From d6732317a5525a95a7eb2d12b46e3e42d321c6b6 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Fri, 25 Mar 2022 15:24:34 -0700 Subject: [PATCH 001/192] hwmon: (xdpe12284) Fix build warning seen if CONFIG_SENSORS_XDPE122_REGULATOR is disabled 0-day reports: drivers/hwmon/pmbus/xdpe12284.c:127:36: warning: unused variable 'xdpe122_reg_desc' This is seen if CONFIG_SENSORS_XDPE122_REGULATOR is not enabled. Mark xdpe122_reg_desc as __maybe_unused to fix the problem. Fixes: f53bfe4d6984 ("hwmon: (xdpe12284) Add regulator support") Reported-by: kernel test robot Cc: Marcello Sylvester Bauer Signed-off-by: Guenter Roeck --- drivers/hwmon/pmbus/xdpe12284.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/pmbus/xdpe12284.c b/drivers/hwmon/pmbus/xdpe12284.c index 18fffc5d749b..32bc7736d609 100644 --- a/drivers/hwmon/pmbus/xdpe12284.c +++ b/drivers/hwmon/pmbus/xdpe12284.c @@ -124,7 +124,7 @@ static int xdpe122_identify(struct i2c_client *client, return 0; } -static const struct regulator_desc xdpe122_reg_desc[] = { +static const struct regulator_desc __maybe_unused xdpe122_reg_desc[] = { PMBUS_REGULATOR("vout", 0), PMBUS_REGULATOR("vout", 1), }; From 4fd45cc8568e6086272d3036f2c29d61e9b776a1 Mon Sep 17 00:00:00 2001 From: Denis Pauk Date: Sun, 3 Apr 2022 22:34:54 +0300 Subject: [PATCH 002/192] hwmon: (asus_wmi_sensors) Fix CROSSHAIR VI HERO name CROSSHAIR VI HERO motherboard is incorrectly named as ROG CROSSHAIR VI HERO. Signed-off-by: Denis Pauk Link: https://lore.kernel.org/r/20220403193455.1363-1-pauk.denis@gmail.com Signed-off-by: Guenter Roeck --- drivers/hwmon/asus_wmi_sensors.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/asus_wmi_sensors.c b/drivers/hwmon/asus_wmi_sensors.c index 8fdcb62ae52d..9e935e34c998 100644 --- a/drivers/hwmon/asus_wmi_sensors.c +++ b/drivers/hwmon/asus_wmi_sensors.c @@ -71,7 +71,7 @@ static const struct dmi_system_id asus_wmi_dmi_table[] = { DMI_EXACT_MATCH_ASUS_BOARD_NAME("PRIME X399-A"), DMI_EXACT_MATCH_ASUS_BOARD_NAME("PRIME X470-PRO"), DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VI EXTREME"), - DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VI HERO"), + DMI_EXACT_MATCH_ASUS_BOARD_NAME("CROSSHAIR VI HERO"), DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VI HERO (WI-FI AC)"), DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VII HERO"), DMI_EXACT_MATCH_ASUS_BOARD_NAME("ROG CROSSHAIR VII HERO (WI-FI)"), From 7b2666ce445c700b8dcee994da44ddcf050a0842 Mon Sep 17 00:00:00 2001 From: Armin Wolf Date: Thu, 7 Apr 2022 12:13:12 +0200 Subject: [PATCH 003/192] hwmon: (adt7470) Fix warning on module removal When removing the adt7470 module, a warning might be printed: do not call blocking ops when !TASK_RUNNING; state=1 set at [] adt7470_update_thread+0x7b/0x130 [adt7470] This happens because adt7470_update_thread() can leave the kthread in TASK_INTERRUPTIBLE state when the kthread is being stopped before the call of set_current_state(). Since kthread_exit() might sleep in exit_signals(), the warning is printed. Fix that by using schedule_timeout_interruptible() and removing the call of set_current_state(). This causes TASK_INTERRUPTIBLE to be set after kthread_should_stop() which might cause the kthread to exit. Reported-by: Zheyu Ma Fixes: 93cacfd41f82 (hwmon: (adt7470) Allow faster removal) Signed-off-by: Armin Wolf Tested-by: Zheyu Ma Link: https://lore.kernel.org/r/20220407101312.13331-1-W_Armin@gmx.de Signed-off-by: Guenter Roeck --- drivers/hwmon/adt7470.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c index fb6d14d213a1..c67cd037a93f 100644 --- a/drivers/hwmon/adt7470.c +++ b/drivers/hwmon/adt7470.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -294,11 +295,10 @@ static int adt7470_update_thread(void *p) adt7470_read_temperatures(data); mutex_unlock(&data->lock); - set_current_state(TASK_INTERRUPTIBLE); if (kthread_should_stop()) break; - schedule_timeout(msecs_to_jiffies(data->auto_update_interval)); + schedule_timeout_interruptible(msecs_to_jiffies(data->auto_update_interval)); } return 0; From 290c4a902b79246ec55e477fc313f27f98393dee Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Sun, 10 Apr 2022 22:06:48 -0500 Subject: [PATCH 004/192] RDMA/rxe: Fix "Replace mr by rkey in responder resources" The referenced commit generates a reference counting error if the rkey has the same index but the wrong key. In this case the reference taken by rxe_pool_get_index() is not dropped. Drop the reference if the keys don't match in rxe_recheck_mr(). Check that the mw and mr are still valid. Fixes: 8a1a0be894da ("RDMA/rxe: Replace mr by rkey in responder resources") Link: https://lore.kernel.org/r/20220411030647.20011-1-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_resp.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 16fc7ea1298d..1d95fab606da 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -680,6 +680,11 @@ static struct resp_res *rxe_prepare_read_res(struct rxe_qp *qp, * It is assumed that the access permissions if originally good * are OK and the mappings to be unchanged. * + * TODO: If someone reregisters an MR to change its size or + * access permissions during the processing of an RDMA read + * we should kill the responder resource and complete the + * operation with an error. + * * Return: mr on success else NULL */ static struct rxe_mr *rxe_recheck_mr(struct rxe_qp *qp, u32 rkey) @@ -690,23 +695,27 @@ static struct rxe_mr *rxe_recheck_mr(struct rxe_qp *qp, u32 rkey) if (rkey_is_mw(rkey)) { mw = rxe_pool_get_index(&rxe->mw_pool, rkey >> 8); - if (!mw || mw->rkey != rkey) + if (!mw) return NULL; - if (mw->state != RXE_MW_STATE_VALID) { + mr = mw->mr; + if (mw->rkey != rkey || mw->state != RXE_MW_STATE_VALID || + !mr || mr->state != RXE_MR_STATE_VALID) { rxe_put(mw); return NULL; } - mr = mw->mr; + rxe_get(mr); rxe_put(mw); - } else { - mr = rxe_pool_get_index(&rxe->mr_pool, rkey >> 8); - if (!mr || mr->rkey != rkey) - return NULL; + + return mr; } - if (mr->state != RXE_MR_STATE_VALID) { + mr = rxe_pool_get_index(&rxe->mr_pool, rkey >> 8); + if (!mr) + return NULL; + + if (mr->rkey != rkey || mr->state != RXE_MR_STATE_VALID) { rxe_put(mr); return NULL; } From 4d0d5c352303a318925ceb84a86818761aa6586b Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 13 Apr 2022 08:47:29 -0500 Subject: [PATCH 005/192] dt-bindings: hwmon: ti,tmp421: Fix type for 'ti,n-factor' 'ti,n-factor' is read as a 32-bit signed value, so the type and constraints are wrong. The same property is also defined for ti,tmp464 and is correct. The constraints should also not be under 'items' as this property is not an array. Cc: Jean Delvare Cc: Guenter Roeck Cc: Krzysztof Kozlowski Cc: linux-hwmon@vger.kernel.org Signed-off-by: Rob Herring Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220413134729.3112190-1-robh@kernel.org Signed-off-by: Guenter Roeck --- Documentation/devicetree/bindings/hwmon/ti,tmp421.yaml | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/hwmon/ti,tmp421.yaml b/Documentation/devicetree/bindings/hwmon/ti,tmp421.yaml index 36f649938fb7..a6f1fa75a67c 100644 --- a/Documentation/devicetree/bindings/hwmon/ti,tmp421.yaml +++ b/Documentation/devicetree/bindings/hwmon/ti,tmp421.yaml @@ -58,10 +58,9 @@ patternProperties: description: | The value (two's complement) to be programmed in the channel specific N correction register. For remote channels only. - $ref: /schemas/types.yaml#/definitions/uint32 - items: - minimum: 0 - maximum: 255 + $ref: /schemas/types.yaml#/definitions/int32 + minimum: -128 + maximum: 127 required: - reg From 4aaaaf0f279836f06d3b9d0ffeec7a1e1a04ceef Mon Sep 17 00:00:00 2001 From: "Ji-Ze Hong (Peter Hong)" Date: Mon, 18 Apr 2022 17:07:06 +0800 Subject: [PATCH 006/192] hwmon: (f71882fg) Fix negative temperature All temperature of Fintek superio hwmonitor that using 1-byte reg will use 2's complement. In show_temp() temp = data->temp[nr] * 1000; When data->temp[nr] read as 255, it indicate -1C, but this code will report 255C to userspace. It'll be ok when change to: temp = ((s8)data->temp[nr]) * 1000; Signed-off-by: Ji-Ze Hong (Peter Hong) Link: https://lore.kernel.org/r/20220418090706.6339-1-hpeter+linux_kernel@gmail.com Signed-off-by: Guenter Roeck --- drivers/hwmon/f71882fg.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/hwmon/f71882fg.c b/drivers/hwmon/f71882fg.c index 938a8b9ec70d..6830e029995d 100644 --- a/drivers/hwmon/f71882fg.c +++ b/drivers/hwmon/f71882fg.c @@ -1578,8 +1578,9 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *devattr, temp *= 125; if (sign) temp -= 128000; - } else - temp = data->temp[nr] * 1000; + } else { + temp = ((s8)data->temp[nr]) * 1000; + } return sprintf(buf, "%d\n", temp); } From b4f5c6b2e52b27462c0599e64e96e53b58438de1 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sat, 16 Apr 2022 13:54:08 +0100 Subject: [PATCH 007/192] ASoC: wm8958: Fix change notifications for DSP controls The WM8958 DSP controls all return 0 on successful write, not a boolean value indicating if the write changed the value of the control. Fix this by returning 1 after a change, there is already a check at the start of each put() that skips the function in the case that there is no change. Signed-off-by: Mark Brown Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20220416125408.197440-1-broonie@kernel.org Cc: stable@vger.kernel.org --- sound/soc/codecs/wm8958-dsp2.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c index e4018ba3b19a..7878c7a58ff1 100644 --- a/sound/soc/codecs/wm8958-dsp2.c +++ b/sound/soc/codecs/wm8958-dsp2.c @@ -530,7 +530,7 @@ static int wm8958_mbc_put(struct snd_kcontrol *kcontrol, wm8958_dsp_apply(component, mbc, wm8994->mbc_ena[mbc]); - return 0; + return 1; } #define WM8958_MBC_SWITCH(xname, xval) {\ @@ -656,7 +656,7 @@ static int wm8958_vss_put(struct snd_kcontrol *kcontrol, wm8958_dsp_apply(component, vss, wm8994->vss_ena[vss]); - return 0; + return 1; } @@ -730,7 +730,7 @@ static int wm8958_hpf_put(struct snd_kcontrol *kcontrol, wm8958_dsp_apply(component, hpf % 3, ucontrol->value.integer.value[0]); - return 0; + return 1; } #define WM8958_HPF_SWITCH(xname, xval) {\ @@ -824,7 +824,7 @@ static int wm8958_enh_eq_put(struct snd_kcontrol *kcontrol, wm8958_dsp_apply(component, eq, ucontrol->value.integer.value[0]); - return 0; + return 1; } #define WM8958_ENH_EQ_SWITCH(xname, xval) {\ From 679ab61bf5f5f519377d812afb4fb93634782c74 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Mon, 18 Apr 2022 23:33:22 +0800 Subject: [PATCH 008/192] RDMA/irdma: Fix deadlock in irdma_cleanup_cm_core() There is a deadlock in irdma_cleanup_cm_core(), which is shown below: (Thread 1) | (Thread 2) | irdma_schedule_cm_timer() irdma_cleanup_cm_core() | add_timer() spin_lock_irqsave() //(1) | (wait a time) ... | irdma_cm_timer_tick() del_timer_sync() | spin_lock_irqsave() //(2) (wait timer to stop) | ... We hold cm_core->ht_lock in position (1) of thread 1 and use del_timer_sync() to wait timer to stop, but timer handler also need cm_core->ht_lock in position (2) of thread 2. As a result, irdma_cleanup_cm_core() will block forever. This patch removes the check of timer_pending() in irdma_cleanup_cm_core(), because the del_timer_sync() function will just return directly if there isn't a pending timer. As a result, the lock is redundant, because there is no resource it could protect. Link: https://lore.kernel.org/r/20220418153322.42524-1-duoming@zju.edu.cn Signed-off-by: Duoming Zhou Reviewed-by: Shiraz Saleem Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/cm.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c index dedb3b7edd8d..a98d962e5efb 100644 --- a/drivers/infiniband/hw/irdma/cm.c +++ b/drivers/infiniband/hw/irdma/cm.c @@ -3246,15 +3246,10 @@ int irdma_setup_cm_core(struct irdma_device *iwdev, u8 rdma_ver) */ void irdma_cleanup_cm_core(struct irdma_cm_core *cm_core) { - unsigned long flags; - if (!cm_core) return; - spin_lock_irqsave(&cm_core->ht_lock, flags); - if (timer_pending(&cm_core->tcp_timer)) - del_timer_sync(&cm_core->tcp_timer); - spin_unlock_irqrestore(&cm_core->ht_lock, flags); + del_timer_sync(&cm_core->tcp_timer); destroy_workqueue(cm_core->event_wq); cm_core->dev->ws_reset(&cm_core->iwdev->vsi); From 95d4782c34a60800ccf91d9f0703137d4367a2fc Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Tue, 19 Apr 2022 14:01:58 -0700 Subject: [PATCH 009/192] iommu/arm-smmu-v3: Fix size calculation in arm_smmu_mm_invalidate_range() The arm_smmu_mm_invalidate_range function is designed to be called by mm core for Shared Virtual Addressing purpose between IOMMU and CPU MMU. However, the ways of two subsystems defining their "end" addresses are slightly different. IOMMU defines its "end" address using the last address of an address range, while mm core defines that using the following address of an address range: include/linux/mm_types.h: unsigned long vm_end; /* The first byte after our end address ... This mismatch resulted in an incorrect calculation for size so it failed to be page-size aligned. Further, it caused a dead loop at "while (iova < end)" check in __arm_smmu_tlb_inv_range function. This patch fixes the issue by doing the calculation correctly. Fixes: 2f7e8c553e98 ("iommu/arm-smmu-v3: Hook up ATC invalidation to mm ops") Cc: stable@vger.kernel.org Signed-off-by: Nicolin Chen Reviewed-by: Jason Gunthorpe Reviewed-by: Robin Murphy Reviewed-by: Jean-Philippe Brucker Link: https://lore.kernel.org/r/20220419210158.21320-1-nicolinc@nvidia.com Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c index 22ddd05bbdcd..c623dae1e115 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -183,7 +183,14 @@ static void arm_smmu_mm_invalidate_range(struct mmu_notifier *mn, { struct arm_smmu_mmu_notifier *smmu_mn = mn_to_smmu(mn); struct arm_smmu_domain *smmu_domain = smmu_mn->domain; - size_t size = end - start + 1; + size_t size; + + /* + * The mm_types defines vm_end as the first byte after the end address, + * different from IOMMU subsystem using the last address of an address + * range. So do a simple translation here by calculating size correctly. + */ + size = end - start; if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_BTM)) arm_smmu_tlb_inv_range_asid(start, size, smmu_mn->cd->asid, From 3756aa16fadaef2873cfbd2659dfa1978a7e1859 Mon Sep 17 00:00:00 2001 From: Olivier Moysan Date: Tue, 12 Apr 2022 13:16:58 +0200 Subject: [PATCH 010/192] ASoC: simple-card-utils: fix sysclk shutdown In asoc_simple_shutdown() the snd_soc_dai_set_sysclk() function is called twice with input direction SND_SOC_CLOCK_IN. Restore one call with output direction SND_SOC_CLOCK_OUT. Fixes: 5ca2ab459817 ("ASoC: simple-card-utils: Add new system-clock-fixed flag") Signed-off-by: Olivier Moysan Link: https://lore.kernel.org/r/20220412111658.11015-1-olivier.moysan@foss.st.com Signed-off-by: Mark Brown --- sound/soc/generic/simple-card-utils.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index f2157944247f..da0c27828ce6 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -322,7 +322,7 @@ void asoc_simple_shutdown(struct snd_pcm_substream *substream) if (props->mclk_fs && !dai->clk_fixed && !snd_soc_dai_active(cpu_dai)) snd_soc_dai_set_sysclk(cpu_dai, - 0, 0, SND_SOC_CLOCK_IN); + 0, 0, SND_SOC_CLOCK_OUT); asoc_simple_clk_disable(dai); } From 570a4bf7440e9fb2a4164244a6bf60a46362b627 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Mon, 18 Apr 2022 12:41:04 -0500 Subject: [PATCH 011/192] RDMA/rxe: Recheck the MR in when generating a READ reply The rping benchmark fails on long runs. The root cause of this failure has been traced to a failure to compute a nonzero value of mr in rare situations. Fix this failure by correctly handling the computation of mr in read_reply() in rxe_resp.c in the replay flow. Fixes: 8a1a0be894da ("RDMA/rxe: Replace mr by rkey in responder resources") Link: https://lore.kernel.org/r/20220418174103.3040-1-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_resp.