From: Sasha Levin Date: Sun, 30 Jan 2022 03:40:47 +0000 (-0500) Subject: Fixes for 5.10 X-Git-Tag: v5.4.176~70 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=58ee0cfd0b3f88921684cc98847eb4f675c09172;p=thirdparty%2Fkernel%2Fstable-queue.git Fixes for 5.10 Signed-off-by: Sasha Levin --- diff --git a/queue-5.10/arm-9170-1-fix-panic-when-kasan-and-kprobe-are-enabl.patch-30400 b/queue-5.10/arm-9170-1-fix-panic-when-kasan-and-kprobe-are-enabl.patch-30400 new file mode 100644 index 00000000000..bb6cd24cc4f --- /dev/null +++ b/queue-5.10/arm-9170-1-fix-panic-when-kasan-and-kprobe-are-enabl.patch-30400 @@ -0,0 +1,119 @@ +From 39bc21f81ebc63b0fc01a81e9a6d627f6c775470 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 15 Dec 2021 10:08:23 +0100 +Subject: ARM: 9170/1: fix panic when kasan and kprobe are enabled + +From: sparkhuang + +[ Upstream commit 8b59b0a53c840921b625378f137e88adfa87647e ] + +arm32 uses software to simulate the instruction replaced +by kprobe. some instructions may be simulated by constructing +assembly functions. therefore, before executing instruction +simulation, it is necessary to construct assembly function +execution environment in C language through binding registers. +after kasan is enabled, the register binding relationship will +be destroyed, resulting in instruction simulation errors and +causing kernel panic. + +the kprobe emulate instruction function is distributed in three +files: actions-common.c actions-arm.c actions-thumb.c, so disable +KASAN when compiling these files. + +for example, use kprobe insert on cap_capable+20 after kasan +enabled, the cap_capable assembly code is as follows: +: +e92d47f0 push {r4, r5, r6, r7, r8, r9, sl, lr} +e1a05000 mov r5, r0 +e280006c add r0, r0, #108 ; 0x6c +e1a04001 mov r4, r1 +e1a06002 mov r6, r2 +e59fa090 ldr sl, [pc, #144] ; +ebfc7bf8 bl c03aa4b4 <__asan_load4> +e595706c ldr r7, [r5, #108] ; 0x6c +e2859014 add r9, r5, #20 +...... +The emulate_ldr assembly code after enabling kasan is as follows: +c06f1384 : +e92d47f0 push {r4, r5, r6, r7, r8, r9, sl, lr} +e282803c add r8, r2, #60 ; 0x3c +e1a05000 mov r5, r0 +e7e37855 ubfx r7, r5, #16, #4 +e1a00008 mov r0, r8 +e1a09001 mov r9, r1 +e1a04002 mov r4, r2 +ebf35462 bl c03c6530 <__asan_load4> +e357000f cmp r7, #15 +e7e36655 ubfx r6, r5, #12, #4 +e205a00f and sl, r5, #15 +0a000001 beq c06f13bc +e0840107 add r0, r4, r7, lsl #2 +ebf3545c bl c03c6530 <__asan_load4> +e084010a add r0, r4, sl, lsl #2 +ebf3545a bl c03c6530 <__asan_load4> +e2890010 add r0, r9, #16 +ebf35458 bl c03c6530 <__asan_load4> +e5990010 ldr r0, [r9, #16] +e12fff30 blx r0 +e356000f cm r6, #15 +1a000014 bne c06f1430 +e1a06000 mov r6, r0 +e2840040 add r0, r4, #64 ; 0x40 +...... + +when running in emulate_ldr to simulate the ldr instruction, panic +occurred, and the log is as follows: +Unable to handle kernel NULL pointer dereference at virtual address +00000090 +pgd = ecb46400 +[00000090] *pgd=2e0fa003, *pmd=00000000 +Internal error: Oops: 206 [#1] SMP ARM +PC is at cap_capable+0x14/0xb0 +LR is at emulate_ldr+0x50/0xc0 +psr: 600d0293 sp : ecd63af8 ip : 00000004 fp : c0a7c30c +r10: 00000000 r9 : c30897f4 r8 : ecd63cd4 +r7 : 0000000f r6 : 0000000a r5 : e59fa090 r4 : ecd63c98 +r3 : c06ae294 r2 : 00000000 r1 : b7611300 r0 : bf4ec008 +Flags: nZCv IRQs off FIQs on Mode SVC_32 ISA ARM Segment user +Control: 32c5387d Table: 2d546400 DAC: 55555555 +Process bash (pid: 1643, stack limit = 0xecd60190) +(cap_capable) from (kprobe_handler+0x218/0x340) +(kprobe_handler) from (kprobe_trap_handler+0x24/0x48) +(kprobe_trap_handler) from (do_undefinstr+0x13c/0x364) +(do_undefinstr) from (__und_svc_finish+0x0/0x30) +(__und_svc_finish) from (cap_capable+0x18/0xb0) +(cap_capable) from (cap_vm_enough_memory+0x38/0x48) +(cap_vm_enough_memory) from +(security_vm_enough_memory_mm+0x48/0x6c) +(security_vm_enough_memory_mm) from +(copy_process.constprop.5+0x16b4/0x25c8) +(copy_process.constprop.5) from (_do_fork+0xe8/0x55c) +(_do_fork) from (SyS_clone+0x1c/0x24) +(SyS_clone) from (__sys_trace_return+0x0/0x10) +Code: 0050a0e1 6c0080e2 0140a0e1 0260a0e1 (f801f0e7) + +Fixes: 35aa1df43283 ("ARM kprobes: instruction single-stepping support") +Fixes: 421015713b30 ("ARM: 9017/2: Enable KASan for ARM") +Signed-off-by: huangshaobo +Acked-by: Ard Biesheuvel +Signed-off-by: Russell King (Oracle) +Signed-off-by: Sasha Levin +--- + arch/arm/probes/kprobes/Makefile | 3 +++ + 1 file changed, 3 insertions(+) + +diff --git a/arch/arm/probes/kprobes/Makefile b/arch/arm/probes/kprobes/Makefile +index 14db56f49f0a3..6159010dac4a6 100644 +--- a/arch/arm/probes/kprobes/Makefile ++++ b/arch/arm/probes/kprobes/Makefile +@@ -1,4 +1,7 @@ + # SPDX-License-Identifier: GPL-2.0 ++KASAN_SANITIZE_actions-common.o := n ++KASAN_SANITIZE_actions-arm.o := n ++KASAN_SANITIZE_actions-thumb.o := n + obj-$(CONFIG_KPROBES) += core.o actions-common.o checkers-common.o + obj-$(CONFIG_ARM_KPROBES_TEST) += test-kprobes.o + test-kprobes-objs := test-core.o +-- +2.34.1 + diff --git a/queue-5.10/ata-pata_platform-fix-a-null-pointer-dereference-in-.patch-22417 b/queue-5.10/ata-pata_platform-fix-a-null-pointer-dereference-in-.patch-22417 new file mode 100644 index 00000000000..070799e5331 --- /dev/null +++ b/queue-5.10/ata-pata_platform-fix-a-null-pointer-dereference-in-.patch-22417 @@ -0,0 +1,46 @@ +From 88fe25462a0e8852afedf05f6673494e4fa7c49a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 25 Jan 2022 00:45:25 +0800 +Subject: ata: pata_platform: Fix a NULL pointer dereference in + __pata_platform_probe() + +From: Zhou Qingyang + +[ Upstream commit 9b6d90e2085ca2ce72ef9ea78658bf270855e62e ] + +In __pata_platform_probe(), devm_kzalloc() is assigned to ap->ops and +there is a dereference of it right after that, which could introduce a +NULL pointer dereference bug. + +Fix this by adding a NULL check of ap->ops. + +This bug was found by a static analyzer. + +Builds with 'make allyesconfig' show no new warnings, +and our static analyzer no longer warns about this code. + +Fixes: f3d5e4f18dba ("ata: pata_of_platform: Allow to use 16-bit wide data transfer") +Signed-off-by: Zhou Qingyang +Signed-off-by: Damien Le Moal +Reviewed-by: Sergey Shtylyov +Signed-off-by: Sasha Levin +--- + drivers/ata/pata_platform.c | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/drivers/ata/pata_platform.c b/drivers/ata/pata_platform.c +index 5aba691f09af5..3ab05145caaf9 100644 +--- a/drivers/ata/pata_platform.c ++++ b/drivers/ata/pata_platform.c +@@ -126,6 +126,8 @@ int __pata_platform_probe(struct device *dev, struct resource *io_res, + ap = host->ports[0]; + + ap->ops = devm_kzalloc(dev, sizeof(*ap->ops), GFP_KERNEL); ++ if (!ap->ops) ++ return -ENOMEM; + ap->ops->inherits = &ata_sff_port_ops; + ap->ops->cable_detect = ata_cable_unknown; + ap->ops->set_mode = pata_platform_set_mode; +-- +2.34.1 + diff --git a/queue-5.10/drm-msm-dpu-invalid-parameter-check-in-dpu_setup_dsp.patch-23932 b/queue-5.10/drm-msm-dpu-invalid-parameter-check-in-dpu_setup_dsp.patch-23932 new file mode 100644 index 00000000000..ac85902ea74 --- /dev/null +++ b/queue-5.10/drm-msm-dpu-invalid-parameter-check-in-dpu_setup_dsp.patch-23932 @@ -0,0 +1,54 @@ +From 2dedc00854dfbddbc995b33c83e891ae2c00d5e7 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sun, 9 Jan 2022 20:24:31 +0100 +Subject: drm/msm/dpu: invalid parameter check in dpu_setup_dspp_pcc +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: José Expósito + +[ Upstream commit 170b22234d5495f5e0844246e23f004639ee89ba ] + +The function performs a check on the "ctx" input parameter, however, it +is used before the check. + +Initialize the "base" variable after the sanity check to avoid a +possible NULL pointer dereference. + +Fixes: 4259ff7ae509e ("drm/msm/dpu: add support for pcc color block in dpu driver") +Addresses-Coverity-ID: 1493866 ("Null pointer dereference") +Signed-off-by: José Expósito +Link: https://lore.kernel.org/r/20220109192431.135949-1-jose.exposito89@gmail.com +Signed-off-by: Dmitry Baryshkov +Signed-off-by: Sasha Levin +--- + drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c | 11 +++++++++-- + 1 file changed, 9 insertions(+), 2 deletions(-) + +diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c +index a7a24539921f3..a6efc11eba93f 100644 +--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c ++++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c +@@ -26,9 +26,16 @@ static void dpu_setup_dspp_pcc(struct dpu_hw_dspp *ctx, + struct dpu_hw_pcc_cfg *cfg) + { + +- u32 base = ctx->cap->sblk->pcc.base; ++ u32 base; + +- if (!ctx || !base) { ++ if (!ctx) { ++ DRM_ERROR("invalid ctx %pK\n", ctx); ++ return; ++ } ++ ++ base = ctx->cap->sblk->pcc.base; ++ ++ if (!base) { + DRM_ERROR("invalid ctx %pK pcc base 0x%x\n", ctx, base); + return; + } +-- +2.34.1 + diff --git a/queue-5.10/drm-msm-dsi-fix-missing-put_device-call-in-dsi_get_p.patch-11600 b/queue-5.10/drm-msm-dsi-fix-missing-put_device-call-in-dsi_get_p.patch-11600 new file mode 100644 index 00000000000..e668fb38351 --- /dev/null +++ b/queue-5.10/drm-msm-dsi-fix-missing-put_device-call-in-dsi_get_p.patch-11600 @@ -0,0 +1,44 @@ +From bcbb984327fbfee9e5a085379a87fe29434da088 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 30 Dec 2021 07:09:40 +0000 +Subject: drm/msm/dsi: Fix missing put_device() call in dsi_get_phy + +From: Miaoqian Lin + +[ Upstream commit c04c3148ca12227d92f91b355b4538cc333c9922 ] + +If of_find_device_by_node() succeeds, dsi_get_phy() doesn't +a corresponding put_device(). Thus add put_device() to fix the exception +handling. + +Fixes: ec31abf ("drm/msm/dsi: Separate PHY to another platform device") +Signed-off-by: Miaoqian Lin +Reviewed-by: Dmitry Baryshkov +Link: https://lore.kernel.org/r/20211230070943.18116-1-linmq006@gmail.com +Signed-off-by: Dmitry Baryshkov +Signed-off-by: Sasha Levin +--- + drivers/gpu/drm/msm/dsi/dsi.c | 7 ++++++- + 1 file changed, 6 insertions(+), 1 deletion(-) + +diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c +index 1adead764feed..f845333593daa 100644 +--- a/drivers/gpu/drm/msm/dsi/dsi.c ++++ b/drivers/gpu/drm/msm/dsi/dsi.c +@@ -33,7 +33,12 @@ static int dsi_get_phy(struct msm_dsi *msm_dsi) + + of_node_put(phy_node); + +- if (!phy_pdev || !msm_dsi->phy) { ++ if (!phy_pdev) { ++ DRM_DEV_ERROR(&pdev->dev, "%s: phy driver is not ready\n", __func__); ++ return -EPROBE_DEFER; ++ } ++ if (!msm_dsi->phy) { ++ put_device(&phy_pdev->dev); + DRM_DEV_ERROR(&pdev->dev, "%s: phy driver is not ready\n", __func__); + return -EPROBE_DEFER; + } +-- +2.34.1 + diff --git a/queue-5.10/drm-msm-dsi-invalid-parameter-check-in-msm_dsi_phy_e.patch-27026 b/queue-5.10/drm-msm-dsi-invalid-parameter-check-in-msm_dsi_phy_e.patch-27026 new file mode 100644 index 00000000000..d997405d32f --- /dev/null +++ b/queue-5.10/drm-msm-dsi-invalid-parameter-check-in-msm_dsi_phy_e.patch-27026 @@ -0,0 +1,52 @@ +From 68dd88ae64fc7ec453470200a802d5c02ded3da8 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sun, 16 Jan 2022 19:18:44 +0100 +Subject: drm/msm/dsi: invalid parameter check in msm_dsi_phy_enable +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: José Expósito + +[ Upstream commit 5e761a2287234bc402ba7ef07129f5103bcd775c ] + +The function performs a check on the "phy" input parameter, however, it +is used before the check. + +Initialize the "dev" variable after the sanity check to avoid a possible +NULL pointer dereference. + +Fixes: 5c8290284402b ("drm/msm/dsi: Split PHY drivers to separate files") +Addresses-Coverity-ID: 1493860 ("Null pointer dereference") +Signed-off-by: José Expósito +Reviewed-by: Dmitry Baryshkov +Link: https://lore.kernel.org/r/20220116181844.7400-1-jose.exposito89@gmail.com +Signed-off-by: Dmitry Baryshkov +Signed-off-by: Sasha Levin +--- + drivers/gpu/drm/msm/dsi/phy/dsi_phy.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +index e8c1a727179cc..e07986ab52c22 100644 +--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c ++++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +@@ -769,12 +769,14 @@ void __exit msm_dsi_phy_driver_unregister(void) + int msm_dsi_phy_enable(struct msm_dsi_phy *phy, int src_pll_id, + struct msm_dsi_phy_clk_request *clk_req) + { +- struct device *dev = &phy->pdev->dev; ++ struct device *dev; + int ret; + + if (!phy || !phy->cfg->ops.enable) + return -EINVAL; + ++ dev = &phy->pdev->dev; ++ + ret = dsi_phy_enable_resource(phy); + if (ret) { + DRM_DEV_ERROR(dev, "%s: resource enable failed, %d\n", +-- +2.34.1 + diff --git a/queue-5.10/drm-msm-fix-wrong-size-calculation.patch-26799 b/queue-5.10/drm-msm-fix-wrong-size-calculation.patch-26799 new file mode 100644 index 00000000000..580d15df1e4 --- /dev/null +++ b/queue-5.10/drm-msm-fix-wrong-size-calculation.patch-26799 @@ -0,0 +1,46 @@ +From 9a786093dac5154fa3e09fd2410a1358f270c5a1 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 12 Jan 2022 20:33:34 +0800 +Subject: drm/msm: Fix wrong size calculation + +From: Xianting Tian + +[ Upstream commit 0a727b459ee39bd4c5ced19d6024258ac87b6b2e ] + +For example, memory-region in .dts as below, + reg = <0x0 0x50000000 0x0 0x20000000> + +We can get below values, +struct resource r; +r.start = 0x50000000; +r.end = 0x6fffffff; + +So the size should be: +size = r.end - r.start + 1 = 0x20000000 + +Signed-off-by: Xianting Tian +Fixes: 072f1f9168ed ("drm/msm: add support for "stolen" mem") +Reviewed-by: Dmitry Baryshkov +Link: https://lore.kernel.org/r/20220112123334.749776-1-xianting.tian@linux.alibaba.com +Signed-off-by: Dmitry Baryshkov +Signed-off-by: Sasha Levin +--- + drivers/gpu/drm/msm/msm_drv.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c +index 33e42b2f9cfcb..e37e5afc680a2 100644 +--- a/drivers/gpu/drm/msm/msm_drv.c ++++ b/drivers/gpu/drm/msm/msm_drv.c +@@ -350,7 +350,7 @@ static int msm_init_vram(struct drm_device *dev) + of_node_put(node); + if (ret) + return ret; +- size = r.end - r.start; ++ size = r.end - r.start + 1; + DRM_INFO("using VRAM carveout: %lx@%pa\n", size, &r.start); + + /* if we have no IOMMU, then we need to use carveout allocator. +-- +2.34.1 + diff --git a/queue-5.10/drm-msm-hdmi-fix-missing-put_device-call-in-msm_hdmi.patch-14235 b/queue-5.10/drm-msm-hdmi-fix-missing-put_device-call-in-msm_hdmi.patch-14235 new file mode 100644 index 00000000000..7758e69a18d --- /dev/null +++ b/queue-5.10/drm-msm-hdmi-fix-missing-put_device-call-in-msm_hdmi.patch-14235 @@ -0,0 +1,47 @@ +From 9b2430e6c1911cd4669af52a4a9d2b942bf1ecf3 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 7 Jan 2022 08:50:22 +0000 +Subject: drm/msm/hdmi: Fix missing put_device() call in msm_hdmi_get_phy + +From: Miaoqian Lin + +[ Upstream commit 774fe0cd838d1b1419d41ab4ea0613c80d4ecbd7 ] + +The reference taken by 'of_find_device_by_node()' must be released when +not needed anymore. +Add the corresponding 'put_device()' in the error handling path. + +Fixes: e00012b256d4 ("drm/msm/hdmi: Make HDMI core get its PHY") +Signed-off-by: Miaoqian Lin +Reviewed-by: Dmitry Baryshkov +Link: https://lore.kernel.org/r/20220107085026.23831-1-linmq006@gmail.com +Signed-off-by: Dmitry Baryshkov +Signed-off-by: Sasha Levin +--- + drivers/gpu/drm/msm/hdmi/hdmi.c | 7 ++++++- + 1 file changed, 6 insertions(+), 1 deletion(-) + +diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c +index 737453b6e5966..94f948ef279d1 100644 +--- a/drivers/gpu/drm/msm/hdmi/hdmi.c ++++ b/drivers/gpu/drm/msm/hdmi/hdmi.c +@@ -97,10 +97,15 @@ static int msm_hdmi_get_phy(struct hdmi *hdmi) + + of_node_put(phy_node); + +- if (!phy_pdev || !hdmi->phy) { ++ if (!phy_pdev) { + DRM_DEV_ERROR(&pdev->dev, "phy driver is not ready\n"); + return -EPROBE_DEFER; + } ++ if (!hdmi->phy) { ++ DRM_DEV_ERROR(&pdev->dev, "phy driver is not ready\n"); ++ put_device(&phy_pdev->dev); ++ return -EPROBE_DEFER; ++ } + + hdmi->phy_dev = get_device(&phy_pdev->dev); + +-- +2.34.1 + diff --git a/queue-5.10/efi-libstub-arm64-fix-image-check-alignment-at-entry.patch-16098 b/queue-5.10/efi-libstub-arm64-fix-image-check-alignment-at-entry.patch-16098 new file mode 100644 index 00000000000..0a7b007365f --- /dev/null +++ b/queue-5.10/efi-libstub-arm64-fix-image-check-alignment-at-entry.patch-16098 @@ -0,0 +1,49 @@ +From 8f38d6564f7fbb6cf1fee8f776439b682cd0569b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 19 Jan 2022 18:14:27 +0200 +Subject: efi/libstub: arm64: Fix image check alignment at entry + +From: Mihai Carabas + +[ Upstream commit e9b7c3a4263bdcfd31bc3d03d48ce0ded7a94635 ] + +The kernel is aligned at SEGMENT_SIZE and this is the size populated in the PE +headers: + +arch/arm64/kernel/efi-header.S: .long SEGMENT_ALIGN // SectionAlignment + +EFI_KIMG_ALIGN is defined as: (SEGMENT_ALIGN > THREAD_ALIGN ? SEGMENT_ALIGN : +THREAD_ALIGN) + +So it depends on THREAD_ALIGN. On newer builds this message started to appear +even though the loader is taking into account the PE header (which is stating +SEGMENT_ALIGN). + +Fixes: c32ac11da3f8 ("efi/libstub: arm64: Double check image alignment at entry") +Signed-off-by: Mihai Carabas +Signed-off-by: Ard Biesheuvel +Signed-off-by: Sasha Levin +--- + drivers/firmware/efi/libstub/arm64-stub.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c +index c1b57dfb12776..415a971e76947 100644 +--- a/drivers/firmware/efi/libstub/arm64-stub.c ++++ b/drivers/firmware/efi/libstub/arm64-stub.c +@@ -119,9 +119,9 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, + if (image->image_base != _text) + efi_err("FIRMWARE BUG: efi_loaded_image_t::image_base has bogus value\n"); + +- if (!IS_ALIGNED((u64)_text, EFI_KIMG_ALIGN)) +- efi_err("FIRMWARE BUG: kernel image not aligned on %ldk boundary\n", +- EFI_KIMG_ALIGN >> 10); ++ if (!IS_ALIGNED((u64)_text, SEGMENT_ALIGN)) ++ efi_err("FIRMWARE BUG: kernel image not aligned on %dk boundary\n", ++ SEGMENT_ALIGN >> 10); + + kernel_size = _edata - _text; + kernel_memsize = kernel_size + (_end - _edata); +-- +2.34.1 + diff --git a/queue-5.10/hwmon-lm90-mark-alert-as-broken-for-max6646-6647-664.patch-31110 b/queue-5.10/hwmon-lm90-mark-alert-as-broken-for-max6646-6647-664.patch-31110 new file mode 100644 index 00000000000..d6f2e739c94 --- /dev/null +++ b/queue-5.10/hwmon-lm90-mark-alert-as-broken-for-max6646-6647-664.patch-31110 @@ -0,0 +1,36 @@ +From 6e31625367381564a932a98672037663929075c2 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 7 Jan 2022 12:36:41 -0800 +Subject: hwmon: (lm90) Mark alert as broken for MAX6646/6647/6649 + +From: Guenter Roeck + +[ Upstream commit f614629f9c1080dcc844a8430e3fb4c37ebbf05d ] + +Experiments with MAX6646 and MAX6648 show that the alert function of those +chips is broken, similar to other chips supported by the lm90 driver. +Mark it accordingly. + +Fixes: 4667bcb8d8fc ("hwmon: (lm90) Introduce chip parameter structure") +Signed-off-by: Guenter Roeck +Signed-off-by: Sasha Levin +--- + drivers/hwmon/lm90.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c +index 54140340c54aa..a7142c32889c0 100644 +--- a/drivers/hwmon/lm90.c ++++ b/drivers/hwmon/lm90.c +@@ -394,7 +394,7 @@ static const struct lm90_params lm90_params[] = { + .max_convrate = 9, + }, + [max6646] = { +- .flags = LM90_HAVE_CRIT, ++ .flags = LM90_HAVE_CRIT | LM90_HAVE_BROKEN_ALERT, + .alert_alarms = 0x7c, + .max_convrate = 6, + .reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL, +-- +2.34.1 + diff --git a/queue-5.10/hwmon-lm90-mark-alert-as-broken-for-max6654.patch-31788 b/queue-5.10/hwmon-lm90-mark-alert-as-broken-for-max6654.patch-31788 new file mode 100644 index 00000000000..2f3e1994ee0 --- /dev/null +++ b/queue-5.10/hwmon-lm90-mark-alert-as-broken-for-max6654.patch-31788 @@ -0,0 +1,35 @@ +From 5026bca57bd6dfd6f88b36766a3755fe87c9dafd Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 7 Jan 2022 11:05:23 -0800 +Subject: hwmon: (lm90) Mark alert as broken for MAX6654 + +From: Guenter Roeck + +[ Upstream commit a53fff96f35763d132a36c620b183fdf11022d7a ] + +Experiments with MAX6654 show that its alert function is broken, +similar to other chips supported by the lm90 driver. Mark it accordingly. + +Fixes: 229d495d8189 ("hwmon: (lm90) Add max6654 support to lm90 driver") +Cc: Josh Lehan +Signed-off-by: Guenter Roeck +Signed-off-by: Sasha Levin +--- + drivers/hwmon/lm90.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c +index fef02bcfedbcf..6841d0401bbd4 100644 +--- a/drivers/hwmon/lm90.c ++++ b/drivers/hwmon/lm90.c +@@ -400,6 +400,7 @@ static const struct lm90_params lm90_params[] = { + .reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL, + }, + [max6654] = { ++ .flags = LM90_HAVE_BROKEN_ALERT, + .alert_alarms = 0x7c, + .max_convrate = 7, + .reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL, +-- +2.34.1 + diff --git a/queue-5.10/hwmon-lm90-mark-alert-as-broken-for-max6680.patch-25015 b/queue-5.10/hwmon-lm90-mark-alert-as-broken-for-max6680.patch-25015 new file mode 100644 index 00000000000..96885d09c4d --- /dev/null +++ b/queue-5.10/hwmon-lm90-mark-alert-as-broken-for-max6680.patch-25015 @@ -0,0 +1,36 @@ +From cfa9fa9d56bd90e6ea5c3d7facf93802cf9b6fbf Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 7 Jan 2022 11:11:00 -0800 +Subject: hwmon: (lm90) Mark alert as broken for MAX6680 + +From: Guenter Roeck + +[ Upstream commit 94746b0ba479743355e0d3cc1cb9cfe3011fb8be ] + +Experiments with MAX6680 and MAX6681 show that the alert function of those +chips is broken, similar to other chips supported by the lm90 driver. +Mark it accordingly. + +Fixes: 4667bcb8d8fc ("hwmon: (lm90) Introduce chip parameter structure") +Signed-off-by: Guenter Roeck +Signed-off-by: Sasha Levin +--- + drivers/hwmon/lm90.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c +index 6841d0401bbd4..54140340c54aa 100644 +--- a/drivers/hwmon/lm90.c ++++ b/drivers/hwmon/lm90.c +@@ -419,7 +419,7 @@ static const struct lm90_params lm90_params[] = { + }, + [max6680] = { + .flags = LM90_HAVE_OFFSET | LM90_HAVE_CRIT +- | LM90_HAVE_CRIT_ALRM_SWP, ++ | LM90_HAVE_CRIT_ALRM_SWP | LM90_HAVE_BROKEN_ALERT, + .alert_alarms = 0x7c, + .max_convrate = 7, + }, +-- +2.34.1 + diff --git a/queue-5.10/hwmon-lm90-reduce-maximum-conversion-rate-for-g781.patch-19402 b/queue-5.10/hwmon-lm90-reduce-maximum-conversion-rate-for-g781.patch-19402 new file mode 100644 index 00000000000..4a39d40f505 --- /dev/null +++ b/queue-5.10/hwmon-lm90-reduce-maximum-conversion-rate-for-g781.patch-19402 @@ -0,0 +1,44 @@ +From cb388cc8af400a1f7b17822694e3116766d29c92 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 6 Jan 2022 11:48:52 -0800 +Subject: hwmon: (lm90) Reduce maximum conversion rate for G781 + +From: Guenter Roeck + +[ Upstream commit a66c5ed539277b9f2363bbace0dba88b85b36c26 ] + +According to its datasheet, G781 supports a maximum conversion rate value +of 8 (62.5 ms). However, chips labeled G781 and G780 were found to only +support a maximum conversion rate value of 7 (125 ms). On the other side, +chips labeled G781-1 and G784 were found to support a conversion rate value +of 8. There is no known means to distinguish G780 from G781 or G784; all +chips report the same manufacturer ID and chip revision. +Setting the conversion rate register value to 8 on chips not supporting +it causes unexpected behavior since the real conversion rate is set to 0 +(16 seconds) if a value of 8 is written into the conversion rate register. +Limit the conversion rate register value to 7 for all G78x chips to avoid +the problem. + +Fixes: ae544f64cc7b ("hwmon: (lm90) Add support for GMT G781") +Signed-off-by: Guenter Roeck +Signed-off-by: Sasha Levin +--- + drivers/hwmon/lm90.