From: Sasha Levin Date: Mon, 29 Nov 2021 00:41:00 +0000 (-0500) Subject: Fixes for 5.10 X-Git-Tag: v5.15.6~50 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=df8fb050547181e62fca94e8b47753dbba863b86;p=thirdparty%2Fkernel%2Fstable-queue.git Fixes for 5.10 Signed-off-by: Sasha Levin --- diff --git a/queue-5.10/alsa-intel-dsp-config-add-quirk-for-jsl-devices-base.patch b/queue-5.10/alsa-intel-dsp-config-add-quirk-for-jsl-devices-base.patch new file mode 100644 index 00000000000..677adba3273 --- /dev/null +++ b/queue-5.10/alsa-intel-dsp-config-add-quirk-for-jsl-devices-base.patch @@ -0,0 +1,52 @@ +From 9b65aaa01f8698cac7b9a7a5bbbe9859d1187e6c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 27 Oct 2021 10:32:54 +0800 +Subject: ALSA: intel-dsp-config: add quirk for JSL devices based on ES8336 + codec + +From: Pierre-Louis Bossart + +[ Upstream commit fa9730b4f28b7bd183d28a0bf636ab7108de35d7 ] + +These devices are based on an I2C/I2S device, we need to force the use +of the SOF driver otherwise the legacy HDaudio driver will be loaded - +only HDMI will be supported. + +We previously added support for other Intel platforms but missed +JasperLake. + +BugLink: https://github.com/thesofproject/linux/issues/3210 +Fixes: 9d36ceab9415 ('ALSA: intel-dsp-config: add quirk for APL/GLK/TGL devices based on ES8336 codec') +Signed-off-by: Pierre-Louis Bossart +Reviewed-by: Kai Vehmanen +Signed-off-by: Bard Liao +Link: https://lore.kernel.org/r/20211027023254.24955-1-yung-chuan.liao@linux.intel.com +Signed-off-by: Takashi Iwai +Signed-off-by: Sasha Levin +--- + sound/hda/intel-dsp-config.c | 9 +++++++++ + 1 file changed, 9 insertions(+) + +diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c +index 6cdb3db7507b1..fc61571a3ac73 100644 +--- a/sound/hda/intel-dsp-config.c ++++ b/sound/hda/intel-dsp-config.c +@@ -298,6 +298,15 @@ static const struct config_entry config_table[] = { + }, + #endif + ++/* JasperLake */ ++#if IS_ENABLED(CONFIG_SND_SOC_SOF_JASPERLAKE) ++ { ++ .flags = FLAG_SOF, ++ .device = 0x4dc8, ++ .codec_hid = "ESSX8336", ++ }, ++#endif ++ + /* Tigerlake */ + #if IS_ENABLED(CONFIG_SND_SOC_SOF_TIGERLAKE) + { +-- +2.33.0 + diff --git a/queue-5.10/arm-dts-bcm2711-fix-pcie-interrupts.patch b/queue-5.10/arm-dts-bcm2711-fix-pcie-interrupts.patch new file mode 100644 index 00000000000..62a64e62fc5 --- /dev/null +++ b/queue-5.10/arm-dts-bcm2711-fix-pcie-interrupts.patch @@ -0,0 +1,51 @@ +From 3afe2c501d88122221ab85a01f6313d7eb512487 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 29 Oct 2021 14:09:26 -0700 +Subject: ARM: dts: bcm2711: Fix PCIe interrupts + +From: Florian Fainelli + +[ Upstream commit 98481f3d72fb88cb5b973153434061015f094925 ] + +The PCIe host bridge has two interrupt lines, one that goes towards it +PCIE_INTR2 second level interrupt controller and one for its MSI second +level interrupt controller. The first interrupt line is not currently +managed by the driver, which is why it was not a functional problem. + +The interrupt-map property was also only listing the PCI_INTA interrupts +when there are also the INTB, C and D. + +Reported-by: Jim Quinlan +Fixes: d5c8dc0d4c88 ("ARM: dts: bcm2711: Enable PCIe controller") +Signed-off-by: Florian Fainelli +Signed-off-by: Sasha Levin +--- + arch/arm/boot/dts/bcm2711.dtsi | 8 +++++++- + 1 file changed, 7 insertions(+), 1 deletion(-) + +diff --git a/arch/arm/boot/dts/bcm2711.dtsi b/arch/arm/boot/dts/bcm2711.dtsi +index 398ecd7b9b68b..4ade854bdcdaf 100644 +--- a/arch/arm/boot/dts/bcm2711.dtsi ++++ b/arch/arm/boot/dts/bcm2711.dtsi +@@ -480,11 +480,17 @@ pcie0: pcie@7d500000 { + #address-cells = <3>; + #interrupt-cells = <1>; + #size-cells = <2>; +- interrupts = , ++ interrupts = , + ; + interrupt-names = "pcie", "msi"; + interrupt-map-mask = <0x0 0x0 0x0 0x7>; + interrupt-map = <0 0 0 1 &gicv2 GIC_SPI 143 ++ IRQ_TYPE_LEVEL_HIGH>, ++ <0 0 0 2 &gicv2 GIC_SPI 144 ++ IRQ_TYPE_LEVEL_HIGH>, ++ <0 0 0 3 &gicv2 GIC_SPI 145 ++ IRQ_TYPE_LEVEL_HIGH>, ++ <0 0 0 4 &gicv2 GIC_SPI 146 + IRQ_TYPE_LEVEL_HIGH>; + msi-controller; + msi-parent = <&pcie0>; +-- +2.33.0 + diff --git a/queue-5.10/arm-dts-bcm5301x-add-interrupt-properties-to-gpio-no.patch b/queue-5.10/arm-dts-bcm5301x-add-interrupt-properties-to-gpio-no.patch new file mode 100644 index 00000000000..84bc15fa064 --- /dev/null +++ b/queue-5.10/arm-dts-bcm5301x-add-interrupt-properties-to-gpio-no.patch @@ -0,0 +1,36 @@ +From cf030f04d883fc7ac039fe9b46cec81d9c0ba5ec Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 28 Oct 2021 09:46:53 -0700 +Subject: ARM: dts: BCM5301X: Add interrupt properties to GPIO node + +From: Florian Fainelli + +[ Upstream commit 40f7342f0587639e5ad625adaa15efdd3cffb18f ] + +The GPIO controller is also an interrupt controller provider and is +currently missing the appropriate 'interrupt-controller' and +'#interrupt-cells' properties to denote that. + +Fixes: fb026d3de33b ("ARM: BCM5301X: Add Broadcom's bus-axi to the DTS file") +Signed-off-by: Florian Fainelli +Signed-off-by: Sasha Levin +--- + arch/arm/boot/dts/bcm5301x.dtsi | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi +index e97a9c0904a98..9fdad20c40d17 100644 +--- a/arch/arm/boot/dts/bcm5301x.dtsi ++++ b/arch/arm/boot/dts/bcm5301x.dtsi +@@ -242,6 +242,8 @@ chipcommon: chipcommon@0 { + + gpio-controller; + #gpio-cells = <2>; ++ interrupt-controller; ++ #interrupt-cells = <2>; + }; + + pcie0: pcie@12000 { +-- +2.33.0 + diff --git a/queue-5.10/arm-dts-bcm5301x-fix-i2c-controller-interrupt.patch b/queue-5.10/arm-dts-bcm5301x-fix-i2c-controller-interrupt.patch new file mode 100644 index 00000000000..f75853b48a6 --- /dev/null +++ b/queue-5.10/arm-dts-bcm5301x-fix-i2c-controller-interrupt.patch @@ -0,0 +1,38 @@ +From 550d0a0bb5cc0b0ca2927bc78b7dff62aab46c56 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 27 Oct 2021 12:37:29 -0700 +Subject: ARM: dts: BCM5301X: Fix I2C controller interrupt + +From: Florian Fainelli + +[ Upstream commit 754c4050a00e802e122690112fc2c3a6abafa7e2 ] + +The I2C interrupt controller line is off by 32 because the datasheet +describes interrupt inputs into the GIC which are for Shared Peripheral +Interrupts and are starting at offset 32. The ARM GIC binding expects +the SPI interrupts to be numbered from 0 relative to the SPI base. + +Fixes: bb097e3e0045 ("ARM: dts: BCM5301X: Add I2C support to the DT") +Tested-by: Christian Lamparter +Signed-off-by: Florian Fainelli +Signed-off-by: Sasha Levin +--- + arch/arm/boot/dts/bcm5301x.dtsi | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi +index 72b0df6910bd5..e97a9c0904a98 100644 +--- a/arch/arm/boot/dts/bcm5301x.dtsi ++++ b/arch/arm/boot/dts/bcm5301x.dtsi +@@ -408,7 +408,7 @@ uart2: serial@18008000 { + i2c0: i2c@18009000 { + compatible = "brcm,iproc-i2c"; + reg = <0x18009000 0x50>; +- interrupts = ; ++ interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + clock-frequency = <100000>; +-- +2.33.0 + diff --git a/queue-5.10/arm-socfpga-fix-crash-with-config_fortiry_source.patch b/queue-5.10/arm-socfpga-fix-crash-with-config_fortiry_source.patch new file mode 100644 index 00000000000..ea2c33a7135 --- /dev/null +++ b/queue-5.10/arm-socfpga-fix-crash-with-config_fortiry_source.patch @@ -0,0 +1,81 @@ +From 02fd17338dcb148dddd0a48764e26c2c379f709e Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 18 Nov 2021 15:25:08 +0100 +Subject: ARM: socfpga: Fix crash with CONFIG_FORTIRY_SOURCE + +From: Takashi Iwai + +[ Upstream commit 187bea472600dcc8d2eb714335053264dd437172 ] + +When CONFIG_FORTIFY_SOURCE is set, memcpy() checks the potential +buffer overflow and panics. The code in sofcpga bootstrapping +contains the memcpy() calls are mistakenly translated as the shorter +size, hence it triggers a panic as if it were overflowing. + +This patch changes the secondary_trampoline and *_end definitions +to arrays for avoiding the false-positive crash above. + +Fixes: 9c4566a117a6 ("ARM: socfpga: Enable SMP for socfpga") +Suggested-by: Kees Cook +Buglink: https://bugzilla.suse.com/show_bug.cgi?id=1192473 +Link: https://lore.kernel.org/r/20211117193244.31162-1-tiwai@suse.de +Signed-off-by: Takashi Iwai +Signed-off-by: Dinh Nguyen +Signed-off-by: Sasha Levin +--- + arch/arm/mach-socfpga/core.h | 2 +- + arch/arm/mach-socfpga/platsmp.c | 8 ++++---- + 2 files changed, 5 insertions(+), 5 deletions(-) + +diff --git a/arch/arm/mach-socfpga/core.h b/arch/arm/mach-socfpga/core.h +index fc2608b18a0d0..18f01190dcfd4 100644 +--- a/arch/arm/mach-socfpga/core.h ++++ b/arch/arm/mach-socfpga/core.h +@@ -33,7 +33,7 @@ extern void __iomem *sdr_ctl_base_addr; + u32 socfpga_sdram_self_refresh(u32 sdr_base); + extern unsigned int socfpga_sdram_self_refresh_sz; + +-extern char secondary_trampoline, secondary_trampoline_end; ++extern char secondary_trampoline[], secondary_trampoline_end[]; + + extern unsigned long socfpga_cpu1start_addr; + +diff --git a/arch/arm/mach-socfpga/platsmp.c b/arch/arm/mach-socfpga/platsmp.c +index fbb80b883e5dd..201191cf68f32 100644 +--- a/arch/arm/mach-socfpga/platsmp.c ++++ b/arch/arm/mach-socfpga/platsmp.c +@@ -20,14 +20,14 @@ + + static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle) + { +- int trampoline_size = &secondary_trampoline_end - &secondary_trampoline; ++ int trampoline_size = secondary_trampoline_end - secondary_trampoline; + + if (socfpga_cpu1start_addr) { + /* This will put CPU #1 into reset. */ + writel(RSTMGR_MPUMODRST_CPU1, + rst_manager_base_addr + SOCFPGA_RSTMGR_MODMPURST); + +- memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size); ++ memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size); + + writel(__pa_symbol(secondary_startup), + sys_manager_base_addr + (socfpga_cpu1start_addr & 0x000000ff)); +@@ -45,12 +45,12 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle) + + static int socfpga_a10_boot_secondary(unsigned int cpu, struct task_struct *idle) + { +- int trampoline_size = &secondary_trampoline_end - &secondary_trampoline; ++ int trampoline_size = secondary_trampoline_end - secondary_trampoline; + + if (socfpga_cpu1start_addr) { + writel(RSTMGR_MPUMODRST_CPU1, rst_manager_base_addr + + SOCFPGA_A10_RSTMGR_MODMPURST); +- memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size); ++ memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size); + + writel(__pa_symbol(secondary_startup), + sys_manager_base_addr + (socfpga_cpu1start_addr & 0x00000fff)); +-- +2.33.0 + diff --git a/queue-5.10/asoc-codecs-wcd934x-return-error-code-correctly-from.patch b/queue-5.10/asoc-codecs-wcd934x-return-error-code-correctly-from.patch new file mode 100644 index 00000000000..46d260ffb29 --- /dev/null +++ b/queue-5.10/asoc-codecs-wcd934x-return-error-code-correctly-from.patch @@ -0,0 +1,42 @@ +From aff29cdd7192dd64942b847f00c15215ee042510 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 16 Nov 2021 11:46:22 +0000 +Subject: ASoC: codecs: wcd934x: return error code correctly from hw_params + +From: Srinivas Kandagatla + +[ Upstream commit 006ea27c4e7037369085755c7b5389effa508c04 ] + +Error returned from wcd934x_slim_set_hw_params() are not passed to upper layer, +this could be misleading to the user which can start sending stream leading +to unnecessary errors. + +Fix this by properly returning the errors. + +Fixes: a61f3b4f476e ("ASoC: wcd934x: add support to wcd9340/wcd9341 codec") +Signed-off-by: Srinivas Kandagatla +Link: https://lore.kernel.org/r/20211116114623.11891-3-srinivas.kandagatla@linaro.org +Signed-off-by: Mark Brown +Signed-off-by: Sasha Levin +--- + sound/soc/codecs/wcd934x.c | 3 +-- + 1 file changed, 1 insertion(+), 2 deletions(-) + +diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c +index d18ae5e3ee809..699b59cd389c0 100644 +--- a/sound/soc/codecs/wcd934x.c ++++ b/sound/soc/codecs/wcd934x.c +@@ -1812,9 +1812,8 @@ static int wcd934x_hw_params(struct snd_pcm_substream *substream, + } + + wcd->dai[dai->id].sconfig.rate = params_rate(params); +- wcd934x_slim_set_hw_params(wcd, &wcd->dai[dai->id], substream->stream); + +- return 0; ++ return wcd934x_slim_set_hw_params(wcd, &wcd->dai[dai->id], substream->stream); + } + + static int wcd934x_hw_free(struct snd_pcm_substream *substream, +-- +2.33.0 + diff --git a/queue-5.10/asoc-qdsp6-q6asm-fix-q6asm_dai_prepare-error-handlin.patch b/queue-5.10/asoc-qdsp6-q6asm-fix-q6asm_dai_prepare-error-handlin.patch new file mode 100644 index 00000000000..10a75609701 --- /dev/null +++ b/queue-5.10/asoc-qdsp6-q6asm-fix-q6asm_dai_prepare-error-handlin.patch @@ -0,0 +1,70 @@ +From 2e0a7219361a97c34199ae8ca985f6c834b2eda8 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 16 Nov 2021 11:47:19 +0000 +Subject: ASoC: qdsp6: q6asm: fix q6asm_dai_prepare error handling + +From: Srinivas Kandagatla + +[ Upstream commit 721a94b4352dc8e47bff90b549a0118c39776756 ] + +Error handling in q6asm_dai_prepare() seems to be completely broken, +Fix this by handling it properly. + +Fixes: 2a9e92d371db ("ASoC: qdsp6: q6asm: Add q6asm dai driver") +Signed-off-by: Srinivas Kandagatla +Link: https://lore.kernel.org/r/20211116114721.12517-4-srinivas.kandagatla@linaro.org +Signed-off-by: Mark Brown +Signed-off-by: Sasha Levin +--- + sound/soc/qcom/qdsp6/q6asm-dai.c | 19 +++++++++++++------ + 1 file changed, 13 insertions(+), 6 deletions(-) + +diff --git a/sound/soc/qcom/qdsp6/q6asm-dai.c b/sound/soc/qcom/qdsp6/q6asm-dai.c +index 9766725c29166..84cf190aa01a6 100644 +--- a/sound/soc/qcom/qdsp6/q6asm-dai.c ++++ b/sound/soc/qcom/qdsp6/q6asm-dai.c +@@ -269,9 +269,7 @@ static int q6asm_dai_prepare(struct snd_soc_component *component, + + if (ret < 0) { + dev_err(dev, "%s: q6asm_open_write failed\n", __func__); +- q6asm_audio_client_free(prtd->audio_client); +- prtd->audio_client = NULL; +- return -ENOMEM; ++ goto open_err; + } + + prtd->session_id = q6asm_get_session_id(prtd->audio_client); +@@ -279,7 +277,7 @@ static int q6asm_dai_prepare(struct snd_soc_component *component, + prtd->session_id, substream->stream); + if (ret) { + dev_err(dev, "%s: stream reg failed ret:%d\n", __func__, ret); +- return ret; ++ goto routing_err; + } + + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { +@@ -301,10 +299,19 @@ static int q6asm_dai_prepare(struct snd_soc_component *component, + } + if (ret < 0) + dev_info(dev, "%s: CMD Format block failed\n", __func__); ++ else ++ prtd->state = Q6ASM_STREAM_RUNNING; + +- prtd->state = Q6ASM_STREAM_RUNNING; ++ return ret; + +- return 0; ++routing_err: ++ q6asm_cmd(prtd->audio_client, prtd->stream_id, CMD_CLOSE); ++open_err: ++ q6asm_unmap_memory_regions(substream->stream, prtd->audio_client); ++ q6asm_audio_client_free(prtd->audio_client); ++ prtd->audio_client = NULL; ++ ++ return ret; + } + + static int q6asm_dai_trigger(struct snd_soc_component *component, +-- +2.33.0 + diff --git a/queue-5.10/asoc-qdsp6-q6routing-conditionally-reset-frontend-mi.patch b/queue-5.10/asoc-qdsp6-q6routing-conditionally-reset-frontend-mi.patch new file mode 100644 index 00000000000..44f3404b226 --- /dev/null +++ b/queue-5.10/asoc-qdsp6-q6routing-conditionally-reset-frontend-mi.patch @@ -0,0 +1,55 @@ +From 7a5f572b2a69e6b28d77854d358a6e7e713589a4 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 16 Nov 2021 11:47:18 +0000 +Subject: ASoC: qdsp6: q6routing: Conditionally reset FrontEnd Mixer + +From: Srinivas Kandagatla + +[ Upstream commit 861afeac7990587588d057b2c0b3222331c3da29 ] + +Stream IDs are reused across multiple BackEnd mixers, do not reset the +stream mixers if they are not already set for that particular FrontEnd. + +Ex: +amixer cset iface=MIXER,name='SLIMBUS_0_RX Audio Mixer MultiMedia1' 1 + +would set the MultiMedia1 steam for SLIMBUS_0_RX, however doing below +command will reset previously setup MultiMedia1 stream, because both of them +are using MultiMedia1 PCM stream. + +amixer cset iface=MIXER,name='SLIMBUS_2_RX Audio Mixer MultiMedia1' 0 + +reset the FrontEnd Mixers conditionally to fix this issue. + +This is more noticeable in desktop setup, where in alsactl tries to restore +the alsa state and overwriting the previous mixer settings. + +Fixes: e3a33673e845 ("ASoC: qdsp6: q6routing: Add q6routing driver") +Signed-off-by: Srinivas Kandagatla +Link: https://lore.kernel.org/r/20211116114721.12517-3-srinivas.kandagatla@linaro.org +Signed-off-by: Mark Brown +Signed-off-by: Sasha Levin +--- + sound/soc/qcom/qdsp6/q6routing.c | 6 +++++- + 1 file changed, 5 insertions(+), 1 deletion(-) + +diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c +index 0a6b9433f6acf..934b3f282bccd 100644 +--- a/sound/soc/qcom/qdsp6/q6routing.c ++++ b/sound/soc/qcom/qdsp6/q6routing.c +@@ -491,7 +491,11 @@ static int msm_routing_put_audio_mixer(struct snd_kcontrol *kcontrol, + session->port_id = be_id; + snd_soc_dapm_mixer_update_power(dapm, kcontrol, 1, update); + } else { +- session->port_id = -1; ++ if (session->port_id == be_id) { ++ session->port_id = -1; ++ return 0; ++ } ++ + snd_soc_dapm_mixer_update_power(dapm, kcontrol, 0, update); + } + +-- +2.33.0 + diff --git a/queue-5.10/asoc-topology-add-missing-rwsem-around-snd_ctl_remov.patch b/queue-5.10/asoc-topology-add-missing-rwsem-around-snd_ctl_remov.patch new file mode 100644 index 00000000000..801cfdd170d --- /dev/null +++ b/queue-5.10/asoc-topology-add-missing-rwsem-around-snd_ctl_remov.patch @@ -0,0 +1,53 @@ +From c232d3fce5c2c6626b30526365b8a6f2b41f0c1c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 16 Nov 2021 08:18:12 +0100 +Subject: ASoC: topology: Add missing rwsem around snd_ctl_remove() calls + +From: Takashi Iwai + +[ Upstream commit 7e567b5ae06315ef2d70666b149962e2bb4b97af ] + +snd_ctl_remove() has to be called with card->controls_rwsem held (when +called after the card instantiation). This patch add the missing +rwsem calls around it. + +Fixes: 8a9782346dcc ("ASoC: topology: Add topology core") +Signed-off-by: Takashi Iwai +Link: https://lore.kernel.org/r/20211116071812.18109-1-tiwai@suse.de +Signed-off-by: Mark Brown +Signed-off-by: Sasha Levin +--- + sound/soc/soc-topology.c | 3 +++ + 1 file changed, 3 insertions(+) + +diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c +index 1030e11017b27..4d24ac255d253 100644 +--- a/sound/soc/soc-topology.c ++++ b/sound/soc/soc-topology.c +@@ -2873,6 +2873,7 @@ EXPORT_SYMBOL_GPL(snd_soc_tplg_widget_remove_all); + /* remove dynamic controls from the component driver */ + int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index) + { ++ struct snd_card *card = comp->card->snd_card; + struct snd_soc_dobj *dobj, *next_dobj; + int pass = SOC_TPLG_PASS_END; + +@@ -2880,6 +2881,7 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index) + while (pass >= SOC_TPLG_PASS_START) { + + /* remove mixer controls */ ++ down_write(&card->controls_rwsem); + list_for_each_entry_safe(dobj, next_dobj, &comp->dobj_list, + list) { + +@@ -2923,6 +2925,7 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp, u32 index) + break; + } + } ++ up_write(&card->controls_rwsem); + pass--; + } + +-- +2.33.0 + diff --git a/queue-5.10/drm-amd-display-set-plane-update-flags-for-all-plane.patch b/queue-5.10/drm-amd-display-set-plane-update-flags-for-all-plane.patch new file mode 100644 index 00000000000..a3224bd40dd --- /dev/null +++ b/queue-5.10/drm-amd-display-set-plane-update-flags-for-all-plane.patch @@ -0,0 +1,50 @@ +From fb5b815a668ed909f8d65e33ce6bc436488948d7 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 9 Nov 2021 11:24:10 -0500 +Subject: drm/amd/display: Set plane update flags for all planes in reset + +From: Nicholas Kazlauskas + +[ Upstream commit 21431f70f6014f81b0d118ff4fcee12b00b9dd70 ] + +[Why] +We're only setting the flags on stream[0]'s planes so this logic fails +if we have more than one stream in the state. + +This can cause a page flip timeout with multiple displays in the +configuration. + +[How] +Index into the stream_status array using the stream index - it's a 1:1 +mapping. + +Fixes: cdaae8371aa9 ("drm/amd/display: Handle GPU reset for DC block") + +Reviewed-by: Harry Wentland +Acked-by: Qingqing Zhuo +Signed-off-by: Nicholas Kazlauskas +Tested-by: Daniel Wheeler +Signed-off-by: Alex Deucher +Signed-off-by: Sasha Levin +--- + drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +index d9525fbedad2d..a5b6f36fe1d72 100644 +--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c ++++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +@@ -1963,8 +1963,8 @@ static int dm_resume(void *handle) + + for (i = 0; i < dc_state->stream_count; i++) { + dc_state->streams[i]->mode_changed = true; +- for (j = 0; j < dc_state->stream_status->plane_count; j++) { +- dc_state->stream_status->plane_states[j]->update_flags.raw ++ for (j = 0; j < dc_state->stream_status[i].plane_count; j++) { ++ dc_state->stream_status[i].plane_states[j]->update_flags.raw + = 0xffffffff; + } + } +-- +2.33.0 + diff --git a/queue-5.10/drm-nouveau-acr-fix-a-couple-null-vs-is_err-checks.patch b/queue-5.10/drm-nouveau-acr-fix-a-couple-null-vs-is_err-checks.patch new file mode 100644 index 00000000000..5406b1d88dd --- /dev/null +++ b/queue-5.10/drm-nouveau-acr-fix-a-couple-null-vs-is_err-checks.patch @@ -0,0 +1,66 @@ +From f968343e89673e54bc00f0c866d01708c74cdefd Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 18 Nov 2021 14:13:14 +0300 +Subject: drm/nouveau/acr: fix a couple NULL vs IS_ERR() checks + +From: Dan Carpenter + +[ Upstream commit b371fd131fcec59f6165c80778bdc2cd1abd616b ] + +The nvkm_acr_lsfw_add() function never returns NULL. It returns error +pointers on error. + +Fixes: 22dcda45a3d1 ("drm/nouveau/acr: implement new subdev to replace "secure boot"") +Signed-off-by: Dan Carpenter +Reviewed-by: Ben Skeggs +Signed-off-by: Karol Herbst +Link: https://patchwork.freedesktop.org/patch/msgid/20211118111314.GB1147@kili +Signed-off-by: Sasha Levin +--- + drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c | 6 ++++-- + drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c | 6 ++++-- + 2 files changed, 8 insertions(+), 4 deletions(-) + +diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c +index cd41b2e6cc879..18502fd6ebaa0 100644 +--- a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c ++++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c +@@ -207,11 +207,13 @@ int + gm200_acr_wpr_parse(struct nvkm_acr *acr) + { + const struct wpr_header *hdr = (void *)acr->wpr_fw->data; ++ struct nvkm_acr_lsfw *lsfw; + + while (hdr->falcon_id != WPR_HEADER_V0_FALCON_ID_INVALID) { + wpr_header_dump(&acr->subdev, hdr); +- if (!nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id)) +- return -ENOMEM; ++ lsfw = nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id); ++ if (IS_ERR(lsfw)) ++ return PTR_ERR(lsfw); + } + + return 0; +diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c +index 80eb9d8dbc803..e5c8303a5b7b7 100644 +--- a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c ++++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c +@@ -161,11 +161,13 @@ int + gp102_acr_wpr_parse(struct nvkm_acr *acr) + { + const struct wpr_header_v1 *hdr = (void *)acr->wpr_fw->data; ++ struct nvkm_acr_lsfw *lsfw; + + while (hdr->falcon_id != WPR_HEADER_V1_FALCON_ID_INVALID) { + wpr_header_v1_dump(&acr->subdev, hdr); +- if (!nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id)) +- return -ENOMEM; ++ lsfw = nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id); ++ if (IS_ERR(lsfw)) ++ return PTR_ERR(lsfw); + } + + return 0; +-- +2.33.0 + diff --git a/queue-5.10/drm-vc4-fix-error-code-in-vc4_create_object.patch b/queue-5.10/drm-vc4-fix-error-code-in-vc4_create_object.patch new file mode 100644 index 00000000000..aa4ce0bd712 --- /dev/null +++ b/queue-5.10/drm-vc4-fix-error-code-in-vc4_create_object.patch @@ -0,0 +1,38 @@ +From b06754c7ebf40f295c8e124493bad81adcfdd0be Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 18 Nov 2021 14:14:16 +0300 +Subject: drm/vc4: fix error code in vc4_create_object() + +From: Dan Carpenter + +[ Upstream commit 96c5f82ef0a145d3e56e5b26f2bf6dcd2ffeae1c ] + +The ->gem_create_object() functions are supposed to return NULL if there +is an error. None of the callers expect error pointers so returing one +will lead to an Oops. See drm_gem_vram_create(), for example. + +Fixes: c826a6e10644 ("drm/vc4: Add a BO cache.") +Signed-off-by: Dan Carpenter +Signed-off-by: Maxime Ripard +Link: https://patchwork.freedesktop.org/patch/msgid/20211118111416.GC1147@kili +Signed-off-by: Sasha Levin +--- + drivers/gpu/drm/vc4/vc4_bo.