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 1d95fab606da..9cd0eaff98de 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -745,8 +745,14 @@ static enum resp_states read_reply(struct rxe_qp *qp, } if (res->state == rdatm_res_state_new) { - mr = qp->resp.mr; - qp->resp.mr = NULL; + if (!res->replay) { + mr = qp->resp.mr; + qp->resp.mr = NULL; + } else { + mr = rxe_recheck_mr(qp, res->read.rkey); + if (!mr) + return RESPST_ERR_RKEY_VIOLATION; + } if (res->read.resid <= mtu) opcode = IB_OPCODE_RC_RDMA_READ_RESPONSE_ONLY; From 08ef48404965cfef99343d6bbbcf75b88c74aa0e Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 20 Apr 2022 14:34:37 +0100 Subject: [PATCH 012/192] ASoC: da7219: Fix change notifications for tone generator frequency The tone generator frequency control just returns 0 on successful write, not a boolean value indicating if there was a change or not. Compare what was written with the value that was there previously so that notifications are generated appropriately when the value changes. Signed-off-by: Mark Brown Reviewed-by: Adam Thomson Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220420133437.569229-1-broonie@kernel.org Signed-off-by: Mark Brown --- sound/soc/codecs/da7219.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/sound/soc/codecs/da7219.c b/sound/soc/codecs/da7219.c index 13009d08b09a..c7493549a9a5 100644 --- a/sound/soc/codecs/da7219.c +++ b/sound/soc/codecs/da7219.c @@ -446,7 +446,7 @@ static int da7219_tonegen_freq_put(struct snd_kcontrol *kcontrol, struct soc_mixer_control *mixer_ctrl = (struct soc_mixer_control *) kcontrol->private_value; unsigned int reg = mixer_ctrl->reg; - __le16 val; + __le16 val_new, val_old; int ret; /* @@ -454,13 +454,19 @@ static int da7219_tonegen_freq_put(struct snd_kcontrol *kcontrol, * Therefore we need to convert to little endian here to align with * HW registers. */ - val = cpu_to_le16(ucontrol->value.integer.value[0]); + val_new = cpu_to_le16(ucontrol->value.integer.value[0]); mutex_lock(&da7219->ctrl_lock); - ret = regmap_raw_write(da7219->regmap, reg, &val, sizeof(val)); + ret = regmap_raw_read(da7219->regmap, reg, &val_old, sizeof(val_old)); + if (ret == 0 && (val_old != val_new)) + ret = regmap_raw_write(da7219->regmap, reg, + &val_new, sizeof(val_new)); mutex_unlock(&da7219->ctrl_lock); - return ret; + if (ret < 0) + return ret; + + return val_old != val_new; } From 2e3a0d1bfa95b54333f7add3e50e288769373873 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 21 Apr 2022 13:38:01 +0100 Subject: [PATCH 013/192] ASoC: meson: Fix event generation for AUI ACODEC mux The AIU ACODEC has a custom put() operation which returns 0 when the value of the mux changes, meaning that events are not generated for userspace. Change to return 1 in this case, the function returns early in the case where there is no change. Signed-off-by: Mark Brown Reviewed-by: Jerome Brunet Link: https://lore.kernel.org/r/20220421123803.292063-2-broonie@kernel.org Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- sound/soc/meson/aiu-acodec-ctrl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/meson/aiu-acodec-ctrl.c b/sound/soc/meson/aiu-acodec-ctrl.c index 22e181646bc3..3776b073a3db 100644 --- a/sound/soc/meson/aiu-acodec-ctrl.c +++ b/sound/soc/meson/aiu-acodec-ctrl.c @@ -58,7 +58,7 @@ static int aiu_acodec_ctrl_mux_put_enum(struct snd_kcontrol *kcontrol, snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); - return 0; + return 1; } static SOC_ENUM_SINGLE_DECL(aiu_acodec_ctrl_mux_enum, AIU_ACODEC_CTRL, From fce49921a22262736cdc3cc74fa67915b75e9363 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 21 Apr 2022 13:38:02 +0100 Subject: [PATCH 014/192] ASoC: meson: Fix event generation for AUI CODEC mux The AIU CODEC has a custom put() operation which returns 0 when the value of the mux changes, meaning that events are not generated for userspace. Change to return 1 in this case, the function returns early in the case where there is no change. Signed-off-by: Mark Brown Reviewed-by: Jerome Brunet Link: https://lore.kernel.org/r/20220421123803.292063-3-broonie@kernel.org Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- sound/soc/meson/aiu-codec-ctrl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/meson/aiu-codec-ctrl.c b/sound/soc/meson/aiu-codec-ctrl.c index 59ee66fc2bcd..286ac4983d40 100644 --- a/sound/soc/meson/aiu-codec-ctrl.c +++ b/sound/soc/meson/aiu-codec-ctrl.c @@ -57,7 +57,7 @@ static int aiu_codec_ctrl_mux_put_enum(struct snd_kcontrol *kcontrol, snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); - return 0; + return 1; } static SOC_ENUM_SINGLE_DECL(aiu_hdmi_ctrl_mux_enum, AIU_HDMI_CLK_DATA_CTRL, From 12131008fc13ff7f7690d170b7a8f72d24fd7d1e Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 21 Apr 2022 13:38:03 +0100 Subject: [PATCH 015/192] ASoC: meson: Fix event generation for G12A tohdmi mux The G12A tohdmi has a custom put() operation which returns 0 when the value of the mux changes, meaning that events are not generated for userspace. Change to return 1 in this case, the function returns early in the case where there is no change. Signed-off-by: Mark Brown Reviewed-by: Jerome Brunet Link: https://lore.kernel.org/r/20220421123803.292063-4-broonie@kernel.org Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- sound/soc/meson/g12a-tohdmitx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/meson/g12a-tohdmitx.c b/sound/soc/meson/g12a-tohdmitx.c index 9b2b59536ced..6c99052feafd 100644 --- a/sound/soc/meson/g12a-tohdmitx.c +++ b/sound/soc/meson/g12a-tohdmitx.c @@ -67,7 +67,7 @@ static int g12a_tohdmitx_i2s_mux_put_enum(struct snd_kcontrol *kcontrol, snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); - return 0; + return 1; } static SOC_ENUM_SINGLE_DECL(g12a_tohdmitx_i2s_mux_enum, TOHDMITX_CTRL0, From eb5773201b1c5d603424bd21f161c8c2d1075b42 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 21 Apr 2022 11:23:28 -0500 Subject: [PATCH 016/192] ASoC: soc-ops: fix error handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit cppcheck throws the following warning: sound/soc/soc-ops.c:461:8: style: Variable 'ret' is assigned a value that is never used. [unreadVariable] ret = err; ^ This seems to be a missing change in the return value. Fixes: 7f3d90a351968 ("ASoC: ops: Fix stereo change notifications in snd_soc_put_volsw_sx()") Signed-off-by: Pierre-Louis Bossart Reviewed-by: Bard Liao Reviewed-by: Rander Wang Reviewed-by: Péter Ujfalusi Link: https://lore.kernel.org/r/20220421162328.302017-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/soc-ops.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index a0ca58ba1627..58347eadd219 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -461,7 +461,7 @@ int snd_soc_put_volsw_sx(struct snd_kcontrol *kcontrol, ret = err; } } - return err; + return ret; } EXPORT_SYMBOL_GPL(snd_soc_put_volsw_sx); From c26830b6c5c534d273ce007eb33d5a2d2ad4e969 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Thu, 21 Apr 2022 17:57:24 +0200 Subject: [PATCH 017/192] ASoC: meson: axg-tdm-interface: Fix formatters in trigger" This reverts commit bf5e4887eeddb48480568466536aa08ec7f179a5 because the following and required commit e138233e56e9829e65b6293887063a1a3ccb2d68 causes the following system crash when using audio: BUG: sleeping function called from invalid context at kernel/locking/mutex.c:282 Fixes: bf5e4887eeddb4848056846 ("ASoC: meson: axg-tdm-interface: manage formatters in trigger") Reported-by: Dmitry Shmidt Signed-off-by: Neil Armstrong Acked-by: Jerome Brunet Link: https://lore.kernel.org/r/20220421155725.2589089-1-narmstrong@baylibre.com Signed-off-by: Mark Brown --- sound/soc/meson/axg-tdm-interface.c | 26 +++++--------------------- 1 file changed, 5 insertions(+), 21 deletions(-) diff --git a/sound/soc/meson/axg-tdm-interface.c b/sound/soc/meson/axg-tdm-interface.c index 0c31934a9630..e076ced30025 100644 --- a/sound/soc/meson/axg-tdm-interface.c +++ b/sound/soc/meson/axg-tdm-interface.c @@ -351,29 +351,13 @@ static int axg_tdm_iface_hw_free(struct snd_pcm_substream *substream, return 0; } -static int axg_tdm_iface_trigger(struct snd_pcm_substream *substream, - int cmd, +static int axg_tdm_iface_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { - struct axg_tdm_stream *ts = - snd_soc_dai_get_dma_data(dai, substream); + struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream); - switch (cmd) { - case SNDRV_PCM_TRIGGER_START: - case SNDRV_PCM_TRIGGER_RESUME: - case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: - axg_tdm_stream_start(ts); - break; - case SNDRV_PCM_TRIGGER_SUSPEND: - case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - case SNDRV_PCM_TRIGGER_STOP: - axg_tdm_stream_stop(ts); - break; - default: - return -EINVAL; - } - - return 0; + /* Force all attached formatters to update */ + return axg_tdm_stream_reset(ts); } static int axg_tdm_iface_remove_dai(struct snd_soc_dai *dai) @@ -413,8 +397,8 @@ static const struct snd_soc_dai_ops axg_tdm_iface_ops = { .set_fmt = axg_tdm_iface_set_fmt, .startup = axg_tdm_iface_startup, .hw_params = axg_tdm_iface_hw_params, + .prepare = axg_tdm_iface_prepare, .hw_free = axg_tdm_iface_hw_free, - .trigger = axg_tdm_iface_trigger, }; /* TDM Backend DAIs */ From 0c9b152c72e53016e96593bdbb8cffe2176694b9 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Thu, 21 Apr 2022 17:57:25 +0200 Subject: [PATCH 018/192] ASoC: meson: axg-card: Fix nonatomic links This commit e138233e56e9829e65b6293887063a1a3ccb2d68 causes the following system crash when using audio on G12A/G12B & SM1 systems: BUG: sleeping function called from invalid context at kernel/locking/mutex.c:282 in_atomic(): 1, irqs_disabled(): 128, non_block: 0, pid: 0, name: swapper/0 preempt_count: 10001, expected: 0 RCU nest depth: 0, expected: 0 Preemption disabled at: schedule_preempt_disabled+0x20/0x2c mutex_lock+0x24/0x60 _snd_pcm_stream_lock_irqsave+0x20/0x3c snd_pcm_period_elapsed+0x24/0xa4 axg_fifo_pcm_irq_block+0x64/0xdc __handle_irq_event_percpu+0x104/0x264 handle_irq_event+0x48/0xb4 ... start_kernel+0x3f0/0x484 __primary_switched+0xc0/0xc8 Revert this commit until the crash is fixed. Fixes: e138233e56e9829e65b6 ("ASoC: meson: axg-card: make links nonatomic") Reported-by: Dmitry Shmidt Signed-off-by: Neil Armstrong Acked-by: Jerome Brunet Link: https://lore.kernel.org/r/20220421155725.2589089-2-narmstrong@baylibre.com Signed-off-by: Mark Brown --- sound/soc/meson/axg-card.c | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/soc/meson/axg-card.c b/sound/soc/meson/axg-card.c index cbbaa55d92a6..2b77010c2c5c 100644 --- a/sound/soc/meson/axg-card.c +++ b/sound/soc/meson/axg-card.c @@ -320,7 +320,6 @@ static int axg_card_add_link(struct snd_soc_card *card, struct device_node *np, dai_link->cpus = cpu; dai_link->num_cpus = 1; - dai_link->nonatomic = true; ret = meson_card_parse_dai(card, np, &dai_link->cpus->of_node, &dai_link->cpus->dai_name); From 60cc5468daaefc18ffc081dc484bdaa1bd270561 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andr=C3=A9=20Almeida?= Date: Thu, 21 Apr 2022 14:32:54 -0300 Subject: [PATCH 019/192] =?UTF-8?q?futex:=20MAINTAINERS,=20.mailmap:=20Upd?= =?UTF-8?q?ate=20Andr=C3=A9's=20email=20address?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Update futex entry to use my new professional email address. Signed-off-by: André Almeida Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20220421173254.29855-1-andrealmeid@igalia.com --- .mailmap | 1 + MAINTAINERS | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/.mailmap b/.mailmap index 93458154ce7d..ea1ba4a9a77e 100644 --- a/.mailmap +++ b/.mailmap @@ -45,6 +45,7 @@ Andrey Konovalov Andrey Ryabinin Andrey Ryabinin Andrzej Hajda +André Almeida Andy Adamson Antoine Tenart Antoine Tenart diff --git a/MAINTAINERS b/MAINTAINERS index 40fa1955ca3f..35dea3d12981 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8109,7 +8109,7 @@ M: Ingo Molnar R: Peter Zijlstra R: Darren Hart R: Davidlohr Bueso -R: André Almeida +R: André Almeida L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core From 214cab6f8020a9ad4a5e9862a4e68088d5a79f08 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Mon, 18 Apr 2022 21:20:16 +0000 Subject: [PATCH 020/192] MAINTAINERS: Update email address for John Stultz I've switched jobs, so update my email address in MAINTAINERS Signed-off-by: John Stultz Signed-off-by: Thomas Gleixner Acked-by: Sumit Semwal Link: https://lore.kernel.org/r/20220418212016.2669086-1-jstultz@google.com --- MAINTAINERS | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 40fa1955ca3f..c2e1b7202449 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5914,7 +5914,7 @@ R: Benjamin Gaignard R: Liam Mark R: Laura Abbott R: Brian Starkey -R: John Stultz +R: John Stultz L: linux-media@vger.kernel.org L: dri-devel@lists.freedesktop.org L: linaro-mm-sig@lists.linaro.org (moderated for non-subscribers) @@ -6584,7 +6584,7 @@ F: drivers/gpu/drm/gma500/ DRM DRIVERS FOR HISILICON M: Xinliang Liu M: Tian Tao -R: John Stultz +R: John Stultz R: Xinwei Kong R: Chen Feng L: dri-devel@lists.freedesktop.org @@ -8845,7 +8845,7 @@ F: Documentation/devicetree/bindings/net/hisilicon*.txt F: drivers/net/ethernet/hisilicon/ HIKEY960 ONBOARD USB GPIO HUB DRIVER -M: John Stultz +M: John Stultz L: linux-kernel@vger.kernel.org S: Maintained F: drivers/misc/hisi_hikey_usb.c @@ -19784,7 +19784,7 @@ F: drivers/net/wireless/ti/ F: include/linux/wl12xx.h TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER -M: John Stultz +M: John Stultz M: Thomas Gleixner R: Stephen Boyd L: linux-kernel@vger.kernel.org From a6ac60b36dade525c13c5bb0838589619533efb7 Mon Sep 17 00:00:00 2001 From: Hui Wang Date: Fri, 22 Apr 2022 15:39:37 +0800 Subject: [PATCH 021/192] ALSA: hda/realtek: Fix mute led issue on thinkpad with cs35l41 s-codec The quirk ALC287_FIXUP_CS35L41_I2C_2 needs to chain the quirk ALC269_FIXUP_THINKPAD_ACPI, otherwise the mute led will not work if a thinkpad machine applies that quirk. And it will be safe if non-thinkpad machines apply that quirk since hda_fixup_thinkpad_acpi() will check and return in this case. Fixes: ae7abe36e352e ("ALSA: hda/realtek: Add CS35L41 support for Thinkpad laptops") Signed-off-by: Hui Wang Link: https://lore.kernel.org/r/20220422073937.10073-1-hui.wang@canonical.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4c0c593f3c0a..f9c3b2c9ca12 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8769,6 +8769,8 @@ static const struct hda_fixup alc269_fixups[] = { [ALC287_FIXUP_CS35L41_I2C_2] = { .type = HDA_FIXUP_FUNC, .v.func = cs35l41_fixup_i2c_two, + .chained = true, + .chain_id = ALC269_FIXUP_THINKPAD_ACPI, }, [ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED] = { .type = HDA_FIXUP_FUNC, From 5f5d8890789c90470d9571a283f0b789acd594af Mon Sep 17 00:00:00 2001 From: Andy Chi Date: Fri, 22 Apr 2022 17:08:43 +0800 Subject: [PATCH 022/192] ALSA: hda/realtek: Enable mute/micmute LEDs support for HP Laptops On HP Laptops, requires the same ALC285_FIXUP_HP_GPIO_LED quirk to make its audio LEDs work. So apply the quirk, and make it the last one since it's an LED quirk. Signed-off-by: Andy Chi Fixes: 07bcab93946c ("ALSA: hda/realtek: Add support for HP Laptops") Link: https://lore.kernel.org/r/20220422090845.230071-1-andy.chi@canonical.