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c +index 959446b0137bc..fef02bcfedbcf 100644 +--- a/drivers/hwmon/lm90.c ++++ b/drivers/hwmon/lm90.c +@@ -373,7 +373,7 @@ static const struct lm90_params lm90_params[] = { + .flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT + | LM90_HAVE_BROKEN_ALERT | LM90_HAVE_CRIT, + .alert_alarms = 0x7c, +- .max_convrate = 8, ++ .max_convrate = 7, + }, + [lm86] = { + .flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT +-- +2.34.1 + diff --git a/queue-5.10/i40e-fix-for-failed-to-init-adminq-while-vf-reset.patch-21045 b/queue-5.10/i40e-fix-for-failed-to-init-adminq-while-vf-reset.patch-21045 new file mode 100644 index 00000000000..8e5dbaadfad --- /dev/null +++ b/queue-5.10/i40e-fix-for-failed-to-init-adminq-while-vf-reset.patch-21045 @@ -0,0 +1,129 @@ +From f27405fc6f79c4888a1455ab9b0cfcf9b7b90316 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 2 Dec 2021 12:52:01 +0100 +Subject: i40e: Fix for failed to init adminq while VF reset + +From: Karen Sornek + +[ Upstream commit 0f344c8129a5337dae50e31b817dd50a60ff238c ] + +Fix for failed to init adminq: -53 while VF is resetting via MAC +address changing procedure. +Added sync module to avoid reading deadbeef value in reinit adminq +during software reset. +Without this patch it is possible to trigger VF reset procedure +during reinit adminq. This resulted in an incorrect reading of +value from the AQP registers and generated the -53 error. + +Fixes: 5c3c48ac6bf5 ("i40e: implement virtual device interface") +Signed-off-by: Grzegorz Szczurek +Signed-off-by: Karen Sornek +Tested-by: Konrad Jankowski +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + .../net/ethernet/intel/i40e/i40e_register.h | 3 ++ + .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 44 ++++++++++++++++++- + .../ethernet/intel/i40e/i40e_virtchnl_pf.h | 1 + + 3 files changed, 46 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h +index 564df22f3f463..8335f151ceefc 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_register.h ++++ b/drivers/net/ethernet/intel/i40e/i40e_register.h +@@ -279,6 +279,9 @@ + #define I40E_VFINT_DYN_CTLN(_INTVF) (0x00024800 + ((_INTVF) * 4)) /* _i=0...511 */ /* Reset: VFR */ + #define I40E_VFINT_DYN_CTLN_CLEARPBA_SHIFT 1 + #define I40E_VFINT_DYN_CTLN_CLEARPBA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN_CLEARPBA_SHIFT) ++#define I40E_VFINT_ICR0_ADMINQ_SHIFT 30 ++#define I40E_VFINT_ICR0_ADMINQ_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ADMINQ_SHIFT) ++#define I40E_VFINT_ICR0_ENA(_VF) (0x0002C000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */ + #define I40E_VPINT_AEQCTL(_VF) (0x0002B800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */ + #define I40E_VPINT_AEQCTL_MSIX_INDX_SHIFT 0 + #define I40E_VPINT_AEQCTL_ITR_INDX_SHIFT 11 +diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +index c51701ab189d8..f71b7334e2955 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +@@ -1323,6 +1323,32 @@ static i40e_status i40e_config_vf_promiscuous_mode(struct i40e_vf *vf, + return aq_ret; + } + ++/** ++ * i40e_sync_vfr_reset ++ * @hw: pointer to hw struct ++ * @vf_id: VF identifier ++ * ++ * Before trigger hardware reset, we need to know if no other process has ++ * reserved the hardware for any reset operations. This check is done by ++ * examining the status of the RSTAT1 register used to signal the reset. ++ **/ ++static int i40e_sync_vfr_reset(struct i40e_hw *hw, int vf_id) ++{ ++ u32 reg; ++ int i; ++ ++ for (i = 0; i < I40E_VFR_WAIT_COUNT; i++) { ++ reg = rd32(hw, I40E_VFINT_ICR0_ENA(vf_id)) & ++ I40E_VFINT_ICR0_ADMINQ_MASK; ++ if (reg) ++ return 0; ++ ++ usleep_range(100, 200); ++ } ++ ++ return -EAGAIN; ++} ++ + /** + * i40e_trigger_vf_reset + * @vf: pointer to the VF structure +@@ -1337,9 +1363,11 @@ static void i40e_trigger_vf_reset(struct i40e_vf *vf, bool flr) + struct i40e_pf *pf = vf->pf; + struct i40e_hw *hw = &pf->hw; + u32 reg, reg_idx, bit_idx; ++ bool vf_active; ++ u32 radq; + + /* warn the VF */ +- clear_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states); ++ vf_active = test_and_clear_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states); + + /* Disable VF's configuration API during reset. The flag is re-enabled + * in i40e_alloc_vf_res(), when it's safe again to access VF's VSI. +@@ -1353,7 +1381,19 @@ static void i40e_trigger_vf_reset(struct i40e_vf *vf, bool flr) + * just need to clean up, so don't hit the VFRTRIG register. + */ + if (!flr) { +- /* reset VF using VPGEN_VFRTRIG reg */ ++ /* Sync VFR reset before trigger next one */ ++ radq = rd32(hw, I40E_VFINT_ICR0_ENA(vf->vf_id)) & ++ I40E_VFINT_ICR0_ADMINQ_MASK; ++ if (vf_active && !radq) ++ /* waiting for finish reset by virtual driver */ ++ if (i40e_sync_vfr_reset(hw, vf->vf_id)) ++ dev_info(&pf->pdev->dev, ++ "Reset VF %d never finished\n", ++ vf->vf_id); ++ ++ /* Reset VF using VPGEN_VFRTRIG reg. It is also setting ++ * in progress state in rstat1 register. ++ */ + reg = rd32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id)); + reg |= I40E_VPGEN_VFRTRIG_VFSWR_MASK; + wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg); +diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +index 49575a640a84c..03c42fd0fea19 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h ++++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +@@ -19,6 +19,7 @@ + #define I40E_MAX_VF_PROMISC_FLAGS 3 + + #define I40E_VF_STATE_WAIT_COUNT 20 ++#define I40E_VFR_WAIT_COUNT 100 + + /* Various queue ctrls */ + enum i40e_queue_ctrl { +-- +2.34.1 + diff --git a/queue-5.10/i40e-fix-issue-when-maximum-queues-is-exceeded.patch-24471 b/queue-5.10/i40e-fix-issue-when-maximum-queues-is-exceeded.patch-24471 new file mode 100644 index 00000000000..ccd59a8beee --- /dev/null +++ b/queue-5.10/i40e-fix-issue-when-maximum-queues-is-exceeded.patch-24471 @@ -0,0 +1,204 @@ +From 465c5aa15278981b69eb320e9fdb094c46cd88ea Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 5 Nov 2021 11:17:00 +0000 +Subject: i40e: Fix issue when maximum queues is exceeded + +From: Jedrzej Jagielski + +[ Upstream commit d701658a50a471591094b3eb3961b4926cc8f104 ] + +Before this patch VF interface vanished when +maximum queue number was exceeded. Driver tried +to add next queues even if there was not enough +space. PF sent incorrect number of queues to +the VF when there were not enough of them. + +Add an additional condition introduced to check +available space in 'qp_pile' before proceeding. +This condition makes it impossible to add queues +if they number is greater than the number resulting +from available space. +Also add the search for free space in PF queue +pair piles. + +Without this patch VF interfaces are not seen +when available space for queues has been +exceeded and following logs appears permanently +in dmesg: +"Unable to get VF config (-32)". +"VF 62 failed opcode 3, retval: -5" +"Unable to get VF config due to PF error condition, not retrying" + +Fixes: 7daa6bf3294e ("i40e: driver core headers") +Fixes: 41c445ff0f48 ("i40e: main driver core") +Signed-off-by: Jaroslaw Gawin +Signed-off-by: Slawomir Laba +Signed-off-by: Jedrzej Jagielski +Tested-by: Konrad Jankowski +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/i40e/i40e.h | 1 - + drivers/net/ethernet/intel/i40e/i40e_main.c | 14 +---- + .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 59 +++++++++++++++++++ + 3 files changed, 61 insertions(+), 13 deletions(-) + +diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h +index 5b83d1bc0e74d..67b0f72f97a24 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e.h ++++ b/drivers/net/ethernet/intel/i40e/i40e.h +@@ -172,7 +172,6 @@ enum i40e_interrupt_policy { + + struct i40e_lump_tracking { + u16 num_entries; +- u16 search_hint; + u16 list[0]; + #define I40E_PILE_VALID_BIT 0x8000 + #define I40E_IWARP_IRQ_PILE_ID (I40E_PILE_VALID_BIT - 2) +diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c +index eb26cd1f55713..9614ddc1f5490 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_main.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_main.c +@@ -195,10 +195,6 @@ int i40e_free_virt_mem_d(struct i40e_hw *hw, struct i40e_virt_mem *mem) + * @id: an owner id to stick on the items assigned + * + * Returns the base item index of the lump, or negative for error +- * +- * The search_hint trick and lack of advanced fit-finding only work +- * because we're highly likely to have all the same size lump requests. +- * Linear search time and any fragmentation should be minimal. + **/ + static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, + u16 needed, u16 id) +@@ -213,8 +209,7 @@ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, + return -EINVAL; + } + +- /* start the linear search with an imperfect hint */ +- i = pile->search_hint; ++ i = 0; + while (i < pile->num_entries) { + /* skip already allocated entries */ + if (pile->list[i] & I40E_PILE_VALID_BIT) { +@@ -233,7 +228,6 @@ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, + for (j = 0; j < needed; j++) + pile->list[i+j] = id | I40E_PILE_VALID_BIT; + ret = i; +- pile->search_hint = i + j; + break; + } + +@@ -256,7 +250,7 @@ static int i40e_put_lump(struct i40e_lump_tracking *pile, u16 index, u16 id) + { + int valid_id = (id | I40E_PILE_VALID_BIT); + int count = 0; +- int i; ++ u16 i; + + if (!pile || index >= pile->num_entries) + return -EINVAL; +@@ -268,8 +262,6 @@ static int i40e_put_lump(struct i40e_lump_tracking *pile, u16 index, u16 id) + count++; + } + +- if (count && index < pile->search_hint) +- pile->search_hint = index; + + return count; + } +@@ -11321,7 +11313,6 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf) + return -ENOMEM; + + pf->irq_pile->num_entries = vectors; +- pf->irq_pile->search_hint = 0; + + /* track first vector for misc interrupts, ignore return */ + (void)i40e_get_lump(pf, pf->irq_pile, 1, I40E_PILE_VALID_BIT - 1); +@@ -12124,7 +12115,6 @@ static int i40e_sw_init(struct i40e_pf *pf) + goto sw_init_done; + } + pf->qp_pile->num_entries = pf->hw.func_caps.num_tx_qp; +- pf->qp_pile->search_hint = 0; + + pf->tx_timeout_recovery_level = 1; + +diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +index 65c4c4fd359fa..c51701ab189d8 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +@@ -2563,6 +2563,59 @@ error_param: + aq_ret); + } + ++/** ++ * i40e_check_enough_queue - find big enough queue number ++ * @vf: pointer to the VF info ++ * @needed: the number of items needed ++ * ++ * Returns the base item index of the queue, or negative for error ++ **/ ++static int i40e_check_enough_queue(struct i40e_vf *vf, u16 needed) ++{ ++ unsigned int i, cur_queues, more, pool_size; ++ struct i40e_lump_tracking *pile; ++ struct i40e_pf *pf = vf->pf; ++ struct i40e_vsi *vsi; ++ ++ vsi = pf->vsi[vf->lan_vsi_idx]; ++ cur_queues = vsi->alloc_queue_pairs; ++ ++ /* if current allocated queues are enough for need */ ++ if (cur_queues >= needed) ++ return vsi->base_queue; ++ ++ pile = pf->qp_pile; ++ if (cur_queues > 0) { ++ /* if the allocated queues are not zero ++ * just check if there are enough queues for more ++ * behind the allocated queues. ++ */ ++ more = needed - cur_queues; ++ for (i = vsi->base_queue + cur_queues; ++ i < pile->num_entries; i++) { ++ if (pile->list[i] & I40E_PILE_VALID_BIT) ++ break; ++ ++ if (more-- == 1) ++ /* there is enough */ ++ return vsi->base_queue; ++ } ++ } ++ ++ pool_size = 0; ++ for (i = 0; i < pile->num_entries; i++) { ++ if (pile->list[i] & I40E_PILE_VALID_BIT) { ++ pool_size = 0; ++ continue; ++ } ++ if (needed <= ++pool_size) ++ /* there is enough */ ++ return i; ++ } ++ ++ return -ENOMEM; ++} ++ + /** + * i40e_vc_request_queues_msg + * @vf: pointer to the VF info +@@ -2597,6 +2650,12 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg) + req_pairs - cur_pairs, + pf->queues_left); + vfres->num_queue_pairs = pf->queues_left + cur_pairs; ++ } else if (i40e_check_enough_queue(vf, req_pairs) < 0) { ++ dev_warn(&pf->pdev->dev, ++ "VF %d requested %d more queues, but there is not enough for it.\n", ++ vf->vf_id, ++ req_pairs - cur_pairs); ++ vfres->num_queue_pairs = cur_pairs; + } else { + /* successful request */ + vf->num_req_queues = req_pairs; +-- +2.34.1 + diff --git a/queue-5.10/i40e-fix-queues-reservation-for-xdp.patch-15396 b/queue-5.10/i40e-fix-queues-reservation-for-xdp.patch-15396 new file mode 100644 index 00000000000..4bcef32d8fd --- /dev/null +++ b/queue-5.10/i40e-fix-queues-reservation-for-xdp.patch-15396 @@ -0,0 +1,94 @@ +From 7c978979b99dbc14db645d49237b8c48856b22ea Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 26 Nov 2021 11:11:22 +0100 +Subject: i40e: Fix queues reservation for XDP + +From: Sylwester Dziedziuch + +[ Upstream commit 92947844b8beee988c0ce17082b705c2f75f0742 ] + +When XDP was configured on a system with large number of CPUs +and X722 NIC there was a call trace with NULL pointer dereference. + +i40e 0000:87:00.0: failed to get tracking for 256 queues for VSI 0 err -12 +i40e 0000:87:00.0: setup of MAIN VSI failed + +BUG: kernel NULL pointer dereference, address: 0000000000000000 +RIP: 0010:i40e_xdp+0xea/0x1b0 [i40e] +Call Trace: +? i40e_reconfig_rss_queues+0x130/0x130 [i40e] +dev_xdp_install+0x61/0xe0 +dev_xdp_attach+0x18a/0x4c0 +dev_change_xdp_fd+0x1e6/0x220 +do_setlink+0x616/0x1030 +? ahci_port_stop+0x80/0x80 +? ata_qc_issue+0x107/0x1e0 +? lock_timer_base+0x61/0x80 +? __mod_timer+0x202/0x380 +rtnl_setlink+0xe5/0x170 +? bpf_lsm_binder_transaction+0x10/0x10 +? security_capable+0x36/0x50 +rtnetlink_rcv_msg+0x121/0x350 +? rtnl_calcit.isra.0+0x100/0x100 +netlink_rcv_skb+0x50/0xf0 +netlink_unicast+0x1d3/0x2a0 +netlink_sendmsg+0x22a/0x440 +sock_sendmsg+0x5e/0x60 +__sys_sendto+0xf0/0x160 +? __sys_getsockname+0x7e/0xc0 +? _copy_from_user+0x3c/0x80 +? __sys_setsockopt+0xc8/0x1a0 +__x64_sys_sendto+0x20/0x30 +do_syscall_64+0x33/0x40 +entry_SYSCALL_64_after_hwframe+0x44/0xae +RIP: 0033:0x7f83fa7a39e0 + +This was caused by PF queue pile fragmentation due to +flow director VSI queue being placed right after main VSI. +Because of this main VSI was not able to resize its +queue allocation for XDP resulting in no queues allocated +for main VSI when XDP was turned on. + +Fix this by always allocating last queue in PF queue pile +for a flow director VSI. + +Fixes: 41c445ff0f48 ("i40e: main driver core") +Fixes: 74608d17fe29 ("i40e: add support for XDP_TX action") +Signed-off-by: Sylwester Dziedziuch +Signed-off-by: Mateusz Palczewski +Reviewed-by: Maciej Fijalkowski +Tested-by: Kiran Bhandare +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/i40e/i40e_main.c | 14 ++++++++++++++ + 1 file changed, 14 insertions(+) + +diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c +index 9614ddc1f5490..500f067d0afcc 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_main.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_main.c +@@ -209,6 +209,20 @@ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, + return -EINVAL; + } + ++ /* Allocate last queue in the pile for FDIR VSI queue ++ * so it doesn't fragment the qp_pile ++ */ ++ if (pile == pf->qp_pile && pf->vsi[id]->type == I40E_VSI_FDIR) { ++ if (pile->list[pile->num_entries - 1] & I40E_PILE_VALID_BIT) { ++ dev_err(&pf->pdev->dev, ++ "Cannot allocate queue %d for I40E_VSI_FDIR\n", ++ pile->num_entries - 1); ++ return -ENOMEM; ++ } ++ pile->list[pile->num_entries - 1] = id | I40E_PILE_VALID_BIT; ++ return pile->num_entries - 1; ++ } ++ + i = 0; + while (i < pile->num_entries) { + /* skip already allocated entries */ +-- +2.34.1 + diff --git a/queue-5.10/i40e-fix-unsigned-stat-widths.patch-20948 b/queue-5.10/i40e-fix-unsigned-stat-widths.patch-20948 new file mode 100644 index 00000000000..9f369845ed6 --- /dev/null +++ b/queue-5.10/i40e-fix-unsigned-stat-widths.patch-20948 @@ -0,0 +1,79 @@ +From fe5ec497673a952dffb4c30409113f08d167a3fb Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 8 Dec 2021 17:56:33 -0800 +Subject: i40e: fix unsigned stat widths + +From: Joe Damato + +[ Upstream commit 3b8428b84539c78fdc8006c17ebd25afd4722d51 ] + +Change i40e_update_vsi_stats and struct i40e_vsi to use u64 fields to match +the width of the stats counters in struct i40e_rx_queue_stats. + +Update debugfs code to use the correct format specifier for u64. + +Fixes: 41c445ff0f48 ("i40e: main driver core") +Signed-off-by: Joe Damato +Reported-by: kernel test robot +Tested-by: Gurucharan G +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/i40e/i40e.h | 8 ++++---- + drivers/net/ethernet/intel/i40e/i40e_debugfs.c | 2 +- + drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++-- + 3 files changed, 7 insertions(+), 7 deletions(-) + +diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h +index 67b0f72f97a24..effdc3361266f 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e.h ++++ b/drivers/net/ethernet/intel/i40e/i40e.h +@@ -754,12 +754,12 @@ struct i40e_vsi { + struct rtnl_link_stats64 net_stats_offsets; + struct i40e_eth_stats eth_stats; + struct i40e_eth_stats eth_stats_offsets; +- u32 tx_restart; +- u32 tx_busy; ++ u64 tx_restart; ++ u64 tx_busy; + u64 tx_linearize; + u64 tx_force_wb; +- u32 rx_buf_failed; +- u32 rx_page_failed; ++ u64 rx_buf_failed; ++ u64 rx_page_failed; + + /* These are containers of ring pointers, allocated at run-time */ + struct i40e_ring **rx_rings; +diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +index 714b578b2b49c..1114a15a9ce3c 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +@@ -240,7 +240,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) + (unsigned long int)vsi->net_stats_offsets.rx_compressed, + (unsigned long int)vsi->net_stats_offsets.tx_compressed); + dev_info(&pf->pdev->dev, +- " tx_restart = %d, tx_busy = %d, rx_buf_failed = %d, rx_page_failed = %d\n", ++ " tx_restart = %llu, tx_busy = %llu, rx_buf_failed = %llu, rx_page_failed = %llu\n", + vsi->tx_restart, vsi->tx_busy, + vsi->rx_buf_failed, vsi->rx_page_failed); + rcu_read_lock(); +diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c +index 500f067d0afcc..bd18a780a0008 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_main.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_main.c +@@ -777,9 +777,9 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) + struct rtnl_link_stats64 *ns; /* netdev stats */ + struct i40e_eth_stats *oes; + struct i40e_eth_stats *es; /* device's eth stats */ +- u32 tx_restart, tx_busy; ++ u64 tx_restart, tx_busy; + struct i40e_ring *p; +- u32 rx_page, rx_buf; ++ u64 rx_page, rx_buf; + u64 bytes, packets; + unsigned int start; + u64 tx_linearize; +-- +2.34.1 + diff --git a/queue-5.10/i40e-increase-delay-to-1-s-after-global-emp-reset.patch-13096 b/queue-5.10/i40e-increase-delay-to-1-s-after-global-emp-reset.patch-13096 new file mode 100644 index 00000000000..84f005f6a0d --- /dev/null +++ b/queue-5.10/i40e-increase-delay-to-1-s-after-global-emp-reset.patch-13096 @@ -0,0 +1,52 @@ +From e2bd35a0eca46df801b07a771e6b625c614dd299 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 28 Oct 2021 13:51:14 +0000 +Subject: i40e: Increase delay to 1 s after global EMP reset + +From: Jedrzej Jagielski + +[ Upstream commit 9b13bd53134c9ddd544a790125199fdbdb505e67 ] + +Recently simplified i40e_rebuild causes that FW sometimes +is not ready after NVM update, the ping does not return. + +Increase the delay in case of EMP reset. +Old delay of 300 ms was introduced for specific cards for 710 series. +Now it works for all the cards and delay was increased. + +Fixes: 1fa51a650e1d ("i40e: Add delay after EMP reset for firmware to recover") +Signed-off-by: Arkadiusz Kubalewski +Signed-off-by: Jedrzej Jagielski +Tested-by: Gurucharan G +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/i40e/i40e_main.c | 12 +++--------- + 1 file changed, 3 insertions(+), 9 deletions(-) + +diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c +index f888a443a067b..eb26cd1f55713 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_main.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_main.c +@@ -10130,15 +10130,9 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) + } + i40e_get_oem_version(&pf->hw); + +- if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) && +- ((hw->aq.fw_maj_ver == 4 && hw->aq.fw_min_ver <= 33) || +- hw->aq.fw_maj_ver < 4) && hw->mac.type == I40E_MAC_XL710) { +- /* The following delay is necessary for 4.33 firmware and older +- * to recover after EMP reset. 200 ms should suffice but we +- * put here 300 ms to be sure that FW is ready to operate +- * after reset. +- */ +- mdelay(300); ++ if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state)) { ++ /* The following delay is necessary for firmware update. */ ++ mdelay(1000); + } + + /* re-verify the eeprom if we just had an EMP reset */ +-- +2.34.1 + diff --git a/queue-5.10/ibmvnic-don-t-spin-in-tasklet.patch-9595 b/queue-5.10/ibmvnic-don-t-spin-in-tasklet.patch-9595 new file mode 100644 index 00000000000..0bd4fb00e98 --- /dev/null +++ b/queue-5.10/ibmvnic-don-t-spin-in-tasklet.patch-9595 @@ -0,0 +1,47 @@ +From d313c14ae3039f53c038d9cf5196bdc9c94ac02b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 21 Jan 2022 18:59:20 -0800 +Subject: ibmvnic: don't spin in tasklet + +From: Sukadev Bhattiprolu + +[ Upstream commit 48079e7fdd0269d66b1d7d66ae88bd03162464ad ] + +ibmvnic_tasklet() continuously spins waiting for responses to all +capability requests. It does this to avoid encountering an error +during initialization of the vnic. However if there is a bug in the +VIOS and we do not receive a response to one or more queries the +tasklet ends up spinning continuously leading to hard lock ups. + +If we fail to receive a message from the VIOS it is reasonable to +timeout the login attempt rather than spin indefinitely in the tasklet. + +Fixes: 249168ad07cd ("ibmvnic: Make CRQ interrupt tasklet wait for all capabilities crqs") +Signed-off-by: Sukadev Bhattiprolu +Reviewed-by: Dany Madden +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/ibm/ibmvnic.c | 6 ------ + 1 file changed, 6 deletions(-) + +diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c +index 232c68af4c60a..c7be7ab131b19 100644 +--- a/drivers/net/ethernet/ibm/ibmvnic.c ++++ b/drivers/net/ethernet/ibm/ibmvnic.c +@@ -5075,12 +5075,6 @@ static void ibmvnic_tasklet(struct tasklet_struct *t) + ibmvnic_handle_crq(crq, adapter); + crq->generic.first = 0; + } +- +- /* remain in tasklet until all +- * capabilities responses are received +- */ +- if (!adapter->wait_capability) +- done = true; + } + /* if capabilities CRQ's were sent in this tasklet, the following + * tasklet must wait until all responses are received +-- +2.34.1 + diff --git a/queue-5.10/ibmvnic-init-running_cap_crqs-early.patch-3045 b/queue-5.10/ibmvnic-init-running_cap_crqs-early.patch-3045 new file mode 100644 index 00000000000..4ca5591fa0b --- /dev/null +++ b/queue-5.10/ibmvnic-init-running_cap_crqs-early.patch-3045 @@ -0,0 +1,327 @@ +From 1ba1554235c46fd5b4af8d1ed191b83df2fe6f61 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 21 Jan 2022 18:59:19 -0800 +Subject: ibmvnic: init ->running_cap_crqs early + +From: Sukadev Bhattiprolu + +[ Upstream commit 151b6a5c06b678687f64f2d9a99fd04d5cd32b72 ] + +We use ->running_cap_crqs to determine when the ibmvnic_tasklet() should +send out the next protocol message type. i.e when we get back responses +to all our QUERY_CAPABILITY CRQs we send out REQUEST_CAPABILITY crqs. +Similiary, when we get responses to all the REQUEST_CAPABILITY crqs, we +send out the QUERY_IP_OFFLOAD CRQ. + +We currently increment ->running_cap_crqs as we send out each CRQ and +have the ibmvnic_tasklet() send out the next message type, when this +running_cap_crqs count drops to 0. + +This assumes that all the CRQs of the current type were sent out before +the count drops to 0. However it is possible that we send out say 6 CRQs, +get preempted and receive all the 6 responses before we send out the +remaining CRQs. This can result in ->running_cap_crqs count dropping to +zero before all messages of the current type were sent and we end up +sending the next protocol message too early. + +Instead initialize the ->running_cap_crqs upfront so the tasklet will +only send the next protocol message after all responses are received. + +Use the cap_reqs local variable to also detect any discrepancy (either +now or in future) in the number of capability requests we actually send. + +Currently only send_query_cap() is affected by this behavior (of sending +next message early) since it is called from the worker thread (during +reset) and from application thread (during ->ndo_open()) and they can be +preempted. send_request_cap() is only called from the tasklet which +processes CRQ responses sequentially, is not be affected. But to +maintain the existing symmtery with send_query_capability() we update +send_request_capability() also. + +Fixes: 249168ad07cd ("ibmvnic: Make CRQ interrupt tasklet wait for all capabilities crqs") +Signed-off-by: Sukadev Bhattiprolu +Reviewed-by: Dany Madden +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/ibm/ibmvnic.c | 106 +++++++++++++++++++---------- + 1 file changed, 71 insertions(+), 35 deletions(-) + +diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c +index 4f99d97638248..232c68af4c60a 100644 +--- a/drivers/net/ethernet/ibm/ibmvnic.c ++++ b/drivers/net/ethernet/ibm/ibmvnic.c +@@ -3401,11 +3401,25 @@ static void send_request_cap(struct ibmvnic_adapter *adapter, int retry) + struct device *dev = &adapter->vdev->dev; + union ibmvnic_crq crq; + int max_entries; ++ int cap_reqs; ++ ++ /* We send out 6 or 7 REQUEST_CAPABILITY CRQs below (depending on ++ * the PROMISC flag). Initialize this count upfront. When the tasklet ++ * receives a response to all of these, it will send the next protocol ++ * message (QUERY_IP_OFFLOAD). ++ */ ++ if (!