ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT; + case OA_1000BT1_HDD_TDR_STATUS_NOISE: + return ETHTOOL_A_CABLE_RESULT_CODE_NOISE; + default: + if (dist_val == OA_1000BT1_HDD_TDR_DISTANCE_RESOLUTION_NOT_POSSIBLE) + return ETHTOOL_A_CABLE_RESULT_CODE_RESOLUTION_NOT_POSSIBLE; + return ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC; + } +} +EXPORT_SYMBOL_GPL(oa_1000bt1_get_ethtool_cable_result_code); + +/** + * oa_1000bt1_get_tdr_distance - Get distance to the main fault from TDR + * register value + * @reg_value: Value read from the TDR register + * + * This function takes a register value from the HDD.TDR register and extracts + * the distance to the main fault detected by the TDR feature. The distance is + * measured in centimeters and ranges from 0 to 3100 centimeters. If the + * distance is not available (0x3f), the function returns -ERANGE. + * + * Return: The distance to the main fault in centimeters, or -ERANGE if the + * resolution is not possible. + */ +int oa_1000bt1_get_tdr_distance(u16 reg_value) +{ + u8 dist_val = FIELD_GET(OA_1000BT1_HDD_TDR_DISTANCE_MASK, reg_value); + + if (dist_val == OA_1000BT1_HDD_TDR_DISTANCE_RESOLUTION_NOT_POSSIBLE) + return -ERANGE; + + return dist_val * 100; +} +EXPORT_SYMBOL_GPL(oa_1000bt1_get_tdr_distance); diff --git a/drivers/net/phy/open_alliance_helpers.h b/drivers/net/phy/open_alliance_helpers.h new file mode 100644 index 0000000000000..8b7d97bc6f186 --- /dev/null +++ b/drivers/net/phy/open_alliance_helpers.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef OPEN_ALLIANCE_HELPERS_H +#define OPEN_ALLIANCE_HELPERS_H + +/* + * These defines reflect the TDR (Time Delay Reflection) diagnostic feature + * for 1000BASE-T1 automotive Ethernet PHYs as specified by the OPEN Alliance. + * + * The register values are part of the HDD.TDR register, which provides + * information about the cable status and faults. The exact register offset + * is device-specific and should be provided by the driver. + */ +#define OA_1000BT1_HDD_TDR_ACTIVATION_MASK GENMASK(1, 0) +#define OA_1000BT1_HDD_TDR_ACTIVATION_OFF 1 +#define OA_1000BT1_HDD_TDR_ACTIVATION_ON 2 + +#define OA_1000BT1_HDD_TDR_STATUS_MASK GENMASK(7, 4) +#define OA_1000BT1_HDD_TDR_STATUS_SHORT 3 +#define OA_1000BT1_HDD_TDR_STATUS_OPEN 6 +#define OA_1000BT1_HDD_TDR_STATUS_NOISE 5 +#define OA_1000BT1_HDD_TDR_STATUS_CABLE_OK 7 +#define OA_1000BT1_HDD_TDR_STATUS_TEST_IN_PROGRESS 8 +#define OA_1000BT1_HDD_TDR_STATUS_TEST_NOT_POSSIBLE 13 + +/* + * OA_1000BT1_HDD_TDR_DISTANCE_MASK: + * This mask is used to extract the distance to the first/main fault + * detected by the TDR feature. Each bit represents an approximate distance + * of 1 meter, ranging from 0 to 31 meters. The exact interpretation of the + * bits may vary, but generally: + * 000000 = no error + * 000001 = error about 0-1m away + * 000010 = error between 1-2m away + * ... + * 011111 = error about 30-31m away + * 111111 = resolution not possible / out of distance + */ +#define OA_1000BT1_HDD_TDR_DISTANCE_MASK GENMASK(13, 8) +#define OA_1000BT1_HDD_TDR_DISTANCE_NO_ERROR 0 +#define OA_1000BT1_HDD_TDR_DISTANCE_RESOLUTION_NOT_POSSIBLE 0x3f + +int oa_1000bt1_get_ethtool_cable_result_code(u16 reg_value); +int oa_1000bt1_get_tdr_distance(u16 reg_value); + +#endif /* OPEN_ALLIANCE_HELPERS_H */ + From 20f77dc7247138c0c1463920f6d9829593804848 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Mon, 12 Aug 2024 09:30:46 +0200 Subject: [PATCH 169/385] net: phy: dp83tg720: Add cable testing support Introduce cable testing support for the DP83TG720 PHY. This implementation is based on the "DP83TG720S-Q1: Configuring for Open Alliance Specification Compliance (Rev. B)" application note. The feature has been tested with cables of various lengths: - No cable: 1m till open reported. - 5 meter cable: reported properly. - 20 meter cable: reported as 19m. - 40 meter cable: reported as cable ok. Reviewed-by: Andrew Lunn Signed-off-by: Oleksij Rempel Link: https://patch.msgid.link/20240812073046.1728288-3-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/phy/Kconfig | 1 + drivers/net/phy/dp83tg720.c | 154 ++++++++++++++++++++++++++++++++++++ 2 files changed, 155 insertions(+) diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 874422e530ff0..f530fcd092fe4 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -417,6 +417,7 @@ config DP83TD510_PHY config DP83TG720_PHY tristate "Texas Instruments DP83TG720 Ethernet 1000Base-T1 PHY" + select OPEN_ALLIANCE_HELPERS help The DP83TG720S-Q1 is an automotive Ethernet physical layer transceiver compliant with IEEE 802.3bp and Open Alliance diff --git a/drivers/net/phy/dp83tg720.c b/drivers/net/phy/dp83tg720.c index c706429b225a2..0ef4d7dba0656 100644 --- a/drivers/net/phy/dp83tg720.c +++ b/drivers/net/phy/dp83tg720.c @@ -3,10 +3,13 @@ * Copyright (c) 2023 Pengutronix, Oleksij Rempel */ #include +#include #include #include #include +#include "open_alliance_helpers.h" + #define DP83TG720S_PHY_ID 0x2000a284 /* MDIO_MMD_VEND2 registers */ @@ -14,6 +17,17 @@ #define DP83TG720S_STS_MII_INT BIT(7) #define DP83TG720S_LINK_STATUS BIT(0) +/* TDR Configuration Register (0x1E) */ +#define DP83TG720S_TDR_CFG 0x1e +/* 1b = TDR start, 0b = No TDR */ +#define DP83TG720S_TDR_START BIT(15) +/* 1b = TDR auto on link down, 0b = Manual TDR start */ +#define DP83TG720S_CFG_TDR_AUTO_RUN BIT(14) +/* 1b = TDR done, 0b = TDR in progress */ +#define DP83TG720S_TDR_DONE BIT(1) +/* 1b = TDR fail, 0b = TDR success */ +#define DP83TG720S_TDR_FAIL BIT(0) + #define DP83TG720S_PHY_RESET 0x1f #define DP83TG720S_HW_RESET BIT(15) @@ -22,18 +36,155 @@ /* Power Mode 0 is Normal mode */ #define DP83TG720S_LPS_CFG3_PWR_MODE_0 BIT(0) +/* Open Aliance 1000BaseT1 compatible HDD.TDR Fault Status Register */ +#define DP83TG720S_TDR_FAULT_STATUS 0x30f + +/* Register 0x0301: TDR Configuration 2 */ +#define DP83TG720S_TDR_CFG2 0x301 + +/* Register 0x0303: TDR Configuration 3 */ +#define DP83TG720S_TDR_CFG3 0x303 + +/* Register 0x0304: TDR Configuration 4 */ +#define DP83TG720S_TDR_CFG4 0x304 + +/* Register 0x0405: Unknown Register */ +#define DP83TG720S_UNKNOWN_0405 0x405 + +/* Register 0x0576: TDR Master Link Down Control */ +#define DP83TG720S_TDR_MASTER_LINK_DOWN 0x576 + #define DP83TG720S_RGMII_DELAY_CTRL 0x602 /* In RGMII mode, Enable or disable the internal delay for RXD */ #define DP83TG720S_RGMII_RX_CLK_SEL BIT(1) /* In RGMII mode, Enable or disable the internal delay for TXD */ #define DP83TG720S_RGMII_TX_CLK_SEL BIT(0) +/* Register 0x083F: Unknown Register */ +#define DP83TG720S_UNKNOWN_083F 0x83f + #define DP83TG720S_SQI_REG_1 0x871 #define DP83TG720S_SQI_OUT_WORST GENMASK(7, 5) #define DP83TG720S_SQI_OUT GENMASK(3, 1) #define DP83TG720_SQI_MAX 7 +/** + * dp83tg720_cable_test_start - Start the cable test for the DP83TG720 PHY. + * @phydev: Pointer to the phy_device structure. + * + * This sequence is based on the documented procedure for the DP83TG720 PHY. + * + * Returns: 0 on success, a negative error code on failure. + */ +static int dp83tg720_cable_test_start(struct phy_device *phydev) +{ + int ret; + + /* Initialize the PHY to run the TDR test as described in the + * "DP83TG720S-Q1: Configuring for Open Alliance Specification + * Compliance (Rev. B)" application note. + * Most of the registers are not documented. Some of register names + * are guessed by comparing the register offsets with the DP83TD510E. + */ + + /* Force master link down */ + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, + DP83TG720S_TDR_MASTER_LINK_DOWN, 0x0400); + if (ret) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG2, + 0xa008); + if (ret) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG3, + 0x0928); + if (ret) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG4, + 0x0004); + if (ret) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_UNKNOWN_0405, + 0x6400); + if (ret) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_UNKNOWN_083F, + 0x3003); + if (ret) + return ret; + + /* Start the TDR */ + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG, + DP83TG720S_TDR_START); + if (ret) + return ret; + + return 0; +} + +/** + * dp83tg720_cable_test_get_status - Get the status of the cable test for the + * DP83TG720 PHY. + * @phydev: Pointer to the phy_device structure. + * @finished: Pointer to a boolean that indicates whether the test is finished. + * + * The function sets the @finished flag to true if the test is complete. + * + * Returns: 0 on success or a negative error code on failure. + */ +static int dp83tg720_cable_test_get_status(struct phy_device *phydev, + bool *finished) +{ + int ret, stat; + + *finished = false; + + /* Read the TDR status */ + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG); + if (ret < 0) + return ret; + + /* Check if the TDR test is done */ + if (!(ret & DP83TG720S_TDR_DONE)) + return 0; + + /* Check for TDR test failure */ + if (!(ret & DP83TG720S_TDR_FAIL)) { + int location; + + /* Read fault status */ + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, + DP83TG720S_TDR_FAULT_STATUS); + if (ret < 0) + return ret; + + /* Get fault type */ + stat = oa_1000bt1_get_ethtool_cable_result_code(ret); + + /* Determine fault location */ + location = oa_1000bt1_get_tdr_distance(ret); + if (location > 0) + ethnl_cable_test_fault_length(phydev, + ETHTOOL_A_CABLE_PAIR_A, + location); + } else { + /* Active link partner or other issues */ + stat = ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC; + } + + *finished = true; + + ethnl_cable_test_result(phydev, ETHTOOL_A_CABLE_PAIR_A, stat); + + return phy_init_hw(phydev); +} + static int dp83tg720_config_aneg(struct phy_device *phydev) { int ret; @@ -195,12 +346,15 @@ static struct phy_driver dp83tg720_driver[] = { PHY_ID_MATCH_MODEL(DP83TG720S_PHY_ID), .name = "TI DP83TG720S", + .flags = PHY_POLL_CABLE_TEST, .config_aneg = dp83tg720_config_aneg, .read_status = dp83tg720_read_status, .get_features = genphy_c45_pma_read_ext_abilities, .config_init = dp83tg720_config_init, .get_sqi = dp83tg720_get_sqi, .get_sqi_max = dp83tg720_get_sqi_max, + .cable_test_start = dp83tg720_cable_test_start, + .cable_test_get_status = dp83tg720_cable_test_get_status, .suspend = genphy_suspend, .resume = genphy_resume, From 6a66873d820b4bd87a7c3f8e21b8bf4a76fa3223 Mon Sep 17 00:00:00 2001 From: Pieter Van Trappen Date: Tue, 13 Aug 2024 16:27:35 +0200 Subject: [PATCH 170/385] dt-bindings: net: dsa: microchip: add microchip,pme-active-high flag Add microchip,pme-active-high property to set the PME (Power Management Event) pin polarity for Wake on Lan interrupts. Note that the polarity is active-low by default. Signed-off-by: Pieter Van Trappen Reviewed-by: Rob Herring (Arm) Reviewed-by: Oleksij Rempel Link: https://patch.msgid.link/20240813142750.772781-2-vtpieter@gmail.com Signed-off-by: Jakub Kicinski --- Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml index 52acc15ebcbf3..c589ebc2c7be8 100644 --- a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml +++ b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml @@ -51,6 +51,11 @@ properties: Set if the output SYNCLKO clock should be disabled. Do not mix with microchip,synclko-125. + microchip,pme-active-high: + $ref: /schemas/types.yaml#/definitions/flag + description: + Indicates if the PME pin polarity is active-high. + microchip,io-drive-strength-microamp: description: IO Pad Drive Strength From f3ac6198a719857c492b04b0a8eb22c2cc81197b Mon Sep 17 00:00:00 2001 From: Pieter Van Trappen Date: Tue, 13 Aug 2024 16:27:36 +0200 Subject: [PATCH 171/385] net: dsa: microchip: move KSZ9477 WoL functions to ksz_common Move KSZ9477 WoL functions to ksz_common, in preparation for adding KSZ87xx family support. Signed-off-by: Pieter Van Trappen Acked-by: Arun Ramadoss Link: https://patch.msgid.link/20240813142750.772781-3-vtpieter@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/microchip/ksz9477.c | 181 ------------------------ drivers/net/dsa/microchip/ksz9477.h | 5 - drivers/net/dsa/microchip/ksz9477_reg.h | 12 -- drivers/net/dsa/microchip/ksz_common.c | 181 ++++++++++++++++++++++++ drivers/net/dsa/microchip/ksz_common.h | 19 +++ 5 files changed, 200 insertions(+), 198 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 755de092b2c2c..6c1540f725e5d 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -56,187 +56,6 @@ int ksz9477_change_mtu(struct ksz_device *dev, int port, int mtu) REG_SW_MTU_MASK, frame_size); } -/** - * ksz9477_handle_wake_reason - Handle wake reason on a specified port. - * @dev: The device structure. - * @port: The port number. - * - * This function reads the PME (Power Management Event) status register of a - * specified port to determine the wake reason. If there is no wake event, it - * returns early. Otherwise, it logs the wake reason which could be due to a - * "Magic Packet", "Link Up", or "Energy Detect" event. The PME status register - * is then cleared to acknowledge the handling of the wake event. - * - * Return: 0 on success, or an error code on failure. - */ -static int ksz9477_handle_wake_reason(struct ksz_device *dev, int port) -{ - u8 pme_status; - int ret; - - ret = ksz_pread8(dev, port, REG_PORT_PME_STATUS, &pme_status); - if (ret) - return ret; - - if (!pme_status) - return 0; - - dev_dbg(dev->dev, "Wake event on port %d due to:%s%s%s\n", port, - pme_status & PME_WOL_MAGICPKT ? " \"Magic Packet\"" : "", - pme_status & PME_WOL_LINKUP ? " \"Link Up\"" : "", - pme_status & PME_WOL_ENERGY ? " \"Energy detect\"" : ""); - - return ksz_pwrite8(dev, port, REG_PORT_PME_STATUS, pme_status); -} - -/** - * ksz9477_get_wol - Get Wake-on-LAN settings for a specified port. - * @dev: The device structure. - * @port: The port number. - * @wol: Pointer to ethtool Wake-on-LAN settings structure. - * - * This function checks the PME Pin Control Register to see if PME Pin Output - * Enable is set, indicating PME is enabled. If enabled, it sets the supported - * and active WoL flags. - */ -void ksz9477_get_wol(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol) -{ - u8 pme_ctrl; - int ret; - - if (!dev->wakeup_source) - return; - - wol->supported = WAKE_PHY; - - /* Check if the current MAC address on this port can be set - * as global for WAKE_MAGIC support. The result may vary - * dynamically based on other ports configurations. - */ - if (ksz_is_port_mac_global_usable(dev->ds, port)) - wol->supported |= WAKE_MAGIC; - - ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl); - if (ret) - return; - - if (pme_ctrl & PME_WOL_MAGICPKT) - wol->wolopts |= WAKE_MAGIC; - if (pme_ctrl & (PME_WOL_LINKUP | PME_WOL_ENERGY)) - wol->wolopts |= WAKE_PHY; -} - -/** - * ksz9477_set_wol - Set Wake-on-LAN settings for a specified port. - * @dev: The device structure. - * @port: The port number. - * @wol: Pointer to ethtool Wake-on-LAN settings structure. - * - * This function configures Wake-on-LAN (WoL) settings for a specified port. - * It validates the provided WoL options, checks if PME is enabled via the - * switch's PME Pin Control Register, clears any previous wake reasons, - * and sets the Magic Packet flag in the port's PME control register if - * specified. - * - * Return: 0 on success, or other error codes on failure. - */ -int ksz9477_set_wol(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol) -{ - u8 pme_ctrl = 0, pme_ctrl_old = 0; - bool magic_switched_off; - bool magic_switched_on; - int ret; - - if (wol->wolopts & ~(WAKE_PHY | WAKE_MAGIC)) - return -EINVAL; - - if (!dev->wakeup_source) - return -EOPNOTSUPP; - - ret = ksz9477_handle_wake_reason(dev, port); - if (ret) - return ret; - - if (wol->wolopts & WAKE_MAGIC) - pme_ctrl |= PME_WOL_MAGICPKT; - if (wol->wolopts & WAKE_PHY) - pme_ctrl |= PME_WOL_LINKUP | PME_WOL_ENERGY; - - ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl_old); - if (ret) - return ret; - - if (pme_ctrl_old == pme_ctrl) - return 0; - - magic_switched_off = (pme_ctrl_old & PME_WOL_MAGICPKT) && - !(pme_ctrl & PME_WOL_MAGICPKT); - magic_switched_on = !(pme_ctrl_old & PME_WOL_MAGICPKT) && - (pme_ctrl & PME_WOL_MAGICPKT); - - /* To keep reference count of MAC address, we should do this - * operation only on change of WOL settings. - */ - if (magic_switched_on) { - ret = ksz_switch_macaddr_get(dev->ds, port, NULL); - if (ret) - return ret; - } else if (magic_switched_off) { - ksz_switch_macaddr_put(dev->ds); - } - - ret = ksz_pwrite8(dev, port, REG_PORT_PME_CTRL, pme_ctrl); - if (ret) { - if (magic_switched_on) - ksz_switch_macaddr_put(dev->ds); - return ret; - } - - return 0; -} - -/** - * ksz9477_wol_pre_shutdown - Prepares the switch device for shutdown while - * considering Wake-on-LAN (WoL) settings. - * @dev: The switch device structure. - * @wol_enabled: Pointer to a boolean which will be set to true if WoL is - * enabled on any port. - * - * This function prepares the switch device for a safe shutdown while taking - * into account the Wake-on-LAN (WoL) settings on the user ports. It updates - * the wol_enabled flag accordingly to reflect whether WoL is active on any - * port. - */ -void ksz9477_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled) -{ - struct dsa_port *dp; - int ret; - - *wol_enabled = false; - - if (!dev->wakeup_source) - return; - - dsa_switch_for_each_user_port(dp, dev->ds) { - u8 pme_ctrl = 0; - - ret = ksz_pread8(dev, dp->index, REG_PORT_PME_CTRL, &pme_ctrl); - if (!ret && pme_ctrl) - *wol_enabled = true; - - /* make sure there are no pending wake events which would - * prevent the device from going to sleep/shutdown. - */ - ksz9477_handle_wake_reason(dev, dp->index); - } - - /* Now we are save to enable PME pin. */ - if (*wol_enabled) - ksz_write8(dev, REG_SW_PME_CTRL, PME_ENABLE); -} - static int ksz9477_wait_vlan_ctrl_ready(struct ksz_device *dev) { unsigned int val; diff --git a/drivers/net/dsa/microchip/ksz9477.h b/drivers/net/dsa/microchip/ksz9477.h index 239a281da10b3..d2166b0d881ed 100644 --- a/drivers/net/dsa/microchip/ksz9477.h +++ b/drivers/net/dsa/microchip/ksz9477.h @@ -60,11 +60,6 @@ void ksz9477_switch_exit(struct ksz_device *dev); void ksz9477_port_queue_split(struct ksz_device *dev, int port); void ksz9477_hsr_join(struct dsa_switch *ds, int port, struct net_device *hsr); void ksz9477_hsr_leave(struct dsa_switch *ds, int port, struct net_device *hsr); -void ksz9477_get_wol(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol); -int ksz9477_set_wol(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol); -void ksz9477_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled); int ksz9477_port_acl_init(struct ksz_device *dev, int port); void ksz9477_port_acl_free(struct ksz_device *dev, int port); diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h index d5354c600ea1e..04235c22bf40e 100644 --- a/drivers/net/dsa/microchip/ksz9477_reg.h +++ b/drivers/net/dsa/microchip/ksz9477_reg.h @@ -38,11 +38,6 @@ #define SWITCH_REVISION_S 4 #define SWITCH_RESET 0x01 -#define REG_SW_PME_CTRL 0x0006 - -#define PME_ENABLE BIT(1) -#define PME_POLARITY BIT(0) - #define REG_GLOBAL_OPTIONS 0x000F #define SW_GIGABIT_ABLE BIT(6) @@ -807,13 +802,6 @@ #define REG_PORT_AVB_SR_1_TYPE 0x0008 #define REG_PORT_AVB_SR_2_TYPE 0x000A -#define REG_PORT_PME_STATUS 0x0013 -#define REG_PORT_PME_CTRL 0x0017 - -#define PME_WOL_MAGICPKT BIT(2) -#define PME_WOL_LINKUP BIT(1) -#define PME_WOL_ENERGY BIT(0) - #define REG_PORT_INT_STATUS 0x001B #define REG_PORT_INT_MASK 0x001F diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 1491099528be8..7afe958d0e21d 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -3751,6 +3751,77 @@ static void ksz_get_wol(struct dsa_switch *ds, int port, dev->dev_ops->get_wol(dev, port, wol); } +/** + * ksz9477_handle_wake_reason - Handle wake reason on a specified port. + * @dev: The device structure. + * @port: The port number. + * + * This function reads the PME (Power Management Event) status register of a + * specified port to determine the wake reason. If there is no wake event, it + * returns early. Otherwise, it logs the wake reason which could be due to a + * "Magic Packet", "Link Up", or "Energy Detect" event. The PME status register + * is then cleared to acknowledge the handling of the wake event. + * + * Return: 0 on success, or an error code on failure. + */ +int ksz9477_handle_wake_reason(struct ksz_device *dev, int port) +{ + u8 pme_status; + int ret; + + ret = ksz_pread8(dev, port, REG_PORT_PME_STATUS, &pme_status); + if (ret) + return ret; + + if (!pme_status) + return 0; + + dev_dbg(dev->dev, "Wake event on port %d due to:%s%s%s\n", port, + pme_status & PME_WOL_MAGICPKT ? " \"Magic Packet\"" : "", + pme_status & PME_WOL_LINKUP ? " \"Link Up\"" : "", + pme_status & PME_WOL_ENERGY ? " \"Energy detect\"" : ""); + + return ksz_pwrite8(dev, port, REG_PORT_PME_STATUS, pme_status); +} + +/** + * ksz9477_get_wol - Get Wake-on-LAN settings for a specified port. + * @dev: The device structure. + * @port: The port number. + * @wol: Pointer to ethtool Wake-on-LAN settings structure. + * + * This function checks the PME Pin Control Register to see if PME Pin Output + * Enable is set, indicating PME is enabled. If enabled, it sets the supported + * and active WoL flags. + */ +void ksz9477_get_wol(struct ksz_device *dev, int port, + struct ethtool_wolinfo *wol) +{ + u8 pme_ctrl; + int ret; + + if (!dev->wakeup_source) + return; + + wol->supported = WAKE_PHY; + + /* Check if the current MAC address on this port can be set + * as global for WAKE_MAGIC support. The result may vary + * dynamically based on other ports configurations. + */ + if (ksz_is_port_mac_global_usable(dev->ds, port)) + wol->supported |= WAKE_MAGIC; + + ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl); + if (ret) + return; + + if (pme_ctrl & PME_WOL_MAGICPKT) + wol->wolopts |= WAKE_MAGIC; + if (pme_ctrl & (PME_WOL_LINKUP | PME_WOL_ENERGY)) + wol->wolopts |= WAKE_PHY; +} + static int ksz_set_wol(struct dsa_switch *ds, int port, struct ethtool_wolinfo *wol) { @@ -3762,6 +3833,116 @@ static int ksz_set_wol(struct dsa_switch *ds, int port, return -EOPNOTSUPP; } +/** + * ksz9477_set_wol - Set Wake-on-LAN settings for a specified port. + * @dev: The device structure. + * @port: The port number. + * @wol: Pointer to ethtool Wake-on-LAN settings structure. + * + * This function configures Wake-on-LAN (WoL) settings for a specified port. + * It validates the provided WoL options, checks if PME is enabled via the + * switch's PME Pin Control Register, clears any previous wake reasons, + * and sets the Magic Packet flag in the port's PME control register if + * specified. + * + * Return: 0 on success, or other error codes on failure. + */ +int ksz9477_set_wol(struct ksz_device *dev, int port, + struct ethtool_wolinfo *wol) +{ + u8 pme_ctrl = 0, pme_ctrl_old = 0; + bool magic_switched_off; + bool magic_switched_on; + int ret; + + if (wol->wolopts & ~(WAKE_PHY | WAKE_MAGIC)) + return -EINVAL; + + if (!dev->wakeup_source) + return -EOPNOTSUPP; + + ret = ksz9477_handle_wake_reason(dev, port); + if (ret) + return ret; + + if (wol->wolopts & WAKE_MAGIC) + pme_ctrl |= PME_WOL_MAGICPKT; + if (wol->wolopts & WAKE_PHY) + pme_ctrl |= PME_WOL_LINKUP | PME_WOL_ENERGY; + + ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl_old); + if (ret) + return ret; + + if (pme_ctrl_old == pme_ctrl) + return 0; + + magic_switched_off = (pme_ctrl_old & PME_WOL_MAGICPKT) && + !(pme_ctrl & PME_WOL_MAGICPKT); + magic_switched_on = !(pme_ctrl_old & PME_WOL_MAGICPKT) && + (pme_ctrl & PME_WOL_MAGICPKT); + + /* To keep reference count of MAC address, we should do this + * operation only on change of WOL settings. + */ + if (magic_switched_on) { + ret = ksz_switch_macaddr_get(dev->ds, port, NULL); + if (ret) + return ret; + } else if (magic_switched_off) { + ksz_switch_macaddr_put(dev->ds); + } + + ret = ksz_pwrite8(dev, port, REG_PORT_PME_CTRL, pme_ctrl); + if (ret) { + if (magic_switched_on) + ksz_switch_macaddr_put(dev->ds); + return ret; + } + + return 0; +} + +/** + * ksz9477_wol_pre_shutdown - Prepares the switch device for shutdown while + * considering Wake-on-LAN (WoL) settings. + * @dev: The switch device structure. + * @wol_enabled: Pointer to a boolean which will be set to true if WoL is + * enabled on any port. + * + * This function prepares the switch device for a safe shutdown while taking + * into account the Wake-on-LAN (WoL) settings on the user ports. It updates + * the wol_enabled flag accordingly to reflect whether WoL is active on any + * port. + */ +void ksz9477_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled) +{ + struct dsa_port *dp; + int ret; + + *wol_enabled = false; + + if (!dev->wakeup_source) + return; + + dsa_switch_for_each_user_port(dp, dev->ds) { + u8 pme_ctrl = 0; + + ret = ksz_pread8(dev, dp->index, REG_PORT_PME_CTRL, &pme_ctrl); + if (!ret && pme_ctrl) + *wol_enabled = true; + + /* make sure there are no pending wake events which would + * prevent the device from going to sleep/shutdown. + */ + ksz9477_handle_wake_reason(dev, dp->index); + } + + /* Now we are save to enable PME pin. */ + if (*wol_enabled) + ksz_write8(dev, REG_SW_PME_CTRL, PME_ENABLE); +} + static int ksz_port_set_mac_address(struct dsa_switch *ds, int port, const unsigned char *addr) { diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 5f0a628b9849e..e35caca96f89f 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -391,6 +391,12 @@ int ksz_switch_macaddr_get(struct dsa_switch *ds, int port, struct netlink_ext_ack *extack); void ksz_switch_macaddr_put(struct dsa_switch *ds); void ksz_switch_shutdown(struct ksz_device *dev); +int ksz9477_handle_wake_reason(struct ksz_device *dev, int port); +void ksz9477_get_wol(struct ksz_device *dev, int port, + struct ethtool_wolinfo *wol); +int ksz9477_set_wol(struct ksz_device *dev, int port, + struct ethtool_wolinfo *wol); +void ksz9477_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled); /* Common register access functions */ static inline struct regmap *ksz_regmap_8(struct ksz_device *dev) @@ -695,6 +701,19 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port) #define P_MII_MAC_MODE BIT(2) #define P_MII_SEL_M 0x3 +/* KSZ9477, KSZ8795 Wake-on-LAN (WoL) masks */ +#define REG_PORT_PME_STATUS 0x0013 +#define REG_PORT_PME_CTRL 0x0017 + +#define PME_WOL_MAGICPKT BIT(2) +#define PME_WOL_LINKUP BIT(1) +#define PME_WOL_ENERGY BIT(0) + +#define REG_SW_PME_CTRL 0x0006 + +#define PME_ENABLE BIT(1) +#define PME_POLARITY BIT(0) + /* Interrupt */ #define REG_SW_PORT_INT_STATUS__1 0x001B #define REG_SW_PORT_INT_MASK__1 0x001F From fd250fed1f8856c37caa7b9a5e6015ad6f5011e5 Mon Sep 17 00:00:00 2001 From: Pieter Van Trappen Date: Tue, 13 Aug 2024 16:27:37 +0200 Subject: [PATCH 172/385] net: dsa: microchip: generalize KSZ9477 WoL functions at ksz_common Generalize KSZ9477 WoL functions at ksz_common. Move dedicated registers and generic masks to existing structures & defines for that purpose. Introduction of PME (port) read/write helper functions, which happen to be the generic read/write for KSZ9477 but not for the incoming KSZ87xx patch. Signed-off-by: Pieter Van Trappen Acked-by: Arun Ramadoss Link: https://patch.msgid.link/20240813142750.772781-4-vtpieter@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/microchip/ksz9477.c | 16 ++-- drivers/net/dsa/microchip/ksz_common.c | 113 +++++++++++++------------ drivers/net/dsa/microchip/ksz_common.h | 30 +++---- 3 files changed, 81 insertions(+), 78 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 6c1540f725e5d..0ba658a72d8fe 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -1023,6 +1023,7 @@ void ksz9477_port_queue_split(struct ksz_device *dev, int port) void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) { + const u16 *regs = dev->info->regs; struct dsa_switch *ds = dev->ds; u16 data16; u8 member; @@ -1067,12 +1068,12 @@ void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) ksz9477_port_acl_init(dev, port); /* clear pending wake flags */ - ksz9477_handle_wake_reason(dev, port); + ksz_handle_wake_reason(dev, port); /* Disable all WoL options by default. Otherwise * ksz_switch_macaddr_get/put logic will not work properly. */ - ksz_pwrite8(dev, port, REG_PORT_PME_CTRL, 0); + ksz_pwrite8(dev, port, regs[REG_PORT_PME_CTRL], 0); } void ksz9477_config_cpu_port(struct dsa_switch *ds) @@ -1169,6 +1170,7 @@ int ksz9477_enable_stp_addr(struct ksz_device *dev) int ksz9477_setup(struct dsa_switch *ds) { struct ksz_device *dev = ds->priv; + const u16 *regs = dev->info->regs; int ret = 0; ds->mtu_enforcement_ingress = true; @@ -1199,13 +1201,11 @@ int ksz9477_setup(struct dsa_switch *ds) /* enable global MIB counter freeze function */ ksz_cfg(dev, REG_SW_MAC_CTRL_6, SW_MIB_COUNTER_FREEZE, true); - /* Make sure PME (WoL) is not enabled. If requested, it will be - * enabled by ksz9477_wol_pre_shutdown(). Otherwise, some PMICs do not - * like PME events changes before shutdown. + /* Make sure PME (WoL) is not enabled. If requested, it will + * be enabled by ksz_wol_pre_shutdown(). Otherwise, some PMICs + * do not like PME events changes before shutdown. */ - ksz_write8(dev, REG_SW_PME_CTRL, 0); - - return 0; + return ksz_write8(dev, regs[REG_SW_PME_CTRL], 0); } u32 ksz9477_get_port_addr(int port, int offset) diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 7afe958d0e21d..e2a9a652c41ab 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -348,9 +348,9 @@ static const struct ksz_dev_ops ksz9477_dev_ops = { .mdb_add = ksz9477_mdb_add, .mdb_del = ksz9477_mdb_del, .change_mtu = ksz9477_change_mtu, - .get_wol = ksz9477_get_wol, - .set_wol = ksz9477_set_wol, - .wol_pre_shutdown = ksz9477_wol_pre_shutdown, + .pme_write8 = ksz_write8, + .pme_pread8 = ksz_pread8, + .pme_pwrite8 = ksz_pwrite8, .config_cpu_port = ksz9477_config_cpu_port, .tc_cbs_set_cinc = ksz9477_tc_cbs_set_cinc, .enable_stp_addr = ksz9477_enable_stp_addr, @@ -539,6 +539,9 @@ static const u16 ksz9477_regs[] = { [S_MULTICAST_CTRL] = 0x0331, [P_XMII_CTRL_0] = 0x0300, [P_XMII_CTRL_1] = 0x0301, + [REG_SW_PME_CTRL] = 0x0006, + [REG_PORT_PME_STATUS] = 0x0013, + [REG_PORT_PME_CTRL] = 0x0017, }; static const u32 ksz9477_masks[] = { @@ -3742,17 +3745,8 @@ static int ksz_setup_tc(struct dsa_switch *ds, int port, } } -static void ksz_get_wol(struct dsa_switch *ds, int port, - struct ethtool_wolinfo *wol) -{ - struct ksz_device *dev = ds->priv; - - if (dev->dev_ops->get_wol) - dev->dev_ops->get_wol(dev, port, wol); -} - /** - * ksz9477_handle_wake_reason - Handle wake reason on a specified port. + * ksz_handle_wake_reason - Handle wake reason on a specified port. * @dev: The device structure. * @port: The port number. * @@ -3764,12 +3758,15 @@ static void ksz_get_wol(struct dsa_switch *ds, int port, * * Return: 0 on success, or an error code on failure. */ -int ksz9477_handle_wake_reason(struct ksz_device *dev, int port) +int ksz_handle_wake_reason(struct ksz_device *dev, int port) { + const struct ksz_dev_ops *ops = dev->dev_ops; + const u16 *regs = dev->info->regs; u8 pme_status; int ret; - ret = ksz_pread8(dev, port, REG_PORT_PME_STATUS, &pme_status); + ret = ops->pme_pread8(dev, port, regs[REG_PORT_PME_STATUS], + &pme_status); if (ret) return ret; @@ -3781,25 +3778,31 @@ int ksz9477_handle_wake_reason(struct ksz_device *dev, int port) pme_status & PME_WOL_LINKUP ? " \"Link Up\"" : "", pme_status & PME_WOL_ENERGY ? " \"Energy detect\"" : ""); - return ksz_pwrite8(dev, port, REG_PORT_PME_STATUS, pme_status); + return ops->pme_pwrite8(dev, port, regs[REG_PORT_PME_STATUS], + pme_status); } /** - * ksz9477_get_wol - Get Wake-on-LAN settings for a specified port. - * @dev: The device structure. + * ksz_get_wol - Get Wake-on-LAN settings for a specified port. + * @ds: The dsa_switch structure. * @port: The port number. * @wol: Pointer to ethtool Wake-on-LAN settings structure. * - * This function checks the PME Pin Control Register to see if PME Pin Output - * Enable is set, indicating PME is enabled. If enabled, it sets the supported - * and active WoL flags. + * This function checks the device PME wakeup_source flag and chip_id. + * If enabled and supported, it sets the supported and active WoL + * flags. */ -void ksz9477_get_wol(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol) +static void ksz_get_wol(struct dsa_switch *ds, int port, + struct ethtool_wolinfo *wol) { + struct ksz_device *dev = ds->priv; + const u16 *regs = dev->info->regs; u8 pme_ctrl; int ret; + if (!is_ksz9477(dev)) + return; + if (!dev->wakeup_source) return; @@ -3812,7 +3815,8 @@ void ksz9477_get_wol(struct ksz_device *dev, int port, if (ksz_is_port_mac_global_usable(dev->ds, port)) wol->supported |= WAKE_MAGIC; - ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl); + ret = dev->dev_ops->pme_pread8(dev, port, regs[REG_PORT_PME_CTRL], + &pme_ctrl); if (ret) return; @@ -3822,35 +3826,26 @@ void ksz9477_get_wol(struct ksz_device *dev, int port, wol->wolopts |= WAKE_PHY; } -static int ksz_set_wol(struct dsa_switch *ds, int port, - struct ethtool_wolinfo *wol) -{ - struct ksz_device *dev = ds->priv; - - if (dev->dev_ops->set_wol) - return dev->dev_ops->set_wol(dev, port, wol); - - return -EOPNOTSUPP; -} - /** - * ksz9477_set_wol - Set Wake-on-LAN settings for a specified port. - * @dev: The device structure. + * ksz_set_wol - Set Wake-on-LAN settings for a specified port. + * @ds: The dsa_switch structure. * @port: The port number. * @wol: Pointer to ethtool Wake-on-LAN settings structure. * - * This function configures Wake-on-LAN (WoL) settings for a specified port. - * It validates the provided WoL options, checks if PME is enabled via the - * switch's PME Pin Control Register, clears any previous wake reasons, - * and sets the Magic Packet flag in the port's PME control register if + * This function configures Wake-on-LAN (WoL) settings for a specified + * port. It validates the provided WoL options, checks if PME is + * enabled and supported, clears any previous wake reasons, and sets + * the Magic Packet flag in the port's PME control register if * specified. * * Return: 0 on success, or other error codes on failure. */ -int ksz9477_set_wol(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol) +static int ksz_set_wol(struct dsa_switch *ds, int port, + struct ethtool_wolinfo *wol) { u8 pme_ctrl = 0, pme_ctrl_old = 0; + struct ksz_device *dev = ds->priv; + const u16 *regs = dev->info->regs; bool magic_switched_off; bool magic_switched_on; int ret; @@ -3858,10 +3853,13 @@ int ksz9477_set_wol(struct ksz_device *dev, int port, if (wol->wolopts & ~(WAKE_PHY | WAKE_MAGIC)) return -EINVAL; + if (!is_ksz9477(dev)) + return -EOPNOTSUPP; + if (!dev->wakeup_source) return -EOPNOTSUPP; - ret = ksz9477_handle_wake_reason(dev, port); + ret = ksz_handle_wake_reason(dev, port); if (ret) return ret; @@ -3870,7 +3868,8 @@ int ksz9477_set_wol(struct ksz_device *dev, int port, if (wol->wolopts & WAKE_PHY) pme_ctrl |= PME_WOL_LINKUP | PME_WOL_ENERGY; - ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl_old); + ret = dev->dev_ops->pme_pread8(dev, port, regs[REG_PORT_PME_CTRL], + &pme_ctrl_old); if (ret) return ret; @@ -3893,7 +3892,8 @@ int ksz9477_set_wol(struct ksz_device *dev, int port, ksz_switch_macaddr_put(dev->ds); } - ret = ksz_pwrite8(dev, port, REG_PORT_PME_CTRL, pme_ctrl); + ret = dev->dev_ops->pme_pwrite8(dev, port, regs[REG_PORT_PME_CTRL], + pme_ctrl); if (ret) { if (magic_switched_on) ksz_switch_macaddr_put(dev->ds); @@ -3904,8 +3904,8 @@ int ksz9477_set_wol(struct ksz_device *dev, int port, } /** - * ksz9477_wol_pre_shutdown - Prepares the switch device for shutdown while - * considering Wake-on-LAN (WoL) settings. + * ksz_wol_pre_shutdown - Prepares the switch device for shutdown while + * considering Wake-on-LAN (WoL) settings. * @dev: The switch device structure. * @wol_enabled: Pointer to a boolean which will be set to true if WoL is * enabled on any port. @@ -3915,32 +3915,38 @@ int ksz9477_set_wol(struct ksz_device *dev, int port, * the wol_enabled flag accordingly to reflect whether WoL is active on any * port. */ -void ksz9477_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled) +static void ksz_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled) { + const struct ksz_dev_ops *ops = dev->dev_ops; + const u16 *regs = dev->info->regs; struct dsa_port *dp; int ret; *wol_enabled = false; + if (!is_ksz9477(dev)) + return; + if (!dev->wakeup_source) return; dsa_switch_for_each_user_port(dp, dev->ds) { u8 pme_ctrl = 0; - ret = ksz_pread8(dev, dp->index, REG_PORT_PME_CTRL, &pme_ctrl); + ret = ops->pme_pread8(dev, dp->index, + regs[REG_PORT_PME_CTRL], &pme_ctrl); if (!ret && pme_ctrl) *wol_enabled = true; /* make sure there are no pending wake events which would * prevent the device from going to sleep/shutdown. */ - ksz9477_handle_wake_reason(dev, dp->index); + ksz_handle_wake_reason(dev, dp->index); } /* Now we are save to enable PME pin. */ if (*wol_enabled) - ksz_write8(dev, REG_SW_PME_CTRL, PME_ENABLE); + ops->pme_write8(dev, regs[REG_SW_PME_CTRL], PME_ENABLE); } static int ksz_port_set_mac_address(struct dsa_switch *ds, int port, @@ -4253,8 +4259,7 @@ void ksz_switch_shutdown(struct ksz_device *dev) { bool wol_enabled = false; - if (dev->dev_ops->wol_pre_shutdown) - dev->dev_ops->wol_pre_shutdown(dev, &wol_enabled); + ksz_wol_pre_shutdown(dev, &wol_enabled); if (dev->dev_ops->reset && !wol_enabled) dev->dev_ops->reset(dev); diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index e35caca96f89f..c60c218afa64d 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -235,6 +235,9 @@ enum ksz_regs { S_MULTICAST_CTRL, P_XMII_CTRL_0, P_XMII_CTRL_1, + REG_SW_PME_CTRL, + REG_PORT_PME_STATUS, + REG_PORT_PME_CTRL, }; enum ksz_masks { @@ -354,6 +357,11 @@ struct ksz_dev_ops { void (*get_caps)(struct ksz_device *dev, int port, struct phylink_config *config); int (*change_mtu)(struct ksz_device *dev, int port, int mtu); + int (*pme_write8)(struct ksz_device *dev, u32 reg, u8 value); + int (*pme_pread8)(struct ksz_device *dev, int port, int offset, + u8 *data); + int (*pme_pwrite8)(struct ksz_device *dev, int port, int offset, + u8 data); void (*freeze_mib)(struct ksz_device *dev, int port, bool freeze); void (*port_init_cnt)(struct ksz_device *dev, int port); void (*phylink_mac_link_up)(struct ksz_device *dev, int port, @@ -363,11 +371,6 @@ struct ksz_dev_ops { int duplex, bool tx_pause, bool rx_pause); void (*setup_rgmii_delay)(struct ksz_device *dev, int port); int (*tc_cbs_set_cinc)(struct ksz_device *dev, int port, u32 val); - void (*get_wol)(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol); - int (*set_wol)(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol); - void (*wol_pre_shutdown)(struct ksz_device *dev, bool *wol_enabled); void (*config_cpu_port)(struct dsa_switch *ds); int (*enable_stp_addr)(struct ksz_device *dev); int (*reset)(struct ksz_device *dev); @@ -391,12 +394,7 @@ int ksz_switch_macaddr_get(struct dsa_switch *ds, int port, struct netlink_ext_ack *extack); void ksz_switch_macaddr_put(struct dsa_switch *ds); void ksz_switch_shutdown(struct ksz_device *dev); -int ksz9477_handle_wake_reason(struct ksz_device *dev, int port); -void ksz9477_get_wol(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol); -int ksz9477_set_wol(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol); -void ksz9477_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled); +int ksz_handle_wake_reason(struct ksz_device *dev, int port); /* Common register access functions */ static inline struct regmap *ksz_regmap_8(struct ksz_device *dev) @@ -635,6 +633,11 @@ static inline bool is_ksz8(struct ksz_device *dev) return ksz_is_ksz87xx(dev) || ksz_is_ksz88x3(dev); } +static inline bool is_ksz9477(struct ksz_device *dev) +{ + return dev->chip_id == KSZ9477_CHIP_ID; +} + static inline int is_lan937x(struct ksz_device *dev) { return dev->chip_id == LAN9370_CHIP_ID || @@ -702,15 +705,10 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port) #define P_MII_SEL_M 0x3 /* KSZ9477, KSZ8795 Wake-on-LAN (WoL) masks */ -#define REG_PORT_PME_STATUS 0x0013 -#define REG_PORT_PME_CTRL 0x0017 - #define PME_WOL_MAGICPKT BIT(2) #define PME_WOL_LINKUP BIT(1) #define PME_WOL_ENERGY BIT(0) -#define REG_SW_PME_CTRL 0x0006 - #define PME_ENABLE BIT(1) #define PME_POLARITY BIT(0) From 90b06ac06529b4c90af97763e57cf38d96999827 Mon Sep 17 00:00:00 2001 From: Pieter Van Trappen Date: Tue, 13 Aug 2024 16:27:38 +0200 Subject: [PATCH 173/385] net: dsa: microchip: add WoL support for KSZ87xx family Add WoL support for KSZ87xx family of switches. This code was tested with a KSZ8794 chip. Implement ksz_common usage of the new device-tree property 'microchip,pme-active-high'. Make use of the now generalized ksz_common WoL functions, adding an additional interrupt register write for KSZ87xx. Add helper functions to convert from PME (port) read/writes to indirect register read/writes in the dedicated ksz8795 sources. Add initial configuration during (port) setup as per KSZ9477. Signed-off-by: Pieter Van Trappen Acked-by: Arun Ramadoss Link: https://patch.msgid.link/20240813142750.772781-5-vtpieter@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/microchip/ksz8.h | 3 + drivers/net/dsa/microchip/ksz8795.c | 94 +++++++++++++++++++++++++- drivers/net/dsa/microchip/ksz_common.c | 24 +++++-- drivers/net/dsa/microchip/ksz_common.h | 6 +- 4 files changed, 119 insertions(+), 8 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz8.h b/drivers/net/dsa/microchip/ksz8.h index ae43077e76c35..e1c79ff971237 100644 --- a/drivers/net/dsa/microchip/ksz8.h +++ b/drivers/net/dsa/microchip/ksz8.h @@ -54,6 +54,9 @@ int ksz8_reset_switch(struct ksz_device *dev); int ksz8_switch_init(struct ksz_device *dev); void ksz8_switch_exit(struct ksz_device *dev); int ksz8_change_mtu(struct ksz_device *dev, int port, int mtu); +int ksz8_pme_write8(struct ksz_device *dev, u32 reg, u8 value); +int ksz8_pme_pread8(struct ksz_device *dev, int port, int offset, u8 *data); +int ksz8_pme_pwrite8(struct ksz_device *dev, int port, int offset, u8 data); void ksz8_phylink_mac_link_up(struct phylink_config *config, struct phy_device *phydev, unsigned int mode, phy_interface_t interface, int speed, int duplex, diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index d27b9c36d73fc..a01079297a8cd 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -38,6 +38,20 @@ static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits, bits, set ? bits : 0); } +/** + * ksz8_ind_write8 - EEE/ACL/PME indirect register write + * @dev: The device structure. + * @table: Function & table select, register 110. + * @addr: Indirect access control, register 111. + * @data: The data to be written. + * + * This function performs an indirect register write for EEE, ACL or + * PME switch functionalities. Both 8-bit registers 110 and 111 are + * written at once with ksz_write16, using the serial multiple write + * functionality. + * + * Return: 0 on success, or an error code on failure. + */ static int ksz8_ind_write8(struct ksz_device *dev, u8 table, u16 addr, u8 data) { const u16 *regs; @@ -58,6 +72,59 @@ static int ksz8_ind_write8(struct ksz_device *dev, u8 table, u16 addr, u8 data) return ret; } +/** + * ksz8_ind_read8 - EEE/ACL/PME indirect register read + * @dev: The device structure. + * @table: Function & table select, register 110. + * @addr: Indirect access control, register 111. + * @val: The value read. + * + * This function performs an indirect register read for EEE, ACL or + * PME switch functionalities. Both 8-bit registers 110 and 111 are + * written at once with ksz_write16, using the serial multiple write + * functionality. + * + * Return: 0 on success, or an error code on failure. + */ +static int ksz8_ind_read8(struct ksz_device *dev, u8 table, u16 addr, u8 *val) +{ + const u16 *regs; + u16 ctrl_addr; + int ret = 0; + + regs = dev->info->regs; + + mutex_lock(&dev->alu_mutex); + + ctrl_addr = IND_ACC_TABLE(table | TABLE_READ) | addr; + ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr); + if (!ret) + ret = ksz_read8(dev, regs[REG_IND_BYTE], val); + + mutex_unlock(&dev->alu_mutex); + + return ret; +} + +int ksz8_pme_write8(struct ksz_device *dev, u32 reg, u8 value) +{ + return ksz8_ind_write8(dev, (u8)(reg >> 8), (u8)(reg), value); +} + +int ksz8_pme_pread8(struct ksz_device *dev, int port, int offset, u8 *data) +{ + u8 table = (u8)(offset >> 8 | (port + 1)); + + return ksz8_ind_read8(dev, table, (u8)(offset), data); +} + +int ksz8_pme_pwrite8(struct ksz_device *dev, int port, int offset, u8 data) +{ + u8 table = (u8)(offset >> 8 | (port + 1)); + + return ksz8_ind_write8(dev, table, (u8)(offset), data); +} + int ksz8_reset_switch(struct ksz_device *dev) { if (ksz_is_ksz88x3(dev)) { @@ -1545,6 +1612,7 @@ static void ksz8795_cpu_interface_select(struct ksz_device *dev, int port) void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port) { + const u16 *regs = dev->info->regs; struct dsa_switch *ds = dev->ds; const u32 *masks; int queues; @@ -1575,6 +1643,13 @@ void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port) member = BIT(dsa_upstream_port(ds, port)); ksz8_cfg_port_member(dev, port, member); + + /* Disable all WoL options by default. Otherwise + * ksz_switch_macaddr_get/put logic will not work properly. + * CPU port 4 has no WoL functionality. + */ + if (ksz_is_ksz87xx(dev) && !cpu_port) + ksz8_pme_pwrite8(dev, port, regs[REG_PORT_PME_CTRL], 0); } static void ksz88x3_config_rmii_clk(struct ksz_device *dev) @@ -1790,7 +1865,8 @@ int ksz8_enable_stp_addr(struct ksz_device *dev) int ksz8_setup(struct dsa_switch *ds) { struct ksz_device *dev = ds->priv; - int i; + const u16 *regs = dev->info->regs; + int i, ret = 0; ds->mtu_enforcement_ingress = true; @@ -1829,7 +1905,21 @@ int ksz8_setup(struct dsa_switch *ds) for (i = 0; i < (dev->info->num_vlans / 4); i++) ksz8_r_vlan_entries(dev, i); - return ksz8_handle_global_errata(ds); + /* Make sure PME (WoL) is not enabled. If requested, it will + * be enabled by ksz_wol_pre_shutdown(). Otherwise, some PMICs + * do not like PME events changes before shutdown. PME only + * available on KSZ87xx family. + */ + if (ksz_is_ksz87xx(dev)) { + ret = ksz8_pme_write8(dev, regs[REG_SW_PME_CTRL], 0); + if (!ret) + ret = ksz_rmw8(dev, REG_INT_ENABLE, INT_PME, 0); + } + + if (!ret) + return ksz8_handle_global_errata(ds); + else + return ret; } void ksz8_get_caps(struct ksz_device *dev, int port, diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index e2a9a652c41ab..3f3230d181d87 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -307,6 +307,9 @@ static const struct ksz_dev_ops ksz8_dev_ops = { .init = ksz8_switch_init, .exit = ksz8_switch_exit, .change_mtu = ksz8_change_mtu, + .pme_write8 = ksz8_pme_write8, + .pme_pread8 = ksz8_pme_pread8, + .pme_pwrite8 = ksz8_pme_pwrite8, }; static void ksz9477_phylink_mac_link_up(struct phylink_config *config, @@ -423,6 +426,9 @@ static const u16 ksz8795_regs[] = { [S_MULTICAST_CTRL] = 0x04, [P_XMII_CTRL_0] = 0x06, [P_XMII_CTRL_1] = 0x06, + [REG_SW_PME_CTRL] = 0x8003, + [REG_PORT_PME_STATUS] = 0x8003, + [REG_PORT_PME_CTRL] = 0x8007, }; static const u32 ksz8795_masks[] = { @@ -3800,7 +3806,7 @@ static void ksz_get_wol(struct dsa_switch *ds, int port, u8 pme_ctrl; int ret; - if (!is_ksz9477(dev)) + if (!is_ksz9477(dev) && !ksz_is_ksz87xx(dev)) return; if (!dev->wakeup_source) @@ -3853,7 +3859,7 @@ static int ksz_set_wol(struct dsa_switch *ds, int port, if (wol->wolopts & ~(WAKE_PHY | WAKE_MAGIC)) return -EINVAL; - if (!is_ksz9477(dev)) + if (!is_ksz9477(dev) && !ksz_is_ksz87xx(dev)) return -EOPNOTSUPP; if (!dev->wakeup_source) @@ -3919,12 +3925,13 @@ static void ksz_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled) { const struct ksz_dev_ops *ops = dev->dev_ops; const u16 *regs = dev->info->regs; + u8 pme_pin_en = PME_ENABLE; struct dsa_port *dp; int ret; *wol_enabled = false; - if (!is_ksz9477(dev)) + if (!is_ksz9477(dev) && !ksz_is_ksz87xx(dev)) return; if (!dev->wakeup_source) @@ -3945,8 +3952,13 @@ static void ksz_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled) } /* Now we are save to enable PME pin. */ - if (*wol_enabled) - ops->pme_write8(dev, regs[REG_SW_PME_CTRL], PME_ENABLE); + if (*wol_enabled) { + if (dev->pme_active_high) + pme_pin_en |= PME_POLARITY; + ops->pme_write8(dev, regs[REG_SW_PME_CTRL], pme_pin_en); + if (ksz_is_ksz87xx(dev)) + ksz_write8(dev, KSZ87XX_REG_INT_EN, KSZ87XX_INT_PME_MASK); + } } static int ksz_port_set_mac_address(struct dsa_switch *ds, int port, @@ -4661,6 +4673,8 @@ int ksz_switch_register(struct ksz_device *dev) dev->wakeup_source = of_property_read_bool(dev->dev->of_node, "wakeup-source"); + dev->pme_active_high = of_property_read_bool(dev->dev->of_node, + "microchip,pme-active-high"); } ret = dsa_register_switch(dev->ds); diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index c60c218afa64d..8094d90d6ca46 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -174,6 +174,7 @@ struct ksz_device { bool synclko_125; bool synclko_disable; bool wakeup_source; + bool pme_active_high; struct vlan_table *vlan_cache; @@ -704,7 +705,7 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port) #define P_MII_MAC_MODE BIT(2) #define P_MII_SEL_M 0x3 -/* KSZ9477, KSZ8795 Wake-on-LAN (WoL) masks */ +/* KSZ9477, KSZ87xx Wake-on-LAN (WoL) masks */ #define PME_WOL_MAGICPKT BIT(2) #define PME_WOL_LINKUP BIT(1) #define PME_WOL_ENERGY BIT(0) @@ -712,6 +713,9 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port) #define PME_ENABLE BIT(1) #define PME_POLARITY BIT(0) +#define KSZ87XX_REG_INT_EN 0x7D +#define KSZ87XX_INT_PME_MASK BIT(4) + /* Interrupt */ #define REG_SW_PORT_INT_STATUS__1 0x001B #define REG_SW_PORT_INT_MASK__1 0x001F From 0d3edc90c4a0ac77332a25e1e6b709a39b202de9 Mon Sep 17 00:00:00 2001 From: Pieter Van Trappen Date: Tue, 13 Aug 2024 16:27:39 +0200 Subject: [PATCH 174/385] net: dsa: microchip: fix KSZ87xx family structure wrt the datasheet The KSZ87xx switches have 32 static MAC address table entries and not 8. This fixes -ENOSPC non-critical errors from ksz8_add_sta_mac when configured as a bridge. Add a new ksz87xx_dev_ops structure to be able to use the ksz_r_mib_stat64 pointer for this family; this corrects a wrong mib->counters cast to ksz88xx_stats_raw. This fixes iproute2 statistics. Rename ksz8_dev_ops structure to ksz88x3_dev_ops, in line with ksz_is_* naming conventions from ksz_common.h. Signed-off-by: Pieter Van Trappen Acked-by: Arun Ramadoss Link: https://patch.msgid.link/20240813142750.772781-6-vtpieter@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/microchip/ksz_common.c | 51 ++++++++++++++++++++++---- 1 file changed, 43 insertions(+), 8 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 3f3230d181d87..cd3991792b69f 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -277,7 +277,7 @@ static const struct phylink_mac_ops ksz8_phylink_mac_ops = { .mac_link_up = ksz8_phylink_mac_link_up, }; -static const struct ksz_dev_ops ksz8_dev_ops = { +static const struct ksz_dev_ops ksz88x3_dev_ops = { .setup = ksz8_setup, .get_port_addr = ksz8_get_port_addr, .cfg_port_member = ksz8_cfg_port_member, @@ -312,6 +312,41 @@ static const struct ksz_dev_ops ksz8_dev_ops = { .pme_pwrite8 = ksz8_pme_pwrite8, }; +static const struct ksz_dev_ops ksz87xx_dev_ops = { + .setup = ksz8_setup, + .get_port_addr = ksz8_get_port_addr, + .cfg_port_member = ksz8_cfg_port_member, + .flush_dyn_mac_table = ksz8_flush_dyn_mac_table, + .port_setup = ksz8_port_setup, + .r_phy = ksz8_r_phy, + .w_phy = ksz8_w_phy, + .r_mib_cnt = ksz8_r_mib_cnt, + .r_mib_pkt = ksz8_r_mib_pkt, + .r_mib_stat64 = ksz_r_mib_stats64, + .freeze_mib = ksz8_freeze_mib, + .port_init_cnt = ksz8_port_init_cnt, + .fdb_dump = ksz8_fdb_dump, + .fdb_add = ksz8_fdb_add, + .fdb_del = ksz8_fdb_del, + .mdb_add = ksz8_mdb_add, + .mdb_del = ksz8_mdb_del, + .vlan_filtering = ksz8_port_vlan_filtering, + .vlan_add = ksz8_port_vlan_add, + .vlan_del = ksz8_port_vlan_del, + .mirror_add = ksz8_port_mirror_add, + .mirror_del = ksz8_port_mirror_del, + .get_caps = ksz8_get_caps, + .config_cpu_port = ksz8_config_cpu_port, + .enable_stp_addr = ksz8_enable_stp_addr, + .reset = ksz8_reset_switch, + .init = ksz8_switch_init, + .exit = ksz8_switch_exit, + .change_mtu = ksz8_change_mtu, + .pme_write8 = ksz8_pme_write8, + .pme_pread8 = ksz8_pme_pread8, + .pme_pwrite8 = ksz8_pme_pwrite8, +}; + static void ksz9477_phylink_mac_link_up(struct phylink_config *config, struct phy_device *phydev, unsigned int mode, @@ -1262,12 +1297,12 @@ const struct ksz_chip_data ksz_switch_chips[] = { .dev_name = "KSZ8795", .num_vlans = 4096, .num_alus = 0, - .num_statics = 8, + .num_statics = 32, .cpu_ports = 0x10, /* can be configured as cpu port */ .port_cnt = 5, /* total cpu and user ports */ .num_tx_queues = 4, .num_ipms = 4, - .ops = &ksz8_dev_ops, + .ops = &ksz87xx_dev_ops, .phylink_mac_ops = &ksz8_phylink_mac_ops, .ksz87xx_eee_link_erratum = true, .mib_names = ksz9477_mib_names, @@ -1303,12 +1338,12 @@ const struct ksz_chip_data ksz_switch_chips[] = { .dev_name = "KSZ8794", .num_vlans = 4096, .num_alus = 0, - .num_statics = 8, + .num_statics = 32, .cpu_ports = 0x10, /* can be configured as cpu port */ .port_cnt = 5, /* total cpu and user ports */ .num_tx_queues = 4, .num_ipms = 4, - .ops = &ksz8_dev_ops, + .ops = &ksz87xx_dev_ops, .phylink_mac_ops = &ksz8_phylink_mac_ops, .ksz87xx_eee_link_erratum = true, .mib_names = ksz9477_mib_names, @@ -1330,12 +1365,12 @@ const struct ksz_chip_data ksz_switch_chips[] = { .dev_name = "KSZ8765", .num_vlans = 4096, .num_alus = 0, - .num_statics = 8, + .num_statics = 32, .cpu_ports = 0x10, /* can be configured as cpu port */ .port_cnt = 5, /* total cpu and user ports */ .num_tx_queues = 4, .num_ipms = 4, - .ops = &ksz8_dev_ops, + .ops = &ksz87xx_dev_ops, .phylink_mac_ops = &ksz8_phylink_mac_ops, .ksz87xx_eee_link_erratum = true, .mib_names = ksz9477_mib_names, @@ -1362,7 +1397,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .port_cnt = 3, .num_tx_queues = 4, .num_ipms = 4, - .ops = &ksz8_dev_ops, + .ops = &ksz88x3_dev_ops, .phylink_mac_ops = &ksz8830_phylink_mac_ops, .mib_names = ksz88xx_mib_names, .mib_cnt = ARRAY_SIZE(ksz88xx_mib_names), From 6f2b72c04d58a40c16f3cd858776517f16226119 Mon Sep 17 00:00:00 2001 From: Pieter Van Trappen Date: Tue, 13 Aug 2024 16:27:40 +0200 Subject: [PATCH 175/385] net: dsa: microchip: fix tag_ksz egress mask for KSZ8795 family Fix the tag_ksz egress mask for DSA_TAG_PROTO_KSZ8795, the port is encoded in the two and not three LSB. This fix is for completeness, for example the bug doesn't manifest itself on the KSZ8794 because bit 2 seems to be always zero. Signed-off-by: Pieter Van Trappen Acked-by: Arun Ramadoss Link: https://patch.msgid.link/20240813142750.772781-7-vtpieter@gmail.com Signed-off-by: Jakub Kicinski --- net/dsa/tag_ksz.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index ee7b272ab7159..1f46de394f2e8 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -111,9 +111,10 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes) * --------------------------------------------------------------------------- * tag0 : zero-based value represents port - * (eg, 0x00=port1, 0x02=port3, 0x06=port7) + * (eg, 0x0=port1, 0x2=port3, 0x3=port4) */ +#define KSZ8795_TAIL_TAG_EG_PORT_M GENMASK(1, 0) #define KSZ8795_TAIL_TAG_OVERRIDE BIT(6) #define KSZ8795_TAIL_TAG_LOOKUP BIT(7) @@ -141,7 +142,8 @@ static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev) { u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; - return ksz_common_rcv(skb, dev, tag[0] & 7, KSZ_EGRESS_TAG_LEN); + return ksz_common_rcv(skb, dev, tag[0] & KSZ8795_TAIL_TAG_EG_PORT_M, + KSZ_EGRESS_TAG_LEN); } static const struct dsa_device_ops ksz8795_netdev_ops = { From f40a455d01f80c6638be382d75cb1c4e7748d8af Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 13 Aug 2024 14:33:47 +0100 Subject: [PATCH 176/385] ipv6: Add ipv6_addr_{cpu_to_be32,be32_to_cpu} helpers Add helpers to convert an ipv6 addr, expressed as an array of words, from CPU to big-endian byte order, and vice versa. No functional change intended. Compile tested only. Suggested-by: Andrew Lunn Link: https://lore.kernel.org/netdev/c7684349-535c-45a4-9a74-d47479a50020@lunn.ch/ Reviewed-by: Andrew Lunn Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240813-ipv6_addr-helpers-v2-1-5c974f8cca3e@kernel.org Signed-off-by: Jakub Kicinski --- include/net/ipv6.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 88a8e554f7a12..e7113855a10fd 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1365,4 +1365,16 @@ static inline void ip6_sock_set_recvpktinfo(struct sock *sk) release_sock(sk); } +#define IPV6_ADDR_WORDS 4 + +static inline void ipv6_addr_cpu_to_be32(__be32 *dst, const u32 *src) +{ + cpu_to_be32_array(dst, src, IPV6_ADDR_WORDS); +} + +static inline void ipv6_addr_be32_to_cpu(u32 *dst, const __be32 *src) +{ + be32_to_cpu_array(dst, src, IPV6_ADDR_WORDS); +} + #endif /* _NET_IPV6_H */ From b908c722133e3a158bf703b5003e7a8272e9d540 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 13 Aug 2024 14:33:48 +0100 Subject: [PATCH 177/385] net: ethernet: mtk_eth_soc: Use ipv6_addr_{cpu_to_be32,be32_to_cpu} helpers Use ipv6_addr_cpu_to_be32 and ipv6_addr_be32_to_cpu helpers to convert address, rather than open coding the conversion. No functional change intended. Compile tested only. Suggested-by: Andrew Lunn Link: https://lore.kernel.org/netdev/c7684349-535c-45a4-9a74-d47479a50020@lunn.ch/ Reviewed-by: Andrew Lunn Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240813-ipv6_addr-helpers-v2-2-5c974f8cca3e@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mediatek/mtk_ppe.c | 10 +++++----- drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c | 9 +++++---- 2 files changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index 0acee405a7498..ada852adc5f70 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -8,8 +8,11 @@ #include #include #include + #include #include +#include + #include "mtk_eth_soc.h" #include "mtk_ppe.h" #include "mtk_ppe_regs.h" @@ -338,7 +341,6 @@ int mtk_foe_entry_set_ipv6_tuple(struct mtk_eth *eth, { int type = mtk_get_ib1_pkt_type(eth, entry->ib1); u32 *src, *dest; - int i; switch (type) { case MTK_PPE_PKT_TYPE_IPV4_DSLITE: @@ -359,10 +361,8 @@ int mtk_foe_entry_set_ipv6_tuple(struct mtk_eth *eth, return -EINVAL; } - for (i = 0; i < 4; i++) - src[i] = be32_to_cpu(src_addr[i]); - for (i = 0; i < 4; i++) - dest[i] = be32_to_cpu(dest_addr[i]); + ipv6_addr_be32_to_cpu(src, src_addr); + ipv6_addr_be32_to_cpu(dest, dest_addr); return 0; } diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c b/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c index 1a97feca77f23..570ebf91f6935 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c @@ -3,6 +3,9 @@ #include #include + +#include + #include "mtk_eth_soc.h" struct mtk_flow_addr_info @@ -47,16 +50,14 @@ static const char *mtk_foe_pkt_type_str(int type) static void mtk_print_addr(struct seq_file *m, u32 *addr, bool ipv6) { - __be32 n_addr[4]; - int i; + __be32 n_addr[IPV6_ADDR_WORDS]; if (!ipv6) { seq_printf(m, "%pI4h", addr); return; } - for (i = 0; i < ARRAY_SIZE(n_addr); i++) - n_addr[i] = htonl(addr[i]); + ipv6_addr_cpu_to_be32(n_addr, addr); seq_printf(m, "%pI6", n_addr); } From c7be6e70d20c0f8a20b484a0c51d2a12ef8f8ec7 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 13 Aug 2024 14:33:49 +0100 Subject: [PATCH 178/385] net: hns3: Use ipv6_addr_{cpu_to_be32,be32_to_cpu} helpers Use new ipv6_addr_cpu_to_be32 and ipv6_addr_be32_to_cpu helpers, and IPV6_ADDR_WORDS. This is arguably slightly nicer. No functional change intended. Compile tested only. Suggested-by: Andrew Lunn Link: https://lore.kernel.org/netdev/c7684349-535c-45a4-9a74-d47479a50020@lunn.ch/ Reviewed-by: Andrew Lunn Reviewed-by: Jijie Shao Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240813-ipv6_addr-helpers-v2-3-5c974f8cca3e@kernel.org Signed-off-by: Jakub Kicinski --- .../hisilicon/hns3/hns3pf/hclge_main.c | 79 +++++++++---------- .../hisilicon/hns3/hns3pf/hclge_main.h | 8 +- 2 files changed, 44 insertions(+), 43 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 6c33195a1168f..bd86efd92a5a7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -13,8 +13,9 @@ #include #include #include -#include + #include + #include "hclge_cmd.h" #include "hclge_dcb.h" #include "hclge_main.h" @@ -6290,15 +6291,15 @@ static void hclge_fd_get_ip4_tuple(struct ethtool_rx_flow_spec *fs, static void hclge_fd_get_tcpip6_tuple(struct ethtool_rx_flow_spec *fs, struct hclge_fd_rule *rule, u8 ip_proto) { - be32_to_cpu_array(rule->tuples.src_ip, fs->h_u.tcp_ip6_spec.ip6src, - IPV6_SIZE); - be32_to_cpu_array(rule->tuples_mask.src_ip, fs->m_u.tcp_ip6_spec.ip6src, - IPV6_SIZE); + ipv6_addr_be32_to_cpu(rule->tuples.src_ip, + fs->h_u.tcp_ip6_spec.ip6src); + ipv6_addr_be32_to_cpu(rule->tuples_mask.src_ip, + fs->m_u.tcp_ip6_spec.ip6src); - be32_to_cpu_array(rule->tuples.dst_ip, fs->h_u.tcp_ip6_spec.ip6dst, - IPV6_SIZE); - be32_to_cpu_array(rule->tuples_mask.dst_ip, fs->m_u.tcp_ip6_spec.ip6dst, - IPV6_SIZE); + ipv6_addr_be32_to_cpu(rule->tuples.dst_ip, + fs->h_u.tcp_ip6_spec.ip6dst); + ipv6_addr_be32_to_cpu(rule->tuples_mask.dst_ip, + fs->m_u.tcp_ip6_spec.ip6dst); rule->tuples.src_port = be16_to_cpu(fs->h_u.tcp_ip6_spec.psrc); rule->tuples_mask.src_port = be16_to_cpu(fs->m_u.tcp_ip6_spec.psrc); @@ -6319,15 +6320,15 @@ static void hclge_fd_get_tcpip6_tuple(struct ethtool_rx_flow_spec *fs, static void hclge_fd_get_ip6_tuple(struct ethtool_rx_flow_spec *fs, struct hclge_fd_rule *rule) { - be32_to_cpu_array(rule->tuples.src_ip, fs->h_u.usr_ip6_spec.ip6src, - IPV6_SIZE); - be32_to_cpu_array(rule->tuples_mask.src_ip, fs->m_u.usr_ip6_spec.ip6src, - IPV6_SIZE); + ipv6_addr_be32_to_cpu(rule->tuples.src_ip, + fs->h_u.usr_ip6_spec.ip6src); + ipv6_addr_be32_to_cpu(rule->tuples_mask.src_ip, + fs->m_u.usr_ip6_spec.ip6src); - be32_to_cpu_array(rule->tuples.dst_ip, fs->h_u.usr_ip6_spec.ip6dst, - IPV6_SIZE); - be32_to_cpu_array(rule->tuples_mask.dst_ip, fs->m_u.usr_ip6_spec.ip6dst, - IPV6_SIZE); + ipv6_addr_be32_to_cpu(rule->tuples.dst_ip, + fs->h_u.usr_ip6_spec.ip6dst); + ipv6_addr_be32_to_cpu(rule->tuples_mask.dst_ip, + fs->m_u.usr_ip6_spec.ip6dst); rule->tuples.ip_proto = fs->h_u.usr_ip6_spec.l4_proto; rule->tuples_mask.ip_proto = fs->m_u.usr_ip6_spec.l4_proto; @@ -6756,21 +6757,19 @@ static void hclge_fd_get_tcpip6_info(struct hclge_fd_rule *rule, struct ethtool_tcpip6_spec *spec, struct ethtool_tcpip6_spec *spec_mask) { - cpu_to_be32_array(spec->ip6src, - rule->tuples.src_ip, IPV6_SIZE); - cpu_to_be32_array(spec->ip6dst, - rule->tuples.dst_ip, IPV6_SIZE); + ipv6_addr_cpu_to_be32(spec->ip6src, rule->tuples.src_ip); + ipv6_addr_cpu_to_be32(spec->ip6dst, rule->tuples.dst_ip); if (rule->unused_tuple & BIT(INNER_SRC_IP)) memset(spec_mask->ip6src, 0, sizeof(spec_mask->ip6src)); else - cpu_to_be32_array(spec_mask->ip6src, rule->tuples_mask.src_ip, - IPV6_SIZE); + ipv6_addr_cpu_to_be32(spec_mask->ip6src, + rule->tuples_mask.src_ip); if (rule->unused_tuple & BIT(INNER_DST_IP)) memset(spec_mask->ip6dst, 0, sizeof(spec_mask->ip6dst)); else - cpu_to_be32_array(spec_mask->ip6dst, rule->tuples_mask.dst_ip, - IPV6_SIZE); + ipv6_addr_cpu_to_be32(spec_mask->ip6dst, + rule->tuples_mask.dst_ip); spec->tclass = rule->tuples.ip_tos; spec_mask->tclass = rule->unused_tuple & BIT(INNER_IP_TOS) ? @@ -6789,19 +6788,19 @@ static void hclge_fd_get_ip6_info(struct hclge_fd_rule *rule, struct ethtool_usrip6_spec *spec, struct ethtool_usrip6_spec *spec_mask) { - cpu_to_be32_array(spec->ip6src, rule->tuples.src_ip, IPV6_SIZE); - cpu_to_be32_array(spec->ip6dst, rule->tuples.dst_ip, IPV6_SIZE); + ipv6_addr_cpu_to_be32(spec->ip6src, rule->tuples.src_ip); + ipv6_addr_cpu_to_be32(spec->ip6dst, rule->tuples.dst_ip); if (rule->unused_tuple & BIT(INNER_SRC_IP)) memset(spec_mask->ip6src, 0, sizeof(spec_mask->ip6src)); else - cpu_to_be32_array(spec_mask->ip6src, - rule->tuples_mask.src_ip, IPV6_SIZE); + ipv6_addr_cpu_to_be32(spec_mask->ip6src, + rule->tuples_mask.src_ip); if (rule->unused_tuple & BIT(INNER_DST_IP)) memset(spec_mask->ip6dst, 0, sizeof(spec_mask->ip6dst)); else - cpu_to_be32_array(spec_mask->ip6dst, - rule->tuples_mask.dst_ip, IPV6_SIZE); + ipv6_addr_cpu_to_be32(spec_mask->ip6dst, + rule->tuples_mask.dst_ip); spec->tclass = rule->tuples.ip_tos; spec_mask->tclass = rule->unused_tuple & BIT(INNER_IP_TOS) ? @@ -7019,7 +7018,7 @@ static void hclge_fd_get_flow_tuples(const struct flow_keys *fkeys, } else { int i; - for (i = 0; i < IPV6_SIZE; i++) { + for (i = 0; i < IPV6_ADDR_WORDS; i++) { tuples->src_ip[i] = be32_to_cpu(flow_ip6_src[i]); tuples->dst_ip[i] = be32_to_cpu(flow_ip6_dst[i]); } @@ -7274,14 +7273,14 @@ static int hclge_get_cls_key_ip(const struct flow_rule *flow, struct flow_match_ipv6_addrs match; flow_rule_match_ipv6_addrs(flow, &match); - be32_to_cpu_array(rule->tuples.src_ip, match.key->src.s6_addr32, - IPV6_SIZE); - be32_to_cpu_array(rule->tuples_mask.src_ip, - match.mask->src.s6_addr32, IPV6_SIZE); - be32_to_cpu_array(rule->tuples.dst_ip, match.key->dst.s6_addr32, - IPV6_SIZE); - be32_to_cpu_array(rule->tuples_mask.dst_ip, - match.mask->dst.s6_addr32, IPV6_SIZE); + ipv6_addr_be32_to_cpu(rule->tuples.src_ip, + match.key->src.s6_addr32); + ipv6_addr_be32_to_cpu(rule->tuples_mask.src_ip, + match.mask->src.s6_addr32); + ipv6_addr_be32_to_cpu(rule->tuples.dst_ip, + match.key->dst.s6_addr32); + ipv6_addr_be32_to_cpu(rule->tuples_mask.dst_ip, + match.mask->dst.s6_addr32); } else { rule->unused_tuple |= BIT(INNER_SRC_IP); rule->unused_tuple |= BIT(INNER_DST_IP); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index b5178b0f88b34..b9fc719880bb5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -8,7 +8,9 @@ #include #include #include + #include +#include #include "hclge_cmd.h" #include "hclge_ptp.h" @@ -718,15 +720,15 @@ struct hclge_fd_cfg { }; #define IPV4_INDEX 3 -#define IPV6_SIZE 4 + struct hclge_fd_rule_tuples { u8 src_mac[ETH_ALEN]; u8 dst_mac[ETH_ALEN]; /* Be compatible for ip address of both ipv4 and ipv6. * For ipv4 address, we store it in src/dst_ip[3]. */ - u32 src_ip[IPV6_SIZE]; - u32 dst_ip[IPV6_SIZE]; + u32 src_ip[IPV6_ADDR_WORDS]; + u32 dst_ip[IPV6_ADDR_WORDS]; u16 src_port; u16 dst_port; u16 vlan_tag1; From 30dcdd6a3a6caa27d75196bcc4f6ea9c7a51ad19 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 14 Aug 2024 14:10:01 +0300 Subject: [PATCH 179/385] selftests: fib_rule_tests: Remove unused functions The functions are unused since commit 816cda9ae531 ("selftests: net: fib_rule_tests: add support to select a test to run"). Remove them. Signed-off-by: Ido Schimmel Link: https://patch.msgid.link/20240814111005.955359-2-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/fib_rule_tests.sh | 16 ---------------- 1 file changed, 16 deletions(-) diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 7c01f58a20dea..c821d91b9ee83 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -56,14 +56,6 @@ log_test() fi } -log_section() -{ - echo - echo "######################################################################" - echo "TEST SECTION: $*" - echo "######################################################################" -} - check_nettest() { if which nettest > /dev/null 2>&1; then @@ -453,14 +445,6 @@ fib_rule4_connect_test() $IP -4 rule del dsfield 0x04 table $RTABLE_PEER cleanup_peer } - -run_fibrule_tests() -{ - log_section "IPv4 fib rule" - fib_rule4_test - log_section "IPv6 fib rule" - fib_rule6_test -} ################################################################################ # usage From b1487d6abeb5ccfc23f61d600ca63d2b09964f9a Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 14 Aug 2024 14:10:02 +0300 Subject: [PATCH 180/385] selftests: fib_rule_tests: Clarify test results Clarify the test results by grouping the output of test cases belonging to the same test under a common title. This is consistent with the output of fib_tests.sh. Before: # ./fib_rule_tests.sh TEST: rule6 check: oif redirect to table [ OK ] TEST: rule6 del by pref: oif redirect to table [ OK ] [...] TEST: rule4 check: oif redirect to table [ OK ] TEST: rule4 del by pref: oif redirect to table [ OK ] [...] Tests passed: 116 Tests failed: 0 After: # ./fib_rule_tests.sh IPv6 FIB rule tests TEST: rule6 check: oif redirect to table [ OK ] TEST: rule6 del by pref: oif redirect to table [ OK ] [...] IPv4 FIB rule tests TEST: rule4 check: oif redirect to table [ OK ] TEST: rule4 del by pref: oif redirect to table [ OK ] [...] Tests passed: 116 Tests failed: 0 Signed-off-by: Ido Schimmel Link: https://patch.msgid.link/20240814111005.955359-3-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/fib_rule_tests.sh | 27 ++++++++++++------- 1 file changed, 18 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index c821d91b9ee83..9100dd4d03822 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -35,18 +35,13 @@ log_test() local expected=$2 local msg="$3" - $IP rule show | grep -q l3mdev - if [ $? -eq 0 ]; then - msg="$msg (VRF)" - fi - if [ ${rc} -eq ${expected} ]; then nsuccess=$((nsuccess+1)) - printf "\n TEST: %-60s [ OK ]\n" "${msg}" + printf " TEST: %-60s [ OK ]\n" "${msg}" else ret=1 nfail=$((nfail+1)) - printf "\n TEST: %-60s [FAIL]\n" "${msg}" + printf " TEST: %-60s [FAIL]\n" "${msg}" if [ "${PAUSE_ON_FAIL}" = "yes" ]; then echo echo "hit enter to continue, 'q' to quit" @@ -205,10 +200,14 @@ fib_rule6_test_reject() fib_rule6_test() { + local ext_name=$1; shift local getmatch local match local cnt + echo + echo "IPv6 FIB rule tests $ext_name" + # setup the fib rule redirect route $IP -6 route add table $RTABLE default via $GW_IP6 dev $DEV onlink @@ -267,7 +266,7 @@ fib_rule6_test() fib_rule6_vrf_test() { setup_vrf - fib_rule6_test + fib_rule6_test "- with VRF" cleanup_vrf } @@ -277,6 +276,9 @@ fib_rule6_connect_test() { local dsfield + echo + echo "IPv6 FIB rule connect tests" + if ! check_nettest; then echo "SKIP: Could not run test without nettest tool" return @@ -344,10 +346,14 @@ fib_rule4_test_reject() fib_rule4_test() { + local ext_name=$1; shift local getmatch local match local cnt + echo + echo "IPv4 FIB rule tests $ext_name" + # setup the fib rule redirect route $IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink @@ -411,7 +417,7 @@ fib_rule4_test() fib_rule4_vrf_test() { setup_vrf - fib_rule4_test + fib_rule4_test "- with VRF" cleanup_vrf } @@ -421,6 +427,9 @@ fib_rule4_connect_test() { local dsfield + echo + echo "IPv4 FIB rule connect tests" + if ! check_nettest; then echo "SKIP: Could not run test without nettest tool" return From 9b6dcef32c2d8fe357592da5f6f52ef2edf1652d Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 14 Aug 2024 14:10:03 +0300 Subject: [PATCH 181/385] selftests: fib_rule_tests: Add negative match tests The fib_rule{4,6} tests verify the behavior of a given FIB rule selector (e.g., dport, sport) by redirecting to a routing table with a default route using a FIB rule with the given selector and checking that a route lookup using the selector matches this default route. Add negative tests to verify that a FIB rule is not hit when it should not. Signed-off-by: Ido Schimmel Link: https://patch.msgid.link/20240814111005.955359-4-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/fib_rule_tests.sh | 87 +++++++++++++++---- 1 file changed, 69 insertions(+), 18 deletions(-) diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 9100dd4d03822..085e21ed9fc30 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -174,12 +174,17 @@ fib_rule6_test_match_n_redirect() { local match="$1" local getmatch="$2" - local description="$3" + local getnomatch="$3" + local description="$4" + local nomatch_description="$5" $IP -6 rule add $match table $RTABLE $IP -6 route get $GW_IP6 $getmatch | grep -q "table $RTABLE" log_test $? 0 "rule6 check: $description" + $IP -6 route get $GW_IP6 $getnomatch 2>&1 | grep -q "table $RTABLE" + log_test $? 1 "rule6 check: $nomatch_description" + fib_rule6_del_by_pref "$match" log_test $? 0 "rule6 del by pref: $description" } @@ -201,6 +206,7 @@ fib_rule6_test_reject() fib_rule6_test() { local ext_name=$1; shift + local getnomatch local getmatch local match local cnt @@ -212,10 +218,14 @@ fib_rule6_test() $IP -6 route add table $RTABLE default via $GW_IP6 dev $DEV onlink match="oif $DEV" - fib_rule6_test_match_n_redirect "$match" "$match" "oif redirect to table" + getnomatch="oif lo" + fib_rule6_test_match_n_redirect "$match" "$match" "$getnomatch" \ + "oif redirect to table" "oif no redirect to table" match="from $SRC_IP6 iif $DEV" - fib_rule6_test_match_n_redirect "$match" "$match" "iif redirect to table" + getnomatch="from $SRC_IP6 iif lo" + fib_rule6_test_match_n_redirect "$match" "$match" "$getnomatch" \ + "iif redirect to table" "iif no redirect to table" # Reject dsfield (tos) options which have ECN bits set for cnt in $(seq 1 3); do @@ -229,37 +239,52 @@ fib_rule6_test() # Using option 'tos' instead of 'dsfield' as old iproute2 # versions don't support 'dsfield' in ip rule show. getmatch="tos $cnt" + getnomatch="tos 0x20" fib_rule6_test_match_n_redirect "$match" "$getmatch" \ - "$getmatch redirect to table" + "$getnomatch" "$getmatch redirect to table" \ + "$getnomatch no redirect to table" done match="fwmark 0x64" getmatch="mark 0x64" - fib_rule6_test_match_n_redirect "$match" "$getmatch" "fwmark redirect to table" + getnomatch="mark 0x63" + fib_rule6_test_match_n_redirect "$match" "$getmatch" "$getnomatch" \ + "fwmark redirect to table" "fwmark no redirect to table" fib_check_iproute_support "uidrange" "uid" if [ $? -eq 0 ]; then match="uidrange 100-100" getmatch="uid 100" - fib_rule6_test_match_n_redirect "$match" "$getmatch" "uid redirect to table" + getnomatch="uid 101" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "uid redirect to table" \ + "uid no redirect to table" fi fib_check_iproute_support "sport" "sport" if [ $? -eq 0 ]; then match="sport 666 dport 777" - fib_rule6_test_match_n_redirect "$match" "$match" "sport and dport redirect to table" + getnomatch="sport 667 dport 778" + fib_rule6_test_match_n_redirect "$match" "$match" \ + "$getnomatch" "sport and dport redirect to table" \ + "sport and dport no redirect to table" fi fib_check_iproute_support "ipproto" "ipproto" if [ $? -eq 0 ]; then match="ipproto tcp" - fib_rule6_test_match_n_redirect "$match" "$match" "ipproto match" + getnomatch="ipproto udp" + fib_rule6_test_match_n_redirect "$match" "$match" \ + "$getnomatch" "ipproto tcp match" "ipproto udp no match" fi fib_check_iproute_support "ipproto" "ipproto" if [ $? -eq 0 ]; then match="ipproto ipv6-icmp" - fib_rule6_test_match_n_redirect "$match" "$match" "ipproto ipv6-icmp match" + getnomatch="ipproto tcp" + fib_rule6_test_match_n_redirect "$match" "$match" \ + "$getnomatch" "ipproto ipv6-icmp match" \ + "ipproto ipv6-tcp no match" fi } @@ -320,12 +345,17 @@ fib_rule4_test_match_n_redirect() { local match="$1" local getmatch="$2" - local description="$3" + local getnomatch="$3" + local description="$4" + local nomatch_description="$5" $IP rule add $match table $RTABLE $IP route get $GW_IP4 $getmatch | grep -q "table $RTABLE" log_test $? 0 "rule4 check: $description" + $IP route get $GW_IP4 $getnomatch 2>&1 | grep -q "table $RTABLE" + log_test $? 1 "rule4 check: $nomatch_description" + fib_rule4_del_by_pref "$match" log_test $? 0 "rule4 del by pref: $description" } @@ -347,6 +377,7 @@ fib_rule4_test_reject() fib_rule4_test() { local ext_name=$1; shift + local getnomatch local getmatch local match local cnt @@ -358,14 +389,18 @@ fib_rule4_test() $IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink match="oif $DEV" - fib_rule4_test_match_n_redirect "$match" "$match" "oif redirect to table" + getnomatch="oif lo" + fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \ + "oif redirect to table" "oif no redirect to table" # need enable forwarding and disable rp_filter temporarily as all the # addresses are in the same subnet and egress device == ingress device. ip netns exec $testns sysctl -qw net.ipv4.ip_forward=1 ip netns exec $testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0 match="from $SRC_IP iif $DEV" - fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table" + getnomatch="from $SRC_IP iif lo" + fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \ + "iif redirect to table" "iif no redirect to table" ip netns exec $testns sysctl -qw net.ipv4.ip_forward=0 # Reject dsfield (tos) options which have ECN bits set @@ -380,37 +415,53 @@ fib_rule4_test() # Using option 'tos' instead of 'dsfield' as old iproute2 # versions don't support 'dsfield' in ip rule show. getmatch="tos $cnt" + getnomatch="tos 0x20" fib_rule4_test_match_n_redirect "$match" "$getmatch" \ - "$getmatch redirect to table" + "$getnomatch" "$getmatch redirect to table" \ + "$getnomatch no redirect to table" done match="fwmark 0x64" getmatch="mark 0x64" - fib_rule4_test_match_n_redirect "$match" "$getmatch" "fwmark redirect to table" + getnomatch="mark 0x63" + fib_rule4_test_match_n_redirect "$match" "$getmatch" "$getnomatch" \ + "fwmark redirect to table" "fwmark no redirect to table" fib_check_iproute_support "uidrange" "uid" if [ $? -eq 0 ]; then match="uidrange 100-100" getmatch="uid 100" - fib_rule4_test_match_n_redirect "$match" "$getmatch" "uid redirect to table" + getnomatch="uid 101" + fib_rule4_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "uid redirect to table" \ + "uid no redirect to table" fi fib_check_iproute_support "sport" "sport" if [ $? -eq 0 ]; then match="sport 666 dport 777" - fib_rule4_test_match_n_redirect "$match" "$match" "sport and dport redirect to table" + getnomatch="sport 667 dport 778" + fib_rule4_test_match_n_redirect "$match" "$match" \ + "$getnomatch" "sport and dport redirect to table" \ + "sport and dport no redirect to table" fi fib_check_iproute_support "ipproto" "ipproto" if [ $? -eq 0 ]; then match="ipproto tcp" - fib_rule4_test_match_n_redirect "$match" "$match" "ipproto tcp match" + getnomatch="ipproto udp" + fib_rule4_test_match_n_redirect "$match" "$match" \ + "$getnomatch" "ipproto tcp match" \ + "ipproto udp no match" fi fib_check_iproute_support "ipproto" "ipproto" if [ $? -eq 0 ]; then match="ipproto icmp" - fib_rule4_test_match_n_redirect "$match" "$match" "ipproto icmp match" + getnomatch="ipproto tcp" + fib_rule4_test_match_n_redirect "$match" "$match" \ + "$getnomatch" "ipproto icmp match" \ + "ipproto tcp no match" fi } From 53f88ed85bdd194b8a30605a264692b28a3ee665 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 14 Aug 2024 14:10:04 +0300 Subject: [PATCH 182/385] selftests: fib_rule_tests: Add negative connect tests The fib_rule{4,6}_connect tests verify that locally generated traffic from a socket that specifies a DS Field using the IP_TOS / IPV6_TCLASS socket options is correctly redirected using a FIB rule that matches on the given DS Field. Add negative tests to verify that the FIB rule is not hit when the socket specifies a DS Field that differs from the one used by the FIB rule. Signed-off-by: Ido Schimmel Link: https://patch.msgid.link/20240814111005.955359-5-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/fib_rule_tests.sh | 20 +++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 085e21ed9fc30..a3b2c833f050b 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -325,6 +325,16 @@ fib_rule6_connect_test() log_test $? 0 "rule6 dsfield tcp connect (dsfield ${dsfield})" done + # Check that UDP and TCP connections fail when using a DS Field that + # does not match the previously configured FIB rule. + nettest -q -6 -B -t 5 -N $testns -O $peerns -U -D \ + -Q 0x20 -l 2001:db8::1:11 -r 2001:db8::1:11 + log_test $? 1 "rule6 dsfield udp no connect (dsfield 0x20)" + + nettest -q -6 -B -t 5 -N $testns -O $peerns -Q 0x20 \ + -l 2001:db8::1:11 -r 2001:db8::1:11 + log_test $? 1 "rule6 dsfield tcp no connect (dsfield 0x20)" + $IP -6 rule del dsfield 0x04 table $RTABLE_PEER cleanup_peer } @@ -502,6 +512,16 @@ fib_rule4_connect_test() log_test $? 0 "rule4 dsfield tcp connect (dsfield ${dsfield})" done + # Check that UDP and TCP connections fail when using a DS Field that + # does not match the previously configured FIB rule. + nettest -q -B -t 5 -N $testns -O $peerns -D -U -Q 0x20 \ + -l 198.51.100.11 -r 198.51.100.11 + log_test $? 1 "rule4 dsfield udp no connect (dsfield 0x20)" + + nettest -q -B -t 5 -N $testns -O $peerns -Q 0x20 \ + -l 198.51.100.11 -r 198.51.100.11 + log_test $? 