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c +index cc74a3f3a07af..9006b9861c90c 100644 +--- a/drivers/gpu/drm/vc4/vc4_bo.c ++++ b/drivers/gpu/drm/vc4/vc4_bo.c +@@ -389,7 +389,7 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size) + + bo = kzalloc(sizeof(*bo), GFP_KERNEL); + if (!bo) +- return ERR_PTR(-ENOMEM); ++ return NULL; + + bo->madv = VC4_MADV_WILLNEED; + refcount_set(&bo->usecnt, 0); +-- +2.33.0 + diff --git a/queue-5.10/erofs-fix-deadlock-when-shrink-erofs-slab.patch b/queue-5.10/erofs-fix-deadlock-when-shrink-erofs-slab.patch new file mode 100644 index 00000000000..3ad113df50d --- /dev/null +++ b/queue-5.10/erofs-fix-deadlock-when-shrink-erofs-slab.patch @@ -0,0 +1,83 @@ +From 93b37cb0a3fab40a0144aa198e9fe609282720cb Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 18 Nov 2021 21:58:44 +0800 +Subject: erofs: fix deadlock when shrink erofs slab + +From: Huang Jianan + +[ Upstream commit 57bbeacdbee72a54eb97d56b876cf9c94059fc34 ] + +We observed the following deadlock in the stress test under low +memory scenario: + +Thread A Thread B +- erofs_shrink_scan + - erofs_try_to_release_workgroup + - erofs_workgroup_try_to_freeze -- A + - z_erofs_do_read_page + - z_erofs_collection_begin + - z_erofs_register_collection + - erofs_insert_workgroup + - xa_lock(&sbi->managed_pslots) -- B + - erofs_workgroup_get + - erofs_wait_on_workgroup_freezed -- A + - xa_erase + - xa_lock(&sbi->managed_pslots) -- B + +To fix this, it needs to hold xa_lock before freezing the workgroup +since xarray will be touched then. So let's hold the lock before +accessing each workgroup, just like what we did with the radix tree +before. + +[ Gao Xiang: Jianhua Hao also reports this issue at + https://lore.kernel.org/r/b10b85df30694bac8aadfe43537c897a@xiaomi.com ] + +Link: https://lore.kernel.org/r/20211118135844.3559-1-huangjianan@oppo.com +Fixes: 64094a04414f ("erofs: convert workstn to XArray") +Reviewed-by: Chao Yu +Reviewed-by: Gao Xiang +Signed-off-by: Huang Jianan +Reported-by: Jianhua Hao +Signed-off-by: Gao Xiang +Signed-off-by: Sasha Levin +--- + fs/erofs/utils.c | 8 ++++++-- + 1 file changed, 6 insertions(+), 2 deletions(-) + +diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c +index de9986d2f82fd..5c11199d753a6 100644 +--- a/fs/erofs/utils.c ++++ b/fs/erofs/utils.c +@@ -154,7 +154,7 @@ static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi, + * however in order to avoid some race conditions, add a + * DBG_BUGON to observe this in advance. + */ +- DBG_BUGON(xa_erase(&sbi->managed_pslots, grp->index) != grp); ++ DBG_BUGON(__xa_erase(&sbi->managed_pslots, grp->index) != grp); + + /* last refcount should be connected with its managed pslot. */ + erofs_workgroup_unfreeze(grp, 0); +@@ -169,15 +169,19 @@ static unsigned long erofs_shrink_workstation(struct erofs_sb_info *sbi, + unsigned int freed = 0; + unsigned long index; + ++ xa_lock(&sbi->managed_pslots); + xa_for_each(&sbi->managed_pslots, index, grp) { + /* try to shrink each valid workgroup */ + if (!erofs_try_to_release_workgroup(sbi, grp)) + continue; ++ xa_unlock(&sbi->managed_pslots); + + ++freed; + if (!--nr_shrink) +- break; ++ return freed; ++ xa_lock(&sbi->managed_pslots); + } ++ xa_unlock(&sbi->managed_pslots); + return freed; + } + +-- +2.33.0 + diff --git a/queue-5.10/firmware-arm_scmi-pm-propagate-return-value-to-calle.patch b/queue-5.10/firmware-arm_scmi-pm-propagate-return-value-to-calle.patch new file mode 100644 index 00000000000..91e9498e266 --- /dev/null +++ b/queue-5.10/firmware-arm_scmi-pm-propagate-return-value-to-calle.patch @@ -0,0 +1,39 @@ +From 7ae6564a29d7eaa7d10a64839a8aa499e71d474b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 16 Nov 2021 14:42:27 +0800 +Subject: firmware: arm_scmi: pm: Propagate return value to caller + +From: Peng Fan + +[ Upstream commit 1446fc6c678e8d8b31606a4b877abe205f344b38 ] + +of_genpd_add_provider_onecell may return error, so let's propagate +its return value to caller + +Link: https://lore.kernel.org/r/20211116064227.20571-1-peng.fan@oss.nxp.com +Fixes: 898216c97ed2 ("firmware: arm_scmi: add device power domain support using genpd") +Signed-off-by: Peng Fan +Signed-off-by: Sudeep Holla +Signed-off-by: Sasha Levin +--- + drivers/firmware/arm_scmi/scmi_pm_domain.c | 4 +--- + 1 file changed, 1 insertion(+), 3 deletions(-) + +diff --git a/drivers/firmware/arm_scmi/scmi_pm_domain.c b/drivers/firmware/arm_scmi/scmi_pm_domain.c +index 9e44479f02842..a4e4aa9a35426 100644 +--- a/drivers/firmware/arm_scmi/scmi_pm_domain.c ++++ b/drivers/firmware/arm_scmi/scmi_pm_domain.c +@@ -106,9 +106,7 @@ static int scmi_pm_domain_probe(struct scmi_device *sdev) + scmi_pd_data->domains = domains; + scmi_pd_data->num_domains = num_domains; + +- of_genpd_add_provider_onecell(np, scmi_pd_data); +- +- return 0; ++ return of_genpd_add_provider_onecell(np, scmi_pd_data); + } + + static const struct scmi_device_id scmi_id_table[] = { +-- +2.33.0 + diff --git a/queue-5.10/firmware-smccc-fix-check-for-arch_soc_id-not-impleme.patch b/queue-5.10/firmware-smccc-fix-check-for-arch_soc_id-not-impleme.patch new file mode 100644 index 00000000000..8a18add0354 --- /dev/null +++ b/queue-5.10/firmware-smccc-fix-check-for-arch_soc_id-not-impleme.patch @@ -0,0 +1,43 @@ +From d7b46eb7f73642ee95df86ea79fb02f8d6f505b3 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 19 Nov 2021 15:39:01 -0800 +Subject: firmware: smccc: Fix check for ARCH_SOC_ID not implemented + +From: Michael Kelley + +[ Upstream commit e95d8eaee21cd0d117d34125d4cdc97489c1ab82 ] + +The ARCH_FEATURES function ID is a 32-bit SMC call, which returns +a 32-bit result per the SMCCC spec. Current code is doing a 64-bit +comparison against -1 (SMCCC_RET_NOT_SUPPORTED) to detect that the +feature is unimplemented. That check doesn't work in a Hyper-V VM, +where the upper 32-bits are zero as allowed by the spec. + +Cast the result as an 'int' so the comparison works. The change also +makes the code consistent with other similar checks in this file. + +Fixes: 821b67fa4639 ("firmware: smccc: Add ARCH_SOC_ID support") +Signed-off-by: Michael Kelley +Reviewed-by: Sudeep Holla +Signed-off-by: Arnd Bergmann +Signed-off-by: Sasha Levin +--- + drivers/firmware/smccc/soc_id.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/firmware/smccc/soc_id.c b/drivers/firmware/smccc/soc_id.c +index 581aa5e9b0778..dd7c3d5e8b0bb 100644 +--- a/drivers/firmware/smccc/soc_id.c ++++ b/drivers/firmware/smccc/soc_id.c +@@ -50,7 +50,7 @@ static int __init smccc_soc_init(void) + arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_SOC_ID, &res); + +- if (res.a0 == SMCCC_RET_NOT_SUPPORTED) { ++ if ((int)res.a0 == SMCCC_RET_NOT_SUPPORTED) { + pr_info("ARCH_SOC_ID not implemented, skipping ....\n"); + return 0; + } +-- +2.33.0 + diff --git a/queue-5.10/iavf-prevent-changing-static-itr-values-if-adaptive-.patch b/queue-5.10/iavf-prevent-changing-static-itr-values-if-adaptive-.patch new file mode 100644 index 00000000000..4597518a2b7 --- /dev/null +++ b/queue-5.10/iavf-prevent-changing-static-itr-values-if-adaptive-.patch @@ -0,0 +1,91 @@ +From 9e7953c68306b834ec68eae102370b86016bd8b7 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 4 Jun 2021 09:53:31 -0700 +Subject: iavf: Prevent changing static ITR values if adaptive moderation is on + +From: Nitesh B Venkatesh + +[ Upstream commit e792779e6b639c182df91b46ac1e5803460b0b15 ] + +Resolve being able to change static values on VF when adaptive interrupt +moderation is enabled. + +This problem is fixed by checking the interrupt settings is not +a combination of change of static value while adaptive interrupt +moderation is turned on. + +Without this fix, the user would be able to change static values +on VF with adaptive moderation enabled. + +Fixes: 65e87c0398f5 ("i40evf: support queue-specific settings for interrupt moderation") +Signed-off-by: Nitesh B Venkatesh +Tested-by: George Kuruvinakunnel +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + .../net/ethernet/intel/iavf/iavf_ethtool.c | 30 ++++++++++++++++--- + 1 file changed, 26 insertions(+), 4 deletions(-) + +diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +index ea85b06857fa2..90f5ec982d513 100644 +--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c ++++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +@@ -719,12 +719,31 @@ static int iavf_get_per_queue_coalesce(struct net_device *netdev, u32 queue, + * + * Change the ITR settings for a specific queue. + **/ +-static void iavf_set_itr_per_queue(struct iavf_adapter *adapter, +- struct ethtool_coalesce *ec, int queue) ++static int iavf_set_itr_per_queue(struct iavf_adapter *adapter, ++ struct ethtool_coalesce *ec, int queue) + { + struct iavf_ring *rx_ring = &adapter->rx_rings[queue]; + struct iavf_ring *tx_ring = &adapter->tx_rings[queue]; + struct iavf_q_vector *q_vector; ++ u16 itr_setting; ++ ++ itr_setting = rx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; ++ ++ if (ec->rx_coalesce_usecs != itr_setting && ++ ec->use_adaptive_rx_coalesce) { ++ netif_info(adapter, drv, adapter->netdev, ++ "Rx interrupt throttling cannot be changed if adaptive-rx is enabled\n"); ++ return -EINVAL; ++ } ++ ++ itr_setting = tx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; ++ ++ if (ec->tx_coalesce_usecs != itr_setting && ++ ec->use_adaptive_tx_coalesce) { ++ netif_info(adapter, drv, adapter->netdev, ++ "Tx interrupt throttling cannot be changed if adaptive-tx is enabled\n"); ++ return -EINVAL; ++ } + + rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); + tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); +@@ -747,6 +766,7 @@ static void iavf_set_itr_per_queue(struct iavf_adapter *adapter, + * the Tx and Rx ITR values based on the values we have entered + * into the q_vector, no need to write the values now. + */ ++ return 0; + } + + /** +@@ -788,9 +808,11 @@ static int __iavf_set_coalesce(struct net_device *netdev, + */ + if (queue < 0) { + for (i = 0; i < adapter->num_active_queues; i++) +- iavf_set_itr_per_queue(adapter, ec, i); ++ if (iavf_set_itr_per_queue(adapter, ec, i)) ++ return -EINVAL; + } else if (queue < adapter->num_active_queues) { +- iavf_set_itr_per_queue(adapter, ec, queue); ++ if (iavf_set_itr_per_queue(adapter, ec, queue)) ++ return -EINVAL; + } else { + netif_info(adapter, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", + adapter->num_active_queues - 1); +-- +2.33.0 + diff --git a/queue-5.10/ice-avoid-bpf_prog-refcount-underflow.patch b/queue-5.10/ice-avoid-bpf_prog-refcount-underflow.patch new file mode 100644 index 00000000000..828844bb2ad --- /dev/null +++ b/queue-5.10/ice-avoid-bpf_prog-refcount-underflow.patch @@ -0,0 +1,132 @@ +From e1a8eca144f2f5bf9837d8a842b188cd642cbff5 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 26 Oct 2021 18:47:19 +0200 +Subject: ice: avoid bpf_prog refcount underflow + +From: Marta Plantykow + +[ Upstream commit f65ee535df775a13a1046c0a0b2d72db342f8a5b ] + +Ice driver has the routines for managing XDP resources that are shared +between ndo_bpf op and VSI rebuild flow. The latter takes place for +example when user changes queue count on an interface via ethtool's +set_channels(). + +There is an issue around the bpf_prog refcounting when VSI is being +rebuilt - since ice_prepare_xdp_rings() is called with vsi->xdp_prog as +an argument that is used later on by ice_vsi_assign_bpf_prog(), same +bpf_prog pointers are swapped with each other. Then it is also +interpreted as an 'old_prog' which in turn causes us to call +bpf_prog_put on it that will decrement its refcount. + +Below splat can be interpreted in a way that due to zero refcount of a +bpf_prog it is wiped out from the system while kernel still tries to +refer to it: + +[ 481.069429] BUG: unable to handle page fault for address: ffffc9000640f038 +[ 481.077390] #PF: supervisor read access in kernel mode +[ 481.083335] #PF: error_code(0x0000) - not-present page +[ 481.089276] PGD 100000067 P4D 100000067 PUD 1001cb067 PMD 106d2b067 PTE 0 +[ 481.097141] Oops: 0000 [#1] PREEMPT SMP PTI +[ 481.101980] CPU: 12 PID: 3339 Comm: sudo Tainted: G OE 5.15.0-rc5+ #1 +[ 481.110840] Hardware name: Intel Corp. GRANTLEY/GRANTLEY, BIOS GRRFCRB1.86B.0276.D07.1605190235 05/19/2016 +[ 481.122021] RIP: 0010:dev_xdp_prog_id+0x25/0x40 +[ 481.127265] Code: 80 00 00 00 00 0f 1f 44 00 00 89 f6 48 c1 e6 04 48 01 fe 48 8b 86 98 08 00 00 48 85 c0 74 13 48 8b 50 18 31 c0 48 85 d2 74 07 <48> 8b 42 38 8b 40 20 c3 48 8b 96 90 08 00 00 eb e8 66 2e 0f 1f 84 +[ 481.148991] RSP: 0018:ffffc90007b63868 EFLAGS: 00010286 +[ 481.155034] RAX: 0000000000000000 RBX: ffff889080824000 RCX: 0000000000000000 +[ 481.163278] RDX: ffffc9000640f000 RSI: ffff889080824010 RDI: ffff889080824000 +[ 481.171527] RBP: ffff888107af7d00 R08: 0000000000000000 R09: ffff88810db5f6e0 +[ 481.179776] R10: 0000000000000000 R11: ffff8890885b9988 R12: ffff88810db5f4bc +[ 481.188026] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 +[ 481.196276] FS: 00007f5466d5bec0(0000) GS:ffff88903fb00000(0000) knlGS:0000000000000000 +[ 481.205633] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +[ 481.212279] CR2: ffffc9000640f038 CR3: 000000014429c006 CR4: 00000000003706e0 +[ 481.220530] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 +[ 481.228771] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 +[ 481.237029] Call Trace: +[ 481.239856] rtnl_fill_ifinfo+0x768/0x12e0 +[ 481.244602] rtnl_dump_ifinfo+0x525/0x650 +[ 481.249246] ? __alloc_skb+0xa5/0x280 +[ 481.253484] netlink_dump+0x168/0x3c0 +[ 481.257725] netlink_recvmsg+0x21e/0x3e0 +[ 481.262263] ____sys_recvmsg+0x87/0x170 +[ 481.266707] ? __might_fault+0x20/0x30 +[ 481.271046] ? _copy_from_user+0x66/0xa0 +[ 481.275591] ? iovec_from_user+0xf6/0x1c0 +[ 481.280226] ___sys_recvmsg+0x82/0x100 +[ 481.284566] ? sock_sendmsg+0x5e/0x60 +[ 481.288791] ? __sys_sendto+0xee/0x150 +[ 481.293129] __sys_recvmsg+0x56/0xa0 +[ 481.297267] do_syscall_64+0x3b/0xc0 +[ 481.301395] entry_SYSCALL_64_after_hwframe+0x44/0xae +[ 481.307238] RIP: 0033:0x7f5466f39617 +[ 481.311373] Code: 0c 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb bd 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2f 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 89 54 24 1c 48 89 74 24 10 +[ 481.342944] RSP: 002b:00007ffedc7f4308 EFLAGS: 00000246 ORIG_RAX: 000000000000002f +[ 481.361783] RAX: ffffffffffffffda RBX: 00007ffedc7f5460 RCX: 00007f5466f39617 +[ 481.380278] RDX: 0000000000000000 RSI: 00007ffedc7f5360 RDI: 0000000000000003 +[ 481.398500] RBP: 00007ffedc7f53f0 R08: 0000000000000000 R09: 000055d556f04d50 +[ 481.416463] R10: 0000000000000077 R11: 0000000000000246 R12: 00007ffedc7f5360 +[ 481.434131] R13: 00007ffedc7f5350 R14: 00007ffedc7f5344 R15: 0000000000000e98 +[ 481.451520] Modules linked in: ice(OE) af_packet binfmt_misc nls_iso8859_1 ipmi_ssif intel_rapl_msr intel_rapl_common x86_pkg_temp_thermal intel_powerclamp mxm_wmi mei_me coretemp mei ipmi_si ipmi_msghandler wmi acpi_pad acpi_power_meter ip_tables x_tables autofs4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel ahci crypto_simd cryptd libahci lpc_ich [last unloaded: ice] +[ 481.528558] CR2: ffffc9000640f038 +[ 481.542041] ---[ end trace d1f24c9ecf5b61c1 ]--- + +Fix this by only calling ice_vsi_assign_bpf_prog() inside +ice_prepare_xdp_rings() when current vsi->xdp_prog pointer is NULL. +This way set_channels() flow will not attempt to swap the vsi->xdp_prog +pointers with itself. + +Also, sprinkle around some comments that provide a reasoning about +correlation between driver and kernel in terms of bpf_prog refcount. + +Fixes: efc2214b6047 ("ice: Add support for XDP") +Reviewed-by: Alexander Lobakin +Signed-off-by: Marta Plantykow +Co-developed-by: Maciej Fijalkowski +Signed-off-by: Maciej Fijalkowski +Tested-by: Kiran Bhandare +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/ice/ice_main.c | 18 +++++++++++++++++- + 1 file changed, 17 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c +index 5b67d24b2b5ed..746a5bd178d3b 100644 +--- a/drivers/net/ethernet/intel/ice/ice_main.c ++++ b/drivers/net/ethernet/intel/ice/ice_main.c +@@ -2397,7 +2397,18 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) + ice_stat_str(status)); + goto clear_xdp_rings; + } +- ice_vsi_assign_bpf_prog(vsi, prog); ++ ++ /* assign the prog only when it's not already present on VSI; ++ * this flow is a subject of both ethtool -L and ndo_bpf flows; ++ * VSI rebuild that happens under ethtool -L can expose us to ++ * the bpf_prog refcount issues as we would be swapping same ++ * bpf_prog pointers from vsi->xdp_prog and calling bpf_prog_put ++ * on it as it would be treated as an 'old_prog'; for ndo_bpf ++ * this is not harmful as dev_xdp_install bumps the refcount ++ * before calling the op exposed by the driver; ++ */ ++ if (!ice_is_xdp_ena_vsi(vsi)) ++ ice_vsi_assign_bpf_prog(vsi, prog); + + return 0; + clear_xdp_rings: +@@ -2527,6 +2538,11 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, + if (xdp_ring_err) + NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); + } else { ++ /* safe to call even when prog == vsi->xdp_prog as ++ * dev_xdp_install in net/core/dev.c incremented prog's ++ * refcount so corresponding bpf_prog_put won't cause ++ * underflow ++ */ + ice_vsi_assign_bpf_prog(vsi, prog); + } + +-- +2.33.0 + diff --git a/queue-5.10/ice-fix-vsi-txq_map-sizing.patch b/queue-5.10/ice-fix-vsi-txq_map-sizing.patch new file mode 100644 index 00000000000..c9022bddc14 --- /dev/null +++ b/queue-5.10/ice-fix-vsi-txq_map-sizing.patch @@ -0,0 +1,96 @@ +From 913324ccb14f1d370b96ed3b251d400ba133b054 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 26 Oct 2021 18:47:18 +0200 +Subject: ice: fix vsi->txq_map sizing + +From: Maciej Fijalkowski + +[ Upstream commit 792b2086584f25d84081a526beee80d103c2a913 ] + +The approach of having XDP queue per CPU regardless of user's setting +exposed a hidden bug that could occur in case when Rx queue count differ +from Tx queue count. Currently vsi->txq_map's size is equal to the +doubled vsi->alloc_txq, which is not correct due to the fact that XDP +rings were previously based on the Rx queue count. Below splat can be +seen