(adapter->netdev->flags & IFF_PROMISC) || ++ adapter->promisc_supported) ++ cap_reqs = 7; ++ else ++ cap_reqs = 6; + + if (!retry) { + /* Sub-CRQ entries are 32 byte long */ + int entries_page = 4 * PAGE_SIZE / (sizeof(u64) * 4); + ++ atomic_set(&adapter->running_cap_crqs, cap_reqs); ++ + if (adapter->min_tx_entries_per_subcrq > entries_page || + adapter->min_rx_add_entries_per_subcrq > entries_page) { + dev_err(dev, "Fatal, invalid entries per sub-crq\n"); +@@ -3466,44 +3480,45 @@ static void send_request_cap(struct ibmvnic_adapter *adapter, int retry) + adapter->opt_rx_comp_queues; + + adapter->req_rx_add_queues = adapter->max_rx_add_queues; ++ } else { ++ atomic_add(cap_reqs, &adapter->running_cap_crqs); + } +- + memset(&crq, 0, sizeof(crq)); + crq.request_capability.first = IBMVNIC_CRQ_CMD; + crq.request_capability.cmd = REQUEST_CAPABILITY; + + crq.request_capability.capability = cpu_to_be16(REQ_TX_QUEUES); + crq.request_capability.number = cpu_to_be64(adapter->req_tx_queues); +- atomic_inc(&adapter->running_cap_crqs); ++ cap_reqs--; + ibmvnic_send_crq(adapter, &crq); + + crq.request_capability.capability = cpu_to_be16(REQ_RX_QUEUES); + crq.request_capability.number = cpu_to_be64(adapter->req_rx_queues); +- atomic_inc(&adapter->running_cap_crqs); ++ cap_reqs--; + ibmvnic_send_crq(adapter, &crq); + + crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_QUEUES); + crq.request_capability.number = cpu_to_be64(adapter->req_rx_add_queues); +- atomic_inc(&adapter->running_cap_crqs); ++ cap_reqs--; + ibmvnic_send_crq(adapter, &crq); + + crq.request_capability.capability = + cpu_to_be16(REQ_TX_ENTRIES_PER_SUBCRQ); + crq.request_capability.number = + cpu_to_be64(adapter->req_tx_entries_per_subcrq); +- atomic_inc(&adapter->running_cap_crqs); ++ cap_reqs--; + ibmvnic_send_crq(adapter, &crq); + + crq.request_capability.capability = + cpu_to_be16(REQ_RX_ADD_ENTRIES_PER_SUBCRQ); + crq.request_capability.number = + cpu_to_be64(adapter->req_rx_add_entries_per_subcrq); +- atomic_inc(&adapter->running_cap_crqs); ++ cap_reqs--; + ibmvnic_send_crq(adapter, &crq); + + crq.request_capability.capability = cpu_to_be16(REQ_MTU); + crq.request_capability.number = cpu_to_be64(adapter->req_mtu); +- atomic_inc(&adapter->running_cap_crqs); ++ cap_reqs--; + ibmvnic_send_crq(adapter, &crq); + + if (adapter->netdev->flags & IFF_PROMISC) { +@@ -3511,16 +3526,21 @@ static void send_request_cap(struct ibmvnic_adapter *adapter, int retry) + crq.request_capability.capability = + cpu_to_be16(PROMISC_REQUESTED); + crq.request_capability.number = cpu_to_be64(1); +- atomic_inc(&adapter->running_cap_crqs); ++ cap_reqs--; + ibmvnic_send_crq(adapter, &crq); + } + } else { + crq.request_capability.capability = + cpu_to_be16(PROMISC_REQUESTED); + crq.request_capability.number = cpu_to_be64(0); +- atomic_inc(&adapter->running_cap_crqs); ++ cap_reqs--; + ibmvnic_send_crq(adapter, &crq); + } ++ ++ /* Keep at end to catch any discrepancy between expected and actual ++ * CRQs sent. ++ */ ++ WARN_ON(cap_reqs != 0); + } + + static int pending_scrq(struct ibmvnic_adapter *adapter, +@@ -3953,118 +3973,132 @@ static void send_query_map(struct ibmvnic_adapter *adapter) + static void send_query_cap(struct ibmvnic_adapter *adapter) + { + union ibmvnic_crq crq; ++ int cap_reqs; ++ ++ /* We send out 25 QUERY_CAPABILITY CRQs below. Initialize this count ++ * upfront. When the tasklet receives a response to all of these, it ++ * can send out the next protocol messaage (REQUEST_CAPABILITY). ++ */ ++ cap_reqs = 25; ++ ++ atomic_set(&adapter->running_cap_crqs, cap_reqs); + +- atomic_set(&adapter->running_cap_crqs, 0); + memset(&crq, 0, sizeof(crq)); + crq.query_capability.first = IBMVNIC_CRQ_CMD; + crq.query_capability.cmd = QUERY_CAPABILITY; + + crq.query_capability.capability = cpu_to_be16(MIN_TX_QUEUES); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(MIN_RX_QUEUES); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(MIN_RX_ADD_QUEUES); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(MAX_TX_QUEUES); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(MAX_RX_QUEUES); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(MAX_RX_ADD_QUEUES); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = + cpu_to_be16(MIN_TX_ENTRIES_PER_SUBCRQ); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = + cpu_to_be16(MIN_RX_ADD_ENTRIES_PER_SUBCRQ); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = + cpu_to_be16(MAX_TX_ENTRIES_PER_SUBCRQ); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = + cpu_to_be16(MAX_RX_ADD_ENTRIES_PER_SUBCRQ); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(TCP_IP_OFFLOAD); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(PROMISC_SUPPORTED); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(MIN_MTU); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(MAX_MTU); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(MAX_MULTICAST_FILTERS); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(VLAN_HEADER_INSERTION); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(RX_VLAN_HEADER_INSERTION); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(MAX_TX_SG_ENTRIES); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(RX_SG_SUPPORTED); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(OPT_TX_COMP_SUB_QUEUES); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(OPT_RX_COMP_QUEUES); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = + cpu_to_be16(OPT_RX_BUFADD_Q_PER_RX_COMP_Q); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = + cpu_to_be16(OPT_TX_ENTRIES_PER_SUBCRQ); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = + cpu_to_be16(OPT_RXBA_ENTRIES_PER_SUBCRQ); +- atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; + + crq.query_capability.capability = cpu_to_be16(TX_RX_DESC_REQ); +- atomic_inc(&adapter->running_cap_crqs); ++ + ibmvnic_send_crq(adapter, &crq); ++ cap_reqs--; ++ ++ /* Keep at end to catch any discrepancy between expected and actual ++ * CRQs sent. ++ */ ++ WARN_ON(cap_reqs != 0); + } + + static void send_query_ip_offload(struct ibmvnic_adapter *adapter) +@@ -4369,6 +4403,8 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq, + char *name; + + atomic_dec(&adapter->running_cap_crqs); ++ netdev_dbg(adapter->netdev, "Outstanding request-caps: %d\n", ++ atomic_read(&adapter->running_cap_crqs)); + switch (be16_to_cpu(crq->request_capability_rsp.capability)) { + case REQ_TX_QUEUES: + req_value = &adapter->req_tx_queues; +-- +2.34.1 + diff --git a/queue-5.10/ipv4-avoid-using-shared-ip-generator-for-connected-s.patch-2008 b/queue-5.10/ipv4-avoid-using-shared-ip-generator-for-connected-s.patch-2008 new file mode 100644 index 00000000000..00ebee8f6e4 --- /dev/null +++ b/queue-5.10/ipv4-avoid-using-shared-ip-generator-for-connected-s.patch-2008 @@ -0,0 +1,70 @@ +From 46819fba426881103c855ef797b36dd104761a2b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 26 Jan 2022 17:10:22 -0800 +Subject: ipv4: avoid using shared IP generator for connected sockets + +From: Eric Dumazet + +[ Upstream commit 23f57406b82de51809d5812afd96f210f8b627f3 ] + +ip_select_ident_segs() has been very conservative about using +the connected socket private generator only for packets with IP_DF +set, claiming it was needed for some VJ compression implementations. + +As mentioned in this referenced document, this can be abused. +(Ref: Off-Path TCP Exploits of the Mixed IPID Assignment) + +Before switching to pure random IPID generation and possibly hurt +some workloads, lets use the private inet socket generator. + +Not only this will remove one vulnerability, this will also +improve performance of TCP flows using pmtudisc==IP_PMTUDISC_DONT + +Fixes: 73f156a6e8c1 ("inetpeer: get rid of ip_id_count") +Signed-off-by: Eric Dumazet +Reviewed-by: David Ahern +Reported-by: Ray Che +Cc: Willy Tarreau +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + include/net/ip.h | 21 ++++++++++----------- + 1 file changed, 10 insertions(+), 11 deletions(-) + +diff --git a/include/net/ip.h b/include/net/ip.h +index 5538e54d4620c..de2dc22a78f93 100644 +--- a/include/net/ip.h ++++ b/include/net/ip.h +@@ -506,19 +506,18 @@ static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, + { + struct iphdr *iph = ip_hdr(skb); + ++ /* We had many attacks based on IPID, use the private ++ * generator as much as we can. ++ */ ++ if (sk && inet_sk(sk)->inet_daddr) { ++ iph->id = htons(inet_sk(sk)->inet_id); ++ inet_sk(sk)->inet_id += segs; ++ return; ++ } + if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) { +- /* This is only to work around buggy Windows95/2000 +- * VJ compression implementations. If the ID field +- * does not change, they drop every other packet in +- * a TCP stream using header compression. +- */ +- if (sk && inet_sk(sk)->inet_daddr) { +- iph->id = htons(inet_sk(sk)->inet_id); +- inet_sk(sk)->inet_id += segs; +- } else { +- iph->id = 0; +- } ++ iph->id = 0; + } else { ++ /* Unfortunately we need the big hammer to get a suitable IPID */ + __ip_select_ident(net, iph, segs); + } + } +-- +2.34.1 + diff --git a/queue-5.10/ipv4-fix-ip-option-filtering-for-locally-generated-f.patch-27601 b/queue-5.10/ipv4-fix-ip-option-filtering-for-locally-generated-f.patch-27601 new file mode 100644 index 00000000000..1f26d9a9eb3 --- /dev/null +++ b/queue-5.10/ipv4-fix-ip-option-filtering-for-locally-generated-f.patch-27601 @@ -0,0 +1,111 @@ +From 6f44a803728e82326c3f3776c1d8f4b1d2162094 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 21 Jan 2022 16:57:31 -0800 +Subject: ipv4: fix ip option filtering for locally generated fragments + +From: Jakub Kicinski + +[ Upstream commit 27a8caa59babb96c5890569e131bc0eb6d45daee ] + +During IP fragmentation we sanitize IP options. This means overwriting +options which should not be copied with NOPs. Only the first fragment +has the original, full options. + +ip_fraglist_prepare() copies the IP header and options from previous +fragment to the next one. Commit 19c3401a917b ("net: ipv4: place control +buffer handling away from fragmentation iterators") moved sanitizing +options before ip_fraglist_prepare() which means options are sanitized +and then overwritten again with the old values. + +Fixing this is not enough, however, nor did the sanitization work +prior to aforementioned commit. + +ip_options_fragment() (which does the sanitization) uses ipcb->opt.optlen +for the length of the options. ipcb->opt of fragments is not populated +(it's 0), only the head skb has the state properly built. So even when +called at the right time ip_options_fragment() does nothing. This seems +to date back all the way to v2.5.44 when the fast path for pre-fragmented +skbs had been introduced. Prior to that ip_options_build() would have been +called for every fragment (in fact ever since v2.5.44 the fragmentation +handing in ip_options_build() has been dead code, I'll clean it up in +-next). + +In the original patch (see Link) caixf mentions fixing the handling +for fragments other than the second one, but I'm not sure how _any_ +fragment could have had their options sanitized with the code +as it stood. + +Tested with python (MTU on lo lowered to 1000 to force fragmentation): + + import socket + s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM) + s.setsockopt(socket.IPPROTO_IP, socket.IP_OPTIONS, + bytearray([7,4,5,192, 20|0x80,4,1,0])) + s.sendto(b'1'*2000, ('127.0.0.1', 1234)) + +Before: + +IP (tos 0x0, ttl 64, id 1053, offset 0, flags [+], proto UDP (17), length 996, options (RR [bad length 4] [bad ptr 5] 192.148.4.1,,RA value 256)) + localhost.36500 > localhost.search-agent: UDP, length 2000 +IP (tos 0x0, ttl 64, id 1053, offset 968, flags [+], proto UDP (17), length 996, options (RR [bad length 4] [bad ptr 5] 192.148.4.1,,RA value 256)) + localhost > localhost: udp +IP (tos 0x0, ttl 64, id 1053, offset 1936, flags [none], proto UDP (17), length 100, options (RR [bad length 4] [bad ptr 5] 192.148.4.1,,RA value 256)) + localhost > localhost: udp + +After: + +IP (tos 0x0, ttl 96, id 42549, offset 0, flags [+], proto UDP (17), length 996, options (RR [bad length 4] [bad ptr 5] 192.148.4.1,,RA value 256)) + localhost.51607 > localhost.search-agent: UDP, bad length 2000 > 960 +IP (tos 0x0, ttl 96, id 42549, offset 968, flags [+], proto UDP (17), length 996, options (NOP,NOP,NOP,NOP,RA value 256)) + localhost > localhost: udp +IP (tos 0x0, ttl 96, id 42549, offset 1936, flags [none], proto UDP (17), length 100, options (NOP,NOP,NOP,NOP,RA value 256)) + localhost > localhost: udp + +RA (20 | 0x80) is now copied as expected, RR (7) is "NOPed out". + +Link: https://lore.kernel.org/netdev/20220107080559.122713-1-ooppublic@163.com/ +Fixes: 19c3401a917b ("net: ipv4: place control buffer handling away from fragmentation iterators") +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: caixf +Signed-off-by: Jakub Kicinski +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ipv4/ip_output.c | 15 ++++++++++++--- + 1 file changed, 12 insertions(+), 3 deletions(-) + +diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c +index e77afaecc9818..4f76e8183f403 100644 +--- a/net/ipv4/ip_output.c ++++ b/net/ipv4/ip_output.c +@@ -834,15 +834,24 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + /* Everything is OK. Generate! */ + ip_fraglist_init(skb, iph, hlen, &iter); + +- if (iter.frag) +- ip_options_fragment(iter.frag); +- + for (;;) { + /* Prepare header of the next frame, + * before previous one went down. */ + if (iter.frag) { ++ bool first_frag = (iter.offset == 0); ++ + IPCB(iter.frag)->flags = IPCB(skb)->flags; + ip_fraglist_prepare(skb, &iter); ++ if (first_frag && IPCB(skb)->opt.optlen) { ++ /* ipcb->opt is not populated for frags ++ * coming from __ip_make_skb(), ++ * ip_options_fragment() needs optlen ++ */ ++ IPCB(iter.frag)->opt.optlen = ++ IPCB(skb)->opt.optlen; ++ ip_options_fragment(iter.frag); ++ ip_send_check(iter.iph); ++ } + } + + skb->tstamp = tstamp; +-- +2.34.1 + diff --git a/queue-5.10/ipv4-raw-lock-the-socket-in-raw_bind.patch-1741 b/queue-5.10/ipv4-raw-lock-the-socket-in-raw_bind.patch-1741 new file mode 100644 index 00000000000..a0acfcc1231 --- /dev/null +++ b/queue-5.10/ipv4-raw-lock-the-socket-in-raw_bind.patch-1741 @@ -0,0 +1,78 @@ +From 8e52bfb939b9f52c4b0df81cd7b91da230cdd079 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 26 Jan 2022 16:51:16 -0800 +Subject: ipv4: raw: lock the socket in raw_bind() + +From: Eric Dumazet + +[ Upstream commit 153a0d187e767c68733b8e9f46218eb1f41ab902 ] + +For some reason, raw_bind() forgot to lock the socket. + +BUG: KCSAN: data-race in __ip4_datagram_connect / raw_bind + +write to 0xffff8881170d4308 of 4 bytes by task 5466 on cpu 0: + raw_bind+0x1b0/0x250 net/ipv4/raw.c:739 + inet_bind+0x56/0xa0 net/ipv4/af_inet.c:443 + __sys_bind+0x14b/0x1b0 net/socket.c:1697 + __do_sys_bind net/socket.c:1708 [inline] + __se_sys_bind net/socket.c:1706 [inline] + __x64_sys_bind+0x3d/0x50 net/socket.c:1706 + do_syscall_x64 arch/x86/entry/common.c:50 [inline] + do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 + entry_SYSCALL_64_after_hwframe+0x44/0xae + +read to 0xffff8881170d4308 of 4 bytes by task 5468 on cpu 1: + __ip4_datagram_connect+0xb7/0x7b0 net/ipv4/datagram.c:39 + ip4_datagram_connect+0x2a/0x40 net/ipv4/datagram.c:89 + inet_dgram_connect+0x107/0x190 net/ipv4/af_inet.c:576 + __sys_connect_file net/socket.c:1900 [inline] + __sys_connect+0x197/0x1b0 net/socket.c:1917 + __do_sys_connect net/socket.c:1927 [inline] + __se_sys_connect net/socket.c:1924 [inline] + __x64_sys_connect+0x3d/0x50 net/socket.c:1924 + do_syscall_x64 arch/x86/entry/common.c:50 [inline] + do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 + entry_SYSCALL_64_after_hwframe+0x44/0xae + +value changed: 0x00000000 -> 0x0003007f + +Reported by Kernel Concurrency Sanitizer on: +CPU: 1 PID: 5468 Comm: syz-executor.5 Not tainted 5.17.0-rc1-syzkaller #0 +Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 + +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: Eric Dumazet +Reported-by: syzbot +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ipv4/raw.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c +index 7d26e0f8bdaeb..5d95f80314f95 100644 +--- a/net/ipv4/raw.c ++++ b/net/ipv4/raw.c +@@ -721,6 +721,7 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) + int ret = -EINVAL; + int chk_addr_ret; + ++ lock_sock(sk); + if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_in)) + goto out; + +@@ -740,7 +741,9 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) + inet->inet_saddr = 0; /* Use device */ + sk_dst_reset(sk); + ret = 0; +-out: return ret; ++out: ++ release_sock(sk); ++ return ret; + } + + /* +-- +2.34.1 + diff --git a/queue-5.10/ipv4-remove-sparse-error-in-ip_neigh_gw4.patch-3162 b/queue-5.10/ipv4-remove-sparse-error-in-ip_neigh_gw4.patch-3162 new file mode 100644 index 00000000000..c1e48691c6b --- /dev/null +++ b/queue-5.10/ipv4-remove-sparse-error-in-ip_neigh_gw4.patch-3162 @@ -0,0 +1,39 @@ +From de35b38d24d28cc867bddde6524465fc4876e066 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 26 Jan 2022 17:34:04 -0800 +Subject: ipv4: remove sparse error in ip_neigh_gw4() + +From: Eric Dumazet + +[ Upstream commit 3c42b2019863b327caa233072c50739d4144dd16 ] + +./include/net/route.h:373:48: warning: incorrect type in argument 2 (different base types) +./include/net/route.h:373:48: expected unsigned int [usertype] key +./include/net/route.h:373:48: got restricted __be32 [usertype] daddr + +Fixes: 5c9f7c1dfc2e ("ipv4: Add helpers for neigh lookup for nexthop") +Signed-off-by: Eric Dumazet +Reviewed-by: David Ahern +Link: https://lore.kernel.org/r/20220127013404.1279313-1-eric.dumazet@gmail.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + include/net/route.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/include/net/route.h b/include/net/route.h +index ff021cab657e5..a07c277cd33e8 100644 +--- a/include/net/route.h ++++ b/include/net/route.h +@@ -369,7 +369,7 @@ static inline struct neighbour *ip_neigh_gw4(struct net_device *dev, + { + struct neighbour *neigh; + +- neigh = __ipv4_neigh_lookup_noref(dev, daddr); ++ neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)daddr); + if (unlikely(!neigh)) + neigh = __neigh_create(&arp_tbl, &daddr, dev, false); + +-- +2.34.1 + diff --git a/queue-5.10/ipv4-tcp-send-zero-ipid-in-synack-messages.patch-31729 b/queue-5.10/ipv4-tcp-send-zero-ipid-in-synack-messages.patch-31729 new file mode 100644 index 00000000000..80992c18793 --- /dev/null +++ b/queue-5.10/ipv4-tcp-send-zero-ipid-in-synack-messages.patch-31729 @@ -0,0 +1,77 @@ +From b1513dbb3b54c34e5ff511436716175058e424ad Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 26 Jan 2022 17:10:21 -0800 +Subject: ipv4: tcp: send zero IPID in SYNACK messages + +From: Eric Dumazet + +[ Upstream commit 970a5a3ea86da637471d3cd04d513a0755aba4bf ] + +In commit 431280eebed9 ("ipv4: tcp: send zero IPID for RST and +ACK sent in SYN-RECV and TIME-WAIT state") we took care of some +ctl packets sent by TCP. + +It turns out we need to use a similar strategy for SYNACK packets. + +By default, they carry IP_DF and IPID==0, but there are ways +to ask them to use the hashed IP ident generator and thus +be used to build off-path attacks. +(Ref: Off-Path TCP Exploits of the Mixed IPID Assignment) + +One of this way is to force (before listener is started) +echo 1 >/proc/sys/net/ipv4/ip_no_pmtu_disc + +Another way is using forged ICMP ICMP_FRAG_NEEDED +with a very small MTU (like 68) to force a false return from +ip_dont_fragment() + +In this patch, ip_build_and_send_pkt() uses the following +heuristics. + +1) Most SYNACK packets are smaller than IPV4_MIN_MTU and therefore +can use IP_DF regardless of the listener or route pmtu setting. + +2) In case the SYNACK packet is bigger than IPV4_MIN_MTU, +we use prandom_u32() generator instead of the IPv4 hashed ident one. + +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: Eric Dumazet +Reported-by: Ray Che +Reviewed-by: David Ahern +Cc: Geoff Alexander +Cc: Willy Tarreau +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/ipv4/ip_output.c | 11 +++++++++-- + 1 file changed, 9 insertions(+), 2 deletions(-) + +diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c +index 4f76e8183f403..5e48b3d3a00db 100644 +--- a/net/ipv4/ip_output.c ++++ b/net/ipv4/ip_output.c +@@ -162,12 +162,19 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, + iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); + iph->saddr = saddr; + iph->protocol = sk->sk_protocol; +- if (ip_dont_fragment(sk, &rt->dst)) { ++ /* Do not bother generating IPID for small packets (eg SYNACK) */ ++ if (skb->len <= IPV4_MIN_MTU || ip_dont_fragment(sk, &rt->dst)) { + iph->frag_off = htons(IP_DF); + iph->id = 0; + } else { + iph->frag_off = 0; +- __ip_select_ident(net, iph, 1); ++ /* TCP packets here are SYNACK with fat IPv4/TCP options. ++ * Avoid using the hashed IP ident generator. ++ */ ++ if (sk->sk_protocol == IPPROTO_TCP) ++ iph->id = (__force __be16)prandom_u32(); ++ else ++ __ip_select_ident(net, iph, 1); + } + + if (opt && opt->opt.optlen) { +-- +2.34.1 + diff --git a/queue-5.10/ipv6-annotate-accesses-to-fn-fn_sernum.patch-11803 b/queue-5.10/ipv6-annotate-accesses-to-fn-fn_sernum.patch-11803 new file mode 100644 index 00000000000..bb418964f9d --- /dev/null +++ b/queue-5.10/ipv6-annotate-accesses-to-fn-fn_sernum.patch-11803 @@ -0,0 +1,197 @@ +From bf426655155df0ade3570a4e0a74c84e6dca6121 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 20 Jan 2022 09:41:12 -0800 +Subject: ipv6: annotate accesses to fn->fn_sernum + +From: Eric Dumazet + +[ Upstream commit aafc2e3285c2d7a79b7ee15221c19fbeca7b1509 ] + +struct fib6_node's fn_sernum field can be +read while other threads change it. + +Add READ_ONCE()/WRITE_ONCE() annotations. + +Do not change existing smp barriers in fib6_get_cookie_safe() +and __fib6_update_sernum_upto_root() + +syzbot reported: + +BUG: KCSAN: data-race in fib6_clean_node / inet6_csk_route_socket + +write to 0xffff88813df62e2c of 4 bytes by task 1920 on cpu 1: + fib6_clean_node+0xc2/0x260 net/ipv6/ip6_fib.c:2178 + fib6_walk_continue+0x38e/0x430 net/ipv6/ip6_fib.c:2112 + fib6_walk net/ipv6/ip6_fib.c:2160 [inline] + fib6_clean_tree net/ipv6/ip6_fib.c:2240 [inline] + __fib6_clean_all+0x1a9/0x2e0 net/ipv6/ip6_fib.c:2256 + fib6_flush_trees+0x6c/0x80 net/ipv6/ip6_fib.c:2281 + rt_genid_bump_ipv6 include/net/net_namespace.h:488 [inline] + addrconf_dad_completed+0x57f/0x870 net/ipv6/addrconf.c:4230 + addrconf_dad_work+0x908/0x1170 + process_one_work+0x3f6/0x960 kernel/workqueue.c:2307 + worker_thread+0x616/0xa70 kernel/workqueue.c:2454 + kthread+0x1bf/0x1e0 kernel/kthread.c:359 + ret_from_fork+0x1f/0x30 + +read to 0xffff88813df62e2c of 4 bytes by task 15701 on cpu 0: + fib6_get_cookie_safe include/net/ip6_fib.h:285 [inline] + rt6_get_cookie include/net/ip6_fib.h:306 [inline] + ip6_dst_store include/net/ip6_route.h:234 [inline] + inet6_csk_route_socket+0x352/0x3c0 net/ipv6/inet6_connection_sock.c:109 + inet6_csk_xmit+0x91/0x1e0 net/ipv6/inet6_connection_sock.c:121 + __tcp_transmit_skb+0x1323/0x1840 net/ipv4/tcp_output.c:1402 + tcp_transmit_skb net/ipv4/tcp_output.c:1420 [inline] + tcp_write_xmit+0x1450/0x4460 net/ipv4/tcp_output.c:2680 + __tcp_push_pending_frames+0x68/0x1c0 net/ipv4/tcp_output.c:2864 + tcp_push+0x2d9/0x2f0 net/ipv4/tcp.c:725 + mptcp_push_release net/mptcp/protocol.c:1491 [inline] + __mptcp_push_pending+0x46c/0x490 net/mptcp/protocol.c:1578 + mptcp_sendmsg+0x9ec/0xa50 net/mptcp/protocol.c:1764 + inet6_sendmsg+0x5f/0x80 net/ipv6/af_inet6.c:643 + sock_sendmsg_nosec net/socket.c:705 [inline] + sock_sendmsg net/socket.c:725 [inline] + kernel_sendmsg+0x97/0xd0 net/socket.c:745 + sock_no_sendpage+0x84/0xb0 net/core/sock.c:3086 + inet_sendpage+0x9d/0xc0 net/ipv4/af_inet.c:834 + kernel_sendpage+0x187/0x200 net/socket.c:3492 + sock_sendpage+0x5a/0x70 net/socket.c:1007 + pipe_to_sendpage+0x128/0x160 fs/splice.c:364 + splice_from_pipe_feed fs/splice.c:418 [inline] + __splice_from_pipe+0x207/0x500 fs/splice.c:562 + splice_from_pipe fs/splice.c:597 [inline] + generic_splice_sendpage+0x94/0xd0 fs/splice.c:746 + do_splice_from fs/splice.c:767 [inline] + direct_splice_actor+0x80/0xa0 fs/splice.c:936 + splice_direct_to_actor+0x345/0x650 fs/splice.c:891 + do_splice_direct+0x106/0x190 fs/splice.c:979 + do_sendfile+0x675/0xc40 fs/read_write.c:1245 + __do_sys_sendfile64 fs/read_write.c:1310 [inline] + __se_sys_sendfile64 fs/read_write.c:1296 [inline] + __x64_sys_sendfile64+0x102/0x140 fs/read_write.c:1296 + do_syscall_x64 arch/x86/entry/common.c:50 [inline] + do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 + entry_SYSCALL_64_after_hwframe+0x44/0xae + +value changed: 0x0000026f -> 0x00000271 + +Reported by Kernel Concurrency Sanitizer on: +CPU: 0 PID: 15701 Comm: syz-executor.2 Not tainted 5.16.0-syzkaller #0 +Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 + +The Fixes tag I chose is probably arbitrary, I do not think +we need to backport this patch to older kernels. + +Fixes: c5cff8561d2d ("ipv6: add rcu grace period before freeing fib6_node") +Signed-off-by: Eric Dumazet +Reported-by: syzbot +Link: https://lore.kernel.org/r/20220120174112.1126644-1-eric.dumazet@gmail.