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index f9c3b2c9ca12..c65d3dbc6cc9 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9025,12 +9025,12 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8896, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED), - SND_PCI_QUIRK(0x103c, 0x896e, "HP EliteBook x360 830 G9", ALC245_FIXUP_CS35L41_SPI_2), - SND_PCI_QUIRK(0x103c, 0x8971, "HP EliteBook 830 G9", ALC245_FIXUP_CS35L41_SPI_2), - SND_PCI_QUIRK(0x103c, 0x8972, "HP EliteBook 840 G9", ALC245_FIXUP_CS35L41_SPI_2), - SND_PCI_QUIRK(0x103c, 0x8973, "HP EliteBook 860 G9", ALC245_FIXUP_CS35L41_SPI_2), - SND_PCI_QUIRK(0x103c, 0x8974, "HP EliteBook 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2), - SND_PCI_QUIRK(0x103c, 0x8975, "HP EliteBook x360 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x103c, 0x896e, "HP EliteBook x360 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8971, "HP EliteBook 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8972, "HP EliteBook 840 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8973, "HP EliteBook 860 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8974, "HP EliteBook 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8975, "HP EliteBook x360 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8981, "HP Elite Dragonfly G3", ALC245_FIXUP_CS35L41_SPI_4), SND_PCI_QUIRK(0x103c, 0x898e, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x898f, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), From 4a25f2ea0e030b2fc852c4059a50181bfc5b2f57 Mon Sep 17 00:00:00 2001 From: Ashish Mhetre Date: Thu, 21 Apr 2022 13:45:04 +0530 Subject: [PATCH 023/192] iommu: arm-smmu: disable large page mappings for Nvidia arm-smmu Tegra194 and Tegra234 SoCs have the erratum that causes walk cache entries to not be invalidated correctly. The problem is that the walk cache index generated for IOVA is not same across translation and invalidation requests. This is leading to page faults when PMD entry is released during unmap and populated with new PTE table during subsequent map request. Disabling large page mappings avoids the release of PMD entry and avoid translations seeing stale PMD entry in walk cache. Fix this by limiting the page mappings to PAGE_SIZE for Tegra194 and Tegra234 devices. This is recommended fix from Tegra hardware design team. Acked-by: Robin Murphy Reviewed-by: Krishna Reddy Co-developed-by: Pritesh Raithatha Signed-off-by: Pritesh Raithatha Signed-off-by: Ashish Mhetre Link: https://lore.kernel.org/r/20220421081504.24678-1-amhetre@nvidia.com Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c | 30 ++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c index 01e9b50b10a1..87bf522b9d2e 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c @@ -258,6 +258,34 @@ static void nvidia_smmu_probe_finalize(struct arm_smmu_device *smmu, struct devi dev_name(dev), err); } +static int nvidia_smmu_init_context(struct arm_smmu_domain *smmu_domain, + struct io_pgtable_cfg *pgtbl_cfg, + struct device *dev) +{ + struct arm_smmu_device *smmu = smmu_domain->smmu; + const struct device_node *np = smmu->dev->of_node; + + /* + * Tegra194 and Tegra234 SoCs have the erratum that causes walk cache + * entries to not be invalidated correctly. The problem is that the walk + * cache index generated for IOVA is not same across translation and + * invalidation requests. This is leading to page faults when PMD entry + * is released during unmap and populated with new PTE table during + * subsequent map request. Disabling large page mappings avoids the + * release of PMD entry and avoid translations seeing stale PMD entry in + * walk cache. + * Fix this by limiting the page mappings to PAGE_SIZE on Tegra194 and + * Tegra234. + */ + if (of_device_is_compatible(np, "nvidia,tegra234-smmu") || + of_device_is_compatible(np, "nvidia,tegra194-smmu")) { + smmu->pgsize_bitmap = PAGE_SIZE; + pgtbl_cfg->pgsize_bitmap = smmu->pgsize_bitmap; + } + + return 0; +} + static const struct arm_smmu_impl nvidia_smmu_impl = { .read_reg = nvidia_smmu_read_reg, .write_reg = nvidia_smmu_write_reg, @@ -268,10 +296,12 @@ static const struct arm_smmu_impl nvidia_smmu_impl = { .global_fault = nvidia_smmu_global_fault, .context_fault = nvidia_smmu_context_fault, .probe_finalize = nvidia_smmu_probe_finalize, + .init_context = nvidia_smmu_init_context, }; static const struct arm_smmu_impl nvidia_smmu_single_impl = { .probe_finalize = nvidia_smmu_probe_finalize, + .init_context = nvidia_smmu_init_context, }; struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu) From 87c18514bb8477563a61f50b4285da156296edc4 Mon Sep 17 00:00:00 2001 From: ChiYuan Huang Date: Fri, 22 Apr 2022 14:26:50 +0800 Subject: [PATCH 024/192] ASoC: rt9120: Correct the reg 0x09 size to one byte Correct the reg 0x09 size to one byte. Signed-off-by: ChiYuan Huang Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/1650608810-3829-1-git-send-email-u0084500@gmail.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt9120.c | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/soc/codecs/rt9120.c b/sound/soc/codecs/rt9120.c index 7aa1772a915f..6e0d7cf0c8c9 100644 --- a/sound/soc/codecs/rt9120.c +++ b/sound/soc/codecs/rt9120.c @@ -341,7 +341,6 @@ static int rt9120_get_reg_size(unsigned int reg) { switch (reg) { case 0x00: - case 0x09: case 0x20 ... 0x27: return 2; case 0x30 ... 0x3D: From e13433b4416fa31a24e621cbbbb39227a3d651dd Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Thu, 21 Apr 2022 10:32:34 -0400 Subject: [PATCH 025/192] SUNRPC release the transport of a relocated task with an assigned transport A relocated task must release its previous transport. Fixes: 82ee41b85cef1 ("SUNRPC don't resend a task on an offlined transport") Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust --- net/sunrpc/clnt.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index af0174d7ce5a..98133aa54f19 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1065,10 +1065,13 @@ rpc_task_get_next_xprt(struct rpc_clnt *clnt) static void rpc_task_set_transport(struct rpc_task *task, struct rpc_clnt *clnt) { - if (task->tk_xprt && - !(test_bit(XPRT_OFFLINE, &task->tk_xprt->state) && - (task->tk_flags & RPC_TASK_MOVEABLE))) - return; + if (task->tk_xprt) { + if (!(test_bit(XPRT_OFFLINE, &task->tk_xprt->state) && + (task->tk_flags & RPC_TASK_MOVEABLE))) + return; + xprt_release(task); + xprt_put(task->tk_xprt); + } if (task->tk_flags & RPC_TASK_NO_ROUND_ROBIN) task->tk_xprt = rpc_task_get_first_xprt(clnt); else From b7c81f80246fac44077166f3e07103affe6db8ff Mon Sep 17 00:00:00 2001 From: Chengfeng Ye Date: Sat, 9 Apr 2022 13:12:41 +0900 Subject: [PATCH 026/192] firewire: fix potential uaf in outbound_phy_packet_callback() &e->event and e point to the same address, and &e->event could be freed in queue_event. So there is a potential uaf issue if we dereference e after calling queue_event(). Fix this by adding a temporary variable to maintain e->client in advance, this can avoid the potential uaf issue. Cc: Signed-off-by: Chengfeng Ye Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20220409041243.603210-2-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- drivers/firewire/core-cdev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 9f89c17730b1..708e417200f4 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -1500,6 +1500,7 @@ static void outbound_phy_packet_callback(struct fw_packet *packet, { struct outbound_phy_packet_event *e = container_of(packet, struct outbound_phy_packet_event, p); + struct client *e_client; switch (status) { /* expected: */ @@ -1516,9 +1517,10 @@ static void outbound_phy_packet_callback(struct fw_packet *packet, } e->phy_packet.data[0] = packet->timestamp; + e_client = e->client; queue_event(e->client, &e->event, &e->phy_packet, sizeof(e->phy_packet) + e->phy_packet.length, NULL, 0); - client_put(e->client); + client_put(e_client); } static int ioctl_send_phy_packet(struct client *client, union ioctl_arg *arg) From 9423973869bd4632ffe669f950510c49296656e0 Mon Sep 17 00:00:00 2001 From: Jakob Koschel Date: Sat, 9 Apr 2022 13:12:42 +0900 Subject: [PATCH 027/192] firewire: remove check of list iterator against head past the loop body When list_for_each_entry() completes the iteration over the whole list without breaking the loop, the iterator value will be a bogus pointer computed based on the head element. While it is safe to use the pointer to determine if it was computed based on the head element, either with list_entry_is_head() or &pos->member == head, using the iterator variable after the loop should be avoided. In preparation to limit the scope of a list iterator to the list traversal loop, use a dedicated pointer to point to the found element [1]. Link: https://lore.kernel.org/all/CAHk-=wgRr_D8CB-D9Kg-c=EHreAsk5SqXPwr9Y7k9sA6cWXJ6w@mail.gmail.com/ [1] Cc: Signed-off-by: Jakob Koschel Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20220409041243.603210-3-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- drivers/firewire/core-transaction.c | 30 +++++++++++++++-------------- drivers/firewire/sbp2.c | 13 +++++++------ 2 files changed, 23 insertions(+), 20 deletions(-) diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index ac487c96bb71..6c20815cc8d1 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -73,24 +73,25 @@ static int try_cancel_split_timeout(struct fw_transaction *t) static int close_transaction(struct fw_transaction *transaction, struct fw_card *card, int rcode) { - struct fw_transaction *t; + struct fw_transaction *t = NULL, *iter; unsigned long flags; spin_lock_irqsave(&card->lock, flags); - list_for_each_entry(t, &card->transaction_list, link) { - if (t == transaction) { - if (!try_cancel_split_timeout(t)) { + list_for_each_entry(iter, &card->transaction_list, link) { + if (iter == transaction) { + if (!try_cancel_split_timeout(iter)) { spin_unlock_irqrestore(&card->lock, flags); goto timed_out; } - list_del_init(&t->link); - card->tlabel_mask &= ~(1ULL << t->tlabel); + list_del_init(&iter->link); + card->tlabel_mask &= ~(1ULL << iter->tlabel); + t = iter; break; } } spin_unlock_irqrestore(&card->lock, flags); - if (&t->link != &card->transaction_list) { + if (t) { t->callback(card, rcode, NULL, 0, t->callback_data); return 0; } @@ -935,7 +936,7 @@ EXPORT_SYMBOL(fw_core_handle_request); void fw_core_handle_response(struct fw_card *card, struct fw_packet *p) { - struct fw_transaction *t; + struct fw_transaction *t = NULL, *iter; unsigned long flags; u32 *data; size_t data_length; @@ -947,20 +948,21 @@ void fw_core_handle_response(struct fw_card *card, struct fw_packet *p) rcode = HEADER_GET_RCODE(p->header[1]); spin_lock_irqsave(&card->lock, flags); - list_for_each_entry(t, &card->transaction_list, link) { - if (t->node_id == source && t->tlabel == tlabel) { - if (!try_cancel_split_timeout(t)) { + list_for_each_entry(iter, &card->transaction_list, link) { + if (iter->node_id == source && iter->tlabel == tlabel) { + if (!try_cancel_split_timeout(iter)) { spin_unlock_irqrestore(&card->lock, flags); goto timed_out; } - list_del_init(&t->link); - card->tlabel_mask &= ~(1ULL << t->tlabel); + list_del_init(&iter->link); + card->tlabel_mask &= ~(1ULL << iter->tlabel); + t = iter; break; } } spin_unlock_irqrestore(&card->lock, flags); - if (&t->link == &card->transaction_list) { + if (!t) { timed_out: fw_notice(card, "unsolicited response (source %x, tlabel %x)\n", source, tlabel); diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index 85cd379fd383..60051c0cabea 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -408,7 +408,7 @@ static void sbp2_status_write(struct fw_card *card, struct fw_request *request, void *payload, size_t length, void *callback_data) { struct sbp2_logical_unit *lu = callback_data; - struct sbp2_orb *orb; + struct sbp2_orb *orb = NULL, *iter; struct sbp2_status status; unsigned long flags; @@ -433,17 +433,18 @@ static void sbp2_status_write(struct fw_card *card, struct fw_request *request, /* Lookup the orb corresponding to this status write. */ spin_lock_irqsave(&lu->tgt->lock, flags); - list_for_each_entry(orb, &lu->orb_list, link) { + list_for_each_entry(iter, &lu->orb_list, link) { if (STATUS_GET_ORB_HIGH(status) == 0 && - STATUS_GET_ORB_LOW(status) == orb->request_bus) { - orb->rcode = RCODE_COMPLETE; - list_del(&orb->link); + STATUS_GET_ORB_LOW(status) == iter->request_bus) { + iter->rcode = RCODE_COMPLETE; + list_del(&iter->link); + orb = iter; break; } } spin_unlock_irqrestore(&lu->tgt->lock, flags); - if (&orb->link != &lu->orb_list) { + if (orb) { orb->callback(orb, &status); kref_put(&orb->kref, free_orb); /* orb callback reference */ } else { From a7ecbe92b9243edbe94772f6f2c854e4142a3345 Mon Sep 17 00:00:00 2001 From: Niels Dossche Date: Sat, 9 Apr 2022 13:12:43 +0900 Subject: [PATCH 028/192] firewire: core: extend card->lock in fw_core_handle_bus_reset card->local_node and card->bm_retries are both always accessed under card->lock. fw_core_handle_bus_reset has a check whose condition depends on card->local_node and whose body writes to card->bm_retries. Both of these accesses are not under card->lock. Move the lock acquiring of card->lock to before this check such that these accesses do happen when card->lock is held. fw_destroy_nodes is called inside the check. Since fw_destroy_nodes already acquires card->lock inside its function body, move this out to the callsites of fw_destroy_nodes. Also add a comment to indicate which locking is necessary when calling fw_destroy_nodes. Cc: Signed-off-by: Niels Dossche Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20220409041243.603210-4-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- drivers/firewire/core-card.c | 3 +++ drivers/firewire/core-topology.c | 9 +++------ 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index 54be88167c60..f3b3953cac83 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -668,6 +668,7 @@ EXPORT_SYMBOL_GPL(fw_card_release); void fw_core_remove_card(struct fw_card *card) { struct fw_card_driver dummy_driver = dummy_driver_template; + unsigned long flags; card->driver->update_phy_reg(card, 4, PHY_LINK_ACTIVE | PHY_CONTENDER, 0); @@ -682,7 +683,9 @@ void fw_core_remove_card(struct fw_card *card) dummy_driver.stop_iso = card->driver->stop_iso; card->driver = &dummy_driver; + spin_lock_irqsave(&card->lock, flags); fw_destroy_nodes(card); + spin_unlock_irqrestore(&card->lock, flags); /* Wait for all users, especially device workqueue jobs, to finish. */ fw_card_put(card); diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c index b63d55f5ebd3..f40c81534381 100644 --- a/drivers/firewire/core-topology.c +++ b/drivers/firewire/core-topology.c @@ -375,16 +375,13 @@ static void report_found_node(struct fw_card *card, card->bm_retries = 0; } +/* Must be called with card->lock held */ void fw_destroy_nodes(struct fw_card *card) { - unsigned long flags; - - spin_lock_irqsave(&card->lock, flags); card->color++; if (card->local_node != NULL) for_each_fw_node(card, card->local_node, report_lost_node); card->local_node = NULL; - spin_unlock_irqrestore(&card->lock, flags); } static void move_tree(struct fw_node *node0, struct fw_node *node1, int port) @@ -510,6 +507,8 @@ void fw_core_handle_bus_reset(struct