when ethtool -L is used and XDP rings are configured: + +[ 682.875339] BUG: kernel NULL pointer dereference, address: 000000000000000f +[ 682.883403] #PF: supervisor read access in kernel mode +[ 682.889345] #PF: error_code(0x0000) - not-present page +[ 682.895289] PGD 0 P4D 0 +[ 682.898218] Oops: 0000 [#1] PREEMPT SMP PTI +[ 682.903055] CPU: 42 PID: 2878 Comm: ethtool Tainted: G OE 5.15.0-rc5+ #1 +[ 682.912214] Hardware name: Intel Corp. GRANTLEY/GRANTLEY, BIOS GRRFCRB1.86B.0276.D07.1605190235 05/19/2016 +[ 682.923380] RIP: 0010:devres_remove+0x44/0x130 +[ 682.928527] Code: 49 89 f4 55 48 89 fd 4c 89 ff 53 48 83 ec 10 e8 92 b9 49 00 48 8b 9d a8 02 00 00 48 8d 8d a0 02 00 00 49 89 c2 48 39 cb 74 0f <4c> 3b 63 10 74 25 48 8b 5b 08 48 39 cb 75 f1 4c 89 ff 4c 89 d6 e8 +[ 682.950237] RSP: 0018:ffffc90006a679f0 EFLAGS: 00010002 +[ 682.956285] RAX: 0000000000000286 RBX: ffffffffffffffff RCX: ffff88908343a370 +[ 682.964538] RDX: 0000000000000001 RSI: ffffffff81690d60 RDI: 0000000000000000 +[ 682.972789] RBP: ffff88908343a0d0 R08: 0000000000000000 R09: 0000000000000000 +[ 682.981040] R10: 0000000000000286 R11: 3fffffffffffffff R12: ffffffff81690d60 +[ 682.989282] R13: ffffffff81690a00 R14: ffff8890819807a8 R15: ffff88908343a36c +[ 682.997535] FS: 00007f08c7bfa740(0000) GS:ffff88a03fd00000(0000) knlGS:0000000000000000 +[ 683.006910] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +[ 683.013557] CR2: 000000000000000f CR3: 0000001080a66003 CR4: 00000000003706e0 +[ 683.021819] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 +[ 683.030075] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 +[ 683.038336] Call Trace: +[ 683.041167] devm_kfree+0x33/0x50 +[ 683.045004] ice_vsi_free_arrays+0x5e/0xc0 [ice] +[ 683.050380] ice_vsi_rebuild+0x4c8/0x750 [ice] +[ 683.055543] ice_vsi_recfg_qs+0x9a/0x110 [ice] +[ 683.060697] ice_set_channels+0x14f/0x290 [ice] +[ 683.065962] ethnl_set_channels+0x333/0x3f0 +[ 683.070807] genl_family_rcv_msg_doit+0xea/0x150 +[ 683.076152] genl_rcv_msg+0xde/0x1d0 +[ 683.080289] ? channels_prepare_data+0x60/0x60 +[ 683.085432] ? genl_get_cmd+0xd0/0xd0 +[ 683.089667] netlink_rcv_skb+0x50/0xf0 +[ 683.094006] genl_rcv+0x24/0x40 +[ 683.097638] netlink_unicast+0x239/0x340 +[ 683.102177] netlink_sendmsg+0x22e/0x470 +[ 683.106717] sock_sendmsg+0x5e/0x60 +[ 683.110756] __sys_sendto+0xee/0x150 +[ 683.114894] ? handle_mm_fault+0xd0/0x2a0 +[ 683.119535] ? do_user_addr_fault+0x1f3/0x690 +[ 683.134173] __x64_sys_sendto+0x25/0x30 +[ 683.148231] do_syscall_64+0x3b/0xc0 +[ 683.161992] entry_SYSCALL_64_after_hwframe+0x44/0xae + +Fix this by taking into account the value that num_possible_cpus() +yields in addition to vsi->alloc_txq instead of doubling the latter. + +Fixes: efc2214b6047 ("ice: Add support for XDP") +Fixes: 22bf877e528f ("ice: introduce XDP_TX fallback path") +Reviewed-by: Alexander Lobakin +Signed-off-by: Maciej Fijalkowski +Tested-by: Kiran Bhandare +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/ice/ice_lib.c | 9 +++++++-- + 1 file changed, 7 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c +index dc944d605a741..52ac6cc08e83e 100644 +--- a/drivers/net/ethernet/intel/ice/ice_lib.c ++++ b/drivers/net/ethernet/intel/ice/ice_lib.c +@@ -83,8 +83,13 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) + if (!vsi->rx_rings) + goto err_rings; + +- /* XDP will have vsi->alloc_txq Tx queues as well, so double the size */ +- vsi->txq_map = devm_kcalloc(dev, (2 * vsi->alloc_txq), ++ /* txq_map needs to have enough space to track both Tx (stack) rings ++ * and XDP rings; at this point vsi->num_xdp_txq might not be set, ++ * so use num_possible_cpus() as we want to always provide XDP ring ++ * per CPU, regardless of queue count settings from user that might ++ * have come from ethtool's set_channels() callback; ++ */ ++ vsi->txq_map = devm_kcalloc(dev, (vsi->alloc_txq + num_possible_cpus()), + sizeof(*vsi->txq_map), GFP_KERNEL); + + if (!vsi->txq_map) +-- +2.33.0 + diff --git a/queue-5.10/igb-fix-netpoll-exit-with-traffic.patch b/queue-5.10/igb-fix-netpoll-exit-with-traffic.patch new file mode 100644 index 00000000000..a2cb283a1b2 --- /dev/null +++ b/queue-5.10/igb-fix-netpoll-exit-with-traffic.patch @@ -0,0 +1,56 @@ +From 299729c76726dc1e1f31de89aa22bb66273289c0 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 23 Nov 2021 12:40:00 -0800 +Subject: igb: fix netpoll exit with traffic + +From: Jesse Brandeburg + +[ Upstream commit eaeace60778e524a2820d0c0ad60bf80289e292c ] + +Oleksandr brought a bug report where netpoll causes trace +messages in the log on igb. + +Danielle brought this back up as still occurring, so we'll try +again. + +[22038.710800] ------------[ cut here ]------------ +[22038.710801] igb_poll+0x0/0x1440 [igb] exceeded budget in poll +[22038.710802] WARNING: CPU: 12 PID: 40362 at net/core/netpoll.c:155 netpoll_poll_dev+0x18a/0x1a0 + +As Alex suggested, change the driver to return work_done at the +exit of napi_poll, which should be safe to do in this driver +because it is not polling multiple queues in this single napi +context (multiple queues attached to one MSI-X vector). Several +other drivers contain the same simple sequence, so I hope +this will not create new problems. + +Fixes: 16eb8815c235 ("igb: Refactor clean_rx_irq to reduce overhead and improve performance") +Reported-by: Oleksandr Natalenko +Reported-by: Danielle Ratson +Suggested-by: Alexander Duyck +Signed-off-by: Jesse Brandeburg +Tested-by: Oleksandr Natalenko +Tested-by: Danielle Ratson +Link: https://lore.kernel.org/r/20211123204000.1597971-1-jesse.brandeburg@intel.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/igb/igb_main.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c +index e24fb122c03a2..d5432d1448c05 100644 +--- a/drivers/net/ethernet/intel/igb/igb_main.c ++++ b/drivers/net/ethernet/intel/igb/igb_main.c +@@ -8032,7 +8032,7 @@ static int igb_poll(struct napi_struct *napi, int budget) + if (likely(napi_complete_done(napi, work_done))) + igb_ring_irq_enable(q_vector); + +- return min(work_done, budget - 1); ++ return work_done; + } + + /** +-- +2.33.0 + diff --git a/queue-5.10/ipv6-fix-typos-in-__ip6_finish_output.patch b/queue-5.10/ipv6-fix-typos-in-__ip6_finish_output.patch new file mode 100644 index 00000000000..9e30dffc6fc --- /dev/null +++ b/queue-5.10/ipv6-fix-typos-in-__ip6_finish_output.patch @@ -0,0 +1,45 @@ +From 723b4eca94a36c7a505eb526f9c09a90f572a48a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 18 Nov 2021 17:37:58 -0800 +Subject: ipv6: fix typos in __ip6_finish_output() + +From: Eric Dumazet + +[ Upstream commit 19d36c5f294879949c9d6f57cb61d39cc4c48553 ] + +We deal with IPv6 packets, so we need to use IP6CB(skb)->flags and +IP6SKB_REROUTED, instead of IPCB(skb)->flags and IPSKB_REROUTED + +Found by code inspection, please double check that fixing this bug +does not surface other bugs. + +Fixes: 09ee9dba9611 ("ipv6: Reinject IPv6 packets if IPsec policy matches after SNAT") +Signed-off-by: Eric Dumazet +Cc: Tobias Brunner +Cc: Steffen Klassert +Cc: David Ahern +Reviewed-by: David Ahern +Tested-by: Tobias Brunner +Acked-by: Tobias Brunner +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ipv6/ip6_output.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c +index c2f8e69d7d7a0..54cabf1c2ae15 100644 +--- a/net/ipv6/ip6_output.c ++++ b/net/ipv6/ip6_output.c +@@ -193,7 +193,7 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff + #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) + /* Policy lookup after SNAT yielded a new policy */ + if (skb_dst(skb)->xfrm) { +- IPCB(skb)->flags |= IPSKB_REROUTED; ++ IP6CB(skb)->flags |= IP6SKB_REROUTED; + return dst_output(net, sk, skb); + } + #endif +-- +2.33.0 + diff --git a/queue-5.10/lan743x-fix-deadlock-in-lan743x_phy_link_status_chan.patch b/queue-5.10/lan743x-fix-deadlock-in-lan743x_phy_link_status_chan.patch new file mode 100644 index 00000000000..42c02ba47bd --- /dev/null +++ b/queue-5.10/lan743x-fix-deadlock-in-lan743x_phy_link_status_chan.patch @@ -0,0 +1,73 @@ +From 65fae475ec26f9671b470349d49b622a819bb8f1 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 24 Nov 2021 08:16:25 +0100 +Subject: lan743x: fix deadlock in lan743x_phy_link_status_change() + +From: Heiner Kallweit + +[ Upstream commit ddb826c2c92d461f290a7bab89e7c28696191875 ] + +Usage of phy_ethtool_get_link_ksettings() in the link status change +handler isn't needed, and in combination with the referenced change +it results in a deadlock. Simply remove the call and replace it with +direct access to phydev->speed. The duplex argument of +lan743x_phy_update_flowcontrol() isn't used and can be removed. + +Fixes: c10a485c3de5 ("phy: phy_ethtool_ksettings_get: Lock the phy for consistency") +Reported-by: Alessandro B Maurici +Tested-by: Alessandro B Maurici +Signed-off-by: Heiner Kallweit +Reviewed-by: Andrew Lunn +Link: https://lore.kernel.org/r/40e27f76-0ba3-dcef-ee32-a78b9df38b0f@gmail.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/microchip/lan743x_main.c | 12 +++--------- + 1 file changed, 3 insertions(+), 9 deletions(-) + +diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c +index 3eea8cf076c48..481f89d193f77 100644 +--- a/drivers/net/ethernet/microchip/lan743x_main.c ++++ b/drivers/net/ethernet/microchip/lan743x_main.c +@@ -922,8 +922,7 @@ static int lan743x_phy_reset(struct lan743x_adapter *adapter) + } + + static void lan743x_phy_update_flowcontrol(struct lan743x_adapter *adapter, +- u8 duplex, u16 local_adv, +- u16 remote_adv) ++ u16 local_adv, u16 remote_adv) + { + struct lan743x_phy *phy = &adapter->phy; + u8 cap; +@@ -951,7 +950,6 @@ static void lan743x_phy_link_status_change(struct net_device *netdev) + + phy_print_status(phydev); + if (phydev->state == PHY_RUNNING) { +- struct ethtool_link_ksettings ksettings; + int remote_advertisement = 0; + int local_advertisement = 0; + +@@ -988,18 +986,14 @@ static void lan743x_phy_link_status_change(struct net_device *netdev) + } + lan743x_csr_write(adapter, MAC_CR, data); + +- memset(&ksettings, 0, sizeof(ksettings)); +- phy_ethtool_get_link_ksettings(netdev, &ksettings); + local_advertisement = + linkmode_adv_to_mii_adv_t(phydev->advertising); + remote_advertisement = + linkmode_adv_to_mii_adv_t(phydev->lp_advertising); + +- lan743x_phy_update_flowcontrol(adapter, +- ksettings.base.duplex, +- local_advertisement, ++ lan743x_phy_update_flowcontrol(adapter, local_advertisement, + remote_advertisement); +- lan743x_ptp_update_latency(adapter, ksettings.base.speed); ++ lan743x_ptp_update_latency(adapter, phydev->speed); + } + } + +-- +2.33.0 + diff --git a/queue-5.10/mips-loongson64-fix-ftlb-configuration.patch b/queue-5.10/mips-loongson64-fix-ftlb-configuration.patch new file mode 100644 index 00000000000..542725ef262 --- /dev/null +++ b/queue-5.10/mips-loongson64-fix-ftlb-configuration.patch @@ -0,0 +1,47 @@ +From c9231fdff765f611ad6de185fda0a361e67684ac Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 25 Nov 2021 18:59:49 +0800 +Subject: MIPS: loongson64: fix FTLB configuration + +From: Huang Pei + +[ Upstream commit 7db5e9e9e5e6c10d7d26f8df7f8fd8841cb15ee7 ] + +It turns out that 'decode_configs' -> 'set_ftlb_enable' is called under +c->cputype unset, which leaves FTLB disabled on BOTH 3A2000 and 3A3000 + +Fix it by calling "decode_configs" after c->cputype is initialized + +Fixes: da1bd29742b1 ("MIPS: Loongson64: Probe CPU features via CPUCFG") +Signed-off-by: Huang Pei +Signed-off-by: Thomas Bogendoerfer +Signed-off-by: Sasha Levin +--- + arch/mips/kernel/cpu-probe.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c +index 067cb3eb16141..d120201910acf 100644 +--- a/arch/mips/kernel/cpu-probe.c ++++ b/arch/mips/kernel/cpu-probe.c +@@ -1721,8 +1721,6 @@ static inline void decode_cpucfg(struct cpuinfo_mips *c) + + static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) + { +- decode_configs(c); +- + /* All Loongson processors covered here define ExcCode 16 as GSExc. */ + c->options |= MIPS_CPU_GSEXCEX; + +@@ -1783,6 +1781,8 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) + panic("Unknown Loongson Processor ID!"); + break; + } ++ ++ decode_configs(c); + } + #else + static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { } +-- +2.33.0 + diff --git a/queue-5.10/mips-use-3-level-pgtable-for-64kb-page-size-on-mips_.patch b/queue-5.10/mips-use-3-level-pgtable-for-64kb-page-size-on-mips_.patch new file mode 100644 index 00000000000..8e234eab8b8 --- /dev/null +++ b/queue-5.10/mips-use-3-level-pgtable-for-64kb-page-size-on-mips_.patch @@ -0,0 +1,39 @@ +From 91eb1a5b0615a0220a671c64f0f98b8548750109 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 25 Nov 2021 18:59:48 +0800 +Subject: MIPS: use 3-level pgtable for 64KB page size on MIPS_VA_BITS_48 + +From: Huang Pei + +[ Upstream commit 41ce097f714401e6ad8f3f5eb30d7f91b0b5e495 ] + +It hangup when booting Loongson 3A1000 with BOTH +CONFIG_PAGE_SIZE_64KB and CONFIG_MIPS_VA_BITS_48, that it turn +out to use 2-level pgtable instead of 3-level. 64KB page size +with 2-level pgtable only cover 42 bits VA, use 3-level pgtable +to cover all 48 bits VA(55 bits) + +Fixes: 1e321fa917fb ("MIPS64: Support of at least 48 bits of SEGBITS) +Signed-off-by: Huang Pei +Signed-off-by: Thomas Bogendoerfer +Signed-off-by: Sasha Levin +--- + arch/mips/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig +index 94a748e95231b..23d756fe0fd6c 100644 +--- a/arch/mips/Kconfig ++++ b/arch/mips/Kconfig +@@ -3189,7 +3189,7 @@ config STACKTRACE_SUPPORT + config PGTABLE_LEVELS + int + default 4 if PAGE_SIZE_4KB && MIPS_VA_BITS_48 +- default 3 if 64BIT && !PAGE_SIZE_64KB ++ default 3 if 64BIT && (!PAGE_SIZE_64KB || MIPS_VA_BITS_48) + default 2 + + config MIPS_AUTO_PFN_OFFSET +-- +2.33.0 + diff --git a/queue-5.10/mlxsw-spectrum-protect-driver-from-buggy-firmware.patch b/queue-5.10/mlxsw-spectrum-protect-driver-from-buggy-firmware.patch new file mode 100644 index 00000000000..b308dccc7d8 --- /dev/null +++ b/queue-5.10/mlxsw-spectrum-protect-driver-from-buggy-firmware.patch @@ -0,0 +1,45 @@ +From 0bf24a0cd9d42c232e58f495f06c7fd7c97cfe25 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 23 Nov 2021 09:52:56 +0200 +Subject: mlxsw: spectrum: Protect driver from buggy firmware + +From: Amit Cohen + +[ Upstream commit 63b08b1f6834bbb0b4f7783bf63b80c8c8e9a047 ] + +When processing port up/down events generated by the device's firmware, +the driver protects itself from events reported for non-existent local +ports, but not the CPU port (local port 0), which exists, but lacks a +netdev. + +This can result in a NULL pointer dereference when calling +netif_carrier_{on,off}(). + +Fix this by bailing early when processing an event reported for the CPU +port. Problem was only observed when running on top of a buggy emulator. + +Fixes: 28b1987ef506 ("mlxsw: spectrum: Register CPU port with devlink") +Signed-off-by: Amit Cohen +Signed-off-by: Ido Schimmel +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +index 1a9978f501ba9..4110e15c22c79 100644 +--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c ++++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +@@ -2058,7 +2058,7 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg, + max_ports = mlxsw_core_max_ports(mlxsw_sp->core); + local_port = mlxsw_reg_pude_local_port_get(pude_pl); + +- if (WARN_ON_ONCE(local_port >= max_ports)) ++ if (WARN_ON_ONCE(!local_port || local_port >= max_ports)) + return; + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + if (!mlxsw_sp_port) +-- +2.33.0 + diff --git a/queue-5.10/mlxsw-verify-the-accessed-index-doesn-t-exceed-the-a.patch b/queue-5.10/mlxsw-verify-the-accessed-index-doesn-t-exceed-the-a.patch new file mode 100644 index 00000000000..54f1c2a4043 --- /dev/null +++ b/queue-5.10/mlxsw-verify-the-accessed-index-doesn-t-exceed-the-a.patch @@ -0,0 +1,133 @@ +From 6f84db0a73adca066685bb13a77acdb0a68502f5 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 17 May 2021 20:03:57 +0300 +Subject: mlxsw: Verify the accessed index doesn't exceed the array length + +From: Danielle Ratson + +[ Upstream commit 837ec05cfea08284c575e8e834777b107da5ff9d ] + +There are few cases in which an array index queried from a fw register, +is accessed without any validation that it doesn't exceed the array +length. + +Add a proper length validation, so accessing memory past the end of an +array will be forbidden. + +Signed-off-by: Danielle Ratson +Signed-off-by: Ido Schimmel +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/mellanox/mlxsw/minimal.c | 4 ++++ + drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 5 +++++ + drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c | 3 +++ + drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 3 +++ + drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 4 ++++ + 5 files changed, 19 insertions(+) + +diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c +index c010db2c9dba9..443dc44452ef8 100644 +--- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c ++++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c +@@ -234,6 +234,7 @@ static void mlxsw_m_port_remove(struct mlxsw_m *mlxsw_m, u8 local_port) + static int mlxsw_m_port_module_map(struct mlxsw_m *mlxsw_m, u8 local_port, + u8 *last_module) + { ++ unsigned int max_ports = mlxsw_core_max_ports(mlxsw_m->core); + u8 module, width; + int err; + +@@ -249,6 +250,9 @@ static int mlxsw_m_port_module_map(struct mlxsw_m *mlxsw_m, u8 local_port, + if (module == *last_module) + return 0; + *last_module = module; ++ ++ if (WARN_ON_ONCE(module >= max_ports)) ++ return -EINVAL; + mlxsw_m->module_to_port[module] = ++mlxsw_m->max_ports; + + return 0; +diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +index b08853f71b2be..1a9978f501ba9 100644 +--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c ++++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +@@ -2052,9 +2052,14 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg, + struct mlxsw_sp *mlxsw_sp = priv; + struct mlxsw_sp_port *mlxsw_sp_port; + enum mlxsw_reg_pude_oper_status status; ++ unsigned int max_ports; + u8 local_port; + ++ max_ports = mlxsw_core_max_ports(mlxsw_sp->core); + local_port = mlxsw_reg_pude_local_port_get(pude_pl); ++ ++ if (WARN_ON_ONCE(local_port >= max_ports)) ++ return; + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + if (!mlxsw_sp_port) + return; +diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +index ca8090a28dec6..50eca2daad843 100644 +--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c ++++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +@@ -568,10 +568,13 @@ void mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress, + u8 domain_number, u16 sequence_id, + u64 timestamp) + { ++ unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core); + struct mlxsw_sp_port *mlxsw_sp_port; + struct mlxsw_sp1_ptp_key key; + u8 types; + ++ if (WARN_ON_ONCE(local_port >= max_ports)) ++ return; + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + if (!mlxsw_sp_port) + return; +diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +index 4381f8c6c3fb7..53128382fc2e0 100644 +--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c ++++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +@@ -2177,6 +2177,7 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp, + char *rauhtd_pl, + int ent_index) + { ++ u64 max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); + struct net_device *dev; + struct neighbour *n; + __be32 dipn; +@@ -2185,6 +2186,8 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp, + + mlxsw_reg_rauhtd_ent_ipv4_unpack(rauhtd_pl, ent_index, &rif, &dip); + ++ if (WARN_ON_ONCE(rif >= max_rifs)) ++ return; + if (!mlxsw_sp->router->rifs[rif]) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Incorrect RIF in neighbour entry\n"); + return; +diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +index 6501ce94ace58..368fa0e5ad315 100644 +--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c ++++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +@@ -2410,6 +2410,7 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, + char *sfn_pl, int rec_index, + bool adding) + { ++ unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core); + struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; + struct mlxsw_sp_bridge_device *bridge_device; + struct mlxsw_sp_bridge_port *bridge_port; +@@ -2422,6 +2423,9 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, + int err; + + mlxsw_reg_sfn_mac_unpack(sfn_pl, rec_index, mac, &fid, &local_port); ++ ++ if (WARN_ON_ONCE(local_port >= max_ports)) ++ return; + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + if (!mlxsw_sp_port) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Incorrect local port in FDB notification\n"); +-- +2.33.0 + diff --git a/queue-5.10/mptcp-fix-delack-timer.patch b/queue-5.10/mptcp-fix-delack-timer.patch new file mode 100644 index 00000000000..c76cf79ca26 --- /dev/null +++ b/queue-5.10/mptcp-fix-delack-timer.patch @@ -0,0 +1,42 @@ +From f446af9a3adc01a861fdf11f11ed1d38cce97862 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 19 Nov 2021 15:27:54 +0100 +Subject: mptcp: fix delack timer + +From: Eric Dumazet + +[ Upstream commit ee50e67ba0e17b1a1a8d76691d02eadf9e0f392c ] + +To compute the rtx timeout schedule_3rdack_retransmission() does multiple +things in the wrong way: srtt_us is measured in usec/8 and the timeout +itself is an absolute value. + +Fixes: ec3edaa7ca6ce02f ("mptcp: Add handling of outgoing MP_JOIN requests") +Acked-by: Paolo Abeni +Reviewed-by: Mat Martineau @linux.intel.com> +Signed-off-by: Eric Dumazet +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/mptcp/options.