1 "rule4 dsfield tcp no connect (dsfield 0x20)" + $IP -4 rule del dsfield 0x04 table $RTABLE_PEER cleanup_peer } From 5f1b4f1be2d2b8d85dd07352b097cfc7064ad2e5 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 14 Aug 2024 14:10:05 +0300 Subject: [PATCH 183/385] selftests: fib_rule_tests: Test TOS matching with input routes The TOS value reaches the FIB rule core via different call paths when an input route is looked up compared to an output route. Re-test TOS matching with input routes to exercise these code paths. Pass the 'iif' and 'from' selectors separately from the 'get{,no}match' variables as otherwise the test name is too long to be printed without misalignments. Signed-off-by: Ido Schimmel Link: https://patch.msgid.link/20240814111005.955359-6-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/fib_rule_tests.sh | 31 +++++++++++++++++-- 1 file changed, 28 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index a3b2c833f050b..89034c5b69dc6 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -245,6 +245,19 @@ fib_rule6_test() "$getnomatch no redirect to table" done + # Re-test TOS matching, but with input routes since they are handled + # differently from output routes. + match="tos 0x10" + for cnt in "0x10" "0x11" "0x12" "0x13"; do + getmatch="tos $cnt" + getnomatch="tos 0x20" + fib_rule6_test_match_n_redirect "$match" \ + "from $SRC_IP6 iif $DEV $getmatch" \ + "from $SRC_IP6 iif $DEV $getnomatch" \ + "iif $getmatch redirect to table" \ + "iif $getnomatch no redirect to table" + done + match="fwmark 0x64" getmatch="mark 0x64" getnomatch="mark 0x63" @@ -403,15 +416,14 @@ fib_rule4_test() fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \ "oif redirect to table" "oif no redirect to table" - # need enable forwarding and disable rp_filter temporarily as all the - # addresses are in the same subnet and egress device == ingress device. + # Enable forwarding and disable rp_filter as all the addresses are in + # the same subnet and egress device == ingress device. ip netns exec $testns sysctl -qw net.ipv4.ip_forward=1 ip netns exec $testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0 match="from $SRC_IP iif $DEV" getnomatch="from $SRC_IP iif lo" fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \ "iif redirect to table" "iif no redirect to table" - ip netns exec $testns sysctl -qw net.ipv4.ip_forward=0 # Reject dsfield (tos) options which have ECN bits set for cnt in $(seq 1 3); do @@ -431,6 +443,19 @@ fib_rule4_test() "$getnomatch no redirect to table" done + # Re-test TOS matching, but with input routes since they are handled + # differently from output routes. + match="tos 0x10" + for cnt in "0x10" "0x11" "0x12" "0x13"; do + getmatch="tos $cnt" + getnomatch="tos 0x20" + fib_rule4_test_match_n_redirect "$match" \ + "from $SRC_IP iif $DEV $getmatch" \ + "from $SRC_IP iif $DEV $getnomatch" \ + "iif $getmatch redirect to table" \ + "iif $getnomatch no redirect to table" + done + match="fwmark 0x64" getmatch="mark 0x64" getnomatch="mark 0x63" From df37fcf58f2a02eb0d49d27020e3dbd6c1115288 Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Tue, 13 Aug 2024 10:04:57 -0700 Subject: [PATCH 184/385] net: ag71xx: devm_clk_get_enabled Allows removal of clk_prepare_enable to simplify the code slightly. Tested on a TP-LINK Archer C7v2. Signed-off-by: Rosen Penev Link: https://patch.msgid.link/20240813170516.7301-2-rosenp@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/atheros/ag71xx.c | 37 +++++---------------------- 1 file changed, 7 insertions(+), 30 deletions(-) diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 2916fdb1970be..9cd2b1168740e 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -699,29 +699,20 @@ static int ag71xx_mdio_probe(struct ag71xx *ag) np = dev->of_node; ag->mii_bus = NULL; - ag->clk_mdio = devm_clk_get(dev, "mdio"); + ag->clk_mdio = devm_clk_get_enabled(dev, "mdio"); if (IS_ERR(ag->clk_mdio)) { netif_err(ag, probe, ndev, "Failed to get mdio clk.\n"); return PTR_ERR(ag->clk_mdio); } - err = clk_prepare_enable(ag->clk_mdio); - if (err) { - netif_err(ag, probe, ndev, "Failed to enable mdio clk.\n"); - return err; - } - mii_bus = devm_mdiobus_alloc(dev); - if (!mii_bus) { - err = -ENOMEM; - goto mdio_err_put_clk; - } + if (!mii_bus) + return -ENOMEM; ag->mdio_reset = of_reset_control_get_exclusive(np, "mdio"); if (IS_ERR(ag->mdio_reset)) { netif_err(ag, probe, ndev, "Failed to get reset mdio.\n"); - err = PTR_ERR(ag->mdio_reset); - goto mdio_err_put_clk; + return PTR_ERR(ag->mdio_reset); } mii_bus->name = "ag71xx_mdio"; @@ -743,22 +734,17 @@ static int ag71xx_mdio_probe(struct ag71xx *ag) err = of_mdiobus_register(mii_bus, mnp); of_node_put(mnp); if (err) - goto mdio_err_put_clk; + return err; ag->mii_bus = mii_bus; return 0; - -mdio_err_put_clk: - clk_disable_unprepare(ag->clk_mdio); - return err; } static void ag71xx_mdio_remove(struct ag71xx *ag) { if (ag->mii_bus) mdiobus_unregister(ag->mii_bus); - clk_disable_unprepare(ag->clk_mdio); } static void ag71xx_hw_stop(struct ag71xx *ag) @@ -1853,7 +1839,7 @@ static int ag71xx_probe(struct platform_device *pdev) return -EINVAL; } - ag->clk_eth = devm_clk_get(&pdev->dev, "eth"); + ag->clk_eth = devm_clk_get_enabled(&pdev->dev, "eth"); if (IS_ERR(ag->clk_eth)) { netif_err(ag, probe, ndev, "Failed to get eth clk.\n"); return PTR_ERR(ag->clk_eth); @@ -1933,19 +1919,13 @@ static int ag71xx_probe(struct platform_device *pdev) netif_napi_add_weight(ndev, &ag->napi, ag71xx_poll, AG71XX_NAPI_WEIGHT); - err = clk_prepare_enable(ag->clk_eth); - if (err) { - netif_err(ag, probe, ndev, "Failed to enable eth clk.\n"); - return err; - } - ag71xx_wr(ag, AG71XX_REG_MAC_CFG1, 0); ag71xx_hw_init(ag); err = ag71xx_mdio_probe(ag); if (err) - goto err_put_clk; + return err; platform_set_drvdata(pdev, ndev); @@ -1970,8 +1950,6 @@ static int ag71xx_probe(struct platform_device *pdev) err_mdio_remove: ag71xx_mdio_remove(ag); -err_put_clk: - clk_disable_unprepare(ag->clk_eth); return err; } @@ -1986,7 +1964,6 @@ static void ag71xx_remove(struct platform_device *pdev) ag = netdev_priv(ndev); unregister_netdev(ndev); ag71xx_mdio_remove(ag); - clk_disable_unprepare(ag->clk_eth); platform_set_drvdata(pdev, NULL); } From 8ef34bea8cad381e0b5c90f9e4e539f48e8c2d7f Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Tue, 13 Aug 2024 10:04:58 -0700 Subject: [PATCH 185/385] net: ag71xx: use devm for of_mdiobus_register Allows removing ag71xx_mdio_remove. Removed ag.mii_bus variable. Local one can be used with devm. Easier to reason about as mii_bus is only used here now. Also shrinks the struct slightly. Signed-off-by: Rosen Penev Link: https://patch.msgid.link/20240813170516.7301-3-rosenp@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/atheros/ag71xx.c | 23 +++-------------------- 1 file changed, 3 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 9cd2b1168740e..7bc0fb33e582f 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -380,7 +380,6 @@ struct ag71xx { int mac_idx; struct reset_control *mdio_reset; - struct mii_bus *mii_bus; struct clk *clk_mdio; struct clk *clk_eth; }; @@ -697,7 +696,6 @@ static int ag71xx_mdio_probe(struct ag71xx *ag) int err; np = dev->of_node; - ag->mii_bus = NULL; ag->clk_mdio = devm_clk_get_enabled(dev, "mdio"); if (IS_ERR(ag->clk_mdio)) { @@ -731,22 +729,14 @@ static int ag71xx_mdio_probe(struct ag71xx *ag) } mnp = of_get_child_by_name(np, "mdio"); - err = of_mdiobus_register(mii_bus, mnp); + err = devm_of_mdiobus_register(dev, mii_bus, mnp); of_node_put(mnp); if (err) return err; - ag->mii_bus = mii_bus; - return 0; } -static void ag71xx_mdio_remove(struct ag71xx *ag) -{ - if (ag->mii_bus) - mdiobus_unregister(ag->mii_bus); -} - static void ag71xx_hw_stop(struct ag71xx *ag) { /* disable all interrupts and stop the rx/tx engine */ @@ -1932,14 +1922,14 @@ static int ag71xx_probe(struct platform_device *pdev) err = ag71xx_phylink_setup(ag); if (err) { netif_err(ag, probe, ndev, "failed to setup phylink (%d)\n", err); - goto err_mdio_remove; + return err; } err = register_netdev(ndev); if (err) { netif_err(ag, probe, ndev, "unable to register net device\n"); platform_set_drvdata(pdev, NULL); - goto err_mdio_remove; + return err; } netif_info(ag, probe, ndev, "Atheros AG71xx at 0x%08lx, irq %d, mode:%s\n", @@ -1947,23 +1937,16 @@ static int ag71xx_probe(struct platform_device *pdev) phy_modes(ag->phy_if_mode)); return 0; - -err_mdio_remove: - ag71xx_mdio_remove(ag); - return err; } static void ag71xx_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); - struct ag71xx *ag; if (!ndev) return; - ag = netdev_priv(ndev); unregister_netdev(ndev); - ag71xx_mdio_remove(ag); platform_set_drvdata(pdev, NULL); } From cc20a4791641a1cbd1525695fac0d4725dd72509 Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Tue, 13 Aug 2024 10:04:59 -0700 Subject: [PATCH 186/385] net: ag71xx: use devm for register_netdev Allows completely removing the remove function. Nothing is being done manually now. Tested on TP-LINK Archer C7v2. Signed-off-by: Rosen Penev Link: https://patch.msgid.link/20240813170516.7301-4-rosenp@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/atheros/ag71xx.c | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 7bc0fb33e582f..ee5d429abdaa6 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1925,7 +1925,7 @@ static int ag71xx_probe(struct platform_device *pdev) return err; } - err = register_netdev(ndev); + err = devm_register_netdev(&pdev->dev, ndev); if (err) { netif_err(ag, probe, ndev, "unable to register net device\n"); platform_set_drvdata(pdev, NULL); @@ -1939,17 +1939,6 @@ static int ag71xx_probe(struct platform_device *pdev) return 0; } -static void ag71xx_remove(struct platform_device *pdev) -{ - struct net_device *ndev = platform_get_drvdata(pdev); - - if (!ndev) - return; - - unregister_netdev(ndev); - platform_set_drvdata(pdev, NULL); -} - static const u32 ar71xx_fifo_ar7100[] = { 0x0fff0000, 0x00001fff, 0x00780fff, }; @@ -2034,7 +2023,6 @@ static const struct of_device_id ag71xx_match[] = { static struct platform_driver ag71xx_driver = { .probe = ag71xx_probe, - .remove_new = ag71xx_remove, .driver = { .name = "ag71xx", .of_match_table = ag71xx_match, From 795b1aa8f37e38cf1a6202d274960bdd9c2ac44a Mon Sep 17 00:00:00 2001 From: Pavan Kumar Linga Date: Wed, 14 Aug 2024 10:59:02 -0700 Subject: [PATCH 187/385] idpf: remove redundant 'req_vec_chunks' NULL check 'req_vec_chunks' is used to store the vector info received from the device control plane. The memory for it is allocated in idpf_send_alloc_vectors_msg and returns an error if the memory allocation fails. 'req_vec_chunks' cannot be NULL in the later code flow. So remove the conditional check to extract the vector ids received from the device control plane. Smatch static checker warning: drivers/net/ethernet/intel/idpf/idpf_lib.c:417 idpf_intr_req() error: we previously assumed 'adapter->req_vec_chunks' could be null (see line 360) Reported-by: Dan Carpenter Closes: https://lore.kernel.org/intel-wired-lan/a355ae8a-9011-4a85-a4d1-5b2793bb5f7b@stanley.mountain/ Reviewed-by: Dan Carpenter Signed-off-by: Pavan Kumar Linga Tested-by: Krishneil Singh Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20240814175903.4166390-1-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/idpf/idpf_lib.c | 23 +++++----------------- 1 file changed, 5 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 0b6c8fd5bc90f..4f20343e49a98 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -357,24 +357,11 @@ int idpf_intr_req(struct idpf_adapter *adapter) goto free_msix; } - if (adapter->req_vec_chunks) { - struct virtchnl2_vector_chunks *vchunks; - struct virtchnl2_alloc_vectors *ac; - - ac = adapter->req_vec_chunks; - vchunks = &ac->vchunks; - - num_vec_ids = idpf_get_vec_ids(adapter, vecids, total_vecs, - vchunks); - if (num_vec_ids < v_actual) { - err = -EINVAL; - goto free_vecids; - } - } else { - int i; - - for (i = 0; i < v_actual; i++) - vecids[i] = i; + num_vec_ids = idpf_get_vec_ids(adapter, vecids, total_vecs, + &adapter->req_vec_chunks->vchunks); + if (num_vec_ids < v_actual) { + err = -EINVAL; + goto free_vecids; } for (vector = 0; vector < v_actual; vector++) { From 02404bdb811dbea6ab523675ec98d9f815cfb3b2 Mon Sep 17 00:00:00 2001 From: Frank Li Date: Thu, 15 Aug 2024 12:34:07 -0400 Subject: [PATCH 188/385] dt-bindings: net: mdio: change nodename match pattern Change mdio.yaml nodename match pattern to '^mdio(-(bus|external))?(@.+|-([0-9]+))$' Fix mdio.yaml wrong parser mdio controller's address instead phy's address when mdio-mux exista. For example: mdio-mux-emi1@54 { compatible = "mdio-mux-mmioreg", "mdio-mux"; mdio@20 { reg = <0x20>; ^^^ This is mdio controller register ethernet-phy@2 { reg = <0x2>; ^^^ This phy's address }; }; }; Only phy's address is limited to 31 because MDIO bus definition. But CHECK_DTBS report below warning: arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dtb: mdio-mux-emi1@54: mdio@20:reg:0:0: 32 is greater than the maximum of 31 The reason is that "mdio-mux-emi1@54" match "nodename: '^mdio(@.*)?'" in mdio.yaml. Change to '^mdio(-(bus|external))?(@.+|-([0-9]+))?$' to avoid wrong match mdio mux controller's node. Signed-off-by: Frank Li Reviewed-by: Rob Herring (Arm) Link: https://patch.msgid.link/20240815163408.4184705-1-Frank.Li@nxp.com Signed-off-by: Jakub Kicinski --- Documentation/devicetree/bindings/net/mdio.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/net/mdio.yaml b/Documentation/devicetree/bindings/net/mdio.yaml index a266ade918ca7..bed3987a8fbf6 100644 --- a/Documentation/devicetree/bindings/net/mdio.yaml +++ b/Documentation/devicetree/bindings/net/mdio.yaml @@ -19,7 +19,7 @@ description: properties: $nodename: - pattern: "^mdio(@.*)?" + pattern: '^mdio(-(bus|external))?(@.+|-([0-9]+))?$' "#address-cells": const: 1 From 9480fd0cd8a4621d42a88d43b0e7864048a6b09e Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Thu, 15 Aug 2024 17:23:43 +0300 Subject: [PATCH 189/385] docs: networking: Align documentation with behavior change Following commit 9f7e8fbb91f8 ("net/mlx5: offset comp irq index in name by one"), which fixed the index in IRQ name to start once again from 0, we change the documentation accordingly. Signed-off-by: Tariq Toukan Reviewed-by: Dragos Tatulea Link: https://patch.msgid.link/20240815142343.2254247-1-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- Documentation/networking/multi-pf-netdev.rst | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/Documentation/networking/multi-pf-netdev.rst b/Documentation/networking/multi-pf-netdev.rst index 268819225866c..2cd25d81aaa7a 100644 --- a/Documentation/networking/multi-pf-netdev.rst +++ b/Documentation/networking/multi-pf-netdev.rst @@ -111,11 +111,11 @@ The relation between PF, irq, napi, and queue can be observed via netlink spec:: Here you can clearly observe our channels distribution policy:: $ ls /proc/irq/{36,39,40,41,42}/mlx5* -d -1 - /proc/irq/36/mlx5_comp1@pci:0000:08:00.0 - /proc/irq/39/mlx5_comp1@pci:0000:09:00.0 - /proc/irq/40/mlx5_comp2@pci:0000:08:00.0 - /proc/irq/41/mlx5_comp2@pci:0000:09:00.0 - /proc/irq/42/mlx5_comp3@pci:0000:08:00.0 + /proc/irq/36/mlx5_comp0@pci:0000:08:00.0 + /proc/irq/39/mlx5_comp0@pci:0000:09:00.0 + /proc/irq/40/mlx5_comp1@pci:0000:08:00.0 + /proc/irq/41/mlx5_comp1@pci:0000:09:00.0 + /proc/irq/42/mlx5_comp2@pci:0000:08:00.0 Steering ======== From f232de7cdb4b99adb2c7f2bc5e0b7e4e1292873b Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Thu, 15 Aug 2024 10:16:08 +0300 Subject: [PATCH 190/385] net/mlx5e: SHAMPO, Fix page leak When SHAMPO is used, a receive queue currently almost always leaks one page on shutdown. A page has MLX5E_SHAMPO_WQ_HEADER_PER_PAGE (8) headers. These headers are tracked in the SHAMPO bitmap. Each page is released when the last header index in the group is processed. During header allocation, there can be leftovers from a page that will be used in a subsequent allocation. This is normally fine, except for the following scenario (simplified a bit): 1) Allocate N new page fragments, showing only the relevant last 4 fragments: 0: new page 1: new page 2: new page 3: new page 4: page from previous allocation 5: page from previous allocation 6: page from previous allocation 7: page from previous allocation 2) NAPI processes header indices 4-7 because they are the oldest allocated. Bit 7 will be set to 0. 3) Receive queue shutdown occurs. All the remaining bits are being iterated on to release the pages. But the page assigned to header indices 0-3 will not be freed due to what happened in step 2. This patch fixes the issue by making sure that on allocation, header fragments are always allocated in groups of MLX5E_SHAMPO_WQ_HEADER_PER_PAGE so that there is never a partial page left over between allocations. A more appropriate fix would be a refactoring of mlx5e_alloc_rx_hd_mpwqe() and mlx5e_build_shampo_hd_umr(). But this refactoring is too big for net. It will be targeted for net-next. Fixes: e839ac9a89cb ("net/mlx5e: SHAMPO, Simplify header page release in teardown") Signed-off-by: Dragos Tatulea Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240815071611.2211873-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 225da8d691fcf..23aa555ca0ae8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -735,6 +735,7 @@ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq) ksm_entries = bitmap_find_window(shampo->bitmap, shampo->hd_per_wqe, shampo->hd_per_wq, shampo->pi); + ksm_entries = ALIGN_DOWN(ksm_entries, MLX5E_SHAMPO_WQ_HEADER_PER_PAGE); if (!ksm_entries) return 0; From 94e521937839475b83bac46e4d3ccba332e12064 Mon Sep 17 00:00:00 2001 From: Dragos Tatulea Date: Thu, 15 Aug 2024 10:16:09 +0300 Subject: [PATCH 191/385] net/mlx5e: SHAMPO, Release in progress headers The change in the fixes tag cleaned up too much: it removed the part that was releasing header pages that were posted via UMR but haven't been acknowledged yet on the ICOSQ. This patch corrects this omission by setting the bits between pi and ci to on when shutting down a queue with SHAMPO. To be consistent with the Striding RQ code, this action is done in mlx5e_free_rx_missing_descs(). Fixes: e839ac9a89cb ("net/mlx5e: SHAMPO, Simplify header page release in teardown") Signed-off-by: Dragos Tatulea Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240815071611.2211873-3-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 + .../net/ethernet/mellanox/mlx5/core/en_main.c | 8 ++++++ .../net/ethernet/mellanox/mlx5/core/en_rx.c | 25 +++++++++++-------- 3 files changed, 24 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index bb5da42edc23a..d9e241423bc56 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -998,6 +998,7 @@ void mlx5e_build_ptys2ethtool_map(void); bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_shift, enum mlx5e_mpwrq_umr_mode umr_mode); +void mlx5e_shampo_fill_umr(struct mlx5e_rq *rq, int len); void mlx5e_shampo_dealloc_hd(struct mlx5e_rq *rq); void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats); void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5df904639b0ce..583fa24a7ae98 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1236,6 +1236,14 @@ void mlx5e_free_rx_missing_descs(struct mlx5e_rq *rq) rq->mpwqe.actual_wq_head = wq->head; rq->mpwqe.umr_in_progress = 0; rq->mpwqe.umr_completed = 0; + + if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) { + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; + u16 len; + + len = (shampo->pi - shampo->ci) & shampo->hd_per_wq; + mlx5e_shampo_fill_umr(rq, len); + } } void mlx5e_free_rx_descs(struct mlx5e_rq *rq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 23aa555ca0ae8..de9d01036c280 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -963,26 +963,31 @@ void mlx5e_free_icosq_descs(struct mlx5e_icosq *sq) sq->cc = sqcc; } -static void mlx5e_handle_shampo_hd_umr(struct mlx5e_shampo_umr umr, - struct mlx5e_icosq *sq) +void mlx5e_shampo_fill_umr(struct mlx5e_rq *rq, int len) { - struct mlx5e_channel *c = container_of(sq, struct mlx5e_channel, icosq); - struct mlx5e_shampo_hd *shampo; - /* assume 1:1 relationship between RQ and icosq */ - struct mlx5e_rq *rq = &c->rq; - int end, from, len = umr.len; + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; + int end, from, full_len = len; - shampo = rq->mpwqe.shampo; end = shampo->hd_per_wq; from = shampo->ci; - if (from + len > shampo->hd_per_wq) { + if (from + len > end) { len -= end - from; bitmap_set(shampo->bitmap, from, end - from); from = 0; } bitmap_set(shampo->bitmap, from, len); - shampo->ci = (shampo->ci + umr.len) & (shampo->hd_per_wq - 1); + shampo->ci = (shampo->ci + full_len) & (shampo->hd_per_wq - 1); +} + +static void mlx5e_handle_shampo_hd_umr(struct mlx5e_shampo_umr umr, + struct mlx5e_icosq *sq) +{ + struct mlx5e_channel *c = container_of(sq, struct mlx5e_channel, icosq); + /* assume 1:1 relationship between RQ and icosq */ + struct mlx5e_rq *rq = &c->rq; + + mlx5e_shampo_fill_umr(rq, umr.len); } int mlx5e_poll_ico_cq(struct mlx5e_cq *cq) From a07e953dafe5ebd88942dc861dfb06eaf055fb07 Mon Sep 17 00:00:00 2001 From: Carolina Jubran Date: Thu, 15 Aug 2024 10:16:10 +0300 Subject: [PATCH 192/385] net/mlx5e: XPS, Fix oversight of Multi-PF Netdev changes The offending commit overlooked the Multi-PF Netdev changes. Revert mlx5e_set_default_xps_cpumasks to incorporate Multi-PF Netdev changes. Fixes: bcee093751f8 ("net/mlx5e: Modifying channels number and updating TX queues") Signed-off-by: Carolina Jubran Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240815071611.2211873-4-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 583fa24a7ae98..16b67c457b605 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3028,15 +3028,18 @@ int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv) static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv, struct mlx5e_params *params) { - struct mlx5_core_dev *mdev = priv->mdev; - int num_comp_vectors, ix, irq; - - num_comp_vectors = mlx5_comp_vectors_max(mdev); + int ix; for (ix = 0; ix < params->num_channels; ix++) { + int num_comp_vectors, irq, vec_ix; + struct mlx5_core_dev *mdev; + + mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix); + num_comp_vectors = mlx5_comp_vectors_max(mdev); cpumask_clear(priv->scratchpad.cpumask); + vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix); - for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) { + for (irq = vec_ix; irq < num_comp_vectors; irq += params->num_channels) { int cpu = mlx5_comp_vector_get_cpu(mdev, irq); cpumask_set_cpu(cpu, priv->scratchpad.cpumask); From 607e1df7bd47fe91cab85a97f57870a26d066137 Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 15 Aug 2024 10:16:11 +0300 Subject: [PATCH 193/385] net/mlx5: Fix IPsec RoCE MPV trace call Prevent the call trace below from happening, by not allowing IPsec creation over a slave, if master device doesn't support IPsec. WARNING: CPU: 44 PID: 16136 at kernel/locking/rwsem.c:240 down_read+0x75/0x94 Modules linked in: esp4_offload esp4 act_mirred act_vlan cls_flower sch_ingress mlx5_vdpa vringh vhost_iotlb vdpa mst_pciconf(OE) nfsv3 nfs_acl nfs lockd grace fscache netfs xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4 nft_compat nft_counter nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 rfkill cuse fuse rpcrdma sunrpc rdma_ucm ib_srpt ib_isert iscsi_target_mod target_core_mod ib_umad ib_iser libiscsi scsi_transport_iscsi rdma_cm ib_ipoib iw_cm ib_cm ipmi_ssif intel_rapl_msr intel_rapl_common amd64_edac edac_mce_amd kvm_amd kvm irqbypass crct10dif_pclmul crc32_pclmul mlx5_ib ghash_clmulni_intel sha1_ssse3 dell_smbios ib_uverbs aesni_intel crypto_simd dcdbas wmi_bmof dell_wmi_descriptor cryptd pcspkr ib_core acpi_ipmi sp5100_tco ccp i2c_piix4 ipmi_si ptdma k10temp ipmi_devintf ipmi_msghandler acpi_power_meter acpi_cpufreq ext4 mbcache jbd2 sd_mod t10_pi sg mgag200 drm_kms_helper syscopyarea sysfillrect mlx5_core sysimgblt fb_sys_fops cec ahci libahci mlxfw drm pci_hyperv_intf libata tg3 sha256_ssse3 tls megaraid_sas i2c_algo_bit psample wmi dm_mirror dm_region_hash dm_log dm_mod [last unloaded: mst_pci] CPU: 44 PID: 16136 Comm: kworker/44:3 Kdump: loaded Tainted: GOE 5.15.0-20240509.el8uek.uek7_u3_update_v6.6_ipsec_bf.x86_64 #2 Hardware name: Dell Inc. PowerEdge R7525/074H08, BIOS 2.0.3 01/15/2021 Workqueue: events xfrm_state_gc_task RIP: 0010:down_read+0x75/0x94 Code: 00 48 8b 45 08 65 48 8b 14 25 80 fc 01 00 83 e0 02 48 09 d0 48 83 c8 01 48 89 45 08 5d 31 c0 89 c2 89 c6 89 c7 e9 cb 88 3b 00 <0f> 0b 48 8b 45 08 a8 01 74 b2 a8 02 75 ae 48 89 c2 48 83 ca 02 f0 RSP: 0018:ffffb26387773da8 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffffa08b658af900 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ff886bc5e1366f2f RDI: 0000000000000000 RBP: ffffa08b658af940 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffa0a9bfb31540 R13: ffffa0a9bfb37900 R14: 0000000000000000 R15: ffffa0a9bfb37905 FS: 0000000000000000(0000) GS:ffffa0a9bfb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055a45ed814e8 CR3: 000000109038a000 CR4: 0000000000350ee0 Call Trace: ? show_trace_log_lvl+0x1d6/0x2f9 ? show_trace_log_lvl+0x1d6/0x2f9 ? mlx5_devcom_for_each_peer_begin+0x29/0x60 [mlx5_core] ? down_read+0x75/0x94 ? __warn+0x80/0x113 ? down_read+0x75/0x94 ? report_bug+0xa4/0x11d ? handle_bug+0x35/0x8b ? exc_invalid_op+0x14/0x75 ? asm_exc_invalid_op+0x16/0x1b ? down_read+0x75/0x94 ? down_read+0xe/0x94 mlx5_devcom_for_each_peer_begin+0x29/0x60 [mlx5_core] mlx5_ipsec_fs_roce_tx_destroy+0xb1/0x130 [mlx5_core] tx_destroy+0x1b/0xc0 [mlx5_core] tx_ft_put+0x53/0xc0 [mlx5_core] mlx5e_xfrm_free_state+0x45/0x90 [mlx5_core] ___xfrm_state_destroy+0x10f/0x1a2 xfrm_state_gc_task+0x81/0xa9 process_one_work+0x1f1/0x3c6 worker_thread+0x53/0x3e4 ? process_one_work.cold+0x46/0x3c kthread+0x127/0x144 ? set_kthread_struct+0x60/0x52 ret_from_fork+0x22/0x2d ---[ end trace 5ef7896144d398e1 ]--- Fixes: dfbd229abeee ("net/mlx5: Configure IPsec steering for egress RoCEv2 MPV traffic") Reviewed-by: Leon Romanovsky Signed-off-by: Patrisious Haddad Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/20240815071611.2211873-5-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c index 234cd00f71a1c..b7d4b1a2baf2e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c @@ -386,7 +386,8 @@ static int ipsec_fs_roce_tx_mpv_create(struct mlx5_core_dev *mdev, return -EOPNOTSUPP; peer_priv = mlx5_devcom_get_next_peer_data(*ipsec_roce->devcom, &tmp); - if (!peer_priv) { + if (!peer_priv || !peer_priv->ipsec) { + mlx5_core_err(mdev, "IPsec not supported on master device\n"); err = -EOPNOTSUPP; goto release_peer; } @@ -455,7 +456,8 @@ static int ipsec_fs_roce_rx_mpv_create(struct mlx5_core_dev *mdev, return -EOPNOTSUPP; peer_priv = mlx5_devcom_get_next_peer_data(*ipsec_roce->devcom, &tmp); - if (!peer_priv) { + if (!peer_priv || !peer_priv->ipsec) { + mlx5_core_err(mdev, "IPsec not supported on master device\n"); err = -EOPNOTSUPP; goto release_peer; } From 1f803c95693f140bed46cd5581b97592e20b723e Mon Sep 17 00:00:00 2001 From: Aleksander Jan Bajkowski Date: Thu, 15 Aug 2024 09:49:56 +0200 Subject: [PATCH 194/385] net: ethernet: lantiq_etop: remove unused variable Remove a variable that has never been used. Signed-off-by: Aleksander Jan Bajkowski Link: https://patch.msgid.link/20240815074956.155224-1-olek2@wp.pl Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/lantiq_etop.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 9e69848153864..3c289bfe0a092 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -95,7 +95,6 @@ struct ltq_etop_priv { struct mii_bus *mii_bus; struct ltq_etop_chan ch[MAX_DMA_CHAN]; - int tx_free[MAX_DMA_CHAN >> 1]; int tx_burst_len; int rx_burst_len; From 1c66df862561a11a8ea9b4c97ecfe91983c3bda7 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 15 Aug 2024 16:19:25 +0100 Subject: [PATCH 195/385] net: txgbe: Remove unnecessary NULL check before free Remove unnecessary NULL check before freeing using kvfree(). This function will ignore a NULL argument. Flagged by Coccinelle: .../txgbe_hw.c:187:2-8: WARNING: NULL check before some freeing functions is not needed. No functional change intended. Compile tested only. Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240815-txgbe-kvfree-v1-1-5ecf8656f555@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c index d6b2b3c781b6f..cd1372da92a94 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c @@ -103,8 +103,7 @@ static int txgbe_calc_eeprom_checksum(struct wx *wx, u16 *checksum) if (i != wx->eeprom.sw_region_offset + TXGBE_EEPROM_CHECKSUM) *checksum += local_buffer[i]; - if (eeprom_ptrs) - kvfree(eeprom_ptrs); + kvfree(eeprom_ptrs); *checksum = TXGBE_EEPROM_SUM - *checksum; From f4ae8420f6ebdabf97e0c4f5f99412768687985f Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Thu, 15 Aug 2024 09:12:01 -0700 Subject: [PATCH 196/385] mpls: Reduce skb re-allocations due to skb_cow() mpls_xmit() needs to prepend the MPLS-labels to the packet. That implies one needs to make sure there is enough space for it in the headers. Calling skb_cow() implies however that one wants to change even the playload part of the packet (which is not true for MPLS). Thus, call skb_cow_head() instead, which is what other tunnelling protocols do. Running a server with this comm it entirely removed the calls to pskb_expand_head() from the callstack in mpls_xmit() thus having significant CPU-reduction, especially at peak times. Cc: Roopa Prabhu Reported-by: Craig Taylor Signed-off-by: Christoph Paasch Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240815161201.22021-1-cpaasch@apple.com Signed-off-by: Jakub Kicinski --- net/mpls/mpls_iptunnel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 4385fd3b13be3..6e73da94af7fb 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -106,7 +106,7 @@ static int mpls_xmit(struct sk_buff *skb) hh_len = 0; /* Ensure there is enough space for the headers in the skb */ - if (skb_cow(skb, hh_len + new_header_size)) + if (skb_cow_head(skb, hh_len + new_header_size)) goto drop; skb_set_inner_protocol(skb, skb->protocol); From a99ef548bba01435f19137cf1670861be1c1ee4b Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 15 Aug 2024 16:27:46 +0100 Subject: [PATCH 197/385] bnx2x: Set ivi->vlan field as an integer In bnx2x_get_vf_config(): * The vlan field of ivi is a 32-bit integer, it is used to store a vlan ID. * The vlan field of bulletin is a 16-bit integer, it is also used to store a vlan ID. In the current code, ivi->vlan is set using memset. But in the case of setting it to the value of bulletin->vlan, this involves reading 32 bits from a 16bit source. This is likely safe, as the following 6 bytes are padding in the same structure, but none the less, it seems undesirable. However, it is entirely unclear to me how this scheme works on big-endian systems. Resolve this by simply assigning integer values to ivi->vlan. Flagged by W=1 builds. f.e. gcc-14 reports: In function 'fortify_memcpy_chk', inlined from 'bnx2x_get_vf_config' at .../bnx2x_sriov.c:2655:4: .../fortify-string.h:580:25: warning: call to '__read_overflow2_field' declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 580 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Compile tested only. Signed-off-by: Simon Horman Reviewed-by: Brett Creeley Link: https://patch.msgid.link/20240815-bnx2x-int-vlan-v1-1-5940b76e37ad@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 77d4cb4ad7823..12198fc3ab22b 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -2652,10 +2652,10 @@ int bnx2x_get_vf_config(struct net_device *dev, int vfidx, /* vlan */ if (bulletin->valid_bitmap & (1 << VLAN_VALID)) /* vlan configured by ndo so its in bulletin board */ - memcpy(&ivi->vlan, &bulletin->vlan, VLAN_HLEN); + ivi->vlan = bulletin->vlan; else /* function has not been loaded yet. Show vlans as 0s */ - memset(&ivi->vlan, 0, VLAN_HLEN); + ivi->vlan = 0; mutex_unlock(&bp->vfdb->bulletin_mutex); } From a0c9fe5eecc97680323ee83780ea3eaf440ba1b7 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 15 Aug 2024 16:37:13 +0100 Subject: [PATCH 198/385] tc-testing: don't access non-existent variable on exception Since commit 255c1c7279ab ("tc-testing: Allow test cases to be skipped") the variable test_ordinal doesn't exist in call_pre_case(). So it should not be accessed when an exception occurs. This resolves the following splat: ... During handling of the above exception, another exception occurred: Traceback (most recent call last): File ".../tdc.py", line 1028, in main() File ".../tdc.py", line 1022, in main set_operation_mode(pm, parser, args, remaining) File ".../tdc.py", line 966, in set_operation_mode catresults = test_runner_serial(pm, args, alltests) File ".../tdc.py", line 642, in test_runner_serial (index, tsr) = test_runner(pm, args, alltests) File ".../tdc.py", line 536, in test_runner res = run_one_test(pm, args, index, tidx) File ".../tdc.py", line 419, in run_one_test pm.call_pre_case(tidx) File ".../tdc.py", line 146, in call_pre_case print('test_ordinal is {}'.format(test_ordinal)) NameError: name 'test_ordinal' is not defined Fixes: 255c1c7279ab ("tc-testing: Allow test cases to be skipped") Signed-off-by: Simon Horman Acked-by: Jamal Hadi Salim Link: https://patch.msgid.link/20240815-tdc-test-ordinal-v1-1-0255c122a427@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/tc-testing/tdc.py | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index ee349187636fc..4f255cec0c22e 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -143,7 +143,6 @@ def call_pre_case(self, caseinfo, *, test_skip=False): except Exception as ee: print('exception {} in call to pre_case for {} plugin'. format(ee, pgn_inst.__class__)) - print('test_ordinal is {}'.format(test_ordinal)) print('testid is {}'.format(caseinfo['id'])) raise From 1bf8e07c382bd4f04ede81ecc05267a8ffd60999 Mon Sep 17 00:00:00 2001 From: Frank Li Date: Wed, 14 Aug 2024 16:46:18 -0400 Subject: [PATCH 199/385] dt-binding: ptp: fsl,ptp: add pci1957,ee02 compatible string for fsl,enetc-ptp fsl,enetc-ptp is embedded pcie device. Add compatible string pci1957,ee02. Fix warning: arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-kbox-a-230-ls.dtb: ethernet@0,4: compatible:0: 'pci1957,ee02' is not one of ['fsl,etsec-ptp', 'fsl,fman-ptp-timer', 'fsl,dpaa2-ptp', 'fsl,enetc-ptp'] Signed-off-by: Frank Li Acked-by: Rob Herring (Arm) Signed-off-by: David S. Miller --- .../devicetree/bindings/ptp/fsl,ptp.yaml | 22 ++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml b/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml index 3bb8615e3e919..42ca895f3c4eb 100644 --- a/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml +++ b/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml @@ -11,11 +11,14 @@ maintainers: properties: compatible: - enum: - - fsl,etsec-ptp - - fsl,fman-ptp-timer - - fsl,dpaa2-ptp - - fsl,enetc-ptp + oneOf: + - enum: + - fsl,etsec-ptp + - fsl,fman-ptp-timer + - fsl,dpaa2-ptp + - items: + - const: pci1957,ee02 + - const: fsl,enetc-ptp reg: maxItems: 1 @@ -123,6 +126,15 @@ required: - compatible - reg +allOf: + - if: + properties: + compatible: + contains: + const: fsl,enetc-ptp + then: + $ref: /schemas/pci/pci-device.yaml + additionalProperties: false examples: From 7167395a4be7930ecac6a33b4e54d7e3dd9ee209 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Thu, 15 Aug 2024 15:59:50 +0800 Subject: [PATCH 200/385] selftests: udpgro: report error when receive failed Currently, we only check the latest senders's exit code. If the receiver report failed, it is not recoreded. Fix it by checking the exit code of all the involved processes. Before: bad GRO lookup ok multiple GRO socks ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520 ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520 failed $ echo $? 0 After: bad GRO lookup ok multiple GRO socks ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520 ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520 failed $ echo $? 1 Fixes: 3327a9c46352 ("selftests: add functionals test for UDP GRO") Suggested-by: Paolo Abeni Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- tools/testing/selftests/net/udpgro.sh | 44 ++++++++++++++++----------- 1 file changed, 27 insertions(+), 17 deletions(-) diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index 11a1ebda564fd..4659cf01e4384 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -46,17 +46,19 @@ run_one() { local -r all="$@" local -r tx_args=${all%rx*} local -r rx_args=${all#*rx} + local ret=0 cfg_veth - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} && \ - echo "ok" || \ - echo "failed" & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} & + local PID1=$! wait_local_port_listen ${PEER_NS} 8000 udp ./udpgso_bench_tx ${tx_args} - ret=$? - wait $(jobs -p) + check_err $? + wait ${PID1} + check_err $? + [ "$ret" -eq 0 ] && echo "ok" || echo "failed" return $ret } @@ -73,6 +75,7 @@ run_one_nat() { local -r all="$@" local -r tx_args=${all%rx*} local -r rx_args=${all#*rx} + local ret=0 if [[ ${tx_args} = *-4* ]]; then ipt_cmd=iptables @@ -93,16 +96,17 @@ run_one_nat() { # ... so that GRO will match the UDP_GRO enabled socket, but packets # will land on the 'plain' one ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 & - pid=$! - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} && \ - echo "ok" || \ - echo "failed"& + local PID1=$! + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} & + local PID2=$! wait_local_port_listen "${PEER_NS}" 8000 udp ./udpgso_bench_tx ${tx_args} - ret=$? - kill -INT $pid - wait $(jobs -p) + check_err $? + kill -INT ${PID1} + wait ${PID2} + check_err $? + [ "$ret" -eq 0 ] && echo "ok" || echo "failed" return $ret } @@ -111,20 +115,26 @@ run_one_2sock() { local -r all="$@" local -r tx_args=${all%rx*} local -r rx_args=${all#*rx} + local ret=0 cfg_veth ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} -p 12345 & - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} && \ - echo "ok" || \ - echo "failed" & + local PID1=$! + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} & + local PID2=$! wait_local_port_listen "${PEER_NS}" 12345 udp ./udpgso_bench_tx ${tx_args} -p 12345 + check_err $? wait_local_port_listen "${PEER_NS}" 8000 udp ./udpgso_bench_tx ${tx_args} - ret=$? - wait $(jobs -p) + check_err $? + wait ${PID1} + check_err $? + wait ${PID2} + check_err $? + [ "$ret" -eq 0 ] && echo "ok" || echo "failed" return $ret } From d7818402b1d80347c764001583f6d63fa68c2e1a Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Thu, 15 Aug 2024 15:59:51 +0800 Subject: [PATCH 201/385] selftests: udpgro: no need to load xdp for gro MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After commit d7db7775ea2e ("net: veth: do not manipulate GRO when using XDP"), there is no need to load XDP program to enable GRO. On the other hand, the current test is failed due to loading the XDP program. e.g. # selftests: net: udpgro.sh # ipv4 # no GRO ok # no GRO chk cmsg ok # GRO ./udpgso_bench_rx: recv: bad packet len, got 1472, expected 14720 # # failed [...] # bad GRO lookup ok # multiple GRO socks ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520 # # ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520 # # failed ok 1 selftests: net: udpgro.sh After fix, all the test passed. # ./udpgro.sh ipv4 no GRO ok [...] multiple GRO socks ok Fixes: d7db7775ea2e ("net: veth: do not manipulate GRO when using XDP") Reported-by: Yi Chen Closes: https://issues.redhat.com/browse/RHEL-53858 Reviewed-by: Toke Høiland-Jørgensen Acked-by: Paolo Abeni Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- tools/testing/selftests/net/udpgro.sh | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index 4659cf01e4384..d5ffd8c9172e1 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -7,8 +7,6 @@ source net_helper.sh readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)" -BPF_FILE="xdp_dummy.bpf.o" - # set global exit status, but never reset nonzero one. check_err() { @@ -38,7 +36,7 @@ cfg_veth() { ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24 ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad ip -netns "${PEER_NS}" link set dev veth1 up - ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp + ip netns exec "${PEER_NS}" ethtool -K veth1 gro on } run_one() { @@ -206,11 +204,6 @@ run_all() { return $ret } -if [ ! -f ${BPF_FILE} ]; then - echo "Missing ${BPF_FILE}. Run 'make' first" - exit -1 -fi - if [[ $# -eq 0 ]]; then run_all elif [[ $1 == "__subprocess" ]]; then From 565d121b69980637f040eb4d84289869cdaabedf Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 13 Aug 2024 00:28:25 +0200 Subject: [PATCH 202/385] tcp: prevent concurrent execution of tcp_sk_exit_batch Its possible that two threads call tcp_sk_exit_batch() concurrently, once from the cleanup_net workqueue, once from a task that failed to clone a new netns. In the latter case, error unwinding calls the exit handlers in reverse order for the 'failed' netns. tcp_sk_exit_batch() calls tcp_twsk_purge(). Problem is that since commit b099ce2602d8 ("net: Batch inet_twsk_purge"), this function picks up twsk in any dying netns, not just the one passed in via exit_batch list. This means that the error unwind of setup_net() can "steal" and destroy timewait sockets belonging to the exiting netns. This allows the netns exit worker to proceed to call WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount)); without the expected 1 -> 0 transition, which then splats. At same time, error unwind path that is also running inet_twsk_purge() will splat as well: WARNING: .. at lib/refcount.c:31 refcount_warn_saturate+0x1ed/0x210 ... refcount_dec include/linux/refcount.h:351 [inline] inet_twsk_kill+0x758/0x9c0 net/ipv4/inet_timewait_sock.c:70 inet_twsk_deschedule_put net/ipv4/inet_timewait_sock.c:221 inet_twsk_purge+0x725/0x890 net/ipv4/inet_timewait_sock.c:304 tcp_sk_exit_batch+0x1c/0x170 net/ipv4/tcp_ipv4.c:3522 ops_exit_list+0x128/0x180 net/core/net_namespace.c:178 setup_net+0x714/0xb40 net/core/net_namespace.c:375 copy_net_ns+0x2f0/0x670 net/core/net_namespace.c:508 create_new_namespaces+0x3ea/0xb10 kernel/nsproxy.c:110 ... because refcount_dec() of tw_refcount unexpectedly dropped to 0. This doesn't seem like an actual bug (no tw sockets got lost and I don't see a use-after-free) but as erroneous trigger of debug check. Add a mutex to force strict ordering: the task that calls tcp_twsk_purge() blocks other task from doing final _dec_and_test before mutex-owner has removed all tw sockets of dying netns. Fixes: e9bd0cca09d1 ("tcp: Don't allocate tcp_death_row outside of struct netns_ipv4.") Reported-by: syzbot+8ea26396ff85d23a8929@syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/0000000000003a5292061f5e4e19@google.com/ Link: https://lore.kernel.org/netdev/20240812140104.GA21559@breakpoint.cc/ Signed-off-by: Florian Westphal Reviewed-by: Kuniyuki Iwashima Reviewed-by: Jason Xing Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240812222857.29837-1-fw@strlen.de Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_ipv4.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fd17f25ff288a..a4e510846905e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -97,6 +97,8 @@ static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; +static DEFINE_MUTEX(tcp_exit_batch_mutex); + static u32 tcp_v4_init_seq(const struct sk_buff *skb) { return secure_tcp_seq(ip_hdr(skb)->daddr, @@ -3514,6 +3516,16 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; + /* make sure concurrent calls to tcp_sk_exit_batch from net_cleanup_work + * and failed setup_net error unwinding path are serialized. + * + * tcp_twsk_purge() handles twsk in any dead netns, not just those in + * net_exit_list, the thread that dismantles a particular twsk must + * do so without other thread progressing to refcount_dec_and_test() of + * tcp_death_row.tw_refcount. + */ + mutex_lock(&tcp_exit_batch_mutex); + tcp_twsk_purge(net_exit_list); list_for_each_entry(net, net_exit_list, exit_list) { @@ -3521,6 +3533,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount)); tcp_fastopen_ctx_destroy(net); } + + mutex_unlock(&tcp_exit_batch_mutex); } static struct pernet_operations __net_initdata tcp_sk_ops = { From 26a77d02891ab62172085a4f94af9b3c90aed387 Mon Sep 17 00:00:00 2001 From: Antonio Ojea Date: Thu, 27 Jun 2024 13:27:10 +0200 Subject: [PATCH 203/385] netfilter: nfnetlink_queue: unbreak SCTP traffic when packet is enqueued with nfqueue and GSO is enabled, checksum calculation has to take into account the protocol, as SCTP uses a 32 bits CRC checksum. Enter skb_gso_segment() path in case of SCTP GSO packets because skb_zerocopy() does not support for GSO_BY_FRAGS. Joint work with Pablo. Signed-off-by: Antonio Ojea Signed-off-by: Pablo Neira Ayuso --- net/core/dev.c | 1 + net/netfilter/nfnetlink_queue.c | 12 ++++++++++-- 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index e7260889d4cb0..8384282acadf7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3386,6 +3386,7 @@ int skb_crc32c_csum_help(struct sk_buff *skb) out: return ret; } +EXPORT_SYMBOL(skb_crc32c_csum_help); __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index e0716da256bf5..d2773ce9b5853 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -540,6 +540,14 @@ static int nfqnl_put_bridge(struct nf_queue_entry *entry, struct sk_buff *skb) return -1; } +static int nf_queue_checksum_help(struct sk_buff *entskb) +{ + if (skb_csum_is_sctp(entskb)) + return skb_crc32c_csum_help(entskb); + + return skb_checksum_help(entskb); +} + static struct sk_buff * nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry, @@ -602,7 +610,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, case NFQNL_COPY_PACKET: if (!(queue->flags & NFQA_CFG_F_GSO) && entskb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_help(entskb)) + nf_queue_checksum_help(entskb)) return NULL; data_len = READ_ONCE(queue->copy_range); @@ -1014,7 +1022,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) break; } - if ((queue->flags & NFQA_CFG_F_GSO) || !skb_is_gso(skb)) + if (!skb_is_gso(skb) || ((queue->flags & NFQA_CFG_F_GSO) && !skb_is_gso_sctp(skb))) return __nfqnl_enqueue_packet(net, queue, entry); nf_bridge_adjust_skb_data(skb); From 4e97d521c2be094718c4c5c7c4f785e8972b4af0 Mon Sep 17 00:00:00 2001 From: Antonio Ojea Date: Tue, 2 Jul 2024 13:15:36 +0200 Subject: [PATCH 204/385] selftests: netfilter: nft_queue.sh: sctp coverage Test that nfqueue with and without GSO process SCTP packets correctly. Joint work with Florian and Pablo. Signed-off-by: Antonio Ojea Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/net/netfilter/config | 2 + .../selftests/net/netfilter/nft_queue.sh | 85 ++++++++++++++++++- 2 files changed, 86 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config index 63ef80ef47a42..b2dd4db452150 100644 --- a/tools/testing/selftests/net/netfilter/config +++ b/tools/testing/selftests/net/netfilter/config @@ -87,3 +87,5 @@ CONFIG_XFRM_USER=m CONFIG_XFRM_STATISTICS=y CONFIG_NET_PKTGEN=m CONFIG_TUN=m +CONFIG_INET_DIAG=m +CONFIG_SCTP_DIAG=m diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh index c61d23a8c88db..f3bdeb1271eb1 100755 --- a/tools/testing/selftests/net/netfilter/nft_queue.sh +++ b/tools/testing/selftests/net/netfilter/nft_queue.sh @@ -25,6 +25,9 @@ cleanup() } checktool "nft --version" "test without nft tool" +checktool "socat -h" "run test without socat" + +modprobe -q sctp trap cleanup EXIT @@ -265,7 +268,6 @@ test_tcp_forward() test_tcp_localhost() { - dd conv=sparse status=none if=/dev/zero bs=1M count=200 of="$TMPINPUT" timeout 5 ip netns exec "$nsrouter" socat -u TCP-LISTEN:12345 STDOUT >/dev/null & local rpid=$! @@ -375,6 +377,82 @@ EOF wait 2>/dev/null } +sctp_listener_ready() +{ + ss -S -N "$1" -ln -o "sport = :12345" | grep -q 12345 +} + +test_sctp_forward() +{ + ip netns exec "$nsrouter" nft -f /dev/stdin < "$TMPFILE1" & + local rpid=$! + + busywait "$BUSYWAIT_TIMEOUT" sctp_listener_ready "$ns2" + + ip netns exec "$nsrouter" ./nf_queue -q 10 -G -t "$timeout" & + local nfqpid=$! + + ip netns exec "$ns1" socat -u STDIN SCTP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null + + if ! ip netns exec "$nsrouter" nft delete table inet sctpq; then + echo "FAIL: Could not delete sctpq table" + exit 1 + fi + + wait "$rpid" && echo "PASS: sctp and nfqueue in forward chain" + + if ! diff -u "$TMPINPUT" "$TMPFILE1" ; then + echo "FAIL: lost packets?!" 1>&2 + exit 1 + fi +} + +test_sctp_output() +{ + ip netns exec "$ns1" nft -f /dev/stdin < "$TMPFILE1" & + local rpid=$! + + busywait "$BUSYWAIT_TIMEOUT" sctp_listener_ready "$ns2" + + ip netns exec "$ns1" ./nf_queue -q 11 -t "$timeout" & + local nfqpid=$! + + ip netns exec "$ns1" socat -u STDIN SCTP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null + + if ! ip netns exec "$ns1" nft delete table inet sctpq; then + echo "FAIL: Could not delete sctpq table" + exit 1 + fi + + # must wait before checking completeness of output file. + wait "$rpid" && echo "PASS: sctp and nfqueue in output chain with GSO" + + if ! diff -u "$TMPINPUT" "$TMPFILE1" ; then + echo "FAIL: lost packets?!" 1>&2 + exit 1 + fi +} + test_queue_removal() { read tainted_then < /proc/sys/kernel/tainted @@ -443,11 +521,16 @@ test_queue 10 # same. We queue to a second program as well. load_ruleset "filter2" 20 test_queue 20 +ip netns exec "$ns1" nft flush ruleset test_tcp_forward test_tcp_localhost test_tcp_localhost_connectclose test_tcp_localhost_requeue +test_sctp_forward +test_sctp_output + +# should be last, adds vrf device in ns1 and changes routes test_icmp_vrf test_queue_removal From e2444c1d463995477fb447be9d0c54150a5c393b Mon Sep 17 00:00:00 2001 From: Donald Hunter Date: Tue, 28 May 2024 11:37:54 +0100 Subject: [PATCH 205/385] netfilter: nfnetlink: convert kfree_skb to consume_skb Use consume_skb in the batch code path to avoid generating spurious NOT_SPECIFIED skb drop reasons. Signed-off-by: Donald Hunter Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 932b3ddb34f13..7784ec094097b 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -402,27 +402,27 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); - return kfree_skb(skb); + return consume_skb(skb); } } if (!ss->valid_genid || !ss->commit || !ss->abort) { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); - return kfree_skb(skb); + return consume_skb(skb); } if (!try_module_get(ss->owner)) { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); - return kfree_skb(skb); + return consume_skb(skb); } if (!ss->valid_genid(net, genid)) { module_put(ss->owner); nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -ERESTART, NULL); - return kfree_skb(skb); + return consume_skb(skb); } nfnl_unlock(subsys_id); @@ -567,7 +567,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, if (status & NFNL_BATCH_REPLAY) { ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD); nfnl_err_reset(&err_list); - kfree_skb(skb); + consume_skb(skb); module_put(ss->owner); goto replay; } else if (status == NFNL_BATCH_DONE) { @@ -593,7 +593,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, err = ss->abort(net, oskb, abort_action); if (err == -EAGAIN) { nfnl_err_reset(&err_list); - kfree_skb(skb); + consume_skb(skb); module_put(ss->owner); status |= NFNL_BATCH_FAILURE; goto replay_abort; @@ -601,7 +601,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, } nfnl_err_deliver(&err_list, oskb); - kfree_skb(skb); + consume_skb(skb); module_put(ss->owner); } From c1aa38866b9c58dc6cf7a5fc6a3e1ca75565169e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 10 Jul 2024 10:58:29 +0200 Subject: [PATCH 206/385] netfilter: nf_tables: store new sets in dedicated list nft_set_lookup_byid() is very slow when transaction becomes large, due to walk of the transaction list. Add a dedicated list that contains only the new sets. Before: nft -f ruleset 0.07s user 0.00s system 0% cpu 1:04.84 total After: nft -f ruleset 0.07s user 0.00s system 0% cpu 30.115 total .. where ruleset contains ~10 sets with ~100k elements. The above number is for a combined flush+reload of the ruleset. With previous flush, even the first NEWELEM has to walk through a few hundred thousands of DELSET(ELEM) transactions before the first NEWSET object. To cope with random-order-newset-newsetelem we'd need to replace commit_set_list with a hashtable. Expectation is that a NEWELEM operation refers to the most recently added set, so last entry of the dedicated list should be the set we want. NB: This is not a bug fix per se (functionality is fine), but with larger transaction batches list search takes forever, so it would be nice to speed this up for -stable too, hence adding a "fixes" tag. Fixes: 958bee14d071 ("netfilter: nf_tables: use new transaction infrastructure to handle sets") Reported-by: Nadia Pinaeva Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 ++ net/netfilter/nf_tables_api.c | 29 ++++++++++++++++++++--------- 2 files changed, 22 insertions(+), 9 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 1bfdd16890fac..2be4738eae1cc 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1674,6 +1674,7 @@ struct nft_trans_rule { struct nft_trans_set { struct nft_trans_binding nft_trans_binding; + struct list_head list_trans_newset; struct nft_set *set; u32 set_id; u32 gc_int; @@ -1875,6 +1876,7 @@ static inline int nft_request_module(struct net *net, const char *fmt, ...) { re struct nftables_pernet { struct list_head tables; struct list_head commit_list; + struct list_head commit_set_list; struct list_head binding_list; struct list_head module_list; struct list_head notify_list; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0a2f793469589..3ea5d01635107 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -393,6 +393,7 @@ static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *tr { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans_binding *binding; + struct nft_trans_set *trans_set; list_add_tail(&trans->list, &nft_net->commit_list); @@ -402,9 +403,13 @@ static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *tr switch (trans->msg_type) { case NFT_MSG_NEWSET: + trans_set = nft_trans_container_set(trans); + if (!nft_trans_set_update(trans) && nft_set_is_anonymous(nft_trans_set(trans))) list_add_tail(&binding->binding_list, &nft_net->binding_list); + + list_add_tail(&trans_set->list_trans_newset, &nft_net->commit_set_list); break; case NFT_MSG_NEWCHAIN: if (!nft_trans_chain_update(trans) && @@ -611,6 +616,7 @@ static int __nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, trans_set = nft_trans_container_set(trans); INIT_LIST_HEAD(&trans_set->nft_trans_binding.binding_list); + INIT_LIST_HEAD(&trans_set->list_trans_newset); if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] && !desc) { nft_trans_set_id(trans) = @@ -4485,17 +4491,16 @@ static struct nft_set *nft_set_lookup_byid(const struct net *net, { struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); - struct nft_trans *trans; + struct nft_trans_set *trans; - list_for_each_entry(trans, &nft_net->commit_list, list) { - if (trans->msg_type == NFT_MSG_NEWSET) { - struct nft_set *set = nft_trans_set(trans); + /* its likely the id we need is at the tail, not at start */ + list_for_each_entry_reverse(trans, &nft_net->commit_set_list, list_trans_newset) { + struct nft_set *set = trans->set; - if (id == nft_trans_set_id(trans) && - set->table == table && - nft_active_genmask(set, genmask)) - return set; - } + if (id == trans->set_id && + set->table == table && + nft_active_genmask(set, genmask)) + return set; } return ERR_PTR(-ENOENT); } @@ -10447,6 +10452,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_NEWSET: + list_del(&nft_trans_container_set(trans)->list_trans_newset); if (nft_trans_set_update(trans)) { struct nft_set *set = nft_trans_set(trans); @@ -10755,6 +10761,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; case NFT_MSG_NEWSET: + list_del(&nft_trans_container_set(trans)->list_trans_newset); if (nft_trans_set_update(trans)) { nft_trans_destroy(trans); break; @@ -10850,6 +10857,8 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } } + WARN_ON_ONCE(!list_empty(&nft_net->commit_set_list)); + nft_set_abort_update(&set_update_list); synchronize_rcu(); @@ -11519,6 +11528,7 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&nft_net->tables); INIT_LIST_HEAD(&nft_net->commit_list); + INIT_LIST_HEAD(&nft_net->commit_set_list); INIT_LIST_HEAD(&nft_net->binding_list); INIT_LIST_HEAD(&nft_net->module_list); INIT_LIST_HEAD(&nft_net->notify_list); @@ -11549,6 +11559,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) gc_seq = nft_gc_seq_begin(nft_net); WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + WARN_ON_ONCE(!list_empty(&nft_net->commit_set_list)); if (!list_empty(&nft_net->module_list)) nf_tables_module_autoload_cleanup(net); From c9526aeb4998393171d85225ff540e28c7d4ab86 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 15 Jul 2024 13:32:31 +0200 Subject: [PATCH 207/385] netfilter: nf_tables: do not remove elements if set backend implements .abort pipapo set backend maintains two copies of the datastructure, removing the elements from the copy that is going to be discarded slows down the abort path significantly, from several minutes to few seconds after this patch. This patch was previously reverted by f86fb94011ae ("netfilter: nf_tables: revert do not remove elements if set backend implements .abort") but it is now possible since recent work by Florian Westphal to perform on-demand clone from insert/remove path: 532aec7e878b ("netfilter: nft_set_pipapo: remove dirty flag") 3f1d886cc7c3 ("netfilter: nft_set_pipapo: move cloning of match info to insert/removal path") a238106703ab ("netfilter: nft_set_pipapo: prepare pipapo_get helper for on-demand clone") c5444786d0ea ("netfilter: nft_set_pipapo: merge deactivate helper into caller") 6c108d9bee44 ("netfilter: nft_set_pipapo: prepare walk function for on-demand clone") 8b8a2417558c ("netfilter: nft_set_pipapo: prepare destroy function for on-demand clone") 80efd2997fb9 ("netfilter: nft_set_pipapo: make pipapo_clone helper return NULL") a590f4760922 ("netfilter: nft_set_pipapo: move prove_locking helper around") after this series, the clone is fully released once aborted, no need to take it back to previous state. Thus, no stale reference to elements can occur. Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 3ea5d01635107..c85d037a363b2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -10789,7 +10789,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; } te = nft_trans_container_elem(trans); - nft_setelem_remove(net, te->set, te->elem_priv); + if (!te->set->ops->abort || + nft_setelem_is_catchall(te->set, te->elem_priv)) + nft_setelem_remove(net, te->set, te->elem_priv); + if (!nft_setelem_is_catchall(te->set, te->elem_priv)) atomic_dec(&te->set->nelems); From d5283b47e225e1473e1a07085b9c4e6bfd08ba51 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 17 Jul 2024 22:09:44 -0400 Subject: [PATCH 208/385] netfilter: move nf_ct_netns_get out of nf_conncount_init This patch is to move nf_ct_netns_get() out of nf_conncount_init() and let the consumers of nf_conncount decide if they want to turn on netfilter conntrack. It makes nf_conncount more flexible to be used in other places and avoids netfilter conntrack turned on when using it in openvswitch conntrack. Signed-off-by: Xin Long Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_count.h | 6 ++---- net/netfilter/nf_conncount.c | 15 +++------------ net/netfilter/xt_connlimit.c | 15 +++++++++++++-- net/openvswitch/conntrack.c | 5 ++--- 4 files changed, 20 insertions(+), 21 deletions(-) diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index e227d997fc716..1b58b5b91ff6a 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -15,10 +15,8 @@ struct nf_conncount_list { unsigned int count; /* length of list */ }; -struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family, - unsigned int keylen); -void nf_conncount_destroy(struct net *net, unsigned int family, - struct nf_conncount_data *data); +struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int keylen); +void nf_conncount_destroy(struct net *net, struct nf_conncount_data *data); unsigned int nf_conncount_count(struct net *net, struct nf_conncount_data *data, diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 34ba14e59e95a..4890af4dc263f 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -522,11 +522,10 @@ unsigned int nf_conncount_count(struct net *net, } EXPORT_SYMBOL_GPL(nf_conncount_count); -struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family, - unsigned int keylen) +struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int keylen) { struct nf_conncount_data *data; - int ret, i; + int i; if (keylen % sizeof(u32) || keylen / sizeof(u32) > MAX_KEYLEN || @@ -539,12 +538,6 @@ struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family if (!data) return ERR_PTR(-ENOMEM); - ret = nf_ct_netns_get(net, family); - if (ret < 0) { - kfree(data); - return ERR_PTR(ret); - } - for (i = 0; i < ARRAY_SIZE(data->root); ++i) data->root[i] = RB_ROOT; @@ -581,13 +574,11 @@ static void destroy_tree(struct rb_root *r) } } -void nf_conncount_destroy(struct net *net, unsigned int family, - struct nf_conncount_data *data) +void nf_conncount_destroy(struct net *net, struct nf_conncount_data *data) { unsigned int i; cancel_work_sync(&data->gc_work); - nf_ct_netns_put(net, family); for (i = 0; i < ARRAY_SIZE(data->root); ++i) destroy_tree(&data->root[i]); diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 5d04ef80a61dc..0e762277bcf8f 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -86,6 +86,7 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par) { struct xt_connlimit_info *info = par->matchinfo; unsigned int keylen; + int ret; keylen = sizeof(u32); if (par->family == NFPROTO_IPV6) @@ -93,8 +94,17 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par) else keylen += sizeof(struct in_addr); + ret = nf_ct_netns_get(par->net, par->family); + if (ret < 0) { + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); + return ret; + } + /* init private data */ - info->data = nf_conncount_init(par->net, par->family, keylen); + info->data = nf_conncount_init(par->net, keylen); + if (IS_ERR(info->data)) + nf_ct_netns_put(par->net, par->family); return PTR_ERR_OR_ZERO(info->data); } @@ -103,7 +113,8 @@ static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_connlimit_info *info = par->matchinfo; - nf_conncount_destroy(par->net, par->family, info->data); + nf_conncount_destroy(par->net, info->data); + nf_ct_netns_put(par->net, par->family); } static struct xt_match connlimit_mt_reg __read_mostly = { diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index a3da5ee34f92d..3bb4810234aac 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1608,8 +1608,7 @@ static int ovs_ct_limit_init(struct net *net, struct ovs_net *ovs_net) for (i = 0; i < CT_LIMIT_HASH_BUCKETS; i++) INIT_HLIST_HEAD(&ovs_net->ct_limit_info->limits[i]); - ovs_net->ct_limit_info->data = - nf_conncount_init(net, NFPROTO_INET, sizeof(u32)); + ovs_net->ct_limit_info->data = nf_conncount_init(net, sizeof(u32)); if (IS_ERR(ovs_net->ct_limit_info->data)) { err = PTR_ERR(ovs_net->ct_limit_info->data); @@ -1626,7 +1625,7 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) const struct ovs_ct_limit_info *info = ovs_net->ct_limit_info; int i; - nf_conncount_destroy(net, NFPROTO_INET, info->data); + nf_conncount_destroy(net, info->data); for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { struct hlist_head *head = &info->limits[i]; struct ovs_ct_limit *ct_limit; From a2901083b1490a45df0700ac0aaa0730811cbf15 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 16 Aug 2024 14:22:44 -0700 Subject: [PATCH 209/385] tcp_metrics: use netlink policy for IPv6 addr len validation Use the netlink policy to validate IPv6 address length. Destination address currently has policy for max len set, and source has no policy validation. In both cases the code does the real check. With correct policy check the code can be removed. Reviewed-by: Stephen Hemminger Reviewed-by: David Ahern Link: https://patch.msgid.link/20240816212245.467745-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_metrics.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index b01eb6d944139..95669935494ef 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -617,9 +617,13 @@ static struct genl_family tcp_metrics_nl_family; static const struct nla_policy tcp_metrics_nl_policy[TCP_METRICS_ATTR_MAX + 1] = { [TCP_METRICS_ATTR_ADDR_IPV4] = { .type = NLA_U32, }, - [TCP_METRICS_ATTR_ADDR_IPV6] = { .type = NLA_BINARY, - .len = sizeof(struct in6_addr), }, + [TCP_METRICS_ATTR_ADDR_IPV6] = + NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), + [TCP_METRICS_ATTR_SADDR_IPV4] = { .type = NLA_U32, }, + [TCP_METRICS_ATTR_SADDR_IPV6] = + NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), + /* Following attributes are not received for GET/DEL, * we keep them for reference */ @@ -811,8 +815,6 @@ static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, if (a) { struct in6_addr in6; - if (nla_len(a) != sizeof(struct in6_addr)) - return -EINVAL; in6 = nla_get_in6_addr(a); inetpeer_set_addr_v6(addr, &in6); if (hash) From ce335db0621648472f9bb4b7191eb2e13a5793cf Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Fri, 16 Aug 2024 18:29:17 +0800 Subject: [PATCH 210/385] net: mctp: test: Use correct skb for route input check In the MCTP route input test, we're routing one skb, then (when delivery is expected) checking the resulting routed skb. However, we're currently checking the original skb length, rather than the routed skb. Check the routed skb instead; the original will have been freed at this point. Fixes: 8892c0490779 ("mctp: Add route input to socket tests") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/kernel-janitors/4ad204f0-94cf-46c5-bdab-49592addf315@kili.mountain/ Signed-off-by: Jeremy Kerr Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240816-mctp-kunit-skb-fix-v1-1-3c367ac89c27@codeconstruct.com.au Signed-off-by: Jakub Kicinski --- net/mctp/test/route-test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index 77e5dd4222580..8551dab1d1e69 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -366,7 +366,7 @@ static void mctp_test_route_input_sk(struct kunit *test) skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc); KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2); - KUNIT_EXPECT_EQ(test, skb->len, 1); + KUNIT_EXPECT_EQ(test, skb2->len, 1); skb_free_datagram(sock->sk, skb2); From 359c5eb0f7364be9a26626402cc315e5e5f0d8c7 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Fri, 16 Aug 2024 18:19:06 +0800 Subject: [PATCH 211/385] gve: Remove unused declaration gve_rx_alloc_rings() Commit f13697cc7a19 ("gve: Switch to config-aware queue allocation") convert this function to gve_rx_alloc_rings_gqi(). Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240816101906.882743-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/google/gve/gve.h | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 09a85ed591431..301fa1ea4f516 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -1153,7 +1153,6 @@ int gve_rx_alloc_ring_gqi(struct gve_priv *priv, int idx); void gve_rx_free_ring_gqi(struct gve_priv *priv, struct gve_rx_ring *rx, struct gve_rx_alloc_rings_cfg *cfg); -int gve_rx_alloc_rings(struct gve_priv *priv); int gve_rx_alloc_rings_gqi(struct gve_priv *priv, struct gve_rx_alloc_rings_cfg *cfg); void gve_rx_free_rings_gqi(struct gve_priv *priv, From 12906bab4414d0e9034218a2ada82c53109ffff9 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Fri, 16 Aug 2024 18:16:38 +0800 Subject: [PATCH 212/385] igbvf: Remove two unused declarations There is no caller and implementations in tree. Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240816101638.882072-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igbvf/igbvf.h | 1 - drivers/net/ethernet/intel/igbvf/mbx.h | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igbvf/igbvf.h b/drivers/net/ethernet/intel/igbvf/igbvf.h index 7b83678ba83a6..6ad35a00a2873 100644 --- a/drivers/net/ethernet/intel/igbvf/igbvf.h +++ b/drivers/net/ethernet/intel/igbvf/igbvf.h @@ -282,7 +282,6 @@ enum igbvf_state_t { extern char igbvf_driver_name[]; -void igbvf_check_options(struct igbvf_adapter *); void igbvf_set_ethtool_ops(struct net_device *); int igbvf_up(struct igbvf_adapter *); diff --git a/drivers/net/ethernet/intel/igbvf/mbx.h b/drivers/net/ethernet/intel/igbvf/mbx.h index e5b31818d5658..7637d21445bf5 100644 --- a/drivers/net/ethernet/intel/igbvf/mbx.h +++ b/drivers/net/ethernet/intel/igbvf/mbx.h @@ -49,7 +49,6 @@ #define E1000_PF_CONTROL_MSG 0x0100 /* PF control message */ -void e1000_init_mbx_ops_generic(struct e1000_hw *hw); s32 e1000_init_mbx_params_vf(struct e1000_hw *); #endif /* _E1000_MBX_H_ */ From c5e2a1b06760a2253c5e8959b49b307e9986bfae Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Fri, 16 Aug 2024 18:15:50 +0800 Subject: [PATCH 213/385] net/mlx5: E-Switch, Remove unused declarations These are never implenmented since commit b691b1116e82 ("net/mlx5: Implement devlink port function cmds to control ipsec_packet"). Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240816101550.881844-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 578466d69f219..f44b4c7ebcfd7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -887,9 +887,6 @@ int mlx5_esw_ipsec_vf_packet_offload_set(struct mlx5_eswitch *esw, struct mlx5_v bool enable); int mlx5_esw_ipsec_vf_packet_offload_supported(struct mlx5_core_dev *dev, u16 vport_num); -void mlx5_esw_vport_ipsec_offload_enable(struct mlx5_eswitch *esw); -void mlx5_esw_vport_ipsec_offload_disable(struct mlx5_eswitch *esw); - #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } From af3dc0ad3167985894a292968c67502f42854e6d Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Fri, 16 Aug 2024 18:04:04 +0800 Subject: [PATCH 214/385] mptcp: Remove unused declaration mptcp_sockopt_sync() Commit a1ab24e5fc4a ("mptcp: consolidate sockopt synchronization") removed the implementation but leave declaration. Signed-off-by: Yue Haibing Reviewed-by: Matthieu Baerts (NGI0) Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240816100404.879598-1-yuehaibing@huawei.com Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.h | 1 - 1 file changed, 1 deletion(-) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 60c6b073d65fe..08387140a646a 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1154,7 +1154,6 @@ static inline void mptcp_pm_close_subflow(struct mptcp_sock *msk) spin_unlock_bh(&msk->pm.lock); } -void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk); void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk); static inline struct mptcp_ext *mptcp_get_ext(const struct sk_buff *skb) From dca9d62a0d7684a5510645ba05960529c5066457 Mon Sep 17 00:00:00 2001 From: Zhang Changzhong Date: Thu, 15 Aug 2024 22:09:42 +0800 Subject: [PATCH 215/385] net: remove redundant check in skb_shift() The check for '!to' is redundant here, since skb_can_coalesce() already contains this check. Signed-off-by: Zhang Changzhong Reviewed-by: Simon Horman Link: https://patch.msgid.link/1723730983-22912-1-git-send-email-zhangchangzhong@huawei.com Signed-off-by: Jakub Kicinski --- net/core/skbuff.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index de2a044cc6656..1748673e1fe0b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4172,8 +4172,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) /* Actual merge is delayed until the point when we know we can * commit all, so that we don't have to undo partial changes */ - if (!to || - !skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), + if (!skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), skb_frag_off(fragfrom))) { merge = -1; } else { From 807067bf014d4a3ae2cc55bd3de16f22a01eb580 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Thu, 15 Aug 2024 15:04:37 -0700 Subject: [PATCH 216/385] kcm: Serialise kcm_sendmsg() for the same socket. syzkaller reported UAF in kcm_release(). [0] The scenario is 1. Thread A builds a skb with MSG_MORE and sets kcm->seq_skb. 2. Thread A resumes building skb from kcm->seq_skb but is blocked by sk_stream_wait_memory() 3. Thread B calls sendmsg() concurrently, finishes building kcm->seq_skb and puts the skb to the write queue 4. Thread A faces an error and finally frees skb that is already in the write queue 5. kcm_release() does double-free the skb in the write queue When a thread is building a MSG_MORE skb, another thread must not touch it. Let's add a per-sk mutex and serialise kcm_sendmsg(). [0]: BUG: KASAN: slab-use-after-free in __skb_unlink include/linux/skbuff.h:2366 [inline] BUG: KASAN: slab-use-after-free in __skb_dequeue include/linux/skbuff.h:2385 [inline] BUG: KASAN: slab-use-after-free in __skb_queue_purge_reason include/linux/skbuff.h:3175 [inline] BUG: KASAN: slab-use-after-free in __skb_queue_purge include/linux/skbuff.h:3181 [inline] BUG: KASAN: slab-use-after-free in kcm_release+0x170/0x4c8 net/kcm/kcmsock.c:1691 Read of size 8 at addr ffff0000ced0fc80 by task syz-executor329/6167 CPU: 1 PID: 6167 Comm: syz-executor329 Tainted: G B 6.8.0-rc5-syzkaller-g9abbc24128bc #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024 Call trace: dump_backtrace+0x1b8/0x1e4 arch/arm64/kernel/stacktrace.c:291 show_stack+0x2c/0x3c arch/arm64/kernel/stacktrace.c:298 __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd0/0x124 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:377 [inline] print_report+0x178/0x518 mm/kasan/report.c:488 kasan_report+0xd8/0x138 mm/kasan/report.c:601 __asan_report_load8_noabort+0x20/0x2c mm/kasan/report_generic.c:381 __skb_unlink include/linux/skbuff.h:2366 [inline] __skb_dequeue include/linux/skbuff.h:2385 [inline] __skb_queue_purge_reason include/linux/skbuff.h:3175 [inline] __skb_queue_purge include/linux/skbuff.h:3181 [inline] kcm_release+0x170/0x4c8 net/kcm/kcmsock.c:1691 __sock_release net/socket.c:659 [inline] sock_close+0xa4/0x1e8 net/socket.c:1421 __fput+0x30c/0x738 fs/file_table.c:376 ____fput+0x20/0x30 fs/file_table.c:404 task_work_run+0x230/0x2e0 kernel/task_work.c:180 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0x618/0x1f64 kernel/exit.c:871 do_group_exit+0x194/0x22c kernel/exit.c:1020 get_signal+0x1500/0x15ec kernel/signal.c:2893 do_signal+0x23c/0x3b44 arch/arm64/kernel/signal.c:1249 do_notify_resume+0x74/0x1f4 arch/arm64/kernel/entry-common.c:148 exit_to_user_mode_prepare arch/arm64/kernel/entry-common.c:169 [inline] exit_to_user_mode arch/arm64/kernel/entry-common.c:178 [inline] el0_svc+0xac/0x168 arch/arm64/kernel/entry-common.c:713 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Allocated by task 6166: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_alloc_info+0x70/0x84 mm/kasan/generic.c:626 unpoison_slab_object mm/kasan/common.c:314 [inline] __kasan_slab_alloc+0x74/0x8c mm/kasan/common.c:340 kasan_slab_alloc include/linux/kasan.h:201 [inline] slab_post_alloc_hook mm/slub.c:3813 [inline] slab_alloc_node mm/slub.c:3860 [inline] kmem_cache_alloc_node+0x204/0x4c0 mm/slub.c:3903 __alloc_skb+0x19c/0x3d8 net/core/skbuff.c:641 alloc_skb include/linux/skbuff.h:1296 [inline] kcm_sendmsg+0x1d3c/0x2124 net/kcm/kcmsock.c:783 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg net/socket.c:745 [inline] sock_sendmsg+0x220/0x2c0 net/socket.c:768 splice_to_socket+0x7cc/0xd58 fs/splice.c:889 do_splice_from fs/splice.c:941 [inline] direct_splice_actor+0xec/0x1d8 fs/splice.c:1164 splice_direct_to_actor+0x438/0xa0c fs/splice.c:1108 do_splice_direct_actor fs/splice.c:1207 [inline] do_splice_direct+0x1e4/0x304 fs/splice.c:1233 do_sendfile+0x460/0xb3c fs/read_write.c:1295 __do_sys_sendfile64 fs/read_write.c:1362 [inline] __se_sys_sendfile64 fs/read_write.c:1348 [inline] __arm64_sys_sendfile64+0x160/0x3b4 fs/read_write.c:1348 __invoke_syscall arch/arm64/kernel/syscall.c:37 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:51 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:136 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:155 el0_svc+0x54/0x168 arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 Freed by task 6167: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x40/0x78 mm/kasan/common.c:68 kasan_save_free_info+0x5c/0x74 mm/kasan/generic.c:640 poison_slab_object+0x124/0x18c mm/kasan/common.c:241 __kasan_slab_free+0x3c/0x78 mm/kasan/common.c:257 kasan_slab_free include/linux/kasan.h:184 [inline] slab_free_hook mm/slub.c:2121 [inline] slab_free mm/slub.c:4299 [inline] kmem_cache_free+0x15c/0x3d4 mm/slub.c:4363 kfree_skbmem+0x10c/0x19c __kfree_skb net/core/skbuff.c:1109 [inline] kfree_skb_reason+0x240/0x6f4 net/core/skbuff.c:1144 kfree_skb include/linux/skbuff.h:1244 [inline] kcm_release+0x104/0x4c8 net/kcm/kcmsock.c:1685 __sock_release net/socket.c:659 [inline] sock_close+0xa4/0x1e8 net/socket.c:1421 __fput+0x30c/0x738 fs/file_table.c:376 ____fput+0x20/0x30 fs/file_table.c:404 task_work_run+0x230/0x2e0 kernel/task_work.c:180 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0x618/0x1f64 kernel/exit.c:871 do_group_exit+0x194/0x22c kernel/exit.c:1020 get_signal+0x1500/0x15ec kernel/signal.c:2893 do_signal+0x23c/0x3b44 arch/arm64/kernel/signal.c:1249 do_notify_resume+0x74/0x1f4 arch/arm64/kernel/entry-common.c:148 exit_to_user_mode_prepare arch/arm64/kernel/entry-common.c:169 [inline] exit_to_user_mode arch/arm64/kernel/entry-common.c:178 [inline] el0_svc+0xac/0x168 arch/arm64/kernel/entry-common.c:713 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 The buggy address belongs to the object at ffff0000ced0fc80 which belongs to the cache skbuff_head_cache of size 240 The buggy address is located 0 bytes inside of freed 240-byte region [ffff0000ced0fc80, ffff0000ced0fd70) The buggy address belongs to the physical page: page:00000000d35f4ae4 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x10ed0f flags: 0x5ffc00000000800(slab|node=0|zone=2|lastcpupid=0x7ff) page_type: 0xffffffff() raw: 05ffc00000000800 ffff0000c1cbf640 fffffdffc3423100 dead000000000004 raw: 0000000000000000 00000000000c000c 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff0000ced0fb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff0000ced0fc00: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc >ffff0000ced0fc80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff0000ced0fd00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fc fc ffff0000ced0fd80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module") Reported-by: syzbot+b72d86aa5df17ce74c60@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=b72d86aa5df17ce74c60 Tested-by: syzbot+b72d86aa5df17ce74c60@syzkaller.appspotmail.com Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240815220437.69511-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/kcm.h | 1 + net/kcm/kcmsock.