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + include/net/ip6_fib.h | 2 +- + net/ipv6/ip6_fib.c | 23 +++++++++++++---------- + net/ipv6/route.c | 2 +- + 3 files changed, 15 insertions(+), 12 deletions(-) + +diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h +index 399394327fc35..82bb51e3bcef1 100644 +--- a/include/net/ip6_fib.h ++++ b/include/net/ip6_fib.h +@@ -280,7 +280,7 @@ static inline bool fib6_get_cookie_safe(const struct fib6_info *f6i, + fn = rcu_dereference(f6i->fib6_node); + + if (fn) { +- *cookie = fn->fn_sernum; ++ *cookie = READ_ONCE(fn->fn_sernum); + /* pairs with smp_wmb() in __fib6_update_sernum_upto_root() */ + smp_rmb(); + status = true; +diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c +index 355e7734bd5d7..78f56f8d86102 100644 +--- a/net/ipv6/ip6_fib.c ++++ b/net/ipv6/ip6_fib.c +@@ -110,7 +110,7 @@ void fib6_update_sernum(struct net *net, struct fib6_info *f6i) + fn = rcu_dereference_protected(f6i->fib6_node, + lockdep_is_held(&f6i->fib6_table->tb6_lock)); + if (fn) +- fn->fn_sernum = fib6_new_sernum(net); ++ WRITE_ONCE(fn->fn_sernum, fib6_new_sernum(net)); + } + + /* +@@ -587,12 +587,13 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, + spin_unlock_bh(&table->tb6_lock); + if (res > 0) { + cb->args[4] = 1; +- cb->args[5] = w->root->fn_sernum; ++ cb->args[5] = READ_ONCE(w->root->fn_sernum); + } + } else { +- if (cb->args[5] != w->root->fn_sernum) { ++ int sernum = READ_ONCE(w->root->fn_sernum); ++ if (cb->args[5] != sernum) { + /* Begin at the root if the tree changed */ +- cb->args[5] = w->root->fn_sernum; ++ cb->args[5] = sernum; + w->state = FWS_INIT; + w->node = w->root; + w->skip = w->count; +@@ -1342,7 +1343,7 @@ static void __fib6_update_sernum_upto_root(struct fib6_info *rt, + /* paired with smp_rmb() in fib6_get_cookie_safe() */ + smp_wmb(); + while (fn) { +- fn->fn_sernum = sernum; ++ WRITE_ONCE(fn->fn_sernum, sernum); + fn = rcu_dereference_protected(fn->parent, + lockdep_is_held(&rt->fib6_table->tb6_lock)); + } +@@ -2171,8 +2172,8 @@ static int fib6_clean_node(struct fib6_walker *w) + }; + + if (c->sernum != FIB6_NO_SERNUM_CHANGE && +- w->node->fn_sernum != c->sernum) +- w->node->fn_sernum = c->sernum; ++ READ_ONCE(w->node->fn_sernum) != c->sernum) ++ WRITE_ONCE(w->node->fn_sernum, c->sernum); + + if (!c->func) { + WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE); +@@ -2536,7 +2537,7 @@ static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter, + iter->w.state = FWS_INIT; + iter->w.node = iter->w.root; + iter->w.args = iter; +- iter->sernum = iter->w.root->fn_sernum; ++ iter->sernum = READ_ONCE(iter->w.root->fn_sernum); + INIT_LIST_HEAD(&iter->w.lh); + fib6_walker_link(net, &iter->w); + } +@@ -2564,8 +2565,10 @@ static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, + + static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) + { +- if (iter->sernum != iter->w.root->fn_sernum) { +- iter->sernum = iter->w.root->fn_sernum; ++ int sernum = READ_ONCE(iter->w.root->fn_sernum); ++ ++ if (iter->sernum != sernum) { ++ iter->sernum = sernum; + iter->w.state = FWS_INIT; + iter->w.node = iter->w.root; + WARN_ON(iter->w.skip); +diff --git a/net/ipv6/route.c b/net/ipv6/route.c +index 654bf4ca61260..352e645c546eb 100644 +--- a/net/ipv6/route.c ++++ b/net/ipv6/route.c +@@ -2674,7 +2674,7 @@ static void ip6_link_failure(struct sk_buff *skb) + if (from) { + fn = rcu_dereference(from->fib6_node); + if (fn && (rt->rt6i_flags & RTF_DEFAULT)) +- fn->fn_sernum = -1; ++ WRITE_ONCE(fn->fn_sernum, -1); + } + } + rcu_read_unlock(); +-- +2.34.1 + diff --git a/queue-5.10/ipv6-correct-comments-about-fib6_node-sernum.patch-17310 b/queue-5.10/ipv6-correct-comments-about-fib6_node-sernum.patch-17310 new file mode 100644 index 00000000000..64d2a7b7b24 --- /dev/null +++ b/queue-5.10/ipv6-correct-comments-about-fib6_node-sernum.patch-17310 @@ -0,0 +1,58 @@ +From 443a8c6a918f36bd8be485c591de30c8b93743f4 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 23 Aug 2021 11:49:00 +0800 +Subject: ipv6: correct comments about fib6_node sernum + +From: zhang kai + +[ Upstream commit 446e7f218b7662c912c610aae99069543aa88a40 ] + +correct comments in set and get fn_sernum + +Signed-off-by: zhang kai +Reviewed-by: David Ahern +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + include/net/ip6_fib.h | 4 ++-- + net/ipv6/ip6_fib.c | 2 +- + 2 files changed, 3 insertions(+), 3 deletions(-) + +diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h +index 88bc66b8d02b0..399394327fc35 100644 +--- a/include/net/ip6_fib.h ++++ b/include/net/ip6_fib.h +@@ -266,7 +266,7 @@ static inline bool fib6_check_expired(const struct fib6_info *f6i) + return false; + } + +-/* Function to safely get fn->sernum for passed in rt ++/* Function to safely get fn->fn_sernum for passed in rt + * and store result in passed in cookie. + * Return true if we can get cookie safely + * Return false if not +@@ -281,7 +281,7 @@ static inline bool fib6_get_cookie_safe(const struct fib6_info *f6i, + + if (fn) { + *cookie = fn->fn_sernum; +- /* pairs with smp_wmb() in fib6_update_sernum_upto_root() */ ++ /* pairs with smp_wmb() in __fib6_update_sernum_upto_root() */ + smp_rmb(); + status = true; + } +diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c +index e43f1fbac28b6..355e7734bd5d7 100644 +--- a/net/ipv6/ip6_fib.c ++++ b/net/ipv6/ip6_fib.c +@@ -1339,7 +1339,7 @@ static void __fib6_update_sernum_upto_root(struct fib6_info *rt, + struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, + lockdep_is_held(&rt->fib6_table->tb6_lock)); + +- /* paired with smp_rmb() in rt6_get_cookie_safe() */ ++ /* paired with smp_rmb() in fib6_get_cookie_safe() */ + smp_wmb(); + while (fn) { + fn->fn_sernum = sernum; +-- +2.34.1 + diff --git a/queue-5.10/ipv6_tunnel-rate-limit-warning-messages.patch-10619 b/queue-5.10/ipv6_tunnel-rate-limit-warning-messages.patch-10619 new file mode 100644 index 00000000000..7de06d03b42 --- /dev/null +++ b/queue-5.10/ipv6_tunnel-rate-limit-warning-messages.patch-10619 @@ -0,0 +1,51 @@ +From 77f4ef8ba29efd5d820572fbdf87a0e3e2e1226b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 20 Jan 2022 10:05:46 +0200 +Subject: ipv6_tunnel: Rate limit warning messages + +From: Ido Schimmel + +[ Upstream commit 6cee105e7f2ced596373951d9ea08dacc3883c68 ] + +The warning messages can be invoked from the data path for every packet +transmitted through an ip6gre netdev, leading to high CPU utilization. + +Fix that by rate limiting the messages. + +Fixes: 09c6bbf090ec ("[IPV6]: Do mandatory IPv6 tunnel endpoint checks in realtime") +Reported-by: Maksym Yaremchuk +Tested-by: Maksym Yaremchuk +Signed-off-by: Ido Schimmel +Reviewed-by: Amit Cohen +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ipv6/ip6_tunnel.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c +index 08441f06afd48..3a2741569b847 100644 +--- a/net/ipv6/ip6_tunnel.c ++++ b/net/ipv6/ip6_tunnel.c +@@ -1066,14 +1066,14 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t, + + if (unlikely(!ipv6_chk_addr_and_flags(net, laddr, ldev, false, + 0, IFA_F_TENTATIVE))) +- pr_warn("%s xmit: Local address not yet configured!\n", +- p->name); ++ pr_warn_ratelimited("%s xmit: Local address not yet configured!\n", ++ p->name); + else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) && + !ipv6_addr_is_multicast(raddr) && + unlikely(ipv6_chk_addr_and_flags(net, raddr, ldev, + true, 0, IFA_F_TENTATIVE))) +- pr_warn("%s xmit: Routing loop! Remote address found on this node!\n", +- p->name); ++ pr_warn_ratelimited("%s xmit: Routing loop! Remote address found on this node!\n", ++ p->name); + else + ret = 1; + rcu_read_unlock(); +-- +2.34.1 + diff --git a/queue-5.10/kernel-delete-repeated-words-in-comments.patch-15671 b/queue-5.10/kernel-delete-repeated-words-in-comments.patch-15671 new file mode 100644 index 00000000000..e06f3b59527 --- /dev/null +++ b/queue-5.10/kernel-delete-repeated-words-in-comments.patch-15671 @@ -0,0 +1,172 @@ +From 05476184f92efef19ac58d574c0767c45fff9bc7 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 25 Feb 2021 17:21:10 -0800 +Subject: kernel: delete repeated words in comments + +From: Randy Dunlap + +[ Upstream commit c034f48e99907d5be147ac8f0f3e630a9307c2be ] + +Drop repeated words in kernel/events/. +{if, the, that, with, time} + +Drop repeated words in kernel/locking/. +{it, no, the} + +Drop repeated words in kernel/sched/. +{in, not} + +Link: https://lkml.kernel.org/r/20210127023412.26292-1-rdunlap@infradead.org +Signed-off-by: Randy Dunlap +Acked-by: Will Deacon [kernel/locking/] +Cc: Peter Zijlstra +Cc: Ingo Molnar +Cc: Arnaldo Carvalho de Melo +Cc: Will Deacon +Cc: Mathieu Desnoyers +Cc: "Paul E. McKenney" +Cc: Juri Lelli +Cc: Vincent Guittot +Signed-off-by: Andrew Morton +Signed-off-by: Linus Torvalds +Signed-off-by: Sasha Levin +--- + kernel/events/core.c | 8 ++++---- + kernel/events/uprobes.c | 2 +- + kernel/locking/rtmutex.c | 4 ++-- + kernel/locking/rwsem.c | 2 +- + kernel/locking/semaphore.c | 2 +- + kernel/sched/fair.c | 2 +- + kernel/sched/membarrier.c | 2 +- + 7 files changed, 11 insertions(+), 11 deletions(-) + +diff --git a/kernel/events/core.c b/kernel/events/core.c +index e2d774cc470ee..8dc7c4d12b789 100644 +--- a/kernel/events/core.c ++++ b/kernel/events/core.c +@@ -266,7 +266,7 @@ static void event_function_call(struct perf_event *event, event_f func, void *da + if (!event->parent) { + /* + * If this is a !child event, we must hold ctx::mutex to +- * stabilize the the event->ctx relation. See ++ * stabilize the event->ctx relation. See + * perf_event_ctx_lock(). + */ + lockdep_assert_held(&ctx->mutex); +@@ -1300,7 +1300,7 @@ static void put_ctx(struct perf_event_context *ctx) + * life-time rules separate them. That is an exiting task cannot fork, and a + * spawning task cannot (yet) exit. + * +- * But remember that that these are parent<->child context relations, and ++ * But remember that these are parent<->child context relations, and + * migration does not affect children, therefore these two orderings should not + * interact. + * +@@ -1439,7 +1439,7 @@ static u64 primary_event_id(struct perf_event *event) + /* + * Get the perf_event_context for a task and lock it. + * +- * This has to cope with with the fact that until it is locked, ++ * This has to cope with the fact that until it is locked, + * the context could get moved to another task. + */ + static struct perf_event_context * +@@ -2492,7 +2492,7 @@ static void perf_set_shadow_time(struct perf_event *event, + * But this is a bit hairy. + * + * So instead, we have an explicit cgroup call to remain +- * within the time time source all along. We believe it ++ * within the time source all along. We believe it + * is cleaner and simpler to understand. + */ + if (is_cgroup_event(event)) +diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c +index 00b0358739ab3..e1bbb3b92921d 100644 +--- a/kernel/events/uprobes.c ++++ b/kernel/events/uprobes.c +@@ -1735,7 +1735,7 @@ void uprobe_free_utask(struct task_struct *t) + } + + /* +- * Allocate a uprobe_task object for the task if if necessary. ++ * Allocate a uprobe_task object for the task if necessary. + * Called when the thread hits a breakpoint. + * + * Returns: +diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c +index 2f8cd616d3b29..f00dd928fc711 100644 +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1438,7 +1438,7 @@ rt_mutex_fasttrylock(struct rt_mutex *lock, + } + + /* +- * Performs the wakeup of the the top-waiter and re-enables preemption. ++ * Performs the wakeup of the top-waiter and re-enables preemption. + */ + void rt_mutex_postunlock(struct wake_q_head *wake_q) + { +@@ -1832,7 +1832,7 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock) + * been started. + * @waiter: the pre-initialized rt_mutex_waiter + * +- * Wait for the the lock acquisition started on our behalf by ++ * Wait for the lock acquisition started on our behalf by + * rt_mutex_start_proxy_lock(). Upon failure, the caller must call + * rt_mutex_cleanup_proxy_lock(). + * +diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c +index a163542d178ee..cc5cc889b5b7f 100644 +--- a/kernel/locking/rwsem.c ++++ b/kernel/locking/rwsem.c +@@ -1177,7 +1177,7 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) + + /* + * If there were already threads queued before us and: +- * 1) there are no no active locks, wake the front ++ * 1) there are no active locks, wake the front + * queued process(es) as the handoff bit might be set. + * 2) there are no active writers and some readers, the lock + * must be read owned; so we try to wake any read lock +diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c +index d9dd94defc0a9..9aa855a96c4ae 100644 +--- a/kernel/locking/semaphore.c ++++ b/kernel/locking/semaphore.c +@@ -119,7 +119,7 @@ EXPORT_SYMBOL(down_killable); + * @sem: the semaphore to be acquired + * + * Try to acquire the semaphore atomically. Returns 0 if the semaphore has +- * been acquired successfully or 1 if it it cannot be acquired. ++ * been acquired successfully or 1 if it cannot be acquired. + * + * NOTE: This return value is inverted from both spin_trylock and + * mutex_trylock! Be careful about this when converting code. +diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c +index 2a33cb5a10e59..8d2f238fdd2ac 100644 +--- a/kernel/sched/fair.c ++++ b/kernel/sched/fair.c +@@ -5149,7 +5149,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) + /* + * When a group wakes up we want to make sure that its quota is not already + * expired/exceeded, otherwise it may be allowed to steal additional ticks of +- * runtime as update_curr() throttling can not not trigger until it's on-rq. ++ * runtime as update_curr() throttling can not trigger until it's on-rq. + */ + static void check_enqueue_throttle(struct cfs_rq *cfs_rq) + { +diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c +index 16f57e71f9c44..b02f04336a085 100644 +--- a/kernel/sched/membarrier.c ++++ b/kernel/sched/membarrier.c +@@ -315,7 +315,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm) + + /* + * For each cpu runqueue, if the task's mm match @mm, ensure that all +- * @mm's membarrier state set bits are also set in in the runqueue's ++ * @mm's membarrier state set bits are also set in the runqueue's + * membarrier state. This ensures that a runqueue scheduling + * between threads which are users of @mm has its membarrier state + * updated. +-- +2.34.1 + diff --git a/queue-5.10/net-bridge-vlan-fix-memory-leak-in-__allowed_ingress.patch-11653 b/queue-5.10/net-bridge-vlan-fix-memory-leak-in-__allowed_ingress.patch-11653 new file mode 100644 index 00000000000..c1da88c4694 --- /dev/null +++ b/queue-5.10/net-bridge-vlan-fix-memory-leak-in-__allowed_ingress.patch-11653 @@ -0,0 +1,47 @@ +From 9fb4f82d4219c356e93cccdf63a364de9908c9c4 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 27 Jan 2022 15:49:53 +0800 +Subject: net: bridge: vlan: fix memory leak in __allowed_ingress + +From: Tim Yi + +[ Upstream commit fd20d9738395cf8e27d0a17eba34169699fccdff ] + +When using per-vlan state, if vlan snooping and stats are disabled, +untagged or priority-tagged ingress frame will go to check pvid state. +If the port state is forwarding and the pvid state is not +learning/forwarding, untagged or priority-tagged frame will be dropped +but skb memory is not freed. +Should free skb when __allowed_ingress returns false. + +Fixes: a580c76d534c ("net: bridge: vlan: add per-vlan state") +Signed-off-by: Tim Yi +Acked-by: Nikolay Aleksandrov +Link: https://lore.kernel.org/r/20220127074953.12632-1-tim.yi@pica8.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/bridge/br_vlan.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c +index 1f508d998fb2d..852f4b54e8811 100644 +--- a/net/bridge/br_vlan.c ++++ b/net/bridge/br_vlan.c +@@ -543,10 +543,10 @@ static bool __allowed_ingress(const struct net_bridge *br, + if (!br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { + if (*state == BR_STATE_FORWARDING) { + *state = br_vlan_get_pvid_state(vg); +- return br_vlan_state_allowed(*state, true); +- } else { +- return true; ++ if (!br_vlan_state_allowed(*state, true)) ++ goto drop; + } ++ return true; + } + } + v = br_vlan_find(vg, *vid); +-- +2.34.1 + diff --git a/queue-5.10/net-bridge-vlan-fix-single-net-device-option-dumping.patch-32125 b/queue-5.10/net-bridge-vlan-fix-single-net-device-option-dumping.patch-32125 new file mode 100644 index 00000000000..a94e9e20770 --- /dev/null +++ b/queue-5.10/net-bridge-vlan-fix-single-net-device-option-dumping.patch-32125 @@ -0,0 +1,42 @@ +From 92db2ef0cc9436e2c2f705cf5289c0c62dfc2c30 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 26 Jan 2022 15:10:25 +0200 +Subject: net: bridge: vlan: fix single net device option dumping + +From: Nikolay Aleksandrov + +[ Upstream commit dcb2c5c6ca9b9177f04abaf76e5a983d177c9414 ] + +When dumping vlan options for a single net device we send the same +entries infinitely because user-space expects a 0 return at the end but +we keep returning skb->len and restarting the dump on retry. Fix it by +returning the value from br_vlan_dump_dev() if it completed or there was +an error. The only case that must return skb->len is when the dump was +incomplete and needs to continue (-EMSGSIZE). + +Reported-by: Benjamin Poirier +Fixes: 8dcea187088b ("net: bridge: vlan: add rtm definitions and dump support") +Signed-off-by: Nikolay Aleksandrov +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/bridge/br_vlan.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c +index 08c77418c687b..1f508d998fb2d 100644 +--- a/net/bridge/br_vlan.c ++++ b/net/bridge/br_vlan.c +@@ -1873,7 +1873,8 @@ static int br_vlan_rtm_dump(struct sk_buff *skb, struct netlink_callback *cb) + goto out_err; + } + err = br_vlan_dump_dev(dev, skb, cb, dump_flags); +- if (err && err != -EMSGSIZE) ++ /* if the dump completed without an error we return 0 here */ ++ if (err != -EMSGSIZE) + goto out_err; + } else { + for_each_netdev_rcu(net, dev) { +-- +2.34.1 + diff --git a/queue-5.10/net-cpsw-properly-initialise-struct-page_pool_params.patch-12745 b/queue-5.10/net-cpsw-properly-initialise-struct-page_pool_params.patch-12745 new file mode 100644 index 00000000000..cdef16e900f --- /dev/null +++ b/queue-5.10/net-cpsw-properly-initialise-struct-page_pool_params.patch-12745 @@ -0,0 +1,48 @@ +From 3c38e8577c1699a2f037ffdcef2f449f81ff066c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 24 Jan 2022 15:35:29 +0100 +Subject: net: cpsw: Properly initialise struct page_pool_params +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Toke Høiland-Jørgensen + +[ Upstream commit c63003e3d99761afb280add3b30de1cf30fa522b ] + +The cpsw driver didn't properly initialise the struct page_pool_params +before calling page_pool_create(), which leads to crashes after the struct +has been expanded with new parameters. + +The second Fixes tag below is where the buggy code was introduced, but +because the code was moved around this patch will only apply on top of the +commit in the first Fixes tag. + +Fixes: c5013ac1dd0e ("net: ethernet: ti: cpsw: move set of common functions in cpsw_priv") +Fixes: 9ed4050c0d75 ("net: ethernet: ti: cpsw: add XDP support") +Reported-by: Colin Foster +Signed-off-by: Toke Høiland-Jørgensen +Tested-by: Colin Foster +Acked-by: Jesper Dangaard Brouer +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/ti/cpsw_priv.