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/net/mptcp/options.c b/net/mptcp/options.c +index ac0233c9cd349..64afe71e2129a 100644 +--- a/net/mptcp/options.c ++++ b/net/mptcp/options.c +@@ -368,9 +368,10 @@ static void schedule_3rdack_retransmission(struct sock *sk) + + /* reschedule with a timeout above RTT, as we must look only for drop */ + if (tp->srtt_us) +- timeout = tp->srtt_us << 1; ++ timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1)); + else + timeout = TCP_TIMEOUT_INIT; ++ timeout += jiffies; + + WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER); + icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; +-- +2.33.0 + diff --git a/queue-5.10/net-hns3-fix-vf-rss-failed-problem-after-pf-enable-m.patch b/queue-5.10/net-hns3-fix-vf-rss-failed-problem-after-pf-enable-m.patch new file mode 100644 index 00000000000..cb17f872afe --- /dev/null +++ b/queue-5.10/net-hns3-fix-vf-rss-failed-problem-after-pf-enable-m.patch @@ -0,0 +1,49 @@ +From f5b945cb38c44b0eb6f7d4f381528fd1684ad6d2 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 26 Nov 2021 20:03:15 +0800 +Subject: net: hns3: fix VF RSS failed problem after PF enable multi-TCs + +From: Guangbin Huang + +[ Upstream commit 8d2ad993aa05c0768f00c886c9d369cd97a337ac ] + +When PF is set to multi-TCs and configured mapping relationship between +priorities and TCs, the hardware will active these settings for this PF +and its VFs. + +In this case when VF just uses one TC and its rx packets contain priority, +and if the priority is not mapped to TC0, as other TCs of VF is not valid, +hardware always put this kind of packets to the queue 0. It cause this kind +of packets of VF can not be used RSS function. + +To fix this problem, set tc mode of all unused TCs of VF to the setting of +TC0, then rx packet with priority which map to unused TC will be direct to +TC0. + +Fixes: e2cb1dec9779 ("net: hns3: Add HNS3 VF HCL(Hardware Compatibility Layer) Support") +Signed-off-by: Guangbin Huang +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +index e27af38f6b161..6e7da1dc2e8c3 100644 +--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c ++++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +@@ -679,9 +679,9 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev, u16 rss_size) + roundup_size = ilog2(roundup_size); + + for (i = 0; i < HCLGEVF_MAX_TC_NUM; i++) { +- tc_valid[i] = !!(hdev->hw_tc_map & BIT(i)); ++ tc_valid[i] = 1; + tc_size[i] = roundup_size; +- tc_offset[i] = rss_size * i; ++ tc_offset[i] = (hdev->hw_tc_map & BIT(i)) ? rss_size * i : 0; + } + + hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_RSS_TC_MODE, false); +-- +2.33.0 + diff --git a/queue-5.10/net-ieee802154-handle-iftypes-as-u32.patch b/queue-5.10/net-ieee802154-handle-iftypes-as-u32.patch new file mode 100644 index 00000000000..a9d4a24556f --- /dev/null +++ b/queue-5.10/net-ieee802154-handle-iftypes-as-u32.patch @@ -0,0 +1,56 @@ +From 9461ea6b6222c2729e398129e3282dd8aa40d3de Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 11 Nov 2021 22:09:16 -0500 +Subject: net: ieee802154: handle iftypes as u32 + +From: Alexander Aring + +[ Upstream commit 451dc48c806a7ce9fbec5e7a24ccf4b2c936e834 ] + +This patch fixes an issue that an u32 netlink value is handled as a +signed enum value which doesn't fit into the range of u32 netlink type. +If it's handled as -1 value some BIT() evaluation ends in a +shift-out-of-bounds issue. To solve the issue we set the to u32 max which +is s32 "-1" value to keep backwards compatibility and let the followed enum +values start counting at 0. This brings the compiler to never handle the +enum as signed and a check if the value is above NL802154_IFTYPE_MAX should +filter -1 out. + +Fixes: f3ea5e44231a ("ieee802154: add new interface command") +Signed-off-by: Alexander Aring +Link: https://lore.kernel.org/r/20211112030916.685793-1-aahringo@redhat.com +Signed-off-by: Stefan Schmidt +Signed-off-by: Sasha Levin +--- + include/net/nl802154.h | 7 ++++--- + 1 file changed, 4 insertions(+), 3 deletions(-) + +diff --git a/include/net/nl802154.h b/include/net/nl802154.h +index ddcee128f5d9a..145acb8f25095 100644 +--- a/include/net/nl802154.h ++++ b/include/net/nl802154.h +@@ -19,6 +19,8 @@ + * + */ + ++#include ++ + #define NL802154_GENL_NAME "nl802154" + + enum nl802154_commands { +@@ -150,10 +152,9 @@ enum nl802154_attrs { + }; + + enum nl802154_iftype { +- /* for backwards compatibility TODO */ +- NL802154_IFTYPE_UNSPEC = -1, ++ NL802154_IFTYPE_UNSPEC = (~(__u32)0), + +- NL802154_IFTYPE_NODE, ++ NL802154_IFTYPE_NODE = 0, + NL802154_IFTYPE_MONITOR, + NL802154_IFTYPE_COORD, + +-- +2.33.0 + diff --git a/queue-5.10/net-ipv6-add-fib6_nh_release_dsts-stub.patch b/queue-5.10/net-ipv6-add-fib6_nh_release_dsts-stub.patch new file mode 100644 index 00000000000..100520b6161 --- /dev/null +++ b/queue-5.10/net-ipv6-add-fib6_nh_release_dsts-stub.patch @@ -0,0 +1,97 @@ +From 4994a9f288ce6aec23c1246921f337605a7193fc Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 22 Nov 2021 17:15:12 +0200 +Subject: net: ipv6: add fib6_nh_release_dsts stub + +From: Nikolay Aleksandrov + +[ Upstream commit 8837cbbf854246f5f4d565f21e6baa945d37aded ] + +We need a way to release a fib6_nh's per-cpu dsts when replacing +nexthops otherwise we can end up with stale per-cpu dsts which hold net +device references, so add a new IPv6 stub called fib6_nh_release_dsts. +It must be used after an RCU grace period, so no new dsts can be created +through a group's nexthop entry. +Similar to fib6_nh_release it shouldn't be used if fib6_nh_init has failed +so it doesn't need a dummy stub when IPv6 is not enabled. + +Fixes: 7bf4796dd099 ("nexthops: add support for replace") +Signed-off-by: Nikolay Aleksandrov +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + include/net/ip6_fib.h | 1 + + include/net/ipv6_stubs.h | 1 + + net/ipv6/af_inet6.c | 1 + + net/ipv6/route.c | 19 +++++++++++++++++++ + 4 files changed, 22 insertions(+) + +diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h +index ac5ff3c3afb14..88bc66b8d02b0 100644 +--- a/include/net/ip6_fib.h ++++ b/include/net/ip6_fib.h +@@ -491,6 +491,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, + struct fib6_config *cfg, gfp_t gfp_flags, + struct netlink_ext_ack *extack); + void fib6_nh_release(struct fib6_nh *fib6_nh); ++void fib6_nh_release_dsts(struct fib6_nh *fib6_nh); + + int call_fib6_entry_notifiers(struct net *net, + enum fib_event_type event_type, +diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h +index 8fce558b5fea3..14a43111ffc6a 100644 +--- a/include/net/ipv6_stubs.h ++++ b/include/net/ipv6_stubs.h +@@ -47,6 +47,7 @@ struct ipv6_stub { + struct fib6_config *cfg, gfp_t gfp_flags, + struct netlink_ext_ack *extack); + void (*fib6_nh_release)(struct fib6_nh *fib6_nh); ++ void (*fib6_nh_release_dsts)(struct fib6_nh *fib6_nh); + void (*fib6_update_sernum)(struct net *net, struct fib6_info *rt); + int (*ip6_del_rt)(struct net *net, struct fib6_info *rt, bool skip_notify); + void (*fib6_rt_update)(struct net *net, struct fib6_info *rt, +diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c +index e648fbebb1670..090575346daf6 100644 +--- a/net/ipv6/af_inet6.c ++++ b/net/ipv6/af_inet6.c +@@ -1016,6 +1016,7 @@ static const struct ipv6_stub ipv6_stub_impl = { + .ip6_mtu_from_fib6 = ip6_mtu_from_fib6, + .fib6_nh_init = fib6_nh_init, + .fib6_nh_release = fib6_nh_release, ++ .fib6_nh_release_dsts = fib6_nh_release_dsts, + .fib6_update_sernum = fib6_update_sernum_stub, + .fib6_rt_update = fib6_rt_update, + .ip6_del_rt = ip6_del_rt, +diff --git a/net/ipv6/route.c b/net/ipv6/route.c +index a68a7d7c07280..6fef0d7586bf6 100644 +--- a/net/ipv6/route.c ++++ b/net/ipv6/route.c +@@ -3570,6 +3570,25 @@ void fib6_nh_release(struct fib6_nh *fib6_nh) + fib_nh_common_release(&fib6_nh->nh_common); + } + ++void fib6_nh_release_dsts(struct fib6_nh *fib6_nh) ++{ ++ int cpu; ++ ++ if (!fib6_nh->rt6i_pcpu) ++ return; ++ ++ for_each_possible_cpu(cpu) { ++ struct rt6_info *pcpu_rt, **ppcpu_rt; ++ ++ ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); ++ pcpu_rt = xchg(ppcpu_rt, NULL); ++ if (pcpu_rt) { ++ dst_dev_put(&pcpu_rt->dst); ++ dst_release(&pcpu_rt->dst); ++ } ++ } ++} ++ + static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, + gfp_t gfp_flags, + struct netlink_ext_ack *extack) +-- +2.33.0 + diff --git a/queue-5.10/net-marvell-mvpp2-increase-mtu-limit-when-xdp-enable.patch b/queue-5.10/net-marvell-mvpp2-increase-mtu-limit-when-xdp-enable.patch new file mode 100644 index 00000000000..58e44b6fc4d --- /dev/null +++ b/queue-5.10/net-marvell-mvpp2-increase-mtu-limit-when-xdp-enable.patch @@ -0,0 +1,72 @@ +From 2cbd213b0e730e53a149d5865ea06d5050aadf4c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 22 Nov 2021 21:08:34 +0100 +Subject: net: marvell: mvpp2: increase MTU limit when XDP enabled +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Marek Behún + +[ Upstream commit 7b1b62bc1e6a7b2fd5ee7a4296268eb291d23aeb ] + +Currently mvpp2_xdp_setup won't allow attaching XDP program if + mtu > ETH_DATA_LEN (1500). + +The mvpp2_change_mtu on the other hand checks whether + MVPP2_RX_PKT_SIZE(mtu) > MVPP2_BM_LONG_PKT_SIZE. + +These two checks are semantically different. + +Moreover this limit can be increased to MVPP2_MAX_RX_BUF_SIZE, since in +mvpp2_rx we have + xdp.data = data + MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM; + xdp.frame_sz = PAGE_SIZE; + +Change the checks to check whether + mtu > MVPP2_MAX_RX_BUF_SIZE + +Fixes: 07dd0a7aae7f ("mvpp2: add basic XDP support") +Signed-off-by: Marek Behún +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 14 ++++++++------ + 1 file changed, 8 insertions(+), 6 deletions(-) + +diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +index ec9b6c564300e..e220d44df2e65 100644 +--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c ++++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +@@ -4652,11 +4652,13 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu) + mtu = ALIGN(MVPP2_RX_PKT_SIZE(mtu), 8); + } + ++ if (port->xdp_prog && mtu > MVPP2_MAX_RX_BUF_SIZE) { ++ netdev_err(dev, "Illegal MTU value %d (> %d) for XDP mode\n", ++ mtu, (int)MVPP2_MAX_RX_BUF_SIZE); ++ return -EINVAL; ++ } ++ + if (MVPP2_RX_PKT_SIZE(mtu) > MVPP2_BM_LONG_PKT_SIZE) { +- if (port->xdp_prog) { +- netdev_err(dev, "Jumbo frames are not supported with XDP\n"); +- return -EINVAL; +- } + if (priv->percpu_pools) { + netdev_warn(dev, "mtu %d too high, switching to shared buffers", mtu); + mvpp2_bm_switch_buffers(priv, false); +@@ -4942,8 +4944,8 @@ static int mvpp2_xdp_setup(struct mvpp2_port *port, struct netdev_bpf *bpf) + bool running = netif_running(port->dev); + bool reset = !prog != !port->xdp_prog; + +- if (port->dev->mtu > ETH_DATA_LEN) { +- NL_SET_ERR_MSG_MOD(bpf->extack, "XDP is not supported with jumbo frames enabled"); ++ if (port->dev->mtu > MVPP2_MAX_RX_BUF_SIZE) { ++ NL_SET_ERR_MSG_MOD(bpf->extack, "MTU too large for XDP"); + return -EOPNOTSUPP; + } + +-- +2.33.0 + diff --git a/queue-5.10/net-marvell-prestera-fix-double-free-issue-on-err-pa.patch b/queue-5.10/net-marvell-prestera-fix-double-free-issue-on-err-pa.patch new file mode 100644 index 00000000000..60b93b1114d --- /dev/null +++ b/queue-5.10/net-marvell-prestera-fix-double-free-issue-on-err-pa.patch @@ -0,0 +1,66 @@ +From 6d9001304f0ec8e2753cc72c5e2498c6b637a622 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 18 Nov 2021 21:51:40 +0200 +Subject: net: marvell: prestera: fix double free issue on err path + +From: Volodymyr Mytnyk + +[ Upstream commit e8d032507cb7912baf1d3e0af54516f823befefd ] + +fix error path handling in prestera_bridge_port_join() that +cases prestera driver to crash (see below). + + Trace: + Internal error: Oops: 96000044 [#1] SMP + Modules linked in: prestera_pci prestera uio_pdrv_genirq + CPU: 1 PID: 881 Comm: ip Not tainted 5.15.0 #1 + pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) + pc : prestera_bridge_destroy+0x2c/0xb0 [prestera] + lr : prestera_bridge_port_join+0x2cc/0x350 [prestera] + sp : ffff800011a1b0f0 + ... + x2 : ffff000109ca6c80 x1 : dead000000000100 x0 : dead000000000122 + Call trace: + prestera_bridge_destroy+0x2c/0xb0 [prestera] + prestera_bridge_port_join+0x2cc/0x350 [prestera] + prestera_netdev_port_event.constprop.0+0x3c4/0x450 [prestera] + prestera_netdev_event_handler+0xf4/0x110 [prestera] + raw_notifier_call_chain+0x54/0x80 + call_netdevice_notifiers_info+0x54/0xa0 + __netdev_upper_dev_link+0x19c/0x380 + +Fixes: e1189d9a5fbe ("net: marvell: prestera: Add Switchdev driver implementation") +Signed-off-by: Volodymyr Mytnyk +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/marvell/prestera/prestera_switchdev.c | 6 ++---- + 1 file changed, 2 insertions(+), 4 deletions(-) + +diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c +index 7d83e1f91ef17..9101d00e96b9d 100644 +--- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c ++++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c +@@ -439,8 +439,8 @@ static int prestera_port_bridge_join(struct prestera_port *port, + + br_port = prestera_bridge_port_add(bridge, port->dev); + if (IS_ERR(br_port)) { +- err = PTR_ERR(br_port); +- goto err_brport_create; ++ prestera_bridge_put(bridge); ++ return PTR_ERR(br_port); + } + + if (bridge->vlan_enabled) +@@ -454,8 +454,6 @@ static int prestera_port_bridge_join(struct prestera_port *port, + + err_port_join: + prestera_bridge_port_put(br_port); +-err_brport_create: +- prestera_bridge_put(bridge); + return err; + } + +-- +2.33.0 + diff --git a/queue-5.10/net-mscc-ocelot-correctly-report-the-timestamping-rx.patch b/queue-5.10/net-mscc-ocelot-correctly-report-the-timestamping-rx.patch new file mode 100644 index 00000000000..a70c0acccf0 --- /dev/null +++ b/queue-5.10/net-mscc-ocelot-correctly-report-the-timestamping-rx.patch @@ -0,0 +1,41 @@ +From 6502dfb317247afe1c03cac480bdc74c400c2f06 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 26 Nov 2021 19:28:45 +0200 +Subject: net: mscc: ocelot: correctly report the timestamping RX filters in + ethtool + +From: Vladimir Oltean + +[ Upstream commit c49a35eedfef08bffd46b53c25dbf9d6016a86ff ] + +The driver doesn't support RX timestamping for non-PTP packets, but it +declares that it does. Restrict the reported RX filters to PTP v2 over +L2 and over L4. + +Fixes: 4e3b0468e6d7 ("net: mscc: PTP Hardware Clock (PHC) support") +Signed-off-by: Vladimir Oltean +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/mscc/ocelot.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c +index 154d67066d012..52401915828a1 100644 +--- a/drivers/net/ethernet/mscc/ocelot.c ++++ b/drivers/net/ethernet/mscc/ocelot.c +@@ -929,7 +929,10 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port, + SOF_TIMESTAMPING_RAW_HARDWARE; + info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON) | + BIT(HWTSTAMP_TX_ONESTEP_SYNC); +- info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL); ++ info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | ++ BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) | ++ BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | ++ BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT); + + return 0; + } +-- +2.33.0 + diff --git a/queue-5.10/net-mscc-ocelot-don-t-downgrade-timestamping-rx-filt.patch b/queue-5.10/net-mscc-ocelot-don-t-downgrade-timestamping-rx-filt.patch new file mode 100644 index 00000000000..467ff44416b --- /dev/null +++ b/queue-5.10/net-mscc-ocelot-don-t-downgrade-timestamping-rx-filt.patch @@ -0,0 +1,49 @@ +From c5ba381e2c2c9b75db337b78e65125ffb03dac5c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 26 Nov 2021 19:28:41 +0200 +Subject: net: mscc: ocelot: don't downgrade timestamping RX filters in + SIOCSHWTSTAMP + +From: Vladimir Oltean + +[ Upstream commit 8a075464d1e9317ffae0973dfe538a7511291a06 ] + +The ocelot driver, when asked to timestamp all receiving packets, 1588 +v1 or NTP, says "nah, here's 1588 v2 for you". + +According to this discussion: +https://patchwork.kernel.org/project/netdevbpf/patch/20211104133204.19757-8-martin.kaistra@linutronix.de/#24577647 +drivers that downgrade from a wider request to a narrower response (or +even a response where the intersection with the request is empty) are +buggy, and should return -ERANGE instead. This patch fixes that. + +Fixes: 4e3b0468e6d7 ("net: mscc: PTP Hardware Clock (PHC) support") +Suggested-by: Richard Cochran +Signed-off-by: Vladimir Oltean +Acked-by: Richard Cochran +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/mscc/ocelot.c | 6 ------ + 1 file changed, 6 deletions(-) + +diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c +index 8c45b236649a9..154d67066d012 100644 +--- a/drivers/net/ethernet/mscc/ocelot.c ++++ b/drivers/net/ethernet/mscc/ocelot.c +@@ -811,12 +811,6 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) + switch (cfg.rx_filter) { + case HWTSTAMP_FILTER_NONE: + break; +- case HWTSTAMP_FILTER_ALL: +- case HWTSTAMP_FILTER_SOME: +- case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: +- case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: +- case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: +- case HWTSTAMP_FILTER_NTP_ALL: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: +-- +2.33.0 + diff --git a/queue-5.10/net-ncsi-add-payload-to-be-32-bit-aligned-to-fix-dro.patch b/queue-5.10/net-ncsi-add-payload-to-be-32-bit-aligned-to-fix-dro.patch new file mode 100644 index 00000000000..2bf76bb8ed4 --- /dev/null +++ b/queue-5.10/net-ncsi-add-payload-to-be-32-bit-aligned-to-fix-dro.patch @@ -0,0 +1,92 @@ +From 7ad1629584ab02746ca0a3348c13857103f4deb5 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 22 Nov 2021 22:08:18 +0530 +Subject: net/ncsi : Add payload to be 32-bit aligned to fix dropped packets + +From: Kumar Thangavel + +[ Upstream commit ac132852147ad303a938dda318970dd1bbdfda4e ] + +Update NC-SI command handler (both standard and OEM) to take into +account of payload paddings in allocating skb (in case of payload +size is not 32-bit aligned). + +The checksum field follows payload field, without taking payload +padding into account can cause checksum being truncated, leading to +dropped packets. + +Fixes: fb4ee67529ff ("net/ncsi: Add NCSI OEM command support") +Signed-off-by: Kumar Thangavel +Acked-by: Samuel Mendoza-Jonas +Reviewed-by: Paul Menzel +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ncsi/ncsi-cmd.c | 24 ++++++++++++++++-------- + 1 file changed, 16 insertions(+), 8 deletions(-) + +diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c +index ba9ae482141b0..dda8b76b77988 100644 +--- a/net/ncsi/ncsi-cmd.c ++++ b/net/ncsi/ncsi-cmd.c +@@ -18,6 +18,8 @@ + #include "internal.h" + #include "ncsi-pkt.h" + ++static const int padding_bytes = 26; ++ + u32 ncsi_calculate_checksum(unsigned char *data, int len) + { + u32 checksum = 0; +@@ -213,12 +215,17 @@ static int ncsi_cmd_handler_oem(struct sk_buff *skb, + { + struct ncsi_cmd_oem_pkt *cmd; + unsigned int len; ++ int payload; ++ /* NC-SI spec DSP_0222_1.2.0, section 8.2.2.2 ++ * requires payload to be padded with 0 to ++ * 32-bit boundary before the checksum field. ++ * Ensure the padding bytes are accounted for in ++ * skb allocation ++ */ + ++ payload = ALIGN(nca->payload, 4); + len = sizeof(struct ncsi_cmd_pkt_hdr) + 4; +- if (nca->payload < 26) +- len += 26; +- else +- len += nca->payload; ++ len += max(payload, padding_bytes); + + cmd = skb_put_zero(skb, len); + memcpy(&cmd->mfr_id, nca->data, nca->payload); +@@ -272,6 +279,7 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca) + struct net_device *dev = nd->dev; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; ++ int payload; + int len = hlen + tlen; + struct sk_buff *skb; + struct ncsi_request *nr; +@@ -281,14 +289,14 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca) + return NULL; + + /* NCSI command packet has 16-bytes header, payload, 4 bytes checksum. ++ * Payload needs padding so that the checksum field following payload is ++ * aligned to 32-bit boundary. + * The packet needs padding if its payload is less than 26 bytes to + * meet 64 bytes minimal ethernet frame length. + */ + len += sizeof(struct ncsi_cmd_pkt_hdr) + 4; +- if (nca->payload < 26) +- len += 26; +- else +- len += nca->payload; ++ payload = ALIGN(nca->payload, 4); ++ len += max(payload, padding_bytes); + + /* Allocate skb */ + skb = alloc_skb(len, GFP_ATOMIC); +-- +2.33.0 + diff --git a/queue-5.10/net-nexthop-release-ipv6-per-cpu-dsts-when-replacing.patch b/queue-5.10/net-nexthop-release-ipv6-per-cpu-dsts-when-replacing.patch new file mode 100644 index 00000000000..7141d54368f --- /dev/null +++ b/queue-5.10/net-nexthop-release-ipv6-per-cpu-dsts-when-replacing.patch @@ -0,0 +1,154 @@ +From 1d887b3a914437b24d343c638032df8a4269e7b3 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 22 Nov 2021 17:15:13 +0200 +Subject: net: nexthop: release IPv6 per-cpu dsts when replacing a nexthop + group + +From: Nikolay Aleksandrov + +[ Upstream commit 1005f19b9357b81aa64e1decd08d6e332caaa284 ] + +When replacing a nexthop group, we must release the IPv6 per-cpu dsts of +the removed nexthop entries after an RCU grace period because they +contain references to the nexthop's net device and to the fib6 info. +With specific series of events[1] we can reach net device refcount +imbalance which is unrecoverable. IPv4 is not affected because dsts +don't take a refcount on the route. + +[1] + $ ip nexthop list + id 200 via 2002:db8::2 dev bridge.10 scope link onlink + id 201 via 2002:db8::3 dev bridge scope link onlink + id 203 group 201/200 + $ ip -6 route + 2001:db8::10 nhid 203 metric 1024 pref medium + nexthop via 2002:db8::3 dev bridge weight 1 onlink + nexthop via 2002:db8::2 dev bridge.10 weight 1 onlink + +Create rt6_info through one of the multipath legs, e.g.: + $ taskset -a -c 1 ./pkt_inj 24 bridge.10 2001:db8::10 + (pkt_inj is just a custom packet generator, nothing special) + +Then remove that leg from the group by replace (let's assume it is id +200 in this case): + $ ip nexthop replace id 203 group 201 + +Now remove the IPv6 route: + $ ip -6 route del 2001:db8::10/128 + +The route won't be really deleted due to the stale rt6_info holding 1 +refcnt in nexthop id 200. +At this point we have the following reference count dependency: + (deleted) IPv6 route holds 1 reference over nhid 203 + nh 203 holds 1 ref over id 201 + nh 200 holds 1 ref over the net device and the route due to the stale + rt6_info + +Now to create circular dependency between nh 200 and the IPv6 route, and +also to get a reference over nh 200, restore nhid 200 in the group: + $ ip nexthop replace id 203 group 201/200 + +And now we have a permanent circular dependncy because nhid 203 holds a +reference over nh 200 and 201, but the route holds a ref over nh 203 and +is deleted. + +To trigger the bug just delete the group (nhid 203): + $ ip nexthop del id 203 + +It won't really be deleted due to the IPv6 route dependency, and now we +have 2 unlinked and deleted objects that reference each other: the group +and the IPv6 route. Since the group drops the reference it holds over its +entries at free time (i.e. its own refcount needs to drop to 0) that will +never happen and we get a permanent ref on them, since one of the entries +holds a reference over the IPv6 route it will also never be released. + +At this point the dependencies are: + (deleted, only unlinked) IPv6 route holds reference over group nh 203 + (deleted, only unlinked) group nh 203 holds reference over nh 201 and 200 + nh 200 holds 1 ref over the net device and the route due to the stale + rt6_info + +This is the last point where it can be fixed by running traffic through +nh 200, and specifically through the same CPU so the rt6_info (dst) will +get released due to the IPv6 genid, that in turn will free the IPv6 +route, which in turn will free the ref count over the group nh 203. + +If nh 200 is deleted at this point, it will never be released due to the +ref from the unlinked group 203, it will only be unlinked: + $ ip nexthop del id 200 + $ ip nexthop + $ + +Now we can never release that stale rt6_info, we have IPv6 route with ref +over group nh 203, group nh 203 with ref over nh 200 and 201, nh 200 with +rt6_info (dst) with ref over the net device and the IPv6 route. All of +these objects are only unlinked, and cannot be released, thus they can't +release their ref counts. + + Message from syslogd@dev at Nov 19 14:04:10 ... + kernel:[73501.828730] unregister_netdevice: waiting for bridge.10 to become free. Usage count = 3 + Message from syslogd@dev at Nov 19 14:04:20 ... + kernel:[73512.068811] unregister_netdevice: waiting for bridge.10 to become free. Usage count = 3 + +Fixes: 7bf4796dd099 ("nexthops: add support for replace") +Signed-off-by: Nikolay Aleksandrov +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ipv4/nexthop.c | 25 +++++++++++++++++++++++-- + 1 file changed, 23 insertions(+), 2 deletions(-) + +diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c +index 4dbc628f8c386..8bd3f5e3c0e7a 100644 +--- a/net/ipv4/nexthop.c ++++ b/net/ipv4/nexthop.c +@@ -924,15 +924,36 @@ static void remove_nexthop(struct net *net, struct nexthop *nh, + /* if any FIB entries reference this nexthop, any dst entries + * need to be regenerated + */ +-static void nh_rt_cache_flush(struct net *net, struct nexthop *nh) ++static void nh_rt_cache_flush(struct net *net, struct nexthop *nh, ++ struct nexthop *replaced_nh) + { + struct fib6_info *f6i; ++ struct nh_group *nhg; ++ int i; + + if (!list_empty(&nh->fi_list)) + rt_cache_flush(net); + + list_for_each_entry(f6i, &nh->f6i_list, nh_list) + ipv6_stub->fib6_update_sernum(net, f6i); ++ ++ /* if an IPv6 group was replaced, we have to release all old ++ * dsts to make sure all refcounts are released ++ */ ++ if (!replaced_nh->is_group) ++ return; ++ ++ /* new dsts must use only the new nexthop group */ ++ synchronize_net(); ++ ++ nhg = rtnl_dereference(replaced_nh->nh_grp); ++ for (i = 0; i < nhg->num_nh; i++) { ++ struct nh_grp_entry *nhge = &nhg->nh_entries[i]; ++ struct nh_info *nhi = rtnl_dereference(nhge->nh->nh_info); ++ ++ if (nhi->family == AF_INET6) ++ ipv6_stub->fib6_nh_release_dsts(&nhi->fib6_nh); ++ } + } + + static int replace_nexthop_grp(struct net *net, struct nexthop *old, +@@ -1111,7 +1132,7 @@ static int replace_nexthop(struct net *net, struct nexthop *old, + err = replace_nexthop_single(net, old, new, extack); + + if (!err) { +- nh_rt_cache_flush(net, old); ++ nh_rt_cache_flush(net, old, new); + + __remove_nexthop(net, new, NULL); + nexthop_put(new); +-- +2.33.0 + diff --git a/queue-5.10/net-phylink-force-link-down-and-retrigger-resolve-on.patch b/queue-5.10/net-phylink-force-link-down-and-retrigger-resolve-on.patch new file mode 100644 index 00000000000..2c93979029e --- /dev/null +++ b/queue-5.10/net-phylink-force-link-down-and-retrigger-resolve-on.patch @@ -0,0 +1,103 @@ +From a4ca11b9b19c0784982296e8869294d0fe940d3b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 23 Nov 2021 16:44:02 +0100 +Subject: net: phylink: Force link down and retrigger resolve on interface + change +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Russell King (Oracle) + +[ Upstream commit 80662f4fd4771bc9c7cc4abdfbe866ebd1179621 ] + +On PHY state change the phylink_resolve() function can read stale +information from the MAC and report incorrect link speed and duplex to +the kernel message log. + +Example with a Marvell 88X3310 PHY connected to a SerDes port on Marvell +88E6393X switch: +- PHY driver triggers state change due to PHY interface mode being + changed from 10gbase-r to 2500base-x due to copper change in speed + from 10Gbps to 2.5Gbps, but the PHY itself either hasn't yet changed + its interface to the host, or the interrupt about loss of SerDes link + hadn't arrived yet (there can be a delay of several milliseconds for + this), so we still think that the 10gbase-r mode is up +- phylink_resolve() + - phylink_mac_pcs_get_state() + - this fills in speed=10g link=up + - interface mode is updated to 2500base-x but speed is left at 10Gbps + - phylink_major_config() + - interface is changed to 2500base-x + - phylink_link_up() + - mv88e6xxx_mac_link_up() + - .port_set_speed_duplex() + - speed is set to 10Gbps + - reports "Link is Up - 10Gbps/Full" to dmesg + +Afterwards when the interrupt finally arrives for mv88e6xxx, another +resolve is forced in which we get the correct speed from +phylink_mac_pcs_get_state(), but since the interface is not being +changed anymore, we don't call phylink_major_config() but only +phylink_mac_config(), which does not set speed/duplex anymore. + +To fix this, we need to force the link down and trigger another resolve +on PHY interface change event. + +Fixes: 9525ae83959b ("phylink: add phylink infrastructure") +Signed-off-by: Russell King (Oracle) +Signed-off-by: Marek Behún +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/phy/phylink.c | 13 ++++++++++++- + 1 file changed, 12 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c +index 899496f089d2e..8279e08dad9db 100644 +--- a/drivers/net/phy/phylink.c ++++ b/drivers/net/phy/phylink.c +@@ -644,6 +644,7 @@ static void phylink_resolve(struct work_struct *w) + struct phylink_link_state link_state; + struct net_device *ndev = pl->netdev; + bool mac_config = false; ++ bool retrigger = false; + bool cur_link_state; + + mutex_lock(&pl->state_mutex); +@@ -657,6 +658,7 @@ static void phylink_resolve(struct work_struct *w) + link_state.link = false; + } else if (pl->mac_link_dropped) { + link_state.link = false; ++ retrigger = true; + } else { + switch (pl->cur_link_an_mode) { + case MLO_AN_PHY: +@@ -680,6 +682,15 @@ static void phylink_resolve(struct work_struct *w) + + /* Only update if the PHY link is up */ + if (pl->phydev && pl->phy_state.link) { ++ /* If the interface has changed, force a ++ * link down event if the link isn't already ++ * down, and re-resolve. ++ */ ++ if (link_state.interface != ++ pl->phy_state.interface) { ++ retrigger = true; ++ link_state.link = false; ++ } + link_state.interface = pl->phy_state.interface; + + /* If we have a PHY, we need to update with +@@ -721,7 +732,7 @@ static void phylink_resolve(struct work_struct *w) + else + phylink_link_up(pl, link_state); + } +- if (!link_state.link && pl->mac_link_dropped) { ++ if (!link_state.link && retrigger) { + pl->mac_link_dropped = false; + queue_work(system_power_efficient_wq, &pl->resolve); + } +-- +2.33.0 + diff --git a/queue-5.10/net-phylink-force-retrigger-in-case-of-latched-link-.patch b/queue-5.10/net-phylink-force-retrigger-in-case-of-latched-link-.patch new file mode 100644 index 00000000000..249244e03c3 --- /dev/null +++ b/queue-5.10/net-phylink-force-retrigger-in-case-of-latched-link-.patch @@ -0,0 +1,66 @@ +From 82a1ffd9d9053c9fde1e845da3d7aba382d89bf6 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 23 Nov 2021 16:44:03 +0100 +Subject: net: phylink: Force retrigger in case of latched link-fail indicator +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Russell King (Oracle) + +[ Upstream commit dbae3388ea9ca33bd1d5eabc3b0ef17e69c74677 ] + +On mv88e6xxx 1G/2.5G PCS, the SerDes register 4.2001.2 has the following +description: + This register bit indicates when link was lost since the last + read. For the current link status, read this register + back-to-back. + +Thus to get current link state, we need to read the register twice. + +But doing that in the link change interrupt handler would lead to +potentially ignoring link down events, which we really want to avoid. + +Thus this needs to be solved in phylink's resolve, by retriggering +another resolve in the event when PCS reports link down and previous +link was up, and by re-reading PCS state if the previous link was down. + +The wrong value is read when phylink requests change from sgmii to +2500base-x mode, and link won't come up. This fixes the bug. + +Fixes: 9525ae83959b ("phylink: add phylink infrastructure") +Signed-off-by: Russell King (Oracle) +Signed-off-by: Marek Behún +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/phy/phylink.c | 13 +++++++++++++ + 1 file changed, 13 insertions(+) + +diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c +index 8279e08dad9db..57b1b138522e0 100644 +--- a/drivers/net/phy/phylink.c ++++ b/drivers/net/phy/phylink.c +@@ -675,6 +675,19 @@ static void phylink_resolve(struct work_struct *w) + case MLO_AN_INBAND: + phylink_mac_pcs_get_state(pl, &link_state); + ++ /* The PCS may have a latching link-fail indicator. ++ * If the link was up, bring the link down and ++ * re-trigger the resolve. Otherwise, re-read the ++ * PCS state to get the current status of the link. ++ */ ++ if (!link_state.link) { ++ if (cur_link_state) ++ retrigger = true; ++ else ++ phylink_mac_pcs_get_state(pl, ++ &link_state); ++ } ++ + /* If we have a phy, the "up" state is the union of + * both the PHY and the MAC */ + if (pl->phydev) +-- +2.33.0 + diff --git a/queue-5.10/net-sched-sch_ets-don-t-peek-at-classes-beyond-nband.patch b/queue-5.10/net-sched-sch_ets-don-t-peek-at-classes-beyond-nband.patch new file mode 100644 index 00000000000..13713d5cdca --- /dev/null +++ b/queue-5.10/net-sched-sch_ets-don-t-peek-at-classes-beyond-nband.patch @@ -0,0 +1,101 @@ +From 193e65928641d48c8c89ee8c70e9a464dfd66a16 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 24 Nov 2021 17:14:40 +0100 +Subject: net/sched: sch_ets: don't peek at classes beyond 'nbands' + +From: Davide Caratti + +[ Upstream commit de6d25924c2a8c2988c6a385990cafbe742061bf ] + +when the number of DRR classes decreases, the round-robin active list can +contain elements that have already been freed in ets_qdisc_change(). As a +consequence, it's possible to see a NULL dereference crash, caused by the +attempt to call cl->qdisc->ops->peek(cl->qdisc) when cl->qdisc is NULL: + + BUG: kernel NULL pointer dereference, address: 0000000000000018 + #PF: supervisor read access in kernel mode + #PF: error_code(0x0000) - not-present page + PGD 0 P4D 0 + Oops: 0000 [#1] PREEMPT SMP NOPTI + CPU: 1 PID: 910 Comm: mausezahn Not tainted 5.16.0-rc1+ #475 + Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 + RIP: 0010:ets_qdisc_dequeue+0x129/0x2c0 [sch_ets] + Code: c5 01 41 39 ad e4 02 00 00 0f 87 18 ff ff ff 49 8b 85 c0 02 00 00 49 39 c4 0f 84 ba 00 00 00 49 8b ad c0 02 00 00 48 8b 7d 10 <48> 8b 47 18 48 8b 40 38 0f ae e8 ff d0 48 89 c3 48 85 c0 0f 84 9d + RSP: 0000:ffffbb36c0b5fdd8 EFLAGS: 00010287 + RAX: ffff956678efed30 RBX: 0000000000000000 RCX: 0000000000000000 + RDX: 0000000000000002 RSI: ffffffff9b938dc9 RDI: 0000000000000000 + RBP: ffff956678efed30 R08: e2f3207fe360129c R09: 0000000000000000 + R10: 0000000000000001 R11: 0000000000000001 R12: ffff956678efeac0 + R13: ffff956678efe800 R14: ffff956611545000 R15: ffff95667ac8f100 + FS: 00007f2aa9120740(0000) GS:ffff95667b800000(0000) knlGS:0000000000000000 + CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 + CR2: 0000000000000018 CR3: 000000011070c000 CR4: 0000000000350ee0 + Call Trace: + + qdisc_peek_dequeued+0x29/0x70 [sch_ets] + tbf_dequeue+0x22/0x260 [sch_tbf] + __qdisc_run+0x7f/0x630 + net_tx_action+0x290/0x4c0 + __do_softirq+0xee/0x4f8 + irq_exit_rcu+0xf4/0x130 + sysvec_apic_timer_interrupt+0x52/0xc0 + asm_sysvec_apic_timer_interrupt+0x12/0x20 + RIP: 0033:0x7f2aa7fc9ad4 + Code: b9 ff ff 48 8b 54 24 18 48 83 c4 08 48 89 ee 48 89 df 5b 5d e9 ed fc ff ff 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa <53> 48 83 ec 10 48 8b 05 10 64 33 00 48 8b 00 48 85 c0 0f 85 84 00 + RSP: 002b:00007ffe5d33fab8 EFLAGS: 00000202 + RAX: 0000000000000002 RBX: 0000561f72c31460 RCX: 0000561f72c31720 + RDX: 0000000000000002 RSI: 0000561f72c31722 RDI: 0000561f72c31720 + RBP: 000000000000002a R08: 00007ffe5d33fa40 R09: 0000000000000014 + R10: 0000000000000000 R11: 0000000000000246 R12: 0000561f7187e380 + R13: 0000000000000000 R14: 0000000000000000 R15: 0000561f72c31460 + + Modules linked in: sch_ets sch_tbf dummy rfkill iTCO_wdt intel_rapl_msr iTCO_vendor_support intel_rapl_common joydev virtio_balloon lpc_ich i2c_i801 i2c_smbus pcspkr ip_tables xfs libcrc32c crct10dif_pclmul crc32_pclmul crc32c_intel ahci libahci ghash_clmulni_intel serio_raw libata virtio_blk virtio_console virtio_net net_failover failover sunrpc dm_mirror dm_region_hash dm_log dm_mod + CR2: 0000000000000018 + +Ensuring that 'alist' was never zeroed [1] was not sufficient, we need to +remove from the active list those elements that are no more SP nor DRR. + +[1] https://lore.kernel.org/netdev/60d274838bf09777f0371253416e8af71360bc08.1633609148.git.dcaratti@redhat.com/ + +v3: fix race between ets_qdisc_change() and ets_qdisc_dequeue() delisting + DRR classes beyond 'nbands' in ets_qdisc_change() with the qdisc lock + acquired, thanks to Cong Wang. + +v2: when a NULL qdisc is found in the DRR active list, try to dequeue skb + from the next list item. + +Reported-by: Hangbin Liu +Fixes: dcc68b4d8084 ("net: sch_ets: Add a new Qdisc") +Signed-off-by: Davide Caratti +Link: https://lore.kernel.org/r/7a5c496eed2d62241620bdbb83eb03fb9d571c99.1637762721.git.dcaratti@redhat.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/sched/sch_ets.c | 8 +++++--- + 1 file changed, 5 insertions(+), 3 deletions(-) + +diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c +index c76701ac35abf..c34cb6e81d855 100644 +--- a/net/sched/sch_ets.c ++++ b/net/sched/sch_ets.c +@@ -667,12 +667,14 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, + q->classes[i].deficit = quanta[i]; + } + } ++ for (i = q->nbands; i < oldbands; i++) { ++ qdisc_tree_flush_backlog(q->classes[i].qdisc); ++ if (i >= q->nstrict) ++ list_del(&q->classes[i].alist); ++ } + q->nstrict = nstrict; + memcpy(q->prio2band, priomap, sizeof(priomap)); + +- for (i = q->nbands; i < oldbands; i++) +- qdisc_tree_flush_backlog(q->classes[i].qdisc); +- + for (i = 0; i < q->nbands; i++) + q->classes[i].quantum = quanta[i]; + +-- +2.33.0 + diff --git a/queue-5.10/net-smc-don-t-call-clcsock-shutdown-twice-when-smc-s.patch b/queue-5.10/net-smc-don-t-call-clcsock-shutdown-twice-when-smc-s.patch new file mode 100644 index 00000000000..db597812ffa --- /dev/null +++ b/queue-5.10/net-smc-don-t-call-clcsock-shutdown-twice-when-smc-s.patch @@ -0,0 +1,67 @@ +From feb2d0ba5b32faf3d0492662b168bf94974cc9ac Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 26 Nov 2021 10:41:35 +0800 +Subject: net/smc: Don't call clcsock shutdown twice when smc shutdown + +From: Tony Lu + +[ Upstream commit bacb6c1e47691cda4a95056c21b5487fb7199fcc ] + +When applications call shutdown() with SHUT_RDWR in userspace, +smc_close_active() calls kernel_sock_shutdown(), and it is called +twice in smc_shutdown(). + +This fixes this by checking sk_state before do clcsock shutdown, and +avoids missing the application's call of smc_shutdown(). + +Link: https://lore.kernel.org/linux-s390/1f67548e-cbf6-0dce-82b5-10288a4583bd@linux.ibm.com/ +Fixes: 606a63c9783a ("net/smc: Ensure the active closing peer first closes clcsock") +Signed-off-by: Tony Lu +Reviewed-by: Wen Gu +Acked-by: Karsten Graul +Link: https://lore.kernel.org/r/20211126024134.45693-1-tonylu@linux.alibaba.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/smc/af_smc.c | 8 +++++++- + 1 file changed, 7 insertions(+), 1 deletion(-) + +diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c +index a0d3f4e07b067..ac8265e35b2d2 100644 +--- a/net/smc/af_smc.c ++++ b/net/smc/af_smc.c +@@ -2098,8 +2098,10 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, + static int smc_shutdown(struct socket *sock, int how) + { + struct sock *sk = sock->sk; ++ bool do_shutdown = true; + struct smc_sock *smc; + int rc = -EINVAL; ++ int old_state; + int rc1 = 0; + + smc = smc_sk(sk); +@@ -2126,7 +2128,11 @@ static int smc_shutdown(struct socket *sock, int how) + } + switch (how) { + case SHUT_RDWR: /* shutdown in both directions */ ++ old_state = sk->sk_state; + rc = smc_close_active(smc); ++ if (old_state == SMC_ACTIVE && ++ sk->sk_state == SMC_PEERCLOSEWAIT1) ++ do_shutdown = false; + break; + case SHUT_WR: + rc = smc_close_shutdown_write(smc); +@@ -2136,7 +2142,7 @@ static int smc_shutdown(struct socket *sock, int how) + /* nothing more to do because peer is not involved */ + break; + } +- if (smc->clcsock) ++ if (do_shutdown && smc->clcsock) + rc1 = kernel_sock_shutdown(smc->clcsock, how); + /* map sock_shutdown_cmd constants to sk_shutdown value range */ + sk->sk_shutdown |= how + 1; +-- +2.33.0 + diff --git a/queue-5.10/net-smc-ensure-the-active-closing-peer-first-closes-.patch b/queue-5.10/net-smc-ensure-the-active-closing-peer-first-closes-.patch new file mode 100644 index 00000000000..1a472bf6b39 --- /dev/null +++ b/queue-5.10/net-smc-ensure-the-active-closing-peer-first-closes-.patch @@ -0,0 +1,77 @@ +From cc7074aa215fa9f9b97e1684ea0fb566440282fe Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 23 Nov 2021 16:25:18 +0800 +Subject: net/smc: Ensure the active closing peer first closes clcsock + +From: Tony Lu + +[ Upstream commit 606a63c9783a32a45bd2ef0eee393711d75b3284 ] + +The side that actively closed socket, it's clcsock doesn't enter +TIME_WAIT state, but the passive side does it. It should show the same +behavior as TCP sockets. + +Consider this, when client actively closes the socket, the clcsock in +server enters TIME_WAIT state, which means the address is occupied and +won't be reused before TIME_WAIT dismissing. If we restarted server, the +service would be unavailable for a long time. + +To solve this issue, shutdown the clcsock in [A], perform the TCP active +close progress first, before the passive closed side closing it. So that +the actively closed side enters TIME_WAIT, not the passive one. + +Client | Server +close() // client actively close | + smc_release() | + smc_close_active() // PEERCLOSEWAIT1 | + smc_close_final() // abort or closed = 1| + smc_cdc_get_slot_and_msg_send() | + [A] | + |smc_cdc_msg_recv_action() // ACTIVE + | queue_work(smc_close_wq, &conn->close_work) + | smc_close_passive_work() // PROCESSABORT or APPCLOSEWAIT1 + | smc_close_passive_abort_received() // only in abort + | + |close() // server recv zero, close + | smc_release() // PROCESSABORT or APPCLOSEWAIT1 + | smc_close_active() + | smc_close_abort() or smc_close_final() // CLOSED + | smc_cdc_get_slot_and_msg_send() // abort or closed = 1 +smc_cdc_msg_recv_action() | smc_clcsock_release() + queue_work(smc_close_wq, &conn->close_work) | sock_release(tcp) // actively close clc, enter TIME_WAIT + smc_close_passive_work() // PEERCLOSEWAIT1 | smc_conn_free() + smc_close_passive_abort_received() // CLOSED| + smc_conn_free() | + smc_clcsock_release() | + sock_release(tcp) // passive close clc | + +Link: https://www.spinics.net/lists/netdev/msg780407.html +Fixes: b38d732477e4 ("smc: socket closing and linkgroup cleanup") +Signed-off-by: Tony Lu +Reviewed-by: Wen Gu +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/smc/smc_close.