fw_card *card, int node_id, int generation, struct fw_node *local_node; unsigned long flags; + spin_lock_irqsave(&card->lock, flags); + /* * If the selfID buffer is not the immediate successor of the * previously processed one, we cannot reliably compare the @@ -521,8 +520,6 @@ void fw_core_handle_bus_reset(struct fw_card *card, int node_id, int generation, card->bm_retries = 0; } - spin_lock_irqsave(&card->lock, flags); - card->broadcast_channel_allocated = card->broadcast_channel_auto_allocated; card->node_id = node_id; /* From 3b79954fd00d540677c97a560622b73f3a1f4e28 Mon Sep 17 00:00:00 2001 From: Zihao Wang Date: Sun, 24 Apr 2022 16:41:20 +0800 Subject: [PATCH 029/192] ALSA: hda/realtek: Add quirk for Yoga Duet 7 13ITL6 speakers Lenovo Yoga Duet 7 13ITL6 has Realtek ALC287 and built-in speakers do not work out of the box. The fix developed for Yoga 7i 14ITL5 also enables speaker output for this model. Signed-off-by: Zihao Wang Cc: Link: https://lore.kernel.org/r/20220424084120.74125-1-wzhd@ustc.edu Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index c65d3dbc6cc9..cf531c1efa13 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9247,6 +9247,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940", ALC298_FIXUP_LENOVO_SPK_VOLUME), SND_PCI_QUIRK(0x17aa, 0x3819, "Lenovo 13s Gen2 ITL", ALC287_FIXUP_13S_GEN2_SPEAKERS), + SND_PCI_QUIRK(0x17aa, 0x3820, "Yoga Duet 7 13ITL6", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3824, "Legion Y9000X 2020", ALC285_FIXUP_LEGION_Y9000X_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF), SND_PCI_QUIRK(0x17aa, 0x3834, "Lenovo IdeaPad Slim 9i 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), From eb9d84b0ffe39893cb23b0b6712bbe3637fa25fa Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Sun, 24 Apr 2022 19:24:28 +0900 Subject: [PATCH 030/192] ALSA: fireworks: fix wrong return count shorter than expected by 4 bytes ALSA fireworks driver has a bug in its initial state to return count shorter than expected by 4 bytes to userspace applications when handling response frame for Echo Audio Fireworks transaction. It's due to missing addition of the size for the type of event in ALSA firewire stack. Fixes: 555e8a8f7f14 ("ALSA: fireworks: Add command/response functionality into hwdep interface") Cc: Signed-off-by: Takashi Sakamoto Link: https://lore.kernel.org/r/20220424102428.21109-1-o-takashi@sakamocchi.jp Signed-off-by: Takashi Iwai --- sound/firewire/fireworks/fireworks_hwdep.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/firewire/fireworks/fireworks_hwdep.c b/sound/firewire/fireworks/fireworks_hwdep.c index 626c0c34b0b6..3a53914277d3 100644 --- a/sound/firewire/fireworks/fireworks_hwdep.c +++ b/sound/firewire/fireworks/fireworks_hwdep.c @@ -34,6 +34,7 @@ hwdep_read_resp_buf(struct snd_efw *efw, char __user *buf, long remained, type = SNDRV_FIREWIRE_EVENT_EFW_RESPONSE; if (copy_to_user(buf, &type, sizeof(type))) return -EFAULT; + count += sizeof(type); remained -= sizeof(type); buf += sizeof(type); From 2fbe467bcbfc760a08f08475eea6bbd4c2874319 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 20 Apr 2022 20:34:53 +0100 Subject: [PATCH 031/192] ASoC: max98090: Reject invalid values in custom control put() The max98090 driver has a custom put function for some controls which can only be updated in certain circumstances which makes no effort to validate that input is suitable for the control, allowing out of spec values to be written to the hardware and presented to userspace. Fix this by returning an error when invalid values are written. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20220420193454.2647908-1-broonie@kernel.org Signed-off-by: Mark Brown --- sound/soc/codecs/max98090.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index b45ec35cd63c..6d9261346842 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -413,6 +413,9 @@ static int max98090_put_enab_tlv(struct snd_kcontrol *kcontrol, val = (val >> mc->shift) & mask; + if (sel < 0 || sel > mc->max) + return -EINVAL; + *select = sel; /* Setting a volume is only valid if it is already On */ From 13fcf676d9e102594effc686d98521ff5c90b925 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 20 Apr 2022 20:34:54 +0100 Subject: [PATCH 032/192] ASoC: max98090: Generate notifications on changes for custom control The max98090 driver has some custom controls which share a put() function which returns 0 unconditionally, meaning that events are not generated when the value changes. Fix that. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20220420193454.2647908-2-broonie@kernel.org Signed-off-by: Mark Brown --- sound/soc/codecs/max98090.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index 6d9261346842..62b41ca050a2 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -430,7 +430,7 @@ static int max98090_put_enab_tlv(struct snd_kcontrol *kcontrol, mask << mc->shift, sel << mc->shift); - return 0; + return *select != val; } static const char *max98090_perf_pwr_text[] = From 2bde1985e39173d8cb64005dad6f34e9bee4c750 Mon Sep 17 00:00:00 2001 From: Codrin Ciubotariu Date: Thu, 21 Apr 2022 15:54:03 +0300 Subject: [PATCH 033/192] ASoC: atmel: mchp-pdmc: set prepare_slave_config Since a pointer to struct snd_dmaengine_pcm_config is passed, snd_dmaengine_pcm_prepare_slave_config() is no longer called unless it's explicitly set in prepare_slave_config. Fixes: 50291652af52 ("ASoC: atmel: mchp-pdmc: add PDMC driver") Suggested-by: Sascha Hauer Signed-off-by: Codrin Ciubotariu Link: https://lore.kernel.org/r/20220421125403.2180824-2-codrin.ciubotariu@microchip.com Signed-off-by: Mark Brown --- sound/soc/atmel/mchp-pdmc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/atmel/mchp-pdmc.c b/sound/soc/atmel/mchp-pdmc.c index 1a7802fbf23c..a3856c73e221 100644 --- a/sound/soc/atmel/mchp-pdmc.c +++ b/sound/soc/atmel/mchp-pdmc.c @@ -966,6 +966,7 @@ static int mchp_pdmc_process(struct snd_pcm_substream *substream, static struct snd_dmaengine_pcm_config mchp_pdmc_config = { .process = mchp_pdmc_process, + .prepare_slave_config = snd_dmaengine_pcm_prepare_slave_config, }; static int mchp_pdmc_probe(struct platform_device *pdev) From 660564fc9a92a893a14f255be434f7ea0b967901 Mon Sep 17 00:00:00 2001 From: Codrin Ciubotariu Date: Thu, 21 Apr 2022 15:54:02 +0300 Subject: [PATCH 034/192] ASoC: dmaengine: Restore NULL prepare_slave_config() callback As pointed out by Sascha Hauer, this patch changes: if (pmc->config && !pcm->config->prepare_slave_config) to: if (pmc->config && !pcm->config->prepare_slave_config) snd_dmaengine_pcm_prepare_slave_config() This breaks the drivers that do not need a call to dmaengine_slave_config(). Drivers that still need to call snd_dmaengine_pcm_prepare_slave_config(), but have a NULL pcm->config->prepare_slave_config should use snd_dmaengine_pcm_prepare_slave_config() as their prepare_slave_config callback. Fixes: 9a1e13440a4f ("ASoC: dmaengine: do not use a NULL prepare_slave_config() callback") Reported-by: Sascha Hauer Signed-off-by: Codrin Ciubotariu Link: https://lore.kernel.org/r/20220421125403.2180824-1-codrin.ciubotariu@microchip.com Signed-off-by: Mark Brown --- sound/soc/soc-generic-dmaengine-pcm.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c index 2ab2ddc1294d..285441d6aeed 100644 --- a/sound/soc/soc-generic-dmaengine-pcm.c +++ b/sound/soc/soc-generic-dmaengine-pcm.c @@ -86,10 +86,10 @@ static int dmaengine_pcm_hw_params(struct snd_soc_component *component, memset(&slave_config, 0, sizeof(slave_config)); - if (pcm->config && pcm->config->prepare_slave_config) - prepare_slave_config = pcm->config->prepare_slave_config; - else + if (!pcm->config) prepare_slave_config = snd_dmaengine_pcm_prepare_slave_config; + else + prepare_slave_config = pcm->config->prepare_slave_config; if (prepare_slave_config) { int ret = prepare_slave_config(substream, params, &slave_config); From 75d2b2b06bd8407d03a3f126bc8b95eb356906c7 Mon Sep 17 00:00:00 2001 From: Adam Wujek Date: Wed, 20 Apr 2022 14:51:25 +0000 Subject: [PATCH 035/192] hwmon: (pmbus) disable PEC if not enabled Explicitly disable PEC when the client does not support it. The problematic scenario is the following. A device with enabled PEC support is up and running and a kernel driver is loaded. Then the driver is unloaded (or device unbound), the HW device is reconfigured externally (e.g. by i2cset) to advertise itself as not supporting PEC. Without a new code, at the second load of the driver (or bind) the "flags" variable is not updated to avoid PEC usage. As a consequence the further communication with the device is done with the PEC enabled, which is wrong and may fail. The implementation first disable the I2C_CLIENT_PEC flag, then the old code enable it if needed. Fixes: 4e5418f787ec ("hwmon: (pmbus_core) Check adapter PEC support") Signed-off-by: Adam Wujek Link: https://lore.kernel.org/r/20220420145059.431061-1-dev_public@wujek.eu Signed-off-by: Guenter Roeck --- drivers/hwmon/pmbus/pmbus_core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index b2618b1d529e..d93574d6a1fb 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -2326,6 +2326,9 @@ static int pmbus_init_common(struct i2c_client *client, struct pmbus_data *data, data->has_status_word = true; } + /* Make sure PEC is disabled, will be enabled later if needed */ + client->flags &= ~I2C_CLIENT_PEC; + /* Enable PEC if the controller and bus supports it */ if (!(data->flags & PMBUS_NO_CAPABILITY)) { ret = i2c_smbus_read_byte_data(client, PMBUS_CAPABILITY); From 00c94ebec5925593c0377b941289224469e72ac7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 25 Apr 2022 18:04:27 -0400 Subject: [PATCH 036/192] NFSv4: Don't invalidate inode attributes on delegation return There is no need to declare attributes such as the ctime, mtime and block size invalid when we're just returning a delegation, so it is inappropriate to call nfs_post_op_update_inode_force_wcc(). Instead, just call nfs_refresh_inode() after faking up the change attribute. We know that the GETATTR op occurs before the DELEGRETURN, so we are safe when doing this. Fixes: 0bc2c9b4dca9 ("NFSv4: Don't discard the attributes returned by asynchronous DELEGRETURN") Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 16106f805ffa..a79f66432bd3 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -363,6 +363,14 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent kunmap_atomic(start); } +static void nfs4_fattr_set_prechange(struct nfs_fattr *fattr, u64 version) +{ + if (!(fattr->valid & NFS_ATTR_FATTR_PRECHANGE)) { + fattr->pre_change_attr = version; + fattr->valid |= NFS_ATTR_FATTR_PRECHANGE; + } +} + static void nfs4_test_and_free_stateid(struct nfs_server *server, nfs4_stateid *stateid, const struct cred *cred) @@ -6553,7 +6561,9 @@ static void nfs4_delegreturn_release(void *calldata) pnfs_roc_release(&data->lr.arg, &data->lr.res, data->res.lr_ret); if (inode) { - nfs_post_op_update_inode_force_wcc(inode, &data->fattr); + nfs4_fattr_set_prechange(&data->fattr, + inode_peek_iversion_raw(inode)); + nfs_refresh_inode(inode, &data->fattr); nfs_iput_and_deactive(inode); } kfree(calldata); From 4bc31edebde51fcf8ad0794763b8679a7ecb5ec0 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 22 Apr 2022 10:08:53 -0700 Subject: [PATCH 037/192] mmc: core: Set HS clock speed before sending HS CMD13 Way back in commit 4f25580fb84d ("mmc: core: changes frequency to hs_max_dtr when selecting hs400es"), Rockchip engineers noticed that some eMMC don't respond to SEND_STATUS commands very reliably if they're still running at a low initial frequency. As mentioned in that commit, JESD84-B51 P49 suggests a sequence in which the host: 1. sets HS_TIMING 2. bumps the clock ("<= 52 MHz") 3. sends further commands It doesn't exactly require that we don't use a lower-than-52MHz frequency, but in practice, these eMMC don't like it. The aforementioned commit tried to get that right for HS400ES, although it's unclear whether this ever truly worked as committed into mainline, as other changes/refactoring adjusted the sequence in conflicting ways: 08573eaf1a70 ("mmc: mmc: do not use CMD13 to get status after speed mode switch") 53e60650f74e ("mmc: core: Allow CMD13 polling when switching to HS mode for mmc") In any case, today we do step 3 before step 2. Let's fix that, and also apply the same logic to HS200/400, where this eMMC has problems too. Resolves errors like this seen when booting some RK3399 Gru/Scarlet systems: [ 2.058881] mmc1: CQHCI version 5.10 [ 2.097545] mmc1: SDHCI controller on fe330000.mmc [fe330000.mmc] using ADMA [ 2.209804] mmc1: mmc_select_hs400es failed, error -84 [ 2.215597] mmc1: error -84 whilst initialising MMC card [ 2.417514] mmc1: mmc_select_hs400es failed, error -110 [ 2.423373] mmc1: error -110 whilst initialising MMC card [ 2.605052] mmc1: mmc_select_hs400es failed, error -110 [ 2.617944] mmc1: error -110 whilst initialising MMC card [ 2.835884] mmc1: mmc_select_hs400es failed, error -110 [ 2.841751] mmc1: error -110 whilst initialising MMC card Ealier versions of this patch bumped to 200MHz/HS200 speeds too early, which caused issues on, e.g., qcom-msm8974-fairphone-fp2. (Thanks for the report Luca!) After a second look, it appears that aligns with JESD84 / page 45 / table 28, so we need to keep to lower (HS / 52 MHz) rates first. Fixes: 08573eaf1a70 ("mmc: mmc: do not use CMD13 to get status after speed mode switch") Fixes: 53e60650f74e ("mmc: core: Allow CMD13 polling when switching to HS mode for mmc") Fixes: 4f25580fb84d ("mmc: core: changes frequency to hs_max_dtr when selecting hs400es") Cc: Shawn Lin Link: https://lore.kernel.org/linux-mmc/11962455.O9o76ZdvQC@g550jk/ Reported-by: Luca Weiss Signed-off-by: Brian Norris Tested-by: Luca Weiss Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220422100824.v4.1.I484f4ee35609f78b932bd50feed639c29e64997e@changeid Signed-off-by: Ulf Hansson --- drivers/mmc/core/mmc.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index e7ea45386c22..efa95dc4fc4e 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1384,13 +1384,17 @@ static int mmc_select_hs400es(struct mmc_card *card) goto out_err; } + /* + * Bump to HS timing and frequency. Some cards don't handle + * SEND_STATUS reliably at the initial frequency. + */ mmc_set_timing(host, MMC_TIMING_MMC_HS); + mmc_set_bus_speed(card); + err = mmc_switch_status(card, true); if (err) goto out_err; - mmc_set_clock(host, card->ext_csd.hs_max_dtr); - /* Switch card to DDR with strobe bit */ val = EXT_CSD_DDR_BUS_WIDTH_8 | EXT_CSD_BUS_WIDTH_STROBE; err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL, @@ -1448,7 +1452,7 @@ out_err: static int mmc_select_hs200(struct mmc_card *card) { struct mmc_host *host = card->host; - unsigned int old_timing, old_signal_voltage; + unsigned int old_timing, old_signal_voltage, old_clock; int err = -EINVAL; u8 val; @@ -1479,8 +1483,17 @@ static int mmc_select_hs200(struct mmc_card *card) false, true, MMC_CMD_RETRIES); if (err) goto err; + + /* + * Bump to HS timing and frequency. Some cards don't handle + * SEND_STATUS reliably at the initial frequency. + * NB: We can't move to full (HS200) speeds until after we've + * successfully switched over. + */ old_timing = host->ios.timing; + old_clock = host->ios.clock; mmc_set_timing(host, MMC_TIMING_MMC_HS200); + mmc_set_clock(card->host, card->ext_csd.hs_max_dtr); /* * For HS200, CRC errors are not a reliable way to know the @@ -1493,8 +1506,10 @@ static int mmc_select_hs200(struct mmc_card *card) * mmc_select_timing() assumes timing has not changed if * it is a switch error. */ - if (err == -EBADMSG) + if (err == -EBADMSG) { + mmc_set_clock(host, old_clock); mmc_set_timing(host, old_timing); + } } err: if (err) { From aa22125c57f9e577f0a667e4fa07fc3fa8ca1e60 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sat, 23 Apr 2022 14:12:39 +0100 Subject: [PATCH 038/192] ASoC: ops: Validate input values in snd_soc_put_volsw_range() Check that values written via snd_soc_put_volsw_range() are within the range advertised by the control, ensuring that we don't write out of spec values to the hardware. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20220423131239.3375261-1-broonie@kernel.org Signed-off-by: Mark Brown --- sound/soc/soc-ops.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index 58347eadd219..e693070f51fe 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -519,7 +519,15 @@ int snd_soc_put_volsw_range(struct snd_kcontrol *kcontrol, unsigned int mask = (1 << fls(max)) - 1; unsigned int invert = mc->invert; unsigned int val, val_mask; - int err, ret; + int err, ret, tmp; + + tmp = ucontrol->value.integer.value[0]; + if (tmp < 0) + return -EINVAL; + if (mc->platform_max && tmp > mc->platform_max) + return -EINVAL; + if (tmp > mc->max - mc->min + 1) + return -EINVAL; if (invert) val = (max - ucontrol->value.integer.value[0]) & mask; @@ -534,6 +542,14 @@ int snd_soc_put_volsw_range(struct snd_kcontrol *kcontrol, ret = err; if (snd_soc_volsw_is_stereo(mc)) { + tmp = ucontrol->value.integer.value[1]; + if (tmp < 0) + return -EINVAL; + if (mc->platform_max && tmp > mc->platform_max) + return -EINVAL; + if (tmp > mc->max - mc->min + 1) + return -EINVAL; + if (invert) val = (max - ucontrol->value.integer.value[1]) & mask; else From 8b202ee218395319aec1ef44f72043e1fbaccdd6 Mon Sep 17 00:00:00 2001 From: Sven Schnelle Date: Mon, 25 Apr 2022 14:17:42 +0200 Subject: [PATCH 039/192] s390: disable -Warray-bounds gcc-12 shows a lot of array bound warnings on s390. This is caused by the S390_lowcore macro which uses a hardcoded address of 0. Wrapping that with absolute_pointer() works, but gcc no longer knows that a 12 bit displacement is sufficient to access lowcore. So it emits instructions like 'lghi %r1,0; l %rx,xxx(%r1)' instead of a single load/store instruction. As s390 stores variables often read/written in lowcore, this is considered problematic. Therefore disable -Warray-bounds on s390 for gcc-12 for the time being, until there is a better solution. Signed-off-by: Sven Schnelle Link: https://lore.kernel.org/r/yt9dzgkelelc.fsf@linux.ibm.com Link: https://lore.kernel.org/r/20220422134308.1613610-1-svens@linux.ibm.com Link: https://lore.kernel.org/r/20220425121742.3222133-1-svens@linux.ibm.com Signed-off-by: Heiko Carstens --- arch/s390/Makefile | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/s390/Makefile b/arch/s390/Makefile index e441b60b1812..df325eacf62d 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -30,6 +30,16 @@ KBUILD_CFLAGS_DECOMPRESSOR += -fno-stack-protector KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, address-of-packed-member) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,)) + +ifdef CONFIG_CC_IS_GCC + ifeq ($(call cc-ifversion, -ge, 1200, y), y) + ifeq ($(call cc-ifversion, -lt, 1300, y), y) + KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds) + KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, array-bounds) + endif + endif +endif + UTS_MACHINE := s390x STACK_SIZE := $(if $(CONFIG_KASAN),65536,16384) CHECKFLAGS += -D__s390__ -D__s390x__ From 08da09f028043fed9653331ae75bc310411f72e6 Mon Sep 17 00:00:00 2001 From: Zev Weiss Date: Tue, 26 Apr 2022 20:51:09 -0700 Subject: [PATCH 040/192] hwmon: (pmbus) delta-ahe50dc-fan: work around hardware quirk CLEAR_FAULTS commands can apparently sometimes trigger catastrophic power output glitches on the ahe-50dc, so block them from being sent at all. Signed-off-by: Zev Weiss Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220427035109.3819-1-zev@bewilderbeest.net Fixes: d387d88ed045 ("hwmon: (pmbus) Add Delta AHE-50DC fan control module driver") Signed-off-by: Guenter Roeck --- drivers/hwmon/pmbus/delta-ahe50dc-fan.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/hwmon/pmbus/delta-ahe50dc-fan.c b/drivers/hwmon/pmbus/delta-ahe50dc-fan.c index 40dffd9c4cbf..f546f0c12497 100644 --- a/drivers/hwmon/pmbus/delta-ahe50dc-fan.c +++ b/drivers/hwmon/pmbus/delta-ahe50dc-fan.c @@ -14,6 +14,21 @@ #define AHE50DC_PMBUS_READ_TEMP4 0xd0 +static int ahe50dc_fan_write_byte(struct i2c_client *client, int page, u8 value) +{ + /* + * The CLEAR_FAULTS operation seems to sometimes (unpredictably, perhaps + * 5% of the time or so) trigger a problematic phenomenon in which the + * fan speeds surge momentarily and at least some (perhaps all?) of the + * system's power outputs experience a glitch. + * + * However, according to Delta it should be OK to simply not send any + * CLEAR_FAULTS commands (the device doesn't seem to be capable of + * reporting any faults anyway), so just blackhole them unconditionally. + */ + return value == PMBUS_CLEAR_FAULTS ? -EOPNOTSUPP : -ENODATA; +} + static int ahe50dc_fan_read_word_data(struct i2c_client *client, int page, int phase, int reg) { /* temp1 in (virtual) page 1 is remapped to mfr-specific temp4 */ @@ -68,6 +83,7 @@ static struct pmbus_driver_info ahe50dc_fan_info = { PMBUS_HAVE_VIN | PMBUS_HAVE_FAN12 | PMBUS_HAVE_FAN34 | PMBUS_HAVE_STATUS_FAN12 | PMBUS_HAVE_STATUS_FAN34 | PMBUS_PAGE_VIRTUAL, .func[1] = PMBUS_HAVE_TEMP | PMBUS_PAGE_VIRTUAL, + .write_byte = ahe50dc_fan_write_byte, .read_word_data = ahe50dc_fan_read_word_data, }; From c61711c1c95791850be48dd65a1d72eb34ba719f Mon Sep 17 00:00:00 2001 From: Ajit Kumar Pandey Date: Tue, 26 Apr 2022 13:33:57 -0500 Subject: [PATCH 041/192] ASoC: SOF: Fix NULL pointer exception in sof_pci_probe callback We are accessing "desc->ops" in sof_pci_probe without checking "desc" pointer. This results in NULL pointer exception if pci_id->driver_data i.e desc pointer isn't defined in sof device probe: BUG: kernel NULL pointer dereference, address: 0000000000000060 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI RIP: 0010:sof_pci_probe+0x1e/0x17f [snd_sof_pci] Code: Unable to access opcode bytes at RIP 0xffffffffc043dff4. RSP: 0018:ffffac4b03b9b8d8 EFLAGS: 00010246 Add NULL pointer check for sof_dev_desc pointer to avoid such exception. Reviewed-by: Ranjani Sridharan Signed-off-by: Ajit Kumar Pandey Signed-off-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20220426183357.102155-1-pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown --- sound/soc/sof/sof-pci-dev.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/soc/sof/sof-pci-dev.c b/sound/soc/sof/sof-pci-dev.c index 12f5cff22448..7fa2649e56e5 100644 --- a/sound/soc/sof/sof-pci-dev.c +++ b/sound/soc/sof/sof-pci-dev.c @@ -153,6 +153,11 @@ int sof_pci_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) dev_dbg(&pci->dev, "PCI DSP detected"); + if (!desc) { + dev_err(dev, "error: no matching PCI descriptor\n"); + return -ENODEV; + } + if (!desc->ops) { dev_err(dev, "error: no matching PCI descriptor ops\n"); return -ENODEV; From 3f65b1e2f424f44585bd701024a3bfd0b1e0ade2 Mon Sep 17 00:00:00 2001 From: Kuogee Hsieh Date: Tue, 26 Apr 2022 14:12:14 -0700 Subject: [PATCH 042/192] drm/msm/dp: remove fail safe mode related code Current DP driver implementation has adding safe mode done at dp_hpd_plug_handle() which is expected to be executed under event thread context. However there is possible circular locking happen (see blow stack trace) after edp driver call dp_hpd_plug_handle() from dp_bridge_enable() which is executed under drm_thread context. After review all possibilities methods and as discussed on https://patchwork.freedesktop.org/patch/483155/, supporting EDID compliance tests in the driver is quite hacky. As seen with other vendor drivers, supporting these will be much easier with IGT. Hence removing all the related fail safe code for it so that no possibility of circular lock will happen. Reviewed-by: Stephen Boyd Reviewed-by: Douglas Anderson Reviewed-by: Dmitry Baryshkov ====================================================== WARNING: possible circular locking dependency detected 5.15.35-lockdep #6 Tainted: G W ------------------------------------------------------ frecon/429 is trying to acquire lock: ffffff808dc3c4e8 (&dev->mode_config.mutex){+.+.}-{3:3}, at: dp_panel_add_fail_safe_mode+0x4c/0xa0 but task is already holding lock: ffffff808dc441e0 (&kms->commit_lock[i]){+.+.}-{3:3}, at: lock_crtcs+0xb4/0x124 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&kms->commit_lock[i]){+.+.}-{3:3}: __mutex_lock_common+0x174/0x1a64 mutex_lock_nested+0x98/0xac lock_crtcs+0xb4/0x124 msm_atomic_commit_tail+0x330/0x748 commit_tail+0x19c/0x278 drm_atomic_helper_commit+0x1dc/0x1f0 drm_atomic_commit+0xc0/0xd8 drm_atomic_helper_set_config+0xb4/0x134 drm_mode_setcrtc+0x688/0x1248 drm_ioctl_kernel+0x1e4/0x338 drm_ioctl+0x3a4/0x684 __arm64_sys_ioctl+0x118/0x154 invoke_syscall+0x78/0x224 el0_svc_common+0x178/0x200 do_el0_svc+0x94/0x13c el0_svc+0x5c/0xec el0t_64_sync_handler+0x78/0x108 el0t_64_sync+0x1a4/0x1a8 -> #2 (crtc_ww_class_mutex){+.+.}-{3:3}: __mutex_lock_common+0x174/0x1a64 ww_mutex_lock+0xb8/0x278 modeset_lock+0x304/0x4ac drm_modeset_lock+0x4c/0x7c drmm_mode_config_init+0x4a8/0xc50 msm_drm_init+0x274/0xac0 msm_drm_bind+0x20/0x2c try_to_bring_up_master+0x3dc/0x470 __component_add+0x18c/0x3c0 component_add+0x1c/0x28 dp_display_probe+0x954/0xa98 platform_probe+0x124/0x15c really_probe+0x1b0/0x5f8 __driver_probe_device+0x174/0x20c driver_probe_device+0x70/0x134 __device_attach_driver+0x130/0x1d0 bus_for_each_drv+0xfc/0x14c __device_attach+0x1bc/0x2bc device_initial_probe+0x1c/0x28 bus_probe_device+0x94/0x178 deferred_probe_work_func+0x1a4/0x1f0 process_one_work+0x5d4/0x9dc worker_thread+0x898/0xccc kthread+0x2d4/0x3d4 ret_from_fork+0x10/0x20 -> #1 (crtc_ww_class_acquire){+.+.}-{0:0}: ww_acquire_init+0x1c4/0x2c8 drm_modeset_acquire_init+0x44/0xc8 drm_helper_probe_single_connector_modes+0xb0/0x12dc drm_mode_getconnector+0x5dc/0xfe8 drm_ioctl_kernel+0x1e4/0x338 drm_ioctl+0x3a4/0x684 __arm64_sys_ioctl+0x118/0x154 invoke_syscall+0x78/0x224 el0_svc_common+0x178/0x200 do_el0_svc+0x94/0x13c el0_svc+0x5c/0xec el0t_64_sync_handler+0x78/0x108 el0t_64_sync+0x1a4/0x1a8 -> #0 (&dev->mode_config.mutex){+.+.}-{3:3}: __lock_acquire+0x2650/0x672c lock_acquire+0x1b4/0x4ac __mutex_lock_common+0x174/0x1a64 mutex_lock_nested+0x98/0xac dp_panel_add_fail_safe_mode+0x4c/0xa0 dp_hpd_plug_handle+0x1f0/0x280 dp_bridge_enable+0x94/0x2b8 drm_atomic_bridge_chain_enable+0x11c/0x168 drm_atomic_helper_commit_modeset_enables+0x500/0x740 msm_atomic_commit_tail+0x3e4/0x748 commit_tail+0x19c/0x278 drm_atomic_helper_commit+0x1dc/0x1f0 drm_atomic_commit+0xc0/0xd8 drm_atomic_helper_set_config+0xb4/0x134 drm_mode_setcrtc+0x688/0x1248 drm_ioctl_kernel+0x1e4/0x338 drm_ioctl+0x3a4/0x684 __arm64_sys_ioctl+0x118/0x154 invoke_syscall+0x78/0x224 el0_svc_common+0x178/0x200 do_el0_svc+0x94/0x13c el0_svc+0x5c/0xec el0t_64_sync_handler+0x78/0x108 el0t_64_sync+0x1a4/0x1a8 Changes in v2: -- re text commit title -- remove all fail safe mode Changes in v3: -- remove dp_panel_add_fail_safe_mode() from dp_panel.h -- add Fixes Changes in v5: -- to=dianders@chromium.org Changes in v6: -- fix Fixes commit ID Fixes: 8b2c181e3dcf ("drm/msm/dp: add fail safe mode outside of event_mutex context") Reported-by: Douglas Anderson Signed-off-by: Kuogee Hsieh Link: https://lore.kernel.org/r/1651007534-31842-1-git-send-email-quic_khsieh@quicinc.com Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/dp/dp_display.c | 6 ------ drivers/gpu/drm/msm/dp/dp_panel.c | 11 ----------- drivers/gpu/drm/msm/dp/dp_panel.h | 1 - 3 files changed, 18 deletions(-) diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index a42732b67349..178b774a5fbd 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -580,12 +580,6 @@ static int dp_hpd_plug_handle(struct dp_display_private *dp, u32 data) dp->dp_display.connector_type, state); mutex_unlock(&dp->event_mutex); - /* - * add fail safe mode outside event_mutex scope - * to avoid potiential circular lock with drm thread - */ - dp_panel_add_fail_safe_mode(dp->dp_display.connector); - /* uevent will complete connection part */ return 0; }; diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index 26c3653c99ec..26f4b6959c31 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -151,15 +151,6 @@ static int dp_panel_update_modes(struct drm_connector *connector, return rc; } -void dp_panel_add_fail_safe_mode(struct drm_connector *connector) -{ - /* fail safe edid */ - mutex_lock(&connector->dev->mode_config.mutex); - if (drm_add_modes_noedid(connector, 640, 480)) - drm_set_preferred_mode(connector, 640, 480); - mutex_unlock(&connector->dev->mode_config.mutex); -} - int dp_panel_read_sink_caps(struct dp_panel *dp_panel, struct drm_connector *connector) { @@ -215,8 +206,6 @@ int dp_panel_read_sink_caps(struct dp_panel *dp_panel, rc = -ETIMEDOUT; goto end; } - - dp_panel_add_fail_safe_mode(connector); } if (panel->aux_cfg_update_done) { diff --git a/drivers/gpu/drm/msm/dp/dp_panel.h b/drivers/gpu/drm/msm/dp/dp_panel.h index 99739ea679a7..9023e5bb4b8b 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.h +++ b/drivers/gpu/drm/msm/dp/dp_panel.h @@ -59,7 +59,6 @@ int dp_panel_init_panel_info(struct dp_panel *dp_panel); int dp_panel_deinit(struct dp_panel *dp_panel); int dp_panel_timing_cfg(struct dp_panel *dp_panel); void dp_panel_dump_regs(struct dp_panel *dp_panel); -void dp_panel_add_fail_safe_mode(struct drm_connector *connector); int dp_panel_read_sink_caps(struct dp_panel *dp_panel, struct drm_connector *connector); u32 dp_panel_get_mode_bpp(struct dp_panel *dp_panel, u32 mode_max_bpp, From f9095ac1ba1ce407cecc1df93c05ad4ac504661c Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 27 Apr 2022 08:58:02 +0200 Subject: [PATCH 043/192] dt-bindings: ufs: cdns,ufshc: Add power-domains The Cadence UFS controller can be part of power domain (as it is in example DTS of TI J721e UFS Host Controller Glue), so allow such property. Reported-by: Rob Herring Signed-off-by: Krzysztof Kozlowski Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20220427065802.110402-1-krzysztof.kozlowski@linaro.org --- Documentation/devicetree/bindings/ufs/cdns,ufshc.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Documentation/devicetree/bindings/ufs/cdns,ufshc.yaml b/Documentation/devicetree/bindings/ufs/cdns,ufshc.yaml index d227dea368be..fb45f66d6454 100644 --- a/Documentation/devicetree/bindings/ufs/cdns,ufshc.yaml +++ b/Documentation/devicetree/bindings/ufs/cdns,ufshc.yaml @@ -43,6 +43,9 @@ properties: - const: phy_clk - const: ref_clk + power-domains: + maxItems: 1 + reg: maxItems: 1 From e17fd4bf54fb579d03566ab22a02dc03b36f4d06 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 26 Apr 2022 08:35:08 -0500 Subject: [PATCH 044/192] dt-bindings: leds-mt6360: Drop redundant 'unevaluatedProperties' The binding has both 'unevaluatedProperties: false' and 'additionalProperties: false' which is redundant. 