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c +index 424e644724e46..e74f2e95a46eb 100644 +--- a/drivers/net/ethernet/ti/cpsw_priv.c ++++ b/drivers/net/ethernet/ti/cpsw_priv.c +@@ -1144,7 +1144,7 @@ int cpsw_fill_rx_channels(struct cpsw_priv *priv) + static struct page_pool *cpsw_create_page_pool(struct cpsw_common *cpsw, + int size) + { +- struct page_pool_params pp_params; ++ struct page_pool_params pp_params = {}; + struct page_pool *pool; + + pp_params.order = 0; +-- +2.34.1 + diff --git a/queue-5.10/net-fix-information-leakage-in-proc-net-ptype.patch-15695 b/queue-5.10/net-fix-information-leakage-in-proc-net-ptype.patch-15695 new file mode 100644 index 00000000000..b9e83661d3f --- /dev/null +++ b/queue-5.10/net-fix-information-leakage-in-proc-net-ptype.patch-15695 @@ -0,0 +1,78 @@ +From 4d97d82d94b218488b2e5d68d3b0e1ae60bd1891 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 18 Jan 2022 14:20:13 -0500 +Subject: net: fix information leakage in /proc/net/ptype + +From: Congyu Liu + +[ Upstream commit 47934e06b65637c88a762d9c98329ae6e3238888 ] + +In one net namespace, after creating a packet socket without binding +it to a device, users in other net namespaces can observe the new +`packet_type` added by this packet socket by reading `/proc/net/ptype` +file. This is minor information leakage as packet socket is +namespace aware. + +Add a net pointer in `packet_type` to keep the net namespace of +of corresponding packet socket. In `ptype_seq_show`, this net pointer +must be checked when it is not NULL. + +Fixes: 2feb27dbe00c ("[NETNS]: Minor information leak via /proc/net/ptype file.") +Signed-off-by: Congyu Liu +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + include/linux/netdevice.h | 1 + + net/core/net-procfs.c | 3 ++- + net/packet/af_packet.c | 2 ++ + 3 files changed, 5 insertions(+), 1 deletion(-) + +diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h +index 3476d20b75d49..fe3155736d635 100644 +--- a/include/linux/netdevice.h ++++ b/include/linux/netdevice.h +@@ -2543,6 +2543,7 @@ struct packet_type { + struct net_device *); + bool (*id_match)(struct packet_type *ptype, + struct sock *sk); ++ struct net *af_packet_net; + void *af_packet_priv; + struct list_head list; + }; +diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c +index c714e6a9dad4c..e12c67f9492ba 100644 +--- a/net/core/net-procfs.c ++++ b/net/core/net-procfs.c +@@ -263,7 +263,8 @@ static int ptype_seq_show(struct seq_file *seq, void *v) + + if (v == SEQ_START_TOKEN) + seq_puts(seq, "Type Device Function\n"); +- else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { ++ else if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) && ++ (!pt->dev || net_eq(dev_net(pt->dev), seq_file_net(seq)))) { + if (pt->type == htons(ETH_P_ALL)) + seq_puts(seq, "ALL "); + else +diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c +index f78097aa403a8..6ef035494f30d 100644 +--- a/net/packet/af_packet.c ++++ b/net/packet/af_packet.c +@@ -1735,6 +1735,7 @@ static int fanout_add(struct sock *sk, struct fanout_args *args) + match->prot_hook.dev = po->prot_hook.dev; + match->prot_hook.func = packet_rcv_fanout; + match->prot_hook.af_packet_priv = match; ++ match->prot_hook.af_packet_net = read_pnet(&match->net); + match->prot_hook.id_match = match_fanout_group; + match->max_num_members = args->max_num_members; + list_add(&match->list, &fanout_list); +@@ -3323,6 +3324,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, + po->prot_hook.func = packet_rcv_spkt; + + po->prot_hook.af_packet_priv = sk; ++ po->prot_hook.af_packet_net = sock_net(sk); + + if (proto) { + po->prot_hook.type = proto; +-- +2.34.1 + diff --git a/queue-5.10/net-hns3-handle-empty-unknown-interrupt-for-vf.patch-6323 b/queue-5.10/net-hns3-handle-empty-unknown-interrupt-for-vf.patch-6323 new file mode 100644 index 00000000000..45c4d61febc --- /dev/null +++ b/queue-5.10/net-hns3-handle-empty-unknown-interrupt-for-vf.patch-6323 @@ -0,0 +1,41 @@ +From bbf7cc6743efc929d1b111a22ed42825379223b5 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 25 Jan 2022 15:03:12 +0800 +Subject: net: hns3: handle empty unknown interrupt for VF + +From: Yufeng Mo + +[ Upstream commit 2f61353cd2f789a4229b6f5c1c24a40a613357bb ] + +Since some interrupt states may be cleared by hardware, the driver +may receive an empty interrupt. Currently, the VF driver directly +disables the vector0 interrupt in this case. As a result, the VF +is unavailable. Therefore, the vector0 interrupt should be enabled +in this case. + +Fixes: b90fcc5bd904 ("net: hns3: add reset handling for VF when doing Core/Global/IMP reset") +Signed-off-by: Yufeng Mo +Signed-off-by: Guangbin Huang +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 3 +-- + 1 file changed, 1 insertion(+), 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 6e7da1dc2e8c3..d6580e942724d 100644 +--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c ++++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +@@ -2382,8 +2382,7 @@ static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data) + break; + } + +- if (event_cause != HCLGEVF_VECTOR0_EVENT_OTHER) +- hclgevf_enable_vector(&hdev->misc_vector, true); ++ hclgevf_enable_vector(&hdev->misc_vector, true); + + return IRQ_HANDLED; + } +-- +2.34.1 + diff --git a/queue-5.10/net-ipv4-fix-the-warning-for-dereference.patch-3212 b/queue-5.10/net-ipv4-fix-the-warning-for-dereference.patch-3212 new file mode 100644 index 00000000000..408d379b45f --- /dev/null +++ b/queue-5.10/net-ipv4-fix-the-warning-for-dereference.patch-3212 @@ -0,0 +1,46 @@ +From b240adf93f16b55cc86905b2530e399eb246263f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 30 Aug 2021 17:16:40 +0800 +Subject: net: ipv4: Fix the warning for dereference + +From: Yajun Deng + +[ Upstream commit 1b9fbe813016b08e08b22ddba4ddbf9cb1b04b00 ] + +Add a if statements to avoid the warning. + +Dan Carpenter report: +The patch faf482ca196a: "net: ipv4: Move ip_options_fragment() out of +loop" from Aug 23, 2021, leads to the following Smatch complaint: + + net/ipv4/ip_output.c:833 ip_do_fragment() + warn: variable dereferenced before check 'iter.frag' (see line 828) + +Reported-by: Dan Carpenter +Fixes: faf482ca196a ("net: ipv4: Move ip_options_fragment() out of loop") +Link: https://lore.kernel.org/netdev/20210830073802.GR7722@kadam/T/#t +Signed-off-by: Yajun Deng +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ipv4/ip_output.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c +index fb91a466b2d34..e77afaecc9818 100644 +--- a/net/ipv4/ip_output.c ++++ b/net/ipv4/ip_output.c +@@ -833,7 +833,9 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + + /* Everything is OK. Generate! */ + ip_fraglist_init(skb, iph, hlen, &iter); +- ip_options_fragment(iter.frag); ++ ++ if (iter.frag) ++ ip_options_fragment(iter.frag); + + for (;;) { + /* Prepare header of the next frame, +-- +2.34.1 + diff --git a/queue-5.10/net-ipv4-move-ip_options_fragment-out-of-loop.patch-9656 b/queue-5.10/net-ipv4-move-ip_options_fragment-out-of-loop.patch-9656 new file mode 100644 index 00000000000..53b1b011b48 --- /dev/null +++ b/queue-5.10/net-ipv4-move-ip_options_fragment-out-of-loop.patch-9656 @@ -0,0 +1,79 @@ +From 06e855befb7001de669475477eed297a350947a0 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 23 Aug 2021 11:17:59 +0800 +Subject: net: ipv4: Move ip_options_fragment() out of loop + +From: Yajun Deng + +[ Upstream commit faf482ca196a5b16007190529b3b2dd32ab3f761 ] + +The ip_options_fragment() only called when iter->offset is equal to zero, +so move it out of loop, and inline 'Copy the flags to each fragment.' +As also, remove the unused parameter in ip_frag_ipcb(). + +Signed-off-by: Yajun Deng +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ipv4/ip_output.c | 19 ++++--------------- + 1 file changed, 4 insertions(+), 15 deletions(-) + +diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c +index 10d4cde31c6bf..fb91a466b2d34 100644 +--- a/net/ipv4/ip_output.c ++++ b/net/ipv4/ip_output.c +@@ -614,18 +614,6 @@ void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, + } + EXPORT_SYMBOL(ip_fraglist_init); + +-static void ip_fraglist_ipcb_prepare(struct sk_buff *skb, +- struct ip_fraglist_iter *iter) +-{ +- struct sk_buff *to = iter->frag; +- +- /* Copy the flags to each fragment. */ +- IPCB(to)->flags = IPCB(skb)->flags; +- +- if (iter->offset == 0) +- ip_options_fragment(to); +-} +- + void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) + { + unsigned int hlen = iter->hlen; +@@ -671,7 +659,7 @@ void ip_frag_init(struct sk_buff *skb, unsigned int hlen, + EXPORT_SYMBOL(ip_frag_init); + + static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to, +- bool first_frag, struct ip_frag_state *state) ++ bool first_frag) + { + /* Copy the flags to each fragment. */ + IPCB(to)->flags = IPCB(from)->flags; +@@ -845,12 +833,13 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + + /* Everything is OK. Generate! */ + ip_fraglist_init(skb, iph, hlen, &iter); ++ ip_options_fragment(iter.frag); + + for (;;) { + /* Prepare header of the next frame, + * before previous one went down. */ + if (iter.frag) { +- ip_fraglist_ipcb_prepare(skb, &iter); ++ IPCB(iter.frag)->flags = IPCB(skb)->flags; + ip_fraglist_prepare(skb, &iter); + } + +@@ -905,7 +894,7 @@ slow_path: + err = PTR_ERR(skb2); + goto fail; + } +- ip_frag_ipcb(skb, skb2, first_frag, &state); ++ ip_frag_ipcb(skb, skb2, first_frag); + + /* + * Put this fragment into the sending queue. +-- +2.34.1 + diff --git a/queue-5.10/net-phy-broadcom-hook-up-soft_reset-for-bcm54616s.patch-27858 b/queue-5.10/net-phy-broadcom-hook-up-soft_reset-for-bcm54616s.patch-27858 new file mode 100644 index 00000000000..2dfed6461a0 --- /dev/null +++ b/queue-5.10/net-phy-broadcom-hook-up-soft_reset-for-bcm54616s.patch-27858 @@ -0,0 +1,61 @@ +From 760c92a722269d6634c197cd1875be760cba041a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 18 Jan 2022 15:52:43 -0600 +Subject: net: phy: broadcom: hook up soft_reset for BCM54616S + +From: Robert Hancock + +[ Upstream commit d15c7e875d44367005370e6a82e8f3a382a04f9b ] + +A problem was encountered with the Bel-Fuse 1GBT-SFP05 SFP module (which +is a 1 Gbps copper module operating in SGMII mode with an internal +BCM54616S PHY device) using the Xilinx AXI Ethernet MAC core, where the +module would work properly on the initial insertion or boot of the +device, but after the device was rebooted, the link would either only +come up at 100 Mbps speeds or go up and down erratically. + +I found no meaningful changes in the PHY configuration registers between +the working and non-working boots, but the status registers seemed to +have a lot of error indications set on the SERDES side of the device on +the non-working boot. I suspect the problem is that whatever happens on +the SGMII link when the device is rebooted and the FPGA logic gets +reloaded ends up putting the module's onboard PHY into a bad state. + +Since commit 6e2d85ec0559 ("net: phy: Stop with excessive soft reset") +the genphy_soft_reset call is not made automatically by the PHY core +unless the callback is explicitly specified in the driver structure. For +most of these Broadcom devices, there is probably a hardware reset that +gets asserted to reset the PHY during boot, however for SFP modules +(where the BCM54616S is commonly found) no such reset line exists, so if +the board keeps the SFP cage powered up across a reboot, it will end up +with no reset occurring during reboots. + +Hook up the genphy_soft_reset callback for BCM54616S to ensure that a +PHY reset is performed before the device is initialized. This appears to +fix the issue with erratic operation after a reboot with this SFP +module. + +Fixes: 6e2d85ec0559 ("net: phy: Stop with excessive soft reset") +Signed-off-by: Robert Hancock +Reviewed-by: Florian Fainelli +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/phy/broadcom.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c +index dbed15dc0fe77..644861366d544 100644 +--- a/drivers/net/phy/broadcom.c ++++ b/drivers/net/phy/broadcom.c +@@ -789,6 +789,7 @@ static struct phy_driver broadcom_drivers[] = { + .phy_id_mask = 0xfffffff0, + .name = "Broadcom BCM54616S", + /* PHY_GBIT_FEATURES */ ++ .soft_reset = genphy_soft_reset, + .config_init = bcm54xx_config_init, + .config_aneg = bcm54616s_config_aneg, + .ack_interrupt = bcm_phy_ack_intr, +-- +2.34.1 + diff --git a/queue-5.10/net-procfs-show-net-devices-bound-packet-types.patch-14776 b/queue-5.10/net-procfs-show-net-devices-bound-packet-types.patch-14776 new file mode 100644 index 00000000000..33f4915baa9 --- /dev/null +++ b/queue-5.10/net-procfs-show-net-devices-bound-packet-types.patch-14776 @@ -0,0 +1,117 @@ +From 373d87a41f08746873bd4517db26fb94442db7ab Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 21 Jan 2022 17:15:31 +0800 +Subject: net-procfs: show net devices bound packet types + +From: Jianguo Wu + +[ Upstream commit 1d10f8a1f40b965d449e8f2d5ed7b96a7c138b77 ] + +After commit:7866a621043f ("dev: add per net_device packet type chains"), +we can not get packet types that are bound to a specified net device by +/proc/net/ptype, this patch fix the regression. + +Run "tcpdump -i ens192 udp -nns0" Before and after apply this patch: + +Before: + [root@localhost ~]# cat /proc/net/ptype + Type Device Function + 0800 ip_rcv + 0806 arp_rcv + 86dd ipv6_rcv + +After: + [root@localhost ~]# cat /proc/net/ptype + Type Device Function + ALL ens192 tpacket_rcv + 0800 ip_rcv + 0806 arp_rcv + 86dd ipv6_rcv + +v1 -> v2: + - fix the regression rather than adding new /proc API as + suggested by Stephen Hemminger. + +Fixes: 7866a621043f ("dev: add per net_device packet type chains") +Signed-off-by: Jianguo Wu +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/core/net-procfs.c | 35 ++++++++++++++++++++++++++++++++--- + 1 file changed, 32 insertions(+), 3 deletions(-) + +diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c +index e12c67f9492ba..eadb696360b48 100644 +--- a/net/core/net-procfs.c ++++ b/net/core/net-procfs.c +@@ -193,12 +193,23 @@ static const struct seq_operations softnet_seq_ops = { + .show = softnet_seq_show, + }; + +-static void *ptype_get_idx(loff_t pos) ++static void *ptype_get_idx(struct seq_file *seq, loff_t pos) + { ++ struct list_head *ptype_list = NULL; + struct packet_type *pt = NULL; ++ struct net_device *dev; + loff_t i = 0; + int t; + ++ for_each_netdev_rcu(seq_file_net(seq), dev) { ++ ptype_list = &dev->ptype_all; ++ list_for_each_entry_rcu(pt, ptype_list, list) { ++ if (i == pos) ++ return pt; ++ ++i; ++ } ++ } ++ + list_for_each_entry_rcu(pt, &ptype_all, list) { + if (i == pos) + return pt; +@@ -219,22 +230,40 @@ static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) + { + rcu_read_lock(); +- return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN; ++ return *pos ? ptype_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; + } + + static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) + { ++ struct net_device *dev; + struct packet_type *pt; + struct list_head *nxt; + int hash; + + ++*pos; + if (v == SEQ_START_TOKEN) +- return ptype_get_idx(0); ++ return ptype_get_idx(seq, 0); + + pt = v; + nxt = pt->list.next; ++ if (pt->dev) { ++ if (nxt != &pt->dev->ptype_all) ++ goto found; ++ ++ dev = pt->dev; ++ for_each_netdev_continue_rcu(seq_file_net(seq), dev) { ++ if (!list_empty(&dev->ptype_all)) { ++ nxt = dev->ptype_all.next; ++ goto found; ++ } ++ } ++ ++ nxt = ptype_all.next; ++ goto ptype_all; ++ } ++ + if (pt->type == htons(ETH_P_ALL)) { ++ptype_all: + if (nxt != &ptype_all) + goto found; + hash = 0; +-- +2.34.1 + diff --git a/queue-5.10/netfilter-conntrack-don-t-increment-invalid-counter-.patch-23162 b/queue-5.10/netfilter-conntrack-don-t-increment-invalid-counter-.patch-23162 new file mode 100644 index 00000000000..89f287a2ede --- /dev/null +++ b/queue-5.10/netfilter-conntrack-don-t-increment-invalid-counter-.patch-23162 @@ -0,0 +1,51 @@ +From 275b23b8b6de09c1687ae29de9b893edd55756b7 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 13 Jan 2022 21:37:58 +0100 +Subject: netfilter: conntrack: don't increment invalid counter on NF_REPEAT + +From: Florian Westphal + +[ Upstream commit 830af2eba40327abec64325a5b08b1e85c37a2e0 ] + +The packet isn't invalid, REPEAT means we're trying again after cleaning +out a stale connection, e.g. via tcp tracker. + +This caused increases of invalid stat counter in a test case involving +frequent connection reuse, even though no packet is actually invalid. + +Fixes: 56a62e2218f5 ("netfilter: conntrack: fix NF_REPEAT handling") +Signed-off-by: Florian Westphal +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + net/netfilter/nf_conntrack_core.c | 8 +++++--- + 1 file changed, 5 insertions(+), 3 deletions(-) + +diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c +index f4cf26b606f92..8369af0c50eab 100644 +--- a/net/netfilter/nf_conntrack_core.c ++++ b/net/netfilter/nf_conntrack_core.c +@@ -1832,15 +1832,17 @@ repeat: + pr_debug("nf_conntrack_in: Can't track with proto module\n"); + nf_conntrack_put(&ct->ct_general); + skb->_nfct = 0; +- NF_CT_STAT_INC_ATOMIC(state->net, invalid); +- if (ret == -NF_DROP) +- NF_CT_STAT_INC_ATOMIC(state->net, drop); + /* Special case: TCP tracker reports an attempt to reopen a + * closed/aborted connection. We have to go back and create a + * fresh conntrack. + */ + if (ret == -NF_REPEAT) + goto repeat; ++ ++ NF_CT_STAT_INC_ATOMIC(state->net, invalid); ++ if (ret == -NF_DROP) ++ NF_CT_STAT_INC_ATOMIC(state->net, drop); ++ + ret = -ret; + goto out; + } +-- +2.34.1 + diff --git a/queue-5.10/nfs-ensure-the-server-has-an-up-to-date-ctime-before.patch-15600 b/queue-5.10/nfs-ensure-the-server-has-an-up-to-date-ctime-before.patch-15600 new file mode 100644 index 00000000000..eefe5cd6d27 --- /dev/null +++ b/queue-5.10/nfs-ensure-the-server-has-an-up-to-date-ctime-before.patch-15600 @@ -0,0 +1,37 @@ +From 532d017a99c55d257a1de01f1fbf63f5f8bec971 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 15 Dec 2021 16:38:15 -0500 +Subject: NFS: Ensure the server has an up to date ctime before hardlinking + +From: Trond Myklebust + +[ Upstream commit 204975036b34f55237bc44c8a302a88468ef21b5 ] + +Creating a hard link is required by POSIX to update the file ctime, so +ensure that the file data is synced to disk so that we don't clobber the +updated ctime by writing back after creating the hard link. + +Fixes: 9f7682728728 ("NFS: Move the delegation return down into nfs4_proc_link()") +Signed-off-by: Trond Myklebust +Signed-off-by: Anna Schumaker +Signed-off-by: Sasha Levin +--- + fs/nfs/dir.c | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c +index 8b963c72dd3b1..3db80236020f9 100644 +--- a/fs/nfs/dir.c ++++ b/fs/nfs/dir.c +@@ -2174,6 +2174,8 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) + + trace_nfs_link_enter(inode, dir, dentry); + d_drop(dentry); ++ if (S_ISREG(inode->i_mode)) ++ nfs_sync_inode(inode); + error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); + if (error == 0) { + ihold(inode); +-- +2.34.1 + diff --git a/queue-5.10/nfs-ensure-the-server-has-an-up-to-date-ctime-before.patch-8657 b/queue-5.10/nfs-ensure-the-server-has-an-up-to-date-ctime-before.patch-8657 new file mode 100644 index 00000000000..d55b5ab3430 --- /dev/null +++ b/queue-5.10/nfs-ensure-the-server-has-an-up-to-date-ctime-before.patch-8657 @@ -0,0 +1,37 @@ +From f3682bc090771b53947502640ba9ba1240d6a5f0 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 15 Dec 2021 16:38:16 -0500 +Subject: NFS: Ensure the server has an up to date ctime before renaming + +From: Trond Myklebust + +[ Upstream commit 6ff9d99bb88faebf134ca668842349d9718e5464 ] + +Renaming a file is required by POSIX to update the file ctime, so +ensure that the file data is synced to disk so that we don't clobber the +updated ctime by writing back after creating the hard link. + +Fixes: f2c2c552f119 ("NFS: Move delegation recall into the NFSv4 callback for rename_setup()") +Signed-off-by: Trond Myklebust +Signed-off-by: Anna Schumaker +Signed-off-by: Sasha Levin +--- + fs/nfs/dir.c | 2 ++ + 1 file changed, 2 insertions(+) + +diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c +index 3db80236020f9..7d7fab95b74bb 100644 +--- a/fs/nfs/dir.c ++++ b/fs/nfs/dir.c +@@ -2264,6 +2264,8 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, + } + } + ++ if (S_ISREG(old_inode->i_mode)) ++ nfs_sync_inode(old_inode); + task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, NULL); + if (IS_ERR(task)) { + error = PTR_ERR(task); +-- +2.34.1 + diff --git a/queue-5.10/nfsv4-handle-case-where-the-lookup-of-a-directory-fa.patch-15449 b/queue-5.10/nfsv4-handle-case-where-the-lookup-of-a-directory-fa.patch-15449 new file mode 100644 index 00000000000..7ff879eca37 --- /dev/null +++ b/queue-5.10/nfsv4-handle-case-where-the-lookup-of-a-directory-fa.patch-15449 @@ -0,0 +1,52 @@ +From c3673ede6efc1d933efec034c81d8520ff60e1ce Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 6 Jan 2022 18:24:02 -0500 +Subject: NFSv4: Handle case where the lookup of a directory fails + +From: Trond Myklebust + +[ Upstream commit ac795161c93699d600db16c1a8cc23a65a1eceaf ] + +If the application sets the O_DIRECTORY flag, and tries to open a +regular file, nfs_atomic_open() will punt to doing a regular lookup. +If the server then returns a regular file, we will happily return a +file descriptor with uninitialised open state. + +The fix is to return the expected ENOTDIR error in these cases. + +Reported-by: Lyu Tao +Fixes: 0dd2b474d0b6 ("nfs: implement i_op->atomic_open()") +Signed-off-by: Trond Myklebust +Signed-off-by: Anna Schumaker +Signed-off-by: Sasha Levin +--- + fs/nfs/dir.c | 13 +++++++++++++ + 1 file changed, 13 insertions(+) + +diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c +index 7d7fab95b74bb..4ef392c42ec8a 100644 +--- a/fs/nfs/dir.c ++++ b/fs/nfs/dir.c +@@ -1777,6 +1777,19 @@ out: + + no_open: + res = nfs_lookup(dir, dentry, lookup_flags); ++ if (!res) { ++ inode = d_inode(dentry); ++ if ((lookup_flags & LOOKUP_DIRECTORY) && inode && ++ !S_ISDIR(inode->i_mode)) ++ res = ERR_PTR(-ENOTDIR); ++ } else if (!IS_ERR(res)) { ++ inode = d_inode(res); ++ if ((lookup_flags & LOOKUP_DIRECTORY) && inode && ++ !S_ISDIR(inode->i_mode)) { ++ dput(res); ++ res = ERR_PTR(-ENOTDIR); ++ } ++ } + if (switched) { + d_lookup_done(dentry); + if (!res) +-- +2.34.1 + diff --git a/queue-5.10/nfsv4-nfs_atomic_open-can-race-when-looking-up-a-non.patch-27002 b/queue-5.10/nfsv4-nfs_atomic_open-can-race-when-looking-up-a-non.patch-27002 new file mode 100644 index 00000000000..91f1ef95ec0 --- /dev/null +++ b/queue-5.10/nfsv4-nfs_atomic_open-can-race-when-looking-up-a-non.patch-27002 @@ -0,0 +1,45 @@ +From b5f93faf85c022030412ee6bfb928b60025634dd Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 6 Jan 2022 18:24:03 -0500 +Subject: NFSv4: nfs_atomic_open() can race when looking up a non-regular file + +From: Trond Myklebust + +[ Upstream commit 1751fc1db36f6f411709e143d5393f92d12137a9 ] + +If the file type changes back to being a regular file on the server +between the failed OPEN and our LOOKUP, then we need to re-run the OPEN. + +Fixes: 0dd2b474d0b6 ("nfs: implement i_op->atomic_open()") +Signed-off-by: Trond Myklebust +Signed-off-by: Anna Schumaker +Signed-off-by: Sasha Levin +--- + fs/nfs/dir.c | 5 +++++ + 1 file changed, 5 insertions(+) + +diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c +index 4ef392c42ec8a..a23b7a5dec9ee 100644 +--- a/fs/nfs/dir.c ++++ b/fs/nfs/dir.c +@@ -1782,12 +1782,17 @@ no_open: + if ((lookup_flags & LOOKUP_DIRECTORY) && inode && + !S_ISDIR(inode->i_mode)) + res = ERR_PTR(-ENOTDIR); ++ else if (inode && S_ISREG(inode->i_mode)) ++ res = ERR_PTR(-EOPENSTALE); + } else if (!IS_ERR(res)) { + inode = d_inode(res); + if ((lookup_flags & LOOKUP_DIRECTORY) && inode && + !S_ISDIR(inode->i_mode)) { + dput(res); + res = ERR_PTR(-ENOTDIR); ++ } else if (inode && S_ISREG(inode->i_mode)) { ++ dput(res); ++ res = ERR_PTR(-EOPENSTALE); + } + } + if (switched) { +-- +2.34.1 + diff --git a/queue-5.10/octeontx2-pf-forward-error-codes-to-vf.patch-28837 b/queue-5.10/octeontx2-pf-forward-error-codes-to-vf.patch-28837 new file mode 100644 index 00000000000..1204c292b95 --- /dev/null +++ b/queue-5.10/octeontx2-pf-forward-error-codes-to-vf.patch-28837 @@ -0,0 +1,48 @@ +From 6c5b84850ce3bcedc4ed138445f67f16fca1f2eb Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 21 Jan 2022 12:04:46 +0530 +Subject: octeontx2-pf: Forward error codes to VF + +From: Subbaraya Sundeep + +[ Upstream commit a8db854be28622a2477cb21cdf7f829adbb2c42d ] + +PF forwards its VF messages to AF and corresponding +replies from AF to VF. AF sets proper error code in the +replies after processing message requests. Currently PF +checks the error codes in replies and sends invalid +message to VF. This way VF lacks the information of +error code set by AF for its messages. This patch +changes that such that PF simply forwards AF replies +so that VF can handle error codes. + +Fixes: d424b6c02415 ("octeontx2-pf: Enable SRIOV and added VF mbox handling") +Signed-off-by: Subbaraya Sundeep +Signed-off-by: Sunil Goutham +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 7 ++++++- + 1 file changed, 6 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +index 044a5b1196acb..161174be51c31 100644 +--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c ++++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +@@ -386,7 +386,12 @@ static int otx2_forward_vf_mbox_msgs(struct otx2_nic *pf, + dst_mdev->msg_size = mbox_hdr->msg_size; + dst_mdev->num_msgs = num_msgs; + err = otx2_sync_mbox_msg(dst_mbox); +- if (err) { ++ /* Error code -EIO indicate there is a communication failure ++ * to the AF. Rest of the error codes indicate that AF processed ++ * VF messages and set the error codes in response messages ++ * (if any) so simply forward responses to VF. ++ */ ++ if (err == -EIO) { + dev_warn(pf->dev, + "AF not responding to VF%d messages\n", vf); + /* restore PF mbase and exit */ +-- +2.34.1 + diff --git a/queue-5.10/perf-fix-perf_event_read_local-time.patch-26974 b/queue-5.10/perf-fix-perf_event_read_local-time.patch-26974 new file mode 100644 index 00000000000..204871a047e --- /dev/null +++ b/queue-5.10/perf-fix-perf_event_read_local-time.patch-26974 @@ -0,0 +1,575 @@ +From c8666f0b22c9cb634d82b3f049c7ed4be9176f58 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 20 Dec 2021 13:19:52 +0100 +Subject: perf: Fix perf_event_read_local() time + +From: Peter Zijlstra + +[ Upstream commit 09f5e7dc7ad705289e1b1ec065439aa3c42951c4 ] + +Time readers that cannot take locks (due to NMI etc..) currently make +use of perf_event::shadow_ctx_time, which, for that event gives: + + time' = now + (time - timestamp) + +or, alternatively arranged: + + time' = time + (now - timestamp) + +IOW, the progression of time since the last time the shadow_ctx_time +was updated. + +There's problems with this: + + A) the shadow_ctx_time is per-event, even though the ctx_time it + reflects is obviously per context. The direct concequence of this + is that the context needs to iterate all events all the time to + keep the shadow_ctx_time in sync. + + B) even with the prior point, the context itself might not be active + meaning its time should not advance to begin with. + + C) shadow_ctx_time isn't consistently updated when ctx_time is + +There are 3 users of this stuff, that suffer differently from this: + + - calc_timer_values() + - perf_output_read() + - perf_event_update_userpage() /* A */ + + - perf_event_read_local() /* A,B */ + +In particular, perf_output_read() doesn't suffer at all, because it's +sample driven and hence only relevant when the event is actually +running. + +This same was supposed to be true for perf_event_update_userpage(), +after all self-monitoring implies the context is active *HOWEVER*, as +per commit f79256532682 ("perf/core: fix userpage->time_enabled of +inactive events") this goes wrong when combined with counter +overcommit, in that case those events that do not get scheduled when +the context becomes active (task events typically) miss out on the +EVENT_TIME update and ENABLED time is inflated (for a little while) +with the time the context was inactive. Once the event gets rotated +in, this gets corrected, leading to a non-monotonic timeflow. + +perf_event_read_local() made things even worse, it can request time at +any point, suffering all the problems perf_event_update_userpage() +does and more. Because while perf_event_update_userpage() is limited +by the context being active, perf_event_read_local() users have no +such constraint. + +Therefore, completely overhaul things and do away with +perf_event::shadow_ctx_time. Instead have regular context time updates +keep track of this offset directly and provide perf_event_time_now() +to complement perf_event_time(). + +perf_event_time_now() will, in adition to being context wide, also +take into account if the context is active. For inactive context, it +will not advance time. + +This latter property means the cgroup perf_cgroup_info context needs +to grow addition state to track this. + +Additionally, since all this is strictly per-cpu, we can use barrier() +to order context activity vs context time. + +Fixes: 7d9285e82db5 ("perf/bpf: Extend the perf_event_read_local() interface, a.k.a. "bpf: perf event change needed for subsequent bpf helpers"") +Signed-off-by: Peter Zijlstra (Intel) +Tested-by: Song Liu +Tested-by: Namhyung Kim +Link: https://lkml.kernel.org/r/YcB06DasOBtU0b00@hirez.programming.kicks-ass.net +Signed-off-by: Sasha Levin +--- + include/linux/perf_event.h | 15 +-- + kernel/events/core.c | 246 ++++++++++++++++++++++--------------- + 2 files changed, 149 insertions(+), 112 deletions(-) + +diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h +index c94551091dad3..67a50c78232fe 100644 +--- a/include/linux/perf_event.h ++++ b/include/linux/perf_event.h +@@ -678,18 +678,6 @@ struct perf_event { + u64 total_time_running; + u64 tstamp; + +- /* +- * timestamp shadows the actual context timing but it can +- * be safely used in NMI interrupt context. It reflects the +- * context time as it was when the event was last scheduled in, +- * or when ctx_sched_in failed to schedule the event because we +- * run out of PMC. +- * +- * ctx_time already accounts for ctx->timestamp. Therefore to +- * compute ctx_time for a sample, simply add perf_clock(). +- */ +- u64 shadow_ctx_time; +- + struct perf_event_attr attr; + u16 header_size; + u16 id_header_size; +@@ -834,6 +822,7 @@ struct perf_event_context { + */ + u64 time; + u64 timestamp; ++ u64 timeoffset; + + /* + * These fields let us detect when two contexts have both +@@ -916,6 +905,8 @@ struct bpf_perf_event_data_kern { + struct perf_cgroup_info { + u64 time; + u64 timestamp; ++ u64 timeoffset; ++ int active; + }; + + struct perf_cgroup { +diff --git a/kernel/events/core.c b/kernel/events/core.c +index 8dc7c4d12b789..c6493f7e02359 100644 +--- a/kernel/events/core.c ++++ b/kernel/events/core.c +@@ -673,6 +673,23 @@ perf_event_set_state(struct perf_event *event, enum perf_event_state state) + WRITE_ONCE(event->state, state); + } + ++/* ++ * UP store-release, load-acquire ++ */ ++ ++#define __store_release(ptr, val) \ ++do { \ ++ barrier(); \ ++ WRITE_ONCE(*(ptr), (val)); \ ++} while (0) ++ ++#define __load_acquire(ptr) \ ++({ \ ++ __unqual_scalar_typeof(*(ptr)) ___p = READ_ONCE(*(ptr)); \ ++ barrier(); \ ++ ___p; \ ++}) ++ + #ifdef CONFIG_CGROUP_PERF + + static inline bool +@@ -718,34 +735,51 @@ static inline u64 perf_cgroup_event_time(struct perf_event *event) + return t->time; + } + +-static inline void __update_cgrp_time(struct perf_cgroup *cgrp) ++static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now) + { +- struct perf_cgroup_info *info; +- u64 now; +- +- now = perf_clock(); ++ struct perf_cgroup_info *t; + +- info = this_cpu_ptr(cgrp->info); ++ t = per_cpu_ptr(event->cgrp->info, event->cpu); ++ if (!__load_acquire(&t->active)) ++ return t->time; ++ now += READ_ONCE(t->timeoffset); ++ return now; ++} + +- info->time += now - info->timestamp; ++static inline void __update_cgrp_time(struct perf_cgroup_info *info, u64 now, bool adv) ++{ ++ if (adv) ++ info->time += now - info->timestamp; + info->timestamp = now; ++ /* ++ * see update_context_time() ++ */ ++ WRITE_ONCE(info->timeoffset, info->time - info->timestamp); + } + +-static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) ++static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, bool final) + { + struct perf_cgroup *cgrp = cpuctx->cgrp; + struct cgroup_subsys_state *css; ++ struct perf_cgroup_info *info; + + if (cgrp) { ++ u64 now = perf_clock(); ++ + for (css = &cgrp->css; css; css = css->parent) { + cgrp = container_of(css, struct perf_cgroup, css); +- __update_cgrp_time(cgrp); ++ info = this_cpu_ptr(cgrp->info); ++ ++ __update_cgrp_time(info, now, true); ++ if (final) ++ __store_release(&info->active, 0); + } + } + } + + static inline void update_cgrp_time_from_event(struct perf_event *event) + { ++ struct perf_cgroup_info *info; + struct perf_cgroup *cgrp; + + /* +@@ -759,8 +793,10 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) + /* + * Do not update time when cgroup is not active + */ +- if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) +- __update_cgrp_time(event->cgrp); ++ if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) { ++ info = this_cpu_ptr(event->cgrp->info); ++ __update_cgrp_time(info, perf_clock(), true); ++ } + } + + static inline void +@@ -784,7 +820,8 @@ perf_cgroup_set_timestamp(struct task_struct *task, + for (css = &cgrp->css; css; css = css->parent) { + cgrp = container_of(css, struct perf_cgroup, css); + info = this_cpu_ptr(cgrp->info); +- info->timestamp = ctx->timestamp; ++ __update_cgrp_time(info, ctx->timestamp, false); ++ __store_release(&info->active, 1); + } + } + +@@ -980,14 +1017,6 @@ out: + return ret; + } + +-static inline void +-perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) +-{ +- struct perf_cgroup_info *t; +- t = per_cpu_ptr(event->cgrp->info, event->cpu); +- event->shadow_ctx_time = now - t->timestamp; +-} +- + static inline void + perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ctx) + { +@@ -1065,7 +1094,8 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) + { + } + +-static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) ++static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, ++ bool final) + { + } + +@@ -1097,12 +1127,12 @@ perf_cgroup_switch(struct task_struct *task, struct task_struct *next) + { + } + +-static inline void +-perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) ++static inline u64 perf_cgroup_event_time(struct perf_event *event) + { ++ return 0; + } + +-static inline u64 perf_cgroup_event_time(struct perf_event *event) ++static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now) + { + return 0; + } +@@ -1524,22 +1554,59 @@ static void perf_unpin_context(struct perf_event_context *ctx) + /* + * Update the record of the current time in a context. + */ +-static void update_context_time(struct perf_event_context *ctx) ++static void __update_context_time(struct perf_event_context *ctx, bool adv) + { + u64 now = perf_clock(); + +- ctx->time += now - ctx->timestamp; ++ if (adv) ++ ctx->time += now - ctx->timestamp; + ctx->timestamp = now; ++ ++ /* ++ * The above: time' = time + (now - timestamp), can be re-arranged ++ * into: time` = now + (time - timestamp), which gives a single value ++ * offset to compute future time without locks on. ++ * ++ * See perf_event_time_now(), which can be used from NMI context where ++ * it's (obviously) not possible to acquire ctx->lock in order to read ++ * both the above values in a consistent manner. ++ */ ++ WRITE_ONCE(ctx->timeoffset, ctx->time - ctx->timestamp); ++} ++ ++static void update_context_time(struct perf_event_context *ctx) ++{ ++ __update_context_time(ctx, true); + } + + static u64 perf_event_time(struct perf_event *event) + { + struct perf_event_context *ctx = event->ctx; + ++ if (unlikely(!ctx)) ++ return 0; ++ + if (is_cgroup_event(event)) + return perf_cgroup_event_time(event); + +- return ctx ? ctx->time : 0; ++ return ctx->time; ++} ++ ++static u64 perf_event_time_now(struct perf_event *event, u64 now) ++{ ++ struct perf_event_context *ctx = event->ctx; ++ ++ if (unlikely(!ctx)) ++ return 0; ++ ++ if (is_cgroup_event(event)) ++ return perf_cgroup_event_time_now(event, now); ++ ++ if (!(__load_acquire(&ctx->is_active) & EVENT_TIME)) ++ return ctx->time; ++ ++ now += READ_ONCE(ctx->timeoffset); ++ return now; + } + + static enum event_type_t get_event_type(struct perf_event *event) +@@ -2333,7 +2400,7 @@ __perf_remove_from_context(struct perf_event *event, + + if (ctx->is_active & EVENT_TIME) { + update_context_time(ctx); +- update_cgrp_time_from_cpuctx(cpuctx); ++ update_cgrp_time_from_cpuctx(cpuctx, false); + } + + event_sched_out(event, cpuctx, ctx); +@@ -2342,6 +2409,9 @@ __perf_remove_from_context(struct perf_event *event, + list_del_event(event, ctx); + + if (!ctx->nr_events && ctx->is_active) { ++ if (ctx == &cpuctx->ctx) ++ update_cgrp_time_from_cpuctx(cpuctx, true); ++ + ctx->is_active = 0; + ctx->rotate_necessary = 0; + if (ctx->task) { +@@ -2467,40 +2537,6 @@ void perf_event_disable_inatomic(struct perf_event *event) + irq_work_queue(&event->pending); + } + +-static void perf_set_shadow_time(struct perf_event *event, +- struct perf_event_context *ctx) +-{ +- /* +- * use the correct time source for the time snapshot +- * +- * We could get by without this by leveraging the +- * fact that to get to this function, the caller +- * has most likely already called update_context_time() +- * and update_cgrp_time_xx() and thus both timestamp +- * are identical (or very close). Given that tstamp is, +- * already adjusted for cgroup, we could say that: +- * tstamp - ctx->timestamp +- * is equivalent to +- * tstamp - cgrp->timestamp. +- * +- * Then, in perf_output_read(), the calculation would +- * work with no changes because: +- * - event is guaranteed scheduled in +- * - no scheduled out in between +- * - thus the timestamp would be the same +- * +- * But this is a bit hairy. +- * +- * So instead, we have an explicit cgroup call to remain +- * within the time source all along. We believe it +- * is cleaner and simpler to understand. +- */ +- if (is_cgroup_event(event)) +- perf_cgroup_set_shadow_time(event, event->tstamp); +- else +- event->shadow_ctx_time = event->tstamp - ctx->timestamp; +-} +- + #define MAX_INTERRUPTS (~0ULL) + + static void perf_log_throttle(struct perf_event *event, int enable); +@@ -2541,8 +2577,6 @@ event_sched_in(struct perf_event *event, + + perf_pmu_disable(event->pmu); + +- perf_set_shadow_time(event, ctx); +- + perf_log_itrace_start(event); + + if (event->pmu->add(event, PERF_EF_START)) { +@@ -3216,16 +3250,6 @@ static void ctx_sched_out(struct perf_event_context *ctx, + return; + } + +- ctx->is_active &= ~event_type; +- if (!(ctx->is_active & EVENT_ALL)) +- ctx->is_active = 0; +- +- if (ctx->task) { +- WARN_ON_ONCE(cpuctx->task_ctx != ctx); +- if (!ctx->is_active) +- cpuctx->task_ctx = NULL; +- } +- + /* + * Always update time if it was set; not only when it changes. + * Otherwise we can 'forget' to update time for any but the last +@@ -3239,7 +3263,22 @@ static void ctx_sched_out(struct perf_event_context *ctx, + if (is_active & EVENT_TIME) { + /* update (and stop) ctx time */ + update_context_time(ctx); +- update_cgrp_time_from_cpuctx(cpuctx); ++ update_cgrp_time_from_cpuctx(cpuctx, ctx == &cpuctx->ctx); ++ /* ++ * CPU-release for the below ->is_active store, ++ * see __load_acquire() in perf_event_time_now() ++ */ ++ barrier(); ++ } ++ ++ ctx->is_active &= ~event_type; ++ if (!(ctx->is_active & EVENT_ALL)) ++ ctx->is_active = 0; ++ ++ if (ctx->task) { ++ WARN_ON_ONCE(cpuctx->task_ctx != ctx); ++ if (!ctx->is_active) ++ cpuctx->task_ctx = NULL; + } + + is_active ^= ctx->is_active; /* changed bits */ +@@ -3676,13 +3715,19 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx, + return 0; + } + ++/* ++ * Because the userpage is strictly per-event (there is no concept of context, ++ * so there cannot be a context indirection), every userpage must be updated ++ * when context time starts :-( ++ * ++ * IOW, we must not miss EVENT_TIME edges. ++ */ + static inline bool event_update_userpage(struct perf_event *event) + { + if (likely(!atomic_read(&event->mmap_count))) + return false; + + perf_event_update_time(event); +- perf_set_shadow_time(event, event->ctx); + perf_event_update_userpage(event); + + return true; +@@ -3766,13 +3811,23 @@ ctx_sched_in(struct perf_event_context *ctx, + struct task_struct *task) + { + int is_active = ctx->is_active; +- u64 now; + + lockdep_assert_held(&ctx->lock); + + if (likely(!ctx->nr_events)) + return; + ++ if (is_active ^ EVENT_TIME) { ++ /* start ctx time */ ++ __update_context_time(ctx, false); ++ perf_cgroup_set_timestamp(task, ctx); ++ /* ++ * CPU-release for the below ->is_active store, ++ * see __load_acquire() in perf_event_time_now() ++ */ ++ barrier(); ++ } ++ + ctx->is_active |= (event_type | EVENT_TIME); + if (ctx->task) { + if (!is_active) +@@ -3783,13 +3838,6 @@ ctx_sched_in(struct perf_event_context *ctx, + + is_active ^= ctx->is_active; /* changed bits */ + +- if (is_active & EVENT_TIME) { +- /* start ctx time */ +- now = perf_clock(); +- ctx->timestamp = now; +- perf_cgroup_set_timestamp(task, ctx); +- } +- + /* + * First go through the list and put on any pinned groups + * in order to give them the best chance of going on. +@@ -4325,6 +4373,18 @@ static inline u64 perf_event_count(struct perf_event *event) + return local64_read(&event->count) + atomic64_read(&event->child_count); + } + ++static void calc_timer_values(struct perf_event *event, ++ u64 *now, ++ u64 *enabled, ++ u64 *running) ++{ ++ u64 ctx_time; ++ ++ *now = perf_clock(); ++ ctx_time = perf_event_time_now(event, *now); ++ __perf_update_times(event, ctx_time, enabled, running); ++} ++ + /* + * NMI-safe method to read a local event, that is an event that + * is: +@@ -4384,10 +4444,9 @@ int perf_event_read_local(struct perf_event *event, u64 *value, + + *value = local64_read(&event->count); + if (enabled || running) { +- u64 now = event->shadow_ctx_time + perf_clock(); +- u64 __enabled, __running; ++ u64 __enabled, __running, __now;; + +- __perf_update_times(event, now, &__enabled, &__running); ++ calc_timer_values(event, &__now, &__enabled, &__running); + if (enabled) + *enabled = __enabled; + if (running) +@@ -5694,18 +5753,6 @@ static int perf_event_index(struct perf_event *event) + return event->pmu->event_idx(event); + } + +-static void calc_timer_values(struct perf_event *event, +- u64 *now, +- u64 *enabled, +- u64 *running) +-{ +- u64 ctx_time; +- +- *now = perf_clock(); +- ctx_time = event->shadow_ctx_time + *now; +- __perf_update_times(event, ctx_time, enabled, running); +-} +- + static void perf_event_init_userpage(struct perf_event *event) + { + struct perf_event_mmap_page *userpg; +@@ -6245,7 +6292,6 @@ accounting: + ring_buffer_attach(event, rb); + + perf_event_update_time(event); +- perf_set_shadow_time(event, event->ctx); + perf_event_init_userpage(event); + perf_event_update_userpage(event); + } else { +-- +2.34.1 + diff --git a/queue-5.10/phylib-fix-potential-use-after-free.patch-8764 b/queue-5.10/phylib-fix-potential-use-after-free.patch-8764 new file mode 100644 index 00000000000..9268074190c --- /dev/null +++ b/queue-5.10/phylib-fix-potential-use-after-free.patch-8764 @@ -0,0 +1,58 @@ +From 998d7b539d4cd3286967471855d9e1b456310e37 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 19 Jan 2022 17:27:48 +0100 +Subject: phylib: fix potential use-after-free +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Marek Behún + +[ Upstream commit cbda1b16687580d5beee38273f6241ae3725960c ] + +Commit bafbdd527d56 ("phylib: Add device reset GPIO support") added call +to phy_device_reset(phydev) after the put_device() call in phy_detach(). + +The comment before the put_device() call says that the phydev might go +away with put_device(). + +Fix potential use-after-free by calling phy_device_reset() before +put_device(). + +Fixes: bafbdd527d56 ("phylib: Add device reset GPIO support") +Signed-off-by: Marek Behún +Reviewed-by: Andrew Lunn +Link: https://lore.kernel.org/r/20220119162748.32418-1-kabel@kernel.org +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/phy/phy_device.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c +index 85f3cde5ffd09..d2f6d8107595a 100644 +--- a/drivers/net/phy/phy_device.c ++++ b/drivers/net/phy/phy_device.c +@@ -1682,6 +1682,9 @@ void phy_detach(struct phy_device *phydev) + phy_driver_is_genphy_10g(phydev)) + device_release_driver(&phydev->mdio.dev); + ++ /* Assert the reset signal */ ++ phy_device_reset(phydev, 1); ++ + /* + * The phydev might go away on the put_device() below, so avoid + * a use-after-free bug by reading the underlying bus first. +@@ -1693,9 +1696,6 @@ void phy_detach(struct phy_device *phydev) + ndev_owner = dev->dev.parent->driver->owner; + if (ndev_owner != bus->owner) + module_put(bus->owner); +- +- /* Assert the reset signal */ +- phy_device_reset(phydev, 1); + } + EXPORT_SYMBOL(phy_detach); + +-- +2.34.1 + diff --git a/queue-5.10/ping-fix-the-sk_bound_dev_if-match-in-ping_lookup.patch-18872 b/queue-5.10/ping-fix-the-sk_bound_dev_if-match-in-ping_lookup.patch-18872 new file mode 100644 index 00000000000..62a14e8fa99 --- /dev/null +++ b/queue-5.10/ping-fix-the-sk_bound_dev_if-match-in-ping_lookup.patch-18872 @@ -0,0 +1,51 @@ +From 12eb0b3ad704529822739802c388d79731d32b4c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sat, 22 Jan 2022 06:40:56 -0500 +Subject: ping: fix the sk_bound_dev_if match in ping_lookup + +From: Xin Long + +[ Upstream commit 2afc3b5a31f9edf3ef0f374f5d70610c79c93a42 ] + +When 'ping' changes to use PING socket instead of RAW socket by: + + # sysctl -w net.ipv4.ping_group_range="0 100" + +the selftests 'router_broadcast.sh' will fail, as such command + + # ip vrf exec vrf-h1 ping -I veth0 198.51.100.255 -b + +can't receive the response skb by the PING socket. It's caused by mismatch +of sk_bound_dev_if and dif in ping_rcv() when looking up the PING socket, +as dif is vrf-h1 if dif's master was set to vrf-h1. + +This patch is to fix this regression by also checking the sk_bound_dev_if +against sdif so that the packets can stil be received even if the socket +is not bound to the vrf device but to the real iif. + +Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind") +Reported-by: Hangbin Liu +Signed-off-by: Xin Long +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ipv4/ping.