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c +index 0f9ffba07d268..04620b53b74a7 100644 +--- a/net/smc/smc_close.c ++++ b/net/smc/smc_close.c +@@ -228,6 +228,12 @@ int smc_close_active(struct smc_sock *smc) + /* send close request */ + rc = smc_close_final(conn); + sk->sk_state = SMC_PEERCLOSEWAIT1; ++ ++ /* actively shutdown clcsock before peer close it, ++ * prevent peer from entering TIME_WAIT state. ++ */ ++ if (smc->clcsock && smc->clcsock->sk) ++ rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); + } else { + /* peer event has changed the state */ + goto again; +-- +2.33.0 + diff --git a/queue-5.10/net-smc-fix-loop-in-smc_listen.patch b/queue-5.10/net-smc-fix-loop-in-smc_listen.patch new file mode 100644 index 00000000000..3dfb45a9f1e --- /dev/null +++ b/queue-5.10/net-smc-fix-loop-in-smc_listen.patch @@ -0,0 +1,49 @@ +From eb04e8adc605e3bbb62a5bcda98dfcddacd3ba0d Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 24 Nov 2021 13:32:38 +0100 +Subject: net/smc: Fix loop in smc_listen + +From: Guo DaXing + +[ Upstream commit 9ebb0c4b27a6158303b791b5b91e66d7665ee30e ] + +The kernel_listen function in smc_listen will fail when all the available +ports are occupied. At this point smc->clcsock->sk->sk_data_ready has +been changed to smc_clcsock_data_ready. When we call smc_listen again, +now both smc->clcsock->sk->sk_data_ready and smc->clcsk_data_ready point +to the smc_clcsock_data_ready function. + +The smc_clcsock_data_ready() function calls lsmc->clcsk_data_ready which +now points to itself resulting in an infinite loop. + +This patch restores smc->clcsock->sk->sk_data_ready with the old value. + +Fixes: a60a2b1e0af1 ("net/smc: reduce active tcp_listen workers") +Signed-off-by: Guo DaXing +Acked-by: Tony Lu +Signed-off-by: Karsten Graul +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/smc/af_smc.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c +index cfb5b9be0569d..a0d3f4e07b067 100644 +--- a/net/smc/af_smc.c ++++ b/net/smc/af_smc.c +@@ -1864,8 +1864,10 @@ static int smc_listen(struct socket *sock, int backlog) + smc->clcsock->sk->sk_user_data = + (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); + rc = kernel_listen(smc->clcsock, backlog); +- if (rc) ++ if (rc) { ++ smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; + goto out; ++ } + sk->sk_max_ack_backlog = backlog; + sk->sk_ack_backlog = 0; + sk->sk_state = SMC_LISTEN; +-- +2.33.0 + diff --git a/queue-5.10/net-smc-fix-null-pointer-dereferencing-in-smc_vlan_b.patch b/queue-5.10/net-smc-fix-null-pointer-dereferencing-in-smc_vlan_b.patch new file mode 100644 index 00000000000..5a6328ebdec --- /dev/null +++ b/queue-5.10/net-smc-fix-null-pointer-dereferencing-in-smc_vlan_b.patch @@ -0,0 +1,93 @@ +From 498f8967b4772daa7d19aaba93a705269da56750 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 24 Nov 2021 13:32:37 +0100 +Subject: net/smc: Fix NULL pointer dereferencing in smc_vlan_by_tcpsk() + +From: Karsten Graul + +[ Upstream commit 587acad41f1bc48e16f42bb2aca63bf323380be8 ] + +Coverity reports a possible NULL dereferencing problem: + +in smc_vlan_by_tcpsk(): +6. returned_null: netdev_lower_get_next returns NULL (checked 29 out of 30 times). +7. var_assigned: Assigning: ndev = NULL return value from netdev_lower_get_next. +1623 ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower); +CID 1468509 (#1 of 1): Dereference null return value (NULL_RETURNS) +8. dereference: Dereferencing a pointer that might be NULL ndev when calling is_vlan_dev. +1624 if (is_vlan_dev(ndev)) { + +Remove the manual implementation and use netdev_walk_all_lower_dev() to +iterate over the lower devices. While on it remove an obsolete function +parameter comment. + +Fixes: cb9d43f67754 ("net/smc: determine vlan_id of stacked net_device") +Suggested-by: Julian Wiedmann +Signed-off-by: Karsten Graul +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/smc/smc_core.c | 35 ++++++++++++++++++----------------- + 1 file changed, 18 insertions(+), 17 deletions(-) + +diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c +index 109d790eaebe2..cd625b672429f 100644 +--- a/net/smc/smc_core.c ++++ b/net/smc/smc_core.c +@@ -1209,14 +1209,26 @@ static void smc_link_down_work(struct work_struct *work) + mutex_unlock(&lgr->llc_conf_mutex); + } + +-/* Determine vlan of internal TCP socket. +- * @vlan_id: address to store the determined vlan id into +- */ ++static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, ++ struct netdev_nested_priv *priv) ++{ ++ unsigned short *vlan_id = (unsigned short *)priv->data; ++ ++ if (is_vlan_dev(lower_dev)) { ++ *vlan_id = vlan_dev_vlan_id(lower_dev); ++ return 1; ++ } ++ ++ return 0; ++} ++ ++/* Determine vlan of internal TCP socket. */ + int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) + { + struct dst_entry *dst = sk_dst_get(clcsock->sk); ++ struct netdev_nested_priv priv; + struct net_device *ndev; +- int i, nest_lvl, rc = 0; ++ int rc = 0; + + ini->vlan_id = 0; + if (!dst) { +@@ -1234,20 +1246,9 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) + goto out_rel; + } + ++ priv.data = (void *)&ini->vlan_id; + rtnl_lock(); +- nest_lvl = ndev->lower_level; +- for (i = 0; i < nest_lvl; i++) { +- struct list_head *lower = &ndev->adj_list.lower; +- +- if (list_empty(lower)) +- break; +- lower = lower->next; +- ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower); +- if (is_vlan_dev(ndev)) { +- ini->vlan_id = vlan_dev_vlan_id(ndev); +- break; +- } +- } ++ netdev_walk_all_lower_dev(ndev, smc_vlan_by_tcpsk_walk, &priv); + rtnl_unlock(); + + out_rel: +-- +2.33.0 + diff --git a/queue-5.10/net-stmmac-fix-system-hang-caused-by-eee_ctrl_timer-.patch b/queue-5.10/net-stmmac-fix-system-hang-caused-by-eee_ctrl_timer-.patch new file mode 100644 index 00000000000..0bf67e8fccf --- /dev/null +++ b/queue-5.10/net-stmmac-fix-system-hang-caused-by-eee_ctrl_timer-.patch @@ -0,0 +1,156 @@ +From b14d79398c691ecd96936069230eb526cb6d5ac0 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 8 Sep 2021 15:43:35 +0800 +Subject: net: stmmac: fix system hang caused by eee_ctrl_timer during + suspend/resume + +From: Joakim Zhang + +[ Upstream commit 276aae377206d60b9b7b7df4586cd9f2a813f5d0 ] + +commit 5f58591323bf ("net: stmmac: delete the eee_ctrl_timer after +napi disabled"), this patch tries to fix system hang caused by eee_ctrl_timer, +unfortunately, it only can resolve it for system reboot stress test. System +hang also can be reproduced easily during system suspend/resume stess test +when mount NFS on i.MX8MP EVK board. + +In stmmac driver, eee feature is combined to phylink framework. When do +system suspend, phylink_stop() would queue delayed work, it invokes +stmmac_mac_link_down(), where to deactivate eee_ctrl_timer synchronizly. +In above commit, try to fix issue by deactivating eee_ctrl_timer obviously, +but it is not enough. Looking into eee_ctrl_timer expire callback +stmmac_eee_ctrl_timer(), it could enable hareware eee mode again. What is +unexpected is that LPI interrupt (MAC_Interrupt_Enable.LPIEN bit) is always +asserted. This interrupt has chance to be issued when LPI state entry/exit +from the MAC, and at that time, clock could have been already disabled. +The result is that system hang when driver try to touch register from +interrupt handler. + +The reason why above commit can fix system hang issue in stmmac_release() +is that, deactivate eee_ctrl_timer not just after napi disabled, further +after irq freed. + +In conclusion, hardware would generate LPI interrupt when clock has been +disabled during suspend or resume, since hardware is in eee mode and LPI +interrupt enabled. + +Interrupts from MAC, MTL and DMA level are enabled and never been disabled +when system suspend, so postpone clocks management from suspend stage to +noirq suspend stage should be more safe. + +Fixes: 5f58591323bf ("net: stmmac: delete the eee_ctrl_timer after napi disabled") +Signed-off-by: Joakim Zhang +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + .../net/ethernet/stmicro/stmmac/stmmac_main.c | 14 ------ + .../ethernet/stmicro/stmmac/stmmac_platform.c | 44 +++++++++++++++++++ + 2 files changed, 44 insertions(+), 14 deletions(-) + +diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +index 4a75e73f06bbd..b6a2bc020026a 100644 +--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c ++++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +@@ -5238,7 +5238,6 @@ int stmmac_suspend(struct device *dev) + struct net_device *ndev = dev_get_drvdata(dev); + struct stmmac_priv *priv = netdev_priv(ndev); + u32 chan; +- int ret; + + if (!ndev || !netif_running(ndev)) + return 0; +@@ -5280,13 +5279,6 @@ int stmmac_suspend(struct device *dev) + + stmmac_mac_set(priv, priv->ioaddr, false); + pinctrl_pm_select_sleep_state(priv->device); +- /* Disable clock in case of PWM is off */ +- clk_disable_unprepare(priv->plat->clk_ptp_ref); +- ret = pm_runtime_force_suspend(dev); +- if (ret) { +- mutex_unlock(&priv->lock); +- return ret; +- } + } + mutex_unlock(&priv->lock); + +@@ -5351,12 +5343,6 @@ int stmmac_resume(struct device *dev) + priv->irq_wake = 0; + } else { + pinctrl_pm_select_default_state(priv->device); +- /* enable the clk previously disabled */ +- ret = pm_runtime_force_resume(dev); +- if (ret) +- return ret; +- if (priv->plat->clk_ptp_ref) +- clk_prepare_enable(priv->plat->clk_ptp_ref); + /* reset the phy so that it's ready */ + if (priv->mii) + stmmac_mdio_reset(priv->mii); +diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +index 035f9aef4308f..5c9d29c42bac8 100644 +--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c ++++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +@@ -9,6 +9,7 @@ + *******************************************************************************/ + + #include ++#include + #include + #include + #include +@@ -778,9 +779,52 @@ static int __maybe_unused stmmac_runtime_resume(struct device *dev) + return stmmac_bus_clks_config(priv, true); + } + ++static int stmmac_pltfr_noirq_suspend(struct device *dev) ++{ ++ struct net_device *ndev = dev_get_drvdata(dev); ++ struct stmmac_priv *priv = netdev_priv(ndev); ++ int ret; ++ ++ if (!netif_running(ndev)) ++ return 0; ++ ++ if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { ++ /* Disable clock in case of PWM is off */ ++ clk_disable_unprepare(priv->plat->clk_ptp_ref); ++ ++ ret = pm_runtime_force_suspend(dev); ++ if (ret) ++ return ret; ++ } ++ ++ return 0; ++} ++ ++static int stmmac_pltfr_noirq_resume(struct device *dev) ++{ ++ struct net_device *ndev = dev_get_drvdata(dev); ++ struct stmmac_priv *priv = netdev_priv(ndev); ++ int ret; ++ ++ if (!netif_running(ndev)) ++ return 0; ++ ++ if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { ++ /* enable the clk previously disabled */ ++ ret = pm_runtime_force_resume(dev); ++ if (ret) ++ return ret; ++ ++ clk_prepare_enable(priv->plat->clk_ptp_ref); ++ } ++ ++ return 0; ++} ++ + const struct dev_pm_ops stmmac_pltfr_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_suspend, stmmac_pltfr_resume) + SET_RUNTIME_PM_OPS(stmmac_runtime_suspend, stmmac_runtime_resume, NULL) ++ SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_noirq_suspend, stmmac_pltfr_noirq_resume) + }; + EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops); + +-- +2.33.0 + diff --git a/queue-5.10/net-stmmac-retain-ptp-clock-time-during-siocshwtstam.patch b/queue-5.10/net-stmmac-retain-ptp-clock-time-during-siocshwtstam.patch new file mode 100644 index 00000000000..939c6be3db3 --- /dev/null +++ b/queue-5.10/net-stmmac-retain-ptp-clock-time-during-siocshwtstam.patch @@ -0,0 +1,261 @@ +From c9ba863192529bb6658a089e7c7e1a5ea70b2b83 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sun, 21 Nov 2021 19:57:04 +0200 +Subject: net: stmmac: retain PTP clock time during SIOCSHWTSTAMP ioctls + +From: Holger Assmann + +[ Upstream commit a6da2bbb0005e6b4909472962c9d0af29e75dd06 ] + +Currently, when user space emits SIOCSHWTSTAMP ioctl calls such as +enabling/disabling timestamping or changing filter settings, the driver +reads the current CLOCK_REALTIME value and programming this into the +NIC's hardware clock. This might be necessary during system +initialization, but at runtime, when the PTP clock has already been +synchronized to a grandmaster, a reset of the timestamp settings might +result in a clock jump. Furthermore, if the clock is also controlled by +phc2sys in automatic mode (where the UTC offset is queried from ptp4l), +that UTC-to-TAI offset (currently 37 seconds in 2021) would be +temporarily reset to 0, and it would take a long time for phc2sys to +readjust so that CLOCK_REALTIME and the PHC are apart by 37 seconds +again. + +To address the issue, we introduce a new function called +stmmac_init_tstamp_counter(), which gets called during ndo_open(). +It contains the code snippet moved from stmmac_hwtstamp_set() that +manages the time synchronization. Besides, the sub second increment +configuration is also moved here since the related values are hardware +dependent and runtime invariant. + +Furthermore, the hardware clock must be kept running even when no time +stamping mode is selected in order to retain the synchronized time base. +That way, timestamping can be enabled again at any time only with the +need to compensate the clock's natural drifting. + +As a side effect, this patch fixes the issue that ptp_clock_info::enable +can be called before SIOCSHWTSTAMP and the driver (which looks at +priv->systime_flags) was not prepared to handle that ordering. + +Fixes: 92ba6888510c ("stmmac: add the support for PTP hw clock driver") +Reported-by: Michael Olbrich +Signed-off-by: Ahmad Fatoum +Signed-off-by: Holger Assmann +Signed-off-by: Vladimir Oltean +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/stmicro/stmmac/stmmac.h | 1 + + .../net/ethernet/stmicro/stmmac/stmmac_main.c | 125 +++++++++++------- + .../ethernet/stmicro/stmmac/stmmac_platform.c | 2 +- + 3 files changed, 81 insertions(+), 47 deletions(-) + +diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h +index a4ca283e02284..617c960cfb5a5 100644 +--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h ++++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h +@@ -258,6 +258,7 @@ int stmmac_mdio_register(struct net_device *ndev); + int stmmac_mdio_reset(struct mii_bus *mii); + void stmmac_set_ethtool_ops(struct net_device *netdev); + ++int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags); + void stmmac_ptp_register(struct stmmac_priv *priv); + void stmmac_ptp_unregister(struct stmmac_priv *priv); + int stmmac_resume(struct device *dev); +diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +index b6a2bc020026a..a8c5492cb39be 100644 +--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c ++++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +@@ -47,6 +47,13 @@ + #include "dwxgmac2.h" + #include "hwif.h" + ++/* As long as the interface is active, we keep the timestamping counter enabled ++ * with fine resolution and binary rollover. This avoid non-monotonic behavior ++ * (clock jumps) when changing timestamping settings at runtime. ++ */ ++#define STMMAC_HWTS_ACTIVE (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | \ ++ PTP_TCR_TSCTRLSSR) ++ + #define STMMAC_ALIGN(x) ALIGN(ALIGN(x, SMP_CACHE_BYTES), 16) + #define TSO_MAX_BUFF_SIZE (SZ_16K - 1) + +@@ -508,8 +515,6 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) + { + struct stmmac_priv *priv = netdev_priv(dev); + struct hwtstamp_config config; +- struct timespec64 now; +- u64 temp = 0; + u32 ptp_v2 = 0; + u32 tstamp_all = 0; + u32 ptp_over_ipv4_udp = 0; +@@ -518,11 +523,6 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) + u32 snap_type_sel = 0; + u32 ts_master_en = 0; + u32 ts_event_en = 0; +- u32 sec_inc = 0; +- u32 value = 0; +- bool xmac; +- +- xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; + + if (!(priv->dma_cap.time_stamp || priv->adv_ts)) { + netdev_alert(priv->dev, "No support for HW time stamping\n"); +@@ -684,42 +684,17 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) + priv->hwts_rx_en = ((config.rx_filter == HWTSTAMP_FILTER_NONE) ? 0 : 1); + priv->hwts_tx_en = config.tx_type == HWTSTAMP_TX_ON; + +- if (!priv->hwts_tx_en && !priv->hwts_rx_en) +- stmmac_config_hw_tstamping(priv, priv->ptpaddr, 0); +- else { +- value = (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | PTP_TCR_TSCTRLSSR | +- tstamp_all | ptp_v2 | ptp_over_ethernet | +- ptp_over_ipv6_udp | ptp_over_ipv4_udp | ts_event_en | +- ts_master_en | snap_type_sel); +- stmmac_config_hw_tstamping(priv, priv->ptpaddr, value); +- +- /* program Sub Second Increment reg */ +- stmmac_config_sub_second_increment(priv, +- priv->ptpaddr, priv->plat->clk_ptp_rate, +- xmac, &sec_inc); +- temp = div_u64(1000000000ULL, sec_inc); +- +- /* Store sub second increment and flags for later use */ +- priv->sub_second_inc = sec_inc; +- priv->systime_flags = value; +- +- /* calculate default added value: +- * formula is : +- * addend = (2^32)/freq_div_ratio; +- * where, freq_div_ratio = 1e9ns/sec_inc +- */ +- temp = (u64)(temp << 32); +- priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate); +- stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend); +- +- /* initialize system time */ +- ktime_get_real_ts64(&now); ++ priv->systime_flags = STMMAC_HWTS_ACTIVE; + +- /* lower 32 bits of tv_sec are safe until y2106 */ +- stmmac_init_systime(priv, priv->ptpaddr, +- (u32)now.tv_sec, now.tv_nsec); ++ if (priv->hwts_tx_en || priv->hwts_rx_en) { ++ priv->systime_flags |= tstamp_all | ptp_v2 | ++ ptp_over_ethernet | ptp_over_ipv6_udp | ++ ptp_over_ipv4_udp | ts_event_en | ++ ts_master_en | snap_type_sel; + } + ++ stmmac_config_hw_tstamping(priv, priv->ptpaddr, priv->systime_flags); ++ + memcpy(&priv->tstamp_config, &config, sizeof(config)); + + return copy_to_user(ifr->ifr_data, &config, +@@ -747,6 +722,66 @@ static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr) + sizeof(*config)) ? -EFAULT : 0; + } + ++/** ++ * stmmac_init_tstamp_counter - init hardware timestamping counter ++ * @priv: driver private structure ++ * @systime_flags: timestamping flags ++ * Description: ++ * Initialize hardware counter for packet timestamping. ++ * This is valid as long as the interface is open and not suspended. ++ * Will be rerun after resuming from suspend, case in which the timestamping ++ * flags updated by stmmac_hwtstamp_set() also need to be restored. ++ */ ++int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags) ++{ ++ bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; ++ struct timespec64 now; ++ u32 sec_inc = 0; ++ u64 temp = 0; ++ int ret; ++ ++ if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) ++ return -EOPNOTSUPP; ++ ++ ret = clk_prepare_enable(priv->plat->clk_ptp_ref); ++ if (ret < 0) { ++ netdev_warn(priv->dev, ++ "failed to enable PTP reference clock: %pe\n", ++ ERR_PTR(ret)); ++ return ret; ++ } ++ ++ stmmac_config_hw_tstamping(priv, priv->ptpaddr, systime_flags); ++ priv->systime_flags = systime_flags; ++ ++ /* program Sub Second Increment reg */ ++ stmmac_config_sub_second_increment(priv, priv->ptpaddr, ++ priv->plat->clk_ptp_rate, ++ xmac, &sec_inc); ++ temp = div_u64(1000000000ULL, sec_inc); ++ ++ /* Store sub second increment for later use */ ++ priv->sub_second_inc = sec_inc; ++ ++ /* calculate default added value: ++ * formula is : ++ * addend = (2^32)/freq_div_ratio; ++ * where, freq_div_ratio = 1e9ns/sec_inc ++ */ ++ temp = (u64)(temp << 32); ++ priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate); ++ stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend); ++ ++ /* initialize system time */ ++ ktime_get_real_ts64(&now); ++ ++ /* lower 32 bits of tv_sec are safe until y2106 */ ++ stmmac_init_systime(priv, priv->ptpaddr, (u32)now.tv_sec, now.tv_nsec); ++ ++ return 0; ++} ++EXPORT_SYMBOL_GPL(stmmac_init_tstamp_counter); ++ + /** + * stmmac_init_ptp - init PTP + * @priv: driver private structure +@@ -757,9 +792,11 @@ static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr) + static int stmmac_init_ptp(struct stmmac_priv *priv) + { + bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; ++ int ret; + +- if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) +- return -EOPNOTSUPP; ++ ret = stmmac_init_tstamp_counter(priv, STMMAC_HWTS_ACTIVE); ++ if (ret) ++ return ret; + + priv->adv_ts = 0; + /* Check if adv_ts can be enabled for dwmac 4.x / xgmac core */ +@@ -2721,10 +2758,6 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) + stmmac_mmc_setup(priv); + + if (init_ptp) { +- ret = clk_prepare_enable(priv->plat->clk_ptp_ref); +- if (ret < 0) +- netdev_warn(priv->dev, "failed to enable PTP reference clock: %d\n", ret); +- + ret = stmmac_init_ptp(priv); + if (ret == -EOPNOTSUPP) + netdev_warn(priv->dev, "PTP not supported by HW\n"); +diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +index 5c9d29c42bac8..4387752b26d95 100644 +--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c ++++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +@@ -815,7 +815,7 @@ static int stmmac_pltfr_noirq_resume(struct device *dev) + if (ret) + return ret; + +- clk_prepare_enable(priv->plat->clk_ptp_ref); ++ stmmac_init_tstamp_counter(priv, priv->systime_flags); + } + + return 0; +-- +2.33.0 + diff --git a/queue-5.10/net-vlan-fix-underflow-for-the-real_dev-refcnt.patch b/queue-5.10/net-vlan-fix-underflow-for-the-real_dev-refcnt.patch new file mode 100644 index 00000000000..4e68c3df424 --- /dev/null +++ b/queue-5.10/net-vlan-fix-underflow-for-the-real_dev-refcnt.patch @@ -0,0 +1,78 @@ +From 682ca560fcf34921a453347a0c4f07ea6a81399f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 26 Nov 2021 09:59:42 +0800 +Subject: net: vlan: fix underflow for the real_dev refcnt + +From: Ziyang Xuan + +[ Upstream commit 01d9cc2dea3fde3bad6d27f464eff463496e2b00 ] + +Inject error before dev_hold(real_dev) in register_vlan_dev(), +and execute the following testcase: + +ip link add dev dummy1 type dummy +ip link add name dummy1.100 link dummy1 type vlan id 100 +ip link del dev dummy1 + +When the dummy netdevice is removed, we will get a WARNING as following: + +======================================================================= +refcount_t: decrement hit 0; leaking memory. +WARNING: CPU: 2 PID: 0 at lib/refcount.c:31 refcount_warn_saturate+0xbf/0x1e0 + +and an endless loop of: + +======================================================================= +unregister_netdevice: waiting for dummy1 to become free. Usage count = -1073741824 + +That is because dev_put(real_dev) in vlan_dev_free() be called without +dev_hold(real_dev) in register_vlan_dev(). It makes the refcnt of real_dev +underflow. + +Move the dev_hold(real_dev) to vlan_dev_init() which is the call-back of +ndo_init(). That makes dev_hold() and dev_put() for vlan's real_dev +symmetrical. + +Fixes: 563bcbae3ba2 ("net: vlan: fix a UAF in vlan_dev_real_dev()") +Reported-by: Petr Machata +Suggested-by: Jakub Kicinski +Signed-off-by: Ziyang Xuan +Link: https://lore.kernel.org/r/20211126015942.2918542-1-william.xuanziyang@huawei.