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/include/net/kcm.h b/include/net/kcm.h index 90279e5e09a5c..441e993be634c 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -70,6 +70,7 @@ struct kcm_sock { struct work_struct tx_work; struct list_head wait_psock_list; struct sk_buff *seq_skb; + struct mutex tx_mutex; u32 tx_stopped : 1; /* Don't use bit fields here, these are set under different locks */ diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 2f191e50d4fc9..d4118c796290e 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -755,6 +755,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); int err = -EPIPE; + mutex_lock(&kcm->tx_mutex); lock_sock(sk); /* Per tcp_sendmsg this should be in poll */ @@ -926,6 +927,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) KCM_STATS_ADD(kcm->stats.tx_bytes, copied); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return copied; out_error: @@ -951,6 +953,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) sk->sk_write_space(sk); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return err; } @@ -1204,6 +1207,7 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) spin_unlock_bh(&mux->lock); INIT_WORK(&kcm->tx_work, kcm_tx_work); + mutex_init(&kcm->tx_mutex); spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); From d386d59b7c1a39112ca875327339ed519df2b96c Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Wed, 14 Aug 2024 21:08:26 +0800 Subject: [PATCH 217/385] net/smc: introduce statistics for allocated ringbufs of link group Currently we have the statistics on sndbuf/RMB sizes of all connections that have ever been on the link group, namely smc_stats_memsize. However these statistics are incremental and since the ringbufs of link group are allowed to be reused, we cannot know the actual allocated buffers through these. So here introduces the statistic on actual allocated ringbufs of the link group, it will be incremented when a new ringbuf is added into buf_list and decremented when it is deleted from buf_list. Signed-off-by: Wen Gu Signed-off-by: Paolo Abeni --- include/uapi/linux/smc.h | 4 ++++ net/smc/smc_core.c | 46 ++++++++++++++++++++++++++++++++++++---- net/smc/smc_core.h | 2 ++ 3 files changed, 48 insertions(+), 4 deletions(-) diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index b531e3ef011a4..9b74ef79070af 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -127,6 +127,8 @@ enum { SMC_NLA_LGR_R_NET_COOKIE, /* u64 */ SMC_NLA_LGR_R_PAD, /* flag */ SMC_NLA_LGR_R_BUF_TYPE, /* u8 */ + SMC_NLA_LGR_R_SNDBUF_ALLOC, /* uint */ + SMC_NLA_LGR_R_RMB_ALLOC, /* uint */ __SMC_NLA_LGR_R_MAX, SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1 }; @@ -162,6 +164,8 @@ enum { SMC_NLA_LGR_D_V2_COMMON, /* nest */ SMC_NLA_LGR_D_EXT_GID, /* u64 */ SMC_NLA_LGR_D_PEER_EXT_GID, /* u64 */ + SMC_NLA_LGR_D_SNDBUF_ALLOC, /* uint */ + SMC_NLA_LGR_D_DMB_ALLOC, /* uint */ __SMC_NLA_LGR_D_MAX, SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1 }; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 71fb334d8234d..8dcf1c7f15263 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -221,6 +221,35 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) write_unlock_bh(&lgr->conns_lock); } +static void smc_lgr_buf_list_add(struct smc_link_group *lgr, + bool is_rmb, + struct list_head *buf_list, + struct smc_buf_desc *buf_desc) +{ + list_add(&buf_desc->list, buf_list); + if (is_rmb) { + lgr->alloc_rmbs += buf_desc->len; + lgr->alloc_rmbs += + lgr->is_smcd ? sizeof(struct smcd_cdc_msg) : 0; + } else { + lgr->alloc_sndbufs += buf_desc->len; + } +} + +static void smc_lgr_buf_list_del(struct smc_link_group *lgr, + bool is_rmb, + struct smc_buf_desc *buf_desc) +{ + list_del(&buf_desc->list); + if (is_rmb) { + lgr->alloc_rmbs -= buf_desc->len; + lgr->alloc_rmbs -= + lgr->is_smcd ? sizeof(struct smcd_cdc_msg) : 0; + } else { + lgr->alloc_sndbufs -= buf_desc->len; + } +} + int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); @@ -363,6 +392,10 @@ static int smc_nl_fill_lgr(struct smc_link_group *lgr, smc_target[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target)) goto errattr; + if (nla_put_uint(skb, SMC_NLA_LGR_R_SNDBUF_ALLOC, lgr->alloc_sndbufs)) + goto errattr; + if (nla_put_uint(skb, SMC_NLA_LGR_R_RMB_ALLOC, lgr->alloc_rmbs)) + goto errattr; if (lgr->smc_version > SMC_V1) { v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2_COMMON); if (!v2_attrs) @@ -541,6 +574,10 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, goto errattr; if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd))) goto errattr; + if (nla_put_uint(skb, SMC_NLA_LGR_D_SNDBUF_ALLOC, lgr->alloc_sndbufs)) + goto errattr; + if (nla_put_uint(skb, SMC_NLA_LGR_D_DMB_ALLOC, lgr->alloc_rmbs)) + goto errattr; memcpy(smc_pnet, lgr->smcd->pnetid, SMC_MAX_PNETID_LEN); smc_pnet[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet)) @@ -1138,7 +1175,7 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, lock = is_rmb ? &lgr->rmbs_lock : &lgr->sndbufs_lock; down_write(lock); - list_del(&buf_desc->list); + smc_lgr_buf_list_del(lgr, is_rmb, buf_desc); up_write(lock); smc_buf_free(lgr, is_rmb, buf_desc); @@ -1377,7 +1414,7 @@ static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb) buf_list = &lgr->sndbufs[i]; list_for_each_entry_safe(buf_desc, bf_desc, buf_list, list) { - list_del(&buf_desc->list); + smc_lgr_buf_list_del(lgr, is_rmb, buf_desc); smc_buf_free(lgr, is_rmb, buf_desc); } } @@ -2414,7 +2451,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); buf_desc->used = 1; down_write(lock); - list_add(&buf_desc->list, buf_list); + smc_lgr_buf_list_add(lgr, is_rmb, buf_list, buf_desc); up_write(lock); break; /* found */ } @@ -2496,7 +2533,8 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd) rc = __smc_buf_create(smc, is_smcd, true); if (rc && smc->conn.sndbuf_desc) { down_write(&smc->conn.lgr->sndbufs_lock); - list_del(&smc->conn.sndbuf_desc->list); + smc_lgr_buf_list_del(smc->conn.lgr, false, + smc->conn.sndbuf_desc); up_write(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); smc->conn.sndbuf_desc = NULL; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index d93cf51dbd7ce..0db4e5f79ac4e 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -281,6 +281,8 @@ struct smc_link_group { struct rw_semaphore sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ struct rw_semaphore rmbs_lock; /* protects rx buffers */ + u64 alloc_sndbufs; /* stats of tx buffers */ + u64 alloc_rmbs; /* stats of rx buffers */ u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ From e0d103542b06c36240e3887edfe49578464866eb Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Wed, 14 Aug 2024 21:08:27 +0800 Subject: [PATCH 218/385] net/smc: introduce statistics for ringbufs usage of net namespace The buffer size histograms in smc_stats, namely rx/tx_rmbsize, record the sizes of ringbufs for all connections that have ever appeared in the net namespace. They are incremental and we cannot know the actual ringbufs usage from these. So here introduces statistics for current ringbufs usage of existing smc connections in the net namespace into smc_stats, it will be incremented when new connection uses a ringbuf and decremented when the ringbuf is unused. Signed-off-by: Wen Gu Signed-off-by: Paolo Abeni --- include/uapi/linux/smc.h | 2 ++ net/smc/smc_core.c | 22 +++++++++++++++------- net/smc/smc_stats.c | 6 ++++++ net/smc/smc_stats.h | 28 +++++++++++++++++++--------- 4 files changed, 42 insertions(+), 16 deletions(-) diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 9b74ef79070af..1f58cb0c266bd 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -253,6 +253,8 @@ enum { SMC_NLA_STATS_T_TX_BYTES, /* u64 */ SMC_NLA_STATS_T_RX_CNT, /* u64 */ SMC_NLA_STATS_T_TX_CNT, /* u64 */ + SMC_NLA_STATS_T_RX_RMB_USAGE, /* uint */ + SMC_NLA_STATS_T_TX_RMB_USAGE, /* uint */ __SMC_NLA_STATS_T_MAX, SMC_NLA_STATS_T_MAX = __SMC_NLA_STATS_T_MAX - 1 }; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 8dcf1c7f15263..4e694860ece4a 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1203,22 +1203,30 @@ static void smcd_buf_detach(struct smc_connection *conn) static void smc_buf_unuse(struct smc_connection *conn, struct smc_link_group *lgr) { + struct smc_sock *smc = container_of(conn, struct smc_sock, conn); + bool is_smcd = lgr->is_smcd; + int bufsize; + if (conn->sndbuf_desc) { - if (!lgr->is_smcd && conn->sndbuf_desc->is_vm) { + bufsize = conn->sndbuf_desc->len; + if (!is_smcd && conn->sndbuf_desc->is_vm) { smcr_buf_unuse(conn->sndbuf_desc, false, lgr); } else { - memzero_explicit(conn->sndbuf_desc->cpu_addr, conn->sndbuf_desc->len); + memzero_explicit(conn->sndbuf_desc->cpu_addr, bufsize); WRITE_ONCE(conn->sndbuf_desc->used, 0); } + SMC_STAT_RMB_SIZE(smc, is_smcd, false, false, bufsize); } if (conn->rmb_desc) { - if (!lgr->is_smcd) { + bufsize = conn->rmb_desc->len; + if (!is_smcd) { smcr_buf_unuse(conn->rmb_desc, true, lgr); } else { - memzero_explicit(conn->rmb_desc->cpu_addr, - conn->rmb_desc->len + sizeof(struct smcd_cdc_msg)); + bufsize += sizeof(struct smcd_cdc_msg); + memzero_explicit(conn->rmb_desc->cpu_addr, bufsize); WRITE_ONCE(conn->rmb_desc->used, 0); } + SMC_STAT_RMB_SIZE(smc, is_smcd, true, false, bufsize); } } @@ -2427,7 +2435,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list); if (buf_desc) { buf_desc->is_dma_need_sync = 0; - SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); + SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, true, bufsize); SMC_STAT_BUF_REUSE(smc, is_smcd, is_rmb); break; /* found reusable slot */ } @@ -2448,7 +2456,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) } SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); - SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); + SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, true, bufsize); buf_desc->used = 1; down_write(lock); smc_lgr_buf_list_add(lgr, is_rmb, buf_list, buf_desc); diff --git a/net/smc/smc_stats.c b/net/smc/smc_stats.c index ca14c0f3a07d7..e71b17d1e21cd 100644 --- a/net/smc/smc_stats.c +++ b/net/smc/smc_stats.c @@ -218,6 +218,12 @@ static int smc_nl_fill_stats_tech_data(struct sk_buff *skb, smc_tech->tx_bytes, SMC_NLA_STATS_PAD)) goto errattr; + if (nla_put_uint(skb, SMC_NLA_STATS_T_RX_RMB_USAGE, + smc_tech->rx_rmbuse)) + goto errattr; + if (nla_put_uint(skb, SMC_NLA_STATS_T_TX_RMB_USAGE, + smc_tech->tx_rmbuse)) + goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_CNT, smc_tech->rx_cnt, SMC_NLA_STATS_PAD)) diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h index e19177ce40923..571f9d9e78146 100644 --- a/net/smc/smc_stats.h +++ b/net/smc/smc_stats.h @@ -79,6 +79,8 @@ struct smc_stats_tech { u64 tx_bytes; u64 rx_cnt; u64 tx_cnt; + u64 rx_rmbuse; + u64 tx_rmbuse; }; struct smc_stats { @@ -135,38 +137,46 @@ do { \ } \ while (0) -#define SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _len) \ +#define SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _is_add, _len) \ do { \ + typeof(_smc_stats) stats = (_smc_stats); \ + typeof(_is_add) is_a = (_is_add); \ typeof(_len) _l = (_len); \ typeof(_tech) t = (_tech); \ int _pos; \ int m = SMC_BUF_MAX - 1; \ if (_l <= 0) \ break; \ - _pos = fls((_l - 1) >> 13); \ - _pos = (_pos <= m) ? _pos : m; \ - this_cpu_inc((*(_smc_stats)).smc[t].k ## _rmbsize.buf[_pos]); \ + if (is_a) { \ + _pos = fls((_l - 1) >> 13); \ + _pos = (_pos <= m) ? _pos : m; \ + this_cpu_inc((*stats).smc[t].k ## _rmbsize.buf[_pos]); \ + this_cpu_add((*stats).smc[t].k ## _rmbuse, _l); \ + } else { \ + this_cpu_sub((*stats).smc[t].k ## _rmbuse, _l); \ + } \ } \ while (0) #define SMC_STAT_RMB_SUB(_smc_stats, type, t, key) \ this_cpu_inc((*(_smc_stats)).smc[t].rmb ## _ ## key.type ## _cnt) -#define SMC_STAT_RMB_SIZE(_smc, _is_smcd, _is_rx, _len) \ +#define SMC_STAT_RMB_SIZE(_smc, _is_smcd, _is_rx, _is_add, _len) \ do { \ struct net *_net = sock_net(&(_smc)->sk); \ struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \ + typeof(_is_add) is_add = (_is_add); \ typeof(_is_smcd) is_d = (_is_smcd); \ typeof(_is_rx) is_r = (_is_rx); \ typeof(_len) l = (_len); \ if ((is_d) && (is_r)) \ - SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, rx, l); \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, rx, is_add, l); \ if ((is_d) && !(is_r)) \ - SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, tx, l); \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, tx, is_add, l); \ if (!(is_d) && (is_r)) \ - SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, rx, l); \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, rx, is_add, l); \ if (!(is_d) && !(is_r)) \ - SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, tx, l); \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, tx, is_add, l); \ } \ while (0) From 1eacdd71b3436b54d5fc8218c4bb0187d92a6892 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 20 Aug 2024 09:54:30 +0200 Subject: [PATCH 219/385] netfilter: nft_counter: Disable BH in nft_counter_offload_stats(). The sequence counter nft_counter_seq is a per-CPU counter. There is no lock associated with it. nft_counter_do_eval() is using the same counter and disables BH which suggest that it can be invoked from a softirq. This in turn means that nft_counter_offload_stats(), which disables only preemption, can be interrupted by nft_counter_do_eval() leading to two writer for one seqcount_t. This can lead to loosing stats or reading statistics while they are updated. Disable BH during stats update in nft_counter_offload_stats() to ensure one writer at a time. Fixes: b72920f6e4a9d ("netfilter: nftables: counter hardware offload support") Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_counter.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 291ed2026367e..16f40b503d379 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -265,7 +265,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr, struct nft_counter *this_cpu; seqcount_t *myseq; - preempt_disable(); + local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); myseq = this_cpu_ptr(&nft_counter_seq); @@ -273,7 +273,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr, this_cpu->packets += stats->pkts; this_cpu->bytes += stats->bytes; write_seqcount_end(myseq); - preempt_enable(); + local_bh_enable(); } void nft_counter_init_seqcount(void) From a0b39e2dc7017ac667b70bdeee5293e410fab2fb Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 20 Aug 2024 09:54:31 +0200 Subject: [PATCH 220/385] netfilter: nft_counter: Synchronize nft_counter_reset() against reader. nft_counter_reset() resets the counter by subtracting the previously retrieved value from the counter. This is a write operation on the counter and as such it requires to be performed with a write sequence of nft_counter_seq to serialize against its possible reader. Update the packets/ bytes within write-sequence of nft_counter_seq. Fixes: d84701ecbcd6a ("netfilter: nft_counter: rework atomic dump and reset") Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_counter.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 16f40b503d379..eab0dc66bee6b 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -107,11 +107,16 @@ static void nft_counter_reset(struct nft_counter_percpu_priv *priv, struct nft_counter *total) { struct nft_counter *this_cpu; + seqcount_t *myseq; local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); + myseq = this_cpu_ptr(&nft_counter_seq); + + write_seqcount_begin(myseq); this_cpu->packets -= total->packets; this_cpu->bytes -= total->bytes; + write_seqcount_end(myseq); local_bh_enable(); } From 7ea0522ef81a335c2d3a0ab1c8a4fab9a23c4a03 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 20 Aug 2024 11:56:12 +0200 Subject: [PATCH 221/385] netfilter: nf_tables: pass context structure to nft_parse_register_load Mechanical transformation, no logical changes intended. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 3 ++- net/bridge/netfilter/nft_meta_bridge.c | 2 +- net/ipv4/netfilter/nft_dup_ipv4.c | 4 ++-- net/ipv6/netfilter/nft_dup_ipv6.c | 4 ++-- net/netfilter/nf_tables_api.c | 3 ++- net/netfilter/nft_bitwise.c | 4 ++-- net/netfilter/nft_byteorder.c | 2 +- net/netfilter/nft_cmp.c | 6 +++--- net/netfilter/nft_ct.c | 2 +- net/netfilter/nft_dup_netdev.c | 2 +- net/netfilter/nft_dynset.c | 4 ++-- net/netfilter/nft_exthdr.c | 2 +- net/netfilter/nft_fwd_netdev.c | 6 +++--- net/netfilter/nft_hash.c | 2 +- net/netfilter/nft_lookup.c | 2 +- net/netfilter/nft_masq.c | 4 ++-- net/netfilter/nft_meta.c | 2 +- net/netfilter/nft_nat.c | 8 ++++---- net/netfilter/nft_objref.c | 2 +- net/netfilter/nft_payload.c | 2 +- net/netfilter/nft_queue.c | 2 +- net/netfilter/nft_range.c | 2 +- net/netfilter/nft_redir.c | 4 ++-- net/netfilter/nft_tproxy.c | 4 ++-- 24 files changed, 40 insertions(+), 38 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 2be4738eae1cc..573995e7a27ea 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -254,7 +254,8 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type) int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest); int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); -int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len); +int nft_parse_register_load(const struct nft_ctx *ctx, + const struct nlattr *attr, u8 *sreg, u32 len); int nft_parse_register_store(const struct nft_ctx *ctx, const struct nlattr *attr, u8 *dreg, const struct nft_data *data, diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index bd4d1b4d745f6..4d8e15927217b 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -142,7 +142,7 @@ static int nft_meta_bridge_set_init(const struct nft_ctx *ctx, } priv->len = len; - err = nft_parse_register_load(tb[NFTA_META_SREG], &priv->sreg, len); + err = nft_parse_register_load(ctx, tb[NFTA_META_SREG], &priv->sreg, len); if (err < 0) return err; diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index a522c3a3be523..ef5dd88107ddb 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -40,13 +40,13 @@ static int nft_dup_ipv4_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_ADDR] == NULL) return -EINVAL; - err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, + err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, sizeof(struct in_addr)); if (err < 0) return err; if (tb[NFTA_DUP_SREG_DEV]) - err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], + err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, sizeof(int)); return err; diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index c82f3fdd4a65d..492a811828a71 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -38,13 +38,13 @@ static int nft_dup_ipv6_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_ADDR] == NULL) return -EINVAL; - err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, + err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, sizeof(struct in6_addr)); if (err < 0) return err; if (tb[NFTA_DUP_SREG_DEV]) - err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], + err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, sizeof(int)); return err; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c85d037a363b2..d05fc17bb9b71 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -11038,7 +11038,8 @@ static int nft_validate_register_load(enum nft_registers reg, unsigned int len) return 0; } -int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len) +int nft_parse_register_load(const struct nft_ctx *ctx, + const struct nlattr *attr, u8 *sreg, u32 len) { u32 reg; int err; diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index ca857afbf0616..7de95674fd8c4 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -171,7 +171,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, priv->len = len; - err = nft_parse_register_load(tb[NFTA_BITWISE_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_BITWISE_SREG], &priv->sreg, priv->len); if (err < 0) return err; @@ -365,7 +365,7 @@ static int nft_bitwise_fast_init(const struct nft_ctx *ctx, struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr); int err; - err = nft_parse_register_load(tb[NFTA_BITWISE_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_BITWISE_SREG], &priv->sreg, sizeof(u32)); if (err < 0) return err; diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index f6e791a681015..2f82a444d21bf 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -139,7 +139,7 @@ static int nft_byteorder_init(const struct nft_ctx *ctx, priv->len = len; - err = nft_parse_register_load(tb[NFTA_BYTEORDER_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_BYTEORDER_SREG], &priv->sreg, priv->len); if (err < 0) return err; diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index cd4652259095c..2605f43737bc9 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -83,7 +83,7 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (err < 0) return err; - err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len); + err = nft_parse_register_load(ctx, tb[NFTA_CMP_SREG], &priv->sreg, desc.len); if (err < 0) return err; @@ -222,7 +222,7 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx, if (err < 0) return err; - err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len); + err = nft_parse_register_load(ctx, tb[NFTA_CMP_SREG], &priv->sreg, desc.len); if (err < 0) return err; @@ -323,7 +323,7 @@ static int nft_cmp16_fast_init(const struct nft_ctx *ctx, if (err < 0) return err; - err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len); + err = nft_parse_register_load(ctx, tb[NFTA_CMP_SREG], &priv->sreg, desc.len); if (err < 0) return err; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 452ed94c3a4d8..67a41cd2baaff 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -606,7 +606,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, } priv->len = len; - err = nft_parse_register_load(tb[NFTA_CT_SREG], &priv->sreg, len); + err = nft_parse_register_load(ctx, tb[NFTA_CT_SREG], &priv->sreg, len); if (err < 0) goto err1; diff --git a/net/netfilter/nft_dup_netdev.c b/net/netfilter/nft_dup_netdev.c index e5739a59ebf10..0573f96ce0791 100644 --- a/net/netfilter/nft_dup_netdev.c +++ b/net/netfilter/nft_dup_netdev.c @@ -40,7 +40,7 @@ static int nft_dup_netdev_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_DEV] == NULL) return -EINVAL; - return nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, + return nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, sizeof(int)); } diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index b4ada3ab21679..6920df7542656 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -215,7 +215,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx, return err; } - err = nft_parse_register_load(tb[NFTA_DYNSET_SREG_KEY], &priv->sreg_key, + err = nft_parse_register_load(ctx, tb[NFTA_DYNSET_SREG_KEY], &priv->sreg_key, set->klen); if (err < 0) return err; @@ -226,7 +226,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (set->dtype == NFT_DATA_VERDICT) return -EOPNOTSUPP; - err = nft_parse_register_load(tb[NFTA_DYNSET_SREG_DATA], + err = nft_parse_register_load(ctx, tb[NFTA_DYNSET_SREG_DATA], &priv->sreg_data, set->dlen); if (err < 0) return err; diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 6eb571d0c3fdf..6bfd335162414 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -588,7 +588,7 @@ static int nft_exthdr_tcp_set_init(const struct nft_ctx *ctx, priv->flags = flags; priv->op = op; - return nft_parse_register_load(tb[NFTA_EXTHDR_SREG], &priv->sreg, + return nft_parse_register_load(ctx, tb[NFTA_EXTHDR_SREG], &priv->sreg, priv->len); } diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index 358e742afad70..c83a794025f92 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -52,7 +52,7 @@ static int nft_fwd_netdev_init(const struct nft_ctx *ctx, if (tb[NFTA_FWD_SREG_DEV] == NULL) return -EINVAL; - return nft_parse_register_load(tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, + return nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, sizeof(int)); } @@ -178,12 +178,12 @@ static int nft_fwd_neigh_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - err = nft_parse_register_load(tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, + err = nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, sizeof(int)); if (err < 0) return err; - return nft_parse_register_load(tb[NFTA_FWD_SREG_ADDR], &priv->sreg_addr, + return nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_ADDR], &priv->sreg_addr, addr_len); } diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 868d68302d224..5d034bbb6913c 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -92,7 +92,7 @@ static int nft_jhash_init(const struct nft_ctx *ctx, priv->len = len; - err = nft_parse_register_load(tb[NFTA_HASH_SREG], &priv->sreg, len); + err = nft_parse_register_load(ctx, tb[NFTA_HASH_SREG], &priv->sreg, len); if (err < 0) return err; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index f3080fa1b2263..580e4b1deb9ba 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -113,7 +113,7 @@ static int nft_lookup_init(const struct nft_ctx *ctx, if (IS_ERR(set)) return PTR_ERR(set); - err = nft_parse_register_load(tb[NFTA_LOOKUP_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_LOOKUP_SREG], &priv->sreg, set->klen); if (err < 0) return err; diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 8a14aaca93bbd..cb43c72a8c2ad 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -52,13 +52,13 @@ static int nft_masq_init(const struct nft_ctx *ctx, priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS])); if (tb[NFTA_MASQ_REG_PROTO_MIN]) { - err = nft_parse_register_load(tb[NFTA_MASQ_REG_PROTO_MIN], + err = nft_parse_register_load(ctx, tb[NFTA_MASQ_REG_PROTO_MIN], &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_MASQ_REG_PROTO_MAX]) { - err = nft_parse_register_load(tb[NFTA_MASQ_REG_PROTO_MAX], + err = nft_parse_register_load(ctx, tb[NFTA_MASQ_REG_PROTO_MAX], &priv->sreg_proto_max, plen); if (err < 0) diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 9139ce38ea7b9..0214ad1ced2fe 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -657,7 +657,7 @@ int nft_meta_set_init(const struct nft_ctx *ctx, } priv->len = len; - err = nft_parse_register_load(tb[NFTA_META_SREG], &priv->sreg, len); + err = nft_parse_register_load(ctx, tb[NFTA_META_SREG], &priv->sreg, len); if (err < 0) return err; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 808f5802c2704..983dd937fe029 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -214,13 +214,13 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, priv->family = family; if (tb[NFTA_NAT_REG_ADDR_MIN]) { - err = nft_parse_register_load(tb[NFTA_NAT_REG_ADDR_MIN], + err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_ADDR_MIN], &priv->sreg_addr_min, alen); if (err < 0) return err; if (tb[NFTA_NAT_REG_ADDR_MAX]) { - err = nft_parse_register_load(tb[NFTA_NAT_REG_ADDR_MAX], + err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_ADDR_MAX], &priv->sreg_addr_max, alen); if (err < 0) @@ -234,13 +234,13 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, plen = sizeof_field(struct nf_nat_range, min_proto.all); if (tb[NFTA_NAT_REG_PROTO_MIN]) { - err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MIN], + err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_PROTO_MIN], &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_NAT_REG_PROTO_MAX]) { - err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MAX], + err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_PROTO_MAX], &priv->sreg_proto_max, plen); if (err < 0) diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 509011b1ef597..09da7a3f9f967 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -143,7 +143,7 @@ static int nft_objref_map_init(const struct nft_ctx *ctx, if (!(set->flags & NFT_SET_OBJECT)) return -EINVAL; - err = nft_parse_register_load(tb[NFTA_OBJREF_SET_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_OBJREF_SET_SREG], &priv->sreg, set->klen); if (err < 0) return err; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 50429cbd42da4..330609a76fb20 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -981,7 +981,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, } priv->csum_type = csum_type; - return nft_parse_register_load(tb[NFTA_PAYLOAD_SREG], &priv->sreg, + return nft_parse_register_load(ctx, tb[NFTA_PAYLOAD_SREG], &priv->sreg, priv->len); } diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index b2b8127c8d438..44e6817e6e29b 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -136,7 +136,7 @@ static int nft_queue_sreg_init(const struct nft_ctx *ctx, struct nft_queue *priv = nft_expr_priv(expr); int err; - err = nft_parse_register_load(tb[NFTA_QUEUE_SREG_QNUM], + err = nft_parse_register_load(ctx, tb[NFTA_QUEUE_SREG_QNUM], &priv->sreg_qnum, sizeof(u32)); if (err < 0) return err; diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index 51ae64cd268f4..ea382f7bbd78d 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -83,7 +83,7 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr goto err2; } - err = nft_parse_register_load(tb[NFTA_RANGE_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_RANGE_SREG], &priv->sreg, desc_from.len); if (err < 0) goto err2; diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index a58bd8d291ff2..6568cc264078d 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -51,13 +51,13 @@ static int nft_redir_init(const struct nft_ctx *ctx, plen = sizeof_field(struct nf_nat_range, min_proto.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { - err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MIN], + err = nft_parse_register_load(ctx, tb[NFTA_REDIR_REG_PROTO_MIN], &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_REDIR_REG_PROTO_MAX]) { - err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MAX], + err = nft_parse_register_load(ctx, tb[NFTA_REDIR_REG_PROTO_MAX], &priv->sreg_proto_max, plen); if (err < 0) diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index 71412adb73d41..1b691393d8b1d 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -254,14 +254,14 @@ static int nft_tproxy_init(const struct nft_ctx *ctx, } if (tb[NFTA_TPROXY_REG_ADDR]) { - err = nft_parse_register_load(tb[NFTA_TPROXY_REG_ADDR], + err = nft_parse_register_load(ctx, tb[NFTA_TPROXY_REG_ADDR], &priv->sreg_addr, alen); if (err < 0) return err; } if (tb[NFTA_TPROXY_REG_PORT]) { - err = nft_parse_register_load(tb[NFTA_TPROXY_REG_PORT], + err = nft_parse_register_load(ctx, tb[NFTA_TPROXY_REG_PORT], &priv->sreg_port, sizeof(u16)); if (err < 0) return err; From 14fb07130c7ddd257e30079b87499b3f89097b09 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 20 Aug 2024 11:56:13 +0200 Subject: [PATCH 222/385] netfilter: nf_tables: allow loads only when register is initialized Reject rules where a load occurs from a register that has not seen a store early in the same rule. commit 4c905f6740a3 ("netfilter: nf_tables: initialize registers in nft_do_chain()") had to add a unconditional memset to the nftables register space to avoid leaking stack information to userspace. This memset shows up in benchmarks. After this change, this commit can be reverted again. Note that this breaks userspace compatibility, because theoretically you can do rule 1: reg2 := meta load iif, reg2 == 1 jump ... rule 2: reg2 == 2 jump ... // read access with no store in this rule ... after this change this is rejected. Neither nftables nor iptables-nft generate such rules, each rule is always standalone. This resuts in a small increase of nft_ctx structure by sizeof(long). To cope with hypothetical rulesets like the example above one could emit on-demand "reg[x] = 0" store when generating the datapath blob in nf_tables_commit_chain_prepare(). A patch that does this is linked to below. For now, lets disable this. In nf_tables, a rule is the smallest unit that can be replaced from userspace, i.e. a hypothetical ruleset that relies on earlier initialisations of registers can't be changed at will as register usage would need to be coordinated. Link: https://lore.kernel.org/netfilter-devel/20240627135330.17039-4-fw@strlen.de/ Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 1 + net/netfilter/nf_tables_api.c | 38 +++++++++++++++++++++++++++---- 2 files changed, 35 insertions(+), 4 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 573995e7a27ea..1cc33d946d41f 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -221,6 +221,7 @@ struct nft_ctx { u8 family; u8 level; bool report; + DECLARE_BITMAP(reg_inited, NFT_REG32_NUM); }; enum nft_data_desc_flags { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d05fc17bb9b71..904f2e25b4a4d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -146,6 +146,8 @@ static void nft_ctx_init(struct nft_ctx *ctx, ctx->report = nlmsg_report(nlh); ctx->flags = nlh->nlmsg_flags; ctx->seq = nlh->nlmsg_seq; + + bitmap_zero(ctx->reg_inited, NFT_REG32_NUM); } static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx, @@ -11041,8 +11043,8 @@ static int nft_validate_register_load(enum nft_registers reg, unsigned int len) int nft_parse_register_load(const struct nft_ctx *ctx, const struct nlattr *attr, u8 *sreg, u32 len) { - u32 reg; - int err; + int err, invalid_reg; + u32 reg, next_register; err = nft_parse_register(attr, ®); if (err < 0) @@ -11052,11 +11054,36 @@ int nft_parse_register_load(const struct nft_ctx *ctx, if (err < 0) return err; + next_register = DIV_ROUND_UP(len, NFT_REG32_SIZE) + reg; + + /* Can't happen: nft_validate_register_load() should have failed */ + if (WARN_ON_ONCE(next_register > NFT_REG32_NUM)) + return -EINVAL; + + /* find first register that did not see an earlier store. */ + invalid_reg = find_next_zero_bit(ctx->reg_inited, NFT_REG32_NUM, reg); + + /* invalid register within the range that we're loading from? */ + if (invalid_reg < next_register) + return -ENODATA; + *sreg = reg; return 0; } EXPORT_SYMBOL_GPL(nft_parse_register_load); +static void nft_saw_register_store(const struct nft_ctx *__ctx, + int reg, unsigned int len) +{ + unsigned int registers = DIV_ROUND_UP(len, NFT_REG32_SIZE); + struct nft_ctx *ctx = (struct nft_ctx *)__ctx; + + if (WARN_ON_ONCE(len == 0 || reg < 0)) + return; + + bitmap_set(ctx->reg_inited, reg, registers); +} + static int nft_validate_register_store(const struct nft_ctx *ctx, enum nft_registers reg, const struct nft_data *data, @@ -11078,7 +11105,7 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, return err; } - return 0; + break; default: if (type != NFT_DATA_VALUE) return -EINVAL; @@ -11091,8 +11118,11 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, sizeof_field(struct nft_regs, data)) return -ERANGE; - return 0; + break; } + + nft_saw_register_store(ctx, reg, len); + return 0; } int nft_parse_register_store(const struct nft_ctx *ctx, From c88baabf16d1ef74ab8832de9761226406af5507 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 20 Aug 2024 11:56:14 +0200 Subject: [PATCH 223/385] netfilter: nf_tables: don't initialize registers in nft_do_chain() revert commit 4c905f6740a3 ("netfilter: nf_tables: initialize registers in nft_do_chain()"). Previous patch makes sure that loads from uninitialized registers are detected from the control plane. in this case rule blob auto-zeroes registers. Thus the explicit zeroing is not needed anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index a48d5f0e2f3e1..75598520b0fa0 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -256,7 +256,7 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) const struct net *net = nft_net(pkt); const struct nft_expr *expr, *last; const struct nft_rule_dp *rule; - struct nft_regs regs = {}; + struct nft_regs regs; unsigned int stackptr = 0; struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE]; bool genbit = READ_ONCE(net->nft.gencursor); From 4b3e33fcc38f7750604b065c55a43e94c5bc3145 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Thu, 15 Aug 2024 17:14:16 +0200 Subject: [PATCH 224/385] ip6_tunnel: Fix broken GRO GRO code checks for matching layer 2 headers to see, if packet belongs to the same flow and because ip6 tunnel set dev->hard_header_len this check fails in cases, where it shouldn't. To fix this don't set hard_header_len, but use needed_headroom like ipv4/ip_tunnel.c does. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Thomas Bogendoerfer Link: https://patch.msgid.link/20240815151419.109864-1-tbogendoerfer@suse.de Signed-off-by: Paolo Abeni --- net/ipv6/ip6_tunnel.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 9dee0c1279554..87dfb565a9f81 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1507,7 +1507,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) tdev = __dev_get_by_index(t->net, p->link); if (tdev) { - dev->hard_header_len = tdev->hard_header_len + t_hlen; + dev->needed_headroom = tdev->hard_header_len + + tdev->needed_headroom + t_hlen; mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU); mtu = mtu - t_hlen; @@ -1731,7 +1732,9 @@ ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr, int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { struct ip6_tnl *tnl = netdev_priv(dev); + int t_hlen; + t_hlen = tnl->hlen + sizeof(struct ipv6hdr); if (tnl->parms.proto == IPPROTO_IPV6) { if (new_mtu < IPV6_MIN_MTU) return -EINVAL; @@ -1740,10 +1743,10 @@ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; } if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) { - if (new_mtu > IP6_MAX_MTU - dev->hard_header_len) + if (new_mtu > IP6_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } else { - if (new_mtu > IP_MAX_MTU - dev->hard_header_len) + if (new_mtu > IP_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); @@ -1887,12 +1890,11 @@ ip6_tnl_dev_init_gen(struct net_device *dev) t_hlen = t->hlen + sizeof(struct ipv6hdr); dev->type = ARPHRD_TUNNEL6; - dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len; + dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len - t_hlen; netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); From 8fed54758cd248cd311a2b5c1e180abef1866237 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 14 Aug 2024 15:52:22 +0300 Subject: [PATCH 225/385] ipv4: Mask upper DSCP bits and ECN bits in NETLINK_FIB_LOOKUP family The NETLINK_FIB_LOOKUP netlink family can be used to perform a FIB lookup according to user provided parameters and communicate the result back to user space. However, unlike other users of the FIB lookup API, the upper DSCP bits and the ECN bits of the DS field are not masked, which can result in the wrong result being returned. Solve this by masking the upper DSCP bits and the ECN bits using IPTOS_RT_MASK. The structure that communicates the request and the response is not exported to user space, so it is unlikely that this netlink family is actually in use [1]. [1] https://lore.kernel.org/netdev/ZpqpB8vJU%2FQ6LSqa@debian/ Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Signed-off-by: Paolo Abeni --- net/ipv4/fib_frontend.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 7ad2cafb92763..da540ddb7af65 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1343,7 +1343,7 @@ static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn) struct flowi4 fl4 = { .flowi4_mark = frn->fl_mark, .daddr = frn->fl_addr, - .flowi4_tos = frn->fl_tos, + .flowi4_tos = frn->fl_tos & IPTOS_RT_MASK, .flowi4_scope = frn->fl_scope, }; struct fib_table *tb; From 548a2029eb6668a47e9bc86a7ded3d33a738aa0c Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 14 Aug 2024 15:52:23 +0300 Subject: [PATCH 226/385] netfilter: nft_fib: Mask upper DSCP bits before FIB lookup As part of its functionality, the nftables FIB expression module performs a FIB lookup, but unlike other users of the FIB lookup API, it does so without masking the upper DSCP bits. In particular, this differs from the equivalent iptables match ("rpfilter") that does mask the upper DSCP bits before the FIB lookup. Align the module to other users of the FIB lookup API and mask the upper DSCP bits using IPTOS_RT_MASK before the lookup. No regressions in nft_fib.sh: # ./nft_fib.sh PASS: fib expression did not cause unwanted packet drops PASS: fib expression did drop packets for 1.1.1.1 PASS: fib expression did drop packets for 1c3::c01d PASS: fib expression forward check with policy based routing Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Signed-off-by: Paolo Abeni --- net/ipv4/netfilter/nft_fib_ipv4.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index 9eee535c64dd4..df94bc28c3d79 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -22,8 +22,6 @@ static __be32 get_saddr(__be32 addr) return addr; } -#define DSCP_BITS 0xfc - void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { @@ -110,7 +108,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, if (priv->flags & NFTA_FIB_F_MARK) fl4.flowi4_mark = pkt->skb->mark; - fl4.flowi4_tos = iph->tos & DSCP_BITS; + fl4.flowi4_tos = iph->tos & IPTOS_RT_MASK; if (priv->flags & NFTA_FIB_F_DADDR) { fl4.daddr = iph->daddr; From 1fa3314c14c6a20d098991a0a6980f9b18b2f930 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 14 Aug 2024 15:52:24 +0300 Subject: [PATCH 227/385] ipv4: Centralize TOS matching The TOS field in the IPv4 flow information structure ('flowi4_tos') is matched by the kernel against the TOS selector in IPv4 rules and routes. The field is initialized differently by different call sites. Some treat it as DSCP (RFC 2474) and initialize all six DSCP bits, some treat it as RFC 1349 TOS and initialize it using RT_TOS() and some treat it as RFC 791 TOS and initialize it using IPTOS_RT_MASK. What is common to all these call sites is that they all initialize the lower three DSCP bits, which fits the TOS definition in the initial IPv4 specification (RFC 791). Therefore, the kernel only allows configuring IPv4 FIB rules that match on the lower three DSCP bits which are always guaranteed to be initialized by all call sites: # ip -4 rule add tos 0x1c table 100 # ip -4 rule add tos 0x3c table 100 Error: Invalid tos. While this works, it is unlikely to be very useful. RFC 791 that initially defined the TOS and IP precedence fields was updated by RFC 2474 over twenty five years ago where these fields were replaced by a single six bits DSCP field. Extending FIB rules to match on DSCP can be done by adding a new DSCP selector while maintaining the existing semantics of the TOS selector for applications that rely on that. A prerequisite for allowing FIB rules to match on DSCP is to adjust all the call sites to initialize the high order DSCP bits and remove their masking along the path to the core where the field is matched on. However, making this change alone will result in a behavior change. For example, a forwarded IPv4 packet with a DS field of 0xfc will no longer match a FIB rule that was configured with 'tos 0x1c'. This behavior change can be avoided by masking the upper three DSCP bits in 'flowi4_tos' before comparing it against the TOS selectors in FIB rules and routes. Implement the above by adding a new function that checks whether a given DSCP value matches the one specified in the IPv4 flow information structure and invoke it from the three places that currently match on 'flowi4_tos'. Use RT_TOS() for the masking of 'flowi4_tos' instead of IPTOS_RT_MASK since the latter is not uAPI and we should be able to remove it at some point. Include in since the former defines IPTOS_TOS_MASK which is used in the definition of RT_TOS() in . No regressions in FIB tests: # ./fib_tests.sh [...] Tests passed: 218 Tests failed: 0 And FIB rule tests: # ./fib_rule_tests.sh [...] Tests passed: 116 Tests failed: 0 Signed-off-by: Ido Schimmel Signed-off-by: Paolo Abeni --- include/net/ip_fib.h | 6 ++++++ include/uapi/linux/in_route.h | 2 ++ net/ipv4/fib_rules.c | 2 +- net/ipv4/fib_semantics.c | 3 +-- net/ipv4/fib_trie.c | 3 +-- 5 files changed, 11 insertions(+), 5 deletions(-) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 72af2f223e591..269ec10f63e45 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -22,6 +22,7 @@ #include #include #include +#include struct fib_config { u8 fc_dst_len; @@ -434,6 +435,11 @@ static inline bool fib4_rules_early_flow_dissect(struct net *net, #endif /* CONFIG_IP_MULTIPLE_TABLES */ +static inline bool fib_dscp_masked_match(dscp_t dscp, const struct flowi4 *fl4) +{ + return dscp == inet_dsfield_to_dscp(RT_TOS(fl4->flowi4_tos)); +} + /* Exported by fib_frontend.c */ extern const struct nla_policy rtm_ipv4_policy[]; void ip_fib_init(void); diff --git a/include/uapi/linux/in_route.h b/include/uapi/linux/in_route.h index 0cc2c23b47f84..10bdd7e7107fa 100644 --- a/include/uapi/linux/in_route.h +++ b/include/uapi/linux/in_route.h @@ -2,6 +2,8 @@ #ifndef _LINUX_IN_ROUTE_H #define _LINUX_IN_ROUTE_H +#include + /* IPv4 routing cache flags */ #define RTCF_DEAD RTNH_F_DEAD diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 5bdd1c0160094..c26776b71e97f 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -186,7 +186,7 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule, ((daddr ^ r->dst) & r->dstmask)) return 0; - if (r->dscp && r->dscp != inet_dsfield_to_dscp(fl4->flowi4_tos)) + if (r->dscp && !fib_dscp_masked_match(r->dscp, fl4)) return 0; if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto)) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 2b57cd2b96e2a..0f70341cb8b5e 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -2066,8 +2066,7 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) if (fa->fa_slen != slen) continue; - if (fa->fa_dscp && - fa->fa_dscp != inet_dsfield_to_dscp(flp->flowi4_tos)) + if (fa->fa_dscp && !fib_dscp_masked_match(fa->fa_dscp, flp)) continue; if (fa->tb_id != tb->tb_id) continue; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 8f30e3f00b7f2..09e31757e96c7 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1580,8 +1580,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, if (index >= (1ul << fa->fa_slen)) continue; } - if (fa->fa_dscp && - inet_dscp_to_dsfield(fa->fa_dscp) != flp->flowi4_tos) + if (fa->fa_dscp && !fib_dscp_masked_match(fa->fa_dscp, flp)) continue; /* Paired with WRITE_ONCE() in fib_release_info() */ if (READ_ONCE(fi->fib_dead)) From 797653865b982d53ecca517dd2b0ffb8bd967022 Mon Sep 17 00:00:00 2001 From: Zhang Zekun Date: Fri, 16 Aug 2024 09:58:37 +0800 Subject: [PATCH 228/385] net: ethernet: ibm: Simpify code with for_each_child_of_node() for_each_child_of_node can help to iterate through the device_node, and we don't need to use while loop. No functional change with this conversion. Signed-off-by: Zhang Zekun Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240816015837.109627-1-zhangzekun11@huawei.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/ibm/ehea/ehea_main.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index 1e29e5c9a2dfb..c41c3f1cc506f 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -3063,14 +3063,13 @@ static void ehea_shutdown_single_port(struct ehea_port *port) static int ehea_setup_ports(struct ehea_adapter *adapter) { struct device_node *lhea_dn; - struct device_node *eth_dn = NULL; + struct device_node *eth_dn; const u32 *dn_log_port_id; int i = 0; lhea_dn = adapter->ofdev->dev.of_node; - while ((eth_dn = of_get_next_child(lhea_dn, eth_dn))) { - + for_each_child_of_node(lhea_dn, eth_dn) { dn_log_port_id = of_get_property(eth_dn, "ibm,hea-port-no", NULL); if (!dn_log_port_id) { @@ -3102,12 +3101,11 @@ static struct device_node *ehea_get_eth_dn(struct ehea_adapter *adapter, u32 logical_port_id) { struct device_node *lhea_dn; - struct device_node *eth_dn = NULL; + struct device_node *eth_dn; const u32 *dn_log_port_id; lhea_dn = adapter->ofdev->dev.of_node; - while ((eth_dn = of_get_next_child(lhea_dn, eth_dn))) { - + for_each_child_of_node(lhea_dn, eth_dn) { dn_log_port_id = of_get_property(eth_dn, "ibm,hea-port-no", NULL); if (dn_log_port_id) From fc59b9a5f7201b9f7272944596113a82cc7773d5 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 16 Aug 2024 14:48:10 +0300 Subject: [PATCH 229/385] bonding: fix bond_ipsec_offload_ok return type Fix the return type which should be bool. Fixes: 955b785ec6b3 ("bonding: fix suspicious RCU usage in bond_ipsec_offload_ok()") Signed-off-by: Nikolay Aleksandrov Reviewed-by: Hangbin Liu Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_main.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1cd92c12e7824..85b5868deeeaf 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -599,34 +599,28 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) struct net_device *real_dev; struct slave *curr_active; struct bonding *bond; - int err; + bool ok = false; bond = netdev_priv(bond_dev); rcu_read_lock(); curr_active = rcu_dereference(bond->curr_active_slave); real_dev = curr_active->dev; - if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { - err = false; + if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) goto out; - } - if (!xs->xso.real_dev) { - err = false; + if (!xs->xso.real_dev) goto out; - } if (!real_dev->xfrmdev_ops || !real_dev->xfrmdev_ops->xdo_dev_offload_ok || - netif_is_bond_master(real_dev)) { - err = false; + netif_is_bond_master(real_dev)) goto out; - } - err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); + ok = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs); out: rcu_read_unlock(); - return err; + return ok; } static const struct xfrmdev_ops bond_xfrmdev_ops = { From 95c90e4ad89d493a7a14fa200082e466e2548f9d Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 16 Aug 2024 14:48:11 +0300 Subject: [PATCH 230/385] bonding: fix null pointer deref in bond_ipsec_offload_ok We must check if there is an active slave before dereferencing the pointer. Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Nikolay Aleksandrov Reviewed-by: Hangbin Liu Reviewed-by: Eric Dumazet Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 85b5868deeeaf..65ddb71eebcda 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -604,6 +604,8 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) bond = netdev_priv(bond_dev); rcu_read_lock(); curr_active = rcu_dereference(bond->curr_active_slave); + if (!curr_active) + goto out; real_dev = curr_active->dev; if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) From f8cde9805981c50d0c029063dc7d82821806fc44 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 16 Aug 2024 14:48:12 +0300 Subject: [PATCH 231/385] bonding: fix xfrm real_dev null pointer dereference We shouldn't set real_dev to NULL because packets can be in transit and xfrm might call xdo_dev_offload_ok() in parallel. All callbacks assume real_dev is set. Example trace: kernel: BUG: unable to handle page fault for address: 0000000000001030 kernel: bond0: (slave eni0np1): making interface the new active one kernel: #PF: supervisor write access in kernel mode kernel: #PF: error_code(0x0002) - not-present page kernel: PGD 0 P4D 0 kernel: Oops: 0002 [#1] PREEMPT SMP kernel: CPU: 4 PID: 2237 Comm: ping Not tainted 6.7.7+ #12 kernel: Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-2.fc40 04/01/2014 kernel: RIP: 0010:nsim_ipsec_offload_ok+0xc/0x20 [netdevsim] kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA kernel: Code: e0 0f 0b 48 83 7f 38 00 74 de 0f 0b 48 8b 47 08 48 8b 37 48 8b 78 40 e9 b2 e5 9a d7 66 90 0f 1f 44 00 00 48 8b 86 80 02 00 00 <83> 80 30 10 00 00 01 b8 01 00 00 00 c3 0f 1f 80 00 00 00 00 0f 1f kernel: bond0: (slave eni0np1): making interface the new active one kernel: RSP: 0018:ffffabde81553b98 EFLAGS: 00010246 kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA kernel: kernel: RAX: 0000000000000000 RBX: ffff9eb404e74900 RCX: ffff9eb403d97c60 kernel: RDX: ffffffffc090de10 RSI: ffff9eb404e74900 RDI: ffff9eb3c5de9e00 kernel: RBP: ffff9eb3c0a42000 R08: 0000000000000010 R09: 0000000000000014 kernel: R10: 7974203030303030 R11: 3030303030303030 R12: 0000000000000000 kernel: R13: ffff9eb3c5de9e00 R14: ffffabde81553cc8 R15: ffff9eb404c53000 kernel: FS: 00007f2a77a3ad00(0000) GS:ffff9eb43bd00000(0000) knlGS:0000000000000000 kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 kernel: CR2: 0000000000001030 CR3: 00000001122ab000 CR4: 0000000000350ef0 kernel: bond0: (slave eni0np1): making interface the new active one kernel: Call Trace: kernel: kernel: ? __die+0x1f/0x60 kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA kernel: ? page_fault_oops+0x142/0x4c0 kernel: ? do_user_addr_fault+0x65/0x670 kernel: ? kvm_read_and_reset_apf_flags+0x3b/0x50 kernel: bond0: (slave eni0np1): making interface the new active one kernel: ? exc_page_fault+0x7b/0x180 kernel: ? asm_exc_page_fault+0x22/0x30 kernel: ? nsim_bpf_uninit+0x50/0x50 [netdevsim] kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA kernel: ? nsim_ipsec_offload_ok+0xc/0x20 [netdevsim] kernel: bond0: (slave eni0np1): making interface the new active one kernel: bond_ipsec_offload_ok+0x7b/0x90 [bonding] kernel: xfrm_output+0x61/0x3b0 kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA kernel: ip_push_pending_frames+0x56/0x80 Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Nikolay Aleksandrov Reviewed-by: Hangbin Liu Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_main.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 65ddb71eebcda..f74bacf071fca 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -582,7 +582,6 @@ static void bond_ipsec_del_sa_all(struct bonding *bond) } else { slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs); } - ipsec->xs->xso.real_dev = NULL; } spin_unlock_bh(&bond->ipsec_lock); rcu_read_unlock(); From c4c5c5d2ef40a9f67a9241dc5422eac9ffe19547 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 16 Aug 2024 14:48:13 +0300 Subject: [PATCH 232/385] bonding: fix xfrm state handling when clearing active slave If the active slave is cleared manually the xfrm state is not flushed. This leads to xfrm add/del imbalance and adding the same state multiple times. For example when the device cannot handle anymore states we get: [ 1169.884811] bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA because it's filled with the same state after multiple active slave clearings. This change also has a few nice side effects: user-space gets a notification for the change, the old device gets its mac address and promisc/mcast adjusted properly. Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves") Signed-off-by: Nikolay Aleksandrov Reviewed-by: Hangbin Liu Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_options.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index bc80fb6397dcd..95d59a18c0223 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -936,7 +936,7 @@ static int bond_option_active_slave_set(struct bonding *bond, /* check to see if we are clearing active */ if (!slave_dev) { netdev_dbg(bond->dev, "Clearing current active slave\n"); - RCU_INIT_POINTER(bond->curr_active_slave, NULL); + bond_change_active_slave(bond, NULL); bond_select_active_slave(bond); } else { struct slave *old_active = rtnl_dereference(bond->curr_active_slave); From 50b2143356e888777fc5bca023c39f34f404613a Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Wed, 7 Aug 2024 12:53:24 +0200 Subject: [PATCH 233/385] ice: fix page reuse when PAGE_SIZE is over 8k Architectures that have PAGE_SIZE >= 8192 such as arm64 should act the same as x86 currently, meaning reuse of a page should only take place when no one else is busy with it. Do two things independently of underlying PAGE_SIZE: - store the page count under ice_rx_buf::pgcnt - then act upon its value vs ice_rx_buf::pagecnt_bias when making the decision regarding page reuse Fixes: 2b245cb29421 ("ice: Implement transmit and NAPI support") Signed-off-by: Maciej Fijalkowski Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_txrx.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 8d25b69812698..50211188c1a7a 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -837,16 +837,15 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) if (!dev_page_is_reusable(page)) return false; -#if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1)) return false; -#else +#if (PAGE_SIZE >= 8192) #define ICE_LAST_OFFSET \ (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_2048) if (rx_buf->page_offset > ICE_LAST_OFFSET) return false; -#endif /* PAGE_SIZE < 8192) */ +#endif /* PAGE_SIZE >= 8192) */ /* If we have drained the page fragment pool we need to update * the pagecnt_bias and page count so that we fully restock the @@ -949,12 +948,7 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, struct ice_rx_buf *rx_buf; rx_buf = &rx_ring->rx_buf[ntc]; - rx_buf->pgcnt = -#if (PAGE_SIZE < 8192) - page_count(rx_buf->page); -#else - 0; -#endif + rx_buf->pgcnt = page_count(rx_buf->page); prefetchw(rx_buf->page); if (!size) From b966ad832942b5a11e002f9b5ef102b08425b84a Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Wed, 7 Aug 2024 12:53:25 +0200 Subject: [PATCH 234/385] ice: fix ICE_LAST_OFFSET formula For bigger PAGE_SIZE archs, ice driver works on 3k Rx buffers. Therefore, ICE_LAST_OFFSET should take into account ICE_RXBUF_3072, not ICE_RXBUF_2048. Fixes: 7237f5b0dba4 ("ice: introduce legacy Rx flag") Suggested-by: Luiz Capitulino Signed-off-by: Maciej Fijalkowski Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 50211188c1a7a..4b690952bb403 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -842,7 +842,7 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) return false; #if (PAGE_SIZE >= 8192) #define ICE_LAST_OFFSET \ - (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_2048) + (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_3072) if (rx_buf->page_offset > ICE_LAST_OFFSET) return false; #endif /* PAGE_SIZE >= 8192) */ From d53d4dcce69be5773e2d0878c9899ebfbf58c393 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Wed, 7 Aug 2024 12:53:26 +0200 Subject: [PATCH 235/385] ice: fix truesize operations for PAGE_SIZE >= 8192 When working on multi-buffer packet on arch that has PAGE_SIZE >= 8192, truesize is calculated and stored in xdp_buff::frame_sz per each processed Rx buffer. This means that frame_sz will contain the truesize based on last received buffer, but commit 1dc1a7e7f410 ("ice: Centrallize Rx buffer recycling") assumed this value will be constant for each buffer, which breaks the page recycling scheme and mess up the way we update the page::page_offset. To fix this, let us work on constant truesize when PAGE_SIZE >= 8192 instead of basing this on size of a packet read from Rx descriptor. This way we can simplify the code and avoid calculating truesize per each received frame and on top of that when using xdp_update_skb_shared_info(), current formula for truesize update will be valid. This means ice_rx_frame_truesize() can be removed altogether. Furthermore, first call to it within ice_clean_rx_irq() for 4k PAGE_SIZE was redundant as xdp_buff::frame_sz is initialized via xdp_init_buff() in ice_vsi_cfg_rxq(). This should have been removed at the point where xdp_buff struct started to be a member of ice_rx_ring and it was no longer a stack based variable. There are two fixes tags as my understanding is that the first one exposed us to broken truesize and page_offset handling and then second introduced broken skb_shared_info update in ice_{construct,build}_skb(). Reported-and-tested-by: Luiz Capitulino Closes: https://lore.kernel.org/netdev/8f9e2a5c-fd30-4206-9311-946a06d031bb@redhat.com/ Fixes: 1dc1a7e7f410 ("ice: Centrallize Rx buffer recycling") Fixes: 2fba7dc5157b ("ice: Add support for XDP multi-buffer on Rx side") Signed-off-by: Maciej Fijalkowski Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_base.c | 21 ++++++++++++++- drivers/net/ethernet/intel/ice/ice_txrx.c | 33 ----------------------- 2 files changed, 20 insertions(+), 34 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 1facf179a96fd..f448d3a845642 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -512,6 +512,25 @@ static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring) xsk_pool_fill_cb(ring->xsk_pool, &desc); } +/** + * ice_get_frame_sz - calculate xdp_buff::frame_sz + * @rx_ring: the ring being configured + * + * Return frame size based on underlying PAGE_SIZE + */ +static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring) +{ + unsigned int frame_sz; + +#if (PAGE_SIZE >= 8192) + frame_sz = rx_ring->rx_buf_len; +#else + frame_sz = ice_rx_pg_size(rx_ring) / 2; +#endif + + return frame_sz; +} + /** * ice_vsi_cfg_rxq - Configure an Rx queue * @ring: the ring being configured @@ -576,7 +595,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) } } - xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq); + xdp_init_buff(&ring->xdp, ice_get_frame_sz(ring), &ring->xdp_rxq); ring->xdp.data = NULL; ring->xdp_ext.pkt_ctx = &ring->pkt_ctx; err = ice_setup_rx_ctx(ring); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 4b690952bb403..c9bc3f1add5d3 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -521,30 +521,6 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring) return -ENOMEM; } -/** - * ice_rx_frame_truesize - * @rx_ring: ptr to Rx ring - * @size: size - * - * calculate the truesize with taking into the account PAGE_SIZE of - * underlying arch - */ -static unsigned int -ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size) -{ - unsigned int truesize; - -#if (PAGE_SIZE < 8192) - truesize = ice_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */ -#else - truesize = rx_ring->rx_offset ? - SKB_DATA_ALIGN(rx_ring->rx_offset + size) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) : - SKB_DATA_ALIGN(size); -#endif - return truesize; -} - /** * ice_run_xdp - Executes an XDP program on initialized xdp_buff * @rx_ring: Rx ring @@ -1154,11 +1130,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) bool failure; u32 first; - /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ -#if (PAGE_SIZE < 8192) - xdp->frame_sz = ice_rx_frame_truesize(rx_ring, 0); -#endif - xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (xdp_prog) { xdp_ring = rx_ring->xdp_ring; @@ -1217,10 +1188,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) hard_start = page_address(rx_buf->page) + rx_buf->page_offset - offset; xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); -#if (PAGE_SIZE > 4096) - /* At larger PAGE_SIZE, frame_sz depend on len size */ - xdp->frame_sz = ice_rx_frame_truesize(rx_ring, size); -#endif xdp_buff_clear_frags_flag(xdp); } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { break; From 503ab6ee40fc103ea55cc9e50bb879e571d65aac Mon Sep 17 00:00:00 2001 From: Michal Swiatkowski Date: Mon, 19 Aug 2024 09:17:42 +0200 Subject: [PATCH 236/385] ice: use internal pf id instead of function number Use always the same pf id in devlink port number. When doing pass-through the PF to VM bus info func number can be any value. Fixes: 2ae0aa4758b0 ("ice: Move devlink port to PF/VF struct") Reviewed-by: Wojciech Drewek Suggested-by: Jiri Pirko Signed-off-by: Michal Swiatkowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/devlink/devlink_port.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c index 00fed5a61d62a..62ef8e2fb5f1b 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c @@ -337,7 +337,7 @@ int ice_devlink_create_pf_port(struct ice_pf *pf) return -EIO; attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - attrs.phys.port_number = pf->hw.bus.func; + attrs.phys.port_number = pf->hw.pf_id; /* As FW supports only port split options for whole device, * set port split options only for first PF. @@ -455,7 +455,7 @@ int ice_devlink_create_vf_port(struct ice_vf *vf) return -EINVAL; attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF; - attrs.pci_vf.pf = pf->hw.bus.func; + attrs.pci_vf.pf = pf->hw.pf_id; attrs.pci_vf.vf = vf->vf_id; ice_devlink_set_switch_id(pf, &attrs.switch_id); From c50e7475961c36ec4d21d60af055b32f9436b431 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Sat, 17 Aug 2024 09:52:46 +0300 Subject: [PATCH 237/385] dpaa2-switch: Fix error checking in dpaa2_switch_seed_bp() The dpaa2_switch_add_bufs() function returns the number of bufs that it was able to add. It returns BUFS_PER_CMD (7) for complete success or a smaller number if there are not enough pages available. However, the error checking is looking at the total number of bufs instead of the number which were added on this iteration. Thus the error checking only works correctly for the first iteration through the loop and subsequent iterations are always counted as a success. Fix this by checking only the bufs added in the current iteration. Fixes: 0b1b71370458 ("staging: dpaa2-switch: handle Rx path on control interface") Signed-off-by: Dan Carpenter Reviewed-by: Simon Horman Reviewed-by: Ioana Ciornei Tested-by: Ioana Ciornei Link: https://patch.msgid.link/eec27f30-b43f-42b6-b8ee-04a6f83423b6@stanley.mountain Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index a71f848adc054..a293b08f36d46 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -2638,13 +2638,14 @@ static int dpaa2_switch_refill_bp(struct ethsw_core *ethsw) static int dpaa2_switch_seed_bp(struct ethsw_core *ethsw) { - int *count, i; + int *count, ret, i; for (i = 0; i < DPAA2_ETHSW_NUM_BUFS; i += BUFS_PER_CMD) { + ret = dpaa2_switch_add_bufs(ethsw, ethsw->bpid); count = ðsw->buf_count; - *count += dpaa2_switch_add_bufs(ethsw, ethsw->bpid); + *count += ret; - if (unlikely(*count < BUFS_PER_CMD)) + if (unlikely(ret < BUFS_PER_CMD)) return -ENOMEM; } From 555e5531635a7c5dba663d06cea240362624dfde Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sat, 17 Aug 2024 13:36:59 -0700 Subject: [PATCH 238/385] selftests: net/forwarding: spawn sh inside vrf to speed up ping loop Looking at timestamped output of netdev CI reveals that most of the time in forwarding tests for custom route hashing is spent on a single case, namely the test which uses ping (mausezahn does not support flow labels). On a non-debug kernel we spend 714 of 730 total test runtime (97%) on this test case. While having flow label support in a traffic gen tool / mausezahn would be best, we can significantly speed up the loop by putting ip vrf exec outside of the iteration. In a test of 1000 pings using a normal loop takes 50 seconds to finish. While using: ip vrf exec $vrf sh -c "$loop-body" takes 12 seconds (1/4 of the time). Some of the slowness is likely due to our inefficient virtualization setup, but even on my laptop running "ip link help" 16k times takes 25-30 seconds, so I think it's worth optimizing even for fastest setups. Reviewed-by: Ido Schimmel Tested-by: Ido Schimmel Reviewed-by: Hangbin Liu Link: https://patch.msgid.link/20240817203659.712085-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- .../selftests/net/forwarding/custom_multipath_hash.sh | 8 ++++---- .../selftests/net/forwarding/gre_custom_multipath_hash.sh | 8 ++++---- .../net/forwarding/ip6gre_custom_multipath_hash.sh | 8 ++++---- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh index 1783c10215e5c..7d531f7091e6f 100755 --- a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh @@ -224,10 +224,10 @@ send_dst_ipv6() send_flowlabel() { # Generate 16384 echo requests, each with a random flow label. - for _ in $(seq 1 16384); do - ip vrf exec v$h1 \ - $PING6 2001:db8:4::2 -F 0 -c 1 -q >/dev/null 2>&1 - done + ip vrf exec v$h1 sh -c \ + "for _ in {1..16384}; do \ + $PING6 2001:db8:4::2 -F 0 -c 1 -q >/dev/null 2>&1; \ + done" } send_src_udp6() diff --git a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh index 9788bd0f6e8b3..dda11a4a9450a 100755 --- a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh @@ -319,10 +319,10 @@ send_dst_ipv6() send_flowlabel() { # Generate 16384 echo requests, each with a random flow label. - for _ in $(seq 1 16384); do - ip vrf exec v$h1 \ - $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1 - done + ip vrf exec v$h1 sh -c \ + "for _ in {1..16384}; do \ + $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1; \ + done" } send_src_udp6() diff --git a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh index 2ab9eaaa5532a..e28b4a079e525 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh @@ -321,10 +321,10 @@ send_dst_ipv6() send_flowlabel() { # Generate 16384 echo requests, each with a random flow label. - for _ in $(seq 1 16384); do - ip vrf exec v$h1 \ - $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1 - done + ip vrf exec v$h1 sh -c \ + "for _ in {1..16384}; do \ + $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1; \ + done" } send_src_udp6() From 2cbece60a4af03803634abd1e840e513db48d42e Mon Sep 17 00:00:00 2001 From: Zhang Zekun Date: Sun, 18 Aug 2024 13:25:18 +0800 Subject: [PATCH 239/385] net: hns3: Use ARRAY_SIZE() to improve readability There is a helper function ARRAY_SIZE() to help calculating the u32 array size, and we don't need to do it mannually. So, let's use ARRAY_SIZE() to calculate the array size, and improve the code readability. Signed-off-by: Zhang Zekun Reviewed-by: Jijie Shao Link: https://patch.msgid.link/20240818052518.45489-1-zhangzekun11@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c index 65b9dcd381375..6db415d8b9176 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c @@ -134,17 +134,17 @@ void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version, reg += hclgevf_reg_get_header(reg); /* fetching per-VF registers values from VF PCIe register space */ - reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32); + reg_um = ARRAY_SIZE(cmdq_reg_addr_list); reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_CMDQ, reg_um, reg); for (i = 0; i < reg_um; i++) *reg++ = hclgevf_read_dev(&hdev->hw, cmdq_reg_addr_list[i]); - reg_um = sizeof(common_reg_addr_list) / sizeof(u32); + reg_um = ARRAY_SIZE(common_reg_addr_list); reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_COMMON, reg_um, reg); for (i = 0; i < reg_um; i++) *reg++ = hclgevf_read_dev(&hdev->hw, common_reg_addr_list[i]); - reg_um = sizeof(ring_reg_addr_list) / sizeof(u32); + reg_um = ARRAY_SIZE(ring_reg_addr_list); for (j = 0; j < hdev->num_tqps; j++) { reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_RING, reg_um, reg); for (i = 0; i < reg_um; i++) @@ -153,7 +153,7 @@ void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version, HCLGEVF_RING_REG_OFFSET * j); } - reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32); + reg_um = ARRAY_SIZE(tqp_intr_reg_addr_list); for (j = 0; j < hdev->num_msi_used - 1; j++) { reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_TQP_INTR, reg_um, reg); for (i = 0; i < reg_um; i++) From 13cfd6a6d7ac78e845768278ab745acbd19c43ce Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Sun, 18 Aug 2024 14:43:51 +0300 Subject: [PATCH 240/385] net: Silence false field-spanning write warning in metadata_dst memcpy When metadata_dst struct is allocated (using metadata_dst_alloc()), it reserves room for options at the end of the struct. Change the memcpy() to unsafe_memcpy() as it is guaranteed that enough room (md_size bytes) was allocated and the field-spanning write is intentional. This resolves the following warning: ------------[ cut here ]------------ memcpy: detected field-spanning write (size 104) of single field "&new_md->u.tun_info" at include/net/dst_metadata.h:166 (size 96) WARNING: CPU: 2 PID: 391470 at include/net/dst_metadata.h:166 tun_dst_unclone+0x114/0x138 [geneve] Modules linked in: act_tunnel_key geneve ip6_udp_tunnel udp_tunnel act_vlan act_mirred act_skbedit cls_matchall nfnetlink_cttimeout act_gact cls_flower sch_ingress sbsa_gwdt ipmi_devintf ipmi_msghandler xfrm_interface xfrm6_tunnel tunnel6 tunnel4 xfrm_user xfrm_algo nvme_fabrics overlay optee openvswitch nsh nf_conncount ib_srp scsi_transport_srp rpcrdma rdma_ucm ib_iser rdma_cm ib_umad iw_cm libiscsi ib_ipoib scsi_transport_iscsi ib_cm uio_pdrv_genirq uio mlxbf_pmc pwr_mlxbf mlxbf_bootctl bluefield_edac nft_chain_nat binfmt_misc xt_MASQUERADE nf_nat xt_tcpmss xt_NFLOG nfnetlink_log xt_recent xt_hashlimit xt_state xt_conntrack nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 xt_mark xt_comment ipt_REJECT nf_reject_ipv4 nft_compat nf_tables nfnetlink sch_fq_codel dm_multipath fuse efi_pstore ip_tables btrfs blake2b_generic raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor xor_neon raid6_pq raid1 raid0 nvme nvme_core mlx5_ib ib_uverbs ib_core ipv6 crc_ccitt mlx5_core crct10dif_ce mlxfw psample i2c_mlxbf gpio_mlxbf2 mlxbf_gige mlxbf_tmfifo CPU: 2 PID: 391470 Comm: handler6 Not tainted 6.10.0-rc1 #1 Hardware name: https://www.mellanox.com BlueField SoC/BlueField SoC, BIOS 4.5.0.12993 Dec 6 2023 pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : tun_dst_unclone+0x114/0x138 [geneve] lr : tun_dst_unclone+0x114/0x138 [geneve] sp : ffffffc0804533f0 x29: ffffffc0804533f0 x28: 000000000000024e x27: 0000000000000000 x26: ffffffdcfc0e8e40 x25: ffffff8086fa6600 x24: ffffff8096a0c000 x23: 0000000000000068 x22: 0000000000000008 x21: ffffff8092ad7000 x20: ffffff8081e17900 x19: ffffff8092ad7900 x18: 00000000fffffffd x17: 0000000000000000 x16: ffffffdcfa018488 x15: 695f6e75742e753e x14: 2d646d5f77656e26 x13: 6d5f77656e262220 x12: 646c65696620656c x11: ffffffdcfbe33ae8 x10: ffffffdcfbe1baa8 x9 : ffffffdcfa0a4c10 x8 : 0000000000017fe8 x7 : c0000000ffffefff x6 : 0000000000000001 x5 : ffffff83fdeeb010 x4 : 0000000000000000 x3 : 0000000000000027 x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffffff80913f6780 Call trace: tun_dst_unclone+0x114/0x138 [geneve] geneve_xmit+0x214/0x10e0 [geneve] dev_hard_start_xmit+0xc0/0x220 __dev_queue_xmit+0xa14/0xd38 dev_queue_xmit+0x14/0x28 [openvswitch] ovs_vport_send+0x98/0x1c8 [openvswitch] do_output+0x80/0x1a0 [openvswitch] do_execute_actions+0x172c/0x1958 [openvswitch] ovs_execute_actions+0x64/0x1a8 [openvswitch] ovs_packet_cmd_execute+0x258/0x2d8 [openvswitch] genl_family_rcv_msg_doit+0xc8/0x138 genl_rcv_msg+0x1ec/0x280 netlink_rcv_skb+0x64/0x150 genl_rcv+0x40/0x60 netlink_unicast+0x2e4/0x348 netlink_sendmsg+0x1b0/0x400 __sock_sendmsg+0x64/0xc0 ____sys_sendmsg+0x284/0x308 ___sys_sendmsg+0x88/0xf0 __sys_sendmsg+0x70/0xd8 __arm64_sys_sendmsg+0x2c/0x40 invoke_syscall+0x50/0x128 el0_svc_common.constprop.0+0x48/0xf0 do_el0_svc+0x24/0x38 el0_svc+0x38/0x100 el0t_64_sync_handler+0xc0/0xc8 el0t_64_sync+0x1a4/0x1a8 ---[ end trace 0000000000000000 ]--- Reviewed-by: Cosmin Ratiu Reviewed-by: Tariq Toukan Signed-off-by: Gal Pressman Link: https://patch.msgid.link/20240818114351.3612692-1-gal@nvidia.com Signed-off-by: Jakub Kicinski --- include/net/dst_metadata.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 4160731dcb6e3..84c15402931cd 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -163,8 +163,11 @@ static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb) if (!new_md) return ERR_PTR(-ENOMEM); - memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, - sizeof(struct ip_tunnel_info) + md_size); + unsafe_memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, + sizeof(struct ip_tunnel_info) + md_size, + /* metadata_dst_alloc() reserves room (md_size bytes) for + * options right after the ip_tunnel_info struct. + */); #ifdef CONFIG_DST_CACHE /* Unclone the dst cache if there is one */ if (new_md->u.tun_info.dst_cache.cache) { From 55da77dec1be92afafb5683cc28a60bc2cc83716 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 18 Aug 2024 19:29:02 +0200 Subject: [PATCH 241/385] dt-bindings: net: mediatek,net: narrow interrupts per variants Each variable-length property like interrupts must have fixed constraints on number of items for given variant in binding. The clauses in "if:then:" block should define both limits: upper and lower. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Rob Herring (Arm) Link: https://patch.msgid.link/20240818172905.121829-1-krzysztof.kozlowski@linaro.org Signed-off-by: Jakub Kicinski --- Documentation/devicetree/bindings/net/mediatek,net.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Documentation/devicetree/bindings/net/mediatek,net.yaml b/Documentation/devicetree/bindings/net/mediatek,net.yaml index 686b5c2fae402..8c00a6f75357b 100644 --- a/Documentation/devicetree/bindings/net/mediatek,net.yaml +++ b/Documentation/devicetree/bindings/net/mediatek,net.yaml @@ -127,6 +127,7 @@ allOf: then: properties: interrupts: + minItems: 3 maxItems: 3 clocks: @@ -183,6 +184,7 @@ allOf: then: properties: interrupts: + minItems: 3 maxItems: 3 clocks: @@ -222,6 +224,7 @@ allOf: then: properties: interrupts: + minItems: 3 maxItems: 3 clocks: From 06ab21c3cb6e124bdc2da226f38bc8eb45946887 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 18 Aug 2024 19:29:03 +0200 Subject: [PATCH 242/385] dt-bindings: net: mediatek,net: add top-level constraints Properties with variable number of items per each device are expected to have widest constraints in top-level "properties:" block and further customized (narrowed) in "if:then:". Add missing top-level constraints for clocks and clock-names. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Rob Herring (Arm) Link: https://patch.msgid.link/20240818172905.121829-2-krzysztof.kozlowski@linaro.org Signed-off-by: Jakub Kicinski --- Documentation/devicetree/bindings/net/mediatek,net.yaml | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/net/mediatek,net.yaml b/Documentation/devicetree/bindings/net/mediatek,net.yaml index 8c00a6f75357b..9e02fd80af835 100644 --- a/Documentation/devicetree/bindings/net/mediatek,net.yaml +++ b/Documentation/devicetree/bindings/net/mediatek,net.yaml @@ -30,8 +30,13 @@ properties: reg: maxItems: 1 - clocks: true - clock-names: true + clocks: + minItems: 2 + maxItems: 24 + + clock-names: + minItems: 2 + maxItems: 24 interrupts: minItems: 1 From 70d16e13368c0526eb3e2a326ed002183a087c21 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 18 Aug 2024 19:29:04 +0200 Subject: [PATCH 243/385] dt-bindings: net: renesas,etheravb: add top-level constraints Properties with variable number of items per each device are expected to have widest constraints in top-level "properties:" block and further customized (narrowed) in "if:then:". Add missing top-level constraints for reg, clocks, clock-names, interrupts and interrupt-names. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Rob Herring (Arm) Link: https://patch.msgid.link/20240818172905.121829-3-krzysztof.kozlowski@linaro.org Signed-off-by: Jakub Kicinski --- .../bindings/net/renesas,etheravb.yaml | 29 ++++++++++++------- 1 file changed, 19 insertions(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml index 21a92f179093d..1e00ef5b3acda 100644 --- a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml +++ b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml @@ -62,15 +62,27 @@ properties: - renesas,r9a08g045-gbeth # RZ/G3S - const: renesas,rzg2l-gbeth # RZ/{G2L,G2UL,V2L} family - reg: true + reg: + minItems: 1 + items: + - description: MAC register block + - description: Stream buffer - interrupts: true + interrupts: + minItems: 1 + maxItems: 29 - interrupt-names: true + interrupt-names: + minItems: 1 + maxItems: 29 - clocks: true + clocks: + minItems: 1 + maxItems: 3 - clock-names: true + clock-names: + minItems: 1 + maxItems: 3 iommus: maxItems: 1 @@ -150,14 +162,11 @@ allOf: then: properties: reg: - items: - - description: MAC register block - - description: Stream buffer + minItems: 2 else: properties: reg: - items: - - description: MAC register block + maxItems: 1 - if: properties: From 2862c9349d5d8667d897aa5cecf0f3886979ecb1 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 18 Aug 2024 19:29:05 +0200 Subject: [PATCH 244/385] dt-bindings: net: socionext,uniphier-ave4: add top-level constraints Properties with variable number of items per each device are expected to have widest constraints in top-level "properties:" block and further customized (narrowed) in "if:then:". Add missing top-level constraints for clock-names and reset-names. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Rob Herring (Arm) Link: https://patch.msgid.link/20240818172905.121829-4-krzysztof.kozlowski@linaro.org Signed-off-by: Jakub Kicinski --- .../devicetree/bindings/net/socionext,uniphier-ave4.yaml | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml index b0ebcef6801ce..4eb63b303cffc 100644 --- a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml +++ b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml @@ -41,13 +41,17 @@ properties: minItems: 1 maxItems: 4 - clock-names: true + clock-names: + minItems: 1 + maxItems: 4 resets: minItems: 1 maxItems: 2 - reset-names: true + reset-names: + minItems: 1 + maxItems: 2 socionext,syscon-phy-mode: $ref: /schemas/types.yaml#/definitions/phandle-array From 80a1e7b83bb1834b5568a3872e64c05795d88f31 Mon Sep 17 00:00:00 2001 From: Nikolay Kuratov Date: Mon, 19 Aug 2024 10:54:08 +0300 Subject: [PATCH 245/385] cxgb4: add forgotten u64 ivlan cast before shift It is done everywhere in cxgb4 code, e.g. in is_filter_exact_match() There is no reason it should not be done here Found by Linux Verification Center (linuxtesting.org) with SVACE Signed-off-by: Nikolay Kuratov Cc: stable@vger.kernel.org Fixes: 12b276fbf6e0 ("cxgb4: add support to create hash filters") Reviewed-by: Simon Horman Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20240819075408.92378-1-kniv@yandex-team.ru Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 786ceae344887..dd9e68465e697 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -1244,7 +1244,8 @@ static u64 hash_filter_ntuple(struct ch_filter_specification *fs, * in the Compressed Filter Tuple. */ if (tp->vlan_shift >= 0 && fs->mask.ivlan) - ntuple |= (FT_VLAN_VLD_F | fs->val.ivlan) << tp->vlan_shift; + ntuple |= (u64)(FT_VLAN_VLD_F | + fs->val.ivlan) << tp->vlan_shift; if (tp->port_shift >= 0 && fs->mask.iport) ntuple |= (u64)fs->val.iport << tp->port_shift; From 8aba27c4a5020abdf60149239198297f88338a8d Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 16 Aug 2024 17:20:34 +0200 Subject: [PATCH 246/385] igb: cope with large MAX_SKB_FRAGS Sabrina reports that the igb driver does not cope well with large MAX_SKB_FRAG values: setting MAX_SKB_FRAG to 45 causes payload corruption on TX. An easy reproducer is to run ssh to connect to the machine. With MAX_SKB_FRAGS=17 it works, with MAX_SKB_FRAGS=45 it fails. This has been reported originally in https://bugzilla.redhat.com/show_bug.cgi?id=2265320 The root cause of the issue is that the driver does not take into account properly the (possibly large) shared info size when selecting the ring layout, and will try to fit two packets inside the same 4K page even when the 1st fraglist will trump over the 2nd head. Address the issue by checking if 2K buffers are insufficient. Fixes: 3948b05950fd ("net: introduce a config option to tweak MAX_SKB_FRAGS") Reported-by: Jan Tluka Reported-by: Jirka Hladky Reported-by: Sabrina Dubroca Tested-by: Sabrina Dubroca Tested-by: Corinna Vinschen Signed-off-by: Paolo Abeni Signed-off-by: Corinna Vinschen Link: https://patch.msgid.link/20240816152034.1453285-1-vinschen@redhat.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igb/igb_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 11be39f435f38..33a42b4c21e0b 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4808,6 +4808,7 @@ static void igb_set_rx_buffer_len(struct igb_adapter *adapter, #if (PAGE_SIZE < 8192) if (adapter->max_frame_size > IGB_MAX_FRAME_BUILD_SKB || + IGB_2K_TOO_SMALL_WITH_PADDING || rd32(E1000_RCTL) & E1000_RCTL_SBP) set_ring_uses_large_buffer(rx_ring); #endif From 8594d9b85c07f05e431bd07e895c2a3ad9b85d6f Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 16 Aug 2024 16:39:21 -0700 Subject: [PATCH 247/385] af_unix: Don't call skb_get() for OOB skb. Since introduced, OOB skb holds an additional reference count with no special reason and caused many issues. Also, kfree_skb() and consume_skb() are used to decrement the count, which is confusing. Let's drop the unnecessary skb_get() in queue_oob() and corresponding kfree_skb(), consume_skb(), and skb_unref(). Now unix_sk(sk)->oob_skb is just a pointer to skb in the receive queue, so special handing is no longer needed in GC. Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20240816233921.57800-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/unix/af_unix.c | 27 +++++---------------------- net/unix/garbage.c | 16 ++-------------- 2 files changed, 7 insertions(+), 36 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0be0dcb07f7b6..a1894019ebd56 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -693,10 +693,7 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_state_unlock(sk); #if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - kfree_skb(u->oob_skb); - u->oob_skb = NULL; - } + u->oob_skb = NULL; #endif wake_up_interruptible_all(&u->peer_wait); @@ -2226,13 +2223,9 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other } maybe_add_creds(skb, sock, other); - skb_get(skb); - scm_stat_add(other, skb); spin_lock(&other->sk_receive_queue.lock); - if (ousk->oob_skb) - consume_skb(ousk->oob_skb); WRITE_ONCE(ousk->oob_skb, skb); __skb_queue_tail(&other->sk_receive_queue, skb); spin_unlock(&other->sk_receive_queue.lock); @@ -2640,8 +2633,6 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) if (!(state->flags & MSG_PEEK)) WRITE_ONCE(u->oob_skb, NULL); - else - skb_get(oob_skb); spin_unlock(&sk->sk_receive_queue.lock); unix_state_unlock(sk); @@ -2651,8 +2642,6 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) if (!(state->flags & MSG_PEEK)) UNIXCB(oob_skb).consumed += 1; - consume_skb(oob_skb); - mutex_unlock(&u->iolock); if (chunk < 0) @@ -2694,12 +2683,10 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, if (copied) { skb = NULL; } else if (!(flags & MSG_PEEK)) { - if (sock_flag(sk, SOCK_URGINLINE)) { - WRITE_ONCE(u->oob_skb, NULL); - consume_skb(skb); - } else { + WRITE_ONCE(u->oob_skb, NULL); + + if (!sock_flag(sk, SOCK_URGINLINE)) { __skb_unlink(skb, &sk->sk_receive_queue); - WRITE_ONCE(u->oob_skb, NULL); unlinked_skb = skb; skb = skb_peek(&sk->sk_receive_queue); } @@ -2710,10 +2697,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, spin_unlock(&sk->sk_receive_queue.lock); - if (unlinked_skb) { - WARN_ON_ONCE(skb_unref(unlinked_skb)); - kfree_skb(unlinked_skb); - } + kfree_skb(unlinked_skb); } return skb; } @@ -2756,7 +2740,6 @@ static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor) unix_state_unlock(sk); if (drop) { - WARN_ON_ONCE(skb_unref(skb)); kfree_skb(skb); return -EAGAIN; } diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 06d94ad999e99..0068e758be4dd 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -337,18 +337,6 @@ static bool unix_vertex_dead(struct unix_vertex *vertex) return true; } -static void unix_collect_queue(struct unix_sock *u, struct sk_buff_head *hitlist) -{ - skb_queue_splice_init(&u->sk.sk_receive_queue, hitlist); - -#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - WARN_ON_ONCE(skb_unref(u->oob_skb)); - u->oob_skb = NULL; - } -#endif -} - static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist) { struct unix_vertex *vertex; @@ -371,11 +359,11 @@ static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist struct sk_buff_head *embryo_queue = &skb->sk->sk_receive_queue; spin_lock(&embryo_queue->lock); - unix_collect_queue(unix_sk(skb->sk), hitlist); + skb_queue_splice_init(embryo_queue, hitlist); spin_unlock(&embryo_queue->lock); } } else { - unix_collect_queue(u, hitlist); + skb_queue_splice_init(queue, hitlist); } spin_unlock(&queue->lock); From 6efea5135417ae8194485d1d05ea79a21cf1a11c Mon Sep 17 00:00:00 2001 From: Martin Whitaker Date: Sat, 17 Aug 2024 10:41:41 +0100 Subject: [PATCH 248/385] net: dsa: microchip: fix PTP config failure when using multiple ports When performing the port_hwtstamp_set operation, ptp_schedule_worker() will be called if hardware timestamoing is enabled on any of the ports. When using multiple ports for PTP, port_hwtstamp_set is executed for each port. When called for the first time ptp_schedule_worker() returns 0. On subsequent calls it returns 1, indicating the worker is already scheduled. Currently the ksz driver treats 1 as an error and fails to complete the port_hwtstamp_set operation, thus leaving the timestamping configuration for those ports unchanged. This patch fixes this by ignoring the ptp_schedule_worker() return value. Cc: stable@vger.kernel.org Link: https://lore.kernel.org/7aae307a-35ca-4209-a850-7b2749d40f90@martin-whitaker.me.uk Fixes: bb01ad30570b0 ("net: dsa: microchip: ptp: manipulating absolute time using ptp hw clock") Signed-off-by: Martin Whitaker Reviewed-by: Andrew Lunn Acked-by: Arun Ramadoss Link: https://patch.msgid.link/20240817094141.3332-1-foss@martin-whitaker.me.uk Signed-off-by: Jakub Kicinski --- drivers/net/dsa/microchip/ksz_ptp.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c index f0bd46e5d4ec0..050f17c43ef60 100644 --- a/drivers/net/dsa/microchip/ksz_ptp.c +++ b/drivers/net/dsa/microchip/ksz_ptp.c @@ -266,7 +266,6 @@ static int ksz_ptp_enable_mode(struct ksz_device *dev) struct ksz_port *prt; struct dsa_port *dp; bool tag_en = false; - int ret; dsa_switch_for_each_user_port(dp, dev->ds) { prt = &dev->ports[dp->index]; @@ -277,9 +276,7 @@ static int ksz_ptp_enable_mode(struct ksz_device *dev) } if (tag_en) { - ret = ptp_schedule_worker(ptp_data->clock, 0); - if (ret) - return ret; + ptp_schedule_worker(ptp_data->clock, 0); } else { ptp_cancel_worker_sync(ptp_data->clock); } From bc3dd9ed04d69cba3bb603da06fa26d888233cff Mon Sep 17 00:00:00 2001 From: James Chapman Date: Mon, 19 Aug 2024 15:33:33 +0100 Subject: [PATCH 249/385] l2tp: use skb_queue_purge in l2tp_ip_destroy_sock Recent commit ed8ebee6def7 ("l2tp: have l2tp_ip_destroy_sock use ip_flush_pending_frames") was incorrect in that l2tp_ip does not use socket cork and ip_flush_pending_frames is for sockets that do. Use __skb_queue_purge instead and remove the unnecessary lock. Also unexport ip_flush_pending_frames since it was originally exported in commit 4ff8863419cd ("ipv4: export ip_flush_pending_frames") for l2tp and is not used by other modules. Suggested-by: xiyou.wangcong@gmail.com Signed-off-by: James Chapman Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240819143333.3204957-1-jchapman@katalix.com Signed-off-by: Jakub Kicinski --- net/ipv4/ip_output.c | 1 - net/l2tp/l2tp_ip.c | 4 +--- 2 files changed, 1 insertion(+), 4 deletions(-) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8a10a7c67834f..b90d0f78ac808 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1534,7 +1534,6 @@ void ip_flush_pending_frames(struct sock *sk) { __ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base); } -EXPORT_SYMBOL_GPL(ip_flush_pending_frames); struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4, diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 39f3f1334c4aa..4bc24fddfd524 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -258,9 +258,7 @@ static void l2tp_ip_destroy_sock(struct sock *sk) { struct l2tp_tunnel *tunnel; - lock_sock(sk); - ip_flush_pending_frames(sk); - release_sock(sk); + __skb_queue_purge(&sk->sk_write_queue); tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) { From 528876d867a23b5198022baf2e388052ca67c952 Mon Sep 17 00:00:00 2001 From: Joseph Huang Date: Mon, 19 Aug 2024 19:52:50 -0400 Subject: [PATCH 250/385] net: dsa: mv88e6xxx: Fix out-of-bound access If an ATU violation was caused by a CPU Load operation, the SPID could be larger than DSA_MAX_PORTS (the size of mv88e6xxx_chip.ports[] array). Fixes: 75c05a74e745 ("net: dsa: mv88e6xxx: Fix counting of ATU violations") Signed-off-by: Joseph Huang Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20240819235251.1331763-1-Joseph.Huang@garmin.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/mv88e6xxx/global1_atu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index ce3b3690c3c05..c47f068f56b32 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -457,7 +457,8 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) trace_mv88e6xxx_atu_full_violation(chip->dev, spid, entry.portvec, entry.mac, fid); - chip->ports[spid].atu_full_violation++; + if (spid < ARRAY_SIZE(chip->ports)) + chip->ports[spid].atu_full_violation++; } return IRQ_HANDLED; From c07ff8592d57ed258afee5a5e04991a48dbaf382 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Mon, 19 Aug 2024 10:56:45 -0700 Subject: [PATCH 251/385] netem: fix return value if duplicate enqueue fails There is a bug in netem_enqueue() introduced by commit 5845f706388a ("net: netem: fix skb length BUG_ON in __skb_to_sgvec") that can lead to a use-after-free. This commit made netem_enqueue() always return NET_XMIT_SUCCESS when a packet is duplicated, which can cause the parent qdisc's q.qlen to be mistakenly incremented. When this happens qlen_notify() may be skipped on the parent during destruction, leaving a dangling pointer for some classful qdiscs like DRR. There are two ways for the bug happen: - If the duplicated packet is dropped by rootq->enqueue() and then the original packet is also dropped. - If rootq->enqueue() sends the duplicated packet to a different qdisc and the original packet is dropped. In both cases NET_XMIT_SUCCESS is returned even though no packets are enqueued at the netem qdisc. The fix is to defer the enqueue of the duplicate packet until after the original packet has been guaranteed to return NET_XMIT_SUCCESS. Fixes: 5845f706388a ("net: netem: fix skb length BUG_ON in __skb_to_sgvec") Reported-by: Budimir Markovic Signed-off-by: Stephen Hemminger Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240819175753.5151-1-stephen@networkplumber.org Signed-off-by: Jakub Kicinski --- net/sched/sch_netem.c | 47 ++++++++++++++++++++++++++----------------- 1 file changed, 29 insertions(+), 18 deletions(-) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index edc72962ae63a..0f8d581438c39 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -446,12 +446,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct netem_sched_data *q = qdisc_priv(sch); /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; - struct sk_buff *skb2; + struct sk_buff *skb2 = NULL; struct sk_buff *segs = NULL; unsigned int prev_len = qdisc_pkt_len(skb); int count = 1; - int rc = NET_XMIT_SUCCESS; - int rc_drop = NET_XMIT_DROP; /* Do not fool qdisc_drop_all() */ skb->prev = NULL; @@ -480,19 +478,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, skb_orphan_partial(skb); /* - * If we need to duplicate packet, then re-insert at top of the - * qdisc tree, since parent queuer expects that only one - * skb will be queued. + * If we need to duplicate packet, then clone it before + * original is modified. */ - if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) { - struct Qdisc *rootq = qdisc_root_bh(sch); - u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ - - q->duplicate = 0; - rootq->enqueue(skb2, rootq, to_free); - q->duplicate = dupsave; - rc_drop = NET_XMIT_SUCCESS; - } + if (count > 1) + skb2 = skb_clone(skb, GFP_ATOMIC); /* * Randomized packet corruption. @@ -504,7 +494,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb_is_gso(skb)) { skb = netem_segment(skb, sch, to_free); if (!skb) - return rc_drop; + goto finish_segs; + segs = skb->next; skb_mark_not_on_list(skb); qdisc_skb_cb(skb)->pkt_len = skb->len; @@ -530,7 +521,24 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* re-link segs, so that qdisc_drop_all() frees them all */ skb->next = segs; qdisc_drop_all(skb, sch, to_free); - return rc_drop; + if (skb2) + __qdisc_drop(skb2, to_free); + return NET_XMIT_DROP; + } + + /* + * If doing duplication then re-insert at top of the + * qdisc tree, since parent queuer expects that only one + * skb will be queued. + */ + if (skb2) { + struct Qdisc *rootq = qdisc_root_bh(sch); + u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ + + q->duplicate = 0; + rootq->enqueue(skb2, rootq, to_free); + q->duplicate = dupsave; + skb2 = NULL; } qdisc_qstats_backlog_inc(sch, skb); @@ -601,9 +609,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, } finish_segs: + if (skb2) + __qdisc_drop(skb2, to_free); + if (segs) { unsigned int len, last_len; - int nb; + int rc, nb; len = skb ? skb->len : 0; nb = skb ? 1 : 0; From e255683c06df572ead96db5efb5d21be30c0efaa Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:19 +0200 Subject: [PATCH 252/385] mptcp: pm: re-using ID of unused removed ADD_ADDR If no subflow is attached to the 'signal' endpoint that is being removed, the addr ID will not be marked as available again. Mark the linked ID as available when removing the address entry from the list to cover this case. Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-1-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 4cae2aa7be5cb..26f0329e16bbf 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1431,7 +1431,10 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, ret = remove_anno_list_by_saddr(msk, addr); if (ret || force) { spin_lock_bh(&msk->pm.lock); - msk->pm.add_addr_signaled -= ret; + if (ret) { + __set_bit(addr->id, msk->pm.id_avail_bitmap); + msk->pm.add_addr_signaled--; + } mptcp_pm_remove_addr(msk, &list); spin_unlock_bh(&msk->pm.lock); } From a13d5aad4dd9a309eecdc33cfd75045bd5f376a3 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:20 +0200 Subject: [PATCH 253/385] selftests: mptcp: join: check re-using ID of unused ADD_ADDR This test extends "delete re-add signal" to validate the previous commit. An extra address is announced by the server, but this address cannot be used by the client. The result is that no subflow will be established to this address. Later, the server will delete this extra endpoint, and set a new one, with a valid address, but re-using the same ID. Before the previous commit, the server would not have been able to announce this new address. While at it, extra checks have been added to validate the expected numbers of MPJ, ADD_ADDR and RM_ADDR. The 'Fixes' tag here below is the same as the one from the previous commit: this patch here is not fixing anything wrong in the selftests, but it validates the previous fix for an issue introduced by this commit ID. Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-2-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/mptcp/mptcp_join.sh | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 9ea6d698e9d38..25077ccf31d27 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3601,9 +3601,11 @@ endpoint_tests() # remove and re-add if reset "delete re-add signal" && mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then - pm_nl_set_limits $ns1 1 1 - pm_nl_set_limits $ns2 1 1 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal + # broadcast IP: no packet for this address will be received on ns1 + pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal test_linkfail=4 speed=20 \ run_tests $ns1 $ns2 10.0.1.1 & local tests_pid=$! @@ -3615,15 +3617,21 @@ endpoint_tests() chk_mptcp_info subflows 1 subflows 1 pm_nl_del_endpoint $ns1 1 10.0.2.1 + pm_nl_del_endpoint $ns1 2 224.0.0.1 sleep 0.5 chk_subflow_nr "after delete" 1 chk_mptcp_info subflows 0 subflows 0 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal wait_mpj $ns2 - chk_subflow_nr "after re-add" 2 - chk_mptcp_info subflows 1 subflows 1 + chk_subflow_nr "after re-add" 3 + chk_mptcp_info subflows 2 subflows 2 mptcp_lib_kill_wait $tests_pid + + chk_join_nr 3 3 3 + chk_add_nr 4 4 + chk_rm_nr 2 1 invert fi } From edd8b5d868a4d459f3065493001e293901af758d Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:21 +0200 Subject: [PATCH 254/385] mptcp: pm: re-using ID of unused removed subflows If no subflow is attached to the 'subflow' endpoint that is being removed, the addr ID will not be marked as available again. Mark the linked ID as available when removing the 'subflow' endpoint if no subflow is attached to it. While at it, the local_addr_used counter is decremented if the ID was marked as being used to reflect the reality, but also to allow adding new endpoints after that. Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-3-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 26f0329e16bbf..8b232a210a066 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1469,8 +1469,17 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr); mptcp_pm_remove_anno_addr(msk, addr, remove_subflow && !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)); - if (remove_subflow) + + if (remove_subflow) { mptcp_pm_remove_subflow(msk, &list); + } else if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { + /* If the subflow has been used, but now closed */ + spin_lock_bh(&msk->pm.lock); + if (!__test_and_set_bit(entry->addr.id, msk->pm.id_avail_bitmap)) + msk->pm.local_addr_used--; + spin_unlock_bh(&msk->pm.lock); + } + release_sock(sk); next: From 65fb58afa341ad68e71e5c4d816b407e6a683a66 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:22 +0200 Subject: [PATCH 255/385] selftests: mptcp: join: check re-using ID of closed subflow This test extends "delete and re-add" to validate the previous commit. A new 'subflow' endpoint is added, but the subflow request will be rejected. The result is that no subflow will be established from this address. Later, the endpoint is removed and re-added after having cleared the firewall rule. Before the previous commit, the client would not have been able to create this new subflow. While at it, extra checks have been added to validate the expected numbers of MPJ and RM_ADDR. The 'Fixes' tag here below is the same as the one from the previous commit: this patch here is not fixing anything wrong in the selftests, but it validates the previous fix for an issue introduced by this commit ID. Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-4-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/mptcp/mptcp_join.sh | 27 +++++++++++++++---- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 25077ccf31d27..fbb0174145ad3 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -436,9 +436,10 @@ reset_with_tcp_filter() local ns="${!1}" local src="${2}" local target="${3}" + local chain="${4:-INPUT}" if ! ip netns exec "${ns}" ${iptables} \ - -A INPUT \ + -A "${chain}" \ -s "${src}" \ -p tcp \ -j "${target}"; then @@ -3571,10 +3572,10 @@ endpoint_tests() mptcp_lib_kill_wait $tests_pid fi - if reset "delete and re-add" && + if reset_with_tcp_filter "delete and re-add" ns2 10.0.3.2 REJECT OUTPUT && mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then - pm_nl_set_limits $ns1 1 1 - pm_nl_set_limits $ns2 1 1 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow test_linkfail=4 speed=20 \ run_tests $ns1 $ns2 10.0.1.1 & @@ -3591,11 +3592,27 @@ endpoint_tests() chk_subflow_nr "after delete" 1 chk_mptcp_info subflows 0 subflows 0 - pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow wait_mpj $ns2 chk_subflow_nr "after re-add" 2 chk_mptcp_info subflows 1 subflows 1 + + pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow + wait_attempt_fail $ns2 + chk_subflow_nr "after new reject" 2 + chk_mptcp_info subflows 1 subflows 1 + + ip netns exec "${ns2}" ${iptables} -D OUTPUT -s "10.0.3.2" -p tcp -j REJECT + pm_nl_del_endpoint $ns2 3 10.0.3.2 + pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow + wait_mpj $ns2 + chk_subflow_nr "after no reject" 3 + chk_mptcp_info subflows 2 subflows 2 + mptcp_lib_kill_wait $tests_pid + + chk_join_nr 3 3 3 + chk_rm_nr 1 1 fi # remove and re-add From ef34a6ea0cab1800f4b3c9c3c2cefd5091e03379 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:23 +0200 Subject: [PATCH 256/385] mptcp: pm: re-using ID of unused flushed subflows If no subflows are attached to the 'subflow' endpoints that are being flushed, the corresponding addr IDs will not be marked as available again. Mark all ID as being available when flushing all the 'subflow' endpoints, and reset local_addr_used counter to cover these cases. Note that mptcp_pm_remove_addrs_and_subflows() helper is only called for flushing operations, not to remove a specific set of addresses and subflows. Fixes: 06faa2271034 ("mptcp: remove multi addresses and subflows in PM") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-5-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 8b232a210a066..2c26696b820e8 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1623,8 +1623,15 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, mptcp_pm_remove_addr(msk, &alist); spin_unlock_bh(&msk->pm.lock); } + if (slist.nr) mptcp_pm_remove_subflow(msk, &slist); + + /* Reset counters: maybe some subflows have been removed before */ + spin_lock_bh(&msk->pm.lock); + bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); + msk->pm.local_addr_used = 0; + spin_unlock_bh(&msk->pm.lock); } static void mptcp_nl_remove_addrs_list(struct net *net, From e06959e9eebdfea4654390f53b65cff57691872e Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:24 +0200 Subject: [PATCH 257/385] selftests: mptcp: join: test for flush/re-add endpoints After having flushed endpoints that didn't cause the creation of new subflows, it is important to check endpoints can be re-created, re-using previously used IDs. Before the previous commit, the client would not have been able to re-create the subflow that was previously rejected. The 'Fixes' tag here below is the same as the one from the previous commit: this patch here is not fixing anything wrong in the selftests, but it validates the previous fix for an issue introduced by this commit ID. Fixes: 06faa2271034 ("mptcp: remove multi addresses and subflows in PM") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-6-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/mptcp/mptcp_join.sh | 30 +++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index fbb0174145ad3..f609c02c6123e 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3651,6 +3651,36 @@ endpoint_tests() chk_rm_nr 2 1 invert fi + # flush and re-add + if reset_with_tcp_filter "flush re-add" ns2 10.0.3.2 REJECT OUTPUT && + mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + # broadcast IP: no packet for this address will be received on ns1 + pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow + test_linkfail=4 speed=20 \ + run_tests $ns1 $ns2 10.0.1.1 & + local tests_pid=$! + + wait_attempt_fail $ns2 + chk_subflow_nr "before flush" 1 + chk_mptcp_info subflows 0 subflows 0 + + pm_nl_flush_endpoint $ns2 + pm_nl_flush_endpoint $ns1 + wait_rm_addr $ns2 0 + ip netns exec "${ns2}" ${iptables} -D OUTPUT -s "10.0.3.2" -p tcp -j REJECT + pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow + wait_mpj $ns2 + pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal + wait_mpj $ns2 + mptcp_lib_kill_wait $tests_pid + + chk_join_nr 2 2 2 + chk_add_nr 2 2 + chk_rm_nr 1 0 invert + fi } # [$1: error message] From f448451aa62d54be16acb0034223c17e0d12bc69 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:25 +0200 Subject: [PATCH 258/385] mptcp: pm: remove mptcp_pm_remove_subflow() This helper is confusing. It is in pm.c, but it is specific to the in-kernel PM and it cannot be used by the userspace one. Also, it simply calls one in-kernel specific function with the PM lock, while the similar mptcp_pm_remove_addr() helper requires the PM lock. What's left is the pr_debug(), which is not that useful, because a similar one is present in the only function called by this helper: mptcp_pm_nl_rm_subflow_received() After these modifications, this helper can be marked as 'static', and the lock can be taken only once in mptcp_pm_flush_addrs_and_subflows(). Note that it is not a bug fix, but it will help backporting the following commits. Fixes: 0ee4261a3681 ("mptcp: implement mptcp_pm_remove_subflow") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-7-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm.c | 10 ---------- net/mptcp/pm_netlink.c | 16 +++++++--------- net/mptcp/protocol.h | 3 --- 3 files changed, 7 insertions(+), 22 deletions(-) diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 23bb89c94e90d..925123e99889b 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -60,16 +60,6 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ return 0; } -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list) -{ - pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr); - - spin_lock_bh(&msk->pm.lock); - mptcp_pm_nl_rm_subflow_received(msk, rm_list); - spin_unlock_bh(&msk->pm.lock); - return 0; -} - /* path manager event handlers */ void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 2c26696b820e8..44fc1c5959ac8 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -857,8 +857,8 @@ static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk) mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR); } -void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, - const struct mptcp_rm_list *rm_list) +static void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, + const struct mptcp_rm_list *rm_list) { mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW); } @@ -1471,7 +1471,9 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)); if (remove_subflow) { - mptcp_pm_remove_subflow(msk, &list); + spin_lock_bh(&msk->pm.lock); + mptcp_pm_nl_rm_subflow_received(msk, &list); + spin_unlock_bh(&msk->pm.lock); } else if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { /* If the subflow has been used, but now closed */ spin_lock_bh(&msk->pm.lock); @@ -1617,18 +1619,14 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, alist.ids[alist.nr++] = entry->addr.id; } + spin_lock_bh(&msk->pm.lock); if (alist.nr) { - spin_lock_bh(&msk->pm.lock); msk->pm.add_addr_signaled -= alist.nr; mptcp_pm_remove_addr(msk, &alist); - spin_unlock_bh(&msk->pm.lock); } - if (slist.nr) - mptcp_pm_remove_subflow(msk, &slist); - + mptcp_pm_nl_rm_subflow_received(msk, &slist); /* Reset counters: maybe some subflows have been removed before */ - spin_lock_bh(&msk->pm.lock); bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); msk->pm.local_addr_used = 0; spin_unlock_bh(&msk->pm.lock); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 60c6b073d65fe..a1c1b0ff1ce1c 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1026,7 +1026,6 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool echo); int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list); void mptcp_free_local_addr_list(struct mptcp_sock *msk); @@ -1133,8 +1132,6 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_work(struct mptcp_sock *msk); -void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, - const struct mptcp_rm_list *rm_list); unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk); From 322ea3778965da72862cca2a0c50253aacf65fe6 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:26 +0200 Subject: [PATCH 259/385] mptcp: pm: only mark 'subflow' endp as available Adding the following warning ... WARN_ON_ONCE(msk->pm.local_addr_used == 0) ... before decrementing the local_addr_used counter helped to find a bug when running the "remove single address" subtest from the mptcp_join.sh selftests. Removing a 'signal' endpoint will trigger the removal of all subflows linked to this endpoint via mptcp_pm_nl_rm_addr_or_subflow() with rm_type == MPTCP_MIB_RMSUBFLOW. This will decrement the local_addr_used counter, which is wrong in this case because this counter is linked to 'subflow' endpoints, and here it is a 'signal' endpoint that is being removed. Now, the counter is decremented, only if the ID is being used outside of mptcp_pm_nl_rm_addr_or_subflow(), only for 'subflow' endpoints, and if the ID is not 0 -- local_addr_used is not taking into account these ones. This marking of the ID as being available, and the decrement is done no matter if a subflow using this ID is currently available, because the subflow could have been closed before. Fixes: 06faa2271034 ("mptcp: remove multi addresses and subflows in PM") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-8-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 44fc1c5959ac8..4cf7cc851f80a 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -833,10 +833,10 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, if (rm_type == MPTCP_MIB_RMSUBFLOW) __MPTCP_INC_STATS(sock_net(sk), rm_type); } - if (rm_type == MPTCP_MIB_RMSUBFLOW) - __set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap); - else if (rm_type == MPTCP_MIB_RMADDR) + + if (rm_type == MPTCP_MIB_RMADDR) __MPTCP_INC_STATS(sock_net(sk), rm_type); + if (!removed) continue; @@ -846,8 +846,6 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, if (rm_type == MPTCP_MIB_RMADDR) { msk->pm.add_addr_accepted--; WRITE_ONCE(msk->pm.accept_addr, true); - } else if (rm_type == MPTCP_MIB_RMSUBFLOW) { - msk->pm.local_addr_used--; } } } @@ -1441,6 +1439,14 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, return ret; } +static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id) +{ + /* If it was marked as used, and not ID 0, decrement local_addr_used */ + if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) && + id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0)) + msk->pm.local_addr_used--; +} + static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, const struct mptcp_pm_addr_entry *entry) { @@ -1474,11 +1480,11 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, spin_lock_bh(&msk->pm.lock); mptcp_pm_nl_rm_subflow_received(msk, &list); spin_unlock_bh(&msk->pm.lock); - } else if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { - /* If the subflow has been used, but now closed */ + } + + if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { spin_lock_bh(&msk->pm.lock); - if (!__test_and_set_bit(entry->addr.id, msk->pm.id_avail_bitmap)) - msk->pm.local_addr_used--; + __mark_subflow_endp_available(msk, list.ids[0]); spin_unlock_bh(&msk->pm.lock); } @@ -1516,6 +1522,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net, spin_lock_bh(&msk->pm.lock); mptcp_pm_remove_addr(msk, &list); mptcp_pm_nl_rm_subflow_received(msk, &list); + __mark_subflow_endp_available(msk, 0); spin_unlock_bh(&msk->pm.lock); release_sock(sk); @@ -1917,6 +1924,7 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk, spin_lock_bh(&msk->pm.lock); mptcp_pm_nl_rm_subflow_received(msk, &list); + __mark_subflow_endp_available(msk, list.ids[0]); mptcp_pm_create_subflow_or_signal_addr(msk); spin_unlock_bh(&msk->pm.lock); } From 1c1f721375989579e46741f59523e39ec9b2a9bd Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:27 +0200 Subject: [PATCH 260/385] mptcp: pm: only decrement add_addr_accepted for MPJ req Adding the following warning ... WARN_ON_ONCE(msk->pm.add_addr_accepted == 0) ... before decrementing the add_addr_accepted counter helped to find a bug when running the "remove single subflow" subtest from the mptcp_join.sh selftest. Removing a 'subflow' endpoint will first trigger a RM_ADDR, then the subflow closure. Before this patch, and upon the reception of the RM_ADDR, the other peer will then try to decrement this add_addr_accepted. That's not correct because the attached subflows have not been created upon the reception of an ADD_ADDR. A way to solve that is to decrement the counter only if the attached subflow was an MP_JOIN to a remote id that was not 0, and initiated by the host receiving the RM_ADDR. Fixes: d0876b2284cf ("mptcp: add the incoming RM_ADDR support") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-9-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 4cf7cc851f80a..882781571c7b4 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -829,7 +829,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, mptcp_close_ssk(sk, ssk, subflow); spin_lock_bh(&msk->pm.lock); - removed = true; + removed |= subflow->request_join; if (rm_type == MPTCP_MIB_RMSUBFLOW) __MPTCP_INC_STATS(sock_net(sk), rm_type); } @@ -843,7 +843,11 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, if (!mptcp_pm_is_kernel(msk)) continue; - if (rm_type == MPTCP_MIB_RMADDR) { + if (rm_type == MPTCP_MIB_RMADDR && rm_id && + !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) { + /* Note: if the subflow has been closed before, this + * add_addr_accepted counter will not be decremented. + */ msk->pm.add_addr_accepted--; WRITE_ONCE(msk->pm.accept_addr, true); } From 0137a3c7c2ea3f9df8ebfc65d78b4ba712a187bb Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:28 +0200 Subject: [PATCH 261/385] mptcp: pm: check add_addr_accept_max before accepting new ADD_ADDR The limits might have changed in between, it is best to check them before accepting new ADD_ADDR. Fixes: d0876b2284cf ("mptcp: add the incoming RM_ADDR support") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-10-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 882781571c7b4..28a9a37261461 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -848,8 +848,8 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, /* Note: if the subflow has been closed before, this * add_addr_accepted counter will not be decremented. */ - msk->pm.add_addr_accepted--; - WRITE_ONCE(msk->pm.accept_addr, true); + if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk)) + WRITE_ONCE(msk->pm.accept_addr, true); } } } From ca6e55a703ca2894611bb5c5bca8bfd2290fd91e Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:29 +0200 Subject: [PATCH 262/385] mptcp: pm: only in-kernel cannot have entries with ID 0 The ID 0 is specific per MPTCP connections. The per netns entries cannot have this special ID 0 then. But that's different for the userspace PM where the entries are per connection, they can then use this special ID 0. Fixes: f40be0db0b76 ("mptcp: unify pm get_flags_and_ifindex_by_id") Cc: stable@vger.kernel.org Acked-by: Geliang Tang Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-11-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm.c | 3 --- net/mptcp/pm_netlink.c | 4 ++++ 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 925123e99889b..3e6e0f5510bb1 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -434,9 +434,6 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id *flags = 0; *ifindex = 0; - if (!id) - return 0; - if (mptcp_pm_is_userspace(msk)) return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 28a9a37261461..d0a80f537fc3e 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1395,6 +1395,10 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int struct sock *sk = (struct sock *)msk; struct net *net = sock_net(sk); + /* No entries with ID 0 */ + if (id == 0) + return 0; + rcu_read_lock(); entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id); if (entry) { From 09355f7abb9fbfc1a240be029837921ea417bf4f Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:30 +0200 Subject: [PATCH 263/385] mptcp: pm: fullmesh: select the right ID later When reacting upon the reception of an ADD_ADDR, the in-kernel PM first looks for fullmesh endpoints. If there are some, it will pick them, using their entry ID. It should set the ID 0 when using the endpoint corresponding to the initial subflow, it is a special case imposed by the MPTCP specs. Note that msk->mpc_endpoint_id might not be set when receiving the first ADD_ADDR from the server. So better to compare the addresses. Fixes: 1a0d6136c5f0 ("mptcp: local addresses fullmesh") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-12-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index d0a80f537fc3e..a2e37ab1c40fc 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -636,6 +636,7 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, { struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *entry; + struct mptcp_addr_info mpc_addr; struct pm_nl_pernet *pernet; unsigned int subflows_max; int i = 0; @@ -643,6 +644,8 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, pernet = pm_nl_get_pernet_from_msk(msk); subflows_max = mptcp_pm_get_subflows_max(msk); + mptcp_local_address((struct sock_common *)msk, &mpc_addr); + rcu_read_lock(); list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH)) @@ -653,7 +656,13 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, if (msk->pm.subflows < subflows_max) { msk->pm.subflows++; - addrs[i++] = entry->addr; + addrs[i] = entry->addr; + + /* Special case for ID0: set the correct ID */ + if (mptcp_addresses_equal(&entry->addr, &mpc_addr, entry->addr.port)) + addrs[i].id = 0; + + i++; } } rcu_read_unlock(); From 4878f9f8421f4587bee7b232c1c8a9d3a7d4d782 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:31 +0200 Subject: [PATCH 264/385] selftests: mptcp: join: validate fullmesh endp on 1st sf This case was not covered, and the wrong ID was set before the previous commit. The rest is not modified, it is just that it will increase the code coverage. The right address ID can be verified by looking at the packet traces. We could automate that using Netfilter with some cBPF code for example, but that's always a bit cryptic. Packetdrill seems better fitted for that. Fixes: 4f49d63352da ("selftests: mptcp: add fullmesh testcases") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-13-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index f609c02c6123e..89e553e0e0c2e 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3059,6 +3059,7 @@ fullmesh_tests() pm_nl_set_limits $ns1 1 3 pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,fullmesh fullmesh=1 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 3 3 3 From 48e50dcbcbaaf713d82bf2da5c16aeced94ad07d Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Mon, 19 Aug 2024 21:45:32 +0200 Subject: [PATCH 265/385] mptcp: pm: avoid possible UaF when selecting endp select_local_address() and select_signal_address() both select an endpoint entry from the list inside an RCU protected section, but return a reference to it, to be read later on. If the entry is dereferenced after the RCU unlock, reading info could cause a Use-after-Free. A simple solution is to copy the required info while inside the RCU protected section to avoid any risk of UaF later. The address ID might need to be modified later to handle the ID0 case later, so a copy seems OK to deal with. Reported-by: Paolo Abeni Closes: https://lore.kernel.org/45cd30d3-7710-491c-ae4d-a1368c00beb1@redhat.com Fixes: 01cacb00b35c ("mptcp: add netlink-based PM") Cc: stable@vger.kernel.org Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-14-38035d40de5b@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 64 ++++++++++++++++++++++-------------------- 1 file changed, 34 insertions(+), 30 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index a2e37ab1c40fc..3e4ad801786f2 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -143,11 +143,13 @@ static bool lookup_subflow_by_daddr(const struct list_head *list, return false; } -static struct mptcp_pm_addr_entry * +static bool select_local_address(const struct pm_nl_pernet *pernet, - const struct mptcp_sock *msk) + const struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *new_entry) { - struct mptcp_pm_addr_entry *entry, *ret = NULL; + struct mptcp_pm_addr_entry *entry; + bool found = false; msk_owned_by_me(msk); @@ -159,17 +161,21 @@ select_local_address(const struct pm_nl_pernet *pernet, if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap)) continue; - ret = entry; + *new_entry = *entry; + found = true; break; } rcu_read_unlock(); - return ret; + + return found; } -static struct mptcp_pm_addr_entry * -select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) +static bool +select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *new_entry) { - struct mptcp_pm_addr_entry *entry, *ret = NULL; + struct mptcp_pm_addr_entry *entry; + bool found = false; rcu_read_lock(); /* do not keep any additional per socket state, just signal @@ -184,11 +190,13 @@ select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) continue; - ret = entry; + *new_entry = *entry; + found = true; break; } rcu_read_unlock(); - return ret; + + return found; } unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk) @@ -512,9 +520,10 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info) static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { - struct mptcp_pm_addr_entry *local, *signal_and_subflow = NULL; struct sock *sk = (struct sock *)msk; + struct mptcp_pm_addr_entry local; unsigned int add_addr_signal_max; + bool signal_and_subflow = false; unsigned int local_addr_max; struct pm_nl_pernet *pernet; unsigned int subflows_max; @@ -565,23 +574,22 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL)) return; - local = select_signal_address(pernet, msk); - if (!local) + if (!select_signal_address(pernet, msk, &local)) goto subflow; /* If the alloc fails, we are on memory pressure, not worth * continuing, and trying to create subflows. */ - if (!mptcp_pm_alloc_anno_list(msk, &local->addr)) + if (!mptcp_pm_alloc_anno_list(msk, &local.addr)) return; - __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); + __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); msk->pm.add_addr_signaled++; - mptcp_pm_announce_addr(msk, &local->addr, false); + mptcp_pm_announce_addr(msk, &local.addr, false); mptcp_pm_nl_addr_send_ack(msk); - if (local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) - signal_and_subflow = local; + if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) + signal_and_subflow = true; } subflow: @@ -592,26 +600,22 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) bool fullmesh; int i, nr; - if (signal_and_subflow) { - local = signal_and_subflow; - signal_and_subflow = NULL; - } else { - local = select_local_address(pernet, msk); - if (!local) - break; - } + if (signal_and_subflow) + signal_and_subflow = false; + else if (!select_local_address(pernet, msk, &local)) + break; - fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH); + fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH); msk->pm.local_addr_used++; - __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); - nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs); + __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); + nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs); if (nr == 0) continue; spin_unlock_bh(&msk->pm.lock); for (i = 0; i < nr; i++) - __mptcp_subflow_connect(sk, &local->addr, &addrs[i]); + __mptcp_subflow_connect(sk, &local.addr, &addrs[i]); spin_lock_bh(&msk->pm.lock); } mptcp_pm_nl_check_work_pending(msk); From 4d36b2b1dea4ff528bd7d312d9c713a827656d75 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 19 Aug 2024 17:44:35 -0700 Subject: [PATCH 266/385] net: dsa: b53: Use dev_err_probe() Rather than print an error even when we get -EPROBE_DEFER, use dev_err_probe() to filter out those messages. Link: https://github.com/openwrt/openwrt/pull/11680 Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20240820004436.224603-1-florian.fainelli@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/b53/b53_mdio.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/b53/b53_mdio.c b/drivers/net/dsa/b53/b53_mdio.c index 897e5e8b3d692..31d070bf161a3 100644 --- a/drivers/net/dsa/b53/b53_mdio.c +++ b/drivers/net/dsa/b53/b53_mdio.c @@ -343,10 +343,9 @@ static int b53_mdio_probe(struct mdio_device *mdiodev) dev_set_drvdata(&mdiodev->dev, dev); ret = b53_switch_register(dev); - if (ret) { - dev_err(&mdiodev->dev, "failed to register switch: %i\n", ret); - return ret; - } + if (ret) + return dev_err_probe(&mdiodev->dev, ret, + "failed to register switch\n"); return ret; } From d785ed945de6955361aafc2d540d9bb7c6a69a65 Mon Sep 17 00:00:00 2001 From: Jinjian Song Date: Sat, 17 Aug 2024 16:33:55 +0800 Subject: [PATCH 267/385] net: wwan: t7xx: PCIe reset rescan WWAN device is programmed to boot in normal mode or fastboot mode, when triggering a device reset through ACPI call or fastboot switch command. Maintain state machine synchronization and reprobe logic after a device reset. The PCIe device reset triggered by several ways. E.g.: - fastboot: echo "fastboot_switching" > /sys/bus/pci/devices/${bdf}/t7xx_mode. - reset: echo "reset" > /sys/bus/pci/devices/${bdf}/t7xx_mode. - IRQ: PCIe device request driver to reset itself by an interrupt request. Use pci_reset_function() as a generic way to reset device, save and restore the PCIe configuration before and after reset device to ensure the reprobe process. Suggestion from Bjorn: Link: https://lore.kernel.org/all/20230127133034.GA1364550@bhelgaas/ Signed-off-by: Jinjian Song Signed-off-by: David S. Miller --- drivers/net/wwan/t7xx/t7xx_modem_ops.c | 47 ++++++++++++++++--- drivers/net/wwan/t7xx/t7xx_modem_ops.h | 9 +++- drivers/net/wwan/t7xx/t7xx_pci.c | 53 ++++++++++++++++++---- drivers/net/wwan/t7xx/t7xx_pci.h | 3 ++ drivers/net/wwan/t7xx/t7xx_port_proxy.c | 1 - drivers/net/wwan/t7xx/t7xx_port_trace.c | 1 + drivers/net/wwan/t7xx/t7xx_state_monitor.c | 34 +++++--------- 7 files changed, 105 insertions(+), 43 deletions(-) diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.c b/drivers/net/wwan/t7xx/t7xx_modem_ops.c index 8d864d4ed77f5..79f17100f70b1 100644 --- a/drivers/net/wwan/t7xx/t7xx_modem_ops.c +++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.c @@ -53,6 +53,7 @@ #define RGU_RESET_DELAY_MS 10 #define PORT_RESET_DELAY_MS 2000 +#define FASTBOOT_RESET_DELAY_MS 2000 #define EX_HS_TIMEOUT_MS 5000 #define EX_HS_POLL_DELAY_MS 10 @@ -167,19 +168,52 @@ static int t7xx_acpi_reset(struct t7xx_pci_dev *t7xx_dev, char *fn_name) } kfree(buffer.pointer); +#else + struct device *dev = &t7xx_dev->pdev->dev; + int ret; + ret = pci_reset_function(t7xx_dev->pdev); + if (ret) { + dev_err(dev, "Failed to reset device, error:%d\n", ret); + return ret; + } #endif return 0; } -int t7xx_acpi_fldr_func(struct t7xx_pci_dev *t7xx_dev) +static void t7xx_host_event_notify(struct t7xx_pci_dev *t7xx_dev, unsigned int event_id) { - return t7xx_acpi_reset(t7xx_dev, "_RST"); + u32 value; + + value = ioread32(IREG_BASE(t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS); + value &= ~HOST_EVENT_MASK; + value |= FIELD_PREP(HOST_EVENT_MASK, event_id); + iowrite32(value, IREG_BASE(t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS); } -int t7xx_acpi_pldr_func(struct t7xx_pci_dev *t7xx_dev) +int t7xx_reset_device(struct t7xx_pci_dev *t7xx_dev, enum reset_type type) { - return t7xx_acpi_reset(t7xx_dev, "MRST._RST"); + int ret = 0; + + pci_save_state(t7xx_dev->pdev); + t7xx_pci_reprobe_early(t7xx_dev); + t7xx_mode_update(t7xx_dev, T7XX_RESET); + + if (type == FLDR) { + ret = t7xx_acpi_reset(t7xx_dev, "_RST"); + } else if (type == PLDR) { + ret = t7xx_acpi_reset(t7xx_dev, "MRST._RST"); + } else if (type == FASTBOOT) { + t7xx_host_event_notify(t7xx_dev, FASTBOOT_DL_NOTIFY); + t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DEVICE_RESET); + msleep(FASTBOOT_RESET_DELAY_MS); + } + + pci_restore_state(t7xx_dev->pdev); + if (ret) + return ret; + + return t7xx_pci_reprobe(t7xx_dev, true); } static void t7xx_reset_device_via_pmic(struct t7xx_pci_dev *t7xx_dev) @@ -188,16 +222,15 @@ static void t7xx_reset_device_via_pmic(struct t7xx_pci_dev *t7xx_dev) val = ioread32(IREG_BASE(t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS); if (val & MISC_RESET_TYPE_PLDR) - t7xx_acpi_reset(t7xx_dev, "MRST._RST"); + t7xx_reset_device(t7xx_dev, PLDR); else if (val & MISC_RESET_TYPE_FLDR) - t7xx_acpi_fldr_func(t7xx_dev); + t7xx_reset_device(t7xx_dev, FLDR); } static irqreturn_t t7xx_rgu_isr_thread(int irq, void *data) { struct t7xx_pci_dev *t7xx_dev = data; - t7xx_mode_update(t7xx_dev, T7XX_RESET); msleep(RGU_RESET_DELAY_MS); t7xx_reset_device_via_pmic(t7xx_dev); return IRQ_HANDLED; diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.h b/drivers/net/wwan/t7xx/t7xx_modem_ops.h index b39e945a92e01..39ed0000fbba2 100644 --- a/drivers/net/wwan/t7xx/t7xx_modem_ops.h +++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.h @@ -78,14 +78,19 @@ struct t7xx_modem { spinlock_t exp_lock; /* Protects exception events */ }; +enum reset_type { + FLDR, + PLDR, + FASTBOOT, +}; + void t7xx_md_exception_handshake(struct t7xx_modem *md); void t7xx_md_event_notify(struct t7xx_modem *md, enum md_event_id evt_id); int t7xx_md_reset(struct t7xx_pci_dev *t7xx_dev); int t7xx_md_init(struct t7xx_pci_dev *t7xx_dev); void t7xx_md_exit(struct t7xx_pci_dev *t7xx_dev); void t7xx_clear_rgu_irq(struct t7xx_pci_dev *t7xx_dev); -int t7xx_acpi_fldr_func(struct t7xx_pci_dev *t7xx_dev); -int t7xx_acpi_pldr_func(struct t7xx_pci_dev *t7xx_dev); +int t7xx_reset_device(struct t7xx_pci_dev *t7xx_dev, enum reset_type type); int t7xx_pci_mhccif_isr(struct t7xx_pci_dev *t7xx_dev); #endif /* __T7XX_MODEM_OPS_H__ */ diff --git a/drivers/net/wwan/t7xx/t7xx_pci.c b/drivers/net/wwan/t7xx/t7xx_pci.c index 10a8c1080b102..e556e5bd49abc 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.c +++ b/drivers/net/wwan/t7xx/t7xx_pci.c @@ -69,6 +69,7 @@ static ssize_t t7xx_mode_store(struct device *dev, { struct t7xx_pci_dev *t7xx_dev; struct pci_dev *pdev; + enum t7xx_mode mode; int index = 0; pdev = to_pci_dev(dev); @@ -76,12 +77,22 @@ static ssize_t t7xx_mode_store(struct device *dev, if (!t7xx_dev) return -ENODEV; + mode = READ_ONCE(t7xx_dev->mode); + index = sysfs_match_string(t7xx_mode_names, buf); + if (index == mode) + return -EBUSY; + if (index == T7XX_FASTBOOT_SWITCHING) { + if (mode == T7XX_FASTBOOT_DOWNLOAD) + return count; + WRITE_ONCE(t7xx_dev->mode, T7XX_FASTBOOT_SWITCHING); + pm_runtime_resume(dev); + t7xx_reset_device(t7xx_dev, FASTBOOT); } else if (index == T7XX_RESET) { - WRITE_ONCE(t7xx_dev->mode, T7XX_RESET); - t7xx_acpi_pldr_func(t7xx_dev); + pm_runtime_resume(dev); + t7xx_reset_device(t7xx_dev, PLDR); } return count; @@ -446,7 +457,7 @@ static int t7xx_pcie_reinit(struct t7xx_pci_dev *t7xx_dev, bool is_d3) if (is_d3) { t7xx_mhccif_init(t7xx_dev); - return t7xx_pci_pm_reinit(t7xx_dev); + t7xx_pci_pm_reinit(t7xx_dev); } return 0; @@ -481,6 +492,33 @@ static int t7xx_send_fsm_command(struct t7xx_pci_dev *t7xx_dev, u32 event) return ret; } +int t7xx_pci_reprobe_early(struct t7xx_pci_dev *t7xx_dev) +{ + enum t7xx_mode mode = READ_ONCE(t7xx_dev->mode); + int ret; + + if (mode == T7XX_FASTBOOT_DOWNLOAD) + pm_runtime_put_noidle(&t7xx_dev->pdev->dev); + + ret = t7xx_send_fsm_command(t7xx_dev, FSM_CMD_STOP); + if (ret) + return ret; + + return 0; +} + +int t7xx_pci_reprobe(struct t7xx_pci_dev *t7xx_dev, bool boot) +{ + int ret; + + ret = t7xx_pcie_reinit(t7xx_dev, boot); + if (ret) + return ret; + + t7xx_clear_rgu_irq(t7xx_dev); + return t7xx_send_fsm_command(t7xx_dev, FSM_CMD_START); +} + static int __t7xx_pci_pm_resume(struct pci_dev *pdev, bool state_check) { struct t7xx_pci_dev *t7xx_dev; @@ -507,16 +545,11 @@ static int __t7xx_pci_pm_resume(struct pci_dev *pdev, bool state_check) if (prev_state == PM_RESUME_REG_STATE_L3 || (prev_state == PM_RESUME_REG_STATE_INIT && atr_reg_val == ATR_SRC_ADDR_INVALID)) { - ret = t7xx_send_fsm_command(t7xx_dev, FSM_CMD_STOP); - if (ret) - return ret; - - ret = t7xx_pcie_reinit(t7xx_dev, true); + ret = t7xx_pci_reprobe_early(t7xx_dev); if (ret) return ret; - t7xx_clear_rgu_irq(t7xx_dev); - return t7xx_send_fsm_command(t7xx_dev, FSM_CMD_START); + return t7xx_pci_reprobe(t7xx_dev, true); } if (prev_state == PM_RESUME_REG_STATE_EXP || diff --git a/drivers/net/wwan/t7xx/t7xx_pci.h b/drivers/net/wwan/t7xx/t7xx_pci.h index 49a11586d8d84..cd8ea17c26441 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.h +++ b/drivers/net/wwan/t7xx/t7xx_pci.h @@ -133,4 +133,7 @@ int t7xx_pci_pm_entity_unregister(struct t7xx_pci_dev *t7xx_dev, struct md_pm_en void t7xx_pci_pm_init_late(struct t7xx_pci_dev *t7xx_dev); void t7xx_pci_pm_exp_detected(struct t7xx_pci_dev *t7xx_dev); void t7xx_mode_update(struct t7xx_pci_dev *t7xx_dev, enum t7xx_mode mode); +int t7xx_pci_reprobe(struct t7xx_pci_dev *t7xx_dev, bool boot); +int t7xx_pci_reprobe_early(struct t7xx_pci_dev *t7xx_dev); + #endif /* __T7XX_PCI_H__ */ diff --git a/drivers/net/wwan/t7xx/t7xx_port_proxy.c b/drivers/net/wwan/t7xx/t7xx_port_proxy.c index 7d6388bf1d7c3..35743e7de0c30 100644 --- a/drivers/net/wwan/t7xx/t7xx_port_proxy.c +++ b/drivers/net/wwan/t7xx/t7xx_port_proxy.c @@ -553,7 +553,6 @@ static int t7xx_proxy_alloc(struct t7xx_modem *md) md->port_prox = port_prox; port_prox->dev = dev; - t7xx_port_proxy_set_cfg(md, PORT_CFG_ID_EARLY); return 0; } diff --git a/drivers/net/wwan/t7xx/t7xx_port_trace.c b/drivers/net/wwan/t7xx/t7xx_port_trace.c index 6a3f363858655..4ed8b4e29bf1d 100644 --- a/drivers/net/wwan/t7xx/t7xx_port_trace.c +++ b/drivers/net/wwan/t7xx/t7xx_port_trace.c @@ -59,6 +59,7 @@ static void t7xx_trace_port_uninit(struct t7xx_port *port) relay_close(relaych); debugfs_remove_recursive(debugfs_dir); + port->log.relaych = NULL; } static int t7xx_trace_port_recv_skb(struct t7xx_port *port, struct sk_buff *skb) diff --git a/drivers/net/wwan/t7xx/t7xx_state_monitor.c b/drivers/net/wwan/t7xx/t7xx_state_monitor.c index 9889ca4621cf5..3931c7a13f5ab 100644 --- a/drivers/net/wwan/t7xx/t7xx_state_monitor.c +++ b/drivers/net/wwan/t7xx/t7xx_state_monitor.c @@ -213,16 +213,6 @@ static void fsm_routine_exception(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_comm fsm_finish_command(ctl, cmd, 0); } -static void t7xx_host_event_notify(struct t7xx_modem *md, unsigned int event_id) -{ - u32 value; - - value = ioread32(IREG_BASE(md->t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS); - value &= ~HOST_EVENT_MASK; - value |= FIELD_PREP(HOST_EVENT_MASK, event_id); - iowrite32(value, IREG_BASE(md->t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS); -} - static void t7xx_lk_stage_event_handling(struct t7xx_fsm_ctl *ctl, unsigned int status) { struct t7xx_modem *md = ctl->md; @@ -264,8 +254,14 @@ static void t7xx_lk_stage_event_handling(struct t7xx_fsm_ctl *ctl, unsigned int static int fsm_stopped_handler(struct t7xx_fsm_ctl *ctl) { + enum t7xx_mode mode; + ctl->curr_state = FSM_STATE_STOPPED; + mode = READ_ONCE(ctl->md->t7xx_dev->mode); + if (mode == T7XX_FASTBOOT_DOWNLOAD || mode == T7XX_FASTBOOT_DUMP) + return 0; + t7xx_fsm_broadcast_state(ctl, MD_STATE_STOPPED); return t7xx_md_reset(ctl->md->t7xx_dev); } @@ -284,8 +280,6 @@ static void fsm_routine_stopping(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_comma { struct cldma_ctrl *md_ctrl = ctl->md->md_ctrl[CLDMA_ID_MD]; struct t7xx_pci_dev *t7xx_dev = ctl->md->t7xx_dev; - enum t7xx_mode mode = READ_ONCE(t7xx_dev->mode); - int err; if (ctl->curr_state == FSM_STATE_STOPPED || ctl->curr_state == FSM_STATE_STOPPING) { fsm_finish_command(ctl, cmd, -EINVAL); @@ -296,21 +290,10 @@ static void fsm_routine_stopping(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_comma t7xx_fsm_broadcast_state(ctl, MD_STATE_WAITING_TO_STOP); t7xx_cldma_stop(md_ctrl); - if (mode == T7XX_FASTBOOT_SWITCHING) - t7xx_host_event_notify(ctl->md, FASTBOOT_DL_NOTIFY); - t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DRM_DISABLE_AP); /* Wait for the DRM disable to take effect */ msleep(FSM_DRM_DISABLE_DELAY_MS); - if (mode == T7XX_FASTBOOT_SWITCHING) { - t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DEVICE_RESET); - } else { - err = t7xx_acpi_fldr_func(t7xx_dev); - if (err) - t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DEVICE_RESET); - } - fsm_finish_command(ctl, cmd, fsm_stopped_handler(ctl)); } @@ -414,7 +397,9 @@ static void fsm_routine_start(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_command case T7XX_DEV_STAGE_LK: dev_dbg(dev, "LK_STAGE Entered\n"); + t7xx_port_proxy_set_cfg(md, PORT_CFG_ID_EARLY); t7xx_lk_stage_event_handling(ctl, status); + break; case T7XX_DEV_STAGE_LINUX: @@ -436,6 +421,9 @@ static void fsm_routine_start(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_command } finish_command: + if (ret) + t7xx_mode_update(md->t7xx_dev, T7XX_UNKNOWN); + fsm_finish_command(ctl, cmd, ret); } From b128ed5ab27330deeeaf51ea8bb69f1442a96f7f Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Mon, 19 Aug 2024 17:06:21 +0200 Subject: [PATCH 268/385] udp: fix receiving fraglist GSO packets When assembling fraglist GSO packets, udp4_gro_complete does not set skb->csum_start, which makes the extra validation in __udp_gso_segment fail. Fixes: 89add40066f9 ("net: drop bad gso csum_start and offset in virtio_net_hdr") Signed-off-by: Felix Fietkau Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20240819150621.59833-1-nbd@nbd.name Signed-off-by: Jakub Kicinski --- net/ipv4/udp_offload.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index b254a5dadfcf3..d842303587af9 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -279,7 +279,8 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, return ERR_PTR(-EINVAL); if (unlikely(skb_checksum_start(gso_skb) != - skb_transport_header(gso_skb))) + skb_transport_header(gso_skb) && + !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST))) return ERR_PTR(-EINVAL); /* We don't know if egress device can segment and checksum the packet From 488d34643ec3f4ce5ce120846fc81412534e9af1 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Mon, 19 Aug 2024 19:27:11 -0600 Subject: [PATCH 269/385] nfc: pn533: Avoid -Wflex-array-member-not-at-end warnings -Wflex-array-member-not-at-end was introduced in GCC-14, and we are getting ready to enable it, globally. Remove unnecessary flex-array member `data[]`, and with this fix the following warnings: drivers/nfc/pn533/usb.c:268:38: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end] drivers/nfc/pn533/usb.c:275:38: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end] Signed-off-by: Gustavo A. R. Silva Reviewed-by: Simon Horman Link: https://patch.msgid.link/ZsPw7+6vNoS651Cb@elsanto Signed-off-by: Jakub Kicinski --- drivers/nfc/pn533/usb.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index a187f0e0b0f7d..ffd7367ce1194 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -254,7 +254,6 @@ struct pn533_acr122_ccid_hdr { * byte for reposnse msg */ u8 params[3]; - u8 data[]; /* payload */ } __packed; struct pn533_acr122_apdu_hdr { From e58c3f3d5196952ffa29dd987a15405b7f559af9 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Tue, 20 Aug 2024 15:48:05 +0800 Subject: [PATCH 270/385] net: dsa: ocelot: Simplify with scoped for each OF child loop Use scoped for_each_available_child_of_node_scoped() when iterating over device nodes to make code a bit simpler. Signed-off-by: Jinjie Ruan Link: https://patch.msgid.link/20240820074805.680674-1-ruanjinjie@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/ocelot/felix.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index e554699f06d41..800711c2b6cbd 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1265,9 +1265,8 @@ static int felix_parse_ports_node(struct felix *felix, phy_interface_t *port_phy_modes) { struct device *dev = felix->ocelot.dev; - struct device_node *child; - for_each_available_child_of_node(ports_node, child) { + for_each_available_child_of_node_scoped(ports_node, child) { phy_interface_t phy_mode; u32 port; int err; @@ -1276,7 +1275,6 @@ static int felix_parse_ports_node(struct felix *felix, if (of_property_read_u32(child, "reg", &port) < 0) { dev_err(dev, "Port number not defined in device tree " "(property \"reg\")\n"); - of_node_put(child); return -ENODEV; } @@ -1286,7 +1284,6 @@ static int felix_parse_ports_node(struct felix *felix, dev_err(dev, "Failed to read phy-mode or " "phy-interface-type property for port %d\n", port); - of_node_put(child); return -ENODEV; } From 2d86ecb64b51127f0d9eac29cd4c58215246a029 Mon Sep 17 00:00:00 2001 From: Jinjie Ruan Date: Tue, 20 Aug 2024 15:50:47 +0800 Subject: [PATCH 271/385] net: dsa: sja1105: Simplify with scoped for each OF child loop Use scoped for_each_available_child_of_node_scoped() when iterating over device nodes to make code a bit simpler. Signed-off-by: Jinjie Ruan Link: https://patch.msgid.link/20240820075047.681223-1-ruanjinjie@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/sja1105/sja1105_main.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index c7282ce3d11c5..bc7e50dcb57c7 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1188,9 +1188,8 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, struct device_node *ports_node) { struct device *dev = &priv->spidev->dev; - struct device_node *child; - for_each_available_child_of_node(ports_node, child) { + for_each_available_child_of_node_scoped(ports_node, child) { struct device_node *phy_node; phy_interface_t phy_mode; u32 index; @@ -1200,7 +1199,6 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, if (of_property_read_u32(child, "reg", &index) < 0) { dev_err(dev, "Port number not defined in device tree " "(property \"reg\")\n"); - of_node_put(child); return -ENODEV; } @@ -1210,7 +1208,6 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, dev_err(dev, "Failed to read phy-mode or " "phy-interface-type property for port %d\n", index); - of_node_put(child); return -ENODEV; } @@ -1219,7 +1216,6 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, if (!of_phy_is_fixed_link(child)) { dev_err(dev, "phy-handle or fixed-link " "properties missing!\n"); - of_node_put(child); return -ENODEV; } /* phy-handle is missing, but fixed-link isn't. @@ -1233,10 +1229,8 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, priv->phy_mode[index] = phy_mode; err = sja1105_parse_rgmii_delays(priv, index, child); - if (err) { - of_node_put(child); + if (err) return err; - } } return 0; From f8669d7b5f5d2d88959456ae9123d8bb6fdc1ebe Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 20 Aug 2024 12:53:47 +0200 Subject: [PATCH 272/385] selftests: mlxsw: ethtool_lanes: Source ethtool lib from correct path Source the ethtool library from the correct path and avoid the following error: ./ethtool_lanes.sh: line 14: ./../../../net/forwarding/ethtool_lib.sh: No such file or directory Fixes: 40d269c000bd ("selftests: forwarding: Move several selftests") Signed-off-by: Ido Schimmel Signed-off-by: Petr Machata Reviewed-by: Simon Horman Link: https://patch.msgid.link/2112faff02e536e1ac14beb4c2be09c9574b90ae.1724150067.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh b/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh index 877cd6df94a10..fe905a7f34b3c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh @@ -2,6 +2,7 @@ # SPDX-License-Identifier: GPL-2.0 lib_dir=$(dirname $0)/../../../net/forwarding +ethtool_lib_dir=$(dirname $0)/../hw ALL_TESTS=" autoneg @@ -11,7 +12,7 @@ ALL_TESTS=" NUM_NETIFS=2 : ${TIMEOUT:=30000} # ms source $lib_dir/lib.sh -source $lib_dir/ethtool_lib.sh +source $ethtool_lib_dir/ethtool_lib.sh setup_prepare() { From d35a3a8f1b7f27ac1ea0f7068dcab0c08846ac44 Mon Sep 17 00:00:00 2001 From: Xi Huang Date: Tue, 20 Aug 2024 19:54:42 +0800 Subject: [PATCH 273/385] ipv6: remove redundant check err varibale will be set everytime,like -ENOBUFS and in if (err < 0), when code gets into this path. This check will just slowdown the execution and that's all. Signed-off-by: Xi Huang Reviewed-by: Florian Westphal Link: https://patch.msgid.link/20240820115442.49366-1-xuiagnh@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv6/addrconf.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 04ee75af2f6b7..d680beb91b0a2 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5619,8 +5619,7 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err); } static void ipv6_store_devconf(const struct ipv6_devconf *cnf, @@ -6175,8 +6174,7 @@ void inet6_ifinfo_notify(int event, struct inet6_dev *idev) rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFINFO, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_IFINFO, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_IFINFO, err); } static inline size_t inet6_prefix_nlmsg_size(void) @@ -6243,8 +6241,7 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev, rtnl_notify(skb, net, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err); } static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) From 0ce054f2b891afdd102c8bcc1fc57253c8964e40 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 20 Aug 2024 16:43:46 +0300 Subject: [PATCH 274/385] ice: Fix a 32bit bug BIT() is unsigned long but ->pu.flg_msk and ->pu.flg_val are u64 type. On 32 bit systems, unsigned long is a u32 and the mismatch between u32 and u64 will break things for the high 32 bits. Fixes: 9a4c07aaa0f5 ("ice: add parser execution main loop") Signed-off-by: Dan Carpenter Reviewed-by: Alexander Lobakin Link: https://patch.msgid.link/ddc231a8-89c1-4ff4-8704-9198bcb41f8d@stanley.mountain Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ice/ice_parser_rt.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_parser_rt.c b/drivers/net/ethernet/intel/ice/ice_parser_rt.c index d5bcc266b01ec..dedf5e854e4b7 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser_rt.c +++ b/drivers/net/ethernet/intel/ice/ice_parser_rt.c @@ -377,11 +377,11 @@ static void ice_pg_exe(struct ice_parser_rt *rt) static void ice_flg_add(struct ice_parser_rt *rt, int idx, bool val) { - rt->pu.flg_msk |= BIT(idx); + rt->pu.flg_msk |= BIT_ULL(idx); if (val) - rt->pu.flg_val |= BIT(idx); + rt->pu.flg_val |= BIT_ULL(idx); else - rt->pu.flg_val &= ~BIT(idx); + rt->pu.flg_val &= ~BIT_ULL(idx); ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Pending update for flag %d value %d\n", idx, val); From 007d4271a5f10638cba6f0b99698557ef30014b9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Aug 2024 16:20:53 +0000 Subject: [PATCH 275/385] netpoll: do not export netpoll_poll_[disable|enable]() netpoll_poll_disable() and netpoll_poll_enable() are only used from core networking code, there is no need to export them. Signed-off-by: Eric Dumazet Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240820162053.3870927-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/core/netpoll.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 55bcacf67df3b..d657b042d5a04 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -228,7 +228,6 @@ void netpoll_poll_disable(struct net_device *dev) down(&ni->dev_lock); srcu_read_unlock(&netpoll_srcu, idx); } -EXPORT_SYMBOL(netpoll_poll_disable); void netpoll_poll_enable(struct net_device *dev) { @@ -239,7 +238,6 @@ void netpoll_poll_enable(struct net_device *dev) up(&ni->dev_lock); rcu_read_unlock(); } -EXPORT_SYMBOL(netpoll_poll_enable); static void refill_skbs(void) { From faa389b2fbaaec7fd27a390b4896139f9da662e3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Aug 2024 16:08:57 +0000 Subject: [PATCH 276/385] ipv6: prevent UAF in ip6_send_skb() syzbot reported an UAF in ip6_send_skb() [1] After ip6_local_out() has returned, we no longer can safely dereference rt, unless we hold rcu_read_lock(). A similar issue has been fixed in commit a688caa34beb ("ipv6: take rcu lock in rawv6_send_hdrinc()") Another potential issue in ip6_finish_output2() is handled in a separate patch. [1] BUG: KASAN: slab-use-after-free in ip6_send_skb+0x18d/0x230 net/ipv6/ip6_output.c:1964 Read of size 8 at addr ffff88806dde4858 by task syz.1.380/6530 CPU: 1 UID: 0 PID: 6530 Comm: syz.1.380 Not tainted 6.11.0-rc3-syzkaller-00306-gdf6cbc62cc9b #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/06/2024 Call Trace: __dump_stack lib/dump_stack.c:93 [inline] dump_stack_lvl+0x241/0x360 lib/dump_stack.c:119 print_address_description mm/kasan/report.c:377 [inline] print_report+0x169/0x550 mm/kasan/report.c:488 kasan_report+0x143/0x180 mm/kasan/report.c:601 ip6_send_skb+0x18d/0x230 net/ipv6/ip6_output.c:1964 rawv6_push_pending_frames+0x75c/0x9e0 net/ipv6/raw.c:588 rawv6_sendmsg+0x19c7/0x23c0 net/ipv6/raw.c:926 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x1a6/0x270 net/socket.c:745 sock_write_iter+0x2dd/0x400 net/socket.c:1160 do_iter_readv_writev+0x60a/0x890 vfs_writev+0x37c/0xbb0 fs/read_write.c:971 do_writev+0x1b1/0x350 fs/read_write.c:1018 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f936bf79e79 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f936cd7f038 EFLAGS: 00000246 ORIG_RAX: 0000000000000014 RAX: ffffffffffffffda RBX: 00007f936c115f80 RCX: 00007f936bf79e79 RDX: 0000000000000001 RSI: 0000000020000040 RDI: 0000000000000004 RBP: 00007f936bfe7916 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000000000 R14: 00007f936c115f80 R15: 00007fff2860a7a8 Allocated by task 6530: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 unpoison_slab_object mm/kasan/common.c:312 [inline] __kasan_slab_alloc+0x66/0x80 mm/kasan/common.c:338 kasan_slab_alloc include/linux/kasan.h:201 [inline] slab_post_alloc_hook mm/slub.c:3988 [inline] slab_alloc_node mm/slub.c:4037 [inline] kmem_cache_alloc_noprof+0x135/0x2a0 mm/slub.c:4044 dst_alloc+0x12b/0x190 net/core/dst.c:89 ip6_blackhole_route+0x59/0x340 net/ipv6/route.c:2670 make_blackhole net/xfrm/xfrm_policy.c:3120 [inline] xfrm_lookup_route+0xd1/0x1c0 net/xfrm/xfrm_policy.c:3313 ip6_dst_lookup_flow+0x13e/0x180 net/ipv6/ip6_output.c:1257 rawv6_sendmsg+0x1283/0x23c0 net/ipv6/raw.c:898 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x1a6/0x270 net/socket.c:745 ____sys_sendmsg+0x525/0x7d0 net/socket.c:2597 ___sys_sendmsg net/socket.c:2651 [inline] __sys_sendmsg+0x2b0/0x3a0 net/socket.c:2680 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f Freed by task 45: kasan_save_stack mm/kasan/common.c:47 [inline] kasan_save_track+0x3f/0x80 mm/kasan/common.c:68 kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:579 poison_slab_object+0xe0/0x150 mm/kasan/common.c:240 __kasan_slab_free+0x37/0x60 mm/kasan/common.c:256 kasan_slab_free include/linux/kasan.h:184 [inline] slab_free_hook mm/slub.c:2252 [inline] slab_free mm/slub.c:4473 [inline] kmem_cache_free+0x145/0x350 mm/slub.c:4548 dst_destroy+0x2ac/0x460 net/core/dst.c:124 rcu_do_batch kernel/rcu/tree.c:2569 [inline] rcu_core+0xafd/0x1830 kernel/rcu/tree.c:2843 handle_softirqs+0x2c4/0x970 kernel/softirq.c:554 __do_softirq kernel/softirq.c:588 [inline] invoke_softirq kernel/softirq.c:428 [inline] __irq_exit_rcu+0xf4/0x1c0 kernel/softirq.c:637 irq_exit_rcu+0x9/0x30 kernel/softirq.c:649 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1043 [inline] sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1043 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:702 Last potentially related work creation: kasan_save_stack+0x3f/0x60 mm/kasan/common.c:47 __kasan_record_aux_stack+0xac/0xc0 mm/kasan/generic.c:541 __call_rcu_common kernel/rcu/tree.c:3106 [inline] call_rcu+0x167/0xa70 kernel/rcu/tree.c:3210 refdst_drop include/net/dst.h:263 [inline] skb_dst_drop include/net/dst.h:275 [inline] nf_ct_frag6_queue net/ipv6/netfilter/nf_conntrack_reasm.c:306 [inline] nf_ct_frag6_gather+0xb9a/0x2080 net/ipv6/netfilter/nf_conntrack_reasm.c:485 ipv6_defrag+0x2c8/0x3c0 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:67 nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline] nf_hook_slow+0xc3/0x220 net/netfilter/core.c:626 nf_hook include/linux/netfilter.h:269 [inline] __ip6_local_out+0x6fa/0x800 net/ipv6/output_core.c:143 ip6_local_out+0x26/0x70 net/ipv6/output_core.c:153 ip6_send_skb+0x112/0x230 net/ipv6/ip6_output.c:1959 rawv6_push_pending_frames+0x75c/0x9e0 net/ipv6/raw.c:588 rawv6_sendmsg+0x19c7/0x23c0 net/ipv6/raw.c:926 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg+0x1a6/0x270 net/socket.c:745 sock_write_iter+0x2dd/0x400 net/socket.c:1160 do_iter_readv_writev+0x60a/0x890 Fixes: 0625491493d9 ("ipv6: ip6_push_pending_frames() should increment IPSTATS_MIB_OUTDISCARDS") Signed-off-by: Eric Dumazet Reported-by: syzbot Reviewed-by: David Ahern Link: https://patch.msgid.link/20240820160859.3786976-2-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_output.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ab504d31f0cdd..f7b53effc80f8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1956,6 +1956,7 @@ int ip6_send_skb(struct sk_buff *skb) struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); int err; + rcu_read_lock(); err = ip6_local_out(net, skb->sk, skb); if (err) { if (err > 0) @@ -1965,6 +1966,7 @@ int ip6_send_skb(struct sk_buff *skb) IPSTATS_MIB_OUTDISCARDS); } + rcu_read_unlock(); return err; } From da273b377ae0d9bd255281ed3c2adb228321687b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Aug 2024 16:08:58 +0000 Subject: [PATCH 277/385] ipv6: fix possible UAF in ip6_finish_output2() If skb_expand_head() returns NULL, skb has been freed and associated dst/idev could also have been freed. We need to hold rcu_read_lock() to make sure the dst and associated idev are alive. Fixes: 5796015fa968 ("ipv6: allocate enough headroom in ip6_finish_output2()") Signed-off-by: Eric Dumazet Cc: Vasily Averin Reviewed-by: David Ahern Link: https://patch.msgid.link/20240820160859.3786976-3-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_output.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index f7b53effc80f8..1b9ebee7308f0 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -70,11 +70,15 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * /* Be paranoid, rather than too clever. */ if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) { + /* Make sure idev stays alive */ + rcu_read_lock(); skb = skb_expand_head(skb, hh_len); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); return -ENOMEM; } + rcu_read_unlock(); } hdr = ipv6_hdr(skb); From 2d5ff7e339d04622d8282661df36151906d0e1c7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Aug 2024 16:08:59 +0000 Subject: [PATCH 278/385] ipv6: prevent possible UAF in ip6_xmit() If skb_expand_head() returns NULL, skb has been freed and the associated dst/idev could also have been freed. We must use rcu_read_lock() to prevent a possible UAF. Fixes: 0c9f227bee11 ("ipv6: use skb_expand_head in ip6_xmit") Signed-off-by: Eric Dumazet Cc: Vasily Averin Reviewed-by: David Ahern Link: https://patch.msgid.link/20240820160859.3786976-4-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/ip6_output.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 1b9ebee7308f0..f26841f1490f5 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -287,11 +287,15 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, head_room += opt->opt_nflen + opt->opt_flen; if (unlikely(head_room > skb_headroom(skb))) { + /* Make sure idev stays alive */ + rcu_read_lock(); skb = skb_expand_head(skb, head_room); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); return -ENOBUFS; } + rcu_read_unlock(); } if (opt) { From 8baeef7616d5194045c5a6b97fd1246b87c55b13 Mon Sep 17 00:00:00 2001 From: Somnath Kotur Date: Tue, 20 Aug 2024 13:34:15 -0700 Subject: [PATCH 279/385] bnxt_en: Fix double DMA unmapping for XDP_REDIRECT Remove the dma_unmap_page_attrs() call in the driver's XDP_REDIRECT code path. This should have been removed when we let the page pool handle the DMA mapping. This bug causes the warning: WARNING: CPU: 7 PID: 59 at drivers/iommu/dma-iommu.c:1198 iommu_dma_unmap_page+0xd5/0x100 CPU: 7 PID: 59 Comm: ksoftirqd/7 Tainted: G W 6.8.0-1010-gcp #11-Ubuntu Hardware name: Dell Inc. PowerEdge R7525/0PYVT1, BIOS 2.15.2 04/02/2024 RIP: 0010:iommu_dma_unmap_page+0xd5/0x100 Code: 89 ee 48 89 df e8 cb f2 69 ff 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d 31 c0 31 d2 31 c9 31 f6 31 ff 45 31 c0 e9 ab 17 71 00 <0f> 0b 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d 31 c0 31 d2 31 c9 RSP: 0018:ffffab1fc0597a48 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff99ff838280c8 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffab1fc0597a78 R08: 0000000000000002 R09: ffffab1fc0597c1c R10: ffffab1fc0597cd3 R11: ffff99ffe375acd8 R12: 00000000e65b9000 R13: 0000000000000050 R14: 0000000000001000 R15: 0000000000000002 FS: 0000000000000000(0000) GS:ffff9a06efb80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000565c34c37210 CR3: 00000005c7e3e000 CR4: 0000000000350ef0 ? show_regs+0x6d/0x80 ? __warn+0x89/0x150 ? iommu_dma_unmap_page+0xd5/0x100 ? report_bug+0x16a/0x190 ? handle_bug+0x51/0xa0 ? exc_invalid_op+0x18/0x80 ? iommu_dma_unmap_page+0xd5/0x100 ? iommu_dma_unmap_page+0x35/0x100 dma_unmap_page_attrs+0x55/0x220 ? bpf_prog_4d7e87c0d30db711_xdp_dispatcher+0x64/0x9f bnxt_rx_xdp+0x237/0x520 [bnxt_en] bnxt_rx_pkt+0x640/0xdd0 [bnxt_en] __bnxt_poll_work+0x1a1/0x3d0 [bnxt_en] bnxt_poll+0xaa/0x1e0 [bnxt_en] __napi_poll+0x33/0x1e0 net_rx_action+0x18a/0x2f0 Fixes: 578fcfd26e2a ("bnxt_en: Let the page pool manage the DMA mapping") Reviewed-by: Andy Gospodarek Reviewed-by: Kalesh AP Signed-off-by: Somnath Kotur Signed-off-by: Michael Chan Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20240820203415.168178-1-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 345681d5007e3..f88b641533fcc 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -297,11 +297,6 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, * redirect is coming from a frame received by the * bnxt_en driver. */ - rx_buf = &rxr->rx_buf_ring[cons]; - mapping = rx_buf->mapping - bp->rx_dma_offset; - dma_unmap_page_attrs(&pdev->dev, mapping, - BNXT_RX_PAGE_SIZE, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); /* if we are unable to allocate a new buffer, abort and reuse */ if (bnxt_alloc_rx_data(bp, rxr, rxr->rx_prod, GFP_ATOMIC)) { From 74b1e94e94ea369923e5656eeb10b26b16591327 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 20 Aug 2024 13:51:19 -0700 Subject: [PATCH 280/385] net: repack struct netdev_queue Adding the NAPI pointer to struct netdev_queue made it grow into another cacheline, even though there was 44 bytes of padding available. The struct was historically grouped as follows: /* read-mostly stuff (align) */ /* ... random control path fields ... */ /* write-mostly stuff (align) */ /* ... 