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c +index 8ce8b7300b9d3..a5722905456c2 100644 +--- a/net/ipv4/ping.c ++++ b/net/ipv4/ping.c +@@ -220,7 +220,8 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) + continue; + } + +- if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) ++ if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif && ++ sk->sk_bound_dev_if != inet_sdif(skb)) + continue; + + sock_hold(sk); +-- +2.34.1 + diff --git a/queue-5.10/powerpc-perf-fix-power_pmu_disable-to-call-clear_pmi.patch-26206 b/queue-5.10/powerpc-perf-fix-power_pmu_disable-to-call-clear_pmi.patch-26206 new file mode 100644 index 00000000000..6a1548e372b --- /dev/null +++ b/queue-5.10/powerpc-perf-fix-power_pmu_disable-to-call-clear_pmi.patch-26206 @@ -0,0 +1,95 @@ +From 2a948d3006111935a336f67ff0b8fb560063fb98 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sat, 22 Jan 2022 09:04:29 +0530 +Subject: powerpc/perf: Fix power_pmu_disable to call clear_pmi_irq_pending + only if PMI is pending + +From: Athira Rajeev + +[ Upstream commit fb6433b48a178d4672cb26632454ee0b21056eaa ] + +Running selftest with CONFIG_PPC_IRQ_SOFT_MASK_DEBUG enabled in kernel +triggered below warning: + +[ 172.851380] ------------[ cut here ]------------ +[ 172.851391] WARNING: CPU: 8 PID: 2901 at arch/powerpc/include/asm/hw_irq.h:246 power_pmu_disable+0x270/0x280 +[ 172.851402] Modules linked in: dm_mod bonding nft_ct nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables rfkill nfnetlink sunrpc xfs libcrc32c pseries_rng xts vmx_crypto uio_pdrv_genirq uio sch_fq_codel ip_tables ext4 mbcache jbd2 sd_mod t10_pi sg ibmvscsi ibmveth scsi_transport_srp fuse +[ 172.851442] CPU: 8 PID: 2901 Comm: lost_exception_ Not tainted 5.16.0-rc5-03218-g798527287598 #2 +[ 172.851451] NIP: c00000000013d600 LR: c00000000013d5a4 CTR: c00000000013b180 +[ 172.851458] REGS: c000000017687860 TRAP: 0700 Not tainted (5.16.0-rc5-03218-g798527287598) +[ 172.851465] MSR: 8000000000029033 CR: 48004884 XER: 20040000 +[ 172.851482] CFAR: c00000000013d5b4 IRQMASK: 1 +[ 172.851482] GPR00: c00000000013d5a4 c000000017687b00 c000000002a10600 0000000000000004 +[ 172.851482] GPR04: 0000000082004000 c0000008ba08f0a8 0000000000000000 00000008b7ed0000 +[ 172.851482] GPR08: 00000000446194f6 0000000000008000 c00000000013b118 c000000000d58e68 +[ 172.851482] GPR12: c00000000013d390 c00000001ec54a80 0000000000000000 0000000000000000 +[ 172.851482] GPR16: 0000000000000000 0000000000000000 c000000015d5c708 c0000000025396d0 +[ 172.851482] GPR20: 0000000000000000 0000000000000000 c00000000a3bbf40 0000000000000003 +[ 172.851482] GPR24: 0000000000000000 c0000008ba097400 c0000000161e0d00 c00000000a3bb600 +[ 172.851482] GPR28: c000000015d5c700 0000000000000001 0000000082384090 c0000008ba0020d8 +[ 172.851549] NIP [c00000000013d600] power_pmu_disable+0x270/0x280 +[ 172.851557] LR [c00000000013d5a4] power_pmu_disable+0x214/0x280 +[ 172.851565] Call Trace: +[ 172.851568] [c000000017687b00] [c00000000013d5a4] power_pmu_disable+0x214/0x280 (unreliable) +[ 172.851579] [c000000017687b40] [c0000000003403ac] perf_pmu_disable+0x4c/0x60 +[ 172.851588] [c000000017687b60] [c0000000003445e4] __perf_event_task_sched_out+0x1d4/0x660 +[ 172.851596] [c000000017687c50] [c000000000d1175c] __schedule+0xbcc/0x12a0 +[ 172.851602] [c000000017687d60] [c000000000d11ea8] schedule+0x78/0x140 +[ 172.851608] [c000000017687d90] [c0000000001a8080] sys_sched_yield+0x20/0x40 +[ 172.851615] [c000000017687db0] [c0000000000334dc] system_call_exception+0x18c/0x380 +[ 172.851622] [c000000017687e10] [c00000000000c74c] system_call_common+0xec/0x268 + +The warning indicates that MSR_EE being set(interrupt enabled) when +there was an overflown PMC detected. This could happen in +power_pmu_disable since it runs under interrupt soft disable +condition ( local_irq_save ) and not with interrupts hard disabled. +commit 2c9ac51b850d ("powerpc/perf: Fix PMU callbacks to clear +pending PMI before resetting an overflown PMC") intended to clear +PMI pending bit in Paca when disabling the PMU. It could happen +that PMC gets overflown while code is in power_pmu_disable +callback function. Hence add a check to see if PMI pending bit +is set in Paca before clearing it via clear_pmi_pending. + +Fixes: 2c9ac51b850d ("powerpc/perf: Fix PMU callbacks to clear pending PMI before resetting an overflown PMC") +Reported-by: Sachin Sant +Signed-off-by: Athira Rajeev +Tested-by: Sachin Sant +Reviewed-by: Nicholas Piggin +Signed-off-by: Michael Ellerman +Link: https://lore.kernel.org/r/20220122033429.25395-1-atrajeev@linux.vnet.ibm.com +Signed-off-by: Sasha Levin +--- + arch/powerpc/perf/core-book3s.c | 17 ++++++++++++++--- + 1 file changed, 14 insertions(+), 3 deletions(-) + +diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c +index bd34e062bd290..e49aa8fc6a491 100644 +--- a/arch/powerpc/perf/core-book3s.c ++++ b/arch/powerpc/perf/core-book3s.c +@@ -1273,9 +1273,20 @@ static void power_pmu_disable(struct pmu *pmu) + * Otherwise provide a warning if there is PMI pending, but + * no counter is found overflown. + */ +- if (any_pmc_overflown(cpuhw)) +- clear_pmi_irq_pending(); +- else ++ if (any_pmc_overflown(cpuhw)) { ++ /* ++ * Since power_pmu_disable runs under local_irq_save, it ++ * could happen that code hits a PMC overflow without PMI ++ * pending in paca. Hence only clear PMI pending if it was ++ * set. ++ * ++ * If a PMI is pending, then MSR[EE] must be disabled (because ++ * the masked PMI handler disabling EE). So it is safe to ++ * call clear_pmi_irq_pending(). ++ */ ++ if (pmi_irq_pending()) ++ clear_pmi_irq_pending(); ++ } else + WARN_ON(pmi_irq_pending()); + + val = mmcra = cpuhw->mmcr.mmcra; +-- +2.34.1 + diff --git a/queue-5.10/powerpc64-bpf-limit-ldbrx-to-processors-compliant-wi.patch-12659 b/queue-5.10/powerpc64-bpf-limit-ldbrx-to-processors-compliant-wi.patch-12659 new file mode 100644 index 00000000000..cb73dd41cba --- /dev/null +++ b/queue-5.10/powerpc64-bpf-limit-ldbrx-to-processors-compliant-wi.patch-12659 @@ -0,0 +1,104 @@ +From 12ee0241ae1f2c7f1d456ed91bf6a198a2400d3a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 6 Jan 2022 17:15:12 +0530 +Subject: powerpc64/bpf: Limit 'ldbrx' to processors compliant with ISA v2.06 + +From: Naveen N. Rao + +[ Upstream commit 3f5f766d5f7f95a69a630da3544a1a0cee1cdddf ] + +Johan reported the below crash with test_bpf on ppc64 e5500: + + test_bpf: #296 ALU_END_FROM_LE 64: 0x0123456789abcdef -> 0x67452301 jited:1 + Oops: Exception in kernel mode, sig: 4 [#1] + BE PAGE_SIZE=4K SMP NR_CPUS=24 QEMU e500 + Modules linked in: test_bpf(+) + CPU: 0 PID: 76 Comm: insmod Not tainted 5.14.0-03771-g98c2059e008a-dirty #1 + NIP: 8000000000061c3c LR: 80000000006dea64 CTR: 8000000000061c18 + REGS: c0000000032d3420 TRAP: 0700 Not tainted (5.14.0-03771-g98c2059e008a-dirty) + MSR: 0000000080089000 CR: 88002822 XER: 20000000 IRQMASK: 0 + <...> + NIP [8000000000061c3c] 0x8000000000061c3c + LR [80000000006dea64] .__run_one+0x104/0x17c [test_bpf] + Call Trace: + .__run_one+0x60/0x17c [test_bpf] (unreliable) + .test_bpf_init+0x6a8/0xdc8 [test_bpf] + .do_one_initcall+0x6c/0x28c + .do_init_module+0x68/0x28c + .load_module+0x2460/0x2abc + .__do_sys_init_module+0x120/0x18c + .system_call_exception+0x110/0x1b8 + system_call_common+0xf0/0x210 + --- interrupt: c00 at 0x101d0acc + <...> + ---[ end trace 47b2bf19090bb3d0 ]--- + + Illegal instruction + +The illegal instruction turned out to be 'ldbrx' emitted for +BPF_FROM_[L|B]E, which was only introduced in ISA v2.06. Guard use of +the same and implement an alternative approach for older processors. + +Fixes: 156d0e290e969c ("powerpc/ebpf/jit: Implement JIT compiler for extended BPF") +Reported-by: Johan Almbladh +Signed-off-by: Naveen N. Rao +Tested-by: Johan Almbladh +Acked-by: Johan Almbladh +Signed-off-by: Michael Ellerman +Link: https://lore.kernel.org/r/d1e51c6fdf572062cf3009a751c3406bda01b832.1641468127.git.naveen.n.rao@linux.vnet.ibm.com +Signed-off-by: Sasha Levin +--- + arch/powerpc/include/asm/ppc-opcode.h | 1 + + arch/powerpc/net/bpf_jit_comp64.c | 22 +++++++++++++--------- + 2 files changed, 14 insertions(+), 9 deletions(-) + +diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h +index a6e3700c4566a..f0c0816f57270 100644 +--- a/arch/powerpc/include/asm/ppc-opcode.h ++++ b/arch/powerpc/include/asm/ppc-opcode.h +@@ -449,6 +449,7 @@ + #define PPC_RAW_LDX(r, base, b) (0x7c00002a | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) + #define PPC_RAW_LHZ(r, base, i) (0xa0000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) + #define PPC_RAW_LHBRX(r, base, b) (0x7c00062c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) ++#define PPC_RAW_LWBRX(r, base, b) (0x7c00042c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) + #define PPC_RAW_LDBRX(r, base, b) (0x7c000428 | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) + #define PPC_RAW_STWCX(s, a, b) (0x7c00012d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) + #define PPC_RAW_CMPWI(a, i) (0x2c000000 | ___PPC_RA(a) | IMM_L(i)) +diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c +index 8936090acb579..0d47514e8870d 100644 +--- a/arch/powerpc/net/bpf_jit_comp64.c ++++ b/arch/powerpc/net/bpf_jit_comp64.c +@@ -651,17 +651,21 @@ bpf_alu32_trunc: + EMIT(PPC_RAW_MR(dst_reg, b2p[TMP_REG_1])); + break; + case 64: +- /* +- * Way easier and faster(?) to store the value +- * into stack and then use ldbrx +- * +- * ctx->seen will be reliable in pass2, but +- * the instructions generated will remain the +- * same across all passes +- */ ++ /* Store the value to stack and then use byte-reverse loads */ + PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx)); + EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx))); +- EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1])); ++ if (cpu_has_feature(CPU_FTR_ARCH_206)) { ++ EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1])); ++ } else { ++ EMIT(PPC_RAW_LWBRX(dst_reg, 0, b2p[TMP_REG_1])); ++ if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN)) ++ EMIT(PPC_RAW_SLDI(dst_reg, dst_reg, 32)); ++ EMIT(PPC_RAW_LI(b2p[TMP_REG_2], 4)); ++ EMIT(PPC_RAW_LWBRX(b2p[TMP_REG_2], b2p[TMP_REG_2], b2p[TMP_REG_1])); ++ if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) ++ EMIT(PPC_RAW_SLDI(b2p[TMP_REG_2], b2p[TMP_REG_2], 32)); ++ EMIT(PPC_RAW_OR(dst_reg, dst_reg, b2p[TMP_REG_2])); ++ } + break; + } + break; +-- +2.34.1 + diff --git a/queue-5.10/revert-ipv6-honor-all-ipv6-pio-valid-lifetime-values.patch-17485 b/queue-5.10/revert-ipv6-honor-all-ipv6-pio-valid-lifetime-values.patch-17485 new file mode 100644 index 00000000000..b68906b8424 --- /dev/null +++ b/queue-5.10/revert-ipv6-honor-all-ipv6-pio-valid-lifetime-values.patch-17485 @@ -0,0 +1,96 @@ +From 5c2a36fb9ec5480a35a2f0522819d9540f1d43eb Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 26 Jan 2022 16:38:52 +0100 +Subject: Revert "ipv6: Honor all IPv6 PIO Valid Lifetime values" + +From: Guillaume Nault + +[ Upstream commit 36268983e90316b37000a005642af42234dabb36 ] + +This reverts commit b75326c201242de9495ff98e5d5cff41d7fc0d9d. + +This commit breaks Linux compatibility with USGv6 tests. The RFC this +commit was based on is actually an expired draft: no published RFC +currently allows the new behaviour it introduced. + +Without full IETF endorsement, the flash renumbering scenario this +patch was supposed to enable is never going to work, as other IPv6 +equipements on the same LAN will keep the 2 hours limit. + +Fixes: b75326c20124 ("ipv6: Honor all IPv6 PIO Valid Lifetime values") +Signed-off-by: Guillaume Nault +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + include/net/addrconf.h | 2 ++ + net/ipv6/addrconf.c | 27 ++++++++++++++++++++------- + 2 files changed, 22 insertions(+), 7 deletions(-) + +diff --git a/include/net/addrconf.h b/include/net/addrconf.h +index 78ea3e332688f..e7ce719838b5e 100644 +--- a/include/net/addrconf.h ++++ b/include/net/addrconf.h +@@ -6,6 +6,8 @@ + #define RTR_SOLICITATION_INTERVAL (4*HZ) + #define RTR_SOLICITATION_MAX_INTERVAL (3600*HZ) /* 1 hour */ + ++#define MIN_VALID_LIFETIME (2*3600) /* 2 hours */ ++ + #define TEMP_VALID_LIFETIME (7*86400) + #define TEMP_PREFERRED_LIFETIME (86400) + #define REGEN_MAX_RETRY (3) +diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c +index 29526937077b3..4dde49e628fab 100644 +--- a/net/ipv6/addrconf.c ++++ b/net/ipv6/addrconf.c +@@ -2577,7 +2577,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, + __u32 valid_lft, u32 prefered_lft) + { + struct inet6_ifaddr *ifp = ipv6_get_ifaddr(net, addr, dev, 1); +- int create = 0; ++ int create = 0, update_lft = 0; + + if (!ifp && valid_lft) { + int max_addresses = in6_dev->cnf.max_addresses; +@@ -2621,19 +2621,32 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, + unsigned long now; + u32 stored_lft; + +- /* Update lifetime (RFC4862 5.5.3 e) +- * We deviate from RFC4862 by honoring all Valid Lifetimes to +- * improve the reaction of SLAAC to renumbering events +- * (draft-gont-6man-slaac-renum-06, Section 4.2) +- */ ++ /* update lifetime (RFC2462 5.5.3 e) */ + spin_lock_bh(&ifp->lock); + now = jiffies; + if (ifp->valid_lft > (now - ifp->tstamp) / HZ) + stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ; + else + stored_lft = 0; +- + if (!create && stored_lft) { ++ const u32 minimum_lft = min_t(u32, ++ stored_lft, MIN_VALID_LIFETIME); ++ valid_lft = max(valid_lft, minimum_lft); ++ ++ /* RFC4862 Section 5.5.3e: ++ * "Note that the preferred lifetime of the ++ * corresponding address is always reset to ++ * the Preferred Lifetime in the received ++ * Prefix Information option, regardless of ++ * whether the valid lifetime is also reset or ++ * ignored." ++ * ++ * So we should always update prefered_lft here. ++ */ ++ update_lft = 1; ++ } ++ ++ if (update_lft) { + ifp->valid_lft = valid_lft; + ifp->prefered_lft = prefered_lft; + ifp->tstamp = now; +-- +2.34.1 + diff --git a/queue-5.10/rpmsg-char-fix-race-between-the-release-of-rpmsg_ctr.patch-7720 b/queue-5.10/rpmsg-char-fix-race-between-the-release-of-rpmsg_ctr.patch-7720 new file mode 100644 index 00000000000..cfd0b41f311 --- /dev/null +++ b/queue-5.10/rpmsg-char-fix-race-between-the-release-of-rpmsg_ctr.patch-7720 @@ -0,0 +1,117 @@ +From d06dac9b92008f32107071c7f2c16693002973ef Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 10 Jan 2022 10:47:36 -0800 +Subject: rpmsg: char: Fix race between the release of rpmsg_ctrldev and cdev + +From: Sujit Kautkar + +[ Upstream commit b7fb2dad571d1e21173c06cef0bced77b323990a ] + +struct rpmsg_ctrldev contains a struct cdev. The current code frees +the rpmsg_ctrldev struct in rpmsg_ctrldev_release_device(), but the +cdev is a managed object, therefore its release is not predictable +and the rpmsg_ctrldev could be freed before the cdev is entirely +released, as in the backtrace below. + +[ 93.625603] ODEBUG: free active (active state 0) object type: timer_list hint: delayed_work_timer_fn+0x0/0x7c +[ 93.636115] WARNING: CPU: 0 PID: 12 at lib/debugobjects.c:488 debug_print_object+0x13c/0x1b0 +[ 93.644799] Modules linked in: veth xt_cgroup xt_MASQUERADE rfcomm algif_hash algif_skcipher af_alg uinput ip6table_nat fuse uvcvideo videobuf2_vmalloc venus_enc venus_dec videobuf2_dma_contig hci_uart btandroid btqca snd_soc_rt5682_i2c bluetooth qcom_spmi_temp_alarm snd_soc_rt5682v +[ 93.715175] CPU: 0 PID: 12 Comm: kworker/0:1 Tainted: G B 5.4.163-lockdep #26 +[ 93.723855] Hardware name: Google Lazor (rev3 - 8) with LTE (DT) +[ 93.730055] Workqueue: events kobject_delayed_cleanup +[ 93.735271] pstate: 60c00009 (nZCv daif +PAN +UAO) +[ 93.740216] pc : debug_print_object+0x13c/0x1b0 +[ 93.744890] lr : debug_print_object+0x13c/0x1b0 +[ 93.749555] sp : ffffffacf5bc7940 +[ 93.752978] x29: ffffffacf5bc7940 x28: dfffffd000000000 +[ 93.758448] x27: ffffffacdb11a800 x26: dfffffd000000000 +[ 93.763916] x25: ffffffd0734f856c x24: dfffffd000000000 +[ 93.769389] x23: 0000000000000000 x22: ffffffd0733c35b0 +[ 93.774860] x21: ffffffd0751994a0 x20: ffffffd075ec27c0 +[ 93.780338] x19: ffffffd075199100 x18: 00000000000276e0 +[ 93.785814] x17: 0000000000000000 x16: dfffffd000000000 +[ 93.791291] x15: ffffffffffffffff x14: 6e6968207473696c +[ 93.796768] x13: 0000000000000000 x12: ffffffd075e2b000 +[ 93.802244] x11: 0000000000000001 x10: 0000000000000000 +[ 93.807723] x9 : d13400dff1921900 x8 : d13400dff1921900 +[ 93.813200] x7 : 0000000000000000 x6 : 0000000000000000 +[ 93.818676] x5 : 0000000000000080 x4 : 0000000000000000 +[ 93.824152] x3 : ffffffd0732a0fa4 x2 : 0000000000000001 +[ 93.829628] x1 : ffffffacf5bc7580 x0 : 0000000000000061 +[ 93.835104] Call trace: +[ 93.837644] debug_print_object+0x13c/0x1b0 +[ 93.841963] __debug_check_no_obj_freed+0x25c/0x3c0 +[ 93.846987] debug_check_no_obj_freed+0x18/0x20 +[ 93.851669] slab_free_freelist_hook+0xbc/0x1e4 +[ 93.856346] kfree+0xfc/0x2f4 +[ 93.859416] rpmsg_ctrldev_release_device+0x78/0xb8 +[ 93.864445] device_release+0x84/0x168 +[ 93.868310] kobject_cleanup+0x12c/0x298 +[ 93.872356] kobject_delayed_cleanup+0x10/0x18 +[ 93.876948] process_one_work+0x578/0x92c +[ 93.881086] worker_thread+0x804/0xcf8 +[ 93.884963] kthread+0x2a8/0x314 +[ 93.888303] ret_from_fork+0x10/0x18 + +The cdev_device_add/del() API was created to address this issue (see +commit '233ed09d7fda ("chardev: add helper function to register char +devs with a struct device")'), use it instead of cdev add/del(). + +Fixes: c0cdc19f84a4 ("rpmsg: Driver for user space endpoint interface") +Signed-off-by: Sujit Kautkar +Signed-off-by: Matthias Kaehlcke +Reviewed-by: Mathieu Poirier +Reviewed-by: Bjorn Andersson +Reviewed-by: Stephen Boyd +Signed-off-by: Bjorn Andersson +Link: https://lore.kernel.org/r/20220110104706.v6.1.Iaac908f3e3149a89190ce006ba166e2d3fd247a3@changeid +Signed-off-by: Sasha Levin +--- + drivers/rpmsg/rpmsg_char.c | 11 ++--------- + 1 file changed, 2 insertions(+), 9 deletions(-) + +diff --git a/drivers/rpmsg/rpmsg_char.c b/drivers/rpmsg/rpmsg_char.c +index 4bbbacdbf3bb7..8816b1923cdbc 100644 +--- a/drivers/rpmsg/rpmsg_char.c ++++ b/drivers/rpmsg/rpmsg_char.c +@@ -458,7 +458,6 @@ static void rpmsg_ctrldev_release_device(struct device *dev) + + ida_simple_remove(&rpmsg_ctrl_ida, dev->id); + ida_simple_remove(&rpmsg_minor_ida, MINOR(dev->devt)); +- cdev_del(&ctrldev->cdev); + kfree(ctrldev); + } + +@@ -493,19 +492,13 @@ static int rpmsg_chrdev_probe(struct rpmsg_device *rpdev) + dev->id = ret; + dev_set_name(&ctrldev->dev, "rpmsg_ctrl%d", ret); + +- ret = cdev_add(&ctrldev->cdev, dev->devt, 1); ++ ret = cdev_device_add(&ctrldev->cdev, &ctrldev->dev); + if (ret) + goto free_ctrl_ida; + + /* We can now rely on the release function for cleanup */ + dev->release = rpmsg_ctrldev_release_device; + +- ret = device_add(dev); +- if (ret) { +- dev_err(&rpdev->dev, "device_add failed: %d\n", ret); +- put_device(dev); +- } +- + dev_set_drvdata(&rpdev->dev, ctrldev); + + return ret; +@@ -531,7 +524,7 @@ static void rpmsg_chrdev_remove(struct rpmsg_device *rpdev) + if (ret) + dev_warn(&rpdev->dev, "failed to nuke endpoints: %d\n", ret); + +- device_del(&ctrldev->dev); ++ cdev_device_del(&ctrldev->cdev, &ctrldev->dev); + put_device(&ctrldev->dev); + } + +-- +2.34.1 + diff --git a/queue-5.10/rpmsg-char-fix-race-between-the-release-of-rpmsg_ept.patch-26480 b/queue-5.10/rpmsg-char-fix-race-between-the-release-of-rpmsg_ept.patch-26480 new file mode 100644 index 00000000000..475064c2f75 --- /dev/null +++ b/queue-5.10/rpmsg-char-fix-race-between-the-release-of-rpmsg_ept.patch-26480 @@ -0,0 +1,76 @@ +From 00f8f94636b1bf9b4b480eae7f2884dc7a6d8383 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 10 Jan 2022 10:47:37 -0800 +Subject: rpmsg: char: Fix race between the release of rpmsg_eptdev and cdev + +From: Matthias Kaehlcke + +[ Upstream commit 7a534ae89e34e9b51acb5a63dd0f88308178b46a ] + +struct rpmsg_eptdev contains a struct cdev. The current code frees +the rpmsg_eptdev struct in rpmsg_eptdev_destroy(), but the cdev is +a managed object, therefore its release is not predictable and the +rpmsg_eptdev could be freed before the cdev is entirely released. + +The cdev_device_add/del() API was created to address this issue +(see commit '233ed09d7fda ("chardev: add helper function to register +char devs with a struct device")'), use it instead of cdev add/del(). + +Fixes: c0cdc19f84a4 ("rpmsg: Driver for user space endpoint interface") +Suggested-by: Bjorn Andersson +Signed-off-by: Matthias Kaehlcke +Reviewed-by: Mathieu Poirier +Reviewed-by: Stephen Boyd +Reviewed-by: Bjorn Andersson +Signed-off-by: Bjorn Andersson +Link: https://lore.kernel.org/r/20220110104706.v6.2.Idde68b05b88d4a2e6e54766c653f3a6d9e419ce6@changeid +Signed-off-by: Sasha Levin +--- + drivers/rpmsg/rpmsg_char.c | 11 ++--------- + 1 file changed, 2 insertions(+), 9 deletions(-) + +diff --git a/drivers/rpmsg/rpmsg_char.c b/drivers/rpmsg/rpmsg_char.c +index 8816b1923cdbc..be90d77c5168d 100644 +--- a/drivers/rpmsg/rpmsg_char.c ++++ b/drivers/rpmsg/rpmsg_char.c +@@ -92,7 +92,7 @@ static int rpmsg_eptdev_destroy(struct device *dev, void *data) + /* wake up any blocked readers */ + wake_up_interruptible(&eptdev->readq); + +- device_del(&eptdev->dev); ++ cdev_device_del(&eptdev->cdev, &eptdev->dev); + put_device(&eptdev->dev); + + return 0; +@@ -332,7 +332,6 @@ static void rpmsg_eptdev_release_device(struct device *dev) + + ida_simple_remove(&rpmsg_ept_ida, dev->id); + ida_simple_remove(&rpmsg_minor_ida, MINOR(eptdev->dev.devt)); +- cdev_del(&eptdev->cdev); + kfree(eptdev); + } + +@@ -377,19 +376,13 @@ static int rpmsg_eptdev_create(struct rpmsg_ctrldev *ctrldev, + dev->id = ret; + dev_set_name(dev, "rpmsg%d", ret); + +- ret = cdev_add(&eptdev->cdev, dev->devt, 1); ++ ret = cdev_device_add(&eptdev->cdev, &eptdev->dev); + if (ret) + goto free_ept_ida; + + /* We can now rely on the release function for cleanup */ + dev->release = rpmsg_eptdev_release_device; + +- ret = device_add(dev); +- if (ret) { +- dev_err(dev, "device_add failed: %d\n", ret); +- put_device(dev); +- } +- + return ret; + + free_ept_ida: +-- +2.34.1 + diff --git a/queue-5.10/rxrpc-adjust-retransmission-backoff.patch-30293 b/queue-5.10/rxrpc-adjust-retransmission-backoff.patch-30293 new file mode 100644 index 00000000000..c29a49e6a28 --- /dev/null +++ b/queue-5.10/rxrpc-adjust-retransmission-backoff.patch-30293 @@ -0,0 +1,93 @@ +From 730447b0dff59a7a30068b40f7970d381117d2f3 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 21 Jan 2022 23:12:58 +0000 +Subject: rxrpc: Adjust retransmission backoff + +From: David Howells + +[ Upstream commit 2c13c05c5ff4b9fc907b07f7311821910ebaaf8a ] + +Improve retransmission backoff by only backing off when we retransmit data +packets rather than when we set the lost ack timer. + +To this end: + + (1) In rxrpc_resend(), use rxrpc_get_rto_backoff() when setting the + retransmission timer and only tell it that we are retransmitting if we + actually have things to retransmit. + + Note that it's possible for the retransmission algorithm to race with + the processing of a received ACK, so we may see no packets needing + retransmission. + + (2) In rxrpc_send_data_packet(), don't bump the backoff when setting the + ack_lost_at timer, as it may then get bumped twice. + +With this, when looking at one particular packet, the retransmission +intervals were seen to be 1.5ms, 2ms, 3ms, 5ms, 9ms, 17ms, 33ms, 71ms, +136ms, 264ms, 544ms, 1.088s, 2.1s, 4.2s and 8.3s. + +Fixes: c410bf01933e ("rxrpc: Fix the excessive initial retransmission timeout") +Suggested-by: Marc Dionne +Signed-off-by: David Howells +Reviewed-by: Marc Dionne +Tested-by: Marc Dionne +cc: linux-afs@lists.infradead.org +Link: https://lore.kernel.org/r/164138117069.2023386.17446904856843997127.stgit@warthog.procyon.org.uk/ +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/rxrpc/call_event.c | 8 +++----- + net/rxrpc/output.c | 2 +- + 2 files changed, 4 insertions(+), 6 deletions(-) + +diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c +index 6be2672a65eab..df864e6922679 100644 +--- a/net/rxrpc/call_event.c ++++ b/net/rxrpc/call_event.c +@@ -157,7 +157,7 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call) + static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) + { + struct sk_buff *skb; +- unsigned long resend_at, rto_j; ++ unsigned long resend_at; + rxrpc_seq_t cursor, seq, top; + ktime_t now, max_age, oldest, ack_ts; + int ix; +@@ -165,10 +165,8 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) + + _enter("{%d,%d}", call->tx_hard_ack, call->tx_top); + +- rto_j = call->peer->rto_j; +- + now = ktime_get_real(); +- max_age = ktime_sub(now, jiffies_to_usecs(rto_j)); ++ max_age = ktime_sub(now, jiffies_to_usecs(call->peer->rto_j)); + + spin_lock_bh(&call->lock); + +@@ -213,7 +211,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) + } + + resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); +- resend_at += jiffies + rto_j; ++ resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, retrans); + WRITE_ONCE(call->resend_at, resend_at); + + if (unacked) +diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c +index 10f2bf2e9068a..a45c83f22236e 100644 +--- a/net/rxrpc/output.c ++++ b/net/rxrpc/output.c +@@ -468,7 +468,7 @@ done: + if (call->peer->rtt_count > 1) { + unsigned long nowj = jiffies, ack_lost_at; + +- ack_lost_at = rxrpc_get_rto_backoff(call->peer, retrans); ++ ack_lost_at = rxrpc_get_rto_backoff(call->peer, false); + ack_lost_at += nowj; + WRITE_ONCE(call->ack_lost_at, ack_lost_at); + rxrpc_reduce_call_timer(call, ack_lost_at, nowj, +-- +2.34.1 + diff --git a/queue-5.10/sched-pelt-relax-the-sync-of-util_sum-with-util_avg.patch-4811 b/queue-5.10/sched-pelt-relax-the-sync-of-util_sum-with-util_avg.patch-4811 new file mode 100644 index 00000000000..64d26ca45c9 --- /dev/null +++ b/queue-5.10/sched-pelt-relax-the-sync-of-util_sum-with-util_avg.patch-4811 @@ -0,0 +1,105 @@ +From b0dae8e1a110bd653caa27f5d7dd21da2213b5b6 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 11 Jan 2022 14:46:56 +0100 +Subject: sched/pelt: Relax the sync of util_sum with util_avg + +From: Vincent Guittot + +[ Upstream commit 98b0d890220d45418cfbc5157b3382e6da5a12ab ] + +Rick reported performance regressions in bugzilla because of cpu frequency +being lower than before: + https://bugzilla.kernel.org/show_bug.cgi?id=215045 + +He bisected the problem to: +commit 1c35b07e6d39 ("sched/fair: Ensure _sum and _avg values stay consistent") + +This commit forces util_sum to be synced with the new util_avg after +removing the contribution of a task and before the next periodic sync. By +doing so util_sum is rounded to its lower bound and might lost up to +LOAD_AVG_MAX-1 of accumulated contribution which has not yet been +reflected in util_avg. + +Instead of always setting