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/8021q/vlan.c | 3 --- + net/8021q/vlan_dev.c | 3 +++ + 2 files changed, 3 insertions(+), 3 deletions(-) + +diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c +index ad3780067a7d8..d12c9a8a9953e 100644 +--- a/net/8021q/vlan.c ++++ b/net/8021q/vlan.c +@@ -181,9 +181,6 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) + if (err) + goto out_unregister_netdev; + +- /* Account for reference in struct vlan_dev_priv */ +- dev_hold(real_dev); +- + vlan_stacked_transfer_operstate(real_dev, dev, vlan); + linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */ + +diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c +index c7eba7dab0938..86a1c99025ea0 100644 +--- a/net/8021q/vlan_dev.c ++++ b/net/8021q/vlan_dev.c +@@ -606,6 +606,9 @@ static int vlan_dev_init(struct net_device *dev) + if (!vlan->vlan_pcpu_stats) + return -ENOMEM; + ++ /* Get vlan's reference to real_dev */ ++ dev_hold(real_dev); ++ + return 0; + } + +-- +2.33.0 + diff --git a/queue-5.10/netfilter-ctnetlink-do-not-erase-error-code-with-ein.patch b/queue-5.10/netfilter-ctnetlink-do-not-erase-error-code-with-ein.patch new file mode 100644 index 00000000000..f909b31aa89 --- /dev/null +++ b/queue-5.10/netfilter-ctnetlink-do-not-erase-error-code-with-ein.patch @@ -0,0 +1,38 @@ +From f4455299f04a8f3b1f76a50448e3042354c91e69 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 3 Nov 2021 23:21:55 +0100 +Subject: netfilter: ctnetlink: do not erase error code with EINVAL + +From: Florent Fourcot + +[ Upstream commit 77522ff02f333434612bd72df9b376f8d3836e4d ] + +And be consistent in error management for both orig/reply filtering + +Fixes: cb8aa9a3affb ("netfilter: ctnetlink: add kernel side filtering for dump") +Signed-off-by: Florent Fourcot +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + net/netfilter/nf_conntrack_netlink.c | 4 +--- + 1 file changed, 1 insertion(+), 3 deletions(-) + +diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c +index 39e0ff41688a7..60a1a666e797a 100644 +--- a/net/netfilter/nf_conntrack_netlink.c ++++ b/net/netfilter/nf_conntrack_netlink.c +@@ -974,10 +974,8 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) + filter->family, + &filter->zone, + filter->reply_flags); +- if (err < 0) { +- err = -EINVAL; ++ if (err < 0) + goto err_filter; +- } + } + + return filter; +-- +2.33.0 + diff --git a/queue-5.10/netfilter-ctnetlink-fix-filtering-with-cta_tuple_rep.patch b/queue-5.10/netfilter-ctnetlink-fix-filtering-with-cta_tuple_rep.patch new file mode 100644 index 00000000000..038ecadf875 --- /dev/null +++ b/queue-5.10/netfilter-ctnetlink-fix-filtering-with-cta_tuple_rep.patch @@ -0,0 +1,35 @@ +From 8a7f3000d203c5fafb37804f1de722b2d8081441 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 3 Nov 2021 23:21:54 +0100 +Subject: netfilter: ctnetlink: fix filtering with CTA_TUPLE_REPLY + +From: Florent Fourcot + +[ Upstream commit ad81d4daf6a3f4769a346e635d5e1e967ca455d9 ] + +filter->orig_flags was used for a reply context. + +Fixes: cb8aa9a3affb ("netfilter: ctnetlink: add kernel side filtering for dump") +Signed-off-by: Florent Fourcot +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + net/netfilter/nf_conntrack_netlink.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c +index cb4cfa4f61a8d..39e0ff41688a7 100644 +--- a/net/netfilter/nf_conntrack_netlink.c ++++ b/net/netfilter/nf_conntrack_netlink.c +@@ -973,7 +973,7 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) + CTA_TUPLE_REPLY, + filter->family, + &filter->zone, +- filter->orig_flags); ++ filter->reply_flags); + if (err < 0) { + err = -EINVAL; + goto err_filter; +-- +2.33.0 + diff --git a/queue-5.10/netfilter-flowtable-fix-ipv6-tunnel-addr-match.patch b/queue-5.10/netfilter-flowtable-fix-ipv6-tunnel-addr-match.patch new file mode 100644 index 00000000000..27420137d9f --- /dev/null +++ b/queue-5.10/netfilter-flowtable-fix-ipv6-tunnel-addr-match.patch @@ -0,0 +1,45 @@ +From 6264268b6148959778188ebfa70114e08231d5b1 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sat, 6 Nov 2021 18:28:21 -0700 +Subject: netfilter: flowtable: fix IPv6 tunnel addr match + +From: Will Mortensen + +[ Upstream commit 39f6eed4cb209643f3f8633291854ed7375d7264 ] + +Previously the IPv6 addresses in the key were clobbered and the mask was +left unset. + +I haven't tested this; I noticed it while skimming the code to +understand an unrelated issue. + +Fixes: cfab6dbd0ecf ("netfilter: flowtable: add tunnel match offload support") +Cc: wenxu +Signed-off-by: Will Mortensen +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + net/netfilter/nf_flow_table_offload.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c +index a6b654b028dd4..d1862782be450 100644 +--- a/net/netfilter/nf_flow_table_offload.c ++++ b/net/netfilter/nf_flow_table_offload.c +@@ -63,11 +63,11 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match, + sizeof(struct in6_addr)); + if (memcmp(&key->enc_ipv6.src, &in6addr_any, + sizeof(struct in6_addr))) +- memset(&key->enc_ipv6.src, 0xff, ++ memset(&mask->enc_ipv6.src, 0xff, + sizeof(struct in6_addr)); + if (memcmp(&key->enc_ipv6.dst, &in6addr_any, + sizeof(struct in6_addr))) +- memset(&key->enc_ipv6.dst, 0xff, ++ memset(&mask->enc_ipv6.dst, 0xff, + sizeof(struct in6_addr)); + enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS); + key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; +-- +2.33.0 + diff --git a/queue-5.10/netfilter-ipvs-fix-reuse-connection-if-rs-weight-is-.patch b/queue-5.10/netfilter-ipvs-fix-reuse-connection-if-rs-weight-is-.patch new file mode 100644 index 00000000000..61e2a51ce31 --- /dev/null +++ b/queue-5.10/netfilter-ipvs-fix-reuse-connection-if-rs-weight-is-.patch @@ -0,0 +1,78 @@ +From 18fed3cf5a6f28a2baba84d4fbae1f3df13743ed Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 4 Nov 2021 03:10:29 +0100 +Subject: netfilter: ipvs: Fix reuse connection if RS weight is 0 + +From: yangxingwu + +[ Upstream commit c95c07836fa4c1767ed11d8eca0769c652760e32 ] + +We are changing expire_nodest_conn to work even for reused connections when +conn_reuse_mode=0, just as what was done with commit dc7b3eb900aa ("ipvs: +Fix reuse connection if real server is dead"). + +For controlled and persistent connections, the new connection will get the +needed real server depending on the rules in ip_vs_check_template(). + +Fixes: d752c3645717 ("ipvs: allow rescheduling of new connections when port reuse is detected") +Co-developed-by: Chuanqi Liu +Signed-off-by: Chuanqi Liu +Signed-off-by: yangxingwu +Acked-by: Simon Horman +Acked-by: Julian Anastasov +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + Documentation/networking/ipvs-sysctl.rst | 3 +-- + net/netfilter/ipvs/ip_vs_core.c | 8 ++++---- + 2 files changed, 5 insertions(+), 6 deletions(-) + +diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst +index 2afccc63856ee..1cfbf1add2fc9 100644 +--- a/Documentation/networking/ipvs-sysctl.rst ++++ b/Documentation/networking/ipvs-sysctl.rst +@@ -37,8 +37,7 @@ conn_reuse_mode - INTEGER + + 0: disable any special handling on port reuse. The new + connection will be delivered to the same real server that was +- servicing the previous connection. This will effectively +- disable expire_nodest_conn. ++ servicing the previous connection. + + bit 1: enable rescheduling of new connections when it is safe. + That is, whenever expire_nodest_conn and for TCP sockets, when +diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c +index c0b8215ab3d47..3a76da58d88bb 100644 +--- a/net/netfilter/ipvs/ip_vs_core.c ++++ b/net/netfilter/ipvs/ip_vs_core.c +@@ -1976,7 +1976,6 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int + struct ip_vs_proto_data *pd; + struct ip_vs_conn *cp; + int ret, pkts; +- int conn_reuse_mode; + struct sock *sk; + + /* Already marked as IPVS request or reply? */ +@@ -2053,15 +2052,16 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int + cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, + ipvs, af, skb, &iph); + +- conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); +- if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { ++ if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) { ++ int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); + bool old_ct = false, resched = false; + + if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && + unlikely(!atomic_read(&cp->dest->weight))) { + resched = true; + old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); +- } else if (is_new_conn_expected(cp, conn_reuse_mode)) { ++ } else if (conn_reuse_mode && ++ is_new_conn_expected(cp, conn_reuse_mode)) { + old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); + if (!atomic_read(&cp->n_control)) { + resched = true; +-- +2.33.0 + diff --git a/queue-5.10/nfp-checking-parameter-process-for-rx-usecs-tx-usecs.patch b/queue-5.10/nfp-checking-parameter-process-for-rx-usecs-tx-usecs.patch new file mode 100644 index 00000000000..67d2a72ded2 --- /dev/null +++ b/queue-5.10/nfp-checking-parameter-process-for-rx-usecs-tx-usecs.patch @@ -0,0 +1,64 @@ +From 5e1e4314fef50de75d88ece44cf9716ff357275b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 19 Nov 2021 14:38:03 +0100 +Subject: nfp: checking parameter process for rx-usecs/tx-usecs is invalid + +From: Diana Wang + +[ Upstream commit 3bd6b2a838ba6a3b86d41b077f570b1b61174def ] + +Use nn->tlv_caps.me_freq_mhz instead of nn->me_freq_mhz to check whether +rx-usecs/tx-usecs is valid. + +This is because nn->tlv_caps.me_freq_mhz represents the clock_freq (MHz) of +the flow processing cores (FPC) on the NIC. While nn->me_freq_mhz is not +be set. + +Fixes: ce991ab6662a ("nfp: read ME frequency from vNIC ctrl memory") +Signed-off-by: Diana Wang +Signed-off-by: Simon Horman +Reviewed-by: Jakub Kicinski +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/netronome/nfp/nfp_net.h | 3 --- + drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 2 +- + 2 files changed, 1 insertion(+), 4 deletions(-) + +diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h +index df5b748be068c..cc2ce452000a3 100644 +--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h ++++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h +@@ -557,7 +557,6 @@ struct nfp_net_dp { + * @exn_name: Name for Exception interrupt + * @shared_handler: Handler for shared interrupts + * @shared_name: Name for shared interrupt +- * @me_freq_mhz: ME clock_freq (MHz) + * @reconfig_lock: Protects @reconfig_posted, @reconfig_timer_active, + * @reconfig_sync_present and HW reconfiguration request + * regs/machinery from async requests (sync must take +@@ -640,8 +639,6 @@ struct nfp_net { + irq_handler_t shared_handler; + char shared_name[IFNAMSIZ + 8]; + +- u32 me_freq_mhz; +- + bool link_up; + spinlock_t link_status_lock; + +diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +index c036a1d0f8de6..cd0c9623f7dd2 100644 +--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c ++++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +@@ -1347,7 +1347,7 @@ static int nfp_net_set_coalesce(struct net_device *netdev, + * ME timestamp ticks. There are 16 ME clock cycles for each timestamp + * count. + */ +- factor = nn->me_freq_mhz / 16; ++ factor = nn->tlv_caps.me_freq_mhz / 16; + + /* Each pair of (usecs, max_frames) fields specifies that interrupts + * should be coalesced until +-- +2.33.0 + diff --git a/queue-5.10/nfsv42-don-t-fail-clone-unless-the-op_clone-operatio.patch b/queue-5.10/nfsv42-don-t-fail-clone-unless-the-op_clone-operatio.patch new file mode 100644 index 00000000000..369ff355ad3 --- /dev/null +++ b/queue-5.10/nfsv42-don-t-fail-clone-unless-the-op_clone-operatio.patch @@ -0,0 +1,38 @@ +From aee36319a2cf5f2cf8faa584289693178f1b4197 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 16 Nov 2021 09:55:01 -0500 +Subject: NFSv42: Don't fail clone() unless the OP_CLONE operation failed + +From: Trond Myklebust + +[ Upstream commit d3c45824ad65aebf765fcf51366d317a29538820 ] + +The failure to retrieve post-op attributes has no bearing on whether or +not the clone operation itself was successful. We must therefore ignore +the return value of decode_getfattr() when looking at the success or +failure of nfs4_xdr_dec_clone(). + +Fixes: 36022770de6c ("nfs42: add CLONE xdr functions") +Signed-off-by: Trond Myklebust +Signed-off-by: Sasha Levin +--- + fs/nfs/nfs42xdr.c | 3 +-- + 1 file changed, 1 insertion(+), 2 deletions(-) + +diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c +index c078f88552695..f2248d9d4db51 100644 +--- a/fs/nfs/nfs42xdr.c ++++ b/fs/nfs/nfs42xdr.c +@@ -1396,8 +1396,7 @@ static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp, + status = decode_clone(xdr); + if (status) + goto out; +- status = decode_getfattr(xdr, res->dst_fattr, res->server); +- ++ decode_getfattr(xdr, res->dst_fattr, res->server); + out: + res->rpc_status = status; + return status; +-- +2.33.0 + diff --git a/queue-5.10/nvmet-tcp-fix-incomplete-data-digest-send.patch b/queue-5.10/nvmet-tcp-fix-incomplete-data-digest-send.patch new file mode 100644 index 00000000000..98e8917b5fb --- /dev/null +++ b/queue-5.10/nvmet-tcp-fix-incomplete-data-digest-send.patch @@ -0,0 +1,53 @@ +From 4ed72372357156a7094c4d2cc71c6b7f7944df3f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 22 Nov 2021 15:38:41 +0530 +Subject: nvmet-tcp: fix incomplete data digest send + +From: Varun Prakash + +[ Upstream commit 102110efdff6beedece6ab9b51664c32ac01e2db ] + +Current nvmet_try_send_ddgst() code does not check whether +all data digest bytes are transmitted, fix this by returning +-EAGAIN if all data digest bytes are not transmitted. + +Fixes: 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver") +Signed-off-by: Varun Prakash +Reviewed-by: Sagi Grimberg +Signed-off-by: Christoph Hellwig +Signed-off-by: Sasha Levin +--- + drivers/nvme/target/tcp.c | 7 ++++++- + 1 file changed, 6 insertions(+), 1 deletion(-) + +diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c +index 1251fd6e92780..96b67a70cbbbd 100644 +--- a/drivers/nvme/target/tcp.c ++++ b/drivers/nvme/target/tcp.c +@@ -688,10 +688,11 @@ static int nvmet_try_send_r2t(struct nvmet_tcp_cmd *cmd, bool last_in_batch) + static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch) + { + struct nvmet_tcp_queue *queue = cmd->queue; ++ int left = NVME_TCP_DIGEST_LENGTH - cmd->offset; + struct msghdr msg = { .msg_flags = MSG_DONTWAIT }; + struct kvec iov = { + .iov_base = (u8 *)&cmd->exp_ddgst + cmd->offset, +- .iov_len = NVME_TCP_DIGEST_LENGTH - cmd->offset ++ .iov_len = left + }; + int ret; + +@@ -705,6 +706,10 @@ static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch) + return ret; + + cmd->offset += ret; ++ left -= ret; ++ ++ if (left) ++ return -EAGAIN; + + if (queue->nvme_sq.sqhd_disabled) { + cmd->queue->snd_cmd = NULL; +-- +2.33.0 + diff --git a/queue-5.10/nvmet-use-iocb_nowait-only-if-the-filesystem-support.patch b/queue-5.10/nvmet-use-iocb_nowait-only-if-the-filesystem-support.patch new file mode 100644 index 00000000000..efb645c943b --- /dev/null +++ b/queue-5.10/nvmet-use-iocb_nowait-only-if-the-filesystem-support.patch @@ -0,0 +1,46 @@ +From 4fb51dd1c88b452068de06b0d930997383567e4b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 22 Nov 2021 11:08:27 +0100 +Subject: nvmet: use IOCB_NOWAIT only if the filesystem supports it + +From: Maurizio Lombardi + +[ Upstream commit c024b226a417c4eb9353ff500b1c823165d4d508 ] + +Submit I/O requests with the IOCB_NOWAIT flag set only if +the underlying filesystem supports it. + +Fixes: 50a909db36f2 ("nvmet: use IOCB_NOWAIT for file-ns buffered I/O") +Signed-off-by: Maurizio Lombardi +Reviewed-by: Chaitanya Kulkarni +Signed-off-by: Christoph Hellwig +Signed-off-by: Sasha Levin +--- + drivers/nvme/target/io-cmd-file.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c +index b575997244482..c81690b2a681b 100644 +--- a/drivers/nvme/target/io-cmd-file.c ++++ b/drivers/nvme/target/io-cmd-file.c +@@ -8,6 +8,7 @@ + #include + #include + #include ++#include + #include "nvmet.h" + + #define NVMET_MAX_MPOOL_BVEC 16 +@@ -266,7 +267,8 @@ static void nvmet_file_execute_rw(struct nvmet_req *req) + + if (req->ns->buffered_io) { + if (likely(!req->f.mpool_alloc) && +- nvmet_file_execute_io(req, IOCB_NOWAIT)) ++ (req->ns->file->f_mode & FMODE_NOWAIT) && ++ nvmet_file_execute_io(req, IOCB_NOWAIT)) + return; + nvmet_file_submit_buffered_io(req); + } else +-- +2.33.0 + diff --git a/queue-5.10/pm-hibernate-use-correct-mode-for-swsusp_close.patch b/queue-5.10/pm-hibernate-use-correct-mode-for-swsusp_close.patch new file mode 100644 index 00000000000..718bbf55b03 --- /dev/null +++ b/queue-5.10/pm-hibernate-use-correct-mode-for-swsusp_close.patch @@ -0,0 +1,62 @@ +From 3b44cdd0a249894c11aed28fd8db65975b893966 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 23 Nov 2021 20:18:43 +0100 +Subject: PM: hibernate: use correct mode for swsusp_close() + +From: Thomas Zeitlhofer + +[ Upstream commit cefcf24b4d351daf70ecd945324e200d3736821e ] + +Commit 39fbef4b0f77 ("PM: hibernate: Get block device exclusively in +swsusp_check()") changed the opening mode of the block device to +(FMODE_READ | FMODE_EXCL). + +In the corresponding calls to swsusp_close(), the mode is still just +FMODE_READ which triggers the warning in blkdev_flush_mapping() on +resume from hibernate. + +So, use the mode (FMODE_READ | FMODE_EXCL) also when closing the +device. + +Fixes: 39fbef4b0f77 ("PM: hibernate: Get block device exclusively in swsusp_check()") +Signed-off-by: Thomas Zeitlhofer +Signed-off-by: Rafael J. Wysocki +Signed-off-by: Sasha Levin +--- + kernel/power/hibernate.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c +index 2fc7d509a34fc..bf640fd6142a0 100644 +--- a/kernel/power/hibernate.c ++++ b/kernel/power/hibernate.c +@@ -688,7 +688,7 @@ static int load_image_and_restore(void) + goto Unlock; + + error = swsusp_read(&flags); +- swsusp_close(FMODE_READ); ++ swsusp_close(FMODE_READ | FMODE_EXCL); + if (!error) + error = hibernation_restore(flags & SF_PLATFORM_MODE); + +@@ -978,7 +978,7 @@ static int software_resume(void) + /* The snapshot device should not be opened while we're running */ + if (!hibernate_acquire()) { + error = -EBUSY; +- swsusp_close(FMODE_READ); ++ swsusp_close(FMODE_READ | FMODE_EXCL); + goto Unlock; + } + +@@ -1013,7 +1013,7 @@ static int software_resume(void) + pm_pr_dbg("Hibernation image not present or could not be loaded.