40 byte hole ... */ /* struct dql (align) */ It seems that people want to add control path fields after the read only fields. struct dql looks pretty innocent but it forces its own alignment and nothing indicates that there is a lot of empty space above it. Move dql above the xmit_lock. This shifts the empty space to the end of the struct rather than in the middle of it. Move two example fields there to set an example. Hopefully people will now add new fields at the end of the struct. A lot of the read-only stuff is also control path-only, but if we move it all we'll have another hole in the middle. Before: /* size: 384, cachelines: 6, members: 16 */ /* sum members: 284, holes: 3, sum holes: 100 */ After: /* size: 320, cachelines: 5, members: 16 */ /* sum members: 284, holes: 1, sum holes: 8 */ Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240820205119.1321322-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0ef3eaa23f4b7..614ec5d3d75b3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -644,9 +644,6 @@ struct netdev_queue { struct Qdisc __rcu *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; -#endif -#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) - int numa_node; #endif unsigned long tx_maxrate; /* @@ -660,13 +657,13 @@ struct netdev_queue { #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif - /* NAPI instance for the queue - * Readers and writers must hold RTNL - */ - struct napi_struct *napi; + /* * write-mostly part */ +#ifdef CONFIG_BQL + struct dql dql; +#endif spinlock_t _xmit_lock ____cacheline_aligned_in_smp; int xmit_lock_owner; /* @@ -676,8 +673,16 @@ struct netdev_queue { unsigned long state; -#ifdef CONFIG_BQL - struct dql dql; +/* + * slow- / control-path part + */ + /* NAPI instance for the queue + * Readers and writers must hold RTNL + */ + struct napi_struct *napi; + +#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) + int numa_node; #endif } ____cacheline_aligned_in_smp; From d70e3788da1d335449ba91dd46f7c3e16b01aaae Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Tue, 20 Aug 2024 13:53:41 -0400 Subject: [PATCH 281/385] net: xilinx: axienet: Report RxRject as rx_dropped The Receive Frame Rejected interrupt is asserted whenever there was a receive error (bad FCS, bad length, etc.) or whenever the frame was dropped due to a mismatched address. So this is really a combination of rx_otherhost_dropped, rx_length_errors, rx_frame_errors, and rx_crc_errors. Mismatched addresses are common and aren't really errors at all (much like how fragments are normal on half-duplex links). To avoid confusion, report these events as rx_dropped. This better reflects what's going on: the packet was received by the MAC but dropped before being processed. Signed-off-by: Sean Anderson Reviewed-by: Andrew Lunn Reviewed-by: Radhey Shyam Pandey Link: https://patch.msgid.link/20240820175343.760389-2-sean.anderson@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index ca04c298daa23..b2d7c396e2e33 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1296,7 +1296,7 @@ static irqreturn_t axienet_eth_irq(int irq, void *_ndev) ndev->stats.rx_missed_errors++; if (pending & XAE_INT_RXRJECT_MASK) - ndev->stats.rx_frame_errors++; + ndev->stats.rx_dropped++; axienet_iow(lp, XAE_IS_OFFSET, pending); return IRQ_HANDLED; From 76abb5d675c49baa0bc899c6ef8b49197ac914b8 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Tue, 20 Aug 2024 13:53:42 -0400 Subject: [PATCH 282/385] net: xilinx: axienet: Add statistics support Add support for reading the statistics counters, if they are enabled. The counters may be 64-bit, but we can't detect this statically as there's no ability bit for it and the counters are read-only. Therefore, we assume the counters are 32-bits by default. To ensure we don't miss an overflow, we read all counters at 13-second intervals. This should be often enough to ensure the bytes counters don't wrap at 2.5 Gbit/s. Another complication is that the counters may be reset when the device is reset (depending on configuration). To ensure the counters persist across link up/down (including suspend/resume), we maintain our own versions along with the last counter value we saw. Because we might wait up to 100 ms for the reset to complete, we use a mutex to protect writing hw_stats. We can't sleep in ndo_get_stats64, so we use a seqlock to protect readers. We don't bother disabling the refresh work when we detect 64-bit counters. This is because the reset issue requires us to read hw_stat_base and reset_in_progress anyway, which would still require the seqcount. And I don't think skipping the task is worth the extra bookkeeping. We can't use the byte counters for either get_stats64 or get_eth_mac_stats. This is because the byte counters include everything in the frame (destination address to FCS, inclusive). But rtnl_link_stats64 wants bytes excluding the FCS, and ethtool_eth_mac_stats wants to exclude the L2 overhead (addresses and length/type). It might be possible to calculate the byte values Linux expects based on the frame counters, but I think it is simpler to use the existing software counters. get_ethtool_stats is implemented for nonstandard statistics. This includes the aforementioned byte counters, VLAN and PFC frame counters, and user-defined (e.g. with custom RTL) counters. Signed-off-by: Sean Anderson Link: https://patch.msgid.link/20240820175343.760389-3-sean.anderson@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/xilinx/xilinx_axienet.h | 85 +++++ .../net/ethernet/xilinx/xilinx_axienet_main.c | 325 +++++++++++++++++- 2 files changed, 407 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index ea4103a635f90..8165f5f271ffa 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -156,6 +156,7 @@ #define XAE_TPID0_OFFSET 0x00000028 /* VLAN TPID0 register */ #define XAE_TPID1_OFFSET 0x0000002C /* VLAN TPID1 register */ #define XAE_PPST_OFFSET 0x00000030 /* PCS PMA Soft Temac Status Reg */ +#define XAE_STATS_OFFSET 0x00000200 /* Statistics counters */ #define XAE_RCW0_OFFSET 0x00000400 /* Rx Configuration Word 0 */ #define XAE_RCW1_OFFSET 0x00000404 /* Rx Configuration Word 1 */ #define XAE_TC_OFFSET 0x00000408 /* Tx Configuration */ @@ -163,6 +164,7 @@ #define XAE_EMMC_OFFSET 0x00000410 /* MAC speed configuration */ #define XAE_PHYC_OFFSET 0x00000414 /* RX Max Frame Configuration */ #define XAE_ID_OFFSET 0x000004F8 /* Identification register */ +#define XAE_ABILITY_OFFSET 0x000004FC /* Ability Register offset */ #define XAE_MDIO_MC_OFFSET 0x00000500 /* MDIO Setup */ #define XAE_MDIO_MCR_OFFSET 0x00000504 /* MDIO Control */ #define XAE_MDIO_MWD_OFFSET 0x00000508 /* MDIO Write Data */ @@ -283,6 +285,16 @@ #define XAE_PHYC_SGLINKSPD_100 0x40000000 /* SGMII link 100 Mbit */ #define XAE_PHYC_SGLINKSPD_1000 0x80000000 /* SGMII link 1000 Mbit */ +/* Bit masks for Axi Ethernet ability register */ +#define XAE_ABILITY_PFC BIT(16) +#define XAE_ABILITY_FRAME_FILTER BIT(10) +#define XAE_ABILITY_HALF_DUPLEX BIT(9) +#define XAE_ABILITY_STATS BIT(8) +#define XAE_ABILITY_2_5G BIT(3) +#define XAE_ABILITY_1G BIT(2) +#define XAE_ABILITY_100M BIT(1) +#define XAE_ABILITY_10M BIT(0) + /* Bit masks for Axi Ethernet MDIO interface MC register */ #define XAE_MDIO_MC_MDIOEN_MASK 0x00000040 /* MII management enable */ #define XAE_MDIO_MC_CLOCK_DIVIDE_MAX 0x3F /* Maximum MDIO divisor */ @@ -331,6 +343,7 @@ #define XAE_FEATURE_FULL_RX_CSUM BIT(2) #define XAE_FEATURE_FULL_TX_CSUM BIT(3) #define XAE_FEATURE_DMA_64BIT BIT(4) +#define XAE_FEATURE_STATS BIT(5) #define XAE_NO_CSUM_OFFLOAD 0 @@ -344,6 +357,61 @@ #define XLNX_MII_STD_SELECT_REG 0x11 #define XLNX_MII_STD_SELECT_SGMII BIT(0) +/* enum temac_stat - TEMAC statistics counters + * + * Index of statistics counters within the TEMAC. This must match the + * order/offset of hardware registers exactly. + */ +enum temac_stat { + STAT_RX_BYTES = 0, + STAT_TX_BYTES, + STAT_UNDERSIZE_FRAMES, + STAT_FRAGMENT_FRAMES, + STAT_RX_64_BYTE_FRAMES, + STAT_RX_65_127_BYTE_FRAMES, + STAT_RX_128_255_BYTE_FRAMES, + STAT_RX_256_511_BYTE_FRAMES, + STAT_RX_512_1023_BYTE_FRAMES, + STAT_RX_1024_MAX_BYTE_FRAMES, + STAT_RX_OVERSIZE_FRAMES, + STAT_TX_64_BYTE_FRAMES, + STAT_TX_65_127_BYTE_FRAMES, + STAT_TX_128_255_BYTE_FRAMES, + STAT_TX_256_511_BYTE_FRAMES, + STAT_TX_512_1023_BYTE_FRAMES, + STAT_TX_1024_MAX_BYTE_FRAMES, + STAT_TX_OVERSIZE_FRAMES, + STAT_RX_GOOD_FRAMES, + STAT_RX_FCS_ERRORS, + STAT_RX_BROADCAST_FRAMES, + STAT_RX_MULTICAST_FRAMES, + STAT_RX_CONTROL_FRAMES, + STAT_RX_LENGTH_ERRORS, + STAT_RX_VLAN_FRAMES, + STAT_RX_PAUSE_FRAMES, + STAT_RX_CONTROL_OPCODE_ERRORS, + STAT_TX_GOOD_FRAMES, + STAT_TX_BROADCAST_FRAMES, + STAT_TX_MULTICAST_FRAMES, + STAT_TX_UNDERRUN_ERRORS, + STAT_TX_CONTROL_FRAMES, + STAT_TX_VLAN_FRAMES, + STAT_TX_PAUSE_FRAMES, + STAT_TX_SINGLE_COLLISION_FRAMES, + STAT_TX_MULTIPLE_COLLISION_FRAMES, + STAT_TX_DEFERRED_FRAMES, + STAT_TX_LATE_COLLISIONS, + STAT_TX_EXCESS_COLLISIONS, + STAT_TX_EXCESS_DEFERRAL, + STAT_RX_ALIGNMENT_ERRORS, + STAT_TX_PFC_FRAMES, + STAT_RX_PFC_FRAMES, + STAT_USER_DEFINED0, + STAT_USER_DEFINED1, + STAT_USER_DEFINED2, + STAT_COUNT, +}; + /** * struct axidma_bd - Axi Dma buffer descriptor layout * @next: MM2S/S2MM Next Descriptor Pointer @@ -434,6 +502,16 @@ struct skbuf_dma_descriptor { * @tx_packets: TX packet count for statistics * @tx_bytes: TX byte count for statistics * @tx_stat_sync: Synchronization object for TX stats + * @hw_stat_base: Base offset for statistics counters. This may be nonzero if + * the statistics counteres were reset or wrapped around. + * @hw_last_counter: Last-seen value of each statistic counter + * @reset_in_progress: Set while we are performing a reset and statistics + * counters may be invalid + * @hw_stats_seqcount: Sequence counter for @hw_stat_base, @hw_last_counter, + * and @reset_in_progress. + * @stats_lock: Lock for @hw_stats_seqcount + * @stats_work: Work for reading the hardware statistics counters often enough + * to catch overflows. * @dma_err_task: Work structure to process Axi DMA errors * @tx_irq: Axidma TX IRQ number * @rx_irq: Axidma RX IRQ number @@ -505,6 +583,13 @@ struct axienet_local { u64_stats_t tx_bytes; struct u64_stats_sync tx_stat_sync; + u64 hw_stat_base[STAT_COUNT]; + u32 hw_last_counter[STAT_COUNT]; + seqcount_mutex_t hw_stats_seqcount; + struct mutex stats_lock; + struct delayed_work stats_work; + bool reset_in_progress; + struct work_struct dma_err_task; int tx_irq; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index b2d7c396e2e33..38f7b764fe66e 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -519,11 +519,55 @@ static void axienet_setoptions(struct net_device *ndev, u32 options) lp->options |= options; } +static u64 axienet_stat(struct axienet_local *lp, enum temac_stat stat) +{ + u32 counter; + + if (lp->reset_in_progress) + return lp->hw_stat_base[stat]; + + counter = axienet_ior(lp, XAE_STATS_OFFSET + stat * 8); + return lp->hw_stat_base[stat] + (counter - lp->hw_last_counter[stat]); +} + +static void axienet_stats_update(struct axienet_local *lp, bool reset) +{ + enum temac_stat stat; + + write_seqcount_begin(&lp->hw_stats_seqcount); + lp->reset_in_progress = reset; + for (stat = 0; stat < STAT_COUNT; stat++) { + u32 counter = axienet_ior(lp, XAE_STATS_OFFSET + stat * 8); + + lp->hw_stat_base[stat] += counter - lp->hw_last_counter[stat]; + lp->hw_last_counter[stat] = counter; + } + write_seqcount_end(&lp->hw_stats_seqcount); +} + +static void axienet_refresh_stats(struct work_struct *work) +{ + struct axienet_local *lp = container_of(work, struct axienet_local, + stats_work.work); + + mutex_lock(&lp->stats_lock); + axienet_stats_update(lp, false); + mutex_unlock(&lp->stats_lock); + + /* Just less than 2^32 bytes at 2.5 GBit/s */ + schedule_delayed_work(&lp->stats_work, 13 * HZ); +} + static int __axienet_device_reset(struct axienet_local *lp) { u32 value; int ret; + /* Save statistics counters in case they will be reset */ + mutex_lock(&lp->stats_lock); + if (lp->features & XAE_FEATURE_STATS) + axienet_stats_update(lp, true); + /* Reset Axi DMA. This would reset Axi Ethernet core as well. The reset * process of Axi DMA takes a while to complete as all pending * commands/transfers will be flushed or completed during this @@ -538,7 +582,7 @@ static int __axienet_device_reset(struct axienet_local *lp) XAXIDMA_TX_CR_OFFSET); if (ret) { dev_err(lp->dev, "%s: DMA reset timeout!\n", __func__); - return ret; + goto out; } /* Wait for PhyRstCmplt bit to be set, indicating the PHY reset has finished */ @@ -548,10 +592,29 @@ static int __axienet_device_reset(struct axienet_local *lp) XAE_IS_OFFSET); if (ret) { dev_err(lp->dev, "%s: timeout waiting for PhyRstCmplt\n", __func__); - return ret; + goto out; } - return 0; + /* Update statistics counters with new values */ + if (lp->features & XAE_FEATURE_STATS) { + enum temac_stat stat; + + write_seqcount_begin(&lp->hw_stats_seqcount); + lp->reset_in_progress = false; + for (stat = 0; stat < STAT_COUNT; stat++) { + u32 counter = + axienet_ior(lp, XAE_STATS_OFFSET + stat * 8); + + lp->hw_stat_base[stat] += + lp->hw_last_counter[stat] - counter; + lp->hw_last_counter[stat] = counter; + } + write_seqcount_end(&lp->hw_stats_seqcount); + } + +out: + mutex_unlock(&lp->stats_lock); + return ret; } /** @@ -1530,6 +1593,9 @@ static int axienet_open(struct net_device *ndev) phylink_start(lp->phylink); + /* Start the statistics refresh work */ + schedule_delayed_work(&lp->stats_work, 0); + if (lp->use_dmaengine) { /* Enable interrupts for Axi Ethernet core (if defined) */ if (lp->eth_irq > 0) { @@ -1554,6 +1620,7 @@ static int axienet_open(struct net_device *ndev) if (lp->eth_irq > 0) free_irq(lp->eth_irq, ndev); err_phy: + cancel_delayed_work_sync(&lp->stats_work); phylink_stop(lp->phylink); phylink_disconnect_phy(lp->phylink); return ret; @@ -1579,6 +1646,8 @@ static int axienet_stop(struct net_device *ndev) napi_disable(&lp->napi_rx); } + cancel_delayed_work_sync(&lp->stats_work); + phylink_stop(lp->phylink); phylink_disconnect_phy(lp->phylink); @@ -1692,6 +1761,35 @@ axienet_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->tx_packets = u64_stats_read(&lp->tx_packets); stats->tx_bytes = u64_stats_read(&lp->tx_bytes); } while (u64_stats_fetch_retry(&lp->tx_stat_sync, start)); + + if (!(lp->features & XAE_FEATURE_STATS)) + return; + + do { + start = read_seqcount_begin(&lp->hw_stats_seqcount); + stats->rx_length_errors = + axienet_stat(lp, STAT_RX_LENGTH_ERRORS); + stats->rx_crc_errors = axienet_stat(lp, STAT_RX_FCS_ERRORS); + stats->rx_frame_errors = + axienet_stat(lp, STAT_RX_ALIGNMENT_ERRORS); + stats->rx_errors = axienet_stat(lp, STAT_UNDERSIZE_FRAMES) + + axienet_stat(lp, STAT_FRAGMENT_FRAMES) + + stats->rx_length_errors + + stats->rx_crc_errors + + stats->rx_frame_errors; + stats->multicast = axienet_stat(lp, STAT_RX_MULTICAST_FRAMES); + + stats->tx_aborted_errors = + axienet_stat(lp, STAT_TX_EXCESS_COLLISIONS); + stats->tx_fifo_errors = + axienet_stat(lp, STAT_TX_UNDERRUN_ERRORS); + stats->tx_window_errors = + axienet_stat(lp, STAT_TX_LATE_COLLISIONS); + stats->tx_errors = axienet_stat(lp, STAT_TX_EXCESS_DEFERRAL) + + stats->tx_aborted_errors + + stats->tx_fifo_errors + + stats->tx_window_errors; + } while (read_seqcount_retry(&lp->hw_stats_seqcount, start)); } static const struct net_device_ops axienet_netdev_ops = { @@ -1984,6 +2082,213 @@ static int axienet_ethtools_nway_reset(struct net_device *dev) return phylink_ethtool_nway_reset(lp->phylink); } +static void axienet_ethtools_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, + u64 *data) +{ + struct axienet_local *lp = netdev_priv(dev); + unsigned int start; + + do { + start = read_seqcount_begin(&lp->hw_stats_seqcount); + data[0] = axienet_stat(lp, STAT_RX_BYTES); + data[1] = axienet_stat(lp, STAT_TX_BYTES); + data[2] = axienet_stat(lp, STAT_RX_VLAN_FRAMES); + data[3] = axienet_stat(lp, STAT_TX_VLAN_FRAMES); + data[6] = axienet_stat(lp, STAT_TX_PFC_FRAMES); + data[7] = axienet_stat(lp, STAT_RX_PFC_FRAMES); + data[8] = axienet_stat(lp, STAT_USER_DEFINED0); + data[9] = axienet_stat(lp, STAT_USER_DEFINED1); + data[10] = axienet_stat(lp, STAT_USER_DEFINED2); + } while (read_seqcount_retry(&lp->hw_stats_seqcount, start)); +} + +static const char axienet_ethtool_stats_strings[][ETH_GSTRING_LEN] = { + "Received bytes", + "Transmitted bytes", + "RX Good VLAN Tagged Frames", + "TX Good VLAN Tagged Frames", + "TX Good PFC Frames", + "RX Good PFC Frames", + "User Defined Counter 0", + "User Defined Counter 1", + "User Defined Counter 2", +}; + +static void axienet_ethtools_get_strings(struct net_device *dev, u32 stringset, u8 *data) +{ + switch (stringset) { + case ETH_SS_STATS: + memcpy(data, axienet_ethtool_stats_strings, + sizeof(axienet_ethtool_stats_strings)); + break; + } +} + +static int axienet_ethtools_get_sset_count(struct net_device *dev, int sset) +{ + struct axienet_local *lp = netdev_priv(dev); + + switch (sset) { + case ETH_SS_STATS: + if (lp->features & XAE_FEATURE_STATS) + return ARRAY_SIZE(axienet_ethtool_stats_strings); + fallthrough; + default: + return -EOPNOTSUPP; + } +} + +static void +axienet_ethtools_get_pause_stats(struct net_device *dev, + struct ethtool_pause_stats *pause_stats) +{ + struct axienet_local *lp = netdev_priv(dev); + unsigned int start; + + if (!(lp->features & XAE_FEATURE_STATS)) + return; + + do { + start = read_seqcount_begin(&lp->hw_stats_seqcount); + pause_stats->tx_pause_frames = + axienet_stat(lp, STAT_TX_PAUSE_FRAMES); + pause_stats->rx_pause_frames = + axienet_stat(lp, STAT_RX_PAUSE_FRAMES); + } while (read_seqcount_retry(&lp->hw_stats_seqcount, start)); +} + +static void +axienet_ethtool_get_eth_mac_stats(struct net_device *dev, + struct ethtool_eth_mac_stats *mac_stats) +{ + struct axienet_local *lp = netdev_priv(dev); + unsigned int start; + + if (!(lp->features & XAE_FEATURE_STATS)) + return; + + do { + start = read_seqcount_begin(&lp->hw_stats_seqcount); + mac_stats->FramesTransmittedOK = + axienet_stat(lp, STAT_TX_GOOD_FRAMES); + mac_stats->SingleCollisionFrames = + axienet_stat(lp, STAT_TX_SINGLE_COLLISION_FRAMES); + mac_stats->MultipleCollisionFrames = + axienet_stat(lp, STAT_TX_MULTIPLE_COLLISION_FRAMES); + mac_stats->FramesReceivedOK = + axienet_stat(lp, STAT_RX_GOOD_FRAMES); + mac_stats->FrameCheckSequenceErrors = + axienet_stat(lp, STAT_RX_FCS_ERRORS); + mac_stats->AlignmentErrors = + axienet_stat(lp, STAT_RX_ALIGNMENT_ERRORS); + mac_stats->FramesWithDeferredXmissions = + axienet_stat(lp, STAT_TX_DEFERRED_FRAMES); + mac_stats->LateCollisions = + axienet_stat(lp, STAT_TX_LATE_COLLISIONS); + mac_stats->FramesAbortedDueToXSColls = + axienet_stat(lp, STAT_TX_EXCESS_COLLISIONS); + mac_stats->MulticastFramesXmittedOK = + axienet_stat(lp, STAT_TX_MULTICAST_FRAMES); + mac_stats->BroadcastFramesXmittedOK = + axienet_stat(lp, STAT_TX_BROADCAST_FRAMES); + mac_stats->FramesWithExcessiveDeferral = + axienet_stat(lp, STAT_TX_EXCESS_DEFERRAL); + mac_stats->MulticastFramesReceivedOK = + axienet_stat(lp, STAT_RX_MULTICAST_FRAMES); + mac_stats->BroadcastFramesReceivedOK = + axienet_stat(lp, STAT_RX_BROADCAST_FRAMES); + mac_stats->InRangeLengthErrors = + axienet_stat(lp, STAT_RX_LENGTH_ERRORS); + } while (read_seqcount_retry(&lp->hw_stats_seqcount, start)); +} + +static void +axienet_ethtool_get_eth_ctrl_stats(struct net_device *dev, + struct ethtool_eth_ctrl_stats *ctrl_stats) +{ + struct axienet_local *lp = netdev_priv(dev); + unsigned int start; + + if (!(lp->features & XAE_FEATURE_STATS)) + return; + + do { + start = read_seqcount_begin(&lp->hw_stats_seqcount); + ctrl_stats->MACControlFramesTransmitted = + axienet_stat(lp, STAT_TX_CONTROL_FRAMES); + ctrl_stats->MACControlFramesReceived = + axienet_stat(lp, STAT_RX_CONTROL_FRAMES); + ctrl_stats->UnsupportedOpcodesReceived = + axienet_stat(lp, STAT_RX_CONTROL_OPCODE_ERRORS); + } while (read_seqcount_retry(&lp->hw_stats_seqcount, start)); +} + +static const struct ethtool_rmon_hist_range axienet_rmon_ranges[] = { + { 64, 64 }, + { 65, 127 }, + { 128, 255 }, + { 256, 511 }, + { 512, 1023 }, + { 1024, 1518 }, + { 1519, 16384 }, + { }, +}; + +static void +axienet_ethtool_get_rmon_stats(struct net_device *dev, + struct ethtool_rmon_stats *rmon_stats, + const struct ethtool_rmon_hist_range **ranges) +{ + struct axienet_local *lp = netdev_priv(dev); + unsigned int start; + + if (!(lp->features & XAE_FEATURE_STATS)) + return; + + do { + start = read_seqcount_begin(&lp->hw_stats_seqcount); + rmon_stats->undersize_pkts = + axienet_stat(lp, STAT_UNDERSIZE_FRAMES); + rmon_stats->oversize_pkts = + axienet_stat(lp, STAT_RX_OVERSIZE_FRAMES); + rmon_stats->fragments = + axienet_stat(lp, STAT_FRAGMENT_FRAMES); + + rmon_stats->hist[0] = + axienet_stat(lp, STAT_RX_64_BYTE_FRAMES); + rmon_stats->hist[1] = + axienet_stat(lp, STAT_RX_65_127_BYTE_FRAMES); + rmon_stats->hist[2] = + axienet_stat(lp, STAT_RX_128_255_BYTE_FRAMES); + rmon_stats->hist[3] = + axienet_stat(lp, STAT_RX_256_511_BYTE_FRAMES); + rmon_stats->hist[4] = + axienet_stat(lp, STAT_RX_512_1023_BYTE_FRAMES); + rmon_stats->hist[5] = + axienet_stat(lp, STAT_RX_1024_MAX_BYTE_FRAMES); + rmon_stats->hist[6] = + rmon_stats->oversize_pkts; + + rmon_stats->hist_tx[0] = + axienet_stat(lp, STAT_TX_64_BYTE_FRAMES); + rmon_stats->hist_tx[1] = + axienet_stat(lp, STAT_TX_65_127_BYTE_FRAMES); + rmon_stats->hist_tx[2] = + axienet_stat(lp, STAT_TX_128_255_BYTE_FRAMES); + rmon_stats->hist_tx[3] = + axienet_stat(lp, STAT_TX_256_511_BYTE_FRAMES); + rmon_stats->hist_tx[4] = + axienet_stat(lp, STAT_TX_512_1023_BYTE_FRAMES); + rmon_stats->hist_tx[5] = + axienet_stat(lp, STAT_TX_1024_MAX_BYTE_FRAMES); + rmon_stats->hist_tx[6] = + axienet_stat(lp, STAT_TX_OVERSIZE_FRAMES); + } while (read_seqcount_retry(&lp->hw_stats_seqcount, start)); + + *ranges = axienet_rmon_ranges; +} + static const struct ethtool_ops axienet_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES | ETHTOOL_COALESCE_USECS, @@ -2000,6 +2305,13 @@ static const struct ethtool_ops axienet_ethtool_ops = { .get_link_ksettings = axienet_ethtools_get_link_ksettings, .set_link_ksettings = axienet_ethtools_set_link_ksettings, .nway_reset = axienet_ethtools_nway_reset, + .get_ethtool_stats = axienet_ethtools_get_ethtool_stats, + .get_strings = axienet_ethtools_get_strings, + .get_sset_count = axienet_ethtools_get_sset_count, + .get_pause_stats = axienet_ethtools_get_pause_stats, + .get_eth_mac_stats = axienet_ethtool_get_eth_mac_stats, + .get_eth_ctrl_stats = axienet_ethtool_get_eth_ctrl_stats, + .get_rmon_stats = axienet_ethtool_get_rmon_stats, }; static struct axienet_local *pcs_to_axienet_local(struct phylink_pcs *pcs) @@ -2268,6 +2580,10 @@ static int axienet_probe(struct platform_device *pdev) u64_stats_init(&lp->rx_stat_sync); u64_stats_init(&lp->tx_stat_sync); + mutex_init(&lp->stats_lock); + seqcount_mutex_init(&lp->hw_stats_seqcount, &lp->stats_lock); + INIT_DEFERRABLE_WORK(&lp->stats_work, axienet_refresh_stats); + lp->axi_clk = devm_clk_get_optional(&pdev->dev, "s_axi_lite_clk"); if (!lp->axi_clk) { /* For backward compatibility, if named AXI clock is not present, @@ -2308,6 +2624,9 @@ static int axienet_probe(struct platform_device *pdev) /* Setup checksum offload, but default to off if not specified */ lp->features = 0; + if (axienet_ior(lp, XAE_ABILITY_OFFSET) & XAE_ABILITY_STATS) + lp->features |= XAE_FEATURE_STATS; + ret = of_property_read_u32(pdev->dev.of_node, "xlnx,txcsum", &value); if (!ret) { switch (value) { From f32c821ae0198cf43181711efb18376b2eb6a1cb Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 20 Aug 2024 17:12:22 +0200 Subject: [PATCH 283/385] tools: ynl: lift an assumption about spec file name Currently the parsing code generator assumes that the yaml specification file name and the main 'name' attribute carried inside correspond, that is the field is the c-name representation of the file basename. The above assumption held true within the current tree, but will be hopefully broken soon by the upcoming net shaper specification. Additionally, it makes the field 'name' itself useless. Lift the assumption, always computing the generated include file name from the generated c file name. Signed-off-by: Paolo Abeni Link: https://patch.msgid.link/24da5a3596d814beeb12bd7139a6b4f89756cc19.1724165948.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- tools/net/ynl/ynl-gen-c.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index 51529fabd5174..717530bc9c52e 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -2668,13 +2668,15 @@ def main(): cw.p('#define ' + hdr_prot) cw.nl() + hdr_file=os.path.basename(args.out_file[:-2]) + ".h" + if args.mode == 'kernel': cw.p('#include ') cw.p('#include ') cw.nl() if not args.header: if args.out_file: - cw.p(f'#include "{os.path.basename(args.out_file[:-2])}.h"') + cw.p(f'#include "{hdr_file}"') cw.nl() headers = ['uapi/' + parsed.uapi_header] headers += parsed.kernel_family.get('headers', []) @@ -2686,7 +2688,7 @@ def main(): if family_contains_bitfield32(parsed): cw.p('#include ') else: - cw.p(f'#include "{parsed.name}-user.h"') + cw.p(f'#include "{hdr_file}"') cw.p('#include "ynl.h"') headers = [parsed.uapi_header] for definition in parsed['definitions']: From 924b8bea870b4968cec4784676e6b27597e25d01 Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Sat, 17 Aug 2024 15:18:17 +0200 Subject: [PATCH 284/385] net: ipv6: ioam6: code alignment This patch prepares the next one by correcting the alignment of some lines. Signed-off-by: Justin Iurman Signed-off-by: Paolo Abeni --- net/ipv6/ioam6_iptunnel.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index bf7120ecea1eb..cd2522f04edfd 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -43,7 +43,7 @@ struct ioam6_lwt { atomic_t pkt_cnt; u8 mode; struct in6_addr tundst; - struct ioam6_lwt_encap tuninfo; + struct ioam6_lwt_encap tuninfo; }; static const struct netlink_range_validation freq_range = { @@ -73,7 +73,8 @@ static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = { IOAM6_IPTUNNEL_MODE_MIN, IOAM6_IPTUNNEL_MODE_MAX), [IOAM6_IPTUNNEL_DST] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), - [IOAM6_IPTUNNEL_TRACE] = NLA_POLICY_EXACT_LEN(sizeof(struct ioam6_trace_hdr)), + [IOAM6_IPTUNNEL_TRACE] = NLA_POLICY_EXACT_LEN( + sizeof(struct ioam6_trace_hdr)), }; static bool ioam6_validate_trace_hdr(struct ioam6_trace_hdr *trace) @@ -459,9 +460,9 @@ static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) static const struct lwtunnel_encap_ops ioam6_iptun_ops = { .build_state = ioam6_build_state, .destroy_state = ioam6_destroy_state, - .output = ioam6_output, + .output = ioam6_output, .fill_encap = ioam6_fill_encap_info, - .get_encap_size = ioam6_encap_nlsize, + .get_encap_size = ioam6_encap_nlsize, .cmp_encap = ioam6_encap_cmp, .owner = THIS_MODULE, }; From 273f8c142003dfd874d45b1a60965809e95ccd50 Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Sat, 17 Aug 2024 15:18:18 +0200 Subject: [PATCH 285/385] net: ipv6: ioam6: new feature tunsrc This patch provides a new feature (i.e., "tunsrc") for the tunnel (i.e., "encap") mode of ioam6. Just like seg6 already does, except it is attached to a route. The "tunsrc" is optional: when not provided (by default), the automatic resolution is applied. Using "tunsrc" when possible has a benefit: performance. See the comparison: - before (= "encap" mode): https://ibb.co/bNCzvf7 - after (= "encap" mode with "tunsrc"): https://ibb.co/PT8L6yq Signed-off-by: Justin Iurman Signed-off-by: Paolo Abeni --- include/uapi/linux/ioam6_iptunnel.h | 6 +++ net/ipv6/ioam6_iptunnel.c | 65 +++++++++++++++++++++++++---- 2 files changed, 63 insertions(+), 8 deletions(-) diff --git a/include/uapi/linux/ioam6_iptunnel.h b/include/uapi/linux/ioam6_iptunnel.h index 38f6a8fdfd343..8aef21e4a8c14 100644 --- a/include/uapi/linux/ioam6_iptunnel.h +++ b/include/uapi/linux/ioam6_iptunnel.h @@ -50,6 +50,12 @@ enum { IOAM6_IPTUNNEL_FREQ_K, /* u32 */ IOAM6_IPTUNNEL_FREQ_N, /* u32 */ + /* Tunnel src address. + * For encap,auto modes. + * Optional (automatic if not provided). + */ + IOAM6_IPTUNNEL_SRC, /* struct in6_addr */ + __IOAM6_IPTUNNEL_MAX, }; diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index cd2522f04edfd..e34e1ff24546d 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -42,6 +42,8 @@ struct ioam6_lwt { struct ioam6_lwt_freq freq; atomic_t pkt_cnt; u8 mode; + bool has_tunsrc; + struct in6_addr tunsrc; struct in6_addr tundst; struct ioam6_lwt_encap tuninfo; }; @@ -72,6 +74,7 @@ static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = { [IOAM6_IPTUNNEL_MODE] = NLA_POLICY_RANGE(NLA_U8, IOAM6_IPTUNNEL_MODE_MIN, IOAM6_IPTUNNEL_MODE_MAX), + [IOAM6_IPTUNNEL_SRC] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [IOAM6_IPTUNNEL_DST] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [IOAM6_IPTUNNEL_TRACE] = NLA_POLICY_EXACT_LEN( sizeof(struct ioam6_trace_hdr)), @@ -144,6 +147,11 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, else mode = nla_get_u8(tb[IOAM6_IPTUNNEL_MODE]); + if (tb[IOAM6_IPTUNNEL_SRC] && mode == IOAM6_IPTUNNEL_MODE_INLINE) { + NL_SET_ERR_MSG(extack, "no tunnel src expected with this mode"); + return -EINVAL; + } + if (!tb[IOAM6_IPTUNNEL_DST] && mode != IOAM6_IPTUNNEL_MODE_INLINE) { NL_SET_ERR_MSG(extack, "this mode needs a tunnel destination"); return -EINVAL; @@ -168,16 +176,29 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, ilwt = ioam6_lwt_state(lwt); err = dst_cache_init(&ilwt->cache, GFP_ATOMIC); - if (err) { - kfree(lwt); - return err; - } + if (err) + goto free_lwt; atomic_set(&ilwt->pkt_cnt, 0); ilwt->freq.k = freq_k; ilwt->freq.n = freq_n; ilwt->mode = mode; + + if (!tb[IOAM6_IPTUNNEL_SRC]) { + ilwt->has_tunsrc = false; + } else { + ilwt->has_tunsrc = true; + ilwt->tunsrc = nla_get_in6_addr(tb[IOAM6_IPTUNNEL_SRC]); + + if (ipv6_addr_any(&ilwt->tunsrc)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IOAM6_IPTUNNEL_SRC], + "invalid tunnel source address"); + err = -EINVAL; + goto free_cache; + } + } + if (tb[IOAM6_IPTUNNEL_DST]) ilwt->tundst = nla_get_in6_addr(tb[IOAM6_IPTUNNEL_DST]); @@ -202,6 +223,11 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, *ts = lwt; return 0; +free_cache: + dst_cache_destroy(&ilwt->cache); +free_lwt: + kfree(lwt); + return err; } static int ioam6_do_fill(struct net *net, struct sk_buff *skb) @@ -257,6 +283,8 @@ static int ioam6_do_inline(struct net *net, struct sk_buff *skb, static int ioam6_do_encap(struct net *net, struct sk_buff *skb, struct ioam6_lwt_encap *tuninfo, + bool has_tunsrc, + struct in6_addr *tunsrc, struct in6_addr *tundst) { struct dst_entry *dst = skb_dst(skb); @@ -286,8 +314,12 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb, hdr->nexthdr = NEXTHDR_HOP; hdr->payload_len = cpu_to_be16(skb->len - sizeof(*hdr)); hdr->daddr = *tundst; - ipv6_dev_get_saddr(net, dst->dev, &hdr->daddr, - IPV6_PREFER_SRC_PUBLIC, &hdr->saddr); + + if (has_tunsrc) + memcpy(&hdr->saddr, tunsrc, sizeof(*tunsrc)); + else + ipv6_dev_get_saddr(net, dst->dev, &hdr->daddr, + IPV6_PREFER_SRC_PUBLIC, &hdr->saddr); skb_postpush_rcsum(skb, hdr, len); @@ -329,7 +361,9 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) case IOAM6_IPTUNNEL_MODE_ENCAP: do_encap: /* Encapsulation (ip6ip6) */ - err = ioam6_do_encap(net, skb, &ilwt->tuninfo, &ilwt->tundst); + err = ioam6_do_encap(net, skb, &ilwt->tuninfo, + ilwt->has_tunsrc, &ilwt->tunsrc, + &ilwt->tundst); if (unlikely(err)) goto drop; @@ -415,6 +449,13 @@ static int ioam6_fill_encap_info(struct sk_buff *skb, goto ret; if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) { + if (ilwt->has_tunsrc) { + err = nla_put_in6_addr(skb, IOAM6_IPTUNNEL_SRC, + &ilwt->tunsrc); + if (err) + goto ret; + } + err = nla_put_in6_addr(skb, IOAM6_IPTUNNEL_DST, &ilwt->tundst); if (err) goto ret; @@ -436,8 +477,12 @@ static int ioam6_encap_nlsize(struct lwtunnel_state *lwtstate) nla_total_size(sizeof(ilwt->mode)) + nla_total_size(sizeof(ilwt->tuninfo.traceh)); - if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) + if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) { + if (ilwt->has_tunsrc) + nlsize += nla_total_size(sizeof(ilwt->tunsrc)); + nlsize += nla_total_size(sizeof(ilwt->tundst)); + } return nlsize; } @@ -452,8 +497,12 @@ static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) return (ilwt_a->freq.k != ilwt_b->freq.k || ilwt_a->freq.n != ilwt_b->freq.n || ilwt_a->mode != ilwt_b->mode || + ilwt_a->has_tunsrc != ilwt_b->has_tunsrc || (ilwt_a->mode != IOAM6_IPTUNNEL_MODE_INLINE && !ipv6_addr_equal(&ilwt_a->tundst, &ilwt_b->tundst)) || + (ilwt_a->mode != IOAM6_IPTUNNEL_MODE_INLINE && + ilwt_a->has_tunsrc && + !ipv6_addr_equal(&ilwt_a->tunsrc, &ilwt_b->tunsrc)) || trace_a->namespace_id != trace_b->namespace_id); } From 6ea14ccb60c8ab829349979b22b58a941ec4a3ee Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 13 Aug 2024 12:39:46 +0200 Subject: [PATCH 286/385] netfilter: flowtable: validate vlan header Ensure there is sufficient room to access the protocol field of the VLAN header, validate it once before the flowtable lookup. ===================================================== BUG: KMSAN: uninit-value in nf_flow_offload_inet_hook+0x45a/0x5f0 net/netfilter/nf_flow_table_inet.c:32 nf_flow_offload_inet_hook+0x45a/0x5f0 net/netfilter/nf_flow_table_inet.c:32 nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline] nf_hook_slow+0xf4/0x400 net/netfilter/core.c:626 nf_hook_ingress include/linux/netfilter_netdev.h:34 [inline] nf_ingress net/core/dev.c:5440 [inline] Fixes: 4cd91f7c290f ("netfilter: flowtable: add vlan support") Reported-by: syzbot+8407d9bb88cd4c6bf61a@syzkaller.appspotmail.com Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_flow_table_inet.c | 3 +++ net/netfilter/nf_flow_table_ip.c | 3 +++ 2 files changed, 6 insertions(+) diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 88787b45e30d6..8b541a0803420 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -17,6 +17,9 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, switch (skb->protocol) { case htons(ETH_P_8021Q): + if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth))) + return NF_ACCEPT; + veth = (struct vlan_ethhdr *)skb_mac_header(skb); proto = veth->h_vlan_encapsulated_proto; break; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index c2c005234dcd3..98edcaa37b38d 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -281,6 +281,9 @@ static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto, switch (skb->protocol) { case htons(ETH_P_8021Q): + if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth))) + return false; + veth = (struct vlan_ethhdr *)skb_mac_header(skb); if (veth->h_vlan_encapsulated_proto == proto) { *offset += VLAN_HLEN; From f2916c83d746eb99f50f42c15cf4c47c2ea5f3b3 Mon Sep 17 00:00:00 2001 From: Mengyuan Lou Date: Tue, 20 Aug 2024 11:04:25 +0800 Subject: [PATCH 287/385] net: ngbe: Fix phy mode set to external phy The MAC only has add the TX delay and it can not be modified. MAC and PHY are both set the TX delay cause transmission problems. So just disable TX delay in PHY, when use rgmii to attach to external phy, set PHY_INTERFACE_MODE_RGMII_RXID to phy drivers. And it is does not matter to internal phy. Fixes: bc2426d74aa3 ("net: ngbe: convert phylib to phylink") Signed-off-by: Mengyuan Lou Cc: stable@vger.kernel.org # 6.3+ Reviewed-by: Jacob Keller Link: https://patch.msgid.link/E6759CF1387CF84C+20240820030425.93003-1-mengyuanlou@net-swift.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c index ec54b18c5fe73..a5e9b779c44d0 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c @@ -124,8 +124,12 @@ static int ngbe_phylink_init(struct wx *wx) MAC_SYM_PAUSE | MAC_ASYM_PAUSE; config->mac_managed_pm = true; - phy_mode = PHY_INTERFACE_MODE_RGMII_ID; - __set_bit(PHY_INTERFACE_MODE_RGMII_ID, config->supported_interfaces); + /* The MAC only has add the Tx delay and it can not be modified. + * So just disable TX delay in PHY, and it is does not matter to + * internal phy. + */ + phy_mode = PHY_INTERFACE_MODE_RGMII_RXID; + __set_bit(PHY_INTERFACE_MODE_RGMII_RXID, config->supported_interfaces); phylink = phylink_create(config, NULL, phy_mode, &ngbe_mac_ops); if (IS_ERR(phylink)) From bcc3773c49af2426093645473fe02a5a8e765587 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 20 Aug 2024 18:22:27 -0700 Subject: [PATCH 288/385] selftests: net: add helper for checking if nettest is available A few tests check if nettest exists in the $PATH before adding $PWD to $PATH and re-checking. They don't discard stderr on the first check (and nettest is built as part of selftests, so it's pretty normal for it to not be available in system $PATH). This leads to output noise: which: no nettest in (/home/virtme/tools/fs/bin:/home/virtme/tools/fs/sbin:/home/virtme/tools/fs/usr/bin:/home/virtme/tools/fs/usr/sbin:/bin:/sbin:/usr/bin:/usr/sbin:/usr/local/bin) Add a common helper for the check which does silence stderr. There is another small functional change hiding here, because pmtu.sh and fib_rule_tests.sh used to return from the test case rather than completely exit. Building nettest is not hard, there should be no need to maintain the ability to selectively skip cases in its absence. Reviewed-by: Ido Schimmel Signed-off-by: Jakub Kicinski Reviewed-by: Hangbin Liu Link: https://patch.msgid.link/20240821012227.1398769-1-kuba@kernel.org Signed-off-by: Paolo Abeni --- tools/testing/selftests/net/fcnal-test.sh | 9 +---- tools/testing/selftests/net/fib_rule_tests.sh | 37 +------------------ tools/testing/selftests/net/lib.sh | 15 ++++++++ tools/testing/selftests/net/pmtu.sh | 8 +--- .../selftests/net/unicast_extensions.sh | 9 +---- .../selftests/net/vrf_route_leaking.sh | 3 +- 6 files changed, 22 insertions(+), 59 deletions(-) diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 386ebd829df58..899dbad0104bf 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -4304,14 +4304,7 @@ elif [ "$TESTS" = "ipv6" ]; then TESTS="$TESTS_IPV6" fi -# nettest can be run from PATH or from same directory as this selftest -if ! which nettest >/dev/null; then - PATH=$PWD:$PATH - if ! which nettest >/dev/null; then - echo "'nettest' command not found; skipping tests" - exit $ksft_skip - fi -fi +check_gen_prog "nettest" declare -i nfail=0 declare -i nsuccess=0 diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 89034c5b69dc6..53c5c1ad437e2 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -51,31 +51,6 @@ log_test() fi } -check_nettest() -{ - if which nettest > /dev/null 2>&1; then - return 0 - fi - - # Add the selftest directory to PATH if not already done - if [ "${SELFTEST_PATH}" = "" ]; then - SELFTEST_PATH="$(dirname $0)" - PATH="${PATH}:${SELFTEST_PATH}" - - # Now retry with the new path - if which nettest > /dev/null 2>&1; then - return 0 - fi - - if [ "${ret}" -eq 0 ]; then - ret="${ksft_skip}" - fi - echo "nettest not found (try 'make -C ${SELFTEST_PATH} nettest')" - fi - - return 1 -} - setup() { set -e @@ -317,11 +292,6 @@ fib_rule6_connect_test() echo echo "IPv6 FIB rule connect tests" - if ! check_nettest; then - echo "SKIP: Could not run test without nettest tool" - return - fi - setup_peer $IP -6 rule add dsfield 0x04 table $RTABLE_PEER @@ -516,11 +486,6 @@ fib_rule4_connect_test() echo echo "IPv4 FIB rule connect tests" - if ! check_nettest; then - echo "SKIP: Could not run test without nettest tool" - return - fi - setup_peer $IP -4 rule add dsfield 0x04 table $RTABLE_PEER @@ -584,6 +549,8 @@ if [ ! -x "$(command -v ip)" ]; then exit $ksft_skip fi +check_gen_prog "nettest" + # start clean cleanup &> /dev/null setup diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 8ee4489238ca4..be8707bfb46e5 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -125,6 +125,21 @@ slowwait_for_counter() slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@" } +# Check for existence of tools which are built as part of selftests +# but may also already exist in $PATH +check_gen_prog() +{ + local prog_name=$1; shift + + if ! which $prog_name >/dev/null 2>/dev/null; then + PATH=$PWD:$PATH + if ! which $prog_name >/dev/null; then + echo "'$prog_name' command not found; skipping tests" + exit $ksft_skip + fi + fi +} + remove_ns_list() { local item=$1 diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 24a50622406c2..569bce8b6383e 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -681,13 +681,7 @@ setup_xfrm() { } setup_nettest_xfrm() { - if ! which nettest >/dev/null; then - PATH=$PWD:$PATH - if ! which nettest >/dev/null; then - echo "'nettest' command not found; skipping tests" - return 1 - fi - fi + check_gen_prog "nettest" [ ${1} -eq 6 ] && proto="-6" || proto="" port=${2} diff --git a/tools/testing/selftests/net/unicast_extensions.sh b/tools/testing/selftests/net/unicast_extensions.sh index f52aa5f7da524..3e751234ccfe8 100755 --- a/tools/testing/selftests/net/unicast_extensions.sh +++ b/tools/testing/selftests/net/unicast_extensions.sh @@ -30,14 +30,7 @@ source lib.sh -# nettest can be run from PATH or from same directory as this selftest -if ! which nettest >/dev/null; then - PATH=$PWD:$PATH - if ! which nettest >/dev/null; then - echo "'nettest' command not found; skipping tests" - exit $ksft_skip - fi -fi +check_gen_prog "nettest" result=0 diff --git a/tools/testing/selftests/net/vrf_route_leaking.sh b/tools/testing/selftests/net/vrf_route_leaking.sh index 152171fb1fc8c..e9c2f71da2072 100755 --- a/tools/testing/selftests/net/vrf_route_leaking.sh +++ b/tools/testing/selftests/net/vrf_route_leaking.sh @@ -59,7 +59,6 @@ # while it is forwarded between different vrfs. source lib.sh -PATH=$PWD:$PWD/tools/testing/selftests/net:$PATH VERBOSE=0 PAUSE_ON_FAIL=no DEFAULT_TTYPE=sym @@ -636,6 +635,8 @@ EOF # Some systems don't have a ping6 binary anymore command -v ping6 > /dev/null 2>&1 && ping6=$(command -v ping6) || ping6=$(command -v ping) +check_gen_prog "nettest" + TESTS_IPV4="ipv4_ping_ttl ipv4_traceroute ipv4_ping_frag ipv4_ping_local ipv4_tcp_local ipv4_udp_local ipv4_ping_ttl_asym ipv4_traceroute_asym" TESTS_IPV6="ipv6_ping_ttl ipv6_traceroute ipv6_ping_local ipv6_tcp_local ipv6_udp_local From a2f5c505b4378cd6fc7c4a44ff3665ccef2037db Mon Sep 17 00:00:00 2001 From: Sava Jakovljev Date: Wed, 21 Aug 2024 04:16:57 +0200 Subject: [PATCH 289/385] net: phy: realtek: Fix setting of PHY LEDs Mode B bit on RTL8211F The current implementation incorrectly sets the mode bit of the PHY chip. Bit 15 (RTL8211F_LEDCR_MODE) should not be shifted together with the configuration nibble of a LED- it should be set independently of the index of the LED being configured. As a consequence, the RTL8211F LED control is actually operating in Mode A. Fix the error by or-ing final register value to write with a const-value of RTL8211F_LEDCR_MODE, thus setting Mode bit explicitly. Fixes: 17784801d888 ("net: phy: realtek: Add support for PHY LEDs on RTL8211F") Signed-off-by: Sava Jakovljev Reviewed-by: Marek Vasut Link: https://patch.msgid.link/PAWP192MB21287372F30C4E55B6DF6158C38E2@PAWP192MB2128.EURP192.PROD.OUTLOOK.COM Signed-off-by: Paolo Abeni --- drivers/net/phy/realtek.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 87865918dab6d..25e5bfbb6f89b 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -555,7 +555,7 @@ static int rtl8211f_led_hw_control_set(struct phy_device *phydev, u8 index, unsigned long rules) { const u16 mask = RTL8211F_LEDCR_MASK << (RTL8211F_LEDCR_SHIFT * index); - u16 reg = RTL8211F_LEDCR_MODE; /* Mode B */ + u16 reg = 0; if (index >= RTL8211F_LED_COUNT) return -EINVAL; @@ -575,6 +575,7 @@ static int rtl8211f_led_hw_control_set(struct phy_device *phydev, u8 index, } reg <<= RTL8211F_LEDCR_SHIFT * index; + reg |= RTL8211F_LEDCR_MODE; /* Mode B */ return phy_modify_paged(phydev, 0xd04, RTL8211F_LEDCR, mask, reg); } From af688a99eb1fc7ef69774665d61e6be51cea627a Mon Sep 17 00:00:00 2001 From: Bharat Bhushan Date: Wed, 21 Aug 2024 12:35:58 +0530 Subject: [PATCH 290/385] octeontx2-af: Fix CPT AF register offset calculation Some CPT AF registers are per LF and others are global. Translation of PF/VF local LF slot number to actual LF slot number is required only for accessing perf LF registers. CPT AF global registers access do not require any LF slot number. Also, there is no reason CPT PF/VF to know actual lf's register offset. Without this fix microcode loading will fail, VFs cannot be created and hardware is not usable. Fixes: bc35e28af789 ("octeontx2-af: replace cpt slot with lf id on reg write") Signed-off-by: Bharat Bhushan Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240821070558.1020101-1-bbhushan2@marvell.com Signed-off-by: Paolo Abeni --- .../ethernet/marvell/octeontx2/af/rvu_cpt.c | 23 +++++++++---------- 1 file changed, 11 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c index 3e09d22858147..daf4b951e9059 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c @@ -632,7 +632,9 @@ int rvu_mbox_handler_cpt_inline_ipsec_cfg(struct rvu *rvu, return ret; } -static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req) +static bool validate_and_update_reg_offset(struct rvu *rvu, + struct cpt_rd_wr_reg_msg *req, + u64 *reg_offset) { u64 offset = req->reg_offset; int blkaddr, num_lfs, lf; @@ -663,6 +665,11 @@ static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req) if (lf < 0) return false; + /* Translate local LF's offset to global CPT LF's offset to + * access LFX register. + */ + *reg_offset = (req->reg_offset & 0xFF000) + (lf << 3); + return true; } else if (!(req->hdr.pcifunc & RVU_PFVF_FUNC_MASK)) { /* Registers that can be accessed from PF */ @@ -697,7 +704,7 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu, struct cpt_rd_wr_reg_msg *rsp) { u64 offset = req->reg_offset; - int blkaddr, lf; + int blkaddr; blkaddr = validate_and_get_cpt_blkaddr(req->blkaddr); if (blkaddr < 0) @@ -708,18 +715,10 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu, !is_cpt_vf(rvu, req->hdr.pcifunc)) return CPT_AF_ERR_ACCESS_DENIED; - if (!is_valid_offset(rvu, req)) + if (!validate_and_update_reg_offset(rvu, req, &offset)) return CPT_AF_ERR_ACCESS_DENIED; - /* Translate local LF used by VFs to global CPT LF */ - lf = rvu_get_lf(rvu, &rvu->hw->block[blkaddr], req->hdr.pcifunc, - (offset & 0xFFF) >> 3); - - /* Translate local LF's offset to global CPT LF's offset */ - offset &= 0xFF000; - offset += lf << 3; - - rsp->reg_offset = offset; + rsp->reg_offset = req->reg_offset; rsp->ret_val = req->ret_val; rsp->is_write = req->is_write; From 812a2751e827fa1eb01f3bd268b4d74c23f4226a Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Wed, 21 Aug 2024 09:30:14 +0200 Subject: [PATCH 291/385] net: airoha: configure hw mac address according to the port id GDM1 port on EN7581 SoC is connected to the lan dsa switch. GDM{2,3,4} can be used as wan port connected to an external phy module. Configure hw mac address registers according to the port id. Signed-off-by: Lorenzo Bianconi Link: https://patch.msgid.link/20240821-airoha-eth-wan-mac-addr-v2-1-8706d0cd6cd5@kernel.org Signed-off-by: Paolo Abeni --- drivers/net/ethernet/mediatek/airoha_eth.c | 32 ++++++++++++++++------ 1 file changed, 23 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c index 1fb46db0c1e9a..0c012efca3b07 100644 --- a/drivers/net/ethernet/mediatek/airoha_eth.c +++ b/drivers/net/ethernet/mediatek/airoha_eth.c @@ -67,9 +67,11 @@ #define FE_RST_GDM3_MBI_ARB_MASK BIT(2) #define FE_RST_CORE_MASK BIT(0) +#define REG_FE_WAN_MAC_H 0x0030 #define REG_FE_LAN_MAC_H 0x0040 -#define REG_FE_LAN_MAC_LMIN 0x0044 -#define REG_FE_LAN_MAC_LMAX 0x0048 + +#define REG_FE_MAC_LMIN(_n) ((_n) + 0x04) +#define REG_FE_MAC_LMAX(_n) ((_n) + 0x08) #define REG_FE_CDM1_OQ_MAP0 0x0050 #define REG_FE_CDM1_OQ_MAP1 0x0054 @@ -900,16 +902,28 @@ static void airoha_qdma_irq_disable(struct airoha_qdma *qdma, int index, airoha_qdma_set_irqmask(qdma, index, mask, 0); } -static void airoha_set_macaddr(struct airoha_eth *eth, const u8 *addr) +static bool airhoa_is_lan_gdm_port(struct airoha_gdm_port *port) { - u32 val; + /* GDM1 port on EN7581 SoC is connected to the lan dsa switch. + * GDM{2,3,4} can be used as wan port connected to an external + * phy module. + */ + return port->id == 1; +} + +static void airoha_set_macaddr(struct airoha_gdm_port *port, const u8 *addr) +{ + struct airoha_eth *eth = port->qdma->eth; + u32 val, reg; + reg = airhoa_is_lan_gdm_port(port) ? REG_FE_LAN_MAC_H + : REG_FE_WAN_MAC_H; val = (addr[0] << 16) | (addr[1] << 8) | addr[2]; - airoha_fe_wr(eth, REG_FE_LAN_MAC_H, val); + airoha_fe_wr(eth, reg, val); val = (addr[3] << 16) | (addr[4] << 8) | addr[5]; - airoha_fe_wr(eth, REG_FE_LAN_MAC_LMIN, val); - airoha_fe_wr(eth, REG_FE_LAN_MAC_LMAX, val); + airoha_fe_wr(eth, REG_FE_MAC_LMIN(reg), val); + airoha_fe_wr(eth, REG_FE_MAC_LMAX(reg), val); } static void airoha_set_gdm_port_fwd_cfg(struct airoha_eth *eth, u32 addr, @@ -2340,7 +2354,7 @@ static int airoha_dev_set_macaddr(struct net_device *dev, void *p) if (err) return err; - airoha_set_macaddr(port->qdma->eth, dev->dev_addr); + airoha_set_macaddr(port, dev->dev_addr); return 0; } @@ -2349,7 +2363,7 @@ static int airoha_dev_init(struct net_device *dev) { struct airoha_gdm_port *port = netdev_priv(dev); - airoha_set_macaddr(port->qdma->eth, dev->dev_addr); + airoha_set_macaddr(port, dev->dev_addr); return 0; } From d6f75d86aa786740ef7a7607685e9e1039e30aab Mon Sep 17 00:00:00 2001 From: Yu Jiaoliang Date: Wed, 21 Aug 2024 16:14:45 +0800 Subject: [PATCH 292/385] nfp: bpf: Use kmemdup_array instead of kmemdup for multiple allocation Let the kememdup_array() take care about multiplication and possible overflows. Signed-off-by: Yu Jiaoliang Signed-off-by: Louis Peens Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240821081447.12430-1-yujiaoliang@vivo.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/netronome/nfp/bpf/jit.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index df2ab5cbd49bd..3a02eef58cc6d 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -4537,8 +4537,8 @@ void *nfp_bpf_relo_for_vnic(struct nfp_prog *nfp_prog, struct nfp_bpf_vnic *bv) u64 *prog; int err; - prog = kmemdup(nfp_prog->prog, nfp_prog->prog_len * sizeof(u64), - GFP_KERNEL); + prog = kmemdup_array(nfp_prog->prog, nfp_prog->prog_len, sizeof(u64), + GFP_KERNEL); if (!prog) return ERR_PTR(-ENOMEM); From 1ac66c4960e1c735eb6edfd3e6d52bebb2aa347e Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 21 Aug 2024 09:46:44 +0100 Subject: [PATCH 293/385] MAINTAINERS: Add sonet.h to ATM section of MAINTAINERS This is part of an effort to assign a section in MAINTAINERS to header files that relate to Networking. In this case the files with "net" in their name. It seems that sonet.h is included in ATM related source files, and thus that ATM is the most relevant section for these files. Cc: Chas Williams <3chas3@gmail.com> Signed-off-by: Simon Horman Signed-off-by: Paolo Abeni --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index a964a34651f56..c682203915a2a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3504,7 +3504,9 @@ S: Maintained W: http://linux-atm.sourceforge.net F: drivers/atm/ F: include/linux/atm* +F: include/linux/sonet.h F: include/uapi/linux/atm* +F: include/uapi/linux/sonet.h ATMEL MACB ETHERNET DRIVER M: Nicolas Ferre From eb208fecd77d898709c25af680487289fd5f3e16 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 21 Aug 2024 09:46:45 +0100 Subject: [PATCH 294/385] MAINTAINERS: Add net_tstamp.h to SOCKET TIMESTAMPING section This is part of an effort to assign a section in MAINTAINERS to header files that relate to Networking. In this case the files with "net" in their name. Cc: Richard Cochran Cc: Willem de Bruijn Signed-off-by: Simon Horman Acked-by: Willem de Bruijn Signed-off-by: Paolo Abeni --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index c682203915a2a..e5b9a4d9bc21d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -21057,6 +21057,7 @@ SOCKET TIMESTAMPING M: Willem de Bruijn S: Maintained F: Documentation/networking/timestamping.rst +F: include/linux/net_tstamp.h F: include/uapi/linux/net_tstamp.h F: tools/testing/selftests/net/so_txtime.c From 8cb0a938d90b25f123fcb2e24bbda9eaabd79c9e Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 21 Aug 2024 09:46:46 +0100 Subject: [PATCH 295/385] MAINTAINERS: Add limited globs for Networking headers This aims to add limited globs to improve the coverage of header files in the NETWORKING DRIVERS and NETWORKING [GENERAL] sections. It is done so in a minimal way to exclude overlap with other sections. And so as not to require "X" entries to exclude files otherwise matched by these new globs. While imperfect, due to it's limited nature, this does extend coverage of header files by these sections. And aims to automatically cover new files that seem very likely belong to these sections. The include/linux/netdev* glob (both sections) + Subsumes the entries for: - include/linux/netdevice.h + Extends the sections to cover - include/linux/netdevice_xmit.h - include/linux/netdev_features.h The include/uapi/linux/netdev* globs: (both sections) + Subsumes the entries for: - include/linux/netdevice.h + Extends the sections to cover - include/linux/netdev.h The include/linux/skbuff* glob (NETWORKING [GENERAL] section only): + Subsumes the entry for: - include/linux/skbuff.h + Extends the section to cover - include/linux/skbuff_ref.h A include/uapi/linux/net_* glob was not added to the NETWORKING [GENERAL] section. Although it would subsume the entry for include/uapi/linux/net_namespace.h, which is fine, it would also extend coverage to: - include/uapi/linux/net_dropmon.h, which belongs to the NETWORK DROP MONITOR section - include/uapi/linux/net_tstamp.h which, as per an earlier patch in this series, belongs to the SOCKET TIMESTAMPING section Signed-off-by: Simon Horman Signed-off-by: Paolo Abeni --- MAINTAINERS | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index e5b9a4d9bc21d..03d571b131eb0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15884,10 +15884,10 @@ F: include/linux/fddidevice.h F: include/linux/hippidevice.h F: include/linux/if_* F: include/linux/inetdevice.h -F: include/linux/netdevice.h +F: include/linux/netdev* F: include/uapi/linux/cn_proc.h F: include/uapi/linux/if_* -F: include/uapi/linux/netdevice.h +F: include/uapi/linux/netdev* F: tools/testing/selftests/drivers/net/ X: drivers/net/wireless/ @@ -15940,13 +15940,13 @@ F: include/linux/framer/framer.h F: include/linux/in.h F: include/linux/indirect_call_wrapper.h F: include/linux/net.h -F: include/linux/netdevice.h -F: include/linux/skbuff.h +F: include/linux/netdev* +F: include/linux/skbuff* F: include/net/ F: include/uapi/linux/in.h F: include/uapi/linux/net.h F: include/uapi/linux/net_namespace.h -F: include/uapi/linux/netdevice.h +F: include/uapi/linux/netdev* F: lib/net_utils.c F: lib/random32.c F: net/ From f2d20c9b97f0df64841b89fa1ad3e9c92f7377ae Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 21 Aug 2024 09:46:47 +0100 Subject: [PATCH 296/385] MAINTAINERS: Add header files to NETWORKING sections This is part of an effort to assign a section in MAINTAINERS to header files that relate to Networking. In this case the files with "net" or "skbuff" in their name. This patch adds a number of such files to the NETWORKING DRIVERS and NETWORKING [GENERAL] sections. Signed-off-by: Simon Horman Signed-off-by: Paolo Abeni --- MAINTAINERS | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 03d571b131eb0..798f1ffcbbaaf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15879,13 +15879,16 @@ F: drivers/net/ F: include/dt-bindings/net/ F: include/linux/cn_proc.h F: include/linux/etherdevice.h +F: include/linux/ethtool_netlink.h F: include/linux/fcdevice.h F: include/linux/fddidevice.h F: include/linux/hippidevice.h F: include/linux/if_* F: include/linux/inetdevice.h F: include/linux/netdev* +F: include/linux/platform_data/wiznet.h F: include/uapi/linux/cn_proc.h +F: include/uapi/linux/ethtool_netlink.h F: include/uapi/linux/if_* F: include/uapi/linux/netdev* F: tools/testing/selftests/drivers/net/ @@ -15939,14 +15942,28 @@ F: include/linux/framer/framer-provider.h F: include/linux/framer/framer.h F: include/linux/in.h F: include/linux/indirect_call_wrapper.h +F: include/linux/inet.h +F: include/linux/inet_diag.h F: include/linux/net.h F: include/linux/netdev* +F: include/linux/netlink.h +F: include/linux/netpoll.h +F: include/linux/rtnetlink.h +F: include/linux/seq_file_net.h F: include/linux/skbuff* F: include/net/ +F: include/uapi/linux/genetlink.h +F: include/uapi/linux/hsr_netlink.h F: include/uapi/linux/in.h +F: include/uapi/linux/inet_diag.h +F: include/uapi/linux/nbd-netlink.h F: include/uapi/linux/net.h F: include/uapi/linux/net_namespace.h +F: include/uapi/linux/netconf.h F: include/uapi/linux/netdev* +F: include/uapi/linux/netlink.h +F: include/uapi/linux/netlink_diag.h +F: include/uapi/linux/rtnetlink.h F: lib/net_utils.c F: lib/random32.c F: net/ From 46097a92662496394628cb41138e681d6074cce7 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 21 Aug 2024 09:46:48 +0100 Subject: [PATCH 297/385] MAINTAINERS: Mark JME Network Driver as Odd Fixes This driver only appears to have received sporadic clean-ups, typically part of some tree-wide activity, and fixes for quite some time. And according to the maintainer, Guo-Fu Tseng, the device has been EOLed for a long time (see Link). Accordingly, it seems appropriate to mark this driver as odd fixes. Cc: Moon Yeounsu Cc: Guo-Fu Tseng Link: https://lore.kernel.org/netdev/20240805003139.M94125@cooldavid.org/ Signed-off-by: Simon Horman Signed-off-by: Paolo Abeni --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 798f1ffcbbaaf..0c94ec0ca4782 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11995,7 +11995,7 @@ F: fs/jfs/ JME NETWORK DRIVER M: Guo-Fu Tseng L: netdev@vger.kernel.org -S: Maintained +S: Odd Fixes F: drivers/net/ethernet/jme.* JOURNALLING FLASH FILE SYSTEM V2 (JFFS2) From 8fb4ac1cee88a57e7a56faba49b408a41a4af4db Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 18 Aug 2024 16:07:11 +0900 Subject: [PATCH 298/385] kbuild: fix typos "prequisites" to "prerequisites" This typo in scripts/Makefile.build has been present for more than 20 years. It was accidentally copy-pasted to other scripts/Makefile.* files. Fix them all. Signed-off-by: Masahiro Yamada Reviewed-by: Nathan Chancellor --- scripts/Makefile.build | 2 +- scripts/Makefile.modfinal | 2 +- scripts/Makefile.vmlinux | 2 +- scripts/Makefile.vmlinux_o | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index efacca63c8976..a5ac8ed1936fe 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -487,7 +487,7 @@ $(subdir-ym): need-modorder=$(if $(filter $@/modules.order, $(subdir-modorder)),1) \ $(filter $@/%, $(single-subdir-goals)) -# Add FORCE to the prequisites of a target to force it to be always rebuilt. +# Add FORCE to the prerequisites of a target to force it to be always rebuilt. # --------------------------------------------------------------------------- PHONY += FORCE diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal index 1fa98b5e952b4..306a6bb86e4dc 100644 --- a/scripts/Makefile.modfinal +++ b/scripts/Makefile.modfinal @@ -62,7 +62,7 @@ endif targets += $(modules:%.o=%.ko) $(modules:%.o=%.mod.o) -# Add FORCE to the prequisites of a target to force it to be always rebuilt. +# Add FORCE to the prerequisites of a target to force it to be always rebuilt. # --------------------------------------------------------------------------- PHONY += FORCE diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux index 49946cb968440..5ceecbed31eb7 100644 --- a/scripts/Makefile.vmlinux +++ b/scripts/Makefile.vmlinux @@ -33,7 +33,7 @@ targets += vmlinux vmlinux: scripts/link-vmlinux.sh vmlinux.o $(KBUILD_LDS) FORCE +$(call if_changed_dep,link_vmlinux) -# Add FORCE to the prequisites of a target to force it to be always rebuilt. +# Add FORCE to the prerequisites of a target to force it to be always rebuilt. # --------------------------------------------------------------------------- PHONY += FORCE diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o index 6de297916ce68..d64070b6b4bce 100644 --- a/scripts/Makefile.vmlinux_o +++ b/scripts/Makefile.vmlinux_o @@ -87,7 +87,7 @@ targets += modules.builtin modules.builtin: modules.builtin.modinfo FORCE $(call if_changed,modules_builtin) -# Add FORCE to the prequisites of a target to force it to be always rebuilt. +# Add FORCE to the prerequisites of a target to force it to be always rebuilt. # --------------------------------------------------------------------------- PHONY += FORCE From 4ae738dfef2c0323752ab81786e2d298c9939321 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Thu, 22 Aug 2024 11:40:55 -0400 Subject: [PATCH 299/385] net: xilinx: axienet: Always disable promiscuous mode If promiscuous mode is disabled when there are fewer than four multicast addresses, then it will not be reflected in the hardware. Fix this by always clearing the promiscuous mode flag even when we program multicast addresses. Fixes: 8a3b7a252dca ("drivers/net/ethernet/xilinx: added Xilinx AXI Ethernet driver") Signed-off-by: Sean Anderson Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240822154059.1066595-2-sean.anderson@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 02fdf66e07faa..163d052480071 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -450,6 +450,10 @@ static void axienet_set_multicast_list(struct net_device *ndev) } else if (!netdev_mc_empty(ndev)) { struct netdev_hw_addr *ha; + reg = axienet_ior(lp, XAE_FMI_OFFSET); + reg &= ~XAE_FMI_PM_MASK; + axienet_iow(lp, XAE_FMI_OFFSET, reg); + i = 0; netdev_for_each_mc_addr(ha, ndev) { if (i >= XAE_MULTICAST_CAM_TABLE_NUM) From 797a68c9de0f5a5447baf4bd3bb9c10a3993435b Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Thu, 22 Aug 2024 11:40:56 -0400 Subject: [PATCH 300/385] net: xilinx: axienet: Fix dangling multicast addresses If a multicast address is removed but there are still some multicast addresses, that address would remain programmed into the frame filter. Fix this by explicitly setting the enable bit for each filter. Fixes: 8a3b7a252dca ("drivers/net/ethernet/xilinx: added Xilinx AXI Ethernet driver") Signed-off-by: Sean Anderson Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240822154059.1066595-3-sean.anderson@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/xilinx/xilinx_axienet.h | 1 + .../net/ethernet/xilinx/xilinx_axienet_main.c | 21 ++++++++----------- 2 files changed, 10 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index c7d9221fafdcb..09c9f9787180b 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -170,6 +170,7 @@ #define XAE_UAW0_OFFSET 0x00000700 /* Unicast address word 0 */ #define XAE_UAW1_OFFSET 0x00000704 /* Unicast address word 1 */ #define XAE_FMI_OFFSET 0x00000708 /* Frame Filter Control */ +#define XAE_FFE_OFFSET 0x0000070C /* Frame Filter Enable */ #define XAE_AF0_OFFSET 0x00000710 /* Address Filter 0 */ #define XAE_AF1_OFFSET 0x00000714 /* Address Filter 1 */ diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 163d052480071..9aeb7b9f3ae40 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -432,7 +432,7 @@ static int netdev_set_mac_address(struct net_device *ndev, void *p) */ static void axienet_set_multicast_list(struct net_device *ndev) { - int i; + int i = 0; u32 reg, af0reg, af1reg; struct axienet_local *lp = netdev_priv(ndev); @@ -454,7 +454,6 @@ static void axienet_set_multicast_list(struct net_device *ndev) reg &= ~XAE_FMI_PM_MASK; axienet_iow(lp, XAE_FMI_OFFSET, reg); - i = 0; netdev_for_each_mc_addr(ha, ndev) { if (i >= XAE_MULTICAST_CAM_TABLE_NUM) break; @@ -473,6 +472,7 @@ static void axienet_set_multicast_list(struct net_device *ndev) axienet_iow(lp, XAE_FMI_OFFSET, reg); axienet_iow(lp, XAE_AF0_OFFSET, af0reg); axienet_iow(lp, XAE_AF1_OFFSET, af1reg); + axienet_iow(lp, XAE_FFE_OFFSET, 1); i++; } } else { @@ -480,18 +480,15 @@ static void axienet_set_multicast_list(struct net_device *ndev) reg &= ~XAE_FMI_PM_MASK; axienet_iow(lp, XAE_FMI_OFFSET, reg); - - for (i = 0; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) { - reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00; - reg |= i; - - axienet_iow(lp, XAE_FMI_OFFSET, reg); - axienet_iow(lp, XAE_AF0_OFFSET, 0); - axienet_iow(lp, XAE_AF1_OFFSET, 0); - } - dev_info(&ndev->dev, "Promiscuous mode disabled.\n"); } + + for (; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) { + reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00; + reg |= i; + axienet_iow(lp, XAE_FMI_OFFSET, reg); + axienet_iow(lp, XAE_FFE_OFFSET, 0); + } } /** From 57fb67783c4011581882f32e656d738da1f82042 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Wed, 21 Aug 2024 20:32:52 +0800 Subject: [PATCH 301/385] net: ovs: fix ovs_drop_reasons error There is something wrong with ovs_drop_reasons. ovs_drop_reasons[0] is "OVS_DROP_LAST_ACTION", but OVS_DROP_LAST_ACTION == __OVS_DROP_REASON + 1, which means that ovs_drop_reasons[1] should be "OVS_DROP_LAST_ACTION". And as Adrian tested, without the patch, adding flow to drop packets results in: drop at: do_execute_actions+0x197/0xb20 [openvsw (0xffffffffc0db6f97) origin: software input port ifindex: 8 timestamp: Tue Aug 20 10:19:17 2024 859853461 nsec protocol: 0x800 length: 98 original length: 98 drop reason: OVS_DROP_ACTION_ERROR With the patch, the same results in: drop at: do_execute_actions+0x197/0xb20 [openvsw (0xffffffffc0db6f97) origin: software input port ifindex: 8 timestamp: Tue Aug 20 10:16:13 2024 475856608 nsec protocol: 0x800 length: 98 original length: 98 drop reason: OVS_DROP_LAST_ACTION Fix this by initializing ovs_drop_reasons with index. Fixes: 9d802da40b7c ("net: openvswitch: add last-action drop reason") Signed-off-by: Menglong Dong Tested-by: Adrian Moreno Reviewed-by: Adrian Moreno Link: https://patch.msgid.link/20240821123252.186305-1-dongml2@chinatelecom.cn Signed-off-by: Jakub Kicinski --- net/openvswitch/datapath.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 99d72543abd3a..78d9961fcd446 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2706,7 +2706,7 @@ static struct pernet_operations ovs_net_ops = { }; static const char * const ovs_drop_reasons[] = { -#define S(x) (#x), +#define S(x) [(x) & ~SKB_DROP_REASON_SUBSYS_MASK] = (#x), OVS_DROP_REASONS(S) #undef S }; From 0124fb0ebf3b0ef89892d42147c9387be3105318 Mon Sep 17 00:00:00 2001 From: Alexandra Winter Date: Wed, 21 Aug 2024 11:13:37 +0200 Subject: [PATCH 302/385] s390/iucv: Fix vargs handling in iucv_alloc_device() iucv_alloc_device() gets a format string and a varying number of arguments. This is incorrectly forwarded by calling dev_set_name() with the format string and a va_list, while dev_set_name() expects also a varying number of arguments. Symptoms: Corrupted iucv device names, which can result in log messages like: sysfs: cannot create duplicate filename '/devices/iucv/hvc_iucv1827699952' Fixes: 4452e8ef8c36 ("s390/iucv: Provide iucv_alloc_device() / iucv_release_device()") Link: https://bugzilla.suse.com/show_bug.cgi?id=1228425 Signed-off-by: Alexandra Winter Reviewed-by: Thorsten Winkler Reviewed-by: Przemek Kitszel Link: https://patch.msgid.link/20240821091337.3627068-1-wintera@linux.ibm.com Signed-off-by: Jakub Kicinski --- net/iucv/iucv.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 1e42e13ad24e3..d3e9efab7f4bd 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -86,13 +86,15 @@ struct device *iucv_alloc_device(const struct attribute_group **attrs, { struct device *dev; va_list vargs; + char buf[20]; int rc; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) goto out_error; va_start(vargs, fmt); - rc = dev_set_name(dev, fmt, vargs); + vsnprintf(buf, sizeof(buf), fmt, vargs); + rc = dev_set_name(dev, "%s", buf); va_end(vargs); if (rc) goto out_error; From 5874e0c9f25661c2faefe4809907166defae3d7f Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 21 Aug 2024 16:58:57 +0100 Subject: [PATCH 303/385] net: atlantic: Avoid warning about potential string truncation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit W=1 builds with GCC 14.2.0 warn that: .../aq_ethtool.c:278:59: warning: ‘%d’ directive output may be truncated writing between 1 and 11 bytes into a region of size 6 [-Wformat-truncation=] 278 | snprintf(tc_string, 8, "TC%d ", tc); | ^~ .../aq_ethtool.c:278:56: note: directive argument in the range [-2147483641, 254] 278 | snprintf(tc_string, 8, "TC%d ", tc); | ^~~~~~~ .../aq_ethtool.c:278:33: note: ‘snprintf’ output between 5 and 15 bytes into a destination of size 8 278 | snprintf(tc_string, 8, "TC%d ", tc); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ tc is always in the range 0 - cfg->tcs. And as cfg->tcs is a u8, the range is 0 - 255. Further, on inspecting the code, it seems that cfg->tcs will never be more than AQ_CFG_TCS_MAX (8), so the range is actually 0 - 8. So, it seems that the condition that GCC flags will not occur. But, nonetheless, it would be nice if it didn't emit the warning. It seems that this can be achieved by changing the format specifier from %d to %u, in which case I believe GCC recognises an upper bound on the range of tc of 0 - 255. After some experimentation I think this is due to the combination of the use of %u and the type of cfg->tcs (u8). Empirically, updating the type of the tc variable to unsigned int has the same effect. As both of these changes seem to make sense in relation to what the code is actually doing - iterating over unsigned values - do both. Compile tested only. Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240821-atlantic-str-v1-1-fa2cfe38ca00@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index 38f22918c699f..440ff4616fec1 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -266,7 +266,7 @@ static void aq_ethtool_get_strings(struct net_device *ndev, const int rx_stat_cnt = ARRAY_SIZE(aq_ethtool_queue_rx_stat_names); const int tx_stat_cnt = ARRAY_SIZE(aq_ethtool_queue_tx_stat_names); char tc_string[8]; - int tc; + unsigned int tc; memset(tc_string, 0, sizeof(tc_string)); memcpy(p, aq_ethtool_stat_names, @@ -275,7 +275,7 @@ static void aq_ethtool_get_strings(struct net_device *ndev, for (tc = 0; tc < cfg->tcs; tc++) { if (cfg->is_qos) - snprintf(tc_string, 8, "TC%d ", tc); + snprintf(tc_string, 8, "TC%u ", tc); for (i = 0; i < cfg->vecs; i++) { for (si = 0; si < rx_stat_cnt; si++) { From 1820b84f3c61fbe5d9cf82a09cb9733a23cd463c Mon Sep 17 00:00:00 2001 From: Abhinav Jain Date: Wed, 21 Aug 2024 22:49:01 +0530 Subject: [PATCH 304/385] selftests: net: Create veth pair for testing in networkless kernel Check if the netdev list is empty and create veth pair to be used for feature on/off testing. Remove the veth pair after testing is complete. Signed-off-by: Abhinav Jain Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240821171903.118324-2-jain.abhinav177@gmail.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/netdevice.sh | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh index e3afcb4247103..999d72b6670c2 100755 --- a/tools/testing/selftests/net/netdevice.sh +++ b/tools/testing/selftests/net/netdevice.sh @@ -129,6 +129,7 @@ kci_netdev_ethtool() kci_netdev_ethtool_test 74 'dump' "ethtool -d $netdev" kci_netdev_ethtool_test 94 'stats' "ethtool -S $netdev" + return 0 } @@ -196,10 +197,24 @@ if [ ! -e "$TMP_LIST_NETDEV" ];then fi ip link show |grep '^[0-9]' | grep -oE '[[:space:]].*eth[0-9]*:|[[:space:]].*enp[0-9]s[0-9]:' | cut -d\ -f2 | cut -d: -f1> "$TMP_LIST_NETDEV" + +if [ ! -s "$TMP_LIST_NETDEV" ]; then + echo "No valid network device found, creating veth pair" + ip link add veth0 type veth peer name veth1 + echo "veth0" > "$TMP_LIST_NETDEV" + veth_created=1 +fi + while read netdev do kci_test_netdev "$netdev" done < "$TMP_LIST_NETDEV" +#clean up veth interface pair if it was created +if [ "$veth_created" ]; then + ip link delete veth0 + echo "Removed veth pair" +fi + rm "$TMP_LIST_NETDEV" exit 0 From 6ce7bdbc0d4bde7578727e95e7d138e364512b33 Mon Sep 17 00:00:00 2001 From: Abhinav Jain Date: Wed, 21 Aug 2024 22:49:02 +0530 Subject: [PATCH 305/385] selftests: net: Add on/off checks for non-fixed features of interface Implement on/off testing for all non-fixed features via while loop. Signed-off-by: Abhinav Jain Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240821171903.118324-3-jain.abhinav177@gmail.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/netdevice.sh | 35 +++++++++++++++++++++++- 1 file changed, 34 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh index 999d72b6670c2..f7752e1ebe22d 100755 --- a/tools/testing/selftests/net/netdevice.sh +++ b/tools/testing/selftests/net/netdevice.sh @@ -124,7 +124,40 @@ kci_netdev_ethtool() return 1 fi echo "PASS: $netdev: ethtool list features" - #TODO for each non fixed features, try to turn them on/off + + while read -r FEATURE VALUE FIXED; do + [ "$FEATURE" != "Features" ] || continue # Skip "Features" + [ "$FIXED" != "[fixed]" ] || continue # Skip fixed features + feature="${FEATURE%:*}" + + ethtool --offload "$netdev" "$feature" off + if [ $? -eq 0 ]; then + echo "PASS: $netdev: Turned off feature: $feature" + else + echo "FAIL: $netdev: Failed to turn off feature:" \ + "$feature" + fi + + ethtool --offload "$netdev" "$feature" on + if [ $? -eq 0 ]; then + echo "PASS: $netdev: Turned on feature: $feature" + else + echo "FAIL: $netdev: Failed to turn on feature:" \ + "$feature" + fi + + #restore the feature to its initial state + ethtool --offload "$netdev" "$feature" "$VALUE" + if [ $? -eq 0 ]; then + echo "PASS: $netdev: Restore feature $feature" \ + "to initial state $VALUE" + else + echo "FAIL: $netdev: Failed to restore feature" \ + "$feature to initial state $VALUE" + fi + + done < "$TMP_ETHTOOL_FEATURES" + rm "$TMP_ETHTOOL_FEATURES" kci_netdev_ethtool_test 74 'dump' "ethtool -d $netdev" From 8402a158028ffe030f3a02ec57b8c94cb94b137c Mon Sep 17 00:00:00 2001 From: Abhinav Jain Date: Wed, 21 Aug 2024 22:49:03 +0530 Subject: [PATCH 306/385] selftests: net: Use XFAIL for operations not supported by the driver Check if veth pair was created and if yes, xfail on setting IP address logging an informational message. Use XFAIL instead of SKIP for unsupported ethtool APIs. Signed-off-by: Abhinav Jain Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240821171903.118324-4-jain.abhinav177@gmail.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/netdevice.sh | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh index f7752e1ebe22d..438f7b2acc5fc 100755 --- a/tools/testing/selftests/net/netdevice.sh +++ b/tools/testing/selftests/net/netdevice.sh @@ -67,8 +67,12 @@ kci_net_setup() return $ksft_skip fi - # TODO what ipaddr to set ? DHCP ? - echo "SKIP: $netdev: set IP address" + if [ "$veth_created" ]; then + echo "XFAIL: $netdev: set IP address unsupported for veth*" + else + # TODO what ipaddr to set ? DHCP ? + echo "SKIP: $netdev: set IP address" + fi return $ksft_skip } @@ -86,7 +90,7 @@ kci_netdev_ethtool_test() ret=$? if [ $ret -ne 0 ];then if [ $ret -eq "$1" ];then - echo "SKIP: $netdev: ethtool $2 not supported" + echo "XFAIL: $netdev: ethtool $2 not supported" return $ksft_skip else echo "FAIL: $netdev: ethtool $2" From ef434fae72287a9cd0f7b85ad1701b998cce800b Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 21 Aug 2024 15:52:40 +0300 Subject: [PATCH 307/385] bpf: Unmask upper DSCP bits in bpf_fib_lookup() helper The helper performs a FIB lookup according to the parameters in the 'params' argument, one of which is 'tos'. According to the test in test_tc_neigh_fib.c, it seems that BPF programs are expected to initialize the 'tos' field to the full 8 bit DS field from the IPv4 header. Unmask the upper DSCP bits before invoking the IPv4 FIB lookup APIs so that in the future the lookup could be performed according to the full DSCP value. No functional changes intended since the upper DSCP bits are masked when comparing against the TOS selectors in FIB rules and routes. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Acked-by: Florian Westphal Reviewed-by: David Ahern Link: https://patch.msgid.link/20240821125251.1571445-2-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/core/filter.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/core/filter.c b/net/core/filter.c index f3c72cf860997..89f56fac48fbb 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -84,6 +84,7 @@ #include #include #include +#include #include "dev.h" @@ -5899,7 +5900,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, fl4.flowi4_iif = params->ifindex; fl4.flowi4_oif = 0; } - fl4.flowi4_tos = params->tos & IPTOS_RT_MASK; + fl4.flowi4_tos = params->tos & INET_DSCP_MASK; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = 0; From bc52a4eecefdd686065f8f68ba9e1c83d4ce6f14 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 21 Aug 2024 15:52:41 +0300 Subject: [PATCH 308/385] ipv4: Unmask upper DSCP bits in NETLINK_FIB_LOOKUP family The NETLINK_FIB_LOOKUP netlink family can be used to perform a FIB lookup according to user provided parameters and communicate the result back to user space. Unmask the upper DSCP bits of the user-provided DS field before invoking the IPv4 FIB lookup API so that in the future the lookup could be performed according to the full DSCP value. No functional changes intended since the upper DSCP bits are masked when comparing against the TOS selectors in FIB rules and routes. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Acked-by: Florian Westphal Reviewed-by: David Ahern Link: https://patch.msgid.link/20240821125251.1571445-3-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/fib_frontend.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index da540ddb7af65..8b740f575da1a 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1343,7 +1343,7 @@ static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn) struct flowi4 fl4 = { .flowi4_mark = frn->fl_mark, .daddr = frn->fl_addr, - .flowi4_tos = frn->fl_tos & IPTOS_RT_MASK, + .flowi4_tos = frn->fl_tos & INET_DSCP_MASK, .flowi4_scope = frn->fl_scope, }; struct fib_table *tb; From be2e9089cb34dfc958d8383a755bde3681a817b2 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 21 Aug 2024 15:52:42 +0300 Subject: [PATCH 309/385] ipv4: Unmask upper DSCP bits when constructing the Record Route option The Record Route IP option records the addresses of the routers that routed the packet. In the case of forwarded packets, the kernel performs a route lookup via fib_lookup() and fills in the preferred source address of the matched route. Unmask the upper DSCP bits when performing the lookup so that in the future the lookup could be performed according to the full DSCP value. No functional changes intended since the upper DSCP bits are masked when comparing against the TOS selectors in FIB rules and routes. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Acked-by: Florian Westphal Reviewed-by: David Ahern Link: https://patch.msgid.link/20240821125251.1571445-4-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 13c0f1d455f33..9b6528b7b5629 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1263,7 +1263,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, - .flowi4_tos = iph->tos & IPTOS_RT_MASK, + .flowi4_tos = iph->tos & INET_DSCP_MASK, .flowi4_oif = rt->dst.dev->ifindex, .flowi4_iif = skb->dev->ifindex, .flowi4_mark = skb->mark, From c1ae5ca69b691a7403e85047382fc4fd6a69ee9f Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 21 Aug 2024 15:52:43 +0300 Subject: [PATCH 310/385] netfilter: rpfilter: Unmask upper DSCP bits The rpfilter match performs a reverse path filter test on a packet by performing a FIB lookup with the source and destination addresses swapped. Unmask the upper DSCP bits of the DS field of the tested packet so that in the future the FIB lookup could be performed according to the full DSCP value. No functional changes intended since the upper DSCP bits are masked when comparing against the TOS selectors in FIB rules and routes. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Acked-by: Florian Westphal Reviewed-by: David Ahern Link: https://patch.msgid.link/20240821125251.1571445-5-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/netfilter/ipt_rpfilter.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index ded5bef02f771..1ce7a1655b974 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -75,7 +76,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.daddr = iph->saddr; flow.saddr = rpfilter_get_saddr(iph->daddr); flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; - flow.flowi4_tos = iph->tos & IPTOS_RT_MASK; + flow.flowi4_tos = iph->tos & INET_DSCP_MASK; flow.flowi4_scope = RT_SCOPE_UNIVERSE; flow.flowi4_l3mdev = l3mdev_master_ifindex_rcu(xt_in(par)); flow.flowi4_uid = sock_net_uid(xt_net(par), NULL); From 338385e059c5d299556fa341d10601ae72c6e932 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 21 Aug 2024 15:52:44 +0300 Subject: [PATCH 311/385] netfilter: nft_fib: Unmask upper DSCP bits In a similar fashion to the iptables rpfilter match, unmask the upper DSCP bits of the DS field of the currently tested packet so that in the future the FIB lookup could be performed according to the full DSCP value. No functional changes intended since the upper DSCP bits are masked when comparing against the TOS selectors in FIB rules and routes. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Acked-by: Florian Westphal Reviewed-by: David Ahern Link: https://patch.msgid.link/20240821125251.1571445-6-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/netfilter/nft_fib_ipv4.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index df94bc28c3d79..00da1332bbf1a 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -10,6 +10,7 @@ #include #include +#include #include #include @@ -108,7 +109,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, if (priv->flags & NFTA_FIB_F_MARK) fl4.flowi4_mark = pkt->skb->mark; - fl4.flowi4_tos = iph->tos & IPTOS_RT_MASK; + fl4.flowi4_tos = iph->tos & INET_DSCP_MASK; if (priv->flags & NFTA_FIB_F_DADDR) { fl4.daddr = iph->daddr; From 2bc9778b6696337f1e0b38f07522319296b39d83 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 21 Aug 2024 15:52:45 +0300 Subject: [PATCH 312/385] ipv4: ipmr: Unmask upper DSCP bits in ipmr_rt_fib_lookup() Unmask the upper DSCP bits when calling ipmr_fib_lookup() so that in the future it could perform the FIB lookup according to the full DSCP value. Note that ipmr_fib_lookup() performs a FIB rule lookup (returning the relevant routing table) and that IPv4 multicast FIB rules do not support matching on TOS / DSCP. However, it is still worth unmasking the upper DSCP bits in case support for DSCP matching is ever added. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Acked-by: Florian Westphal Reviewed-by: David Ahern Link: https://patch.msgid.link/20240821125251.1571445-7-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/ipmr.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 6c750bd13dd8d..d5295b69bc0af 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -62,6 +62,7 @@ #include #include #include +#include #include @@ -2080,7 +2081,7 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, - .flowi4_tos = RT_TOS(iph->tos), + .flowi4_tos = iph->tos & INET_DSCP_MASK, .flowi4_oif = (rt_is_output_route(rt) ? skb->dev->ifindex : 0), .flowi4_iif = (rt_is_output_route(rt) ? From 39d3628f7ceabd22385dcd6811ed4c353f7c859b Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 21 Aug 2024 15:52:46 +0300 Subject: [PATCH 313/385] ipv4: Unmask upper DSCP bits in fib_compute_spec_dst() As explained in commit 35ebf65e851c ("ipv4: Create and use fib_compute_spec_dst() helper."), the function is used - for example - to determine the source address for an ICMP reply. If we are responding to a multicast or broadcast packet, the source address is set to the source address that we would use if we were to send a packet to the unicast source of the original packet. This address is determined by performing a FIB lookup and using the preferred source address of the resulting route. Unmask the upper DSCP bits of the DS field of the packet that triggered the reply so that in the future the FIB lookup could be performed according to the full DSCP value. No functional changes intended since the upper DSCP bits are masked when comparing against the TOS selectors in FIB rules and routes. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Acked-by: Florian Westphal Reviewed-by: David Ahern Link: https://patch.msgid.link/20240821125251.1571445-8-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/fib_frontend.