'additionalProperties' is the stricter of the two, so drop 'unevaluatedProperties'. Fixes: e05cab34e417 ("dt-bindings: leds: Add bindings for MT6360 LED") Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20220426133508.1849580-1-robh@kernel.org --- Documentation/devicetree/bindings/leds/leds-mt6360.yaml | 2 -- 1 file changed, 2 deletions(-) diff --git a/Documentation/devicetree/bindings/leds/leds-mt6360.yaml b/Documentation/devicetree/bindings/leds/leds-mt6360.yaml index b2fe6eb89389..10f95bf1d666 100644 --- a/Documentation/devicetree/bindings/leds/leds-mt6360.yaml +++ b/Documentation/devicetree/bindings/leds/leds-mt6360.yaml @@ -43,8 +43,6 @@ patternProperties: - 4 # LED output FLASH1 - 5 # LED output FLASH2 -unevaluatedProperties: false - required: - compatible - "#address-cells" From e6f9d69648029e48b8f97db09368d419b5e2614a Mon Sep 17 00:00:00 2001 From: Chung-Chiang Cheng Date: Fri, 15 Apr 2022 16:04:05 +0800 Subject: [PATCH 045/192] btrfs: export a helper for compression hard check inode_can_compress will be used outside of inode.c to check the availability of setting compression flag by xattr. This patch moves this function as an internal helper and renames it to btrfs_inode_can_compress. Reviewed-by: Nikolay Borisov Signed-off-by: Chung-Chiang Cheng Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/btrfs_inode.h | 11 +++++++++++ fs/btrfs/inode.c | 15 ++------------- 2 files changed, 13 insertions(+), 13 deletions(-) diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 47e72d72f7d0..32131a5d321b 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -384,6 +384,17 @@ static inline bool btrfs_inode_in_log(struct btrfs_inode *inode, u64 generation) return ret; } +/* + * Check if the inode has flags compatible with compression + */ +static inline bool btrfs_inode_can_compress(const struct btrfs_inode *inode) +{ + if (inode->flags & BTRFS_INODE_NODATACOW || + inode->flags & BTRFS_INODE_NODATASUM) + return false; + return true; +} + struct btrfs_dio_private { struct inode *inode; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 8bac68d8e96f..673b9259f6c0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -480,17 +480,6 @@ static noinline int add_async_extent(struct async_chunk *cow, return 0; } -/* - * Check if the inode has flags compatible with compression - */ -static inline bool inode_can_compress(struct btrfs_inode *inode) -{ - if (inode->flags & BTRFS_INODE_NODATACOW || - inode->flags & BTRFS_INODE_NODATASUM) - return false; - return true; -} - /* * Check if the inode needs to be submitted to compression, based on mount * options, defragmentation, properties or heuristics. @@ -500,7 +489,7 @@ static inline int inode_need_compress(struct btrfs_inode *inode, u64 start, { struct btrfs_fs_info *fs_info = inode->root->fs_info; - if (!inode_can_compress(inode)) { + if (!btrfs_inode_can_compress(inode)) { WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), KERN_ERR "BTRFS: unexpected compression for ino %llu\n", btrfs_ino(inode)); @@ -2019,7 +2008,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page ASSERT(!zoned || btrfs_is_data_reloc_root(inode->root)); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, nr_written); - } else if (!inode_can_compress(inode) || + } else if (!btrfs_inode_can_compress(inode) || !inode_need_compress(inode, start, end)) { if (zoned) ret = run_delalloc_zoned(inode, locked_page, start, end, From 0e852ab8974cd2b5946766b2d9baf82c78ace03d Mon Sep 17 00:00:00 2001 From: Chung-Chiang Cheng Date: Fri, 15 Apr 2022 16:04:06 +0800 Subject: [PATCH 046/192] btrfs: do not allow compression on nodatacow files Compression and nodatacow are mutually exclusive. A similar issue was fixed by commit f37c563bab429 ("btrfs: add missing check for nocow and compression inode flags"). Besides ioctl, there is another way to enable/disable/reset compression directly via xattr. The following steps will result in a invalid combination. $ touch bar $ chattr +C bar $ lsattr bar ---------------C-- bar $ setfattr -n btrfs.compression -v zstd bar $ lsattr bar --------c------C-- bar To align with the logic in check_fsflags, nocompress will also be unacceptable after this patch, to prevent mix any compression-related options with nodatacow. $ touch bar $ chattr +C bar $ lsattr bar ---------------C-- bar $ setfattr -n btrfs.compression -v zstd bar setfattr: bar: Invalid argument $ setfattr -n btrfs.compression -v no bar setfattr: bar: Invalid argument When both compression and nodatacow are enabled, then btrfs_run_delalloc_range prefers nodatacow and no compression happens. Reported-by: Jayce Lin CC: stable@vger.kernel.org # 5.10.x: e6f9d6964802: btrfs: export a helper for compression hard check CC: stable@vger.kernel.org # 5.10.x Reviewed-by: Filipe Manana Signed-off-by: Chung-Chiang Cheng Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/props.c | 16 +++++++++++----- fs/btrfs/props.h | 3 ++- fs/btrfs/xattr.c | 2 +- 3 files changed, 14 insertions(+), 7 deletions(-) diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index 1a6d2d5b4b33..5a6f87744c28 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -17,7 +17,8 @@ static DEFINE_HASHTABLE(prop_handlers_ht, BTRFS_PROP_HANDLERS_HT_BITS); struct prop_handler { struct hlist_node node; const char *xattr_name; - int (*validate)(const char *value, size_t len); + int (*validate)(const struct btrfs_inode *inode, const char *value, + size_t len); int (*apply)(struct inode *inode, const char *value, size_t len); const char *(*extract)(struct inode *inode); int inheritable; @@ -55,7 +56,8 @@ find_prop_handler(const char *name, return NULL; } -int btrfs_validate_prop(const char *name, const char *value, size_t value_len) +int btrfs_validate_prop(const struct btrfs_inode *inode, const char *name, + const char *value, size_t value_len) { const struct prop_handler *handler; @@ -69,7 +71,7 @@ int btrfs_validate_prop(const char *name, const char *value, size_t value_len) if (value_len == 0) return 0; - return handler->validate(value, value_len); + return handler->validate(inode, value, value_len); } int btrfs_set_prop(struct btrfs_trans_handle *trans, struct inode *inode, @@ -252,8 +254,12 @@ int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path) return ret; } -static int prop_compression_validate(const char *value, size_t len) +static int prop_compression_validate(const struct btrfs_inode *inode, + const char *value, size_t len) { + if (!btrfs_inode_can_compress(inode)) + return -EINVAL; + if (!value) return 0; @@ -364,7 +370,7 @@ static int inherit_props(struct btrfs_trans_handle *trans, * This is not strictly necessary as the property should be * valid, but in case it isn't, don't propagate it further. */ - ret = h->validate(value, strlen(value)); + ret = h->validate(BTRFS_I(inode), value, strlen(value)); if (ret) continue; diff --git a/fs/btrfs/props.h b/fs/btrfs/props.h index 40b2c65b518c..2b2ac15ab788 100644 --- a/fs/btrfs/props.h +++ b/fs/btrfs/props.h @@ -13,7 +13,8 @@ void __init btrfs_props_init(void); int btrfs_set_prop(struct btrfs_trans_handle *trans, struct inode *inode, const char *name, const char *value, size_t value_len, int flags); -int btrfs_validate_prop(const char *name, const char *value, size_t value_len); +int btrfs_validate_prop(const struct btrfs_inode *inode, const char *name, + const char *value, size_t value_len); int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path); diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 99abf41b89b9..9632d0ff2038 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -403,7 +403,7 @@ static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, struct btrfs_root *root = BTRFS_I(inode)->root; name = xattr_full_name(handler, name); - ret = btrfs_validate_prop(name, value, size); + ret = btrfs_validate_prop(BTRFS_I(inode), name, value, size); if (ret) return ret; From d0e64a981fd841cb0f28fcd6afcac55e6f1e6994 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 21 Apr 2022 10:56:39 +0100 Subject: [PATCH 047/192] btrfs: always log symlinks in full mode On Linux, empty symlinks are invalid, and attempting to create one with the system call symlink(2) results in an -ENOENT error and this is explicitly documented in the man page. If we rename a symlink that was created in the current transaction and its parent directory was logged before, we actually end up logging the symlink without logging its content, which is stored in an inline extent. That means that after a power failure we can end up with an empty symlink, having no content and an i_size of 0 bytes. It can be easily reproduced like this: $ mkfs.btrfs -f /dev/sdc $ mount /dev/sdc /mnt $ mkdir /mnt/testdir $ sync # Create a file inside the directory and fsync the directory. $ touch /mnt/testdir/foo $ xfs_io -c "fsync" /mnt/testdir # Create a symlink inside the directory and then rename the symlink. $ ln -s /mnt/testdir/foo /mnt/testdir/bar $ mv /mnt/testdir/bar /mnt/testdir/baz # Now fsync again the directory, this persist the log tree. $ xfs_io -c "fsync" /mnt/testdir $ mount /dev/sdc /mnt $ stat -c %s /mnt/testdir/baz 0 $ readlink /mnt/testdir/baz $ Fix this by always logging symlinks in full mode (LOG_INODE_ALL), so that their content is also logged. A test case for fstests will follow. CC: stable@vger.kernel.org # 4.9+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 09e4f1a04e6f..11399c8eed87 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -5804,6 +5804,18 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, mutex_lock(&inode->log_mutex); } + /* + * For symlinks, we must always log their content, which is stored in an + * inline extent, otherwise we could end up with an empty symlink after + * log replay, which is invalid on linux (symlink(2) returns -ENOENT if + * one attempts to create an empty symlink). + * We don't need to worry about flushing delalloc, because when we create + * the inline extent when the symlink is created (we never have delalloc + * for symlinks). + */ + if (S_ISLNK(inode->vfs_inode.i_mode)) + inode_only = LOG_INODE_ALL; + /* * Before logging the inode item, cache the value returned by * inode_logged(), because after that we have the need to figure out if @@ -6182,7 +6194,7 @@ again: } ctx->log_new_dentries = false; - if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK) + if (type == BTRFS_FT_DIR) log_mode = LOG_INODE_ALL; ret = btrfs_log_inode(trans, BTRFS_I(di_inode), log_mode, ctx); From 193b4e83986d7ee6caa8ceefb5ee9f58240fbee0 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 21 Apr 2022 11:03:09 +0100 Subject: [PATCH 048/192] btrfs: do not BUG_ON() on failure to update inode when setting xattr We are doing a BUG_ON() if we fail to update an inode after setting (or clearing) a xattr, but there's really no reason to not instead simply abort the transaction and return the error to the caller. This should be a rare error because we have previously reserved enough metadata space to update the inode and the delayed inode should have already been setup, so an -ENOSPC or -ENOMEM, which are the possible errors, are very unlikely to happen. So replace the BUG_ON()s with a transaction abort. CC: stable@vger.kernel.org # 4.9+ Reviewed-by: Qu Wenruo Reviewed-by: Anand Jain Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/xattr.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 9632d0ff2038..367bb87b66df 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -262,7 +262,8 @@ int btrfs_setxattr_trans(struct inode *inode, const char *name, inode_inc_iversion(inode); inode->i_ctime = current_time(inode); ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); - BUG_ON(ret); + if (ret) + btrfs_abort_transaction(trans, ret); out: if (start_trans) btrfs_end_transaction(trans); @@ -416,7 +417,8 @@ static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, inode_inc_iversion(inode); inode->i_ctime = current_time(inode); ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); - BUG_ON(ret); + if (ret) + btrfs_abort_transaction(trans, ret); } btrfs_end_transaction(trans); From 4b73c55fdebd8939f0f6000921075f7f6fa41397 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 21 Apr 2022 11:01:22 +0100 Subject: [PATCH 049/192] btrfs: skip compression property for anything other than files and dirs The compression property only has effect on regular files and directories (so that it's propagated to files and subdirectories created inside a directory). For any other inode type (symlink, fifo, device, socket), it's pointless to set the compression property because it does nothing and ends up unnecessarily wasting leaf space due to the pointless xattr (75 or 76 bytes, depending on the compression value). Symlinks in particular are very common (for example, I have almost 10k symlinks under /etc, /usr and /var alone) and therefore it's worth to avoid wasting leaf space with the compression xattr. For example, the compression property can end up on a symlink or character device implicitly, through inheritance from a parent directory $ mkdir /mnt/testdir $ btrfs property set /mnt/testdir compression lzo $ ln -s yadayada /mnt/testdir/lnk $ mknod /mnt/testdir/dev c 0 0 Or explicitly like this: $ ln -s yadayda /mnt/lnk $ setfattr -h -n btrfs.compression -v lzo /mnt/lnk So skip the compression property on inodes that are neither a regular file nor a directory. CC: stable@vger.kernel.org # 5.4+ Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/props.c | 43 +++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/props.h | 1 + fs/btrfs/xattr.c | 3 +++ 3 files changed, 47 insertions(+) diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index 5a6f87744c28..1b31481f9e72 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -21,6 +21,7 @@ struct prop_handler { size_t len); int (*apply)(struct inode *inode, const char *value, size_t len); const char *(*extract)(struct inode *inode); + bool (*ignore)(const struct btrfs_inode *inode); int inheritable; }; @@ -74,6 +75,28 @@ int btrfs_validate_prop(const struct btrfs_inode *inode, const char *name, return handler->validate(inode, value, value_len); } +/* + * Check if a property should be ignored (not set) for an inode. + * + * @inode: The target inode. + * @name: The property's name. + * + * The caller must be sure the given property name is valid, for example by + * having previously called btrfs_validate_prop(). + * + * Returns: true if the property should be ignored for the given inode + * false if the property must not be ignored for the given inode + */ +bool btrfs_ignore_prop(const struct btrfs_inode *inode, const char *name) +{ + const struct prop_handler *handler; + + handler = find_prop_handler(name, NULL); + ASSERT(handler != NULL); + + return handler->ignore(inode); +} + int btrfs_set_prop(struct btrfs_trans_handle *trans, struct inode *inode, const char *name, const char *value, size_t value_len, int flags) @@ -316,6 +339,22 @@ static int prop_compression_apply(struct inode *inode, const char *value, return 0; } +static bool prop_compression_ignore(const struct btrfs_inode *inode) +{ + /* + * Compression only has effect for regular files, and for directories + * we set it just to propagate it to new files created inside them. + * Everything else (symlinks, devices, sockets, fifos) is pointless as + * it will do nothing, so don't waste metadata space on a compression + * xattr for anything that is neither a file nor a directory. + */ + if (!S_ISREG(inode->vfs_inode.i_mode) && + !S_ISDIR(inode->vfs_inode.i_mode)) + return true; + + return false; +} + static const char *prop_compression_extract(struct inode *inode) { switch (BTRFS_I(inode)->prop_compress) { @@ -336,6 +375,7 @@ static struct prop_handler prop_handlers[] = { .validate = prop_compression_validate, .apply = prop_compression_apply, .extract = prop_compression_extract, + .ignore = prop_compression_ignore, .inheritable = 1 }, }; @@ -362,6 +402,9 @@ static int inherit_props(struct btrfs_trans_handle *trans, if (!h->inheritable) continue; + if (h->ignore(BTRFS_I(inode))) + continue; + value = h->extract(parent); if (!value) continue; diff --git a/fs/btrfs/props.h b/fs/btrfs/props.h index 2b2ac15ab788..59bea741cfcf 100644 --- a/fs/btrfs/props.h +++ b/fs/btrfs/props.h @@ -15,6 +15,7 @@ int btrfs_set_prop(struct btrfs_trans_handle *trans, struct inode *inode, int flags); int btrfs_validate_prop(const struct btrfs_inode *inode, const char *name, const char *value, size_t value_len); +bool btrfs_ignore_prop(const struct btrfs_inode *inode, const char *name); int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path); diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 367bb87b66df..85691dc2232f 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -408,6 +408,9 @@ static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, if (ret) return ret; + if (btrfs_ignore_prop(BTRFS_I(inode), name)) + return 0; + trans = btrfs_start_transaction(root, 2); if (IS_ERR(trans)) return PTR_ERR(trans); From 59bf3557cf2f8a469a554aea1e3d2c8e72a579f7 Mon Sep 17 00:00:00 2001 From: David Stevens Date: Sun, 10 Apr 2022 09:35:33 +0800 Subject: [PATCH 050/192] iommu/vt-d: Calculate mask for non-aligned flushes Calculate the appropriate mask for non-size-aligned page selective invalidation. Since psi uses the mask value to mask out the lower order bits of the target address, properly flushing the iotlb requires using a mask value such that [pfn, pfn+pages) all lie within the flushed size-aligned region. This is not normally an issue because iova.c always allocates iovas that are aligned to their size. However, iovas which come from other sources (e.g. userspace via VFIO) may not be aligned. To properly flush the IOTLB, both the start and end pfns need to be equal after applying the mask. That means that the most efficient mask to use is the index of the lowest bit that is equal where all higher bits are also equal. For example, if pfn=0x17f and pages=3, then end_pfn=0x181, so the smallest mask we can use is 8. Any differences above the highest bit of pages are due to carrying, so by xnor'ing pfn and end_pfn and then masking out the lower order bits based on pages, we get 0xffffff00, where the first set bit is the mask we want to use. Fixes: 6fe1010d6d9c ("vfio/type1: DMA unmap chunking") Cc: stable@vger.kernel.org Signed-off-by: David Stevens Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20220401022430.1262215-1-stevensd@google.com Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20220410013533.3959168-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 27 ++++++++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index df5c62ecf942..0ea47e17b379 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1588,7 +1588,8 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, unsigned long pfn, unsigned int pages, int ih, int map) { - unsigned int mask = ilog2(__roundup_pow_of_two(pages)); + unsigned int aligned_pages = __roundup_pow_of_two(pages); + unsigned int mask = ilog2(aligned_pages); uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT; u16 did = domain->iommu_did[iommu->seq_id]; @@ -1600,10 +1601,30 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, if (domain_use_first_level(domain)) { qi_flush_piotlb(iommu, did, PASID_RID2PASID, addr, pages, ih); } else { + unsigned long bitmask = aligned_pages - 1; + + /* + * PSI masks the low order bits of the base address. If the + * address isn't aligned to the mask, then compute a mask value + * needed to ensure the target range is flushed. + */ + if (unlikely(bitmask & pfn)) { + unsigned long end_pfn = pfn + pages - 1, shared_bits; + + /* + * Since end_pfn <= pfn + bitmask, the only way bits + * higher than bitmask can differ in pfn and end_pfn is + * by carrying. This means after masking out bitmask, + * high bits starting with the first set bit in + * shared_bits are all equal in both pfn and end_pfn. + */ + shared_bits = ~(pfn ^ end_pfn) & ~bitmask; + mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG; + } + /* * Fallback to domain selective flush if no PSI support or - * the size is too big. PSI requires page size to be 2 ^ x, - * and the base address is naturally aligned to the size. + * the size is too big. */ if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap)) From da8669ff41fa31573375c9a4180f5c080677204b Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Sat, 23 Apr 2022 16:23:30 +0800 Subject: [PATCH 051/192] iommu/vt-d: Drop stop marker messages The page fault handling framework in the IOMMU core explicitly states that it doesn't handle PCI PASID Stop Marker and the IOMMU drivers must discard them before reporting faults. This handles Stop Marker messages in prq_event_thread() before reporting events to the core. The VT-d driver explicitly drains the pending page requests when a CPU page table (represented by a mm struct) is unbound from a PASID according to the procedures defined in the VT-d spec. The Stop Marker messages do not need a response. Hence, it is safe to drop the Stop Marker messages silently if any of them is found in the page request queue. Fixes: d5b9e4bfe0d88 ("iommu/vt-d: Report prq to io-pgfault framework") Signed-off-by: Lu Baolu Reviewed-by: Jacob Pan Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20220421113558.3504874-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20220423082330.3897867-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/svm.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 23a38763c1d1..7ee37d996e15 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -757,6 +757,10 @@ bad_req: goto bad_req; } + /* Drop Stop Marker message. No need for a response. */ + if (unlikely(req->lpig && !req->rd_req && !req->wr_req)) + goto prq_advance; + if (!svm || svm->pasid != req->pasid) { /* * It can't go away, because the driver is not permitted From a15932f4377062364d22096afe25bc579134a1c3 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 25 Apr 2022 17:08:26 +0800 Subject: [PATCH 052/192] iommu/dart: check return value after calling platform_get_resource() It will cause null-ptr-deref in resource_size(), if platform_get_resource() returns NULL, move calling resource_size() after devm_ioremap_resource() that will check 'res' to avoid null-ptr-deref. And use devm_platform_get_and_ioremap_resource() to simplify code. Fixes: 46d1fb072e76 ("iommu/dart: Add DART iommu driver") Signed-off-by: Yang Yingliang Reviewed-by: Sven Peter Link: https://lore.kernel.org/r/20220425090826.2532165-1-yangyingliang@huawei.com Signed-off-by: Joerg Roedel --- drivers/iommu/apple-dart.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c index decafb07ad08..15b77f16cfa3 100644 --- a/drivers/iommu/apple-dart.c +++ b/drivers/iommu/apple-dart.c @@ -859,16 +859,15 @@ static int apple_dart_probe(struct platform_device *pdev) dart->dev = dev; spin_lock_init(&dart->lock); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + dart->regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res); + if (IS_ERR(dart->regs)) + return PTR_ERR(dart->regs); + if (resource_size(res) < 0x4000) { dev_err(dev, "MMIO region too small (%pr)\n", res); return -EINVAL; } - dart->regs = devm_ioremap_resource(dev, res); - if (IS_ERR(dart->regs)) - return PTR_ERR(dart->regs); - dart->irq = platform_get_irq(pdev, 0); if (dart->irq < 0) return -ENODEV; From aad41a7d7cf6c6fa804c872a2480f8e541da37cf Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 28 Apr 2022 11:08:13 -0400 Subject: [PATCH 053/192] SUNRPC: Don't leak sockets in xs_local_connect() If there is still a closed socket associated with the transport, then we need to trigger an autoclose before we can set up a new connection. Reported-by: wanghai (M) Fixes: f00432063db1 ("SUNRPC: Ensure we flush any closed sockets before xs_xprt_free()") Signed-off-by: Trond Myklebust --- net/sunrpc/xprtsock.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 8ab64ea46870..f9849b297ea3 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1950,6 +1950,9 @@ static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task) struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); int ret; + if (transport->file) + goto force_disconnect; + if (RPC_IS_ASYNC(task)) { /* * We want the AF_LOCAL connect to be resolved in the @@ -1962,11 +1965,17 @@ static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task) */ task->tk_rpc_status = -ENOTCONN; rpc_exit(task, -ENOTCONN); - return; + goto out_wake; } ret = xs_local_setup_socket(transport); if (ret && !RPC_IS_SOFTCONN(task)) msleep_interruptible(15000); + return; +force_disconnect: + xprt_force_disconnect(xprt); +out_wake: + xprt_clear_connecting(xprt); + xprt_wake_pending_tasks(xprt, -ENOTCONN); } #if IS_ENABLED(CONFIG_SUNRPC_SWAP) From 2c33d775ef4c25c0e1e1cc0fd5496d02f76bfa20 Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Thu, 28 Apr 2022 08:24:32 +0200 Subject: [PATCH 054/192] timekeeping: Mark NMI safe time accessors as notrace Mark the CLOCK_MONOTONIC fast time accessors as notrace. These functions are used in tracing to retrieve timestamps, so they should not recurse. Fixes: 4498e7467e9e ("time: Parametrize all tk_fast_mono users") Fixes: f09cb9a1808e ("time: Introduce tk_fast_raw") Reported-by: Steven Rostedt Signed-off-by: Kurt Kanzenbach Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220426175338.3807ca4f@gandalf.local.home/ Link: https://lore.kernel.org/r/20220428062432.61063-1-kurt@linutronix.de --- kernel/time/timekeeping.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index dcdcb85121e4..3b1398fbddaf 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -482,7 +482,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) * of the following timestamps. Callers need to be aware of that and * deal with it. */ -u64 ktime_get_mono_fast_ns(void) +u64 notrace ktime_get_mono_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_mono); } @@ -494,7 +494,7 @@ EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); * Contrary to ktime_get_mono_fast_ns() this is always correct because the * conversion factor is not affected by NTP/PTP correction. */ -u64 ktime_get_raw_fast_ns(void) +u64 notrace ktime_get_raw_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_raw); } From 72ed3ee9fa0b461ad086403a8b5336154bd82234 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Fri, 22 Apr 2022 10:23:37 +0200 Subject: [PATCH 055/192] can: isotp: remove re-binding of bound socket As a carry over from the CAN_RAW socket (which allows to change the CAN interface while mantaining the filter setup) the re-binding of the CAN_ISOTP socket needs to take care about CAN ID address information and subscriptions. It turned out that this feature is so limited (e.g. the sockopts remain fix) that it finally has never been needed/used. In opposite to the stateless CAN_RAW socket the switching of the CAN ID subscriptions might additionally lead to an interrupted ongoing PDU reception. So better remove this unneeded complexity. Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol") Link: https://lore.kernel.org/all/20220422082337.1676-1-socketcan@hartkopp.net Cc: stable@vger.kernel.org Signed-off-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- net/can/isotp.c | 25 +++++-------------------- 1 file changed, 5 insertions(+), 20 deletions(-) diff --git a/net/can/isotp.c b/net/can/isotp.c index ff5d7870294e..1e7c6a460ef9 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1189,6 +1189,11 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) lock_sock(sk); + if (so->bound) { + err = -EINVAL; + goto out; + } + /* do not register frame reception for functional addressing */ if (so->opt.flags & CAN_ISOTP_SF_BROADCAST) do_rx_reg = 0; @@ -1199,10 +1204,6 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) goto out; } - if (so->bound && addr->can_ifindex == so->ifindex && - rx_id == so->rxid && tx_id == so->txid) - goto out; - dev = dev_get_by_index(net, addr->can_ifindex); if (!dev) { err = -ENODEV; @@ -1237,22 +1238,6 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) dev_put(dev); - if (so->bound && do_rx_reg) { - /* unregister old filter */ - if (so->ifindex) { - dev = dev_get_by_index(net, so->ifindex); - if (dev) { - can_rx_unregister(net, dev, so->rxid, - SINGLE_MASK(so->rxid), - isotp_rcv, sk); - can_rx_unregister(net, dev, so->txid, - SINGLE_MASK(so->txid), - isotp_rcv_echo, sk); - dev_put(dev); - } - } - } - /* switch to new settings */ so->ifindex = ifindex; so->rxid = rx_id; From 47f070a63e735bcc8d481de31be1b5a1aa62b31c Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Mon, 25 Apr 2022 12:24:00 +0800 Subject: [PATCH 056/192] can: grcan: grcan_close(): fix deadlock There are deadlocks caused by del_timer_sync(&priv->hang_timer) and del_timer_sync(&priv->rr_timer) in grcan_close(), one of the deadlocks are shown below: (Thread 1) | (Thread 2) | grcan_reset_timer() grcan_close() | mod_timer() spin_lock_irqsave() //(1) | (wait a time) ... | grcan_initiate_running_reset() del_timer_sync() | spin_lock_irqsave() //(2) (wait timer to stop) | ... We hold priv->lock in position (1) of thread 1 and use del_timer_sync() to wait timer to stop, but timer handler also need priv->lock in position (2) of thread 2. As a result, grcan_close() will block forever. This patch extracts del_timer_sync() from the protection of spin_lock_irqsave(), which could let timer handler to obtain the needed lock. Link: https://lore.kernel.org/all/20220425042400.66517-1-duoming@zju.edu.cn Fixes: 6cec9b07fe6a ("can: grcan: Add device driver for GRCAN and GRHCAN cores") Cc: stable@vger.kernel.org Signed-off-by: Duoming Zhou Reviewed-by: Andreas Larsson Signed-off-by: Marc Kleine-Budde --- drivers/net/can/grcan.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c index d0c5a7a60daf..1189057b5d68 100644 --- a/drivers/net/can/grcan.c +++ b/drivers/net/can/grcan.c @@ -1102,8 +1102,10 @@ static int grcan_close(struct net_device *dev) priv->closing = true; if (priv->need_txbug_workaround) { + spin_unlock_irqrestore(&priv->lock, flags); del_timer_sync(&priv->hang_timer); del_timer_sync(&priv->rr_timer); + spin_lock_irqsave(&priv->lock, flags); } netif_stop_queue(dev); grcan_stop_hardware(dev); From 101da4268626b00d16356a6bf284d66e44c46ff9 Mon Sep 17 00:00:00 2001 From: Daniel Hellstrom Date: Fri, 29 Apr 2022 10:46:54 +0200 Subject: [PATCH 057/192] can: grcan: use ofdev->dev when allocating DMA memory Use the device of the device tree node should be rather than the device of the struct net_device when allocating DMA buffers. The driver got away with it on sparc32 until commit 53b7670e5735 ("sparc: factor the dma coherent mapping into helper") after which the driver oopses. Fixes: 6cec9b07fe6a ("can: grcan: Add device driver for GRCAN and GRHCAN cores") Link: https://lore.kernel.org/all/20220429084656.29788-2-andreas@gaisler.com Cc: stable@vger.kernel.org Signed-off-by: Daniel Hellstrom Signed-off-by: Andreas Larsson Signed-off-by: Marc Kleine-Budde --- drivers/net/can/grcan.