\n"); + return error; + Close_Finish: +- swsusp_close(FMODE_READ); ++ swsusp_close(FMODE_READ | FMODE_EXCL); + goto Finish; + } + +-- +2.33.0 + diff --git a/queue-5.10/scsi-core-sysfs-fix-setting-device-state-to-sdev_run.patch b/queue-5.10/scsi-core-sysfs-fix-setting-device-state-to-sdev_run.patch new file mode 100644 index 00000000000..52936f7803c --- /dev/null +++ b/queue-5.10/scsi-core-sysfs-fix-setting-device-state-to-sdev_run.patch @@ -0,0 +1,41 @@ +From 0937c6ed8c02c5dc2956221a50a7a6979e9b8d76 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sat, 20 Nov 2021 10:49:17 -0600 +Subject: scsi: core: sysfs: Fix setting device state to SDEV_RUNNING + +From: Mike Christie + +[ Upstream commit eb97545d6264b341b06ba7603f52ff6c0b2af6ea ] + +This fixes an issue added in commit 4edd8cd4e86d ("scsi: core: sysfs: Fix +hang when device state is set via sysfs") where if userspace is requesting +to set the device state to SDEV_RUNNING when the state is already +SDEV_RUNNING, we return -EINVAL instead of count. The commmit above set ret +to count for this case, when it should have set it to 0. + +Link: https://lore.kernel.org/r/20211120164917.4924-1-michael.christie@oracle.com +Fixes: 4edd8cd4e86d ("scsi: core: sysfs: Fix hang when device state is set via sysfs") +Reviewed-by: Lee Duncan +Signed-off-by: Mike Christie +Signed-off-by: Martin K. Petersen +Signed-off-by: Sasha Levin +--- + drivers/scsi/scsi_sysfs.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c +index 8de67679a8782..42db9c52208e6 100644 +--- a/drivers/scsi/scsi_sysfs.c ++++ b/drivers/scsi/scsi_sysfs.c +@@ -816,7 +816,7 @@ store_state_field(struct device *dev, struct device_attribute *attr, + + mutex_lock(&sdev->state_mutex); + if (sdev->sdev_state == SDEV_RUNNING && state == SDEV_RUNNING) { +- ret = count; ++ ret = 0; + } else { + ret = scsi_device_set_state(sdev, state); + if (ret == 0 && state == SDEV_RUNNING) +-- +2.33.0 + diff --git a/queue-5.10/scsi-mpt3sas-fix-kernel-panic-during-drive-powercycl.patch b/queue-5.10/scsi-mpt3sas-fix-kernel-panic-during-drive-powercycl.patch new file mode 100644 index 00000000000..dc59d3c2526 --- /dev/null +++ b/queue-5.10/scsi-mpt3sas-fix-kernel-panic-during-drive-powercycl.patch @@ -0,0 +1,42 @@ +From 165d3f6e710b7fb5185ca4d56f86c59434dc8b84 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 17 Nov 2021 16:19:09 +0530 +Subject: scsi: mpt3sas: Fix kernel panic during drive powercycle test + +From: Sreekanth Reddy + +[ Upstream commit 0ee4ba13e09c9d9c1cb6abb59da8295d9952328b ] + +While looping over shost's sdev list it is possible that one +of the drives is getting removed and its sas_target object is +freed but its sdev object remains intact. + +Consequently, a kernel panic can occur while the driver is trying to access +the sas_address field of sas_target object without also checking the +sas_target object for NULL. + +Link: https://lore.kernel.org/r/20211117104909.2069-1-sreekanth.reddy@broadcom.com +Fixes: f92363d12359 ("[SCSI] mpt3sas: add new driver supporting 12GB SAS") +Signed-off-by: Sreekanth Reddy +Signed-off-by: Martin K. Petersen +Signed-off-by: Sasha Levin +--- + drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c +index 31c384108bc9c..8418b59b3743b 100644 +--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c ++++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c +@@ -3675,7 +3675,7 @@ _scsih_ublock_io_device(struct MPT3SAS_ADAPTER *ioc, u64 sas_address) + + shost_for_each_device(sdev, ioc->shost) { + sas_device_priv_data = sdev->hostdata; +- if (!sas_device_priv_data) ++ if (!sas_device_priv_data || !sas_device_priv_data->sas_target) + continue; + if (sas_device_priv_data->sas_target->sas_address + != sas_address) +-- +2.33.0 + diff --git a/queue-5.10/scsi-scsi_debug-zero-clear-zones-at-reset-write-poin.patch b/queue-5.10/scsi-scsi_debug-zero-clear-zones-at-reset-write-poin.patch new file mode 100644 index 00000000000..8d29921fa63 --- /dev/null +++ b/queue-5.10/scsi-scsi_debug-zero-clear-zones-at-reset-write-poin.patch @@ -0,0 +1,54 @@ +From d094da7150dd83c72796427e7d62550aaabb16aa Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 22 Nov 2021 15:12:23 +0900 +Subject: scsi: scsi_debug: Zero clear zones at reset write pointer + +From: Shin'ichiro Kawasaki + +[ Upstream commit 2d62253eb1b60f4ce8b39125eee282739b519297 ] + +When a reset is requested the position of the write pointer is updated but +the data in the corresponding zone is not cleared. Instead scsi_debug +returns any data written before the write pointer was reset. This is an +error and prevents using scsi_debug for stale page cache testing of the +BLKRESETZONE ioctl. + +Zero written data in the zone when resetting the write pointer. + +Link: https://lore.kernel.org/r/20211122061223.298890-1-shinichiro.kawasaki@wdc.com +Fixes: f0d1cf9378bd ("scsi: scsi_debug: Add ZBC zone commands") +Reviewed-by: Damien Le Moal +Acked-by: Douglas Gilbert +Signed-off-by: Shin'ichiro Kawasaki +Signed-off-by: Martin K. Petersen +Signed-off-by: Sasha Levin +--- + drivers/scsi/scsi_debug.c | 5 +++++ + 1 file changed, 5 insertions(+) + +diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c +index 3fc7c2a31c191..1a3f5adc68849 100644 +--- a/drivers/scsi/scsi_debug.c ++++ b/drivers/scsi/scsi_debug.c +@@ -4628,6 +4628,7 @@ static void zbc_rwp_zone(struct sdebug_dev_info *devip, + struct sdeb_zone_state *zsp) + { + enum sdebug_z_cond zc; ++ struct sdeb_store_info *sip = devip2sip(devip, false); + + if (zbc_zone_is_conv(zsp)) + return; +@@ -4639,6 +4640,10 @@ static void zbc_rwp_zone(struct sdebug_dev_info *devip, + if (zsp->z_cond == ZC4_CLOSED) + devip->nr_closed--; + ++ if (zsp->z_wp > zsp->z_start) ++ memset(sip->storep + zsp->z_start * sdebug_sector_size, 0, ++ (zsp->z_wp - zsp->z_start) * sdebug_sector_size); ++ + zsp->z_non_seq_resource = false; + zsp->z_wp = zsp->z_start; + zsp->z_cond = ZC1_EMPTY; +-- +2.33.0 + diff --git a/queue-5.10/series b/queue-5.10/series index fed68c19fae..f4902b977fe 100644 --- a/queue-5.10/series +++ b/queue-5.10/series @@ -38,3 +38,64 @@ pci-aardvark-implement-re-issuing-config-requests-on-crs-response.patch pci-aardvark-simplify-initialization-of-rootcap-on-virtual-bridge.patch pci-aardvark-fix-link-training.patch proc-vmcore-fix-clearing-user-buffer-by-properly-using-clear_user.patch +netfilter-ctnetlink-fix-filtering-with-cta_tuple_rep.patch +netfilter-ctnetlink-do-not-erase-error-code-with-ein.patch +netfilter-ipvs-fix-reuse-connection-if-rs-weight-is-.patch +netfilter-flowtable-fix-ipv6-tunnel-addr-match.patch +arm-dts-bcm5301x-fix-i2c-controller-interrupt.patch +arm-dts-bcm5301x-add-interrupt-properties-to-gpio-no.patch +arm-dts-bcm2711-fix-pcie-interrupts.patch +asoc-qdsp6-q6routing-conditionally-reset-frontend-mi.patch +asoc-qdsp6-q6asm-fix-q6asm_dai_prepare-error-handlin.patch +asoc-topology-add-missing-rwsem-around-snd_ctl_remov.patch +asoc-codecs-wcd934x-return-error-code-correctly-from.patch +net-ieee802154-handle-iftypes-as-u32.patch +firmware-arm_scmi-pm-propagate-return-value-to-calle.patch +nfsv42-don-t-fail-clone-unless-the-op_clone-operatio.patch +arm-socfpga-fix-crash-with-config_fortiry_source.patch +drm-nouveau-acr-fix-a-couple-null-vs-is_err-checks.patch +scsi-mpt3sas-fix-kernel-panic-during-drive-powercycl.patch +drm-vc4-fix-error-code-in-vc4_create_object.patch +net-marvell-prestera-fix-double-free-issue-on-err-pa.patch +iavf-prevent-changing-static-itr-values-if-adaptive-.patch +alsa-intel-dsp-config-add-quirk-for-jsl-devices-base.patch +mptcp-fix-delack-timer.patch +firmware-smccc-fix-check-for-arch_soc_id-not-impleme.patch +ipv6-fix-typos-in-__ip6_finish_output.patch +nfp-checking-parameter-process-for-rx-usecs-tx-usecs.patch +net-stmmac-fix-system-hang-caused-by-eee_ctrl_timer-.patch +net-stmmac-retain-ptp-clock-time-during-siocshwtstam.patch +net-ipv6-add-fib6_nh_release_dsts-stub.patch +net-nexthop-release-ipv6-per-cpu-dsts-when-replacing.patch +ice-fix-vsi-txq_map-sizing.patch +ice-avoid-bpf_prog-refcount-underflow.patch +scsi-core-sysfs-fix-setting-device-state-to-sdev_run.patch +scsi-scsi_debug-zero-clear-zones-at-reset-write-poin.patch +erofs-fix-deadlock-when-shrink-erofs-slab.patch +net-smc-ensure-the-active-closing-peer-first-closes-.patch +mlxsw-verify-the-accessed-index-doesn-t-exceed-the-a.patch +mlxsw-spectrum-protect-driver-from-buggy-firmware.patch +net-marvell-mvpp2-increase-mtu-limit-when-xdp-enable.patch +nvmet-tcp-fix-incomplete-data-digest-send.patch +net-ncsi-add-payload-to-be-32-bit-aligned-to-fix-dro.patch +pm-hibernate-use-correct-mode-for-swsusp_close.patch +drm-amd-display-set-plane-update-flags-for-all-plane.patch +tcp_cubic-fix-spurious-hystart-ack-train-detections-.patch +lan743x-fix-deadlock-in-lan743x_phy_link_status_chan.patch +net-phylink-force-link-down-and-retrigger-resolve-on.patch +net-phylink-force-retrigger-in-case-of-latched-link-.patch +net-smc-fix-null-pointer-dereferencing-in-smc_vlan_b.patch +net-smc-fix-loop-in-smc_listen.patch +nvmet-use-iocb_nowait-only-if-the-filesystem-support.patch +igb-fix-netpoll-exit-with-traffic.patch +mips-loongson64-fix-ftlb-configuration.patch +mips-use-3-level-pgtable-for-64kb-page-size-on-mips_.patch +tls-splice_read-fix-record-type-check.patch +tls-fix-replacing-proto_ops.patch +net-sched-sch_ets-don-t-peek-at-classes-beyond-nband.patch +net-vlan-fix-underflow-for-the-real_dev-refcnt.patch +net-smc-don-t-call-clcsock-shutdown-twice-when-smc-s.patch +net-hns3-fix-vf-rss-failed-problem-after-pf-enable-m.patch +net-mscc-ocelot-don-t-downgrade-timestamping-rx-filt.patch +net-mscc-ocelot-correctly-report-the-timestamping-rx.patch +tcp-correctly-handle-increased-zerocopy-args-struct-.patch diff --git a/queue-5.10/tcp-correctly-handle-increased-zerocopy-args-struct-.patch b/queue-5.10/tcp-correctly-handle-increased-zerocopy-args-struct-.patch new file mode 100644 index 00000000000..9331164b3dc --- /dev/null +++ b/queue-5.10/tcp-correctly-handle-increased-zerocopy-args-struct-.patch @@ -0,0 +1,51 @@ +From 8d216c01c038722d7175cfa55fe1adc4f7782591 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 10 Dec 2020 11:16:03 -0800 +Subject: tcp: correctly handle increased zerocopy args struct size + +From: Arjun Roy + +[ Upstream commit e0fecb289ad3fd2245cdc50bf450b97fcca39884 ] + +A prior patch increased the size of struct tcp_zerocopy_receive +but did not update do_tcp_getsockopt() handling to properly account +for this. + +This patch simply reintroduces content erroneously cut from the +referenced prior patch that handles the new struct size. + +Fixes: 18fb76ed5386 ("net-zerocopy: Copy straggler unaligned data for TCP Rx. zerocopy.") +Signed-off-by: Arjun Roy +Signed-off-by: Eric Dumazet +Signed-off-by: Soheil Hassas Yeganeh +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ipv4/tcp.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c +index bb16c88f58a3c..63c81af41b43e 100644 +--- a/net/ipv4/tcp.c ++++ b/net/ipv4/tcp.c +@@ -3931,7 +3931,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, + } + #ifdef CONFIG_MMU + case TCP_ZEROCOPY_RECEIVE: { +- struct tcp_zerocopy_receive zc; ++ struct tcp_zerocopy_receive zc = {}; + int err; + + if (get_user(len, optlen)) +@@ -3949,7 +3949,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, + lock_sock(sk); + err = tcp_zerocopy_receive(sk, &zc); + release_sock(sk); +- if (len == sizeof(zc)) ++ if (len >= offsetofend(struct tcp_zerocopy_receive, err)) + goto zerocopy_rcv_sk_err; + switch (len) { + case offsetofend(struct tcp_zerocopy_receive, err): +-- +2.33.0 + diff --git a/queue-5.10/tcp_cubic-fix-spurious-hystart-ack-train-detections-.patch b/queue-5.10/tcp_cubic-fix-spurious-hystart-ack-train-detections-.patch new file mode 100644 index 00000000000..779f2057d42 --- /dev/null +++ b/queue-5.10/tcp_cubic-fix-spurious-hystart-ack-train-detections-.patch @@ -0,0 +1,88 @@ +From f570b3189c61b128383c5dda007cece674082bbc Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 23 Nov 2021 12:25:35 -0800 +Subject: tcp_cubic: fix spurious Hystart ACK train detections for + not-cwnd-limited flows + +From: Eric Dumazet + +[ Upstream commit 4e1fddc98d2585ddd4792b5e44433dcee7ece001 ] + +While testing BIG TCP patch series, I was expecting that TCP_RR workloads +with 80KB requests/answers would send one 80KB TSO packet, +then being received as a single GRO packet. + +It turns out this was not happening, and the root cause was that +cubic Hystart ACK train was triggering after a few (2 or 3) rounds of RPC. + +Hystart was wrongly setting CWND/SSTHRESH to 30, while my RPC +needed a budget of ~20 segments. + +Ideally these TCP_RR flows should not exit slow start. + +Cubic Hystart should reset itself at each round, instead of assuming +every TCP flow is a bulk one. + +Note that even after this patch, Hystart can still trigger, depending +on scheduling artifacts, but at a higher CWND/SSTHRESH threshold, +keeping optimal TSO packet sizes. + +Tested: + +ip link set dev eth0 gro_ipv6_max_size 131072 gso_ipv6_max_size 131072 +nstat -n; netperf -H ... -t TCP_RR -l 5 -- -r 80000,80000 -K cubic; nstat|egrep "Ip6InReceives|Hystart|Ip6OutRequests" + +Before: + + 8605 +Ip6InReceives 87541 0.0 +Ip6OutRequests 129496 0.0 +TcpExtTCPHystartTrainDetect 1 0.0 +TcpExtTCPHystartTrainCwnd 30 0.0 + +After: + + 8760 +Ip6InReceives 88514 0.0 +Ip6OutRequests 87975 0.0 + +Fixes: ae27e98a5152 ("[TCP] CUBIC v2.3") +Co-developed-by: Neal Cardwell +Signed-off-by: Neal Cardwell +Signed-off-by: Eric Dumazet +Cc: Stephen Hemminger +Cc: Yuchung Cheng +Cc: Soheil Hassas Yeganeh +Link: https://lore.kernel.org/r/20211123202535.1843771-1-eric.dumazet@gmail.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/ipv4/tcp_cubic.c | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c +index c7bf5b26bf0c2..fffa011a007d4 100644 +--- a/net/ipv4/tcp_cubic.c ++++ b/net/ipv4/tcp_cubic.c +@@ -337,8 +337,6 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) + return; + + if (tcp_in_slow_start(tp)) { +- if (hystart && after(ack, ca->end_seq)) +- bictcp_hystart_reset(sk); + acked = tcp_slow_start(tp, acked); + if (!acked) + return; +@@ -398,6 +396,9 @@ static void hystart_update(struct sock *sk, u32 delay) + struct bictcp *ca = inet_csk_ca(sk); + u32 threshold; + ++ if (after(tp->snd_una, ca->end_seq)) ++ bictcp_hystart_reset(sk); ++ + if (hystart_detect & HYSTART_ACK_TRAIN) { + u32 now = bictcp_clock_us(sk); + +-- +2.33.0 + diff --git a/queue-5.10/tls-fix-replacing-proto_ops.patch b/queue-5.10/tls-fix-replacing-proto_ops.patch new file mode 100644 index 00000000000..bf59cf77083 --- /dev/null +++ b/queue-5.10/tls-fix-replacing-proto_ops.patch @@ -0,0 +1,132 @@ +From f7e66b03ea39f33ec32ef01b3ed0cefb52445750 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 24 Nov 2021 15:25:56 -0800 +Subject: tls: fix replacing proto_ops + +From: Jakub Kicinski + +[ Upstream commit f3911f73f51d1534f4db70b516cc1fcb6be05bae ] + +We replace proto_ops whenever TLS is configured for RX. But our +replacement also overrides sendpage_locked, which will crash +unless TX is also configured. Similarly we plug both of those +in for TLS_HW (NIC crypto offload) even tho TLS_HW has a completely +different implementation for TX. + +Last but not least we always plug in something based on inet_stream_ops +even though a few of the callbacks differ for IPv6 (getname, release, +bind). + +Use a callback building method similar to what we do for struct proto. + +Fixes: c46234ebb4d1 ("tls: RX path for ktls") +Fixes: d4ffb02dee2f ("net/tls: enable sk_msg redirect to tls socket egress") +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/tls/tls_main.c | 47 +++++++++++++++++++++++++++++++++++++++------- + 1 file changed, 40 insertions(+), 7 deletions(-) + +diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c +index 32a51b20509c9..58d22d6b86ae6 100644 +--- a/net/tls/tls_main.c ++++ b/net/tls/tls_main.c +@@ -61,7 +61,7 @@ static DEFINE_MUTEX(tcpv6_prot_mutex); + static const struct proto *saved_tcpv4_prot; + static DEFINE_MUTEX(tcpv4_prot_mutex); + static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; +-static struct proto_ops tls_sw_proto_ops; ++static struct proto_ops tls_proto_ops[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; + static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], + const struct proto *base); + +@@ -71,6 +71,8 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx) + + WRITE_ONCE(sk->sk_prot, + &tls_prots[ip_ver][ctx->tx_conf][ctx->rx_conf]); ++ WRITE_ONCE(sk->sk_socket->ops, ++ &tls_proto_ops[ip_ver][ctx->tx_conf][ctx->rx_conf]); + } + + int wait_on_pending_writer(struct sock *sk, long *timeo) +@@ -578,8 +580,6 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, + if (tx) { + ctx->sk_write_space = sk->sk_write_space; + sk->sk_write_space = tls_write_space; +- } else { +- sk->sk_socket->ops = &tls_sw_proto_ops; + } + goto out; + +@@ -637,6 +637,39 @@ struct tls_context *tls_ctx_create(struct sock *sk) + return ctx; + } + ++static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG], ++ const struct proto_ops *base) ++{ ++ ops[TLS_BASE][TLS_BASE] = *base; ++ ++ ops[TLS_SW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; ++ ops[TLS_SW ][TLS_BASE].sendpage_locked = tls_sw_sendpage_locked; ++ ++ ops[TLS_BASE][TLS_SW ] = ops[TLS_BASE][TLS_BASE]; ++ ops[TLS_BASE][TLS_SW ].splice_read = tls_sw_splice_read; ++ ++ ops[TLS_SW ][TLS_SW ] = ops[TLS_SW ][TLS_BASE]; ++ ops[TLS_SW ][TLS_SW ].splice_read = tls_sw_splice_read; ++ ++#ifdef CONFIG_TLS_DEVICE ++ ops[TLS_HW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; ++ ops[TLS_HW ][TLS_BASE].sendpage_locked = NULL; ++ ++ ops[TLS_HW ][TLS_SW ] = ops[TLS_BASE][TLS_SW ]; ++ ops[TLS_HW ][TLS_SW ].sendpage_locked = NULL; ++ ++ ops[TLS_BASE][TLS_HW ] = ops[TLS_BASE][TLS_SW ]; ++ ++ ops[TLS_SW ][TLS_HW ] = ops[TLS_SW ][TLS_SW ]; ++ ++ ops[TLS_HW ][TLS_HW ] = ops[TLS_HW ][TLS_SW ]; ++ ops[TLS_HW ][TLS_HW ].sendpage_locked = NULL; ++#endif ++#ifdef CONFIG_TLS_TOE ++ ops[TLS_HW_RECORD][TLS_HW_RECORD] = *base; ++#endif ++} ++ + static void tls_build_proto(struct sock *sk) + { + int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; +@@ -648,6 +681,8 @@ static void tls_build_proto(struct sock *sk) + mutex_lock(&tcpv6_prot_mutex); + if (likely(prot != saved_tcpv6_prot)) { + build_protos(tls_prots[TLSV6], prot); ++ build_proto_ops(tls_proto_ops[TLSV6], ++ sk->sk_socket->ops); + smp_store_release(&saved_tcpv6_prot, prot); + } + mutex_unlock(&tcpv6_prot_mutex); +@@ -658,6 +693,8 @@ static void tls_build_proto(struct sock *sk) + mutex_lock(&tcpv4_prot_mutex); + if (likely(prot != saved_tcpv4_prot)) { + build_protos(tls_prots[TLSV4], prot); ++ build_proto_ops(tls_proto_ops[TLSV4], ++ sk->sk_socket->ops); + smp_store_release(&saved_tcpv4_prot, prot); + } + mutex_unlock(&tcpv4_prot_mutex); +@@ -868,10 +905,6 @@ static int __init tls_register(void) + if (err) + return err; + +- tls_sw_proto_ops = inet_stream_ops; +- tls_sw_proto_ops.splice_read = tls_sw_splice_read; +- tls_sw_proto_ops.sendpage_locked = tls_sw_sendpage_locked; +- + tls_device_init(); + tcp_register_ulp(&tcp_tls_ulp_ops); + +-- +2.33.0 + diff --git a/queue-5.10/tls-splice_read-fix-record-type-check.patch b/queue-5.10/tls-splice_read-fix-record-type-check.patch new file mode 100644 index 00000000000..a8653159190 --- /dev/null +++ b/queue-5.10/tls-splice_read-fix-record-type-check.patch @@ -0,0 +1,68 @@ +From e1daaf15e6b17de413030ca0aeefab746a41ba82 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 24 Nov 2021 15:25:52 -0800 +Subject: tls: splice_read: fix record type check + +From: Jakub Kicinski + +[ Upstream commit 520493f66f6822551aef2879cd40207074fe6980 ] + +We don't support splicing control records. TLS 1.3 changes moved +the record type check into the decrypt if(). The skb may already +be decrypted and still be an alert. + +Note that decrypt_skb_update() is idempotent and updates ctx->decrypted +so the if() is pointless. + +Reorder the check for decryption errors with the content type check +while touching them. This part is not really a bug, because if +decryption failed in TLS 1.3 content type will be DATA, and for +TLS 1.2 it will be correct. Nevertheless its strange to touch output +before checking if the function has failed. + +Fixes: fedf201e1296 ("net: tls: Refactor control message handling on recv") +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/tls/tls_sw.c | 23 ++++++++++------------- + 1 file changed, 10 insertions(+), 13 deletions(-) + +diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c +index 14cce61160a58..122d5daed8b61 100644 +--- a/net/tls/tls_sw.c ++++ b/net/tls/tls_sw.c +@@ -2007,21 +2007,18 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, + if (!skb) + goto splice_read_end; + +- if (!ctx->decrypted) { +- err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); +- +- /* splice does not support reading control messages */ +- if (ctx->control != TLS_RECORD_TYPE_DATA) { +- err = -EINVAL; +- goto splice_read_end; +- } ++ err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); ++ if (err < 0) { ++ tls_err_abort(sk, -EBADMSG); ++ goto splice_read_end; ++ } + +- if (err < 0) { +- tls_err_abort(sk, -EBADMSG); +- goto splice_read_end; +- } +- ctx->decrypted = 1; ++ /* splice does not support reading control messages */ ++ if (ctx->control != TLS_RECORD_TYPE_DATA) { ++ err = -EINVAL; ++ goto splice_read_end; + } ++ + rxm = strp_msg(skb); + + chunk = min_t(unsigned int, rxm->full_len, len); +-- +2.33.0 +