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 8b740f575da1a..793e6781399a4 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -293,7 +293,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, - .flowi4_tos = ip_hdr(skb)->tos & IPTOS_RT_MASK, + .flowi4_tos = ip_hdr(skb)->tos & INET_DSCP_MASK, .flowi4_scope = scope, .flowi4_mark = vmark ? skb->mark : 0, }; From df9131c7fafdc0d4c85686f5c7711a4dd4f3ae60 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 21 Aug 2024 15:52:47 +0300 Subject: [PATCH 314/385] ipv4: Unmask upper DSCP bits in input route lookup Unmask the upper DSCP bits in input route lookup so that in the future the lookup could be performed according to the full DSCP value. No functional changes intended since the upper DSCP bits are masked when comparing against the TOS selectors in FIB rules and routes. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Acked-by: Florian Westphal Reviewed-by: David Ahern Link: https://patch.msgid.link/20240821125251.1571445-9-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 9b6528b7b5629..73bb61162445f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2470,7 +2470,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct fib_result res; int err; - tos &= IPTOS_RT_MASK; + tos &= INET_DSCP_MASK; rcu_read_lock(); err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res); rcu_read_unlock(); From b1251a6f1a9b475725a097e75196ee105076cbd1 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 21 Aug 2024 15:52:48 +0300 Subject: [PATCH 315/385] ipv4: Unmask upper DSCP bits in RTM_GETROUTE input route lookup Unmask the upper DSCP bits when looking up an input route via the RTM_GETROUTE netlink message so that in the future the lookup could be performed according to the full DSCP value. No functional changes intended since the upper DSCP bits are masked when comparing against the TOS selectors in FIB rules and routes. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Acked-by: Florian Westphal Reviewed-by: David Ahern Link: https://patch.msgid.link/20240821125251.1571445-10-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 73bb61162445f..524b70ab77a0e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3286,7 +3286,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, skb->dev = dev; skb->mark = mark; err = ip_route_input_rcu(skb, dst, src, - rtm->rtm_tos & IPTOS_RT_MASK, dev, + rtm->rtm_tos & INET_DSCP_MASK, dev, &res); rt = skb_rtable(skb); From 1c6f50b37f711b831d78973dad0df1da99ad0014 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 21 Aug 2024 15:52:49 +0300 Subject: [PATCH 316/385] ipv4: icmp: Pass full DS field to ip_route_input() Align the ICMP code to other callers of ip_route_input() and pass the full DS field. In the future this will allow us to perform a route lookup according to the full DSCP value. No functional changes intended since the upper DSCP bits are masked when comparing against the TOS selectors in FIB rules and routes. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Acked-by: Florian Westphal Reviewed-by: David Ahern Link: https://patch.msgid.link/20240821125251.1571445-11-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/icmp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index ab6d0d98dbc34..b8f56d03fcbb6 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -545,7 +545,7 @@ static struct rtable *icmp_route_lookup(struct net *net, orefdst = skb_in->_skb_refdst; /* save old refdst */ skb_dst_set(skb_in, NULL); err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, - RT_TOS(tos), rt2->dst.dev); + tos, rt2->dst.dev); dst_release(&rt2->dst); rt2 = skb_rtable(skb_in); From b6791ac5ea49aec7f9ef123ebc728fa6a5f9090a Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 21 Aug 2024 15:52:50 +0300 Subject: [PATCH 317/385] ipv4: udp: Unmask upper DSCP bits during early demux Unmask the upper DSCP bits when performing source validation for multicast packets during early demux. In the future, this will allow us to perform the FIB lookup which is performed as part of source validation according to the full DSCP value. No functional changes intended since the upper DSCP bits are masked when comparing against the TOS selectors in FIB rules and routes. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Acked-by: Florian Westphal Reviewed-by: David Ahern Link: https://patch.msgid.link/20240821125251.1571445-12-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/udp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ddb86baaea6c8..8accbf4cb2956 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -115,6 +115,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_IPV6) #include #endif @@ -2618,7 +2619,7 @@ int udp_v4_early_demux(struct sk_buff *skb) if (!inet_sk(sk)->inet_daddr && in_dev) return ip_mc_validate_source(skb, iph->daddr, iph->saddr, - iph->tos & IPTOS_RT_MASK, + iph->tos & INET_DSCP_MASK, skb->dev, in_dev, &itag); } return 0; From be8b8ded77996cfcd1bb2f1d97b91106d5882877 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 21 Aug 2024 15:52:51 +0300 Subject: [PATCH 318/385] ipv4: Unmask upper DSCP bits when using hints Unmask the upper DSCP bits when performing source validation and routing a packet using the same route from a previously processed packet (hint). In the future, this will allow us to perform the FIB lookup that is performed as part of source validation according to the full DSCP value. No functional changes intended since the upper DSCP bits are masked when comparing against the TOS selectors in FIB rules and routes. Signed-off-by: Ido Schimmel Reviewed-by: Guillaume Nault Acked-by: Florian Westphal Reviewed-by: David Ahern Link: https://patch.msgid.link/20240821125251.1571445-13-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 524b70ab77a0e..f6972b24664a0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2160,7 +2160,7 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (rt->rt_type != RTN_LOCAL) goto skip_validate_source; - tos &= IPTOS_RT_MASK; + tos &= INET_DSCP_MASK; err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &tag); if (err < 0) goto martian_source; From 3849687869092094003ba009dc00e2e0237a3b8a Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:09:55 +0200 Subject: [PATCH 319/385] net: phy: Introduce ethernet link topology representation Link topologies containing multiple network PHYs attached to the same net_device can be found when using a PHY as a media converter for use with an SFP connector, on which an SFP transceiver containing a PHY can be used. With the current model, the transceiver's PHY can't be used for operations such as cable testing, timestamping, macsec offload, etc. The reason being that most of the logic for these configuration, coming from either ethtool netlink or ioctls tend to use netdev->phydev, which in multi-phy systems will reference the PHY closest to the MAC. Introduce a numbering scheme allowing to enumerate PHY devices that belong to any netdev, which can in turn allow userspace to take more precise decisions with regard to each PHY's configuration. The numbering is maintained per-netdev, in a phy_device_list. The numbering works similarly to a netdevice's ifindex, with identifiers that are only recycled once INT_MAX has been reached. This prevents races that could occur between PHY listing and SFP transceiver removal/insertion. The identifiers are assigned at phy_attach time, as the numbering depends on the netdevice the phy is attached to. The PHY index can be re-used for PHYs that are persistent. Signed-off-by: Maxime Chevallier Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- MAINTAINERS | 1 + drivers/net/phy/Makefile | 2 +- drivers/net/phy/phy_device.c | 6 ++ drivers/net/phy/phy_link_topology.c | 105 ++++++++++++++++++++++++++++ include/linux/netdevice.h | 4 +- include/linux/phy.h | 4 ++ include/linux/phy_link_topology.h | 82 ++++++++++++++++++++++ include/uapi/linux/ethtool.h | 16 +++++ net/core/dev.c | 15 ++++ 9 files changed, 233 insertions(+), 2 deletions(-) create mode 100644 drivers/net/phy/phy_link_topology.c create mode 100644 include/linux/phy_link_topology.h diff --git a/MAINTAINERS b/MAINTAINERS index 5f45b75eba963..e4fa9010fcb60 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8341,6 +8341,7 @@ F: include/linux/mii.h F: include/linux/of_net.h F: include/linux/phy.h F: include/linux/phy_fixed.h +F: include/linux/phy_link_topology.h F: include/linux/phylib_stubs.h F: include/linux/platform_data/mdio-bcm-unimac.h F: include/linux/platform_data/mdio-gpio.h diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index f086a606a87e9..33adb3df5f64f 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -2,7 +2,7 @@ # Makefile for Linux PHY drivers libphy-y := phy.o phy-c45.o phy-core.o phy_device.o \ - linkmode.o + linkmode.o phy_link_topology.o mdio-bus-y += mdio_bus.o mdio_device.o ifdef CONFIG_MDIO_DEVICE diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 159e71c1c9726..d896c799f7c23 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -1526,6 +1527,10 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, if (phydev->sfp_bus_attached) dev->sfp_bus = phydev->sfp_bus; + + err = phy_link_topo_add_phy(dev, phydev, PHY_UPSTREAM_MAC, dev); + if (err) + goto error; } /* Some Ethernet drivers try to connect to a PHY device before @@ -1953,6 +1958,7 @@ void phy_detach(struct phy_device *phydev) if (dev) { phydev->attached_dev->phydev = NULL; phydev->attached_dev = NULL; + phy_link_topo_del_phy(dev, phydev); } phydev->phylink = NULL; diff --git a/drivers/net/phy/phy_link_topology.c b/drivers/net/phy/phy_link_topology.c new file mode 100644 index 0000000000000..4a5d73002a1a8 --- /dev/null +++ b/drivers/net/phy/phy_link_topology.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Infrastructure to handle all PHY devices connected to a given netdev, + * either directly or indirectly attached. + * + * Copyright (c) 2023 Maxime Chevallier + */ + +#include +#include +#include +#include + +static int netdev_alloc_phy_link_topology(struct net_device *dev) +{ + struct phy_link_topology *topo; + + topo = kzalloc(sizeof(*topo), GFP_KERNEL); + if (!topo) + return -ENOMEM; + + xa_init_flags(&topo->phys, XA_FLAGS_ALLOC1); + topo->next_phy_index = 1; + + dev->link_topo = topo; + + return 0; +} + +int phy_link_topo_add_phy(struct net_device *dev, + struct phy_device *phy, + enum phy_upstream upt, void *upstream) +{ + struct phy_link_topology *topo = dev->link_topo; + struct phy_device_node *pdn; + int ret; + + if (!topo) { + ret = netdev_alloc_phy_link_topology(dev); + if (ret) + return ret; + + topo = dev->link_topo; + } + + pdn = kzalloc(sizeof(*pdn), GFP_KERNEL); + if (!pdn) + return -ENOMEM; + + pdn->phy = phy; + switch (upt) { + case PHY_UPSTREAM_MAC: + pdn->upstream.netdev = (struct net_device *)upstream; + if (phy_on_sfp(phy)) + pdn->parent_sfp_bus = pdn->upstream.netdev->sfp_bus; + break; + case PHY_UPSTREAM_PHY: + pdn->upstream.phydev = (struct phy_device *)upstream; + if (phy_on_sfp(phy)) + pdn->parent_sfp_bus = pdn->upstream.phydev->sfp_bus; + break; + default: + ret = -EINVAL; + goto err; + } + pdn->upstream_type = upt; + + /* Attempt to re-use a previously allocated phy_index */ + if (phy->phyindex) + ret = xa_insert(&topo->phys, phy->phyindex, pdn, GFP_KERNEL); + else + ret = xa_alloc_cyclic(&topo->phys, &phy->phyindex, pdn, + xa_limit_32b, &topo->next_phy_index, + GFP_KERNEL); + + if (ret) + goto err; + + return 0; + +err: + kfree(pdn); + return ret; +} +EXPORT_SYMBOL_GPL(phy_link_topo_add_phy); + +void phy_link_topo_del_phy(struct net_device *dev, + struct phy_device *phy) +{ + struct phy_link_topology *topo = dev->link_topo; + struct phy_device_node *pdn; + + if (!topo) + return; + + pdn = xa_erase(&topo->phys, phy->phyindex); + + /* We delete the PHY from the topology, however we don't re-set the + * phy->phyindex field. If the PHY isn't gone, we can re-assign it the + * same index next time it's added back to the topology + */ + + kfree(pdn); +} +EXPORT_SYMBOL_GPL(phy_link_topo_del_phy); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 614ec5d3d75b3..289a6133769c2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -40,7 +40,6 @@ #include #endif #include - #include #include #include @@ -81,6 +80,7 @@ struct xdp_frame; struct xdp_metadata_ops; struct xdp_md; struct ethtool_netdev_state; +struct phy_link_topology; typedef u32 xdp_features_t; @@ -1951,6 +1951,7 @@ enum netdev_reg_state { * @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp * * @priomap: XXX: need comments on this one + * @link_topo: Physical link topology tracking attached PHYs * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. @@ -2342,6 +2343,7 @@ struct net_device { #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif + struct phy_link_topology *link_topo; struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; diff --git a/include/linux/phy.h b/include/linux/phy.h index 6b7d40d49129d..3b0f4bf806505 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -554,6 +554,9 @@ struct macsec_ops; * @drv: Pointer to the driver for this PHY instance * @devlink: Create a link between phy dev and mac dev, if the external phy * used by current mac interface is managed by another mac interface. + * @phyindex: Unique id across the phy's parent tree of phys to address the PHY + * from userspace, similar to ifindex. A zero index means the PHY + * wasn't assigned an id yet. * @phy_id: UID for this device found during discovery * @c45_ids: 802.3-c45 Device Identifiers if is_c45. * @is_c45: Set to true if this PHY uses clause 45 addressing. @@ -656,6 +659,7 @@ struct phy_device { struct device_link *devlink; + u32 phyindex; u32 phy_id; struct phy_c45_device_ids c45_ids; diff --git a/include/linux/phy_link_topology.h b/include/linux/phy_link_topology.h new file mode 100644 index 0000000000000..68a59e25821c3 --- /dev/null +++ b/include/linux/phy_link_topology.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PHY device list allow maintaining a list of PHY devices that are + * part of a netdevice's link topology. PHYs can for example be chained, + * as is the case when using a PHY that exposes an SFP module, on which an + * SFP transceiver that embeds a PHY is connected. + * + * This list can then be used by userspace to leverage individual PHY + * capabilities. + */ +#ifndef __PHY_LINK_TOPOLOGY_H +#define __PHY_LINK_TOPOLOGY_H + +#include +#include + +struct xarray; +struct phy_device; +struct sfp_bus; + +struct phy_link_topology { + struct xarray phys; + u32 next_phy_index; +}; + +struct phy_device_node { + enum phy_upstream upstream_type; + + union { + struct net_device *netdev; + struct phy_device *phydev; + } upstream; + + struct sfp_bus *parent_sfp_bus; + + struct phy_device *phy; +}; + +#if IS_ENABLED(CONFIG_PHYLIB) +int phy_link_topo_add_phy(struct net_device *dev, + struct phy_device *phy, + enum phy_upstream upt, void *upstream); + +void phy_link_topo_del_phy(struct net_device *dev, struct phy_device *phy); + +static inline struct phy_device * +phy_link_topo_get_phy(struct net_device *dev, u32 phyindex) +{ + struct phy_link_topology *topo = dev->link_topo; + struct phy_device_node *pdn; + + if (!topo) + return NULL; + + pdn = xa_load(&topo->phys, phyindex); + if (pdn) + return pdn->phy; + + return NULL; +} + +#else +static inline int phy_link_topo_add_phy(struct net_device *dev, + struct phy_device *phy, + enum phy_upstream upt, void *upstream) +{ + return 0; +} + +static inline void phy_link_topo_del_phy(struct net_device *dev, + struct phy_device *phy) +{ +} + +static inline struct phy_device * +phy_link_topo_get_phy(struct net_device *dev, u32 phyindex) +{ + return NULL; +} +#endif + +#endif /* __PHY_LINK_TOPOLOGY_H */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 4a0a6e7034839..c405ed63acfa2 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2533,4 +2533,20 @@ struct ethtool_link_settings { * __u32 map_lp_advertising[link_mode_masks_nwords]; */ }; + +/** + * enum phy_upstream - Represents the upstream component a given PHY device + * is connected to, as in what is on the other end of the MII bus. Most PHYs + * will be attached to an Ethernet MAC controller, but in some cases, there's + * an intermediate PHY used as a media-converter, which will driver another + * MII interface as its output. + * @PHY_UPSTREAM_MAC: Upstream component is a MAC (a switch port, + * or ethernet controller) + * @PHY_UPSTREAM_PHY: Upstream component is a PHY (likely a media converter) + */ +enum phy_upstream { + PHY_UPSTREAM_MAC, + PHY_UPSTREAM_PHY, +}; + #endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/net/core/dev.c b/net/core/dev.c index e7260889d4cb0..d0e7483abdcdc 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -158,6 +158,7 @@ #include #include #include +#include #include "dev.h" #include "net-sysfs.h" @@ -10321,6 +10322,17 @@ static void netdev_do_free_pcpu_stats(struct net_device *dev) } } +static void netdev_free_phy_link_topology(struct net_device *dev) +{ + struct phy_link_topology *topo = dev->link_topo; + + if (IS_ENABLED(CONFIG_PHYLIB) && topo) { + xa_destroy(&topo->phys); + kfree(topo); + dev->link_topo = NULL; + } +} + /** * register_netdevice() - register a network device * @dev: device to register @@ -11099,6 +11111,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif + dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); @@ -11191,6 +11204,8 @@ void free_netdev(struct net_device *dev) free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; + netdev_free_phy_link_topology(dev); + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED || dev->reg_state == NETREG_DUMMY) { From 4d76f115ab9121f4458330da962ae9ef5430e60b Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:09:56 +0200 Subject: [PATCH 320/385] net: sfp: pass the phy_device when disconnecting an sfp module's PHY Pass the phy_device as a parameter to the sfp upstream .disconnect_phy operation. This is preparatory work to help track phy devices across a net_device's link. Signed-off-by: Maxime Chevallier Reviewed-by: Andrew Lunn Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 3 ++- drivers/net/phy/sfp-bus.c | 4 ++-- include/linux/sfp.h | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 51c526d227fab..ab4e9fc03017d 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -3423,7 +3423,8 @@ static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy) return ret; } -static void phylink_sfp_disconnect_phy(void *upstream) +static void phylink_sfp_disconnect_phy(void *upstream, + struct phy_device *phydev) { phylink_disconnect_phy(upstream); } diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 2f44fc51848f4..56953e66bb7b2 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -487,7 +487,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus) bus->socket_ops->stop(bus->sfp); bus->socket_ops->detach(bus->sfp); if (bus->phydev && ops && ops->disconnect_phy) - ops->disconnect_phy(bus->upstream); + ops->disconnect_phy(bus->upstream, bus->phydev); } bus->registered = false; } @@ -743,7 +743,7 @@ void sfp_remove_phy(struct sfp_bus *bus) const struct sfp_upstream_ops *ops = sfp_get_upstream_ops(bus); if (ops && ops->disconnect_phy) - ops->disconnect_phy(bus->upstream); + ops->disconnect_phy(bus->upstream, bus->phydev); bus->phydev = NULL; } EXPORT_SYMBOL_GPL(sfp_remove_phy); diff --git a/include/linux/sfp.h b/include/linux/sfp.h index b14be59550e37..54abb4d22b2ec 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -550,7 +550,7 @@ struct sfp_upstream_ops { void (*link_down)(void *priv); void (*link_up)(void *priv); int (*connect_phy)(void *priv, struct phy_device *); - void (*disconnect_phy)(void *priv); + void (*disconnect_phy)(void *priv, struct phy_device *); }; #if IS_ENABLED(CONFIG_SFP) From b2db6f4ace72e71fa09b8d1354f8ac9854140d74 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:09:57 +0200 Subject: [PATCH 321/385] net: phy: add helpers to handle sfp phy connect/disconnect There are a few PHY drivers that can handle SFP modules through their sfp_upstream_ops. Introduce Phylib helpers to keep track of connected SFP PHYs in a netdevice's namespace, by adding the SFP PHY to the upstream PHY's netdev's namespace. By doing so, these SFP PHYs can be enumerated and exposed to users, which will be able to use their capabilities. Signed-off-by: Maxime Chevallier Reviewed-by: Andrew Lunn Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- drivers/net/phy/marvell-88x2222.c | 2 ++ drivers/net/phy/marvell.c | 2 ++ drivers/net/phy/marvell10g.c | 2 ++ drivers/net/phy/phy_device.c | 42 +++++++++++++++++++++++++++++++ drivers/net/phy/qcom/at803x.c | 2 ++ drivers/net/phy/qcom/qca807x.c | 2 ++ include/linux/phy.h | 2 ++ 7 files changed, 54 insertions(+) diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c index b88398e6872bc..0b777cdd7078b 100644 --- a/drivers/net/phy/marvell-88x2222.c +++ b/drivers/net/phy/marvell-88x2222.c @@ -553,6 +553,8 @@ static const struct sfp_upstream_ops sfp_phy_ops = { .link_down = mv2222_sfp_link_down, .attach = phy_sfp_attach, .detach = phy_sfp_detach, + .connect_phy = phy_sfp_connect_phy, + .disconnect_phy = phy_sfp_disconnect_phy, }; static int mv2222_probe(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index b89fbffa6a931..9964bf3dea2fb 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -3613,6 +3613,8 @@ static const struct sfp_upstream_ops m88e1510_sfp_ops = { .module_remove = m88e1510_sfp_remove, .attach = phy_sfp_attach, .detach = phy_sfp_detach, + .connect_phy = phy_sfp_connect_phy, + .disconnect_phy = phy_sfp_disconnect_phy, }; static int m88e1510_probe(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index ad43e280930c3..6642eb642d4bd 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -503,6 +503,8 @@ static int mv3310_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) static const struct sfp_upstream_ops mv3310_sfp_ops = { .attach = phy_sfp_attach, .detach = phy_sfp_detach, + .connect_phy = phy_sfp_connect_phy, + .disconnect_phy = phy_sfp_disconnect_phy, .module_insert = mv3310_sfp_insert, }; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index d896c799f7c23..8f5314c1fecc5 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1385,6 +1385,48 @@ phy_standalone_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(phy_standalone); +/** + * phy_sfp_connect_phy - Connect the SFP module's PHY to the upstream PHY + * @upstream: pointer to the upstream phy device + * @phy: pointer to the SFP module's phy device + * + * This helper allows keeping track of PHY devices on the link. It adds the + * SFP module's phy to the phy namespace of the upstream phy + * + * Return: 0 on success, otherwise a negative error code. + */ +int phy_sfp_connect_phy(void *upstream, struct phy_device *phy) +{ + struct phy_device *phydev = upstream; + struct net_device *dev = phydev->attached_dev; + + if (dev) + return phy_link_topo_add_phy(dev, phy, PHY_UPSTREAM_PHY, phydev); + + return 0; +} +EXPORT_SYMBOL(phy_sfp_connect_phy); + +/** + * phy_sfp_disconnect_phy - Disconnect the SFP module's PHY from the upstream PHY + * @upstream: pointer to the upstream phy device + * @phy: pointer to the SFP module's phy device + * + * This helper allows keeping track of PHY devices on the link. It removes the + * SFP module's phy to the phy namespace of the upstream phy. As the module phy + * will be destroyed, re-inserting the same module will add a new phy with a + * new index. + */ +void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy) +{ + struct phy_device *phydev = upstream; + struct net_device *dev = phydev->attached_dev; + + if (dev) + phy_link_topo_del_phy(dev, phy); +} +EXPORT_SYMBOL(phy_sfp_disconnect_phy); + /** * phy_sfp_attach - attach the SFP bus to the PHY upstream network device * @upstream: pointer to the phy device diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c index c8f83e5f78ab9..105602581a033 100644 --- a/drivers/net/phy/qcom/at803x.c +++ b/drivers/net/phy/qcom/at803x.c @@ -770,6 +770,8 @@ static const struct sfp_upstream_ops at8031_sfp_ops = { .attach = phy_sfp_attach, .detach = phy_sfp_detach, .module_insert = at8031_sfp_insert, + .connect_phy = phy_sfp_connect_phy, + .disconnect_phy = phy_sfp_disconnect_phy, }; static int at8031_parse_dt(struct phy_device *phydev) diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index ba558486c72f4..bd8a51ec0ecd6 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -699,6 +699,8 @@ static const struct sfp_upstream_ops qca807x_sfp_ops = { .detach = phy_sfp_detach, .module_insert = qca807x_sfp_insert, .module_remove = qca807x_sfp_remove, + .connect_phy = phy_sfp_connect_phy, + .disconnect_phy = phy_sfp_disconnect_phy, }; static int qca807x_probe(struct phy_device *phydev) diff --git a/include/linux/phy.h b/include/linux/phy.h index 3b0f4bf806505..a98bc91a0cde9 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1781,6 +1781,8 @@ int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable); +int phy_sfp_connect_phy(void *upstream, struct phy_device *phy); +void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy); void phy_sfp_attach(void *upstream, struct sfp_bus *bus); void phy_sfp_detach(void *upstream, struct sfp_bus *bus); int phy_sfp_probe(struct phy_device *phydev, From 0a2f7de0f3b96c4a30e56d2c79f8d812f89599a1 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:09:58 +0200 Subject: [PATCH 322/385] net: sfp: Add helper to return the SFP bus name Knowing the bus name is helpful when we want to expose the link topology to userspace, add a helper to return the SFP bus name. This call will always be made while holding the RTNL which ensures that the SFP driver won't unbind from the device. The returned pointer to the bus name will only be used while RTNL is held. Signed-off-by: Maxime Chevallier Suggested-by: "Russell King (Oracle)" Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- drivers/net/phy/sfp-bus.c | 22 ++++++++++++++++++++++ include/linux/sfp.h | 6 ++++++ 2 files changed, 28 insertions(+) diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 56953e66bb7b2..f13c00b5b449c 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -722,6 +722,28 @@ void sfp_bus_del_upstream(struct sfp_bus *bus) } EXPORT_SYMBOL_GPL(sfp_bus_del_upstream); +/** + * sfp_get_name() - Get the SFP device name + * @bus: a pointer to the &struct sfp_bus structure for the sfp module + * + * Gets the SFP device's name, if @bus has a registered socket. Callers must + * hold RTNL, and the returned name is only valid until RTNL is released. + * + * Returns: + * - The name of the SFP device registered with sfp_register_socket() + * - %NULL if no device was registered on @bus + */ +const char *sfp_get_name(struct sfp_bus *bus) +{ + ASSERT_RTNL(); + + if (bus->sfp_dev) + return dev_name(bus->sfp_dev); + + return NULL; +} +EXPORT_SYMBOL_GPL(sfp_get_name); + /* Socket driver entry points */ int sfp_add_phy(struct sfp_bus *bus, struct phy_device *phydev) { diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 54abb4d22b2ec..60c65cea74f62 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -576,6 +576,7 @@ struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode); int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, const struct sfp_upstream_ops *ops); void sfp_bus_del_upstream(struct sfp_bus *bus); +const char *sfp_get_name(struct sfp_bus *bus); #else static inline int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, @@ -654,6 +655,11 @@ static inline int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, static inline void sfp_bus_del_upstream(struct sfp_bus *bus) { } + +static inline const char *sfp_get_name(struct sfp_bus *bus) +{ + return NULL; +} #endif #endif From c15e065b46dc4e19837275b826c1960d55564abd Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:09:59 +0200 Subject: [PATCH 323/385] net: ethtool: Allow passing a phy index for some commands Some netlink commands are target towards ethernet PHYs, to control some of their features. As there's several such commands, add the ability to pass a PHY index in the ethnl request, which will populate the generic ethnl_req_info with the passed phy_index. Add a helper that netlink command handlers need to use to grab the targeted PHY from the req_info. This helper needs to hold rtnl_lock() while interacting with the PHY, as it may be removed at any point. Signed-off-by: Maxime Chevallier Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 7 +++ include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/netlink.c | 57 +++++++++++++++++++- net/ethtool/netlink.h | 28 ++++++++++ 4 files changed, 91 insertions(+), 2 deletions(-) diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 3f6c6880e7c48..2d14b85513487 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -57,6 +57,7 @@ Structure of this header is ``ETHTOOL_A_HEADER_DEV_INDEX`` u32 device ifindex ``ETHTOOL_A_HEADER_DEV_NAME`` string device name ``ETHTOOL_A_HEADER_FLAGS`` u32 flags common for all requests + ``ETHTOOL_A_HEADER_PHY_INDEX`` u32 phy device index ============================== ====== ============================= ``ETHTOOL_A_HEADER_DEV_INDEX`` and ``ETHTOOL_A_HEADER_DEV_NAME`` identify the @@ -81,6 +82,12 @@ the behaviour is backward compatible, i.e. requests from old clients not aware of the flag should be interpreted the way the client expects. A client must not set flags it does not understand. +``ETHTOOL_A_HEADER_PHY_INDEX`` identifies the Ethernet PHY the message relates to. +As there are numerous commands that are related to PHY configuration, and because +there may be more than one PHY on the link, the PHY index can be passed in the +request for the commands that needs it. It is, however, not mandatory, and if it +is not passed for commands that target a PHY, the net_device.phydev pointer +is used. Bit sets ======== diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 9074fa309bd6d..49d1f9220fde6 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -134,6 +134,7 @@ enum { ETHTOOL_A_HEADER_DEV_INDEX, /* u32 */ ETHTOOL_A_HEADER_DEV_NAME, /* string */ ETHTOOL_A_HEADER_FLAGS, /* u32 - ETHTOOL_FLAG_* */ + ETHTOOL_A_HEADER_PHY_INDEX, /* u32 */ /* add new constants above here */ __ETHTOOL_A_HEADER_CNT, diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 041548e5f5e64..b00061924e80c 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -2,6 +2,7 @@ #include #include +#include #include #include "netlink.h" #include "module_fw.h" @@ -31,6 +32,24 @@ const struct nla_policy ethnl_header_policy_stats[] = { ETHTOOL_FLAGS_STATS), }; +const struct nla_policy ethnl_header_policy_phy[] = { + [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, + [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, + .len = ALTIFNAMSIZ - 1 }, + [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, + ETHTOOL_FLAGS_BASIC), + [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + +const struct nla_policy ethnl_header_policy_phy_stats[] = { + [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, + [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, + .len = ALTIFNAMSIZ - 1 }, + [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, + ETHTOOL_FLAGS_STATS), + [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + int ethnl_sock_priv_set(struct sk_buff *skb, struct net_device *dev, u32 portid, enum ethnl_sock_type type) { @@ -119,7 +138,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, const struct nlattr *header, struct net *net, struct netlink_ext_ack *extack, bool require_dev) { - struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy)]; + struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy_phy)]; const struct nlattr *devname_attr; struct net_device *dev = NULL; u32 flags = 0; @@ -134,7 +153,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, /* No validation here, command policy should have a nested policy set * for the header, therefore validation should have already been done. */ - ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy) - 1, header, + ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy_phy) - 1, header, NULL, extack); if (ret < 0) return ret; @@ -175,11 +194,45 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, return -EINVAL; } + if (tb[ETHTOOL_A_HEADER_PHY_INDEX]) { + if (dev) { + req_info->phy_index = nla_get_u32(tb[ETHTOOL_A_HEADER_PHY_INDEX]); + } else { + NL_SET_ERR_MSG_ATTR(extack, header, + "phy_index set without a netdev"); + return -EINVAL; + } + } + req_info->dev = dev; req_info->flags = flags; return 0; } +struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info, + const struct nlattr *header, + struct netlink_ext_ack *extack) +{ + struct phy_device *phydev; + + ASSERT_RTNL(); + + if (!req_info->dev) + return NULL; + + if (!req_info->phy_index) + return req_info->dev->phydev; + + phydev = phy_link_topo_get_phy(req_info->dev, req_info->phy_index); + if (!phydev) { + NL_SET_ERR_MSG_ATTR(extack, header, + "no phy matching phyindex"); + return ERR_PTR(-ENODEV); + } + + return phydev; +} + /** * ethnl_fill_reply_header() - Put common header into a reply message * @skb: skb with the message diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 236c189fc9688..e326699405be8 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -251,6 +251,9 @@ static inline unsigned int ethnl_reply_header_size(void) * @dev: network device the request is for (may be null) * @dev_tracker: refcount tracker for @dev reference * @flags: request flags common for all request types + * @phy_index: phy_device index connected to @dev this request is for. Can be + * 0 if the request doesn't target a phy, or if the @dev's attached + * phy is targeted. * * This is a common base for request specific structures holding data from * parsed userspace request. These always embed struct ethnl_req_info at @@ -260,6 +263,7 @@ struct ethnl_req_info { struct net_device *dev; netdevice_tracker dev_tracker; u32 flags; + u32 phy_index; }; static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info) @@ -267,6 +271,27 @@ static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info) netdev_put(req_info->dev, &req_info->dev_tracker); } +/** + * ethnl_req_get_phydev() - Gets the phy_device targeted by this request, + * if any. Must be called under rntl_lock(). + * @req_info: The ethnl request to get the phy from. + * @header: The netlink header, used for error reporting. + * @extack: The netlink extended ACK, for error reporting. + * + * The caller must hold RTNL, until it's done interacting with the returned + * phy_device. + * + * Return: A phy_device pointer corresponding either to the passed phy_index + * if one is provided. If not, the phy_device attached to the + * net_device targeted by this request is returned. If there's no + * targeted net_device, or no phy_device is attached, NULL is + * returned. If the provided phy_index is invalid, an error pointer + * is returned. + */ +struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info, + const struct nlattr *header, + struct netlink_ext_ack *extack); + /** * struct ethnl_reply_data - base type of reply data for GET requests * @dev: device for current reply message; in single shot requests it is @@ -409,9 +434,12 @@ extern const struct ethnl_request_ops ethnl_rss_request_ops; extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops; extern const struct ethnl_request_ops ethnl_plca_status_request_ops; extern const struct ethnl_request_ops ethnl_mm_request_ops; +extern const struct ethnl_request_ops ethnl_phy_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; +extern const struct nla_policy ethnl_header_policy_phy[ETHTOOL_A_HEADER_PHY_INDEX + 1]; +extern const struct nla_policy ethnl_header_policy_phy_stats[ETHTOOL_A_HEADER_PHY_INDEX + 1]; extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_ONLY + 1]; extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1]; extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1]; From 9af0e89d6c2433afd3e5e7cc52c7592ef23526c0 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:10:00 +0200 Subject: [PATCH 324/385] netlink: specs: add phy-index as a header parameter Update the spec to take the newly introduced phy-index as a generic request parameter. Signed-off-by: Maxime Chevallier Reviewed-by: Andrew Lunn Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- Documentation/netlink/specs/ethtool.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 1bbeaba5c6442..7d6c3ace3fa2b 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -54,6 +54,9 @@ attribute-sets: name: flags type: u32 enum: header-flags + - + name: phy-index + type: u32 - name: bitset-bit From 17194be4c8e1e82d8b484e58cdcb495c0714d1fd Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:10:01 +0200 Subject: [PATCH 325/385] net: ethtool: Introduce a command to list PHYs on an interface As we have the ability to track the PHYs connected to a net_device through the link_topology, we can expose this list to userspace. This allows userspace to use these identifiers for phy-specific commands and take the decision of which PHY to target by knowing the link topology. Add PHY_GET and PHY_DUMP, which can be a filtered DUMP operation to list devices on only one interface. Signed-off-by: Maxime Chevallier Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 41 +++ include/uapi/linux/ethtool_netlink.h | 19 ++ net/ethtool/Makefile | 3 +- net/ethtool/netlink.c | 9 + net/ethtool/netlink.h | 5 + net/ethtool/phy.c | 308 +++++++++++++++++++ 6 files changed, 384 insertions(+), 1 deletion(-) create mode 100644 net/ethtool/phy.c diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 2d14b85513487..8c152871c23c4 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -2191,6 +2191,46 @@ string. The ``ETHTOOL_A_MODULE_FW_FLASH_DONE`` and ``ETHTOOL_A_MODULE_FW_FLASH_TOTAL`` attributes encode the completed and total amount of work, respectively. +PHY_GET +======= + +Retrieve information about a given Ethernet PHY sitting on the link. The DO +operation returns all available information about dev->phydev. User can also +specify a PHY_INDEX, in which case the DO request returns information about that +specific PHY. +As there can be more than one PHY, the DUMP operation can be used to list the PHYs +present on a given interface, by passing an interface index or name in +the dump request. + +Request contents: + + ==================================== ====== ========================== + ``ETHTOOL_A_PHY_HEADER`` nested request header + ==================================== ====== ========================== + +Kernel response contents: + + ===================================== ====== =============================== + ``ETHTOOL_A_PHY_HEADER`` nested request header + ``ETHTOOL_A_PHY_INDEX`` u32 the phy's unique index, that can + be used for phy-specific + requests + ``ETHTOOL_A_PHY_DRVNAME`` string the phy driver name + ``ETHTOOL_A_PHY_NAME`` string the phy device name + ``ETHTOOL_A_PHY_UPSTREAM_TYPE`` u32 the type of device this phy is + connected to + ``ETHTOOL_A_PHY_UPSTREAM_INDEX`` u32 the PHY index of the upstream + PHY + ``ETHTOOL_A_PHY_UPSTREAM_SFP_NAME`` string if this PHY is connected to + its parent PHY through an SFP + bus, the name of this sfp bus + ``ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME`` string if the phy controls an sfp bus, + the name of the sfp bus + ===================================== ====== =============================== + +When ``ETHTOOL_A_PHY_UPSTREAM_TYPE`` is PHY_UPSTREAM_PHY, the PHY's parent is +another PHY. + Request translation =================== @@ -2298,4 +2338,5 @@ are netlink only. n/a ``ETHTOOL_MSG_MM_GET`` n/a ``ETHTOOL_MSG_MM_SET`` n/a ``ETHTOOL_MSG_MODULE_FW_FLASH_ACT`` + n/a ``ETHTOOL_MSG_PHY_GET`` =================================== ===================================== diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 49d1f9220fde6..45d8bcdea056e 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -58,6 +58,7 @@ enum { ETHTOOL_MSG_MM_GET, ETHTOOL_MSG_MM_SET, ETHTOOL_MSG_MODULE_FW_FLASH_ACT, + ETHTOOL_MSG_PHY_GET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -111,6 +112,8 @@ enum { ETHTOOL_MSG_MM_GET_REPLY, ETHTOOL_MSG_MM_NTF, ETHTOOL_MSG_MODULE_FW_FLASH_NTF, + ETHTOOL_MSG_PHY_GET_REPLY, + ETHTOOL_MSG_PHY_NTF, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -1055,6 +1058,22 @@ enum { ETHTOOL_A_MODULE_FW_FLASH_MAX = (__ETHTOOL_A_MODULE_FW_FLASH_CNT - 1) }; +enum { + ETHTOOL_A_PHY_UNSPEC, + ETHTOOL_A_PHY_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_PHY_INDEX, /* u32 */ + ETHTOOL_A_PHY_DRVNAME, /* string */ + ETHTOOL_A_PHY_NAME, /* string */ + ETHTOOL_A_PHY_UPSTREAM_TYPE, /* u32 */ + ETHTOOL_A_PHY_UPSTREAM_INDEX, /* u32 */ + ETHTOOL_A_PHY_UPSTREAM_SFP_NAME, /* string */ + ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME, /* string */ + + /* add new constants above here */ + __ETHTOOL_A_PHY_CNT, + ETHTOOL_A_PHY_MAX = (__ETHTOOL_A_PHY_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 9a190635fe953..9b540644ba31f 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -8,4 +8,5 @@ ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \ - module.o cmis_fw_update.o cmis_cdb.o pse-pd.o plca.o mm.o + module.o cmis_fw_update.o cmis_cdb.o pse-pd.o plca.o mm.o \ + phy.o diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index b00061924e80c..e3f0ef6b851bb 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -1234,6 +1234,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_module_fw_flash_act_policy, .maxattr = ARRAY_SIZE(ethnl_module_fw_flash_act_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_PHY_GET, + .doit = ethnl_phy_doit, + .start = ethnl_phy_start, + .dumpit = ethnl_phy_dumpit, + .done = ethnl_phy_done, + .policy = ethnl_phy_get_policy, + .maxattr = ARRAY_SIZE(ethnl_phy_get_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index e326699405be8..203b08eb6c6f6 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -484,6 +484,7 @@ extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADE extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1]; extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1]; extern const struct nla_policy ethnl_module_fw_flash_act_policy[ETHTOOL_A_MODULE_FW_FLASH_PASSWORD + 1]; +extern const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1]; int ethnl_set_features(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info); @@ -494,6 +495,10 @@ int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int ethnl_act_module_fw_flash(struct sk_buff *skb, struct genl_info *info); int ethnl_rss_dump_start(struct netlink_callback *cb); int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int ethnl_phy_start(struct netlink_callback *cb); +int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info); +int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int ethnl_phy_done(struct netlink_callback *cb); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c new file mode 100644 index 0000000000000..560dd039c6625 --- /dev/null +++ b/net/ethtool/phy.c @@ -0,0 +1,308 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2023 Bootlin + * + */ +#include "common.h" +#include "netlink.h" + +#include +#include +#include + +struct phy_req_info { + struct ethnl_req_info base; + struct phy_device_node *pdn; +}; + +#define PHY_REQINFO(__req_base) \ + container_of(__req_base, struct phy_req_info, base) + +const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1] = { + [ETHTOOL_A_PHY_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), +}; + +/* Caller holds rtnl */ +static ssize_t +ethnl_phy_reply_size(const struct ethnl_req_info *req_base, + struct netlink_ext_ack *extack) +{ + struct phy_req_info *req_info = PHY_REQINFO(req_base); + struct phy_device_node *pdn = req_info->pdn; + struct phy_device *phydev = pdn->phy; + size_t size = 0; + + ASSERT_RTNL(); + + /* ETHTOOL_A_PHY_INDEX */ + size += nla_total_size(sizeof(u32)); + + /* ETHTOOL_A_DRVNAME */ + if (phydev->drv) + size += nla_total_size(strlen(phydev->drv->name) + 1); + + /* ETHTOOL_A_NAME */ + size += nla_total_size(strlen(dev_name(&phydev->mdio.dev)) + 1); + + /* ETHTOOL_A_PHY_UPSTREAM_TYPE */ + size += nla_total_size(sizeof(u32)); + + if (phy_on_sfp(phydev)) { + const char *upstream_sfp_name = sfp_get_name(pdn->parent_sfp_bus); + + /* ETHTOOL_A_PHY_UPSTREAM_SFP_NAME */ + if (upstream_sfp_name) + size += nla_total_size(strlen(upstream_sfp_name) + 1); + + /* ETHTOOL_A_PHY_UPSTREAM_INDEX */ + size += nla_total_size(sizeof(u32)); + } + + /* ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME */ + if (phydev->sfp_bus) { + const char *sfp_name = sfp_get_name(phydev->sfp_bus); + + if (sfp_name) + size += nla_total_size(strlen(sfp_name) + 1); + } + + return size; +} + +static int +ethnl_phy_fill_reply(const struct ethnl_req_info *req_base, struct sk_buff *skb) +{ + struct phy_req_info *req_info = PHY_REQINFO(req_base); + struct phy_device_node *pdn = req_info->pdn; + struct phy_device *phydev = pdn->phy; + enum phy_upstream ptype; + + ptype = pdn->upstream_type; + + if (nla_put_u32(skb, ETHTOOL_A_PHY_INDEX, phydev->phyindex) || + nla_put_string(skb, ETHTOOL_A_PHY_NAME, dev_name(&phydev->mdio.dev)) || + nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_TYPE, ptype)) + return -EMSGSIZE; + + if (phydev->drv && + nla_put_string(skb, ETHTOOL_A_PHY_DRVNAME, phydev->drv->name)) + return -EMSGSIZE; + + if (ptype == PHY_UPSTREAM_PHY) { + struct phy_device *upstream = pdn->upstream.phydev; + const char *sfp_upstream_name; + + /* Parent index */ + if (nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_INDEX, upstream->phyindex)) + return -EMSGSIZE; + + if (pdn->parent_sfp_bus) { + sfp_upstream_name = sfp_get_name(pdn->parent_sfp_bus); + if (sfp_upstream_name && + nla_put_string(skb, ETHTOOL_A_PHY_UPSTREAM_SFP_NAME, + sfp_upstream_name)) + return -EMSGSIZE; + } + } + + if (phydev->sfp_bus) { + const char *sfp_name = sfp_get_name(phydev->sfp_bus); + + if (sfp_name && + nla_put_string(skb, ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME, + sfp_name)) + return -EMSGSIZE; + } + + return 0; +} + +static int ethnl_phy_parse_request(struct ethnl_req_info *req_base, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct phy_link_topology *topo = req_base->dev->link_topo; + struct phy_req_info *req_info = PHY_REQINFO(req_base); + struct phy_device *phydev; + + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PHY_HEADER], + extack); + if (!phydev) + return 0; + + if (IS_ERR(phydev)) + return PTR_ERR(phydev); + + if (!topo) + return 0; + + req_info->pdn = xa_load(&topo->phys, phydev->phyindex); + + return 0; +} + +int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct phy_req_info req_info = {}; + struct nlattr **tb = info->attrs; + struct sk_buff *rskb; + void *reply_payload; + int reply_len; + int ret; + + ret = ethnl_parse_header_dev_get(&req_info.base, + tb[ETHTOOL_A_PHY_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + + rtnl_lock(); + + ret = ethnl_phy_parse_request(&req_info.base, tb, info->extack); + if (ret < 0) + goto err_unlock_rtnl; + + /* No PHY, return early */ + if (!req_info.pdn->phy) + goto err_unlock_rtnl; + + ret = ethnl_phy_reply_size(&req_info.base, info->extack); + if (ret < 0) + goto err_unlock_rtnl; + reply_len = ret + ethnl_reply_header_size(); + + rskb = ethnl_reply_init(reply_len, req_info.base.dev, + ETHTOOL_MSG_PHY_GET_REPLY, + ETHTOOL_A_PHY_HEADER, + info, &reply_payload); + if (!rskb) { + ret = -ENOMEM; + goto err_unlock_rtnl; + } + + ret = ethnl_phy_fill_reply(&req_info.base, rskb); + if (ret) + goto err_free_msg; + + rtnl_unlock(); + ethnl_parse_header_dev_put(&req_info.base); + genlmsg_end(rskb, reply_payload); + + return genlmsg_reply(rskb, info); + +err_free_msg: + nlmsg_free(rskb); +err_unlock_rtnl: + rtnl_unlock(); + ethnl_parse_header_dev_put(&req_info.base); + return ret; +} + +struct ethnl_phy_dump_ctx { + struct phy_req_info *phy_req_info; + unsigned long ifindex; + unsigned long phy_index; +}; + +int ethnl_phy_start(struct netlink_callback *cb) +{ + const struct genl_info *info = genl_info_dump(cb); + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + int ret; + + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); + + ctx->phy_req_info = kzalloc(sizeof(*ctx->phy_req_info), GFP_KERNEL); + if (!ctx->phy_req_info) + return -ENOMEM; + + ret = ethnl_parse_header_dev_get(&ctx->phy_req_info->base, + info->attrs[ETHTOOL_A_PHY_HEADER], + sock_net(cb->skb->sk), cb->extack, + false); + ctx->ifindex = 0; + ctx->phy_index = 0; + + if (ret) + kfree(ctx->phy_req_info); + + return ret; +} + +int ethnl_phy_done(struct netlink_callback *cb) +{ + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + + if (ctx->phy_req_info->base.dev) + ethnl_parse_header_dev_put(&ctx->phy_req_info->base); + + kfree(ctx->phy_req_info); + + return 0; +} + +static int ethnl_phy_dump_one_dev(struct sk_buff *skb, struct net_device *dev, + struct netlink_callback *cb) +{ + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + struct phy_req_info *pri = ctx->phy_req_info; + struct phy_device_node *pdn; + int ret = 0; + void *ehdr; + + pri->base.dev = dev; + + if (!dev->link_topo) + return 0; + + xa_for_each_start(&dev->link_topo->phys, ctx->phy_index, pdn, ctx->phy_index) { + ehdr = ethnl_dump_put(skb, cb, ETHTOOL_MSG_PHY_GET_REPLY); + if (!ehdr) { + ret = -EMSGSIZE; + break; + } + + ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_PHY_HEADER); + if (ret < 0) { + genlmsg_cancel(skb, ehdr); + break; + } + + pri->pdn = pdn; + ret = ethnl_phy_fill_reply(&pri->base, skb); + if (ret < 0) { + genlmsg_cancel(skb, ehdr); + break; + } + + genlmsg_end(skb, ehdr); + } + + return ret; +} + +int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + + if (ctx->phy_req_info->base.dev) { + ret = ethnl_phy_dump_one_dev(skb, ctx->phy_req_info->base.dev, cb); + } else { + for_each_netdev_dump(net, dev, ctx->ifindex) { + ret = ethnl_phy_dump_one_dev(skb, dev, cb); + if (ret) + break; + + ctx->phy_index = 0; + } + } + rtnl_unlock(); + + return ret; +} From d3d9a3e48a63eec82082a7ef76f5d5b6d339933f Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:10:02 +0200 Subject: [PATCH 326/385] netlink: specs: add ethnl PHY_GET command set The PHY_GET command, supporting both DUMP and GET operations, is used to retrieve the list of PHYs connected to a netdevice, and get topology information to know where exactly it sits on the physical link. Add the netlink specs corresponding to that command. Signed-off-by: Maxime Chevallier Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- Documentation/netlink/specs/ethtool.yaml | 55 ++++++++++++++++++++++++ 1 file changed, 55 insertions(+) diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 7d6c3ace3fa2b..37211b1e861fe 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -39,6 +39,11 @@ definitions: - ovld-detected - power-not-available - short-detected + - + name: phy-upstream-type + enum-name: + type: enum + entries: [ mac, phy ] attribute-sets: - @@ -1092,6 +1097,35 @@ attribute-sets: - name: total type: uint + - + name: phy + attributes: + - + name: header + type: nest + nested-attributes: header + - + name: index + type: u32 + - + name: drvname + type: string + - + name: name + type: string + - + name: upstream-type + type: u32 + enum: phy-upstream-type + - + name: upstream-index + type: u32 + - + name: upstream-sfp-name + type: string + - + name: downstream-sfp-name + type: string operations: enum-model: directional @@ -1890,3 +1924,24 @@ operations: - status-msg - done - total + - + name: phy-get + doc: Get PHY devices attached to an interface + + attribute-set: phy + + do: &phy-get-op + request: + attributes: + - header + reply: + attributes: + - header + - index + - drvname + - name + - upstream-type + - upstream-index + - upstream-sfp-name + - downstream-sfp-name + dump: *phy-get-op From 02180fb525bac8c259c3b7271ddfa498d47c5dcc Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:10:03 +0200 Subject: [PATCH 327/385] net: ethtool: plca: Target the command to the requested PHY PLCA is a PHY-specific command. Instead of targeting the command towards dev->phydev, use the request to pick the targeted PHY. Signed-off-by: Maxime Chevallier Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- net/ethtool/plca.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c index b1e2e3b5027fc..d95d92f173a6d 100644 --- a/net/ethtool/plca.c +++ b/net/ethtool/plca.c @@ -25,7 +25,7 @@ struct plca_reply_data { const struct nla_policy ethnl_plca_get_cfg_policy[] = { [ETHTOOL_A_PLCA_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static void plca_update_sint(int *dst, struct nlattr **tb, u32 attrid, @@ -58,10 +58,14 @@ static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, struct plca_reply_data *data = PLCA_REPDATA(reply_base); struct net_device *dev = reply_base->dev; const struct ethtool_phy_ops *ops; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; int ret; + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PLCA_HEADER], + info->extack); // check that the PHY device is available and connected - if (!dev->phydev) { + if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; goto out; } @@ -80,7 +84,7 @@ static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, memset(&data->plca_cfg, 0xff, sizeof_field(struct plca_reply_data, plca_cfg)); - ret = ops->get_plca_cfg(dev->phydev, &data->plca_cfg); + ret = ops->get_plca_cfg(phydev, &data->plca_cfg); ethnl_ops_complete(dev); out: @@ -129,7 +133,7 @@ static int plca_get_cfg_fill_reply(struct sk_buff *skb, const struct nla_policy ethnl_plca_set_cfg_policy[] = { [ETHTOOL_A_PLCA_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_PLCA_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_PLCA_NODE_ID] = NLA_POLICY_MAX(NLA_U32, 255), [ETHTOOL_A_PLCA_NODE_CNT] = NLA_POLICY_RANGE(NLA_U32, 1, 255), @@ -141,15 +145,17 @@ const struct nla_policy ethnl_plca_set_cfg_policy[] = { static int ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info) { - struct net_device *dev = req_info->dev; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; struct phy_plca_cfg plca_cfg; + struct phy_device *phydev; bool mod = false; int ret; + phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PLCA_HEADER], + info->extack); // check that the PHY device is available and connected - if (!dev->phydev) + if (IS_ERR_OR_NULL(phydev)) return -EOPNOTSUPP; ops = ethtool_phy_ops; @@ -168,7 +174,7 @@ ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info) if (!mod) return 0; - ret = ops->set_plca_cfg(dev->phydev, &plca_cfg, info->extack); + ret = ops->set_plca_cfg(phydev, &plca_cfg, info->extack); return ret < 0 ? ret : 1; } @@ -191,7 +197,7 @@ const struct ethnl_request_ops ethnl_plca_cfg_request_ops = { const struct nla_policy ethnl_plca_get_status_policy[] = { [ETHTOOL_A_PLCA_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, @@ -201,10 +207,14 @@ static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, struct plca_reply_data *data = PLCA_REPDATA(reply_base); struct net_device *dev = reply_base->dev; const struct ethtool_phy_ops *ops; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; int ret; + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PLCA_HEADER], + info->extack); // check that the PHY device is available and connected - if (!dev->phydev) { + if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; goto out; } @@ -223,7 +233,7 @@ static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, memset(&data->plca_st, 0xff, sizeof_field(struct plca_reply_data, plca_st)); - ret = ops->get_plca_status(dev->phydev, &data->plca_st); + ret = ops->get_plca_status(phydev, &data->plca_st); ethnl_ops_complete(dev); out: return ret; From 31748765bed3fb7cebf4a32b43a6fdf91b9c23de Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:10:04 +0200 Subject: [PATCH 328/385] net: ethtool: pse-pd: Target the command to the requested PHY PSE and PD configuration is a PHY-specific command. Instead of targeting the command towards dev->phydev, use the request to pick the targeted PHY device. As we don't get the PHY directly from the netdev's attached phydev, also adjust the error messages. Signed-off-by: Maxime Chevallier Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- net/ethtool/pse-pd.c | 31 +++++++++++++++++++------------ 1 file changed, 19 insertions(+), 12 deletions(-) diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c index ff81aa7497847..507cb21d6bf0c 100644 --- a/net/ethtool/pse-pd.c +++ b/net/ethtool/pse-pd.c @@ -28,17 +28,15 @@ struct pse_reply_data { /* PSE_GET */ const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1] = { - [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), }; -static int pse_get_pse_attributes(struct net_device *dev, +static int pse_get_pse_attributes(struct phy_device *phydev, struct netlink_ext_ack *extack, struct pse_reply_data *data) { - struct phy_device *phydev = dev->phydev; - if (!phydev) { - NL_SET_ERR_MSG(extack, "No PHY is attached"); + NL_SET_ERR_MSG(extack, "No PHY found"); return -EOPNOTSUPP; } @@ -58,13 +56,20 @@ static int pse_prepare_data(const struct ethnl_req_info *req_base, { struct pse_reply_data *data = PSE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; int ret; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; - ret = pse_get_pse_attributes(dev, info->extack, data); + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PSE_HEADER], + info->extack); + if (IS_ERR(phydev)) + return -ENODEV; + + ret = pse_get_pse_attributes(phydev, info->extack, data); ethnl_ops_complete(dev); @@ -206,7 +211,7 @@ static void pse_cleanup_data(struct ethnl_reply_data *reply_base) /* PSE_SET */ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = { - [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] = NLA_POLICY_RANGE(NLA_U32, ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED, ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED), @@ -219,12 +224,12 @@ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = { static int ethnl_set_pse_validate(struct ethnl_req_info *req_info, struct genl_info *info) { - struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; struct phy_device *phydev; - phydev = dev->phydev; - if (!phydev) { + phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PSE_HEADER], + info->extack); + if (IS_ERR_OR_NULL(phydev)) { NL_SET_ERR_MSG(info->extack, "No PHY is attached"); return -EOPNOTSUPP; } @@ -255,12 +260,14 @@ ethnl_set_pse_validate(struct ethnl_req_info *req_info, struct genl_info *info) static int ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info) { - struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; struct phy_device *phydev; int ret = 0; - phydev = dev->phydev; + phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PSE_HEADER], + info->extack); + if (IS_ERR_OR_NULL(phydev)) + return -ENODEV; if (tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]) { unsigned int pw_limit; From 3688ff3077d3f334cee1d4b61d8bfb6a9508c2d2 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:10:05 +0200 Subject: [PATCH 329/385] net: ethtool: cable-test: Target the command to the requested PHY Cable testing is a PHY-specific command. Instead of targeting the command towards dev->phydev, use the request to pick the targeted PHY. Signed-off-by: Maxime Chevallier Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- net/ethtool/cabletest.c | 35 ++++++++++++++++++++++------------- 1 file changed, 22 insertions(+), 13 deletions(-) diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c index f6f136ec7ddfc..01db8f394869f 100644 --- a/net/ethtool/cabletest.c +++ b/net/ethtool/cabletest.c @@ -13,7 +13,7 @@ const struct nla_policy ethnl_cable_test_act_policy[] = { [ETHTOOL_A_CABLE_TEST_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static int ethnl_cable_test_started(struct phy_device *phydev, u8 cmd) @@ -58,6 +58,7 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) struct ethnl_req_info req_info = {}; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; + struct phy_device *phydev; struct net_device *dev; int ret; @@ -69,12 +70,16 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) return ret; dev = req_info.dev; - if (!dev->phydev) { + + rtnl_lock(); + phydev = ethnl_req_get_phydev(&req_info, + tb[ETHTOOL_A_CABLE_TEST_HEADER], + info->extack); + if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; goto out_dev_put; } - rtnl_lock(); ops = ethtool_phy_ops; if (!ops || !ops->start_cable_test) { ret = -EOPNOTSUPP; @@ -85,13 +90,12 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) if (ret < 0) goto out_rtnl; - ret = ops->start_cable_test(dev->phydev, info->extack); + ret = ops->start_cable_test(phydev, info->extack); ethnl_ops_complete(dev); if (!ret) - ethnl_cable_test_started(dev->phydev, - ETHTOOL_MSG_CABLE_TEST_NTF); + ethnl_cable_test_started(phydev, ETHTOOL_MSG_CABLE_TEST_NTF); out_rtnl: rtnl_unlock(); @@ -216,7 +220,7 @@ static const struct nla_policy cable_test_tdr_act_cfg_policy[] = { const struct nla_policy ethnl_cable_test_tdr_act_policy[] = { [ETHTOOL_A_CABLE_TEST_TDR_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_CABLE_TEST_TDR_CFG] = { .type = NLA_NESTED }, }; @@ -305,6 +309,7 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) struct ethnl_req_info req_info = {}; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; + struct phy_device *phydev; struct phy_tdr_config cfg; struct net_device *dev; int ret; @@ -317,10 +322,6 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) return ret; dev = req_info.dev; - if (!dev->phydev) { - ret = -EOPNOTSUPP; - goto out_dev_put; - } ret = ethnl_act_cable_test_tdr_cfg(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG], info, &cfg); @@ -328,6 +329,14 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) goto out_dev_put; rtnl_lock(); + phydev = ethnl_req_get_phydev(&req_info, + tb[ETHTOOL_A_CABLE_TEST_TDR_HEADER], + info->extack); + if (!IS_ERR_OR_NULL(phydev)) { + ret = -EOPNOTSUPP; + goto out_dev_put; + } + ops = ethtool_phy_ops; if (!ops || !ops->start_cable_test_tdr) { ret = -EOPNOTSUPP; @@ -338,12 +347,12 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) if (ret < 0) goto out_rtnl; - ret = ops->start_cable_test_tdr(dev->phydev, info->extack, &cfg); + ret = ops->start_cable_test_tdr(phydev, info->extack, &cfg); ethnl_ops_complete(dev); if (!ret) - ethnl_cable_test_started(dev->phydev, + ethnl_cable_test_started(phydev, ETHTOOL_MSG_CABLE_TEST_TDR_NTF); out_rtnl: From e96c93aa4be971276f9340fa74e84ae62701f2f0 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:10:06 +0200 Subject: [PATCH 330/385] net: ethtool: strset: Allow querying phy stats by index The ETH_SS_PHY_STATS command gets PHY statistics. Use the phydev pointer from the ethnl request to allow query phy stats from each PHY on the link. Signed-off-by: Maxime Chevallier Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- net/ethtool/strset.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index 56b99606f00b9..b3382b3cf325c 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -126,7 +126,7 @@ struct strset_reply_data { const struct nla_policy ethnl_strset_get_policy[] = { [ETHTOOL_A_STRSET_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_STRSET_STRINGSETS] = { .type = NLA_NESTED }, [ETHTOOL_A_STRSET_COUNTS_ONLY] = { .type = NLA_FLAG }, }; @@ -233,17 +233,18 @@ static void strset_cleanup_data(struct ethnl_reply_data *reply_base) } static int strset_prepare_set(struct strset_info *info, struct net_device *dev, - unsigned int id, bool counts_only) + struct phy_device *phydev, unsigned int id, + bool counts_only) { const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops; const struct ethtool_ops *ops = dev->ethtool_ops; void *strings; int count, ret; - if (id == ETH_SS_PHY_STATS && dev->phydev && + if (id == ETH_SS_PHY_STATS && phydev && !ops->get_ethtool_phy_stats && phy_ops && phy_ops->get_sset_count) - ret = phy_ops->get_sset_count(dev->phydev); + ret = phy_ops->get_sset_count(phydev); else if (ops->get_sset_count && ops->get_strings) ret = ops->get_sset_count(dev, id); else @@ -258,10 +259,10 @@ static int strset_prepare_set(struct strset_info *info, struct net_device *dev, strings = kcalloc(count, ETH_GSTRING_LEN, GFP_KERNEL); if (!strings) return -ENOMEM; - if (id == ETH_SS_PHY_STATS && dev->phydev && + if (id == ETH_SS_PHY_STATS && phydev && !ops->get_ethtool_phy_stats && phy_ops && phy_ops->get_strings) - phy_ops->get_strings(dev->phydev, strings); + phy_ops->get_strings(phydev, strings); else ops->get_strings(dev, id, strings); info->strings = strings; @@ -279,6 +280,8 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base, const struct strset_req_info *req_info = STRSET_REQINFO(req_base); struct strset_reply_data *data = STRSET_REPDATA(reply_base); struct net_device *dev = reply_base->dev; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; unsigned int i; int ret; @@ -296,6 +299,13 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base, return 0; } + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_HEADER_FLAGS], + info->extack); + + /* phydev can be NULL, check for errors only */ + if (IS_ERR(phydev)) + return PTR_ERR(phydev); + ret = ethnl_ops_begin(dev); if (ret < 0) goto err_strset; @@ -304,7 +314,7 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base, !data->sets[i].per_dev) continue; - ret = strset_prepare_set(&data->sets[i], dev, i, + ret = strset_prepare_set(&data->sets[i], dev, phydev, i, req_info->counts_only); if (ret < 0) goto err_ops; From db31e09d517bac2ac7314d8c5749ee2cb2b50ef2 Mon Sep 17 00:00:00 2001 From: Maxime Chevallier Date: Wed, 21 Aug 2024 17:10:07 +0200 Subject: [PATCH 331/385] Documentation: networking: document phy_link_topology The newly introduced phy_link_topology tracks all ethernet PHYs that are attached to a netdevice. Document the base principle, internal and external APIs. As the phy_link_topology is expected to be extended, this documentation will hold any further improvements and additions made relative to topology handling. Signed-off-by: Maxime Chevallier Reviewed-by: Andrew Lunn Reviewed-by: Christophe Leroy Tested-by: Christophe Leroy Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 3 + Documentation/networking/index.rst | 1 + .../networking/phy-link-topology.rst | 121 ++++++++++++++++++ 3 files changed, 125 insertions(+) create mode 100644 Documentation/networking/phy-link-topology.rst diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 8c152871c23c4..44cb9e29f325a 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -2198,10 +2198,13 @@ Retrieve information about a given Ethernet PHY sitting on the link. The DO operation returns all available information about dev->phydev. User can also specify a PHY_INDEX, in which case the DO request returns information about that specific PHY. + As there can be more than one PHY, the DUMP operation can be used to list the PHYs present on a given interface, by passing an interface index or name in the dump request. +For more information, refer to :ref:`phy_link_topology` + Request contents: ==================================== ====== ========================== diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index d1af04b952f81..c71b873461788 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -91,6 +91,7 @@ Contents: operstates packet_mmap phonet + phy-link-topology pktgen plip ppp_generic diff --git a/Documentation/networking/phy-link-topology.rst b/Documentation/networking/phy-link-topology.rst new file mode 100644 index 0000000000000..4dec5d7d6513d --- /dev/null +++ b/Documentation/networking/phy-link-topology.rst @@ -0,0 +1,121 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. _phy_link_topology: + +================= +PHY link topology +================= + +Overview +======== + +The PHY link topology representation in the networking stack aims at representing +the hardware layout for any given Ethernet link. + +An Ethernet interface from userspace's point of view is nothing but a +:c:type:`struct net_device `, which exposes configuration options +through the legacy ioctls and the ethtool netlink commands. The base assumption +when designing these configuration APIs were that the link looks something like :: + + +-----------------------+ +----------+ +--------------+ + | Ethernet Controller / | | Ethernet | | Connector / | + | MAC | ------ | PHY | ---- | Port | ---... to LP + +-----------------------+ +----------+ +--------------+ + struct net_device struct phy_device + +Commands that needs to configure the PHY will go through the net_device.phydev +field to reach the PHY and perform the relevant configuration. + +This assumption falls apart in more complex topologies that can arise when, +for example, using SFP transceivers (although that's not the only specific case). + +Here, we have 2 basic scenarios. Either the MAC is able to output a serialized +interface, that can directly be fed to an SFP cage, such as SGMII, 1000BaseX, +10GBaseR, etc. + +The link topology then looks like this (when an SFP module is inserted) :: + + +-----+ SGMII +------------+ + | MAC | ------- | SFP Module | + +-----+ +------------+ + +Knowing that some modules embed a PHY, the actual link is more like :: + + +-----+ SGMII +--------------+ + | MAC | -------- | PHY (on SFP) | + +-----+ +--------------+ + +In this case, the SFP PHY is handled by phylib, and registered by phylink through +its SFP upstream ops. + +Now some Ethernet controllers aren't able to output a serialized interface, so +we can't directly connect them to an SFP cage. However, some PHYs can be used +as media-converters, to translate the non-serialized MAC MII interface to a +serialized MII interface fed to the SFP :: + + +-----+ RGMII +-----------------------+ SGMII +--------------+ + | MAC | ------- | PHY (media converter) | ------- | PHY (on SFP) | + +-----+ +-----------------------+ +--------------+ + +This is where the model of having a single net_device.phydev pointer shows its +limitations, as we now have 2 PHYs on the link. + +The phy_link topology framework aims at providing a way to keep track of every +PHY on the link, for use by both kernel drivers and subsystems, but also to +report the topology to userspace, allowing to target individual PHYs in configuration +commands. + +API +=== + +The :c:type:`struct phy_link_topology ` is a per-netdevice +resource, that gets initialized at netdevice creation. Once it's initialized, +it is then possible to register PHYs to the topology through : + +:c:func:`phy_link_topo_add_phy` + +Besides registering the PHY to the topology, this call will also assign a unique +index to the PHY, which can then be reported to userspace to refer to this PHY +(akin to the ifindex). This index is a u32, ranging from 1 to U32_MAX. The value +0 is reserved to indicate the PHY doesn't belong to any topology yet. + +The PHY can then be removed from the topology through + +:c:func:`phy_link_topo_del_phy` + +These function are already hooked into the phylib subsystem, so all PHYs that +are linked to a net_device through :c:func:`phy_attach_direct` will automatically +join the netdev's topology. + +PHYs that are on a SFP module will also be automatically registered IF the SFP +upstream is phylink (so, no media-converter). + +PHY drivers that can be used as SFP upstream need to call :c:func:`phy_sfp_attach_phy` +and :c:func:`phy_sfp_detach_phy`, which can be used as a +.attach_phy / .detach_phy implementation for the +:c:type:`struct sfp_upstream_ops `. + +UAPI +==== + +There exist a set of netlink commands to query the link topology from userspace, +see ``Documentation/networking/ethtool-netlink.rst``. + +The whole point of having a topology representation is to assign the phyindex +field in :c:type:`struct phy_device `. This index is reported to +userspace using the ``ETHTOOL_MSG_PHY_GET`` ethtnl command. Performing a DUMP operation +will result in all PHYs from all net_device being listed. The DUMP command +accepts either a ``ETHTOOL_A_HEADER_DEV_INDEX`` or ``ETHTOOL_A_HEADER_DEV_NAME`` +to be passed in the request to filter the DUMP to a single net_device. + +The retrieved index can then be passed as a request parameter using the +``ETHTOOL_A_HEADER_PHY_INDEX`` field in the following ethnl commands : + +* ``ETHTOOL_MSG_STRSET_GET`` to get the stats string set from a given PHY +* ``ETHTOOL_MSG_CABLE_TEST_ACT`` and ``ETHTOOL_MSG_CABLE_TEST_ACT``, to perform + cable testing on a given PHY on the link (most likely the outermost PHY) +* ``ETHTOOL_MSG_PSE_SET`` and ``ETHTOOL_MSG_PSE_GET`` for PHY-controlled PoE and PSE settings +* ``ETHTOOL_MSG_PLCA_GET_CFG``, ``ETHTOOL_MSG_PLCA_SET_CFG`` and ``ETHTOOL_MSG_PLCA_GET_STATUS`` + to set the PLCA (Physical Layer Collision Avoidance) parameters + +Note that the PHY index can be passed to other requests, which will silently +ignore it if present and irrelevant. From 6ef1ca2d14f2a78a83dfd40e34f53e8d5c1c0b4b Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 22 Aug 2024 12:32:43 +0800 Subject: [PATCH 332/385] net: vxlan: delete redundant judgment statements The initial value of err is -ENOBUFS, and err is guaranteed to be less than 0 before all goto errout. Therefore, on the error path of errout, there is no need to repeatedly judge that err is less than 0, and delete redundant judgments to make the code more concise. Signed-off-by: Li Zetao Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- drivers/net/vxlan/vxlan_core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 8983e75e9881d..34391c18bba7e 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -277,8 +277,7 @@ static void __vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); + rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan, From 41aa426392be26865a8a774df3e5ec4c56a98b26 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 22 Aug 2024 12:32:44 +0800 Subject: [PATCH 333/385] fib: rules: delete redundant judgment statements The initial value of err is -ENOMEM, and err is guaranteed to be less than 0 before all goto errout. Therefore, on the error path of errout, there is no need to repeatedly judge that err is less than 0, and delete redundant judgments to make the code more concise. Signed-off-by: Li Zetao Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- net/core/fib_rules.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 6ebffbc632368..3c76b835493da 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -1205,8 +1205,7 @@ static void notify_rule_change(int event, struct fib_rule *rule, rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(net, ops->nlgroup, err); + rtnl_set_sk_err(net, ops->nlgroup, err); } static void attach_rules(struct list_head *rules, struct net_device *dev) From c25bdd2ac8cf7da70a226f1a66cdce7af15ff86f Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 22 Aug 2024 12:32:45 +0800 Subject: [PATCH 334/385] neighbour: delete redundant judgment statements The initial value of err is -ENOBUFS, and err is guaranteed to be less than 0 before all goto errout. Therefore, on the error path of errout, there is no need to repeatedly judge that err is less than 0, and delete redundant judgments to make the code more concise. Signed-off-by: Li Zetao Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- net/core/neighbour.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index a6fe88eca939f..77b819cd995b2 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3530,8 +3530,7 @@ static void __neigh_notify(struct neighbour *n, int type, int flags, rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); + rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } void neigh_app_ns(struct neighbour *n) From 2d522384fb5b8187cb7f8fe7d05c119ac38fd8f3 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 22 Aug 2024 12:32:46 +0800 Subject: [PATCH 335/385] rtnetlink: delete redundant judgment statements The initial value of err is -ENOBUFS, and err is guaranteed to be less than 0 before all goto errout. Therefore, on the error path of errout, there is no need to repeatedly judge that err is less than 0, and delete redundant judgments to make the code more concise. Signed-off-by: Li Zetao Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 73fd7f543fd09..cd9487a12d1a3 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4087,8 +4087,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, } return skb; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_LINK, err); + rtnl_set_sk_err(net, RTNLGRP_LINK, err); return NULL; } From 4c180887775f3e3fb46b9e447cf3ea539286919d Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 22 Aug 2024 12:32:47 +0800 Subject: [PATCH 336/385] ipv4: delete redundant judgment statements The initial value of err is -ENOBUFS, and err is guaranteed to be less than 0 before all goto errout. Therefore, on the error path of errout, there is no need to repeatedly judge that err is less than 0, and delete redundant judgments to make the code more concise. Signed-off-by: Li Zetao Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- net/ipv4/devinet.c | 6 ++---- net/ipv4/fib_semantics.c | 3 +-- 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 61be85154dd19..ab76744383cf3 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1943,8 +1943,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, rtnl_notify(skb, net, portid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); + rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); } static size_t inet_get_link_af_size(const struct net_device *dev, @@ -2140,8 +2139,7 @@ void inet_netconf_notify_devconf(struct net *net, int event, int type, rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); + rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); } static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 0f70341cb8b5e..ba2df3d2ac15c 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -543,8 +543,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, info->nlh, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err); + rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err); } static int fib_detect_death(struct fib_info *fi, int order, From ebe39f95bc8138eedaba9adaa5a4d7bfe98a9806 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 22 Aug 2024 12:32:48 +0800 Subject: [PATCH 337/385] ipmr: delete redundant judgment statements The initial value of err is -ENOBUFS, and err is guaranteed to be less than 0 before all goto errout. Therefore, on the error path of errout, there is no need to repeatedly judge that err is less than 0, and delete redundant judgments to make the code more concise. Signed-off-by: Li Zetao Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- net/ipv4/ipmr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index d5295b69bc0af..b0eda745e3bc4 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2407,8 +2407,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, errout: kfree_skb(skb); - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err); } static size_t igmpmsg_netlink_msgsize(size_t payloadlen) From 649c3c9b8e448f41f6249abcfe9a670a80fac7f7 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 22 Aug 2024 12:32:49 +0800 Subject: [PATCH 338/385] net: nexthop: delete redundant judgment statements The initial value of err is -ENOBUFS, and err is guaranteed to be less than 0 before all goto errout. Therefore, on the error path of errout, there is no need to repeatedly judge that err is less than 0, and delete redundant judgments to make the code more concise. Signed-off-by: Li Zetao Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- net/ipv4/nexthop.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 9db10d409074e..93aaea0006ba7 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1090,8 +1090,7 @@ static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info) info->nlh, gfp_any()); return; errout: - if (err < 0) - rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err); + rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err); } static unsigned long nh_res_bucket_used_time(const struct nh_res_bucket *bucket) @@ -1211,8 +1210,7 @@ static void nexthop_bucket_notify(struct nh_res_table *res_table, rtnl_notify(skb, nh->net, 0, RTNLGRP_NEXTHOP, NULL, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(nh->net, RTNLGRP_NEXTHOP, err); + rtnl_set_sk_err(nh->net, RTNLGRP_NEXTHOP, err); } static bool valid_group_nh(struct nexthop *nh, unsigned int npaths, From aa32799c017b881a79cb1b9263419626fc9a5f66 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 22 Aug 2024 12:32:50 +0800 Subject: [PATCH 339/385] ip6mr: delete redundant judgment statements The initial value of err is -ENOBUFS, and err is guaranteed to be less than 0 before all goto errout. Therefore, on the error path of errout, there is no need to repeatedly judge that err is less than 0, and delete redundant judgments to make the code more concise. Signed-off-by: Li Zetao Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- net/ipv6/ip6mr.