util_sum to the low bound of util_avg, which can +significantly lower the utilization of root cfs_rq after propagating the +change down into the hierarchy, we revert the change of util_sum and +propagate the difference. + +In addition, we also check that cfs's util_sum always stays above the +lower bound for a given util_avg as it has been observed that +sched_entity's util_sum is sometimes above cfs one. + +Fixes: 1c35b07e6d39 ("sched/fair: Ensure _sum and _avg values stay consistent") +Reported-by: Rick Yiu +Signed-off-by: Vincent Guittot +Signed-off-by: Peter Zijlstra (Intel) +Reviewed-by: Dietmar Eggemann +Tested-by: Sachin Sant +Link: https://lkml.kernel.org/r/20220111134659.24961-2-vincent.guittot@linaro.org +Signed-off-by: Sasha Levin +--- + kernel/sched/fair.c | 16 +++++++++++++--- + kernel/sched/pelt.h | 4 +++- + 2 files changed, 16 insertions(+), 4 deletions(-) + +diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c +index 8d2f238fdd2ac..acd9833b8ec22 100644 +--- a/kernel/sched/fair.c ++++ b/kernel/sched/fair.c +@@ -3379,7 +3379,6 @@ void set_task_rq_fair(struct sched_entity *se, + se->avg.last_update_time = n_last_update_time; + } + +- + /* + * When on migration a sched_entity joins/leaves the PELT hierarchy, we need to + * propagate its contribution. The key to this propagation is the invariant +@@ -3447,7 +3446,6 @@ void set_task_rq_fair(struct sched_entity *se, + * XXX: only do this for the part of runnable > running ? + * + */ +- + static inline void + update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) + { +@@ -3676,7 +3674,19 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) + + r = removed_util; + sub_positive(&sa->util_avg, r); +- sa->util_sum = sa->util_avg * divider; ++ sub_positive(&sa->util_sum, r * divider); ++ /* ++ * Because of rounding, se->util_sum might ends up being +1 more than ++ * cfs->util_sum. Although this is not a problem by itself, detaching ++ * a lot of tasks with the rounding problem between 2 updates of ++ * util_avg (~1ms) can make cfs->util_sum becoming null whereas ++ * cfs_util_avg is not. ++ * Check that util_sum is still above its lower bound for the new ++ * util_avg. Given that period_contrib might have moved since the last ++ * sync, we are only sure that util_sum must be above or equal to ++ * util_avg * minimum possible divider ++ */ ++ sa->util_sum = max_t(u32, sa->util_sum, sa->util_avg * PELT_MIN_DIVIDER); + + r = removed_runnable; + sub_positive(&sa->runnable_avg, r); +diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h +index 0b9aeebb9c325..45bf08e22207c 100644 +--- a/kernel/sched/pelt.h ++++ b/kernel/sched/pelt.h +@@ -37,9 +37,11 @@ update_irq_load_avg(struct rq *rq, u64 running) + } + #endif + ++#define PELT_MIN_DIVIDER (LOAD_AVG_MAX - 1024) ++ + static inline u32 get_pelt_divider(struct sched_avg *avg) + { +- return LOAD_AVG_MAX - 1024 + avg->period_contrib; ++ return PELT_MIN_DIVIDER + avg->period_contrib; + } + + static inline void cfs_se_util_change(struct sched_avg *avg) +-- +2.34.1 + diff --git a/queue-5.10/scsi-bnx2fc-flush-destroy_work-queue-before-calling-.patch-1575 b/queue-5.10/scsi-bnx2fc-flush-destroy_work-queue-before-calling-.patch-1575 new file mode 100644 index 00000000000..a42353162fc --- /dev/null +++ b/queue-5.10/scsi-bnx2fc-flush-destroy_work-queue-before-calling-.patch-1575 @@ -0,0 +1,152 @@ +From 0e9b082ee4984d84e83f27029d4747e9d6defdcf Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 14 Jan 2022 23:00:44 -0500 +Subject: scsi: bnx2fc: Flush destroy_work queue before calling + bnx2fc_interface_put() + +From: John Meneghini + +[ Upstream commit 847f9ea4c5186fdb7b84297e3eeed9e340e83fce ] + +The bnx2fc_destroy() functions are removing the interface before calling +destroy_work. This results multiple WARNings from sysfs_remove_group() as +the controller rport device attributes are removed too early. + +Replace the fcoe_port's destroy_work queue. It's not needed. + +The problem is easily reproducible with the following steps. + +Example: + + $ dmesg -w & + $ systemctl enable --now fcoe + $ fipvlan -s -c ens2f1 + $ fcoeadm -d ens2f1.802 + [ 583.464488] host2: libfc: Link down on port (7500a1) + [ 583.472651] bnx2fc: 7500a1 - rport not created Yet!! + [ 583.490468] ------------[ cut here ]------------ + [ 583.538725] sysfs group 'power' not found for kobject 'rport-2:0-0' + [ 583.568814] WARNING: CPU: 3 PID: 192 at fs/sysfs/group.c:279 sysfs_remove_group+0x6f/0x80 + [ 583.607130] Modules linked in: dm_service_time 8021q garp mrp stp llc bnx2fc cnic uio rpcsec_gss_krb5 auth_rpcgss nfsv4 ... + [ 583.942994] CPU: 3 PID: 192 Comm: kworker/3:2 Kdump: loaded Not tainted 5.14.0-39.el9.x86_64 #1 + [ 583.984105] Hardware name: HP ProLiant DL120 G7, BIOS J01 07/01/2013 + [ 584.016535] Workqueue: fc_wq_2 fc_rport_final_delete [scsi_transport_fc] + [ 584.050691] RIP: 0010:sysfs_remove_group+0x6f/0x80 + [ 584.074725] Code: ff 5b 48 89 ef 5d 41 5c e9 ee c0 ff ff 48 89 ef e8 f6 b8 ff ff eb d1 49 8b 14 24 48 8b 33 48 c7 c7 ... + [ 584.162586] RSP: 0018:ffffb567c15afdc0 EFLAGS: 00010282 + [ 584.188225] RAX: 0000000000000000 RBX: ffffffff8eec4220 RCX: 0000000000000000 + [ 584.221053] RDX: ffff8c1586ce84c0 RSI: ffff8c1586cd7cc0 RDI: ffff8c1586cd7cc0 + [ 584.255089] RBP: 0000000000000000 R08: 0000000000000000 R09: ffffb567c15afc00 + [ 584.287954] R10: ffffb567c15afbf8 R11: ffffffff8fbe7f28 R12: ffff8c1486326400 + [ 584.322356] R13: ffff8c1486326480 R14: ffff8c1483a4a000 R15: 0000000000000004 + [ 584.355379] FS: 0000000000000000(0000) GS:ffff8c1586cc0000(0000) knlGS:0000000000000000 + [ 584.394419] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 + [ 584.421123] CR2: 00007fe95a6f7840 CR3: 0000000107674002 CR4: 00000000000606e0 + [ 584.454888] Call Trace: + [ 584.466108] device_del+0xb2/0x3e0 + [ 584.481701] device_unregister+0x13/0x60 + [ 584.501306] bsg_unregister_queue+0x5b/0x80 + [ 584.522029] bsg_remove_queue+0x1c/0x40 + [ 584.541884] fc_rport_final_delete+0xf3/0x1d0 [scsi_transport_fc] + [ 584.573823] process_one_work+0x1e3/0x3b0 + [ 584.592396] worker_thread+0x50/0x3b0 + [ 584.609256] ? rescuer_thread+0x370/0x370 + [ 584.628877] kthread+0x149/0x170 + [ 584.643673] ? set_kthread_struct+0x40/0x40 + [ 584.662909] ret_from_fork+0x22/0x30 + [ 584.680002] ---[ end trace 53575ecefa942ece ]--- + +Link: https://lore.kernel.org/r/20220115040044.1013475-1-jmeneghi@redhat.com +Fixes: 0cbf32e1681d ("[SCSI] bnx2fc: Avoid calling bnx2fc_if_destroy with unnecessary locks") +Tested-by: Guangwu Zhang +Co-developed-by: Maurizio Lombardi +Signed-off-by: Maurizio Lombardi +Signed-off-by: John Meneghini +Signed-off-by: Martin K. Petersen +Signed-off-by: Sasha Levin +--- + drivers/scsi/bnx2fc/bnx2fc_fcoe.c | 20 +++++--------------- + 1 file changed, 5 insertions(+), 15 deletions(-) + +diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +index 6890bbe04a8c1..052e7879704a5 100644 +--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c ++++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +@@ -80,7 +80,7 @@ static int bnx2fc_bind_pcidev(struct bnx2fc_hba *hba); + static void bnx2fc_unbind_pcidev(struct bnx2fc_hba *hba); + static struct fc_lport *bnx2fc_if_create(struct bnx2fc_interface *interface, + struct device *parent, int npiv); +-static void bnx2fc_destroy_work(struct work_struct *work); ++static void bnx2fc_port_destroy(struct fcoe_port *port); + + static struct bnx2fc_hba *bnx2fc_hba_lookup(struct net_device *phys_dev); + static struct bnx2fc_interface *bnx2fc_interface_lookup(struct net_device +@@ -905,9 +905,6 @@ static void bnx2fc_indicate_netevent(void *context, unsigned long event, + __bnx2fc_destroy(interface); + } + mutex_unlock(&bnx2fc_dev_lock); +- +- /* Ensure ALL destroy work has been completed before return */ +- flush_workqueue(bnx2fc_wq); + return; + + default: +@@ -1213,8 +1210,8 @@ static int bnx2fc_vport_destroy(struct fc_vport *vport) + mutex_unlock(&n_port->lp_mutex); + bnx2fc_free_vport(interface->hba, port->lport); + bnx2fc_port_shutdown(port->lport); ++ bnx2fc_port_destroy(port); + bnx2fc_interface_put(interface); +- queue_work(bnx2fc_wq, &port->destroy_work); + return 0; + } + +@@ -1523,7 +1520,6 @@ static struct fc_lport *bnx2fc_if_create(struct bnx2fc_interface *interface, + port->lport = lport; + port->priv = interface; + port->get_netdev = bnx2fc_netdev; +- INIT_WORK(&port->destroy_work, bnx2fc_destroy_work); + + /* Configure fcoe_port */ + rc = bnx2fc_lport_config(lport); +@@ -1651,8 +1647,8 @@ static void __bnx2fc_destroy(struct bnx2fc_interface *interface) + bnx2fc_interface_cleanup(interface); + bnx2fc_stop(interface); + list_del(&interface->list); ++ bnx2fc_port_destroy(port); + bnx2fc_interface_put(interface); +- queue_work(bnx2fc_wq, &port->destroy_work); + } + + /** +@@ -1692,15 +1688,12 @@ netdev_err: + return rc; + } + +-static void bnx2fc_destroy_work(struct work_struct *work) ++static void bnx2fc_port_destroy(struct fcoe_port *port) + { +- struct fcoe_port *port; + struct fc_lport *lport; + +- port = container_of(work, struct fcoe_port, destroy_work); + lport = port->lport; +- +- BNX2FC_HBA_DBG(lport, "Entered bnx2fc_destroy_work\n"); ++ BNX2FC_HBA_DBG(lport, "Entered %s, destroying lport %p\n", __func__, lport); + + bnx2fc_if_destroy(lport); + } +@@ -2554,9 +2547,6 @@ static void bnx2fc_ulp_exit(struct cnic_dev *dev) + __bnx2fc_destroy(interface); + mutex_unlock(&bnx2fc_dev_lock); + +- /* Ensure ALL destroy work has been completed before return */ +- flush_workqueue(bnx2fc_wq); +- + bnx2fc_ulp_stop(hba); + /* unregister cnic device */ + if (test_and_clear_bit(BNX2FC_CNIC_REGISTERED, &hba->reg_with_cnic)) +-- +2.34.1 + diff --git a/queue-5.10/series b/queue-5.10/series index 69946a0b2d3..970d6b42c74 100644 --- a/queue-5.10/series +++ b/queue-5.10/series @@ -32,3 +32,117 @@ usb-gadget-f_sourcesink-fix-isoc-transfer-for-usb_speed_super_plus.patch usb-core-fix-hang-in-usb_kill_urb-by-adding-memory-barriers.patch usb-typec-tcpm-do-not-disconnect-while-receiving-vbus-off.patch ucsi_ccg-check-dev_int-bit-only-when-starting-ccg4.patch +nfs-ensure-the-server-has-an-up-to-date-ctime-before.patch +nfs-ensure-the-server-has-an-up-to-date-ctime-before.patch-26251 +nfsv4-handle-case-where-the-lookup-of-a-directory-fa.patch +nfsv4-nfs_atomic_open-can-race-when-looking-up-a-non.patch +powerpc64-bpf-limit-ldbrx-to-processors-compliant-wi.patch +netfilter-conntrack-don-t-increment-invalid-counter-.patch +rpmsg-char-fix-race-between-the-release-of-rpmsg_ctr.patch +rpmsg-char-fix-race-between-the-release-of-rpmsg_ept.patch +kernel-delete-repeated-words-in-comments.patch +perf-fix-perf_event_read_local-time.patch +sched-pelt-relax-the-sync-of-util_sum-with-util_avg.patch +arm-9170-1-fix-panic-when-kasan-and-kprobe-are-enabl.patch +net-fix-information-leakage-in-proc-net-ptype.patch +net-phy-broadcom-hook-up-soft_reset-for-bcm54616s.patch +ipv6_tunnel-rate-limit-warning-messages.patch +i40e-increase-delay-to-1-s-after-global-emp-reset.patch +i40e-fix-issue-when-maximum-queues-is-exceeded.patch +i40e-fix-queues-reservation-for-xdp.patch +i40e-fix-for-failed-to-init-adminq-while-vf-reset.patch +i40e-fix-unsigned-stat-widths.patch +phylib-fix-potential-use-after-free.patch +ipv6-correct-comments-about-fib6_node-sernum.patch +ipv6-annotate-accesses-to-fn-fn_sernum.patch +octeontx2-pf-forward-error-codes-to-vf.patch +rxrpc-adjust-retransmission-backoff.patch +efi-libstub-arm64-fix-image-check-alignment-at-entry.patch +hwmon-lm90-reduce-maximum-conversion-rate-for-g781.patch +hwmon-lm90-mark-alert-as-broken-for-max6654.patch +hwmon-lm90-mark-alert-as-broken-for-max6680.patch +hwmon-lm90-mark-alert-as-broken-for-max6646-6647-664.patch +powerpc-perf-fix-power_pmu_disable-to-call-clear_pmi.patch +net-procfs-show-net-devices-bound-packet-types.patch +net-ipv4-move-ip_options_fragment-out-of-loop.patch +net-ipv4-fix-the-warning-for-dereference.patch +ipv4-fix-ip-option-filtering-for-locally-generated-f.patch +ibmvnic-init-running_cap_crqs-early.patch +ibmvnic-don-t-spin-in-tasklet.patch +ping-fix-the-sk_bound_dev_if-match-in-ping_lookup.patch +video-hyperv_fb-fix-validation-of-screen-resolution.patch +drm-msm-dsi-fix-missing-put_device-call-in-dsi_get_p.patch +drm-msm-hdmi-fix-missing-put_device-call-in-msm_hdmi.patch +drm-msm-dpu-invalid-parameter-check-in-dpu_setup_dsp.patch +drm-msm-fix-wrong-size-calculation.patch +drm-msm-dsi-invalid-parameter-check-in-msm_dsi_phy_e.patch +scsi-bnx2fc-flush-destroy_work-queue-before-calling-.patch +yam-fix-a-memory-leak-in-yam_siocdevprivate.patch +net-cpsw-properly-initialise-struct-page_pool_params.patch +net-hns3-handle-empty-unknown-interrupt-for-vf.patch +usb-roles-fix-include-linux-usb-role.h-compile-issue.patch +ata-pata_platform-fix-a-null-pointer-dereference-in-.patch +revert-ipv6-honor-all-ipv6-pio-valid-lifetime-values.patch +net-bridge-vlan-fix-single-net-device-option-dumping.patch +ipv4-raw-lock-the-socket-in-raw_bind.patch +ipv4-tcp-send-zero-ipid-in-synack-messages.patch +ipv4-avoid-using-shared-ip-generator-for-connected-s.patch +ipv4-remove-sparse-error-in-ip_neigh_gw4.patch +net-bridge-vlan-fix-memory-leak-in-__allowed_ingress.patch +nfs-ensure-the-server-has-an-up-to-date-ctime-before.patch-15600 +nfs-ensure-the-server-has-an-up-to-date-ctime-before.patch-8657 +nfsv4-handle-case-where-the-lookup-of-a-directory-fa.patch-15449 +nfsv4-nfs_atomic_open-can-race-when-looking-up-a-non.patch-27002 +powerpc64-bpf-limit-ldbrx-to-processors-compliant-wi.patch-12659 +netfilter-conntrack-don-t-increment-invalid-counter-.patch-23162 +rpmsg-char-fix-race-between-the-release-of-rpmsg_ctr.patch-7720 +rpmsg-char-fix-race-between-the-release-of-rpmsg_ept.patch-26480 +kernel-delete-repeated-words-in-comments.patch-15671 +perf-fix-perf_event_read_local-time.patch-26974 +sched-pelt-relax-the-sync-of-util_sum-with-util_avg.patch-4811 +arm-9170-1-fix-panic-when-kasan-and-kprobe-are-enabl.patch-30400 +net-fix-information-leakage-in-proc-net-ptype.patch-15695 +net-phy-broadcom-hook-up-soft_reset-for-bcm54616s.patch-27858 +ipv6_tunnel-rate-limit-warning-messages.patch-10619 +i40e-increase-delay-to-1-s-after-global-emp-reset.patch-13096 +i40e-fix-issue-when-maximum-queues-is-exceeded.patch-24471 +i40e-fix-queues-reservation-for-xdp.patch-15396 +i40e-fix-for-failed-to-init-adminq-while-vf-reset.patch-21045 +i40e-fix-unsigned-stat-widths.patch-20948 +phylib-fix-potential-use-after-free.patch-8764 +ipv6-correct-comments-about-fib6_node-sernum.patch-17310 +ipv6-annotate-accesses-to-fn-fn_sernum.patch-11803 +octeontx2-pf-forward-error-codes-to-vf.patch-28837 +rxrpc-adjust-retransmission-backoff.patch-30293 +efi-libstub-arm64-fix-image-check-alignment-at-entry.patch-16098 +hwmon-lm90-reduce-maximum-conversion-rate-for-g781.patch-19402 +hwmon-lm90-mark-alert-as-broken-for-max6654.patch-31788 +hwmon-lm90-mark-alert-as-broken-for-max6680.patch-25015 +hwmon-lm90-mark-alert-as-broken-for-max6646-6647-664.patch-31110 +powerpc-perf-fix-power_pmu_disable-to-call-clear_pmi.patch-26206 +net-procfs-show-net-devices-bound-packet-types.patch-14776 +net-ipv4-move-ip_options_fragment-out-of-loop.patch-9656 +net-ipv4-fix-the-warning-for-dereference.patch-3212 +ipv4-fix-ip-option-filtering-for-locally-generated-f.patch-27601 +ibmvnic-init-running_cap_crqs-early.patch-3045 +ibmvnic-don-t-spin-in-tasklet.patch-9595 +ping-fix-the-sk_bound_dev_if-match-in-ping_lookup.patch-18872 +video-hyperv_fb-fix-validation-of-screen-resolution.patch-11533 +drm-msm-dsi-fix-missing-put_device-call-in-dsi_get_p.patch-11600 +drm-msm-hdmi-fix-missing-put_device-call-in-msm_hdmi.patch-14235 +drm-msm-dpu-invalid-parameter-check-in-dpu_setup_dsp.patch-23932 +drm-msm-fix-wrong-size-calculation.patch-26799 +drm-msm-dsi-invalid-parameter-check-in-msm_dsi_phy_e.patch-27026 +scsi-bnx2fc-flush-destroy_work-queue-before-calling-.patch-1575 +yam-fix-a-memory-leak-in-yam_siocdevprivate.patch-10148 +net-cpsw-properly-initialise-struct-page_pool_params.patch-12745 +net-hns3-handle-empty-unknown-interrupt-for-vf.patch-6323 +usb-roles-fix-include-linux-usb-role.h-compile-issue.patch-6053 +ata-pata_platform-fix-a-null-pointer-dereference-in-.patch-22417 +revert-ipv6-honor-all-ipv6-pio-valid-lifetime-values.patch-17485 +net-bridge-vlan-fix-single-net-device-option-dumping.patch-32125 +ipv4-raw-lock-the-socket-in-raw_bind.patch-1741 +ipv4-tcp-send-zero-ipid-in-synack-messages.patch-31729 +ipv4-avoid-using-shared-ip-generator-for-connected-s.patch-2008 +ipv4-remove-sparse-error-in-ip_neigh_gw4.patch-3162 +net-bridge-vlan-fix-memory-leak-in-__allowed_ingress.patch-11653 diff --git a/queue-5.10/usb-roles-fix-include-linux-usb-role.h-compile-issue.patch-6053 b/queue-5.10/usb-roles-fix-include-linux-usb-role.h-compile-issue.patch-6053 new file mode 100644 index 00000000000..43a02ef7b76 --- /dev/null +++ b/queue-5.10/usb-roles-fix-include-linux-usb-role.h-compile-issue.patch-6053 @@ -0,0 +1,41 @@ +From 7a4da28ae2b14f1dc673f9b6b60f70499f27f119 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 10 Jan 2022 20:43:28 +0800 +Subject: usb: roles: fix include/linux/usb/role.h compile issue + +From: Linyu Yuan + +[ Upstream commit 945c37ed564770c78dfe6b9f08bed57a1b4e60ef ] + +when CONFIG_USB_ROLE_SWITCH is not defined, +add usb_role_switch_find_by_fwnode() definition which return NULL. + +Fixes: c6919d5e0cd1 ("usb: roles: Add usb_role_switch_find_by_fwnode()") +Signed-off-by: Linyu Yuan +Link: https://lore.kernel.org/r/1641818608-25039-1-git-send-email-quic_linyyuan@quicinc.com +Signed-off-by: Greg Kroah-Hartman +Signed-off-by: Sasha Levin +--- + include/linux/usb/role.h | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/include/linux/usb/role.h b/include/linux/usb/role.h +index 0164fed31b06c..b9ccaeb8a4aef 100644 +--- a/include/linux/usb/role.h ++++ b/include/linux/usb/role.h +@@ -90,6 +90,12 @@ fwnode_usb_role_switch_get(struct fwnode_handle *node) + + static inline void usb_role_switch_put(struct usb_role_switch *sw) { } + ++static inline struct usb_role_switch * ++usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode) ++{ ++ return NULL; ++} ++ + static inline struct usb_role_switch * + usb_role_switch_register(struct device *parent, + const struct usb_role_switch_desc *desc) +-- +2.34.1 + diff --git a/queue-5.10/video-hyperv_fb-fix-validation-of-screen-resolution.patch-11533 b/queue-5.10/video-hyperv_fb-fix-validation-of-screen-resolution.patch-11533 new file mode 100644 index 00000000000..42f5ba819f8 --- /dev/null +++ b/queue-5.10/video-hyperv_fb-fix-validation-of-screen-resolution.patch-11533 @@ -0,0 +1,99 @@ +From ee44596bd54c0d93cdb3e29c0d1a4a12d3286344 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sun, 16 Jan 2022 11:18:31 -0800 +Subject: video: hyperv_fb: Fix validation of screen resolution + +From: Michael Kelley + +[ Upstream commit 9ff5549b1d1d3c3a9d71220d44bd246586160f1d ] + +In the WIN10 version of the Synthetic Video protocol with Hyper-V, +Hyper-V reports a list of supported resolutions as part of the protocol +negotiation. The driver calculates the maximum width and height from +the list of resolutions, and uses those maximums to validate any screen +resolution specified in the video= option on the kernel boot line. + +This method of validation is incorrect. For example, the list of +supported resolutions could contain 1600x1200 and 1920x1080, both of +which fit in an 8 Mbyte frame buffer. But calculating the max width +and height yields 1920 and 1200, and 1920x1200 resolution does not fit +in an 8 Mbyte frame buffer. Unfortunately, this resolution is accepted, +causing a kernel fault when the driver accesses memory outside the +frame buffer. + +Instead, validate the specified screen resolution by calculating +its size, and comparing against the frame buffer size. Delete the +code for calculating the max width and height from the list of +resolutions, since these max values have no use. Also add the +frame buffer size to the info message to aid in understanding why +a resolution might be rejected. + +Fixes: 67e7cdb4829d ("video: hyperv: hyperv_fb: Obtain screen resolution from Hyper-V host") +Signed-off-by: Michael Kelley +Reviewed-by: Haiyang Zhang +Acked-by: Helge Deller +Link: https://lore.kernel.org/r/1642360711-2335-1-git-send-email-mikelley@microsoft.com +Signed-off-by: Wei Liu +Signed-off-by: Sasha Levin +--- + drivers/video/fbdev/hyperv_fb.c | 16 +++------------- + 1 file changed, 3 insertions(+), 13 deletions(-) + +diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c +index 4dc9077dd2ac0..3c309ab208874 100644 +--- a/drivers/video/fbdev/hyperv_fb.c ++++ b/drivers/video/fbdev/hyperv_fb.c +@@ -286,8 +286,6 @@ struct hvfb_par { + + static uint screen_width = HVFB_WIDTH; + static uint screen_height = HVFB_HEIGHT; +-static uint screen_width_max = HVFB_WIDTH; +-static uint screen_height_max = HVFB_HEIGHT; + static uint screen_depth; + static uint screen_fb_size; + static uint dio_fb_size; /* FB size for deferred IO */ +@@ -581,7 +579,6 @@ static int synthvid_get_supported_resolution(struct hv_device *hdev) + int ret = 0; + unsigned long t; + u8 index; +- int i; + + memset(msg, 0, sizeof(struct synthvid_msg)); + msg->vid_hdr.type = SYNTHVID_RESOLUTION_REQUEST; +@@ -612,13 +609,6 @@ static int synthvid_get_supported_resolution(struct hv_device *hdev) + goto out; + } + +- for (i = 0; i < msg->resolution_resp.resolution_count; i++) { +- screen_width_max = max_t(unsigned int, screen_width_max, +- msg->resolution_resp.supported_resolution[i].width); +- screen_height_max = max_t(unsigned int, screen_height_max, +- msg->resolution_resp.supported_resolution[i].height); +- } +- + screen_width = + msg->resolution_resp.supported_resolution[index].width; + screen_height = +@@ -940,7 +930,7 @@ static void hvfb_get_option(struct fb_info *info) + + if (x < HVFB_WIDTH_MIN || y < HVFB_HEIGHT_MIN || + (synthvid_ver_ge(par->synthvid_version, SYNTHVID_VERSION_WIN10) && +- (x > screen_width_max || y > screen_height_max)) || ++ (x * y * screen_depth / 8 > screen_fb_size)) || + (par->synthvid_version == SYNTHVID_VERSION_WIN8 && + x * y * screen_depth / 8 > SYNTHVID_FB_SIZE_WIN8) || + (par->synthvid_version == SYNTHVID_VERSION_WIN7 && +@@ -1193,8 +1183,8 @@ static int hvfb_probe(struct hv_device *hdev, + } + + hvfb_get_option(info); +- pr_info("Screen resolution: %dx%d, Color depth: %d\n", +- screen_width, screen_height, screen_depth); ++ pr_info("Screen resolution: %dx%d, Color depth: %d, Frame buffer size: %d\n", ++ screen_width, screen_height, screen_depth, screen_fb_size); + + ret = hvfb_getmem(hdev, info); + if (ret) { +-- +2.34.1 + diff --git a/queue-5.10/yam-fix-a-memory-leak-in-yam_siocdevprivate.patch-10148 b/queue-5.10/yam-fix-a-memory-leak-in-yam_siocdevprivate.patch-10148 new file mode 100644 index 00000000000..95c7d72f219 --- /dev/null +++ b/queue-5.10/yam-fix-a-memory-leak-in-yam_siocdevprivate.patch-10148 @@ -0,0 +1,37 @@ +From 2e163ecb17ea8ee900cef2bb20cb4c1f1d062d1d Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 24 Jan 2022 11:29:54 +0800 +Subject: yam: fix a memory leak in yam_siocdevprivate() + +From: Hangyu Hua + +[ Upstream commit 29eb31542787e1019208a2e1047bb7c76c069536 ] + +ym needs to be free when ym->cmd != SIOCYAMSMCS. + +Fixes: 0781168e23a2 ("yam: fix a missing-check bug") +Signed-off-by: Hangyu Hua +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/hamradio/yam.c | 4 +--- + 1 file changed, 1 insertion(+), 3 deletions(-) + +diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c +index 5ab53e9942f30..5d30b3e1806ab 100644 +--- a/drivers/net/hamradio/yam.c ++++ b/drivers/net/hamradio/yam.c +@@ -951,9 +951,7 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) + sizeof(struct yamdrv_ioctl_mcs)); + if (IS_ERR(ym)) + return PTR_ERR(ym); +- if (ym->cmd != SIOCYAMSMCS) +- return -EINVAL; +- if (ym->bitrate > YAM_MAXBITRATE) { ++ if (ym->cmd != SIOCYAMSMCS || ym->bitrate > YAM_MAXBITRATE) { + kfree(ym); + return -EINVAL; + } +-- +2.34.1 +