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index dd342e6ecf3f4..e3ee93c562c3a 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2431,8 +2431,7 @@ static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc, errout: kfree_skb(skb); - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err); } static size_t mrt6msg_netlink_msgsize(size_t payloadlen) From cd9ebde125bf77e22ba0c47e3ac657b993089a55 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 22 Aug 2024 12:32:51 +0800 Subject: [PATCH 340/385] net/ipv6: delete redundant judgment statements The initial value of err is -ENOBUFS, and err is guaranteed to be less than 0 before all goto errout. Therefore, on the error path of errout, there is no need to repeatedly judge that err is less than 0, and delete redundant judgments to make the code more concise. Signed-off-by: Li Zetao Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- net/ipv6/route.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 219701caba1e9..7e7de29ad05f8 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6193,8 +6193,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, info->nlh, gfp_any()); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_rt_update(struct net *net, struct fib6_info *rt, @@ -6220,8 +6219,7 @@ void fib6_rt_update(struct net *net, struct fib6_info *rt, info->nlh, gfp_any()); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, From fb8e83cf443a98297cd15b58b5529f8d259b22f5 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 22 Aug 2024 12:32:52 +0800 Subject: [PATCH 341/385] net: mpls: delete redundant judgment statements The initial value of err is -ENOBUFS, and err is guaranteed to be less than 0 before all goto errout. Therefore, on the error path of errout, there is no need to repeatedly judge that err is less than 0, and delete redundant judgments to make the code more concise. Signed-off-by: Li Zetao Reviewed-by: Petr Machata Signed-off-by: David S. Miller --- net/mpls/af_mpls.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 0e6c94a8c2bc6..aba983531ed32 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1201,8 +1201,7 @@ static void mpls_netconf_notify_devconf(struct net *net, int event, rtnl_notify(skb, net, 0, RTNLGRP_MPLS_NETCONF, NULL, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_MPLS_NETCONF, err); + rtnl_set_sk_err(net, RTNLGRP_MPLS_NETCONF, err); } static const struct nla_policy devconf_mpls_policy[NETCONFA_MAX + 1] = { @@ -2278,8 +2277,7 @@ static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err); } static int mpls_valid_getroute_req(struct sk_buff *skb, From 7d3aed652d090508990d245f9d80dcc481910d02 Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Thu, 22 Aug 2024 05:51:54 +0000 Subject: [PATCH 342/385] net: refactor ->ndo_bpf calls into dev_xdp_propagate When net devices propagate xdp configurations to slave devices, we will need to perform a memory provider check to ensure we're not binding xdp to a device using unreadable netmem. Currently the ->ndo_bpf calls in a few places. Adding checks to all these places would not be ideal. Refactor all the ->ndo_bpf calls into one place where we can add this check in the future. Suggested-by: Jakub Kicinski Signed-off-by: Mina Almasry Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 8 ++++---- drivers/net/hyperv/netvsc_bpf.c | 2 +- include/linux/netdevice.h | 1 + net/core/dev.c | 9 +++++++++ 4 files changed, 15 insertions(+), 5 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 96f5470a5f554..a3b6e6c696b4e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2253,7 +2253,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, goto err_sysfs_del; } - res = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + res = dev_xdp_propagate(slave_dev, &xdp); if (res < 0) { /* ndo_bpf() sets extack error message */ slave_dbg(bond_dev, slave_dev, "Error %d calling ndo_bpf\n", res); @@ -2389,7 +2389,7 @@ static int __bond_release_one(struct net_device *bond_dev, .prog = NULL, .extack = NULL, }; - if (slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp)) + if (dev_xdp_propagate(slave_dev, &xdp)) slave_warn(bond_dev, slave_dev, "failed to unload XDP program\n"); } @@ -5579,7 +5579,7 @@ static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog, goto err; } - err = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + err = dev_xdp_propagate(slave_dev, &xdp); if (err < 0) { /* ndo_bpf() sets extack error message */ slave_err(dev, slave_dev, "Error %d calling ndo_bpf\n", err); @@ -5611,7 +5611,7 @@ static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog, if (slave == rollback_slave) break; - err_unwind = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + err_unwind = dev_xdp_propagate(slave_dev, &xdp); if (err_unwind < 0) slave_err(dev, slave_dev, "Error %d when unwinding XDP program change\n", err_unwind); diff --git a/drivers/net/hyperv/netvsc_bpf.c b/drivers/net/hyperv/netvsc_bpf.c index 4a9522689fa4f..e01c5997a551c 100644 --- a/drivers/net/hyperv/netvsc_bpf.c +++ b/drivers/net/hyperv/netvsc_bpf.c @@ -183,7 +183,7 @@ int netvsc_vf_setxdp(struct net_device *vf_netdev, struct bpf_prog *prog) xdp.command = XDP_SETUP_PROG; xdp.prog = prog; - ret = vf_netdev->netdev_ops->ndo_bpf(vf_netdev, &xdp); + ret = dev_xdp_propagate(vf_netdev, &xdp); if (ret && prog) bpf_prog_put(prog); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 289a6133769c2..7dfa836d9dbf8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3925,6 +3925,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u8 dev_xdp_prog_count(struct net_device *dev); +int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); diff --git a/net/core/dev.c b/net/core/dev.c index d0e7483abdcdc..271d6aa0cfb91 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9370,6 +9370,15 @@ u8 dev_xdp_prog_count(struct net_device *dev) } EXPORT_SYMBOL_GPL(dev_xdp_prog_count); +int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) +{ + if (!dev->netdev_ops->ndo_bpf) + return -EOPNOTSUPP; + + return dev->netdev_ops->ndo_bpf(dev, bpf); +} +EXPORT_SYMBOL_GPL(dev_xdp_propagate); + u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_prog *prog = dev_xdp_prog(dev, mode); From 18aaa82bd36ae3d4eaa3f1d1d8cf643e39f151cd Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 22 Aug 2024 09:03:20 +0200 Subject: [PATCH 343/385] net: netlink: Remove the dump_cb_mutex field from struct netlink_sock Commit 5fbf57a937f4 ("net: netlink: remove the cb_mutex "injection" from netlink core") has removed the usage of the 'dump_cb_mutex' field from the struct netlink_sock. Remove the field itself now. It saves a few bytes in the structure. Signed-off-by: Christophe JAILLET Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/netlink/af_netlink.h | 1 - 1 file changed, 1 deletion(-) diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 9751e29d4bbb9..5b0e4e62ab8b9 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -41,7 +41,6 @@ struct netlink_sock { struct netlink_callback cb; struct mutex nl_cb_mutex; - struct mutex *dump_cb_mutex; void (*netlink_rcv)(struct sk_buff *skb); int (*netlink_bind)(struct net *net, int group); void (*netlink_unbind)(struct net *net, int group); From d4c897675a5a9f41a3f2c964d84e93bca5367f7a Mon Sep 17 00:00:00 2001 From: Divya Koppera Date: Wed, 21 Aug 2024 11:29:05 +0530 Subject: [PATCH 344/385] net: phy: Add phy library support to check supported list when autoneg is enabled Adds support in phy library to accept autoneg configuration only when feature is enabled in supported list. Signed-off-by: Divya Koppera Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20240821055906.27717-2-Divya.Koppera@microchip.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/phy.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 785182fa5fe01..cba3af926429d 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -1089,7 +1089,10 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev, if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE) return -EINVAL; - if (autoneg == AUTONEG_ENABLE && linkmode_empty(advertising)) + if (autoneg == AUTONEG_ENABLE && + (linkmode_empty(advertising) || + !linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + phydev->supported))) return -EINVAL; if (autoneg == AUTONEG_DISABLE && From 0941c83282349859e736b279908fd958f23e281a Mon Sep 17 00:00:00 2001 From: Divya Koppera Date: Wed, 21 Aug 2024 11:29:06 +0530 Subject: [PATCH 345/385] net: phy: microchip_t1: Adds support for lan887x phy The LAN887x is a Single-Port Ethernet Physical Layer Transceiver compliant with the IEEE 802.3bw (100BASE-T1) and IEEE 802.3bp (1000BASE-T1) specifications. The device provides 100/1000 Mbit/s transmit and receive capability over a single Unshielded Twisted Pair (UTP) cable. It supports communication with an Ethernet MAC via standard RGMII/SGMII interfaces. LAN887x supports following features, - Events/Interrupts - LED/GPIO Operation - IEEE 1588 (PTP) - SQI - Sleep and Wakeup (TC10) - Cable Diagnostics First patch only supports 100Mbps and 1000Mbps force-mode. Reviewed-by: Andrew Lunn Signed-off-by: Divya Koppera Link: https://patch.msgid.link/20240821055906.27717-3-Divya.Koppera@microchip.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/microchip_t1.c | 577 ++++++++++++++++++++++++++++++++- 1 file changed, 576 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c index a35528497a576..5732ad65e7f9a 100644 --- a/drivers/net/phy/microchip_t1.c +++ b/drivers/net/phy/microchip_t1.c @@ -12,6 +12,7 @@ #define PHY_ID_LAN87XX 0x0007c150 #define PHY_ID_LAN937X 0x0007c180 +#define PHY_ID_LAN887X 0x0007c1f0 /* External Register Control Register */ #define LAN87XX_EXT_REG_CTL (0x14) @@ -94,8 +95,101 @@ /* SQI defines */ #define LAN87XX_MAX_SQI 0x07 +/* Chiptop registers */ +#define LAN887X_PMA_EXT_ABILITY_2 0x12 +#define LAN887X_PMA_EXT_ABILITY_2_1000T1 BIT(1) +#define LAN887X_PMA_EXT_ABILITY_2_100T1 BIT(0) + +/* DSP 100M registers */ +#define LAN887x_CDR_CONFIG1_100 0x0405 +#define LAN887x_LOCK1_EQLSR_CONFIG_100 0x0411 +#define LAN887x_SLV_HD_MUFAC_CONFIG_100 0x0417 +#define LAN887x_PLOCK_MUFAC_CONFIG_100 0x041c +#define LAN887x_PROT_DISABLE_100 0x0425 +#define LAN887x_KF_LOOP_SAT_CONFIG_100 0x0454 + +/* DSP 1000M registers */ +#define LAN887X_LOCK1_EQLSR_CONFIG 0x0811 +#define LAN887X_LOCK3_EQLSR_CONFIG 0x0813 +#define LAN887X_PROT_DISABLE 0x0825 +#define LAN887X_FFE_GAIN6 0x0843 +#define LAN887X_FFE_GAIN7 0x0844 +#define LAN887X_FFE_GAIN8 0x0845 +#define LAN887X_FFE_GAIN9 0x0846 +#define LAN887X_ECHO_DELAY_CONFIG 0x08ec +#define LAN887X_FFE_MAX_CONFIG 0x08ee + +/* PCS 1000M registers */ +#define LAN887X_SCR_CONFIG_3 0x8043 +#define LAN887X_INFO_FLD_CONFIG_5 0x8048 + +/* T1 afe registers */ +#define LAN887X_ZQCAL_CONTROL_1 0x8080 +#define LAN887X_AFE_PORT_TESTBUS_CTRL2 0x8089 +#define LAN887X_AFE_PORT_TESTBUS_CTRL4 0x808b +#define LAN887X_AFE_PORT_TESTBUS_CTRL6 0x808d +#define LAN887X_TX_AMPLT_1000T1_REG 0x80b0 +#define LAN887X_INIT_COEFF_DFE1_100 0x0422 + +/* PMA registers */ +#define LAN887X_DSP_PMA_CONTROL 0x810e +#define LAN887X_DSP_PMA_CONTROL_LNK_SYNC BIT(4) + +/* PCS 100M registers */ +#define LAN887X_IDLE_ERR_TIMER_WIN 0x8204 +#define LAN887X_IDLE_ERR_CNT_THRESH 0x8213 + +/* Misc registers */ +#define LAN887X_REG_REG26 0x001a +#define LAN887X_REG_REG26_HW_INIT_SEQ_EN BIT(8) + +/* Mis registers */ +#define LAN887X_MIS_CFG_REG0 0xa00 +#define LAN887X_MIS_CFG_REG0_RCLKOUT_DIS BIT(5) +#define LAN887X_MIS_CFG_REG0_MAC_MODE_SEL GENMASK(1, 0) + +#define LAN887X_MAC_MODE_RGMII 0x01 +#define LAN887X_MAC_MODE_SGMII 0x03 + +#define LAN887X_MIS_DLL_CFG_REG0 0xa01 +#define LAN887X_MIS_DLL_CFG_REG1 0xa02 + +#define LAN887X_MIS_DLL_DELAY_EN BIT(15) +#define LAN887X_MIS_DLL_EN BIT(0) +#define LAN887X_MIS_DLL_CONF (LAN887X_MIS_DLL_DELAY_EN |\ + LAN887X_MIS_DLL_EN) + +#define LAN887X_MIS_CFG_REG2 0xa03 +#define LAN887X_MIS_CFG_REG2_FE_LPBK_EN BIT(2) + +#define LAN887X_MIS_PKT_STAT_REG0 0xa06 +#define LAN887X_MIS_PKT_STAT_REG1 0xa07 +#define LAN887X_MIS_PKT_STAT_REG3 0xa09 +#define LAN887X_MIS_PKT_STAT_REG4 0xa0a +#define LAN887X_MIS_PKT_STAT_REG5 0xa0b +#define LAN887X_MIS_PKT_STAT_REG6 0xa0c + +/* Chiptop common registers */ +#define LAN887X_COMMON_LED3_LED2 0xc05 +#define LAN887X_COMMON_LED2_MODE_SEL_MASK GENMASK(4, 0) +#define LAN887X_LED_LINK_ACT_ANY_SPEED 0x0 + +/* MX chip top registers */ +#define LAN887X_CHIP_SOFT_RST 0xf03f +#define LAN887X_CHIP_SOFT_RST_RESET BIT(0) + +#define LAN887X_SGMII_CTL 0xf01a +#define LAN887X_SGMII_CTL_SGMII_MUX_EN BIT(0) + +#define LAN887X_SGMII_PCS_CFG 0xf034 +#define LAN887X_SGMII_PCS_CFG_PCS_ENA BIT(9) + +#define LAN887X_EFUSE_READ_DAT9 0xf209 +#define LAN887X_EFUSE_READ_DAT9_SGMII_DIS BIT(9) +#define LAN887X_EFUSE_READ_DAT9_MAC_MODE GENMASK(1, 0) + #define DRIVER_AUTHOR "Nisar Sayed " -#define DRIVER_DESC "Microchip LAN87XX/LAN937x T1 PHY driver" +#define DRIVER_DESC "Microchip LAN87XX/LAN937x/LAN887x T1 PHY driver" struct access_ereg_val { u8 mode; @@ -105,6 +199,32 @@ struct access_ereg_val { u16 mask; }; +struct lan887x_hw_stat { + const char *string; + u8 mmd; + u16 reg; + u8 bits; +}; + +static const struct lan887x_hw_stat lan887x_hw_stats[] = { + { "TX Good Count", MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG0, 14}, + { "RX Good Count", MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG1, 14}, + { "RX ERR Count detected by PCS", MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG3, 16}, + { "TX CRC ERR Count", MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG4, 8}, + { "RX CRC ERR Count", MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG5, 8}, + { "RX ERR Count for SGMII MII2GMII", MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG6, 8}, +}; + +struct lan887x_regwr_map { + u8 mmd; + u16 reg; + u16 val; +}; + +struct lan887x_priv { + u64 stats[ARRAY_SIZE(lan887x_hw_stats)]; +}; + static int lan937x_dsp_workaround(struct phy_device *phydev, u16 ereg, u8 bank) { u8 prev_bank; @@ -860,6 +980,446 @@ static int lan87xx_get_sqi_max(struct phy_device *phydev) return LAN87XX_MAX_SQI; } +static int lan887x_rgmii_init(struct phy_device *phydev) +{ + int ret; + + /* SGMII mux disable */ + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + LAN887X_SGMII_CTL, + LAN887X_SGMII_CTL_SGMII_MUX_EN); + if (ret < 0) + return ret; + + /* Select MAC_MODE as RGMII */ + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_CFG_REG0, + LAN887X_MIS_CFG_REG0_MAC_MODE_SEL, + LAN887X_MAC_MODE_RGMII); + if (ret < 0) + return ret; + + /* Disable PCS */ + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + LAN887X_SGMII_PCS_CFG, + LAN887X_SGMII_PCS_CFG_PCS_ENA); + if (ret < 0) + return ret; + + /* LAN887x Errata: RGMII rx clock active in SGMII mode + * Disabled it for SGMII mode + * Re-enabling it for RGMII mode + */ + return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + LAN887X_MIS_CFG_REG0, + LAN887X_MIS_CFG_REG0_RCLKOUT_DIS); +} + +static int lan887x_sgmii_init(struct phy_device *phydev) +{ + int ret; + + /* SGMII mux enable */ + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, + LAN887X_SGMII_CTL, + LAN887X_SGMII_CTL_SGMII_MUX_EN); + if (ret < 0) + return ret; + + /* Select MAC_MODE as SGMII */ + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_CFG_REG0, + LAN887X_MIS_CFG_REG0_MAC_MODE_SEL, + LAN887X_MAC_MODE_SGMII); + if (ret < 0) + return ret; + + /* LAN887x Errata: RGMII rx clock active in SGMII mode. + * So disabling it for SGMII mode + */ + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_CFG_REG0, + LAN887X_MIS_CFG_REG0_RCLKOUT_DIS); + if (ret < 0) + return ret; + + /* Enable PCS */ + return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, LAN887X_SGMII_PCS_CFG, + LAN887X_SGMII_PCS_CFG_PCS_ENA); +} + +static int lan887x_config_rgmii_en(struct phy_device *phydev) +{ + int txc; + int rxc; + int ret; + + ret = lan887x_rgmii_init(phydev); + if (ret < 0) + return ret; + + /* Control bit to enable/disable TX DLL delay line in signal path */ + txc = phy_read_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_DLL_CFG_REG0); + if (txc < 0) + return txc; + + /* Control bit to enable/disable RX DLL delay line in signal path */ + rxc = phy_read_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_DLL_CFG_REG1); + if (rxc < 0) + return rxc; + + /* Configures the phy to enable RX/TX delay + * RGMII - TX & RX delays are either added by MAC or not needed, + * phy should not add + * RGMII_ID - Configures phy to enable TX & RX delays, MAC shouldn't add + * RGMII_RX_ID - Configures the PHY to enable the RX delay. + * The MAC shouldn't add the RX delay + * RGMII_TX_ID - Configures the PHY to enable the TX delay. + * The MAC shouldn't add the TX delay in this case + */ + switch (phydev->interface) { + case PHY_INTERFACE_MODE_RGMII: + txc &= ~LAN887X_MIS_DLL_CONF; + rxc &= ~LAN887X_MIS_DLL_CONF; + break; + case PHY_INTERFACE_MODE_RGMII_ID: + txc |= LAN887X_MIS_DLL_CONF; + rxc |= LAN887X_MIS_DLL_CONF; + break; + case PHY_INTERFACE_MODE_RGMII_RXID: + txc &= ~LAN887X_MIS_DLL_CONF; + rxc |= LAN887X_MIS_DLL_CONF; + break; + case PHY_INTERFACE_MODE_RGMII_TXID: + txc |= LAN887X_MIS_DLL_CONF; + rxc &= ~LAN887X_MIS_DLL_CONF; + break; + default: + WARN_ONCE(1, "Invalid phydev interface %d\n", phydev->interface); + return 0; + } + + /* Configures the PHY to enable/disable RX delay in signal path */ + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_DLL_CFG_REG1, + LAN887X_MIS_DLL_CONF, rxc); + if (ret < 0) + return ret; + + /* Configures the PHY to enable/disable the TX delay in signal path */ + return phy_modify_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_DLL_CFG_REG0, + LAN887X_MIS_DLL_CONF, txc); +} + +static int lan887x_config_phy_interface(struct phy_device *phydev) +{ + int interface_mode; + int sgmii_dis; + int ret; + + /* Read sku efuse data for interfaces supported by sku */ + ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, LAN887X_EFUSE_READ_DAT9); + if (ret < 0) + return ret; + + /* If interface_mode is 1 then efuse sets RGMII operations. + * If interface mode is 3 then efuse sets SGMII operations. + */ + interface_mode = ret & LAN887X_EFUSE_READ_DAT9_MAC_MODE; + /* SGMII disable is set for RGMII operations */ + sgmii_dis = ret & LAN887X_EFUSE_READ_DAT9_SGMII_DIS; + + switch (phydev->interface) { + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + /* Reject RGMII settings for SGMII only sku */ + ret = -EOPNOTSUPP; + + if (!((interface_mode & LAN887X_MAC_MODE_SGMII) == + LAN887X_MAC_MODE_SGMII)) + ret = lan887x_config_rgmii_en(phydev); + break; + case PHY_INTERFACE_MODE_SGMII: + /* Reject SGMII setting for RGMII only sku */ + ret = -EOPNOTSUPP; + + if (!sgmii_dis) + ret = lan887x_sgmii_init(phydev); + break; + default: + /* Reject setting for unsupported interfaces */ + ret = -EOPNOTSUPP; + } + + return ret; +} + +static int lan887x_get_features(struct phy_device *phydev) +{ + int ret; + + ret = genphy_c45_pma_read_abilities(phydev); + if (ret < 0) + return ret; + + /* Enable twisted pair */ + linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, phydev->supported); + + /* First patch only supports 100Mbps and 1000Mbps force-mode. + * T1 Auto-Negotiation (Clause 98 of IEEE 802.3) will be added later. + */ + linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->supported); + + return 0; +} + +static int lan887x_phy_init(struct phy_device *phydev) +{ + int ret; + + /* Clear loopback */ + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + LAN887X_MIS_CFG_REG2, + LAN887X_MIS_CFG_REG2_FE_LPBK_EN); + if (ret < 0) + return ret; + + /* Configure default behavior of led to link and activity for any + * speed + */ + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1, + LAN887X_COMMON_LED3_LED2, + LAN887X_COMMON_LED2_MODE_SEL_MASK, + LAN887X_LED_LINK_ACT_ANY_SPEED); + if (ret < 0) + return ret; + + /* PHY interface setup */ + return lan887x_config_phy_interface(phydev); +} + +static int lan887x_phy_config(struct phy_device *phydev, + const struct lan887x_regwr_map *reg_map, int cnt) +{ + int ret; + + for (int i = 0; i < cnt; i++) { + ret = phy_write_mmd(phydev, reg_map[i].mmd, + reg_map[i].reg, reg_map[i].val); + if (ret < 0) + return ret; + } + + return 0; +} + +static int lan887x_phy_setup(struct phy_device *phydev) +{ + static const struct lan887x_regwr_map phy_cfg[] = { + /* PORT_AFE writes */ + {MDIO_MMD_PMAPMD, LAN887X_ZQCAL_CONTROL_1, 0x4008}, + {MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL2, 0x0000}, + {MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL6, 0x0040}, + /* 100T1_PCS_VENDOR writes */ + {MDIO_MMD_PCS, LAN887X_IDLE_ERR_CNT_THRESH, 0x0008}, + {MDIO_MMD_PCS, LAN887X_IDLE_ERR_TIMER_WIN, 0x800d}, + /* 100T1 DSP writes */ + {MDIO_MMD_VEND1, LAN887x_CDR_CONFIG1_100, 0x0ab1}, + {MDIO_MMD_VEND1, LAN887x_LOCK1_EQLSR_CONFIG_100, 0x5274}, + {MDIO_MMD_VEND1, LAN887x_SLV_HD_MUFAC_CONFIG_100, 0x0d74}, + {MDIO_MMD_VEND1, LAN887x_PLOCK_MUFAC_CONFIG_100, 0x0aea}, + {MDIO_MMD_VEND1, LAN887x_PROT_DISABLE_100, 0x0360}, + {MDIO_MMD_VEND1, LAN887x_KF_LOOP_SAT_CONFIG_100, 0x0c30}, + /* 1000T1 DSP writes */ + {MDIO_MMD_VEND1, LAN887X_LOCK1_EQLSR_CONFIG, 0x2a78}, + {MDIO_MMD_VEND1, LAN887X_LOCK3_EQLSR_CONFIG, 0x1368}, + {MDIO_MMD_VEND1, LAN887X_PROT_DISABLE, 0x1354}, + {MDIO_MMD_VEND1, LAN887X_FFE_GAIN6, 0x3C84}, + {MDIO_MMD_VEND1, LAN887X_FFE_GAIN7, 0x3ca5}, + {MDIO_MMD_VEND1, LAN887X_FFE_GAIN8, 0x3ca5}, + {MDIO_MMD_VEND1, LAN887X_FFE_GAIN9, 0x3ca5}, + {MDIO_MMD_VEND1, LAN887X_ECHO_DELAY_CONFIG, 0x0024}, + {MDIO_MMD_VEND1, LAN887X_FFE_MAX_CONFIG, 0x227f}, + /* 1000T1 PCS writes */ + {MDIO_MMD_PCS, LAN887X_SCR_CONFIG_3, 0x1e00}, + {MDIO_MMD_PCS, LAN887X_INFO_FLD_CONFIG_5, 0x0fa1}, + }; + + return lan887x_phy_config(phydev, phy_cfg, ARRAY_SIZE(phy_cfg)); +} + +static int lan887x_100M_setup(struct phy_device *phydev) +{ + int ret; + + /* (Re)configure the speed/mode dependent T1 settings */ + if (phydev->master_slave_set == MASTER_SLAVE_CFG_MASTER_FORCE || + phydev->master_slave_set == MASTER_SLAVE_CFG_MASTER_PREFERRED){ + static const struct lan887x_regwr_map phy_cfg[] = { + {MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL4, 0x00b8}, + {MDIO_MMD_PMAPMD, LAN887X_TX_AMPLT_1000T1_REG, 0x0038}, + {MDIO_MMD_VEND1, LAN887X_INIT_COEFF_DFE1_100, 0x000f}, + }; + + ret = lan887x_phy_config(phydev, phy_cfg, ARRAY_SIZE(phy_cfg)); + } else { + static const struct lan887x_regwr_map phy_cfg[] = { + {MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL4, 0x0038}, + {MDIO_MMD_VEND1, LAN887X_INIT_COEFF_DFE1_100, 0x0014}, + }; + + ret = lan887x_phy_config(phydev, phy_cfg, ARRAY_SIZE(phy_cfg)); + } + if (ret < 0) + return ret; + + return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, LAN887X_REG_REG26, + LAN887X_REG_REG26_HW_INIT_SEQ_EN); +} + +static int lan887x_1000M_setup(struct phy_device *phydev) +{ + static const struct lan887x_regwr_map phy_cfg[] = { + {MDIO_MMD_PMAPMD, LAN887X_TX_AMPLT_1000T1_REG, 0x003f}, + {MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL4, 0x00b8}, + }; + int ret; + + /* (Re)configure the speed/mode dependent T1 settings */ + ret = lan887x_phy_config(phydev, phy_cfg, ARRAY_SIZE(phy_cfg)); + if (ret < 0) + return ret; + + return phy_set_bits_mmd(phydev, MDIO_MMD_PMAPMD, LAN887X_DSP_PMA_CONTROL, + LAN887X_DSP_PMA_CONTROL_LNK_SYNC); +} + +static int lan887x_link_setup(struct phy_device *phydev) +{ + int ret = -EINVAL; + + if (phydev->speed == SPEED_1000) + ret = lan887x_1000M_setup(phydev); + else if (phydev->speed == SPEED_100) + ret = lan887x_100M_setup(phydev); + + return ret; +} + +/* LAN887x Errata: speed configuration changes require soft reset + * and chip soft reset + */ +static int lan887x_phy_reset(struct phy_device *phydev) +{ + int ret, val; + + /* Clear 1000M link sync */ + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_PMAPMD, LAN887X_DSP_PMA_CONTROL, + LAN887X_DSP_PMA_CONTROL_LNK_SYNC); + if (ret < 0) + return ret; + + /* Clear 100M link sync */ + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, LAN887X_REG_REG26, + LAN887X_REG_REG26_HW_INIT_SEQ_EN); + if (ret < 0) + return ret; + + /* Chiptop soft-reset to allow the speed/mode change */ + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, LAN887X_CHIP_SOFT_RST, + LAN887X_CHIP_SOFT_RST_RESET); + if (ret < 0) + return ret; + + /* CL22 soft-reset to let the link re-train */ + ret = phy_modify(phydev, MII_BMCR, BMCR_RESET, BMCR_RESET); + if (ret < 0) + return ret; + + /* Wait for reset complete or timeout if > 10ms */ + return phy_read_poll_timeout(phydev, MII_BMCR, val, !(val & BMCR_RESET), + 5000, 10000, true); +} + +static int lan887x_phy_reconfig(struct phy_device *phydev) +{ + int ret; + + linkmode_zero(phydev->advertising); + + ret = genphy_c45_pma_setup_forced(phydev); + if (ret < 0) + return ret; + + return lan887x_link_setup(phydev); +} + +static int lan887x_config_aneg(struct phy_device *phydev) +{ + int ret; + + /* LAN887x Errata: speed configuration changes require soft reset + * and chip soft reset + */ + ret = lan887x_phy_reset(phydev); + if (ret < 0) + return ret; + + return lan887x_phy_reconfig(phydev); +} + +static int lan887x_probe(struct phy_device *phydev) +{ + struct lan887x_priv *priv; + + priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + phydev->priv = priv; + + return lan887x_phy_setup(phydev); +} + +static u64 lan887x_get_stat(struct phy_device *phydev, int i) +{ + struct lan887x_hw_stat stat = lan887x_hw_stats[i]; + struct lan887x_priv *priv = phydev->priv; + int val; + u64 ret; + + if (stat.mmd) + val = phy_read_mmd(phydev, stat.mmd, stat.reg); + else + val = phy_read(phydev, stat.reg); + + if (val < 0) { + ret = U64_MAX; + } else { + val = val & ((1 << stat.bits) - 1); + priv->stats[i] += val; + ret = priv->stats[i]; + } + + return ret; +} + +static void lan887x_get_stats(struct phy_device *phydev, + struct ethtool_stats *stats, u64 *data) +{ + for (int i = 0; i < ARRAY_SIZE(lan887x_hw_stats); i++) + data[i] = lan887x_get_stat(phydev, i); +} + +static int lan887x_get_sset_count(struct phy_device *phydev) +{ + return ARRAY_SIZE(lan887x_hw_stats); +} + +static void lan887x_get_strings(struct phy_device *phydev, u8 *data) +{ + for (int i = 0; i < ARRAY_SIZE(lan887x_hw_stats); i++) + ethtool_puts(&data, lan887x_hw_stats[i].string); +} + static struct phy_driver microchip_t1_phy_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_LAN87XX), @@ -894,6 +1454,20 @@ static struct phy_driver microchip_t1_phy_driver[] = { .get_sqi_max = lan87xx_get_sqi_max, .cable_test_start = lan87xx_cable_test_start, .cable_test_get_status = lan87xx_cable_test_get_status, + }, + { + PHY_ID_MATCH_MODEL(PHY_ID_LAN887X), + .name = "Microchip LAN887x T1 PHY", + .probe = lan887x_probe, + .get_features = lan887x_get_features, + .config_init = lan887x_phy_init, + .config_aneg = lan887x_config_aneg, + .get_stats = lan887x_get_stats, + .get_sset_count = lan887x_get_sset_count, + .get_strings = lan887x_get_strings, + .suspend = genphy_suspend, + .resume = genphy_resume, + .read_status = genphy_c45_read_status, } }; @@ -902,6 +1476,7 @@ module_phy_driver(microchip_t1_phy_driver); static struct mdio_device_id __maybe_unused microchip_t1_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_LAN87XX) }, { PHY_ID_MATCH_MODEL(PHY_ID_LAN937X) }, + { PHY_ID_MATCH_MODEL(PHY_ID_LAN887X) }, { } }; From ae5a0456e0b4cfd7e61619e55251ffdf1bc7adfb Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 22 Aug 2024 04:10:47 -0700 Subject: [PATCH 346/385] netpoll: Ensure clean state on setup failures Modify netpoll_setup() and __netpoll_setup() to ensure that the netpoll structure (np) is left in a clean state if setup fails for any reason. This prevents carrying over misconfigured fields in case of partial setup success. Key changes: - np->dev is now set only after successful setup, ensuring it's always NULL if netpoll is not configured or if netpoll_setup() fails. - np->local_ip is zeroed if netpoll setup doesn't complete successfully. - Added DEBUG_NET_WARN_ON_ONCE() checks to catch unexpected states. - Reordered some operations in __netpoll_setup() for better logical flow. These changes improve the reliability of netpoll configuration, since it assures that the structure is fully initialized or totally unset. Suggested-by: Paolo Abeni Signed-off-by: Breno Leitao Link: https://patch.msgid.link/20240822111051.179850-2-leitao@debian.org Signed-off-by: Jakub Kicinski --- net/core/netpoll.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index cff1f89719b6d..a1aea86cf98c1 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -624,12 +624,9 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) const struct net_device_ops *ops; int err; - np->dev = ndev; - strscpy(np->dev_name, ndev->name, IFNAMSIZ); - if (ndev->priv_flags & IFF_DISABLE_NETPOLL) { np_err(np, "%s doesn't support polling, aborting\n", - np->dev_name); + ndev->name); err = -ENOTSUPP; goto out; } @@ -647,7 +644,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) refcount_set(&npinfo->refcnt, 1); - ops = np->dev->netdev_ops; + ops = ndev->netdev_ops; if (ops->ndo_netpoll_setup) { err = ops->ndo_netpoll_setup(ndev, npinfo); if (err) @@ -658,6 +655,8 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) refcount_inc(&npinfo->refcnt); } + np->dev = ndev; + strscpy(np->dev_name, ndev->name, IFNAMSIZ); npinfo->netpoll = np; /* last thing to do is link it to the net device structure */ @@ -675,6 +674,7 @@ EXPORT_SYMBOL_GPL(__netpoll_setup); int netpoll_setup(struct netpoll *np) { struct net_device *ndev = NULL; + bool ip_overwritten = false; struct in_device *in_dev; int err; @@ -739,6 +739,7 @@ int netpoll_setup(struct netpoll *np) } np->local_ip.ip = ifa->ifa_local; + ip_overwritten = true; np_info(np, "local IP %pI4\n", &np->local_ip.ip); } else { #if IS_ENABLED(CONFIG_IPV6) @@ -755,6 +756,7 @@ int netpoll_setup(struct netpoll *np) !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL)) continue; np->local_ip.in6 = ifp->addr; + ip_overwritten = true; err = 0; break; } @@ -785,6 +787,9 @@ int netpoll_setup(struct netpoll *np) return 0; put: + DEBUG_NET_WARN_ON_ONCE(np->dev); + if (ip_overwritten) + memset(&np->local_ip, 0, sizeof(np->local_ip)); netdev_put(ndev, &np->dev_tracker); unlock: rtnl_unlock(); From 908ee298c8fb3f9129a470735e8bb8037a95221e Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 22 Aug 2024 04:10:48 -0700 Subject: [PATCH 347/385] net: netconsole: Populate dynamic entry even if netpoll fails Currently, netconsole discards targets that fail during initialization, causing two issues: 1) Inconsistency between target list and configfs entries * user pass cmdline0, cmdline1. If cmdline0 fails, then cmdline1 becomes cmdline0 in configfs. 2) Inability to manage failed targets from userspace * If user pass a target that fails with netpoll (interface not loaded at netcons initialization time, such as interface is a module), then the target will not exist in the configfs, so, user cannot re-enable or modify it from userspace. Failed targets are now added to the target list and configfs, but remain disabled until manually enabled or reconfigured. This change does not change the behaviour if CONFIG_NETCONSOLE_DYNAMIC is not set. CC: Aijay Adams Signed-off-by: Breno Leitao Link: https://patch.msgid.link/20240822111051.179850-3-leitao@debian.org Signed-off-by: Jakub Kicinski --- drivers/net/netconsole.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 72384c1ecc5ce..01cf33fa75036 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -1258,11 +1258,18 @@ static struct netconsole_target *alloc_param_target(char *target_config, goto fail; err = netpoll_setup(&nt->np); - if (err) - goto fail; - + if (err) { + pr_err("Not enabling netconsole for %s%d. Netpoll setup failed\n", + NETCONSOLE_PARAM_TARGET_PREFIX, cmdline_count); + if (!IS_ENABLED(CONFIG_NETCONSOLE_DYNAMIC)) + /* only fail if dynamic reconfiguration is set, + * otherwise, keep the target in the list, but disabled. + */ + goto fail; + } else { + nt->enabled = true; + } populate_configfs_item(nt, cmdline_count); - nt->enabled = true; return nt; From b494b1673889c95ead43fb6978687fb61bb042d5 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 22 Aug 2024 02:56:39 -0700 Subject: [PATCH 348/385] net: netconsole: selftests: Create a new netconsole selftest Adds a selftest that creates two virtual interfaces, assigns one to a new namespace, and assigns IP addresses to both. It listens on the destination interface using socat and configures a dynamic target on netconsole, pointing to the destination IP address. The test then checks if the message was received properly on the destination interface. Signed-off-by: Breno Leitao Acked-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20240822095652.3806208-1-leitao@debian.org Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 + tools/testing/selftests/drivers/net/Makefile | 5 +- tools/testing/selftests/drivers/net/config | 4 + .../selftests/drivers/net/netcons_basic.sh | 234 ++++++++++++++++++ 4 files changed, 243 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/drivers/net/netcons_basic.sh diff --git a/MAINTAINERS b/MAINTAINERS index e4fa9010fcb60..30a9b9450e11d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15775,6 +15775,7 @@ M: Breno Leitao S: Maintained F: Documentation/networking/netconsole.rst F: drivers/net/netconsole.c +F: tools/testing/selftests/drivers/net/netcons_basic.sh NETDEVSIM M: Jakub Kicinski diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index e54f382bcb027..39fb97a8c1df2 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -1,8 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 -TEST_INCLUDES := $(wildcard lib/py/*.py) +TEST_INCLUDES := $(wildcard lib/py/*.py) \ + ../../net/net_helper.sh \ + ../../net/lib.sh \ TEST_PROGS := \ + netcons_basic.sh \ ping.py \ queues.py \ stats.py \ diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config index f6a58ce8a2300..a2d8af60876df 100644 --- a/tools/testing/selftests/drivers/net/config +++ b/tools/testing/selftests/drivers/net/config @@ -1,2 +1,6 @@ CONFIG_IPV6=y CONFIG_NETDEVSIM=m +CONFIG_CONFIGFS_FS=y +CONFIG_NETCONSOLE=m +CONFIG_NETCONSOLE_DYNAMIC=y +CONFIG_NETCONSOLE_EXTENDED_LOG=y diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh new file mode 100755 index 0000000000000..06021b2059b71 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -0,0 +1,234 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# This test creates two netdevsim virtual interfaces, assigns one of them (the +# "destination interface") to a new namespace, and assigns IP addresses to both +# interfaces. +# +# It listens on the destination interface using socat and configures a dynamic +# target on netconsole, pointing to the destination IP address. +# +# Finally, it checks whether the message was received properly on the +# destination interface. Note that this test may pollute the kernel log buffer +# (dmesg) and relies on dynamic configuration and namespaces being configured. +# +# Author: Breno Leitao + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +# Simple script to test dynamic targets in netconsole +SRCIF="" # to be populated later +SRCIP=192.168.1.1 +DSTIF="" # to be populated later +DSTIP=192.168.1.2 + +PORT="6666" +MSG="netconsole selftest" +TARGET=$(mktemp -u netcons_XXXXX) +DEFAULT_PRINTK_VALUES=$(cat /proc/sys/kernel/printk) +NETCONS_CONFIGFS="/sys/kernel/config/netconsole" +NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}" +# NAMESPACE will be populated by setup_ns with a random value +NAMESPACE="" + +# IDs for netdevsim +NSIM_DEV_1_ID=$((256 + RANDOM % 256)) +NSIM_DEV_2_ID=$((512 + RANDOM % 256)) + +# Used to create and delete namespaces +source "${SCRIPTDIR}"/../../net/lib.sh +source "${SCRIPTDIR}"/../../net/net_helper.sh + +# Create netdevsim interfaces +create_ifaces() { + local NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device + + echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW" + echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW" + udevadm settle 2> /dev/null || true + + local NSIM1=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_1_ID" + local NSIM2=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_2_ID" + + # These are global variables + SRCIF=$(find "$NSIM1"/net -maxdepth 1 -type d ! \ + -path "$NSIM1"/net -exec basename {} \;) + DSTIF=$(find "$NSIM2"/net -maxdepth 1 -type d ! \ + -path "$NSIM2"/net -exec basename {} \;) +} + +link_ifaces() { + local NSIM_DEV_SYS_LINK="/sys/bus/netdevsim/link_device" + local SRCIF_IFIDX=$(cat /sys/class/net/"$SRCIF"/ifindex) + local DSTIF_IFIDX=$(cat /sys/class/net/"$DSTIF"/ifindex) + + exec {NAMESPACE_FD} $NSIM_DEV_SYS_LINK + then + echo "linking netdevsim1 with netdevsim2 should succeed" + cleanup + exit "${ksft_skip}" + fi +} + +function configure_ip() { + # Configure the IPs for both interfaces + ip netns exec "${NAMESPACE}" ip addr add "${DSTIP}"/24 dev "${DSTIF}" + ip netns exec "${NAMESPACE}" ip link set "${DSTIF}" up + + ip addr add "${SRCIP}"/24 dev "${SRCIF}" + ip link set "${SRCIF}" up +} + +function set_network() { + # setup_ns function is coming from lib.sh + setup_ns NAMESPACE + + # Create both interfaces, and assign the destination to a different + # namespace + create_ifaces + + # Link both interfaces back to back + link_ifaces + + configure_ip +} + +function create_dynamic_target() { + DSTMAC=$(ip netns exec "${NAMESPACE}" \ + ip link show "${DSTIF}" | awk '/ether/ {print $2}') + + # Create a dynamic target + mkdir "${NETCONS_PATH}" + + echo "${DSTIP}" > "${NETCONS_PATH}"/remote_ip + echo "${SRCIP}" > "${NETCONS_PATH}"/local_ip + echo "${DSTMAC}" > "${NETCONS_PATH}"/remote_mac + echo "${SRCIF}" > "${NETCONS_PATH}"/dev_name + + echo 1 > "${NETCONS_PATH}"/enabled +} + +function cleanup() { + local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device" + + # delete netconsole dynamic reconfiguration + echo 0 > "${NETCONS_PATH}"/enabled + # Remove the configfs entry + rmdir "${NETCONS_PATH}" + + # Delete netdevsim devices + echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_DEL" + echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_DEL" + + # this is coming from lib.sh + cleanup_all_ns + + # Restoring printk configurations + echo "${DEFAULT_PRINTK_VALUES}" > /proc/sys/kernel/printk +} + +function listen_port_and_save_to() { + local OUTPUT=${1} + # Just wait for 2 seconds + timeout 2 ip netns exec "${NAMESPACE}" \ + socat UDP-LISTEN:"${PORT}",fork "${OUTPUT}" +} + +function validate_result() { + local TMPFILENAME="$1" + + # Check if the file exists + if [ ! -f "$TMPFILENAME" ]; then + echo "FAIL: File was not generated." >&2 + exit "${ksft_fail}" + fi + + if ! grep -q "${MSG}" "${TMPFILENAME}"; then + echo "FAIL: ${MSG} not found in ${TMPFILENAME}" >&2 + cat "${TMPFILENAME}" >&2 + exit "${ksft_fail}" + fi + + # Delete the file once it is validated, otherwise keep it + # for debugging purposes + rm "${TMPFILENAME}" + exit "${ksft_pass}" +} + +function check_for_dependencies() { + if [ "$(id -u)" -ne 0 ]; then + echo "This test must be run as root" >&2 + exit "${ksft_skip}" + fi + + if ! which socat > /dev/null ; then + echo "SKIP: socat(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if ! which ip > /dev/null ; then + echo "SKIP: ip(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if ! which udevadm > /dev/null ; then + echo "SKIP: udevadm(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if [ ! -d "${NETCONS_CONFIGFS}" ]; then + echo "SKIP: directory ${NETCONS_CONFIGFS} does not exist. Check if NETCONSOLE_DYNAMIC is enabled" >&2 + exit "${ksft_skip}" + fi + + if ip link show "${DSTIF}" 2> /dev/null; then + echo "SKIP: interface ${DSTIF} exists in the system. Not overwriting it." >&2 + exit "${ksft_skip}" + fi + + if ip addr list | grep -E "inet.*(${SRCIP}|${DSTIP})" 2> /dev/null; then + echo "SKIP: IPs already in use. Skipping it" >&2 + exit "${ksft_skip}" + fi +} + +# ========== # +# Start here # +# ========== # +modprobe netdevsim 2> /dev/null || true +modprobe netconsole 2> /dev/null || true + +# The content of kmsg will be save to the following file +OUTPUT_FILE="/tmp/${TARGET}" + +# Check for basic system dependency and exit if not found +check_for_dependencies +# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) +echo "6 5" > /proc/sys/kernel/printk +# Remove the namespace, interfaces and netconsole target on exit +trap cleanup EXIT +# Create one namespace and two interfaces +set_network +# Create a dynamic target for netconsole +create_dynamic_target +# Listed for netconsole port inside the namespace and destination interface +listen_port_and_save_to "${OUTPUT_FILE}" & +# Wait for socat to start and listen to the port. +wait_local_port_listen "${NAMESPACE}" "${PORT}" udp +# Send the message +echo "${MSG}: ${TARGET}" > /dev/kmsg +# Wait until socat saves the file to disk +busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" + +# Make sure the message was received in the dst part +# and exit +validate_result "${OUTPUT_FILE}" From abcd3026dd63417692a5e80aff70e7cd9b5c14ea Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Thu, 22 Aug 2024 14:07:01 +0200 Subject: [PATCH 349/385] ethtool: Extend cable testing interface with result source information Extend the ethtool netlink cable testing interface by adding support for specifying the source of cable testing results. This allows users to differentiate between results obtained through different diagnostic methods. For example, some TI 10BaseT1L PHYs provide two variants of cable diagnostics: Time Domain Reflectometry (TDR) and Active Link Cable Diagnostic (ALCD). By introducing `ETHTOOL_A_CABLE_RESULT_SRC` and `ETHTOOL_A_CABLE_FAULT_LENGTH_SRC` attributes, this update enables drivers to indicate whether the result was derived from TDR or ALCD, improving the clarity and utility of diagnostic information. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20240822120703.1393130-2-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/ethtool.yaml | 6 ++++++ Documentation/networking/ethtool-netlink.rst | 5 +++++ include/uapi/linux/ethtool_netlink.h | 11 +++++++++++ 3 files changed, 22 insertions(+) diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 37211b1e861fe..6a050d755b9cb 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -667,6 +667,9 @@ attribute-sets: - name: code type: u8 + - + name: src + type: u32 - name: cable-fault-length attributes: @@ -676,6 +679,9 @@ attribute-sets: - name: cm type: u32 + - + name: src + type: u32 - name: cable-nest attributes: diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 44cb9e29f325a..ba90457b8b2db 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1314,12 +1314,17 @@ information. +-+-+-----------------------------------------+--------+---------------------+ | | | ``ETHTOOL_A_CABLE_RESULTS_CODE`` | u8 | result code | +-+-+-----------------------------------------+--------+---------------------+ + | | | ``ETHTOOL_A_CABLE_RESULT_SRC`` | u32 | information source | + +-+-+-----------------------------------------+--------+---------------------+ | | ``ETHTOOL_A_CABLE_NEST_FAULT_LENGTH`` | nested | cable length | +-+-+-----------------------------------------+--------+---------------------+ | | | ``ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR`` | u8 | pair number | +-+-+-----------------------------------------+--------+---------------------+ | | | ``ETHTOOL_A_CABLE_FAULT_LENGTH_CM`` | u32 | length in cm | +-+-+-----------------------------------------+--------+---------------------+ + | | | ``ETHTOOL_A_CABLE_FAULT_LENGTH_SRC`` | u32 | information source | + +-+-+-----------------------------------------+--------+---------------------+ + CABLE_TEST TDR ============== diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 45d8bcdea056e..283305f6b0635 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -573,10 +573,20 @@ enum { ETHTOOL_A_CABLE_PAIR_D, }; +/* Information source for specific results. */ +enum { + ETHTOOL_A_CABLE_INF_SRC_UNSPEC, + /* Results provided by the Time Domain Reflectometry (TDR) */ + ETHTOOL_A_CABLE_INF_SRC_TDR, + /* Results provided by the Active Link Cable Diagnostic (ALCD) */ + ETHTOOL_A_CABLE_INF_SRC_ALCD, +}; + enum { ETHTOOL_A_CABLE_RESULT_UNSPEC, ETHTOOL_A_CABLE_RESULT_PAIR, /* u8 ETHTOOL_A_CABLE_PAIR_ */ ETHTOOL_A_CABLE_RESULT_CODE, /* u8 ETHTOOL_A_CABLE_RESULT_CODE_ */ + ETHTOOL_A_CABLE_RESULT_SRC, /* u32 ETHTOOL_A_CABLE_INF_SRC_ */ __ETHTOOL_A_CABLE_RESULT_CNT, ETHTOOL_A_CABLE_RESULT_MAX = (__ETHTOOL_A_CABLE_RESULT_CNT - 1) @@ -586,6 +596,7 @@ enum { ETHTOOL_A_CABLE_FAULT_LENGTH_UNSPEC, ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR, /* u8 ETHTOOL_A_CABLE_PAIR_ */ ETHTOOL_A_CABLE_FAULT_LENGTH_CM, /* u32 */ + ETHTOOL_A_CABLE_FAULT_LENGTH_SRC, /* u32 ETHTOOL_A_CABLE_INF_SRC_ */ __ETHTOOL_A_CABLE_FAULT_LENGTH_CNT, ETHTOOL_A_CABLE_FAULT_LENGTH_MAX = (__ETHTOOL_A_CABLE_FAULT_LENGTH_CNT - 1) From 4715d87e11ac805ab95a75adfbf93d67dfbdbe81 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Thu, 22 Aug 2024 14:07:02 +0200 Subject: [PATCH 350/385] ethtool: Add support for specifying information source in cable test results Enhance the ethtool cable test interface by introducing the ability to specify the source of the diagnostic information for cable test results. This is particularly useful for PHYs that offer multiple diagnostic methods, such as Time Domain Reflectometry (TDR) and Active Link Cable Diagnostic (ALCD). Key changes: - Added `ethnl_cable_test_result_with_src` and `ethnl_cable_test_fault_length_with_src` functions to allow specifying the information source when reporting cable test results. - Updated existing `ethnl_cable_test_result` and `ethnl_cable_test_fault_length` functions to use TDR as the default source, ensuring backward compatibility. - Modified the UAPI to support these new attributes, enabling drivers to provide more detailed diagnostic information. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20240822120703.1393130-3-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- include/linux/ethtool_netlink.h | 29 +++++++++++++++++++++++------ net/ethtool/cabletest.c | 19 +++++++++++++++---- 2 files changed, 38 insertions(+), 10 deletions(-) diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index fae0dfb9a9c82..aba91335273af 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -23,8 +23,10 @@ struct phy_device; int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd); void ethnl_cable_test_free(struct phy_device *phydev); void ethnl_cable_test_finished(struct phy_device *phydev); -int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result); -int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm); +int ethnl_cable_test_result_with_src(struct phy_device *phydev, u8 pair, + u8 result, u32 src); +int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, u8 pair, + u32 cm, u32 src); int ethnl_cable_test_amplitude(struct phy_device *phydev, u8 pair, s16 mV); int ethnl_cable_test_pulse(struct phy_device *phydev, u16 mV); int ethnl_cable_test_step(struct phy_device *phydev, u32 first, u32 last, @@ -54,14 +56,14 @@ static inline void ethnl_cable_test_free(struct phy_device *phydev) static inline void ethnl_cable_test_finished(struct phy_device *phydev) { } -static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, - u8 result) +static inline int ethnl_cable_test_result_with_src(struct phy_device *phydev, + u8 pair, u8 result, u32 src) { return -EOPNOTSUPP; } -static inline int ethnl_cable_test_fault_length(struct phy_device *phydev, - u8 pair, u32 cm) +static inline int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, + u8 pair, u32 cm, u32 src) { return -EOPNOTSUPP; } @@ -119,4 +121,19 @@ static inline bool ethtool_dev_mm_supported(struct net_device *dev) } #endif /* IS_ENABLED(CONFIG_ETHTOOL_NETLINK) */ + +static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, + u8 result) +{ + return ethnl_cable_test_result_with_src(phydev, pair, result, + ETHTOOL_A_CABLE_INF_SRC_TDR); +} + +static inline int ethnl_cable_test_fault_length(struct phy_device *phydev, + u8 pair, u32 cm) +{ + return ethnl_cable_test_fault_length_with_src(phydev, pair, cm, + ETHTOOL_A_CABLE_INF_SRC_TDR); +} + #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c index 01db8f394869f..ff2fe3566ace0 100644 --- a/net/ethtool/cabletest.c +++ b/net/ethtool/cabletest.c @@ -164,7 +164,8 @@ void ethnl_cable_test_finished(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(ethnl_cable_test_finished); -int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result) +int ethnl_cable_test_result_with_src(struct phy_device *phydev, u8 pair, + u8 result, u32 src) { struct nlattr *nest; int ret = -EMSGSIZE; @@ -177,6 +178,10 @@ int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result) goto err; if (nla_put_u8(phydev->skb, ETHTOOL_A_CABLE_RESULT_CODE, result)) goto err; + if (src != ETHTOOL_A_CABLE_INF_SRC_UNSPEC) { + if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_RESULT_SRC, src)) + goto err; + } nla_nest_end(phydev->skb, nest); return 0; @@ -185,9 +190,10 @@ int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result) nla_nest_cancel(phydev->skb, nest); return ret; } -EXPORT_SYMBOL_GPL(ethnl_cable_test_result); +EXPORT_SYMBOL_GPL(ethnl_cable_test_result_with_src); -int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm) +int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, u8 pair, + u32 cm, u32 src) { struct nlattr *nest; int ret = -EMSGSIZE; @@ -201,6 +207,11 @@ int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm) goto err; if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_FAULT_LENGTH_CM, cm)) goto err; + if (src != ETHTOOL_A_CABLE_INF_SRC_UNSPEC) { + if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_FAULT_LENGTH_SRC, + src)) + goto err; + } nla_nest_end(phydev->skb, nest); return 0; @@ -209,7 +220,7 @@ int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm) nla_nest_cancel(phydev->skb, nest); return ret; } -EXPORT_SYMBOL_GPL(ethnl_cable_test_fault_length); +EXPORT_SYMBOL_GPL(ethnl_cable_test_fault_length_with_src); static const struct nla_policy cable_test_tdr_act_cfg_policy[] = { [ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST] = { .type = NLA_U32 }, From 986a7fa4b454c9ee338a133868b8ed740cd45edd Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Thu, 22 Aug 2024 14:07:03 +0200 Subject: [PATCH 351/385] phy: dp83td510: Utilize ALCD for cable length measurement when link is active In industrial environments where 10BaseT1L PHYs are replacing existing field bus systems like CAN, it's often essential to retain the existing cable infrastructure. After installation, collecting metrics such as cable length is crucial for assessing the quality of the infrastructure. Traditionally, TDR (Time Domain Reflectometry) is used for this purpose. However, TDR requires interrupting the link, and if the link partner remains active, the TDR measurement will fail. Unlike multi-pair systems, where TDR can be attempted during the MDI-X switching window, 10BaseT1L systems face greater challenges. The TDR sequence on 10BaseT1L is longer and coincides with uninterrupted autonegotiation pulses, making TDR impossible when the link partner is active. The DP83TD510 PHY provides an alternative through ALCD (Active Link Cable Diagnostics), which allows for cable length measurement without disrupting an active link. Since a live link indicates no short or open cable states, ALCD can be used effectively to gather cable length information. Enhance the dp83td510 driver by: - Leveraging ALCD to measure cable length when the link is active. - Bypassing TDR when a link is detected, as ALCD provides the required information without disruption. Signed-off-by: Oleksij Rempel Reviewed-by: Andrew Lunn Link: https://patch.msgid.link/20240822120703.1393130-4-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/phy/dp83td510.c | 119 ++++++++++++++++++++++++++++++++++-- 1 file changed, 113 insertions(+), 6 deletions(-) diff --git a/drivers/net/phy/dp83td510.c b/drivers/net/phy/dp83td510.c index 551e37786c2da..92aa3a2b9744c 100644 --- a/drivers/net/phy/dp83td510.c +++ b/drivers/net/phy/dp83td510.c @@ -58,6 +58,10 @@ static const u16 dp83td510_mse_sqi_map[] = { 0x0000 /* 24dB =< SNR */ }; +struct dp83td510_priv { + bool alcd_test_active; +}; + /* Time Domain Reflectometry (TDR) Functionality of DP83TD510 PHY * * I assume that this PHY is using a variation of Spread Spectrum Time Domain @@ -169,6 +173,10 @@ static const u16 dp83td510_mse_sqi_map[] = { #define DP83TD510E_UNKN_030E 0x30e #define DP83TD510E_030E_VAL 0x2520 +#define DP83TD510E_ALCD_STAT 0xa9f +#define DP83TD510E_ALCD_COMPLETE BIT(15) +#define DP83TD510E_ALCD_CABLE_LENGTH GENMASK(10, 0) + static int dp83td510_config_intr(struct phy_device *phydev) { int ret; @@ -325,8 +333,23 @@ static int dp83td510_get_sqi_max(struct phy_device *phydev) */ static int dp83td510_cable_test_start(struct phy_device *phydev) { + struct dp83td510_priv *priv = phydev->priv; int ret; + /* If link partner is active, we won't be able to use TDR, since + * we can't force link partner to be silent. The autonegotiation + * pulses will be too frequent and the TDR sequence will be + * too long. So, TDR will always fail. Since the link is established + * we already know that the cable is working, so we can get some + * extra information line the cable length using ALCD. + */ + if (phydev->link) { + priv->alcd_test_active = true; + return 0; + } + + priv->alcd_test_active = false; + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_CTRL, DP83TD510E_CTRL_HW_RESET); if (ret) @@ -402,8 +425,8 @@ static int dp83td510_cable_test_start(struct phy_device *phydev) } /** - * dp83td510_cable_test_get_status - Get the status of the cable test for the - * DP83TD510 PHY. + * dp83td510_cable_test_get_tdr_status - Get the status of the TDR test for the + * DP83TD510 PHY. * @phydev: Pointer to the phy_device structure. * @finished: Pointer to a boolean that indicates whether the test is finished. * @@ -411,13 +434,11 @@ static int dp83td510_cable_test_start(struct phy_device *phydev) * * Returns: 0 on success or a negative error code on failure. */ -static int dp83td510_cable_test_get_status(struct phy_device *phydev, - bool *finished) +static int dp83td510_cable_test_get_tdr_status(struct phy_device *phydev, + bool *finished) { int ret, stat; - *finished = false; - ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_TDR_CFG); if (ret < 0) return ret; @@ -459,6 +480,77 @@ static int dp83td510_cable_test_get_status(struct phy_device *phydev, return phy_init_hw(phydev); } +/** + * dp83td510_cable_test_get_alcd_status - Get the status of the ALCD test for the + * DP83TD510 PHY. + * @phydev: Pointer to the phy_device structure. + * @finished: Pointer to a boolean that indicates whether the test is finished. + * + * The function sets the @finished flag to true if the test is complete. + * The function reads the cable length and reports it to the user. + * + * Returns: 0 on success or a negative error code on failure. + */ +static int dp83td510_cable_test_get_alcd_status(struct phy_device *phydev, + bool *finished) +{ + unsigned int location; + int ret, phy_sts; + + phy_sts = phy_read(phydev, DP83TD510E_PHY_STS); + + if (!(phy_sts & DP83TD510E_LINK_STATUS)) { + /* If the link is down, we can't do any thing usable now */ + ethnl_cable_test_result_with_src(phydev, ETHTOOL_A_CABLE_PAIR_A, + ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC, + ETHTOOL_A_CABLE_INF_SRC_ALCD); + *finished = true; + return 0; + } + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_ALCD_STAT); + if (ret < 0) + return ret; + + if (!(ret & DP83TD510E_ALCD_COMPLETE)) + return 0; + + location = FIELD_GET(DP83TD510E_ALCD_CABLE_LENGTH, ret) * 100; + + ethnl_cable_test_fault_length_with_src(phydev, ETHTOOL_A_CABLE_PAIR_A, + location, + ETHTOOL_A_CABLE_INF_SRC_ALCD); + + ethnl_cable_test_result_with_src(phydev, ETHTOOL_A_CABLE_PAIR_A, + ETHTOOL_A_CABLE_RESULT_CODE_OK, + ETHTOOL_A_CABLE_INF_SRC_ALCD); + *finished = true; + + return 0; +} + +/** + * dp83td510_cable_test_get_status - Get the status of the cable test for the + * DP83TD510 PHY. + * @phydev: Pointer to the phy_device structure. + * @finished: Pointer to a boolean that indicates whether the test is finished. + * + * The function sets the @finished flag to true if the test is complete. + * + * Returns: 0 on success or a negative error code on failure. + */ +static int dp83td510_cable_test_get_status(struct phy_device *phydev, + bool *finished) +{ + struct dp83td510_priv *priv = phydev->priv; + *finished = false; + + if (priv->alcd_test_active) + return dp83td510_cable_test_get_alcd_status(phydev, finished); + + return dp83td510_cable_test_get_tdr_status(phydev, finished); +} + static int dp83td510_get_features(struct phy_device *phydev) { /* This PHY can't respond on MDIO bus if no RMII clock is enabled. @@ -477,12 +569,27 @@ static int dp83td510_get_features(struct phy_device *phydev) return 0; } +static int dp83td510_probe(struct phy_device *phydev) +{ + struct device *dev = &phydev->mdio.dev; + struct dp83td510_priv *priv; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + phydev->priv = priv; + + return 0; +} + static struct phy_driver dp83td510_driver[] = { { PHY_ID_MATCH_MODEL(DP83TD510E_PHY_ID), .name = "TI DP83TD510E", .flags = PHY_POLL_CABLE_TEST, + .probe = dp83td510_probe, .config_aneg = dp83td510_config_aneg, .read_status = dp83td510_read_status, .get_features = dp83td510_get_features, From be91edc81b09ca062e39db894561d25447235c68 Mon Sep 17 00:00:00 2001 From: MD Danish Anwar Date: Thu, 22 Aug 2024 17:56:51 +0530 Subject: [PATCH 352/385] dt-bindings: soc: ti: pruss: Add documentation for PA_STATS support Add documentation for pa-stats node which is syscon regmap for PA_STATS registers. This will be used to dump statistics maintained by ICSSG firmware. Reviewed-by: Krzysztof Kozlowski Reviewed-by: Roger Quadros Acked-by: Nishanth Menon Signed-off-by: MD Danish Anwar Link: https://patch.msgid.link/20240822122652.1071801-2-danishanwar@ti.com Signed-off-by: Jakub Kicinski --- .../devicetree/bindings/soc/ti/ti,pruss.yaml | 20 +++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml b/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml index c402cb2928e89..3cb1471cc6b62 100644 --- a/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml +++ b/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml @@ -278,6 +278,26 @@ patternProperties: additionalProperties: false + ^pa-stats@[a-f0-9]+$: + description: | + PA-STATS sub-module represented as a SysCon. PA_STATS is a set of + registers where different statistics related to ICSSG, are dumped by + ICSSG firmware. This syscon sub-module will help the device to + access/read/write those statistics. + + type: object + + additionalProperties: false + + properties: + compatible: + items: + - const: ti,pruss-pa-st + - const: syscon + + reg: + maxItems: 1 + interrupt-controller@[a-f0-9]+$: description: | PRUSS INTC Node. Each PRUSS has a single interrupt controller instance From 550ee90ac61c1f0cd987c68a9ac6c4c9833925d7 Mon Sep 17 00:00:00 2001 From: MD Danish Anwar Date: Thu, 22 Aug 2024 17:56:52 +0530 Subject: [PATCH 353/385] net: ti: icssg-prueth: Add support for PA Stats Add support for dumping PA stats registers via ethtool. Firmware maintained stats are stored at PA Stats registers. Also modify emac_get_strings() API to use ethtool_puts(). This commit also maintains consistency between miig_stats and pa_stats by - renaming the array icssg_all_stats to icssg_all_miig_stats - renaming the structure icssg_stats to icssg_miig_stats - renaming ICSSG_STATS() to ICSSG_MIIG_STATS() - changing order of stats related data structures and arrays so that data structures of a certain stats type is clubbed together. Signed-off-by: MD Danish Anwar Link: https://patch.msgid.link/20240822122652.1071801-3-danishanwar@ti.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ti/icssg/icssg_ethtool.c | 19 ++- drivers/net/ethernet/ti/icssg/icssg_prueth.c | 6 + drivers/net/ethernet/ti/icssg/icssg_prueth.h | 9 +- drivers/net/ethernet/ti/icssg/icssg_stats.c | 31 +++- drivers/net/ethernet/ti/icssg/icssg_stats.h | 158 +++++++++++------- 5 files changed, 140 insertions(+), 83 deletions(-) diff --git a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c index 5688f054cec5f..5073ec1958541 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c +++ b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c @@ -83,13 +83,11 @@ static void emac_get_strings(struct net_device *ndev, u32 stringset, u8 *data) switch (stringset) { case ETH_SS_STATS: - for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++) { - if (!icssg_all_stats[i].standard_stats) { - memcpy(p, icssg_all_stats[i].name, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } - } + for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) + if (!icssg_all_miig_stats[i].standard_stats) + ethtool_puts(&p, icssg_all_miig_stats[i].name); + for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) + ethtool_puts(&p, icssg_all_pa_stats[i].name); break; default: break; @@ -104,9 +102,12 @@ static void emac_get_ethtool_stats(struct net_device *ndev, emac_update_hardware_stats(emac); - for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++) - if (!icssg_all_stats[i].standard_stats) + for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) + if (!icssg_all_miig_stats[i].standard_stats) *(data++) = emac->stats[i]; + + for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) + *(data++) = emac->pa_stats[i]; } static int emac_get_ts_info(struct net_device *ndev, diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 53a3e44b99a20..f623a0f603fc7 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -1182,6 +1182,12 @@ static int prueth_probe(struct platform_device *pdev) return -ENODEV; } + prueth->pa_stats = syscon_regmap_lookup_by_phandle(np, "ti,pa-stats"); + if (IS_ERR(prueth->pa_stats)) { + dev_err(dev, "couldn't get ti,pa-stats syscon regmap\n"); + return -ENODEV; + } + if (eth0_node) { ret = prueth_get_cores(prueth, ICSS_SLICE0, false); if (ret) diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index f678d656a3ed3..786bd1ba34ab3 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -50,8 +50,10 @@ #define ICSSG_MAX_RFLOWS 8 /* per slice */ +#define ICSSG_NUM_PA_STATS 4 +#define ICSSG_NUM_MIIG_STATS 60 /* Number of ICSSG related stats */ -#define ICSSG_NUM_STATS 60 +#define ICSSG_NUM_STATS (ICSSG_NUM_MIIG_STATS + ICSSG_NUM_PA_STATS) #define ICSSG_NUM_STANDARD_STATS 31 #define ICSSG_NUM_ETHTOOL_STATS (ICSSG_NUM_STATS - ICSSG_NUM_STANDARD_STATS) @@ -190,7 +192,8 @@ struct prueth_emac { int port_vlan; struct delayed_work stats_work; - u64 stats[ICSSG_NUM_STATS]; + u64 stats[ICSSG_NUM_MIIG_STATS]; + u64 pa_stats[ICSSG_NUM_PA_STATS]; /* RX IRQ Coalescing Related */ struct hrtimer rx_hrtimer; @@ -230,6 +233,7 @@ struct icssg_firmwares { * @registered_netdevs: list of registered netdevs * @miig_rt: regmap to mii_g_rt block * @mii_rt: regmap to mii_rt block + * @pa_stats: regmap to pa_stats block * @pru_id: ID for each of the PRUs * @pdev: pointer to ICSSG platform device * @pdata: pointer to platform data for ICSSG driver @@ -263,6 +267,7 @@ struct prueth { struct net_device *registered_netdevs[PRUETH_NUM_MACS]; struct regmap *miig_rt; struct regmap *mii_rt; + struct regmap *pa_stats; enum pruss_pru_id pru_id[PRUSS_NUM_PRUS]; struct platform_device *pdev; diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.c b/drivers/net/ethernet/ti/icssg/icssg_stats.c index 2fb150c13078b..06a15c0b2accc 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_stats.c +++ b/drivers/net/ethernet/ti/icssg/icssg_stats.c @@ -11,6 +11,7 @@ #define ICSSG_TX_PACKET_OFFSET 0xA0 #define ICSSG_TX_BYTE_OFFSET 0xEC +#define ICSSG_FW_STATS_BASE 0x0248 static u32 stats_base[] = { 0x54c, /* Slice 0 stats start */ 0xb18, /* Slice 1 stats start */ @@ -22,24 +23,31 @@ void emac_update_hardware_stats(struct prueth_emac *emac) int slice = prueth_emac_slice(emac); u32 base = stats_base[slice]; u32 tx_pkt_cnt = 0; - u32 val; + u32 val, reg; int i; - for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++) { + for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) { regmap_read(prueth->miig_rt, - base + icssg_all_stats[i].offset, + base + icssg_all_miig_stats[i].offset, &val); regmap_write(prueth->miig_rt, - base + icssg_all_stats[i].offset, + base + icssg_all_miig_stats[i].offset, val); - if (icssg_all_stats[i].offset == ICSSG_TX_PACKET_OFFSET) + if (icssg_all_miig_stats[i].offset == ICSSG_TX_PACKET_OFFSET) tx_pkt_cnt = val; emac->stats[i] += val; - if (icssg_all_stats[i].offset == ICSSG_TX_BYTE_OFFSET) + if (icssg_all_miig_stats[i].offset == ICSSG_TX_BYTE_OFFSET) emac->stats[i] -= tx_pkt_cnt * 8; } + + for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) { + reg = ICSSG_FW_STATS_BASE + icssg_all_pa_stats[i].offset * + PRUETH_NUM_MACS + slice * sizeof(u32); + regmap_read(prueth->pa_stats, reg, &val); + emac->pa_stats[i] += val; + } } void icssg_stats_work_handler(struct work_struct *work) @@ -57,9 +65,14 @@ int emac_get_stat_by_name(struct prueth_emac *emac, char *stat_name) { int i; - for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++) { - if (!strcmp(icssg_all_stats[i].name, stat_name)) - return emac->stats[icssg_all_stats[i].offset / sizeof(u32)]; + for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) { + if (!strcmp(icssg_all_miig_stats[i].name, stat_name)) + return emac->stats[icssg_all_miig_stats[i].offset / sizeof(u32)]; + } + + for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) { + if (!strcmp(icssg_all_pa_stats[i].name, stat_name)) + return emac->pa_stats[icssg_all_pa_stats[i].offset / sizeof(u32)]; } netdev_err(emac->ndev, "Invalid stats %s\n", stat_name); diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.h b/drivers/net/ethernet/ti/icssg/icssg_stats.h index 999a4a91276c3..e88b919f532cd 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_stats.h +++ b/drivers/net/ethernet/ti/icssg/icssg_stats.h @@ -77,82 +77,114 @@ struct miig_stats_regs { u32 tx_bytes; }; -#define ICSSG_STATS(field, stats_type) \ +#define ICSSG_MIIG_STATS(field, stats_type) \ { \ #field, \ offsetof(struct miig_stats_regs, field), \ stats_type \ } -struct icssg_stats { +struct icssg_miig_stats { char name[ETH_GSTRING_LEN]; u32 offset; bool standard_stats; }; -static const struct icssg_stats icssg_all_stats[] = { +static const struct icssg_miig_stats icssg_all_miig_stats[] = { /* Rx */ - ICSSG_STATS(rx_packets, true), - ICSSG_STATS(rx_broadcast_frames, false), - ICSSG_STATS(rx_multicast_frames, true), - ICSSG_STATS(rx_crc_errors, true), - ICSSG_STATS(rx_mii_error_frames, false), - ICSSG_STATS(rx_odd_nibble_frames, false), - ICSSG_STATS(rx_frame_max_size, true), - ICSSG_STATS(rx_max_size_error_frames, false), - ICSSG_STATS(rx_frame_min_size, true), - ICSSG_STATS(rx_min_size_error_frames, false), - ICSSG_STATS(rx_over_errors, true), - ICSSG_STATS(rx_class0_hits, false), - ICSSG_STATS(rx_class1_hits, false), - ICSSG_STATS(rx_class2_hits, false), - ICSSG_STATS(rx_class3_hits, false), - ICSSG_STATS(rx_class4_hits, false), - ICSSG_STATS(rx_class5_hits, false), - ICSSG_STATS(rx_class6_hits, false), - ICSSG_STATS(rx_class7_hits, false), - ICSSG_STATS(rx_class8_hits, false), - ICSSG_STATS(rx_class9_hits, false), - ICSSG_STATS(rx_class10_hits, false), - ICSSG_STATS(rx_class11_hits, false), - ICSSG_STATS(rx_class12_hits, false), - ICSSG_STATS(rx_class13_hits, false), - ICSSG_STATS(rx_class14_hits, false), - ICSSG_STATS(rx_class15_hits, false), - ICSSG_STATS(rx_smd_frags, false), - ICSSG_STATS(rx_bucket1_size, true), - ICSSG_STATS(rx_bucket2_size, true), - ICSSG_STATS(rx_bucket3_size, true), - ICSSG_STATS(rx_bucket4_size, true), - ICSSG_STATS(rx_64B_frames, true), - ICSSG_STATS(rx_bucket1_frames, true), - ICSSG_STATS(rx_bucket2_frames, true), - ICSSG_STATS(rx_bucket3_frames, true), - ICSSG_STATS(rx_bucket4_frames, true), - ICSSG_STATS(rx_bucket5_frames, true), - ICSSG_STATS(rx_bytes, true), - ICSSG_STATS(rx_tx_total_bytes, false), + ICSSG_MIIG_STATS(rx_packets, true), + ICSSG_MIIG_STATS(rx_broadcast_frames, false), + ICSSG_MIIG_STATS(rx_multicast_frames, true), + ICSSG_MIIG_STATS(rx_crc_errors, true), + ICSSG_MIIG_STATS(rx_mii_error_frames, false), + ICSSG_MIIG_STATS(rx_odd_nibble_frames, false), + ICSSG_MIIG_STATS(rx_frame_max_size, true), + ICSSG_MIIG_STATS(rx_max_size_error_frames, false), + ICSSG_MIIG_STATS(rx_frame_min_size, true), + ICSSG_MIIG_STATS(rx_min_size_error_frames, false), + ICSSG_MIIG_STATS(rx_over_errors, true), + ICSSG_MIIG_STATS(rx_class0_hits, false), + ICSSG_MIIG_STATS(rx_class1_hits, false), + ICSSG_MIIG_STATS(rx_class2_hits, false), + ICSSG_MIIG_STATS(rx_class3_hits, false), + ICSSG_MIIG_STATS(rx_class4_hits, false), + ICSSG_MIIG_STATS(rx_class5_hits, false), + ICSSG_MIIG_STATS(rx_class6_hits, false), + ICSSG_MIIG_STATS(rx_class7_hits, false), + ICSSG_MIIG_STATS(rx_class8_hits, false), + ICSSG_MIIG_STATS(rx_class9_hits, false), + ICSSG_MIIG_STATS(rx_class10_hits, false), + ICSSG_MIIG_STATS(rx_class11_hits, false), + ICSSG_MIIG_STATS(rx_class12_hits, false), + ICSSG_MIIG_STATS(rx_class13_hits, false), + ICSSG_MIIG_STATS(rx_class14_hits, false), + ICSSG_MIIG_STATS(rx_class15_hits, false), + ICSSG_MIIG_STATS(rx_smd_frags, false), + ICSSG_MIIG_STATS(rx_bucket1_size, true), + ICSSG_MIIG_STATS(rx_bucket2_size, true), + ICSSG_MIIG_STATS(rx_bucket3_size, true), + ICSSG_MIIG_STATS(rx_bucket4_size, true), + ICSSG_MIIG_STATS(rx_64B_frames, true), + ICSSG_MIIG_STATS(rx_bucket1_frames, true), + ICSSG_MIIG_STATS(rx_bucket2_frames, true), + ICSSG_MIIG_STATS(rx_bucket3_frames, true), + ICSSG_MIIG_STATS(rx_bucket4_frames, true), + ICSSG_MIIG_STATS(rx_bucket5_frames, true), + ICSSG_MIIG_STATS(rx_bytes, true), + ICSSG_MIIG_STATS(rx_tx_total_bytes, false), /* Tx */ - ICSSG_STATS(tx_packets, true), - ICSSG_STATS(tx_broadcast_frames, false), - ICSSG_STATS(tx_multicast_frames, false), - ICSSG_STATS(tx_odd_nibble_frames, false), - ICSSG_STATS(tx_underflow_errors, false), - ICSSG_STATS(tx_frame_max_size, true), - ICSSG_STATS(tx_max_size_error_frames, false), - ICSSG_STATS(tx_frame_min_size, true), - ICSSG_STATS(tx_min_size_error_frames, false), - ICSSG_STATS(tx_bucket1_size, true), - ICSSG_STATS(tx_bucket2_size, true), - ICSSG_STATS(tx_bucket3_size, true), - ICSSG_STATS(tx_bucket4_size, true), - ICSSG_STATS(tx_64B_frames, true), - ICSSG_STATS(tx_bucket1_frames, true), - ICSSG_STATS(tx_bucket2_frames, true), - ICSSG_STATS(tx_bucket3_frames, true), - ICSSG_STATS(tx_bucket4_frames, true), - ICSSG_STATS(tx_bucket5_frames, true), - ICSSG_STATS(tx_bytes, true), + ICSSG_MIIG_STATS(tx_packets, true), + ICSSG_MIIG_STATS(tx_broadcast_frames, false), + ICSSG_MIIG_STATS(tx_multicast_frames, false), + ICSSG_MIIG_STATS(tx_odd_nibble_frames, false), + ICSSG_MIIG_STATS(tx_underflow_errors, false), + ICSSG_MIIG_STATS(tx_frame_max_size, true), + ICSSG_MIIG_STATS(tx_max_size_error_frames, false), + ICSSG_MIIG_STATS(tx_frame_min_size, true), + ICSSG_MIIG_STATS(tx_min_size_error_frames, false), + ICSSG_MIIG_STATS(tx_bucket1_size, true), + ICSSG_MIIG_STATS(tx_bucket2_size, true), + ICSSG_MIIG_STATS(tx_bucket3_size, true), + ICSSG_MIIG_STATS(tx_bucket4_size, true), + ICSSG_MIIG_STATS(tx_64B_frames, true), + ICSSG_MIIG_STATS(tx_bucket1_frames, true), + ICSSG_MIIG_STATS(tx_bucket2_frames, true), + ICSSG_MIIG_STATS(tx_bucket3_frames, true), + ICSSG_MIIG_STATS(tx_bucket4_frames, true), + ICSSG_MIIG_STATS(tx_bucket5_frames, true), + ICSSG_MIIG_STATS(tx_bytes, true), +}; + +/** + * struct pa_stats_regs - ICSSG Firmware maintained PA Stats register + * @fw_rx_cnt: Number of valid packets sent by Rx PRU to Host on PSI + * @fw_tx_cnt: Number of valid packets copied by RTU0 to Tx queues + * @fw_tx_pre_overflow: Host Egress Q (Pre-emptible) Overflow Counter + * @fw_tx_exp_overflow: Host Egress Q (Express) Overflow Counter + */ +struct pa_stats_regs { + u32 fw_rx_cnt; + u32 fw_tx_cnt; + u32 fw_tx_pre_overflow; + u32 fw_tx_exp_overflow; +}; + +#define ICSSG_PA_STATS(field) \ +{ \ + #field, \ + offsetof(struct pa_stats_regs, field), \ +} + +struct icssg_pa_stats { + char name[ETH_GSTRING_LEN]; + u32 offset; +}; + +static const struct icssg_pa_stats icssg_all_pa_stats[] = { + ICSSG_PA_STATS(fw_rx_cnt), + ICSSG_PA_STATS(fw_tx_cnt), + ICSSG_PA_STATS(fw_tx_pre_overflow), + ICSSG_PA_STATS(fw_tx_exp_overflow), }; #endif /* __NET_TI_ICSSG_STATS_H */ From d24dac8eb8111c401b0de40a17760a0a254bcffc Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:22 +0100 Subject: [PATCH 354/385] packet: Correct spelling in if_packet.h Correct spelling in if_packet.h As reported by codespell. Signed-off-by: Simon Horman Acked-by: Willem de Bruijn Link: https://patch.msgid.link/20240822-net-spell-v1-1-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_packet.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index 9efc42382fdb9..1d2718dd96472 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -230,8 +230,8 @@ struct tpacket_hdr_v1 { * ts_first_pkt: * Is always the time-stamp when the block was opened. * Case a) ZERO packets - * No packets to deal with but atleast you know the - * time-interval of this block. + * No packets to deal with but at least you know + * the time-interval of this block. * Case b) Non-zero packets * Use the ts of the first packet in the block. * @@ -265,7 +265,8 @@ enum tpacket_versions { - struct tpacket_hdr - pad to TPACKET_ALIGNMENT=16 - struct sockaddr_ll - - Gap, chosen so that packet data (Start+tp_net) alignes to TPACKET_ALIGNMENT=16 + - Gap, chosen so that packet data (Start+tp_net) aligns to + TPACKET_ALIGNMENT=16 - Start+tp_mac: [ Optional MAC header ] - Start+tp_net: Packet data, aligned to TPACKET_ALIGNMENT=16. - Pad to align to TPACKET_ALIGNMENT=16 From c3494460324832ba03ab8f640a0a5e52283b1b15 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:23 +0100 Subject: [PATCH 355/385] s390/iucv: Correct spelling in iucv.h Correct spelling in iucv.h As reported by codespell. Cc: Alexandra Winter Cc: Thorsten Winkler Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240822-net-spell-v1-2-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- include/net/iucv/iucv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h index 4d114e6d6d23d..dd9e93c122602 100644 --- a/include/net/iucv/iucv.h +++ b/include/net/iucv/iucv.h @@ -15,7 +15,7 @@ * To explore any of the IUCV functions, one must first register their * program using iucv_register(). Once your program has successfully * completed a register, it can exploit the other functions. - * For furthur reference on all IUCV functionality, refer to the + * For further reference on all IUCV functionality, refer to the * CP Programming Services book, also available on the web thru * www.vm.ibm.com/pubs, manual # SC24-6084 * From d0193b167f2756de2f8be4d44186294bfacaaafc Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:24 +0100 Subject: [PATCH 356/385] ip_tunnel: Correct spelling in ip_tunnels.h Correct spelling in ip_tunnels.h As reported by codespell. Cc: David Ahern Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240822-net-spell-v1-3-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- include/net/ip_tunnels.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 1db2417b8ff52..6194fbb564c68 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -573,7 +573,7 @@ static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph, return 0; } -/* Propogate ECN bits out */ +/* Propagate ECN bits out */ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, const struct sk_buff *skb) { From 507285b7f9b2bc90f093fa335d43f2a21a2dbef9 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:25 +0100 Subject: [PATCH 357/385] ipv6: Correct spelling in ipv6.h Correct spelling in ip_tunnels.h As reported by codespell. Cc: David Ahern Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240822-net-spell-v1-4-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- include/net/ipv6.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index e7113855a10fd..248bfb26e2af9 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -851,7 +851,7 @@ static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int * we should *never* get to this point since that * would mean the addrs are equal * - * However, we do get to it 8) And exacly, when + * However, we do get to it 8) And exactly, when * addresses are equal 8) * * ip route add 1111::/128 via ... @@ -973,7 +973,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, hash = skb_get_hash_flowi6(skb, fl6); /* Since this is being sent on the wire obfuscate hash a bit - * to minimize possbility that any useful information to an + * to minimize possibility that any useful information to an * attacker is leaked. Only lower 20 bits are relevant. */ hash = rol32(hash, 16); From e8ac2dba93eafb928fd9e127cdade3b2216a642c Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:26 +0100 Subject: [PATCH 358/385] bonding: Correct spelling in headers Correct spelling in bond_3ad.h and bond_alb.h. As reported by codespell. Cc: Jay Vosburgh Cc: Andy Gospodarek Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240822-net-spell-v1-5-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- include/net/bond_3ad.h | 5 ++++- include/net/bond_alb.h | 2 +- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 9ce5ac2bfbad9..2053cd8e788a7 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -231,7 +231,10 @@ typedef struct port { mux_states_t sm_mux_state; /* state machine mux state */ u16 sm_mux_timer_counter; /* state machine mux timer counter */ tx_states_t sm_tx_state; /* state machine tx state */ - u16 sm_tx_timer_counter; /* state machine tx timer counter(allways on - enter to transmit state 3 time per second) */ + u16 sm_tx_timer_counter; /* state machine tx timer counter + * (always on - enter to transmit + * state 3 time per second) + */ u16 sm_churn_actor_timer_counter; u16 sm_churn_partner_timer_counter; u32 churn_actor_count; diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h index 9dc082b2d5430..e5945427f38dd 100644 --- a/include/net/bond_alb.h +++ b/include/net/bond_alb.h @@ -53,7 +53,7 @@ struct slave; struct tlb_client_info { - struct slave *tx_slave; /* A pointer to slave used for transmiting + struct slave *tx_slave; /* A pointer to slave used for transmitting * packets to a Client that the Hash function * gave this entry index. */ From 19f1f11c9a8e92a2211a3854bd2cfbd4bb6303f1 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:27 +0100 Subject: [PATCH 359/385] net: qualcomm: rmnet: Correct spelling in if_rmnet.h Correct spelling in if_rmnet.h As reported by codespell. Cc: Sean Tranchetti Signed-off-by: Simon Horman Reviewed-by: Subash Abhinov Kasiviswanathan Link: https://patch.msgid.link/20240822-net-spell-v1-6-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/if_rmnet.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h index 839d1e48b85e9..c44bf6e80ecb4 100644 --- a/include/linux/if_rmnet.h +++ b/include/linux/if_rmnet.h @@ -42,7 +42,7 @@ struct rmnet_map_ul_csum_header { /* csum_info field: * OFFSET: where (offset in bytes) to insert computed checksum - * UDP: 1 = UDP checksum (zero checkum means no checksum) + * UDP: 1 = UDP checksum (zero checksum means no checksum) * ENABLED: 1 = checksum computation requested */ #define MAP_CSUM_UL_OFFSET_MASK GENMASK(13, 0) From 6899c2549cf7ca554ee2dd8574f0b70945f3ed1b Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:28 +0100 Subject: [PATCH 360/385] netlabel: Correct spelling in netlabel.h Correct spelling in netlabel.h. As reported by codespell. Cc: Paul Moore Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240822-net-spell-v1-7-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- include/net/netlabel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 654bc777d2a7b..529160f76cac2 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -30,7 +30,7 @@ struct calipso_doi; /* * NetLabel - A management interface for maintaining network packet label - * mapping tables for explicit packet labling protocols. + * mapping tables for explicit packet labeling protocols. * * Network protocols such as CIPSO and RIPSO require a label translation layer * to convert the label on the packet into something meaningful on the host From 10d0749a38c3a02f308fe8c4f4ed29bd6412e5fb Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:29 +0100 Subject: [PATCH 361/385] NFC: Correct spelling in headers Correct spelling in NFC headers. As reported by codespell. Signed-off-by: Simon Horman Reviewed-by: Krzysztof Kozlowski Link: https://patch.msgid.link/20240822-net-spell-v1-8-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- include/net/nfc/nci.h | 2 +- include/net/nfc/nfc.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h index e82f55f543bbe..dc36519d16aad 100644 --- a/include/net/nfc/nci.h +++ b/include/net/nfc/nci.h @@ -332,7 +332,7 @@ struct nci_core_init_rsp_1 { __le32 nfcc_features; __u8 num_supported_rf_interfaces; __u8 supported_rf_interfaces[]; /* variable size array */ - /* continuted in nci_core_init_rsp_2 */ + /* continued in nci_core_init_rsp_2 */ } __packed; struct nci_core_init_rsp_2 { diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 3d07abacf08bd..3a3781838c672 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -80,7 +80,7 @@ struct nfc_ops { #define NFC_ATR_REQ_GT_OFFSET 14 /** - * struct nfc_target - NFC target descriptiom + * struct nfc_target - NFC target description * * @sens_res: 2 bytes describing the target SENS_RES response, if the target * is a type A one. The %sens_res most significant byte must be byte 2 @@ -230,10 +230,10 @@ static inline void nfc_set_parent_dev(struct nfc_dev *nfc_dev, } /** - * nfc_set_drvdata - set driver specifc data + * nfc_set_drvdata - set driver specific data * * @dev: The nfc device - * @data: Pointer to driver specifc data + * @data: Pointer to driver specific data */ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) { @@ -241,7 +241,7 @@ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) } /** - * nfc_get_drvdata - get driver specifc data + * nfc_get_drvdata - get driver specific data * * @dev: The nfc device */ From a7a45f02a093d3b3f80a77db334703b5f53ebd44 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:30 +0100 Subject: [PATCH 362/385] net: sched: Correct spelling in headers Correct spelling in pkt_cls.h and red.h. As reported by codespell. Cc: Krzysztof Kozlowski Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240822-net-spell-v1-9-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- include/net/pkt_cls.h | 2 +- include/net/red.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 41297bd38dff7..4880b3a7aced5 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -491,7 +491,7 @@ int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *, struct tcf_pkt_info *); /** - * tcf_em_tree_match - evaulate an ematch tree + * tcf_em_tree_match - evaluate an ematch tree * * @skb: socket buffer of the packet in question * @tree: ematch tree to be used for evaluation diff --git a/include/net/red.h b/include/net/red.h index 802287d52c9e3..159a09359fc09 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -40,7 +40,7 @@ max_P should be small (not 1), usually 0.01..0.02 is good value. max_P is chosen as a number, so that max_P/(th_max-th_min) - is a negative power of two in order arithmetics to contain + is a negative power of two in order arithmetic to contain only shifts. @@ -159,7 +159,7 @@ static inline u32 red_maxp(u8 Plog) static inline void red_set_vars(struct red_vars *v) { /* Reset average queue length, the value is strictly bound - * to the parameters below, reseting hurts a bit but leaving + * to the parameters below, resetting hurts a bit but leaving * it might result in an unreasonable qavg for a while. --TGR */ v->qavg = 0; @@ -340,7 +340,7 @@ static inline unsigned long red_calc_qavg_no_idle_time(const struct red_parms *p { /* * NOTE: v->qavg is fixed point number with point at Wlog. - * The formula below is equvalent to floating point + * The formula below is equivalent to floating point * version: * * qavg = qavg*(1-W) + backlog*W; @@ -375,7 +375,7 @@ static inline int red_mark_probability(const struct red_parms *p, OK. qR is random number in the interval (0..1/max_P)*(qth_max-qth_min) i.e. 0..(2^Plog). If we used floating point - arithmetics, it would be: (2^Plog)*rnd_num, + arithmetic, it would be: (2^Plog)*rnd_num, where rnd_num is less 1. Taking into account, that qavg have fixed From 7f47fcea8c6b4af25e72e0ebb8d492a181b7ce03 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:31 +0100 Subject: [PATCH 363/385] sctp: Correct spelling in headers Correct spelling in sctp.h and structs.h. As reported by codespell. Cc: Marcelo Ricardo Leitner Signed-off-by: Simon Horman Acked-by: Xin Long Link: https://patch.msgid.link/20240822-net-spell-v1-10-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- include/net/sctp/sctp.h | 2 +- include/net/sctp/structs.h | 20 ++++++++++---------- 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index a2310fa995f64..84e6b9fd56102 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -28,7 +28,7 @@ #define __net_sctp_h__ /* Header Strategy. - * Start getting some control over the header file depencies: + * Start getting some control over the header file dependencies: * includes * constants * structs diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index f24a1bbcb3ef9..31248cfdfb235 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -521,7 +521,7 @@ struct sctp_datamsg { refcount_t refcnt; /* When is this message no longer interesting to the peer? */ unsigned long expires_at; - /* Did the messenge fail to send? */ + /* Did the message fail to send? */ int send_error; u8 send_failed:1, can_delay:1, /* should this message be Nagle delayed */ @@ -792,7 +792,7 @@ struct sctp_transport { */ hb_sent:1, - /* Is the Path MTU update pending on this tranport */ + /* Is the Path MTU update pending on this transport */ pmtu_pending:1, dst_pending_confirm:1, /* need to confirm neighbour */ @@ -1223,7 +1223,7 @@ enum sctp_endpoint_type { }; /* - * A common base class to bridge the implmentation view of a + * A common base class to bridge the implementation view of a * socket (usually listening) endpoint versus an association's * local endpoint. * This common structure is useful for several purposes: @@ -1353,7 +1353,7 @@ struct sctp_endpoint { struct rcu_head rcu; }; -/* Recover the outter endpoint structure. */ +/* Recover the outer endpoint structure. */ static inline struct sctp_endpoint *sctp_ep(struct sctp_ep_common *base) { struct sctp_endpoint *ep; @@ -1906,7 +1906,7 @@ struct sctp_association { __u32 rwnd_over; /* Keeps treack of rwnd pressure. This happens when we have - * a window, but not recevie buffer (i.e small packets). This one + * a window, but not receive buffer (i.e small packets). This one * is releases slowly (1 PMTU at a time ). */ __u32 rwnd_press; @@ -1994,7 +1994,7 @@ struct sctp_association { /* ADDIP Section 5.2 Upon reception of an ASCONF Chunk. * - * This is needed to implement itmes E1 - E4 of the updated + * This is needed to implement items E1 - E4 of the updated * spec. Here is the justification: * * Since the peer may bundle multiple ASCONF chunks toward us, @@ -2005,7 +2005,7 @@ struct sctp_association { /* These ASCONF chunks are waiting to be sent. * - * These chunaks can't be pushed to outqueue until receiving + * These chunks can't be pushed to outqueue until receiving * ASCONF_ACK for the previous ASCONF indicated by * addip_last_asconf, so as to guarantee that only one ASCONF * is in flight at any time. @@ -2059,13 +2059,13 @@ struct sctp_association { struct sctp_transport *new_transport; /* SCTP AUTH: list of the endpoint shared keys. These - * keys are provided out of band by the user applicaton + * keys are provided out of band by the user application * and can't change during the lifetime of the association */ struct list_head endpoint_shared_keys; /* SCTP AUTH: - * The current generated assocaition shared key (secret) + * The current generated association shared key (secret) */ struct sctp_auth_bytes *asoc_shared_key; struct sctp_shared_key *shkey; @@ -2121,7 +2121,7 @@ enum { SCTP_ASSOC_EYECATCHER = 0xa550c123, }; -/* Recover the outter association structure. */ +/* Recover the outer association structure. */ static inline struct sctp_association *sctp_assoc(struct sctp_ep_common *base) { struct sctp_association *asoc; From 01d86846a5a5f34662679dd229a0167fc9d92382 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:32 +0100 Subject: [PATCH 364/385] x25: Correct spelling in x25.h Correct spelling in x25.h As reported by codespell. Signed-off-by: Simon Horman Reviewed-by: Martin Schiller Link: https://patch.msgid.link/20240822-net-spell-v1-11-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- include/net/x25.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/x25.h b/include/net/x25.h index 597eb53c471e3..5e833cfc864e2 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -81,7 +81,7 @@ enum { #define X25_DEFAULT_WINDOW_SIZE 2 /* Default Window Size */ #define X25_DEFAULT_PACKET_SIZE X25_PS128 /* Default Packet Size */ -#define X25_DEFAULT_THROUGHPUT 0x0A /* Deafult Throughput */ +#define X25_DEFAULT_THROUGHPUT 0x0A /* Default Throughput */ #define X25_DEFAULT_REVERSE 0x00 /* Default Reverse Charging */ #define X25_SMODULUS 8 From 70d0bb45fae87a3b08970a318e15f317446a1956 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:33 +0100 Subject: [PATCH 365/385] net: Correct spelling in headers Correct spelling in Networking headers. As reported by codespell. Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240822-net-spell-v1-12-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/etherdevice.h | 2 +- include/linux/netdevice.h | 8 ++++---- include/net/addrconf.h | 2 +- include/net/busy_poll.h | 2 +- include/net/caif/caif_layer.h | 4 ++-- include/net/caif/cfpkt.h | 2 +- include/net/dropreason-core.h | 6 +++--- include/net/dst.h | 2 +- include/net/dst_cache.h | 2 +- include/net/erspan.h | 4 ++-- include/net/hwbm.h | 4 ++-- include/net/llc_pdu.h | 2 +- include/net/netlink.h | 16 ++++++++-------- include/net/netns/sctp.h | 4 ++-- include/net/regulatory.h | 2 +- include/net/sock.h | 4 ++-- include/net/udp.h | 2 +- include/uapi/linux/in.h | 2 +- include/uapi/linux/inet_diag.h | 2 +- 19 files changed, 36 insertions(+), 36 deletions(-) diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 0ed47d00549ba..30114c25ad120 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -645,7 +645,7 @@ static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) } /** - * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame + * eth_skb_pad - Pad buffer to minimum number of octets for Ethernet frame * @skb: Buffer to pad * * An Ethernet frame should have a minimum size of 60 bytes. This function diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7dfa836d9dbf8..fce70990b209c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1237,7 +1237,7 @@ struct netdev_net_notifier { * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, * const unsigned char *addr, u16 vid) - * Deletes the FDB entry from dev coresponding to addr. + * Deletes the FDB entry from dev corresponding to addr. * int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev, * struct netlink_ext_ack *extack); * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, @@ -3514,7 +3514,7 @@ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, dql_completed(&dev_queue->dql, bytes); /* - * Without the memory barrier there is a small possiblity that + * Without the memory barrier there is a small possibility that * netdev_tx_sent_queue will miss the update and cause the queue to * be stopped forever */ @@ -4583,7 +4583,7 @@ void dev_uc_flush(struct net_device *dev); void dev_uc_init(struct net_device *dev); /** - * __dev_uc_sync - Synchonize device's unicast list + * __dev_uc_sync - Synchronize device's unicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed @@ -4627,7 +4627,7 @@ void dev_mc_flush(struct net_device *dev); void dev_mc_init(struct net_device *dev); /** - * __dev_mc_sync - Synchonize device's multicast list + * __dev_mc_sync - Synchronize device's multicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed diff --git a/include/net/addrconf.h b/include/net/addrconf.h index c8ed31828db36..363dd63babe72 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -333,7 +333,7 @@ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev) /** * __in6_dev_stats_get - get inet6_dev pointer for stats * @dev: network device - * @skb: skb for original incoming interface if neeeded + * @skb: skb for original incoming interface if needed * * Caller must hold rcu_read_lock or RTNL, because this function * does not take a reference on the inet6_dev. diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 9b09acac538ee..5e3b5703e4abd 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -131,7 +131,7 @@ static inline void skb_mark_napi_id(struct sk_buff *skb, #endif } -/* used in the protocol hanlder to propagate the napi_id to the socket */ +/* used in the protocol handler to propagate the napi_id to the socket */ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL diff --git a/include/net/caif/caif_layer.h b/include/net/caif/caif_layer.h index 0f45d875905f8..053e7c6a6a663 100644 --- a/include/net/caif/caif_layer.h +++ b/include/net/caif/caif_layer.h @@ -20,7 +20,7 @@ struct caif_payload_info; * @assert: expression to evaluate. * * This function will print a error message and a do WARN_ON if the - * assertion failes. Normally this will do a stack up at the current location. + * assertion fails. Normally this will do a stack up at the current location. */ #define caif_assert(assert) \ do { \ @@ -116,7 +116,7 @@ enum caif_direction { * @dn: Pointer down to the layer below. * @node: List node used when layer participate in a list. * @receive: Packet receive function. - * @transmit: Packet transmit funciton. + * @transmit: Packet transmit function. * @ctrlcmd: Used for control signalling upwards in the stack. * @modemcmd: Used for control signaling downwards in the stack. * @id: The identity of this layer diff --git a/include/net/caif/cfpkt.h b/include/net/caif/cfpkt.h index 44d914a50369c..acf664227d96b 100644 --- a/include/net/caif/cfpkt.h +++ b/include/net/caif/cfpkt.h @@ -18,7 +18,7 @@ struct cfpkt *cfpkt_create(u16 len); /* * Destroy a CAIF Packet. - * pkt Packet to be destoyed. + * pkt Packet to be destroyed. */ void cfpkt_destroy(struct cfpkt *pkt); diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 9707ab54fdd52..4748680e8c88e 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -155,8 +155,8 @@ enum skb_drop_reason { /** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */ SKB_DROP_REASON_SOCKET_RCVBUFF, /** - * @SKB_DROP_REASON_PROTO_MEM: proto memory limition, such as udp packet - * drop out of udp_memory_allocated. + * @SKB_DROP_REASON_PROTO_MEM: proto memory limitation, such as + * udp packet drop out of udp_memory_allocated. */ SKB_DROP_REASON_PROTO_MEM, /** @@ -217,7 +217,7 @@ enum skb_drop_reason { */ SKB_DROP_REASON_TCP_ZEROWINDOW, /** - * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data reveived is already + * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data received is already * received before (spurious retrans may happened), see * LINUX_MIB_DELAYEDACKLOST */ diff --git a/include/net/dst.h b/include/net/dst.h index 0aa331bd2fdb7..0f303cc602520 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -341,7 +341,7 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, skb->dev = dev; /* - * Clear hash so that we can recalulate the hash for the + * Clear hash so that we can recalculate the hash for the * encapsulated packet, unless we have already determine the hash * over the L4 4-tuple. */ diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h index b4a55d2d5e71b..1961699598e2c 100644 --- a/include/net/dst_cache.h +++ b/include/net/dst_cache.h @@ -102,7 +102,7 @@ int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp); * @dst_cache: the cache * * No synchronization is enforced: it must be called only when the cache - * is unsed. + * is unused. */ void dst_cache_destroy(struct dst_cache *dst_cache); diff --git a/include/net/erspan.h b/include/net/erspan.h index 6cb4cbd6a48fe..c6209e7b6c96b 100644 --- a/include/net/erspan.h +++ b/include/net/erspan.h @@ -89,7 +89,7 @@ enum erspan_encap_type { ERSPAN_ENCAP_NOVLAN = 0x0, /* originally without VLAN tag */ ERSPAN_ENCAP_ISL = 0x1, /* originally ISL encapsulated */ ERSPAN_ENCAP_8021Q = 0x2, /* originally 802.1Q encapsulated */ - ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag perserved in frame */ + ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag preserved in frame */ }; #define ERSPAN_V1_MDSIZE 4 @@ -192,7 +192,7 @@ static inline void erspan_build_header(struct sk_buff *skb, enc_type = ERSPAN_ENCAP_NOVLAN; /* If mirrored packet has vlan tag, extract tci and - * perserve vlan header in the mirrored frame. + * preserve vlan header in the mirrored frame. */ if (eth->h_proto == htons(ETH_P_8021Q)) { qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); diff --git a/include/net/hwbm.h b/include/net/hwbm.h index aa495decec35b..bdbe91c609ff9 100644 --- a/include/net/hwbm.h +++ b/include/net/hwbm.h @@ -11,9 +11,9 @@ struct hwbm_pool { int frag_size; /* Number of buffers currently used by this pool */ int buf_num; - /* constructor called during alocation */ + /* constructor called during allocation */ int (*construct)(struct hwbm_pool *bm_pool, void *buf); - /* protect acces to the buffer counter*/ + /* protect access to the buffer counter*/ struct mutex buf_lock; /* private data */ void *priv; diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index 1d55ba7c45be1..86681f29bda7a 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -254,7 +254,7 @@ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, } /** - * llc_pdu_decode_sa - extracs source address (MAC) of input frame + * llc_pdu_decode_sa - extracts, source address (MAC) of input frame * @skb: input skb that source address must be extracted from it. * @sa: pointer to source address (6 byte array). * diff --git a/include/net/netlink.h b/include/net/netlink.h index e78ce008e07cc..db6af207287c8 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -827,7 +827,7 @@ nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen, /** * nlmsg_find_attr - find a specific attribute in a netlink message * @nlh: netlink message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @attrtype: type of attribute to look for * * Returns the first attribute which matches the specified type. @@ -849,7 +849,7 @@ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in liberal mode. - * See documenation of struct nla_policy for more details. + * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ @@ -872,7 +872,7 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len, * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in strict mode. - * See documenation of struct nla_policy for more details. + * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ @@ -887,7 +887,7 @@ static inline int nla_validate(const struct nlattr *head, int len, int maxtype, /** * nlmsg_validate_deprecated - validate a netlink message including attributes * @nlh: netlinket message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct @@ -933,7 +933,7 @@ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) * nlmsg_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @nlh: netlink message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @rem: initialized to len, holds bytes currently remaining in stream */ #define nlmsg_for_each_attr(pos, nlh, hdrlen, rem) \ @@ -1034,7 +1034,7 @@ static inline struct sk_buff *nlmsg_new_large(size_t payload) * @skb: socket buffer the message is stored in * @nlh: netlink message header * - * Corrects the netlink message header to include the appeneded + * Corrects the netlink message header to include the appended * attributes. Only necessary if attributes have been added to * the message. */ @@ -1954,7 +1954,7 @@ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) * @start: container attribute * * Corrects the container attribute header to include the all - * appeneded attributes. + * appended attributes. * * Returns the total data length of the skb. */ @@ -1987,7 +1987,7 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) * * Validates all attributes in the nested attribute stream against the * specified policy. Attributes with a type exceeding maxtype will be - * ignored. See documenation of struct nla_policy for more details. + * ignored. See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index 7eff3d981b893..d25cd7a9c5ff8 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -125,14 +125,14 @@ struct netns_sctp { int pf_expose; /* - * Policy for preforming sctp/socket accounting + * Policy for performing sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_sndbuf * 1 - do sctp accounting, each asoc may use sk_sndbuf bytes */ int sndbuf_policy; /* - * Policy for preforming sctp/socket accounting + * Policy for performing sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_rcvbuf * 1 - do sctp accounting, each asoc may use sk_rcvbuf bytes */ diff --git a/include/net/regulatory.h b/include/net/regulatory.h index a103f4c8cf756..6633627f6e766 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -121,7 +121,7 @@ struct regulatory_request { * @REGULATORY_DISABLE_BEACON_HINTS: enable this if your driver needs to * ensure that passive scan flags and beaconing flags may not be lifted by * cfg80211 due to regulatory beacon hints. For more information on beacon - * hints read the documenation for regulatory_hint_found_beacon() + * hints read the documentation for regulatory_hint_found_beacon() * @REGULATORY_COUNTRY_IE_FOLLOW_POWER: for devices that have a preference * that even though they may have programmed their own custom power * setting prior to wiphy registration, they want to ensure their channel diff --git a/include/net/sock.h b/include/net/sock.h index cce23ac4d5148..f51d61fab0595 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1624,7 +1624,7 @@ bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); * lock_sock_fast - fast version of lock_sock * @sk: socket * - * This version should be used for very small section, where process wont block + * This version should be used for very small section, where process won't block * return false if fast path is taken: * * sk_lock.slock locked, owned = 0, BH disabled @@ -2546,7 +2546,7 @@ struct sock_skb_cb { /* Store sock_skb_cb at the end of skb->cb[] so protocol families * using skb->cb[] would keep using it directly and utilize its - * alignement guarantee. + * alignment guarantee. */ #define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \ sizeof(struct sock_skb_cb))) diff --git a/include/net/udp.h b/include/net/udp.h index 5ca53b1cec674..61222545ab1cf 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -232,7 +232,7 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, } /* Since this is being sent on the wire obfuscate hash a bit - * to minimize possbility that any useful information to an + * to minimize possibility that any useful information to an * attacker is leaked. Only upper 16 bits are relevant in the * computation for 16 bit port value. */ diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index d358add1611cd..5d32d53508d99 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -141,7 +141,7 @@ struct in_addr { */ #define IP_PMTUDISC_INTERFACE 4 /* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get - * fragmented if they exeed the interface mtu + * fragmented if they exceed the interface mtu */ #define IP_PMTUDISC_OMIT 5 diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 50655de04c9b6..86bb2e8b17c9f 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -143,7 +143,7 @@ enum { INET_DIAG_SHUTDOWN, /* - * Next extenstions cannot be requested in struct inet_diag_req_v2: + * Next extensions cannot be requested in struct inet_diag_req_v2: * its field idiag_ext has only 8 bits. */ From a8c924e98738f77668b022ec34107ca8b6093392 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 22 Aug 2024 13:57:34 +0100 Subject: [PATCH 366/385] net: Correct spelling in net/core Correct spelling in net/core. As reported by codespell. Signed-off-by: Simon Horman Link: https://patch.msgid.link/20240822-net-spell-v1-13-3a98971ce2d2@kernel.org Signed-off-by: Jakub Kicinski --- net/core/dev.c | 6 +++--- net/core/dev_addr_lists.c | 6 +++--- net/core/fib_rules.c | 2 +- net/core/gro.c | 2 +- net/core/netpoll.c | 2 +- net/core/pktgen.c | 10 +++++----- net/core/skbuff.c | 4 ++-- net/core/sock.c | 6 +++--- net/core/utils.c | 2 +- 9 files changed, 20 insertions(+), 20 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index f34ec921f8815..63987b8b7c853 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3707,7 +3707,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d next = skb->next; skb_mark_not_on_list(skb); - /* in case skb wont be segmented, point to itself */ + /* in case skb won't be segmented, point to itself */ skb->prev = skb; skb = validate_xmit_skb(skb, dev, again); @@ -11432,7 +11432,7 @@ void unregister_netdevice_many_notify(struct list_head *head, * @head: list of devices * * Note: As most callers use a stack allocated list_head, - * we force a list_del() to make sure stack wont be corrupted later. + * we force a list_del() to make sure stack won't be corrupted later. */ void unregister_netdevice_many(struct list_head *head) { @@ -11490,7 +11490,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, if (dev->features & NETIF_F_NETNS_LOCAL) goto out; - /* Ensure the device has been registrered */ + /* Ensure the device has been registered */ if (dev->reg_state != NETREG_REGISTERED) goto out; diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index baa63dee28295..166e404f7c03c 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -262,7 +262,7 @@ static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, } /* This function only works where there is a strict 1-1 relationship - * between source and destionation of they synch. If you ever need to + * between source and destination of they synch. If you ever need to * sync addresses to more then 1 destination, you need to use * __hw_addr_sync_multiple(). */ @@ -299,8 +299,8 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, EXPORT_SYMBOL(__hw_addr_unsync); /** - * __hw_addr_sync_dev - Synchonize device's multicast list - * @list: address list to syncronize + * __hw_addr_sync_dev - Synchronize device's multicast list + * @list: address list to synchronize * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 3c76b835493da..5a4eb744758c4 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -72,7 +72,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, r->suppress_prefixlen = -1; r->suppress_ifgroup = -1; - /* The lock is not required here, the list in unreacheable + /* The lock is not required here, the list in unreachable * at the moment this function is called */ list_add_tail(&r->list, &ops->rules_list); return 0; diff --git a/net/core/gro.c b/net/core/gro.c index b3b43de1a6502..3abad1b567dd9 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -374,7 +374,7 @@ static void gro_list_prepare(const struct list_head *head, skb_mac_header(skb), maclen); - /* in most common scenarions 'slow_gro' is 0 + /* in most common scenarios 'slow_gro' is 0 * otherwise we are already on some slower paths * either skip all the infrequent tests altogether or * avoid trying too hard to skip each of them individually diff --git a/net/core/netpoll.c b/net/core/netpoll.c index a1aea86cf98c1..e0720ee6fa620 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -162,7 +162,7 @@ static void poll_one_napi(struct napi_struct *napi) if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state)) return; - /* We explicilty pass the polling call a budget of 0 to + /* We explicitly pass the polling call a budget of 0 to * indicate that we are clearing the Tx path only. */ work = napi->poll(napi, 0); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index ea55a758a475a..4baf02db1f6a7 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -69,7 +69,7 @@ * * By design there should only be *one* "controlling" process. In practice * multiple write accesses gives unpredictable result. Understood by "write" - * to /proc gives result code thats should be read be the "writer". + * to /proc gives result code that should be read be the "writer". * For practical use this should be no problem. * * Note when adding devices to a specific CPU there good idea to also assign @@ -2371,11 +2371,11 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) if (pkt_dev->spi) { /* We need as quick as possible to find the right SA - * Searching with minimum criteria to archieve this. + * Searching with minimum criteria to achieve, this. */ x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET); } else { - /* slow path: we dont already have xfrm_state */ + /* slow path: we don't already have xfrm_state */ x = xfrm_stateonly_find(pn->net, DUMMY_MARK, 0, (xfrm_address_t *)&pkt_dev->cur_daddr, (xfrm_address_t *)&pkt_dev->cur_saddr, @@ -3838,8 +3838,8 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->ipsmode = XFRM_MODE_TRANSPORT; pkt_dev->ipsproto = IPPROTO_ESP; - /* xfrm tunnel mode needs additional dst to extract outter - * ip header protocol/ttl/id field, here creat a phony one. + /* xfrm tunnel mode needs additional dst to extract outer + * ip header protocol/ttl/id field, here create a phony one. * instead of looking for a valid rt, which definitely hurting * performance under such circumstance. */ diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1748673e1fe0b..6022c7359385f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5163,7 +5163,7 @@ EXPORT_SYMBOL_GPL(skb_to_sgvec); * 3. sg_unmark_end * 4. skb_to_sgvec(payload2) * - * When mapping mutilple payload conditionally, skb_to_sgvec_nomark + * When mapping multiple payload conditionally, skb_to_sgvec_nomark * is more preferable. */ int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, @@ -6021,7 +6021,7 @@ EXPORT_SYMBOL(skb_try_coalesce); * @skb: buffer to clean * @xnet: packet is crossing netns * - * skb_scrub_packet can be used after encapsulating or decapsulting a packet + * skb_scrub_packet can be used after encapsulating or decapsulating a packet * into/from a tunnel. Some information have to be cleared during these * operations. * skb_scrub_packet can also be used to clean a skb before injecting it in diff --git a/net/core/sock.c b/net/core/sock.c index 9abc4fe259535..468b1239606c6 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2048,7 +2048,7 @@ static inline void sock_lock_init(struct sock *sk) /* * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, - * even temporarly, because of RCU lookups. sk_node should also be left as is. + * even temporarily, because of RCU lookups. sk_node should also be left as is. * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end */ static void sock_copy(struct sock *nsk, const struct sock *osk) @@ -2538,7 +2538,7 @@ void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) skb_set_hash_from_sk(skb, sk); /* * We used to take a refcount on sk, but following operation - * is enough to guarantee sk_free() wont free this sock until + * is enough to guarantee sk_free() won't free this sock until * all in-flight packets are completed */ refcount_add(skb->truesize, &sk->sk_wmem_alloc); @@ -3697,7 +3697,7 @@ EXPORT_SYMBOL(sock_recv_errqueue); * * FIX: POSIX 1003.1g is very ambiguous here. It states that * asynchronous errors should be reported by getsockopt. We assume - * this means if you specify SO_ERROR (otherwise whats the point of it). + * this means if you specify SO_ERROR (otherwise what is the point of it). */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) diff --git a/net/core/utils.c b/net/core/utils.c index c994e95172acf..27f4cffaae05d 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Generic address resultion entity + * Generic address resolution entity * * Authors: * net_random Alan Cox From b4985aa8e312fd40fbbce0fe44ce677368fdee43 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 22 Aug 2024 21:39:03 +0800 Subject: [PATCH 367/385] net: caif: use max() to simplify the code When processing the tail append of sk buffer, the final length needs to be determined based on expectlen and addlen. Using max() here can increase the readability of the code. Signed-off-by: Li Zetao Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240822133908.1042240-4-lizetao1@huawei.com Signed-off-by: Jakub Kicinski --- net/caif/cfpkt_skbuff.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c index 2ae8cfa3df884..96236d21b18e5 100644 --- a/net/caif/cfpkt_skbuff.c +++ b/net/caif/cfpkt_skbuff.c @@ -298,10 +298,8 @@ struct cfpkt *cfpkt_append(struct cfpkt *dstpkt, if (unlikely(is_erronous(dstpkt) || is_erronous(addpkt))) { return dstpkt; } - if (expectlen > addlen) - neededtailspace = expectlen; - else - neededtailspace = addlen; + + neededtailspace = max(expectlen, addlen); if (dst->tail + neededtailspace > dst->end) { /* Create a dumplicate of 'dst' with more tail space */ From 26549dab8a4676ce549cb20bf384daf458a9ea24 Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 22 Aug 2024 21:39:06 +0800 Subject: [PATCH 368/385] ipv6: mcast: use min() to simplify the code When coping sockaddr in ip6_mc_msfget(), the time of copies depends on the minimum value between sl_count and gf_numsrc. Using min() here is very semantic. Signed-off-by: Li Zetao Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240822133908.1042240-7-lizetao1@huawei.com Signed-off-by: Jakub Kicinski --- net/ipv6/mcast.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 7ba01d8cfbae8..b244dbf61d5f3 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -586,7 +586,8 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct ip6_sf_socklist *psl; - int i, count, copycount; + unsigned int count; + int i, copycount; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; @@ -610,7 +611,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, psl = sock_dereference(pmc->sflist, sk); count = psl ? psl->sl_count : 0; - copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; + copycount = min(count, gsf->gf_numsrc); gsf->gf_numsrc = count; for (i = 0; i < copycount; i++) { struct sockaddr_in6 *psin6; From a18308623ce303a0f8954294f3877b3ece8c5e7b Mon Sep 17 00:00:00 2001 From: Li Zetao Date: Thu, 22 Aug 2024 21:39:07 +0800 Subject: [PATCH 369/385] tipc: use min() to simplify the code When calculating size of own domain based on number of peers, the result should be less than MAX_MON_DOMAIN, so using min() here is very semantic. Signed-off-by: Li Zetao Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240822133908.1042240-8-lizetao1@huawei.com Signed-off-by: Jakub Kicinski --- net/tipc/monitor.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 77a3d016cadec..e2f19627e43d5 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -149,7 +149,7 @@ static int dom_size(int peers) while ((i * i) < peers) i++; - return i < MAX_MON_DOMAIN ? i : MAX_MON_DOMAIN; + return min(i, MAX_MON_DOMAIN); } static void map_set(u64 *up_map, int i, unsigned int v) From cd039e6787ff6c496239c0c2f6d740e7c216d763 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Thu, 22 Aug 2024 11:40:57 -0400 Subject: [PATCH 370/385] net: xilinx: axienet: Don't print if we go into promiscuous mode A message about being in promiscuous mode is printed every time each additional multicast address beyond four is added. Suppress this message like is done in other drivers. Signed-off-by: Sean Anderson Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240822154059.1066595-4-sean.anderson@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 88ff82c52d0cd..f612adb07a252 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -447,7 +447,6 @@ static void axienet_set_multicast_list(struct net_device *ndev) reg = axienet_ior(lp, XAE_FMI_OFFSET); reg |= XAE_FMI_PM_MASK; axienet_iow(lp, XAE_FMI_OFFSET, reg); - dev_info(&ndev->dev, "Promiscuous mode enabled.\n"); } else if (!netdev_mc_empty(ndev)) { struct netdev_hw_addr *ha; @@ -481,7 +480,6 @@ static void axienet_set_multicast_list(struct net_device *ndev) reg &= ~XAE_FMI_PM_MASK; axienet_iow(lp, XAE_FMI_OFFSET, reg); - dev_info(&ndev->dev, "Promiscuous mode disabled.\n"); } for (; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) { From 7a826fb3e4c68f42ffdec8361e1fb49cdfbbc991 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Thu, 22 Aug 2024 11:40:58 -0400 Subject: [PATCH 371/385] net: xilinx: axienet: Don't set IFF_PROMISC in ndev->flags Contrary to the comment, we don't have to inform the net subsystem. Signed-off-by: Sean Anderson Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240822154059.1066595-5-sean.anderson@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index f612adb07a252..5c4a5949a0213 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -439,11 +439,6 @@ static void axienet_set_multicast_list(struct net_device *ndev) if (ndev->flags & (IFF_ALLMULTI | IFF_PROMISC) || netdev_mc_count(ndev) > XAE_MULTICAST_CAM_TABLE_NUM) { - /* We must make the kernel realize we had to move into - * promiscuous mode. If it was a promiscuous mode request - * the flag is already set. If not we set it. - */ - ndev->flags |= IFF_PROMISC; reg = axienet_ior(lp, XAE_FMI_OFFSET); reg |= XAE_FMI_PM_MASK; axienet_iow(lp, XAE_FMI_OFFSET, reg); From 749e67d5b297c01b4825315808c9f1c9e7c91d01 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Thu, 22 Aug 2024 11:40:59 -0400 Subject: [PATCH 372/385] net: xilinx: axienet: Support IFF_ALLMULTI Add support for IFF_ALLMULTI by configuring a single filter to match the multicast address bit. This allows us to keep promiscuous mode disabled, even when we have more than four multicast addresses. An even better solution would be to "pack" addresses into the available CAM registers, but that can wait for a future series. Signed-off-by: Sean Anderson Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240822154059.1066595-6-sean.anderson@linux.dev Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/xilinx/xilinx_axienet.h | 2 ++ .../net/ethernet/xilinx/xilinx_axienet_main.c | 34 +++++++++++-------- 2 files changed, 22 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 5a7d6b872f5da..c301dd2ee0839 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -175,6 +175,8 @@ #define XAE_FFE_OFFSET 0x0000070C /* Frame Filter Enable */ #define XAE_AF0_OFFSET 0x00000710 /* Address Filter 0 */ #define XAE_AF1_OFFSET 0x00000714 /* Address Filter 1 */ +#define XAE_AM0_OFFSET 0x00000750 /* Frame Filter Mask Value Bytes 3-0 */ +#define XAE_AM1_OFFSET 0x00000754 /* Frame Filter Mask Value Bytes 7-4 */ #define XAE_TX_VLAN_DATA_OFFSET 0x00004000 /* TX VLAN data table address */ #define XAE_RX_VLAN_DATA_OFFSET 0x00008000 /* RX VLAN data table address */ diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 5c4a5949a0213..fe6a0e2e463f8 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -437,18 +437,27 @@ static void axienet_set_multicast_list(struct net_device *ndev) u32 reg, af0reg, af1reg; struct axienet_local *lp = netdev_priv(ndev); - if (ndev->flags & (IFF_ALLMULTI | IFF_PROMISC) || - netdev_mc_count(ndev) > XAE_MULTICAST_CAM_TABLE_NUM) { - reg = axienet_ior(lp, XAE_FMI_OFFSET); + reg = axienet_ior(lp, XAE_FMI_OFFSET); + reg &= ~XAE_FMI_PM_MASK; + if (ndev->flags & IFF_PROMISC) reg |= XAE_FMI_PM_MASK; + else + reg &= ~XAE_FMI_PM_MASK; + axienet_iow(lp, XAE_FMI_OFFSET, reg); + + if (ndev->flags & IFF_ALLMULTI || + netdev_mc_count(ndev) > XAE_MULTICAST_CAM_TABLE_NUM) { + reg &= 0xFFFFFF00; axienet_iow(lp, XAE_FMI_OFFSET, reg); + axienet_iow(lp, XAE_AF0_OFFSET, 1); /* Multicast bit */ + axienet_iow(lp, XAE_AF1_OFFSET, 0); + axienet_iow(lp, XAE_AM0_OFFSET, 1); /* ditto */ + axienet_iow(lp, XAE_AM1_OFFSET, 0); + axienet_iow(lp, XAE_FFE_OFFSET, 1); + i = 1; } else if (!netdev_mc_empty(ndev)) { struct netdev_hw_addr *ha; - reg = axienet_ior(lp, XAE_FMI_OFFSET); - reg &= ~XAE_FMI_PM_MASK; - axienet_iow(lp, XAE_FMI_OFFSET, reg); - netdev_for_each_mc_addr(ha, ndev) { if (i >= XAE_MULTICAST_CAM_TABLE_NUM) break; @@ -461,24 +470,21 @@ static void axienet_set_multicast_list(struct net_device *ndev) af1reg = (ha->addr[4]); af1reg |= (ha->addr[5] << 8); - reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00; + reg &= 0xFFFFFF00; reg |= i; axienet_iow(lp, XAE_FMI_OFFSET, reg); axienet_iow(lp, XAE_AF0_OFFSET, af0reg); axienet_iow(lp, XAE_AF1_OFFSET, af1reg); + axienet_iow(lp, XAE_AM0_OFFSET, 0xffffffff); + axienet_iow(lp, XAE_AM1_OFFSET, 0x0000ffff); axienet_iow(lp, XAE_FFE_OFFSET, 1); i++; } - } else { - reg = axienet_ior(lp, XAE_FMI_OFFSET); - reg &= ~XAE_FMI_PM_MASK; - - axienet_iow(lp, XAE_FMI_OFFSET, reg); } for (; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) { - reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00; + reg &= 0xFFFFFF00; reg |= i; axienet_iow(lp, XAE_FMI_OFFSET, reg); axienet_iow(lp, XAE_FFE_OFFSET, 0); From 1461f5a3d810869e182f1d11caaac7dee0458ff7 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 22 Aug 2024 11:25:44 -0700 Subject: [PATCH 373/385] l2tp: avoid overriding sk->sk_user_data Although commit 4a4cd70369f1 ("l2tp: don't set sk_user_data in tunnel socket") removed sk->sk_user_data usage, setup_udp_tunnel_sock() still touches sk->sk_user_data, this conflicts with sockmap which also leverages sk->sk_user_data to save psock. Restore this sk->sk_user_data check to avoid such conflicts. Fixes: 4a4cd70369f1 ("l2tp: don't set sk_user_data in tunnel socket") Reported-by: syzbot+8dbe3133b840c470da0e@syzkaller.appspotmail.com Cc: Tom Parkin Signed-off-by: Cong Wang Tested-by: James Chapman Reviewed-by: James Chapman Link: https://patch.msgid.link/20240822182544.378169-1-xiyou.wangcong@gmail.com Signed-off-by: Jakub Kicinski --- net/l2tp/l2tp_core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index af87c781d6a66..df73c35363cbf 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1620,6 +1620,9 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net, (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP)) return -EPROTONOSUPPORT; + if (encap == L2TP_ENCAPTYPE_UDP && sk->sk_user_data) + return -EBUSY; + tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) { l2tp_tunnel_put(tunnel); From d2ab3bb890f6a88facf89494ce50b27ff8236d24 Mon Sep 17 00:00:00 2001 From: Rosen Penev Date: Thu, 22 Aug 2024 12:27:52 -0700 Subject: [PATCH 374/385] net: ag71xx: move clk_eth out of struct It's only used in one place. It doesn't need to be in the struct. Signed-off-by: Rosen Penev Link: https://patch.msgid.link/20240822192758.141201-1-rosenp@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/atheros/ag71xx.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index ee5d429abdaa6..bf02bea03a7be 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -381,7 +381,6 @@ struct ag71xx { struct reset_control *mdio_reset; struct clk *clk_mdio; - struct clk *clk_eth; }; static int ag71xx_desc_empty(struct ag71xx_desc *desc) @@ -1799,6 +1798,7 @@ static int ag71xx_probe(struct platform_device *pdev) const struct ag71xx_dcfg *dcfg; struct net_device *ndev; struct resource *res; + struct clk *clk_eth; int tx_size, err, i; struct ag71xx *ag; @@ -1829,10 +1829,10 @@ static int ag71xx_probe(struct platform_device *pdev) return -EINVAL; } - ag->clk_eth = devm_clk_get_enabled(&pdev->dev, "eth"); - if (IS_ERR(ag->clk_eth)) { + clk_eth = devm_clk_get_enabled(&pdev->dev, "eth"); + if (IS_ERR(clk_eth)) { netif_err(ag, probe, ndev, "Failed to get eth clk.\n"); - return PTR_ERR(ag->clk_eth); + return PTR_ERR(clk_eth); } SET_NETDEV_DEV(ndev, &pdev->dev); From ec82fa2c874f2efa55511684494949393d2789aa Mon Sep 17 00:00:00 2001 From: Kyle Swenson Date: Thu, 22 Aug 2024 22:01:21 +0000 Subject: [PATCH 375/385] dt-bindings: pse: tps23881: add reset-gpios The TPS23881 has an active-low reset pin that can be connected to an SoC. Document this with the device-tree binding. Signed-off-by: Kyle Swenson Reviewed-by: Krzysztof Kozlowski Reviewed-by: Oleksij Rempel Reviewed-by: Kory Maincent Link: https://patch.msgid.link/20240822220100.3030184-2-kyle.swenson@est.tech Signed-off-by: Jakub Kicinski --- Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml index 6992d56832bf9..d08abcb012113 100644 --- a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml +++ b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml @@ -23,6 +23,9 @@ properties: '#pse-cells': const: 1 + reset-gpios: + maxItems: 1 + channels: description: each set of 8 ports can be assigned to one physical channels or two for PoE4. This parameter describes the configuration From 69f47cad3a05f6cd345afca84f1e66740ff48a2d Mon Sep 17 00:00:00 2001 From: Kyle Swenson Date: Thu, 22 Aug 2024 22:01:22 +0000 Subject: [PATCH 376/385] net: pse-pd: tps23881: Support reset-gpios The TPS23880/1 has an active-low reset pin that some boards connect to the SoC to control when the TPS23880 is pulled out of reset. Add support for this via a reset-gpios property in the DTS. Signed-off-by: Kyle Swenson Acked-by: Oleksij Rempel Reviewed-by: Kory Maincent Link: https://patch.msgid.link/20240822220100.3030184-3-kyle.swenson@est.tech Signed-off-by: Jakub Kicinski --- drivers/net/pse-pd/tps23881.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/drivers/net/pse-pd/tps23881.c b/drivers/net/pse-pd/tps23881.c index 2ea75686a3190..5c4e88be46ee3 100644 --- a/drivers/net/pse-pd/tps23881.c +++ b/drivers/net/pse-pd/tps23881.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -737,6 +738,7 @@ static int tps23881_i2c_probe(struct i2c_client *client) { struct device *dev = &client->dev; struct tps23881_priv *priv; + struct gpio_desc *reset; int ret; u8 val; @@ -749,6 +751,25 @@ static int tps23881_i2c_probe(struct i2c_client *client) if (!priv) return -ENOMEM; + reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(reset)) + return dev_err_probe(&client->dev, PTR_ERR(reset), "Failed to get reset GPIO\n"); + + if (reset) { + /* TPS23880 datasheet (Rev G) indicates minimum reset pulse is 5us */ + usleep_range(5, 10); + gpiod_set_value_cansleep(reset, 0); /* De-assert reset */ + + /* TPS23880 datasheet indicates the minimum time after power on reset + * should be 20ms, but the document describing how to load SRAM ("How + * to Load TPS2388x SRAM and Parity Code over I2C" (Rev E)) + * indicates we should delay that programming by at least 50ms. So + * we'll wait the entire 50ms here to ensure we're safe to go to the + * SRAM loading proceedure. + */ + msleep(50); + } + ret = i2c_smbus_read_byte_data(client, TPS23881_REG_DEVID); if (ret < 0) return ret; From 0d9e5df4a257afc3a471a82961ace9a22b88295a Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Fri, 23 Aug 2024 08:11:52 +0800 Subject: [PATCH 377/385] tcp: avoid reusing FIN_WAIT2 when trying to find port in connect() process We found that one close-wait socket was reset by the other side due to a new connection reusing the same port which is beyond our expectation, so we have to investigate the underlying reason. The following experiment is conducted in the test environment. We limit the port range from 40000 to 40010 and delay the time to close() after receiving a fin from the active close side, which can help us easily reproduce like what happened in production. Here are three connections captured by tcpdump: 127.0.0.1.40002 > 127.0.0.1.9999: Flags [S], seq 2965525191 127.0.0.1.9999 > 127.0.0.1.40002: Flags [S.], seq 2769915070 127.0.0.1.40002 > 127.0.0.1.9999: Flags [.], ack 1 127.0.0.1.40002 > 127.0.0.1.9999: Flags [F.], seq 1, ack 1 // a few seconds later, within 60 seconds 127.0.0.1.40002 > 127.0.0.1.9999: Flags [S], seq 2965590730 127.0.0.1.9999 > 127.0.0.1.40002: Flags [.], ack 2 127.0.0.1.40002 > 127.0.0.1.9999: Flags [R], seq 2965525193 // later, very quickly 127.0.0.1.40002 > 127.0.0.1.9999: Flags [S], seq 2965590730 127.0.0.1.9999 > 127.0.0.1.40002: Flags [S.], seq 3120990805 127.0.0.1.40002 > 127.0.0.1.9999: Flags [.], ack 1 As we can see, the first flow is reset because: 1) client starts a new connection, I mean, the second one 2) client tries to find a suitable port which is a timewait socket (its state is timewait, substate is fin_wait2) 3) client occupies that timewait port to send a SYN 4) server finds a corresponding close-wait socket in ehash table, then replies with a challenge ack 5) client sends an RST to terminate this old close-wait socket. I don't think the port selection algo can choose a FIN_WAIT2 socket when we turn on tcp_tw_reuse because on the server side there remain unread data. In some cases, if one side haven't call close() yet, we should not consider it as expendable and treat it at will. Even though, sometimes, the server isn't able to call close() as soon as possible like what we expect, it can not be terminated easily, especially due to a second unrelated connection happening. After this patch, we can see the expected failure if we start a connection when all the ports are occupied in fin_wait2 state: "Ncat: Cannot assign requested address." Reported-by: Jade Dong Signed-off-by: Jason Xing Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240823001152.31004-1-kerneljasonxing@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_ipv4.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a4e510846905e..5087e12209a19 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -120,6 +120,9 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) struct tcp_sock *tp = tcp_sk(sk); int ts_recent_stamp; + if (tw->tw_substate == TCP_FIN_WAIT2) + reuse = 0; + if (reuse == 2) { /* Still does not detect *everything* that goes through * lo, since we require a loopback src or dst address From 9ceebd7a264798a792a3cf515f4c331704d4c5fb Mon Sep 17 00:00:00 2001 From: Hongbo Li Date: Fri, 23 Aug 2024 15:04:53 +0800 Subject: [PATCH 378/385] net/ipv4: fix macro definition sk_for_each_bound_bhash The macro sk_for_each_bound_bhash accepts a parameter __sk, but it was not used, rather the sk2 is directly used, so we replace the sk2 with __sk in macro. Signed-off-by: Hongbo Li Link: https://patch.msgid.link/20240823070453.3327832-1-lihongbo22@huawei.com Signed-off-by: Jakub Kicinski --- net/ipv4/inet_connection_sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 64d07b842e736..ce4d77f492436 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -236,7 +236,7 @@ static bool inet_bhash2_conflict(const struct sock *sk, #define sk_for_each_bound_bhash(__sk, __tb2, __tb) \ hlist_for_each_entry(__tb2, &(__tb)->bhash2, bhash_node) \ - sk_for_each_bound(sk2, &(__tb2)->owners) + sk_for_each_bound((__sk), &(__tb2)->owners) /* This should be called only when the tb and tb2 hashbuckets' locks are held */ static int inet_csk_bind_conflict(const struct sock *sk, From 89683b45f15ca5e0064d6dc1c1bfaa8aacc208f5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 23 Aug 2024 14:00:19 +0000 Subject: [PATCH 379/385] ipv6: avoid indirect calls for SOL_IP socket options ipv6_setsockopt() can directly call ip_setsockopt() instead of going through udp_prot.setsockopt() ipv6_getsockopt() can directly call ip_getsockopt() instead of going through udp_prot.getsockopt() These indirections predate git history, not sure why they were there. Signed-off-by: Eric Dumazet Link: https://patch.msgid.link/20240823140019.3727643-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv6/ipv6_sockglue.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index cd342d5015c6f..1e225e6489ea1 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -985,7 +985,7 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, int err; if (level == SOL_IP && sk->sk_type != SOCK_RAW) - return udp_prot.setsockopt(sk, level, optname, optval, optlen); + return ip_setsockopt(sk, level, optname, optval, optlen); if (level != SOL_IPV6) return -ENOPROTOOPT; @@ -1475,7 +1475,7 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, int err; if (level == SOL_IP && sk->sk_type != SOCK_RAW) - return udp_prot.getsockopt(sk, level, optname, optval, optlen); + return ip_getsockopt(sk, level, optname, optval, optlen); if (level != SOL_IPV6) return -ENOPROTOOPT; From 2c163922de69983e6ccedeb5c00dec85b6a17283 Mon Sep 17 00:00:00 2001 From: Xi Huang Date: Thu, 22 Aug 2024 15:20:42 +0800 Subject: [PATCH 380/385] net: dpaa: reduce number of synchronize_net() calls In the function dpaa_napi_del(), we execute the netif_napi_del() for each cpu, which is actually a high overhead operation because each call to netif_napi_del() contains a synchronize_net(), i.e. an RCU operation. In fact, it is only necessary to call __netif_napi_del and use synchronize_net() once outside of the loop. This change is similar to commit 2543a6000e593a ("gro_cells: reduce number of synchronize_net() calls") and commit 5198d545dba8ad (" net: remove napi_hash_del() from driver-facing API") 5198d545db. Signed-off-by: Xi Huang Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20240822072042.42750-1-xuiagnh@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index cfe6b57b1da0e..5d99cfb4e9948 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -3156,8 +3156,9 @@ static void dpaa_napi_del(struct net_device *net_dev) for_each_possible_cpu(cpu) { percpu_priv = per_cpu_ptr(priv->percpu_priv, cpu); - netif_napi_del(&percpu_priv->np.napi); + __netif_napi_del(&percpu_priv->np.napi); } + synchronize_net(); } static inline void dpaa_bp_free_pf(const struct dpaa_bp *bp, From cda1fba15cb2282b3c364805c9767698f11c3b0e Mon Sep 17 00:00:00 2001 From: Arkadiusz Kubalewski Date: Fri, 23 Aug 2024 00:25:12 +0200 Subject: [PATCH 381/385] dpll: add Embedded SYNC feature for a pin Implement and document new pin attributes for providing Embedded SYNC capabilities to the DPLL subsystem users through a netlink pin-get do/dump messages. Allow the user to set Embedded SYNC frequency with pin-set do netlink message. Reviewed-by: Aleksandr Loktionov Signed-off-by: Arkadiusz Kubalewski Reviewed-by: Jiri Pirko Link: https://patch.msgid.link/20240822222513.255179-2-arkadiusz.kubalewski@intel.com Signed-off-by: Jakub Kicinski --- Documentation/driver-api/dpll.rst | 21 +++++ Documentation/netlink/specs/dpll.yaml | 24 +++++ drivers/dpll/dpll_netlink.c | 130 ++++++++++++++++++++++++++ drivers/dpll/dpll_nl.c | 5 +- include/linux/dpll.h | 15 +++ include/uapi/linux/dpll.h | 3 + 6 files changed, 196 insertions(+), 2 deletions(-) diff --git a/Documentation/driver-api/dpll.rst b/Documentation/driver-api/dpll.rst index ea8d16600e16a..e6855cd37e852 100644 --- a/Documentation/driver-api/dpll.rst +++ b/Documentation/driver-api/dpll.rst @@ -214,6 +214,27 @@ offset values are fractional with 3-digit decimal places and shell be divided with ``DPLL_PIN_PHASE_OFFSET_DIVIDER`` to get integer part and modulo divided to get fractional part. +Embedded SYNC +============= + +Device may provide ability to use Embedded SYNC feature. It allows +to embed additional SYNC signal into the base frequency of a pin - a one +special pulse of base frequency signal every time SYNC signal pulse +happens. The user can configure the frequency of Embedded SYNC. +The Embedded SYNC capability is always related to a given base frequency +and HW capabilities. The user is provided a range of Embedded SYNC +frequencies supported, depending on current base frequency configured for +the pin. + + ========================================= ================================= + ``DPLL_A_PIN_ESYNC_FREQUENCY`` current Embedded SYNC frequency + ``DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED`` nest available Embedded SYNC + frequency ranges + ``DPLL_A_PIN_FREQUENCY_MIN`` attr minimum value of frequency + ``DPLL_A_PIN_FREQUENCY_MAX`` attr maximum value of frequency + ``DPLL_A_PIN_ESYNC_PULSE`` pulse type of Embedded SYNC + ========================================= ================================= + Configuration commands group ============================ diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 94132d30e0e03..f2894ca35de84 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -345,6 +345,26 @@ attribute-sets: Value is in PPM (parts per million). This may be implemented for example for pin of type PIN_TYPE_SYNCE_ETH_PORT. + - + name: esync-frequency + type: u64 + doc: | + Frequency of Embedded SYNC signal. If provided, the pin is configured + with a SYNC signal embedded into its base clock frequency. + - + name: esync-frequency-supported + type: nest + multi-attr: true + nested-attributes: frequency-range + doc: | + If provided a pin is capable of embedding a SYNC signal (within given + range) into its base frequency signal. + - + name: esync-pulse + type: u32 + doc: | + A ratio of high to low state of a SYNC signal pulse embedded + into base clock frequency. Value is in percents. - name: pin-parent-device subset-of: pin @@ -510,6 +530,9 @@ operations: - phase-adjust-max - phase-adjust - fractional-frequency-offset + - esync-frequency + - esync-frequency-supported + - esync-pulse dump: request: @@ -536,6 +559,7 @@ operations: - parent-device - parent-pin - phase-adjust + - esync-frequency - name: pin-create-ntf doc: Notification about pin appearing diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 98e6ad8528d37..fc0280dcddd10 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -342,6 +342,51 @@ dpll_msg_add_pin_freq(struct sk_buff *msg, struct dpll_pin *pin, return 0; } +static int +dpll_msg_add_pin_esync(struct sk_buff *msg, struct dpll_pin *pin, + struct dpll_pin_ref *ref, struct netlink_ext_ack *extack) +{ + const struct dpll_pin_ops *ops = dpll_pin_ops(ref); + struct dpll_device *dpll = ref->dpll; + struct dpll_pin_esync esync; + struct nlattr *nest; + int ret, i; + + if (!ops->esync_get) + return 0; + ret = ops->esync_get(pin, dpll_pin_on_dpll_priv(dpll, pin), dpll, + dpll_priv(dpll), &esync, extack); + if (ret == -EOPNOTSUPP) + return 0; + else if (ret) + return ret; + if (nla_put_64bit(msg, DPLL_A_PIN_ESYNC_FREQUENCY, sizeof(esync.freq), + &esync.freq, DPLL_A_PIN_PAD)) + return -EMSGSIZE; + if (nla_put_u32(msg, DPLL_A_PIN_ESYNC_PULSE, esync.pulse)) + return -EMSGSIZE; + for (i = 0; i < esync.range_num; i++) { + nest = nla_nest_start(msg, + DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED); + if (!nest) + return -EMSGSIZE; + if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MIN, + sizeof(esync.range[i].min), + &esync.range[i].min, DPLL_A_PIN_PAD)) + goto nest_cancel; + if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MAX, + sizeof(esync.range[i].max), + &esync.range[i].max, DPLL_A_PIN_PAD)) + goto nest_cancel; + nla_nest_end(msg, nest); + } + return 0; + +nest_cancel: + nla_nest_cancel(msg, nest); + return -EMSGSIZE; +} + static bool dpll_pin_is_freq_supported(struct dpll_pin *pin, u32 freq) { int fs; @@ -481,6 +526,9 @@ dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin, if (ret) return ret; ret = dpll_msg_add_ffo(msg, pin, ref, extack); + if (ret) + return ret; + ret = dpll_msg_add_pin_esync(msg, pin, ref, extack); if (ret) return ret; if (xa_empty(&pin->parent_refs)) @@ -738,6 +786,83 @@ dpll_pin_freq_set(struct dpll_pin *pin, struct nlattr *a, return ret; } +static int +dpll_pin_esync_set(struct dpll_pin *pin, struct nlattr *a, + struct netlink_ext_ack *extack) +{ + struct dpll_pin_ref *ref, *failed; + const struct dpll_pin_ops *ops; + struct dpll_pin_esync esync; + u64 freq = nla_get_u64(a); + struct dpll_device *dpll; + bool supported = false; + unsigned long i; + int ret; + + xa_for_each(&pin->dpll_refs, i, ref) { + ops = dpll_pin_ops(ref); + if (!ops->esync_set || !ops->esync_get) { + NL_SET_ERR_MSG(extack, + "embedded sync feature is not supported by this device"); + return -EOPNOTSUPP; + } + } + ref = dpll_xa_ref_dpll_first(&pin->dpll_refs); + ops = dpll_pin_ops(ref); + dpll = ref->dpll; + ret = ops->esync_get(pin, dpll_pin_on_dpll_priv(dpll, pin), dpll, + dpll_priv(dpll), &esync, extack); + if (ret) { + NL_SET_ERR_MSG(extack, "unable to get current embedded sync frequency value"); + return ret; + } + if (freq == esync.freq) + return 0; + for (i = 0; i < esync.range_num; i++) + if (freq <= esync.range[i].max && freq >= esync.range[i].min) + supported = true; + if (!supported) { + NL_SET_ERR_MSG_ATTR(extack, a, + "requested embedded sync frequency value is not supported by this device"); + return -EINVAL; + } + + xa_for_each(&pin->dpll_refs, i, ref) { + void *pin_dpll_priv; + + ops = dpll_pin_ops(ref); + dpll = ref->dpll; + pin_dpll_priv = dpll_pin_on_dpll_priv(dpll, pin); + ret = ops->esync_set(pin, pin_dpll_priv, dpll, dpll_priv(dpll), + freq, extack); + if (ret) { + failed = ref; + NL_SET_ERR_MSG_FMT(extack, + "embedded sync frequency set failed for dpll_id: %u", + dpll->id); + goto rollback; + } + } + __dpll_pin_change_ntf(pin); + + return 0; + +rollback: + xa_for_each(&pin->dpll_refs, i, ref) { + void *pin_dpll_priv; + + if (ref == failed) + break; + ops = dpll_pin_ops(ref); + dpll = ref->dpll; + pin_dpll_priv = dpll_pin_on_dpll_priv(dpll, pin); + if (ops->esync_set(pin, pin_dpll_priv, dpll, dpll_priv(dpll), + esync.freq, extack)) + NL_SET_ERR_MSG(extack, "set embedded sync frequency rollback failed"); + } + return ret; +} + static int dpll_pin_on_pin_state_set(struct dpll_pin *pin, u32 parent_idx, enum dpll_pin_state state, @@ -1039,6 +1164,11 @@ dpll_pin_set_from_nlattr(struct dpll_pin *pin, struct genl_info *info) if (ret) return ret; break; + case DPLL_A_PIN_ESYNC_FREQUENCY: + ret = dpll_pin_esync_set(pin, a, info->extack); + if (ret) + return ret; + break; } } diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c index 1e95f5397cfce..fe9b6893d2614 100644 --- a/drivers/dpll/dpll_nl.c +++ b/drivers/dpll/dpll_nl.c @@ -62,7 +62,7 @@ static const struct nla_policy dpll_pin_get_dump_nl_policy[DPLL_A_PIN_ID + 1] = }; /* DPLL_CMD_PIN_SET - do */ -static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_PHASE_ADJUST + 1] = { +static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_ESYNC_FREQUENCY + 1] = { [DPLL_A_PIN_ID] = { .type = NLA_U32, }, [DPLL_A_PIN_FREQUENCY] = { .type = NLA_U64, }, [DPLL_A_PIN_DIRECTION] = NLA_POLICY_RANGE(NLA_U32, 1, 2), @@ -71,6 +71,7 @@ static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_PHASE_ADJUST + [DPLL_A_PIN_PARENT_DEVICE] = NLA_POLICY_NESTED(dpll_pin_parent_device_nl_policy), [DPLL_A_PIN_PARENT_PIN] = NLA_POLICY_NESTED(dpll_pin_parent_pin_nl_policy), [DPLL_A_PIN_PHASE_ADJUST] = { .type = NLA_S32, }, + [DPLL_A_PIN_ESYNC_FREQUENCY] = { .type = NLA_U64, }, }; /* Ops table for dpll */ @@ -138,7 +139,7 @@ static const struct genl_split_ops dpll_nl_ops[] = { .doit = dpll_nl_pin_set_doit, .post_doit = dpll_pin_post_doit, .policy = dpll_pin_set_nl_policy, - .maxattr = DPLL_A_PIN_PHASE_ADJUST, + .maxattr = DPLL_A_PIN_ESYNC_FREQUENCY, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, }; diff --git a/include/linux/dpll.h b/include/linux/dpll.h index d275736230b3b..81f7b623d0ba6 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -15,6 +15,7 @@ struct dpll_device; struct dpll_pin; +struct dpll_pin_esync; struct dpll_device_ops { int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv, @@ -83,6 +84,13 @@ struct dpll_pin_ops { int (*ffo_get)(const struct dpll_pin *pin, void *pin_priv, const struct dpll_device *dpll, void *dpll_priv, s64 *ffo, struct netlink_ext_ack *extack); + int (*esync_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 freq, struct netlink_ext_ack *extack); + int (*esync_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + struct dpll_pin_esync *esync, + struct netlink_ext_ack *extack); }; struct dpll_pin_frequency { @@ -111,6 +119,13 @@ struct dpll_pin_phase_adjust_range { s32 max; }; +struct dpll_pin_esync { + u64 freq; + const struct dpll_pin_frequency *range; + u8 range_num; + u8 pulse; +}; + struct dpll_pin_properties { const char *board_label; const char *panel_label; diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index 0c13d7f1a1bc3..b0654ade7b7eb 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -210,6 +210,9 @@ enum dpll_a_pin { DPLL_A_PIN_PHASE_ADJUST, DPLL_A_PIN_PHASE_OFFSET, DPLL_A_PIN_FRACTIONAL_FREQUENCY_OFFSET, + DPLL_A_PIN_ESYNC_FREQUENCY, + DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED, + DPLL_A_PIN_ESYNC_PULSE, __DPLL_A_PIN_MAX, DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1) From 87abc5666ab753e8c31a2d39df3b5233f4e47b43 Mon Sep 17 00:00:00 2001 From: Arkadiusz Kubalewski Date: Fri, 23 Aug 2024 00:25:13 +0200 Subject: [PATCH 382/385] ice: add callbacks for Embedded SYNC enablement on dpll pins Allow the user to get and set configuration of Embedded SYNC feature on the ice driver dpll pins. Reviewed-by: Aleksandr Loktionov Signed-off-by: Arkadiusz Kubalewski Reviewed-by: Jiri Pirko Link: https://patch.msgid.link/20240822222513.255179-3-arkadiusz.kubalewski@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ice/ice_dpll.c | 223 +++++++++++++++++++++- drivers/net/ethernet/intel/ice/ice_dpll.h | 1 + 2 files changed, 221 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index e92be6f130a3d..cd95705d1e7fd 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -9,6 +9,7 @@ #define ICE_CGU_STATE_ACQ_ERR_THRESHOLD 50 #define ICE_DPLL_PIN_IDX_INVALID 0xff #define ICE_DPLL_RCLK_NUM_PER_PF 1 +#define ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT 25 /** * enum ice_dpll_pin_type - enumerate ice pin types: @@ -30,6 +31,10 @@ static const char * const pin_type_name[] = { [ICE_DPLL_PIN_TYPE_RCLK_INPUT] = "rclk-input", }; +static const struct dpll_pin_frequency ice_esync_range[] = { + DPLL_PIN_FREQUENCY_RANGE(0, DPLL_PIN_FREQUENCY_1_HZ), +}; + /** * ice_dpll_is_reset - check if reset is in progress * @pf: private board structure @@ -394,8 +399,8 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin, switch (pin_type) { case ICE_DPLL_PIN_TYPE_INPUT: - ret = ice_aq_get_input_pin_cfg(&pf->hw, pin->idx, NULL, NULL, - NULL, &pin->flags[0], + ret = ice_aq_get_input_pin_cfg(&pf->hw, pin->idx, &pin->status, + NULL, NULL, &pin->flags[0], &pin->freq, &pin->phase_adjust); if (ret) goto err; @@ -430,7 +435,7 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin, goto err; parent &= ICE_AQC_GET_CGU_OUT_CFG_DPLL_SRC_SEL; - if (ICE_AQC_SET_CGU_OUT_CFG_OUT_EN & pin->flags[0]) { + if (ICE_AQC_GET_CGU_OUT_CFG_OUT_EN & pin->flags[0]) { pin->state[pf->dplls.eec.dpll_idx] = parent == pf->dplls.eec.dpll_idx ? DPLL_PIN_STATE_CONNECTED : @@ -1098,6 +1103,214 @@ ice_dpll_phase_offset_get(const struct dpll_pin *pin, void *pin_priv, return 0; } +/** + * ice_dpll_output_esync_set - callback for setting embedded sync + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @freq: requested embedded sync frequency + * @extack: error reporting + * + * Dpll subsystem callback. Handler for setting embedded sync frequency value + * on output pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_output_esync_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 freq, struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + u8 flags = 0; + int ret; + + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); + if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_OUT_EN) + flags = ICE_AQC_SET_CGU_OUT_CFG_OUT_EN; + if (freq == DPLL_PIN_FREQUENCY_1_HZ) { + if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) { + ret = 0; + } else { + flags |= ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN; + ret = ice_aq_set_output_pin_cfg(&pf->hw, p->idx, flags, + 0, 0, 0); + } + } else { + if (!(p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN)) { + ret = 0; + } else { + flags &= ~ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN; + ret = ice_aq_set_output_pin_cfg(&pf->hw, p->idx, flags, + 0, 0, 0); + } + } + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_output_esync_get - callback for getting embedded sync config + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @esync: on success holds embedded sync pin properties + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting embedded sync frequency value + * and capabilities on output pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_output_esync_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + struct dpll_pin_esync *esync, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); + if (!(p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_ABILITY) || + p->freq != DPLL_PIN_FREQUENCY_10_MHZ) { + mutex_unlock(&pf->dplls.lock); + return -EOPNOTSUPP; + } + esync->range = ice_esync_range; + esync->range_num = ARRAY_SIZE(ice_esync_range); + if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) { + esync->freq = DPLL_PIN_FREQUENCY_1_HZ; + esync->pulse = ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT; + } else { + esync->freq = 0; + esync->pulse = 0; + } + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_input_esync_set - callback for setting embedded sync + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @freq: requested embedded sync frequency + * @extack: error reporting + * + * Dpll subsystem callback. Handler for setting embedded sync frequency value + * on input pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_input_esync_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 freq, struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + u8 flags_en = 0; + int ret; + + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); + if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN) + flags_en = ICE_AQC_SET_CGU_IN_CFG_FLG2_INPUT_EN; + if (freq == DPLL_PIN_FREQUENCY_1_HZ) { + if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN) { + ret = 0; + } else { + flags_en |= ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN; + ret = ice_aq_set_input_pin_cfg(&pf->hw, p->idx, 0, + flags_en, 0, 0); + } + } else { + if (!(p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN)) { + ret = 0; + } else { + flags_en &= ~ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN; + ret = ice_aq_set_input_pin_cfg(&pf->hw, p->idx, 0, + flags_en, 0, 0); + } + } + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_input_esync_get - callback for getting embedded sync config + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @esync: on success holds embedded sync pin properties + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting embedded sync frequency value + * and capabilities on input pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_input_esync_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + struct dpll_pin_esync *esync, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); + if (!(p->status & ICE_AQC_GET_CGU_IN_CFG_STATUS_ESYNC_CAP) || + p->freq != DPLL_PIN_FREQUENCY_10_MHZ) { + mutex_unlock(&pf->dplls.lock); + return -EOPNOTSUPP; + } + esync->range = ice_esync_range; + esync->range_num = ARRAY_SIZE(ice_esync_range); + if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN) { + esync->freq = DPLL_PIN_FREQUENCY_1_HZ; + esync->pulse = ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT; + } else { + esync->freq = 0; + esync->pulse = 0; + } + mutex_unlock(&pf->dplls.lock); + + return 0; +} + /** * ice_dpll_rclk_state_on_pin_set - set a state on rclk pin * @pin: pointer to a pin @@ -1222,6 +1435,8 @@ static const struct dpll_pin_ops ice_dpll_input_ops = { .phase_adjust_get = ice_dpll_pin_phase_adjust_get, .phase_adjust_set = ice_dpll_input_phase_adjust_set, .phase_offset_get = ice_dpll_phase_offset_get, + .esync_set = ice_dpll_input_esync_set, + .esync_get = ice_dpll_input_esync_get, }; static const struct dpll_pin_ops ice_dpll_output_ops = { @@ -1232,6 +1447,8 @@ static const struct dpll_pin_ops ice_dpll_output_ops = { .direction_get = ice_dpll_output_direction, .phase_adjust_get = ice_dpll_pin_phase_adjust_get, .phase_adjust_set = ice_dpll_output_phase_adjust_set, + .esync_set = ice_dpll_output_esync_set, + .esync_get = ice_dpll_output_esync_get, }; static const struct dpll_device_ops ice_dpll_ops = { diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h index 93172e93995b9..c320f1bf7d6d6 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.h +++ b/drivers/net/ethernet/intel/ice/ice_dpll.h @@ -31,6 +31,7 @@ struct ice_dpll_pin { struct dpll_pin_properties prop; u32 freq; s32 phase_adjust; + u8 status; }; /** ice_dpll - store info required for DPLL control From 938863727076f684abb39d1d0f9dce1924e9028e Mon Sep 17 00:00:00 2001 From: Boris Sukholitko Date: Thu, 22 Aug 2024 13:35:08 +0300 Subject: [PATCH 383/385] tc: adjust network header after 2nd vlan push skb network header of the single-tagged vlan packet continues to point the vlan payload (e.g. IP) after second vlan tag is pushed by tc act_vlan. This causes problem at the dissector which expects double-tagged packet network header to point to the inner vlan. The fix is to adjust network header in tcf_act_vlan.c but requires refactoring of skb_vlan_push function. Consider the following shell script snippet configuring TC rules on the veth interface: ip link add veth0 type veth peer veth1 ip link set veth0 up ip link set veth1 up tc qdisc add dev veth0 clsact tc filter add dev veth0 ingress pref 10 chain 0 flower \ num_of_vlans 2 cvlan_ethtype 0x800 action goto chain 5 tc filter add dev veth0 ingress pref 20 chain 0 flower \ num_of_vlans 1 action vlan push id 100 \ protocol 0x8100 action goto chain 5 tc filter add dev veth0 ingress pref 30 chain 5 flower \ num_of_vlans 2 cvlan_ethtype 0x800 action simple sdata "success" Sending double-tagged vlan packet with the IP payload inside: cat <protocol; } else { vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan); if (!vlan) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } proto = vlan->h_vlan_encapsulated_proto; nhoff += sizeof(*vlan); } The "else" clause above gets the protocol of the encapsulated packet from the skb data at the network header location. printk debugging has showed that in the good double-tagged packet case proto is htons(0x800 == ETH_P_IP) as expected. However in the single-tagged packet case proto is garbage leading to the failure to match tc filter 30. proto is being set from the skb header pointed by nhoff parameter which is defined at the beginning of __skb_flow_dissect (net/core/flow_dissector.c:1055 in the current version): nhoff = skb_network_offset(skb); Therefore the culprit seems to be that the skb network offset is different between double-tagged packet received from the interface and single-tagged packet having its vlan tag pushed by TC. Lets look at the interesting points of the lifetime of the single/double tagged packets as they traverse our packet flow. Both of them will start at __netif_receive_skb_core where the first vlan tag will be stripped: if (eth_type_vlan(skb->protocol)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; } At this stage in double-tagged case skb->data points to the second vlan tag while in single-tagged case skb->data points to the network (eg. IP) header. Looking at TC vlan push action (net/sched/act_vlan.c) we have the following code at tcf_vlan_act (interesting points are in square brackets): if (skb_at_tc_ingress(skb)) [1] skb_push_rcsum(skb, skb->mac_len); .... case TCA_VLAN_ACT_PUSH: err = skb_vlan_push(skb, p->tcfv_push_proto, p->tcfv_push_vid | (p->tcfv_push_prio << VLAN_PRIO_SHIFT), 0); if (err) goto drop; break; .... out: if (skb_at_tc_ingress(skb)) [3] skb_pull_rcsum(skb, skb->mac_len); And skb_vlan_push (net/core/skbuff.c:6204) function does: err = __vlan_insert_tag(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (err) return err; skb->protocol = skb->vlan_proto; [2] skb->mac_len += VLAN_HLEN; in the case of pushing the second tag. Lets look at what happens with skb->data of the single-tagged packet at each of the above points: 1. As a result of the skb_push_rcsum, skb->data is moved back to the start of the packet. 2. First VLAN tag is moved from the skb into packet buffer, skb->mac_len is incremented, skb->data still points to the start of the packet. 3. As a result of the skb_pull_rcsum, skb->data is moved forward by the modified skb->mac_len, thus pointing to the network header again. Then __skb_flow_dissect will get confused by having double-tagged vlan packet with the skb->data at the network header. The solution for the bug is to preserve "skb->data at second vlan header" semantics in the skb_vlan_push function. We do this by manipulating skb->network_header rather than skb->mac_len. skb_vlan_push callers are updated to do skb_reset_mac_len. Signed-off-by: Boris Sukholitko Signed-off-by: Paolo Abeni --- net/core/filter.c | 1 + net/core/skbuff.c | 2 +- net/openvswitch/actions.c | 8 ++++++-- net/sched/act_vlan.c | 1 + 4 files changed, 9 insertions(+), 3 deletions(-) diff --git a/net/core/filter.c b/net/core/filter.c index 40b2cacc0df05..f09d875cc0531 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3190,6 +3190,7 @@ BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, bpf_push_mac_rcsum(skb); ret = skb_vlan_push(skb, vlan_proto, vlan_tci); bpf_pull_mac_rcsum(skb); + skb_reset_mac_len(skb); bpf_compute_data_pointers(skb); return ret; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6022c7359385f..a52638363ea5c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -6243,7 +6243,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) return err; skb->protocol = skb->vlan_proto; - skb->mac_len += VLAN_HLEN; + skb->network_header -= VLAN_HLEN; skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 101f9a23792c4..16e2600146844 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -237,14 +237,18 @@ static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key) static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_action_push_vlan *vlan) { + int err; + if (skb_vlan_tag_present(skb)) { invalidate_flow_key(key); } else { key->eth.vlan.tci = vlan->vlan_tci; key->eth.vlan.tpid = vlan->vlan_tpid; } - return skb_vlan_push(skb, vlan->vlan_tpid, - ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK); + err = skb_vlan_push(skb, vlan->vlan_tpid, + ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK); + skb_reset_mac_len(skb); + return err; } /* 'src' is already properly masked. */ diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 22f4b1e8ade9f..383bf18b6862f 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -96,6 +96,7 @@ TC_INDIRECT_SCOPE int tcf_vlan_act(struct sk_buff *skb, if (skb_at_tc_ingress(skb)) skb_pull_rcsum(skb, skb->mac_len); + skb_reset_mac_len(skb); return action; drop: From 59c330eccee82f9e53421dd8a83b1bc236f4557a Mon Sep 17 00:00:00 2001 From: Boris Sukholitko Date: Thu, 22 Aug 2024 13:35:09 +0300 Subject: [PATCH 384/385] selftests: tc_actions: test ingress 2nd vlan push Add new test checking the correctness of inner vlan flushing to the skb data when outer vlan tag is added through act_vlan on ingress. Signed-off-by: Boris Sukholitko Signed-off-by: Paolo Abeni --- .../selftests/net/forwarding/tc_actions.sh | 23 ++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index 5896296365022..f2f1e99a90b22 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -4,7 +4,7 @@ ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ mirred_egress_mirror_test matchall_mirred_egress_mirror_test \ gact_trap_test mirred_egress_to_ingress_test \ - mirred_egress_to_ingress_tcp_test" + mirred_egress_to_ingress_tcp_test ingress_2nd_vlan_push" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -244,6 +244,27 @@ mirred_egress_to_ingress_tcp_test() log_test "mirred_egress_to_ingress_tcp ($tcflags)" } +ingress_2nd_vlan_push() +{ + tc filter add dev $swp1 ingress pref 20 chain 0 handle 20 flower \ + $tcflags num_of_vlans 1 \ + action vlan push id 100 protocol 0x8100 action goto chain 5 + tc filter add dev $swp1 ingress pref 30 chain 5 handle 30 flower \ + $tcflags num_of_vlans 2 \ + cvlan_ethtype 0x800 action pass + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -Q 10 -q + + tc_check_packets "dev $swp1 ingress" 30 1 + check_err $? "No double-vlan packets received" + + tc filter del dev $swp1 ingress pref 20 chain 0 handle 20 flower + tc filter del dev $swp1 ingress pref 30 chain 5 handle 30 flower + + log_test "ingress_2nd_vlan_push ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} From 2da44703a54403b9048ba268b2896dc0537a154f Mon Sep 17 00:00:00 2001 From: Boris Sukholitko Date: Thu, 22 Aug 2024 13:35:10 +0300 Subject: [PATCH 385/385] selftests: tc_actions: test egress 2nd vlan push Add new test checking the correctness of inner vlan flushing to the skb data when outer vlan tag is added through act_vlan on egress. Signed-off-by: Boris Sukholitko Signed-off-by: Paolo Abeni --- .../selftests/net/forwarding/tc_actions.sh | 25 ++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index f2f1e99a90b22..ea89e558672db 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -4,7 +4,8 @@ ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ mirred_egress_mirror_test matchall_mirred_egress_mirror_test \ gact_trap_test mirred_egress_to_ingress_test \ - mirred_egress_to_ingress_tcp_test ingress_2nd_vlan_push" + mirred_egress_to_ingress_tcp_test \ + ingress_2nd_vlan_push egress_2nd_vlan_push" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -265,6 +266,28 @@ ingress_2nd_vlan_push() log_test "ingress_2nd_vlan_push ($tcflags)" } +egress_2nd_vlan_push() +{ + tc filter add dev $h1 egress pref 20 chain 0 handle 20 flower \ + $tcflags num_of_vlans 0 \ + action vlan push id 10 protocol 0x8100 \ + pipe action vlan push id 100 protocol 0x8100 action goto chain 5 + tc filter add dev $h1 egress pref 30 chain 5 handle 30 flower \ + $tcflags num_of_vlans 2 \ + cvlan_ethtype 0x800 action pass + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h1 egress" 30 1 + check_err $? "No double-vlan packets received" + + tc filter del dev $h1 egress pref 20 chain 0 handle 20 flower + tc filter del dev $h1 egress pref 30 chain 5 handle 30 flower + + log_test "egress_2nd_vlan_push ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]}