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c index 1189057b5d68..f8860900575b 100644 --- a/drivers/net/can/grcan.c +++ b/drivers/net/can/grcan.c @@ -248,6 +248,7 @@ struct grcan_device_config { struct grcan_priv { struct can_priv can; /* must be the first member */ struct net_device *dev; + struct device *ofdev_dev; struct napi_struct napi; struct grcan_registers __iomem *regs; /* ioremap'ed registers */ @@ -921,7 +922,7 @@ static void grcan_free_dma_buffers(struct net_device *dev) struct grcan_priv *priv = netdev_priv(dev); struct grcan_dma *dma = &priv->dma; - dma_free_coherent(&dev->dev, dma->base_size, dma->base_buf, + dma_free_coherent(priv->ofdev_dev, dma->base_size, dma->base_buf, dma->base_handle); memset(dma, 0, sizeof(*dma)); } @@ -946,7 +947,7 @@ static int grcan_allocate_dma_buffers(struct net_device *dev, /* Extra GRCAN_BUFFER_ALIGNMENT to allow for alignment */ dma->base_size = lsize + ssize + GRCAN_BUFFER_ALIGNMENT; - dma->base_buf = dma_alloc_coherent(&dev->dev, + dma->base_buf = dma_alloc_coherent(priv->ofdev_dev, dma->base_size, &dma->base_handle, GFP_KERNEL); @@ -1589,6 +1590,7 @@ static int grcan_setup_netdev(struct platform_device *ofdev, memcpy(&priv->config, &grcan_module_config, sizeof(struct grcan_device_config)); priv->dev = dev; + priv->ofdev_dev = &ofdev->dev; priv->regs = base; priv->can.bittiming_const = &grcan_bittiming_const; priv->can.do_set_bittiming = grcan_set_bittiming; From 1e93ed26acf03fe6c97c6d573a10178596aadd43 Mon Sep 17 00:00:00 2001 From: Andreas Larsson Date: Fri, 29 Apr 2022 10:46:55 +0200 Subject: [PATCH 058/192] can: grcan: grcan_probe(): fix broken system id check for errata workaround needs The systemid property was checked for in the wrong place of the device tree and compared to the wrong value. Fixes: 6cec9b07fe6a ("can: grcan: Add device driver for GRCAN and GRHCAN cores") Link: https://lore.kernel.org/all/20220429084656.29788-3-andreas@gaisler.com Cc: stable@vger.kernel.org Signed-off-by: Andreas Larsson Signed-off-by: Marc Kleine-Budde --- drivers/net/can/grcan.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c index f8860900575b..4ca3da56d3aa 100644 --- a/drivers/net/can/grcan.c +++ b/drivers/net/can/grcan.c @@ -241,7 +241,7 @@ struct grcan_device_config { .rxsize = GRCAN_DEFAULT_BUFFER_SIZE, \ } -#define GRCAN_TXBUG_SAFE_GRLIB_VERSION 0x4100 +#define GRCAN_TXBUG_SAFE_GRLIB_VERSION 4100 #define GRLIB_VERSION_MASK 0xffff /* GRCAN private data structure */ @@ -1643,6 +1643,7 @@ exit_free_candev: static int grcan_probe(struct platform_device *ofdev) { struct device_node *np = ofdev->dev.of_node; + struct device_node *sysid_parent; u32 sysid, ambafreq; int irq, err; void __iomem *base; @@ -1651,10 +1652,15 @@ static int grcan_probe(struct platform_device *ofdev) /* Compare GRLIB version number with the first that does not * have the tx bug (see start_xmit) */ - err = of_property_read_u32(np, "systemid", &sysid); - if (!err && ((sysid & GRLIB_VERSION_MASK) - >= GRCAN_TXBUG_SAFE_GRLIB_VERSION)) - txbug = false; + sysid_parent = of_find_node_by_path("/ambapp0"); + if (sysid_parent) { + of_node_get(sysid_parent); + err = of_property_read_u32(sysid_parent, "systemid", &sysid); + if (!err && ((sysid & GRLIB_VERSION_MASK) >= + GRCAN_TXBUG_SAFE_GRLIB_VERSION)) + txbug = false; + of_node_put(sysid_parent); + } err = of_property_read_u32(np, "freq", &ambafreq); if (err) { From 2873d4d52f7c52d60b316ba6c47bd7122b5a9861 Mon Sep 17 00:00:00 2001 From: Andreas Larsson Date: Fri, 29 Apr 2022 10:46:56 +0200 Subject: [PATCH 059/192] can: grcan: only use the NAPI poll budget for RX The previous split budget between TX and RX made it return not using the entire budget but at the same time not having calling called napi_complete. This sometimes led to the poll to not be called, and at the same time having TX and RX interrupts disabled resulting in the driver getting stuck. Fixes: 6cec9b07fe6a ("can: grcan: Add device driver for GRCAN and GRHCAN cores") Link: https://lore.kernel.org/all/20220429084656.29788-4-andreas@gaisler.com Cc: stable@vger.kernel.org Signed-off-by: Andreas Larsson Signed-off-by: Marc Kleine-Budde --- drivers/net/can/grcan.c | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c index 4ca3da56d3aa..5215bd9b2c80 100644 --- a/drivers/net/can/grcan.c +++ b/drivers/net/can/grcan.c @@ -1125,7 +1125,7 @@ static int grcan_close(struct net_device *dev) return 0; } -static int grcan_transmit_catch_up(struct net_device *dev, int budget) +static void grcan_transmit_catch_up(struct net_device *dev) { struct grcan_priv *priv = netdev_priv(dev); unsigned long flags; @@ -1133,7 +1133,7 @@ static int grcan_transmit_catch_up(struct net_device *dev, int budget) spin_lock_irqsave(&priv->lock, flags); - work_done = catch_up_echo_skb(dev, budget, true); + work_done = catch_up_echo_skb(dev, -1, true); if (work_done) { if (!priv->resetting && !priv->closing && !(priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)) @@ -1147,8 +1147,6 @@ static int grcan_transmit_catch_up(struct net_device *dev, int budget) } spin_unlock_irqrestore(&priv->lock, flags); - - return work_done; } static int grcan_receive(struct net_device *dev, int budget) @@ -1230,19 +1228,13 @@ static int grcan_poll(struct napi_struct *napi, int budget) struct net_device *dev = priv->dev; struct grcan_registers __iomem *regs = priv->regs; unsigned long flags; - int tx_work_done, rx_work_done; - int rx_budget = budget / 2; - int tx_budget = budget - rx_budget; + int work_done; - /* Half of the budget for receiving messages */ - rx_work_done = grcan_receive(dev, rx_budget); + work_done = grcan_receive(dev, budget); - /* Half of the budget for transmitting messages as that can trigger echo - * frames being received - */ - tx_work_done = grcan_transmit_catch_up(dev, tx_budget); + grcan_transmit_catch_up(dev); - if (rx_work_done < rx_budget && tx_work_done < tx_budget) { + if (work_done < budget) { napi_complete(napi); /* Guarantee no interference with a running reset that otherwise @@ -1259,7 +1251,7 @@ static int grcan_poll(struct napi_struct *napi, int budget) spin_unlock_irqrestore(&priv->lock, flags); } - return rx_work_done + tx_work_done; + return work_done; } /* Work tx bug by waiting while for the risky situation to clear. If that fails, From efce2d0ba6bf70994394a5a139347ced4d172771 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 28 Apr 2022 11:15:08 -0400 Subject: [PATCH 060/192] SUNRPC: Ensure timely close of disconnected AF_LOCAL sockets When the rpcbind server closes the socket, we need to ensure that the socket is closed by the kernel as soon as feasible, so add a sk_state_change callback to trigger this close. Signed-off-by: Trond Myklebust --- net/sunrpc/xprtsock.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index f9849b297ea3..25b8a8ead56b 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1418,6 +1418,26 @@ static size_t xs_tcp_bc_maxpayload(struct rpc_xprt *xprt) } #endif /* CONFIG_SUNRPC_BACKCHANNEL */ +/** + * xs_local_state_change - callback to handle AF_LOCAL socket state changes + * @sk: socket whose state has changed + * + */ +static void xs_local_state_change(struct sock *sk) +{ + struct rpc_xprt *xprt; + struct sock_xprt *transport; + + if (!(xprt = xprt_from_sock(sk))) + return; + transport = container_of(xprt, struct sock_xprt, xprt); + if (sk->sk_shutdown & SHUTDOWN_MASK) { + clear_bit(XPRT_CONNECTED, &xprt->state); + /* Trigger the socket release */ + xs_run_error_worker(transport, XPRT_SOCK_WAKE_DISCONNECT); + } +} + /** * xs_tcp_state_change - callback to handle TCP socket state changes * @sk: socket whose state has changed @@ -1866,6 +1886,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, sk->sk_user_data = xprt; sk->sk_data_ready = xs_data_ready; sk->sk_write_space = xs_udp_write_space; + sk->sk_state_change = xs_local_state_change; sk->sk_error_report = xs_error_report; xprt_clear_connected(xprt); From f0a6c68f69981214cb7858738dd2bc81475111f7 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Sun, 24 Apr 2022 12:46:23 +0100 Subject: [PATCH 061/192] MIPS: Fix CP0 counter erratum detection for R4k CPUs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the discrepancy between the two places we check for the CP0 counter erratum in along with the incorrect comparison of the R4400 revision number against 0x30 which matches none and consistently consider all R4000 and R4400 processors affected, as documented in processor errata publications[1][2][3], following the mapping between CP0 PRId register values and processor models: PRId | Processor Model ---------+-------------------- 00000422 | R4000 Revision 2.2 00000430 | R4000 Revision 3.0 00000440 | R4400 Revision 1.0 00000450 | R4400 Revision 2.0 00000460 | R4400 Revision 3.0 No other revision of either processor has ever been spotted. Contrary to what has been stated in commit ce202cbb9e0b ("[MIPS] Assume R4000/R4400 newer than 3.0 don't have the mfc0 count bug") marking the CP0 counter as buggy does not preclude it from being used as either a clock event or a clock source device. It just cannot be used as both at a time, because in that case clock event interrupts will be occasionally lost, and the use as a clock event device takes precedence. Compare against 0x4ff in `can_use_mips_counter' so that a single machine instruction is produced. References: [1] "MIPS R4000PC/SC Errata, Processor Revision 2.2 and 3.0", MIPS Technologies Inc., May 10, 1994, Erratum 53, p.13 [2] "MIPS R4400PC/SC Errata, Processor Revision 1.0", MIPS Technologies Inc., February 9, 1994, Erratum 21, p.4 [3] "MIPS R4400PC/SC Errata, Processor Revision 2.0 & 3.0", MIPS Technologies Inc., January 24, 1995, Erratum 14, p.3 Signed-off-by: Maciej W. Rozycki Fixes: ce202cbb9e0b ("[MIPS] Assume R4000/R4400 newer than 3.0 don't have the mfc0 count bug") Cc: stable@vger.kernel.org # v2.6.24+ Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/timex.h | 8 ++++---- arch/mips/kernel/time.c | 11 +++-------- 2 files changed, 7 insertions(+), 12 deletions(-) diff --git a/arch/mips/include/asm/timex.h b/arch/mips/include/asm/timex.h index b05bb70a2e46..8026baf46e72 100644 --- a/arch/mips/include/asm/timex.h +++ b/arch/mips/include/asm/timex.h @@ -40,9 +40,9 @@ typedef unsigned int cycles_t; /* - * On R4000/R4400 before version 5.0 an erratum exists such that if the - * cycle counter is read in the exact moment that it is matching the - * compare register, no interrupt will be generated. + * On R4000/R4400 an erratum exists such that if the cycle counter is + * read in the exact moment that it is matching the compare register, + * no interrupt will be generated. * * There is a suggested workaround and also the erratum can't strike if * the compare interrupt isn't being used as the clock source device. @@ -63,7 +63,7 @@ static inline int can_use_mips_counter(unsigned int prid) if (!__builtin_constant_p(cpu_has_counter)) asm volatile("" : "=m" (cpu_data[0].options)); if (likely(cpu_has_counter && - prid >= (PRID_IMP_R4000 | PRID_REV_ENCODE_44(5, 0)))) + prid > (PRID_IMP_R4000 | PRID_REV_ENCODE_44(15, 15)))) return 1; else return 0; diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c index caa01457dce6..ed339d7979f3 100644 --- a/arch/mips/kernel/time.c +++ b/arch/mips/kernel/time.c @@ -141,15 +141,10 @@ static __init int cpu_has_mfc0_count_bug(void) case CPU_R4400MC: /* * The published errata for the R4400 up to 3.0 say the CPU - * has the mfc0 from count bug. + * has the mfc0 from count bug. This seems the last version + * produced. */ - if ((current_cpu_data.processor_id & 0xff) <= 0x30) - return 1; - - /* - * we assume newer revisions are ok - */ - return 0; + return 1; } return 0; From c6fe81191bd74f7e6ae9ce96a4837df9485f3ab8 Mon Sep 17 00:00:00 2001 From: Nick Kossifidis Date: Tue, 22 Mar 2022 15:28:39 +0200 Subject: [PATCH 062/192] RISC-V: relocate DTB if it's outside memory region In case the DTB provided by the bootloader/BootROM is before the kernel image or outside /memory, we won't be able to access it through the linear mapping, and get a segfault on setup_arch(). Currently OpenSBI relocates DTB but that's not always the case (e.g. if FW_JUMP_FDT_ADDR is not specified), and it's also not the most portable approach since the default FW_JUMP_FDT_ADDR of the generic platform relocates the DTB at a specific offset that may not be available. To avoid this situation copy DTB so that it's visible through the linear mapping. Signed-off-by: Nick Kossifidis Link: https://lore.kernel.org/r/20220322132839.3653682-1-mick@ics.forth.gr Tested-by: Conor Dooley Fixes: f105aa940e78 ("riscv: add BUILTIN_DTB support for MMU-enabled targets") Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/init.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index b0793dc0c291..05ed641a1134 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -208,8 +208,25 @@ static void __init setup_bootmem(void) * early_init_fdt_reserve_self() since __pa() does * not work for DTB pointers that are fixmap addresses */ - if (!IS_ENABLED(CONFIG_BUILTIN_DTB)) - memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); + if (!IS_ENABLED(CONFIG_BUILTIN_DTB)) { + /* + * In case the DTB is not located in a memory region we won't + * be able to locate it later on via the linear mapping and + * get a segfault when accessing it via __va(dtb_early_pa). + * To avoid this situation copy DTB to a memory region. + * Note that memblock_phys_alloc will also reserve DTB region. + */ + if (!memblock_is_memory(dtb_early_pa)) { + size_t fdt_size = fdt_totalsize(dtb_early_va); + phys_addr_t new_dtb_early_pa = memblock_phys_alloc(fdt_size, PAGE_SIZE); + void *new_dtb_early_va = early_memremap(new_dtb_early_pa, fdt_size); + + memcpy(new_dtb_early_va, dtb_early_va, fdt_size); + early_memunmap(new_dtb_early_va, fdt_size); + _dtb_early_pa = new_dtb_early_pa; + } else + memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); + } early_init_fdt_scan_reserved_mem(); dma_contiguous_reserve(dma32_phys_limit); From 3d092ef09303e615707dc5755cf0e29b4df7555f Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Tue, 19 Apr 2022 12:08:09 -0500 Subject: [PATCH 063/192] ipmi: When handling send message responses, don't process the message A chunk was dropped when the code handling send messages was rewritten. Those messages shouldn't be processed normally, they are just an indication that the message was successfully sent and the timers should be started for the real response that should be coming later. Add back in the missing chunk to just discard the message and go on. Fixes: 059747c245f0 ("ipmi: Add support for IPMB direct messages") Reported-by: Joe Wiese Cc: stable@vger.kernel.org # v5.16+ Signed-off-by: Corey Minyard Tested-by: Joe Wiese --- drivers/char/ipmi/ipmi_msghandler.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index c59265146e9c..5f7abf456a17 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -4518,6 +4518,8 @@ return_unspecified: } else /* The message was sent, start the timer. */ intf_start_seq_timer(intf, msg->msgid); + requeue = 0; + goto out; } else if (((msg->rsp[0] >> 2) != ((msg->data[0] >> 2) | 1)) || (msg->rsp[1] != msg->data[1])) { /* From 9cc3aac42566a0021e0ab7c4e9b31667ad75b1e3 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Thu, 21 Apr 2022 06:49:43 -0500 Subject: [PATCH 064/192] ipmi:ipmi_ipmb: Fix null-ptr-deref in ipmi_unregister_smi() KASAN report null-ptr-deref as follows: KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 RIP: 0010:ipmi_unregister_smi+0x7d/0xd50 drivers/char/ipmi/ipmi_msghandler.c:3680 Call Trace: ipmi_ipmb_remove+0x138/0x1a0 drivers/char/ipmi/ipmi_ipmb.c:443 ipmi_ipmb_probe+0x409/0xda1 drivers/char/ipmi/ipmi_ipmb.c:548 i2c_device_probe+0x959/0xac0 drivers/i2c/i2c-core-base.c:563 really_probe+0x3f3/0xa70 drivers/base/dd.c:541 In ipmi_ipmb_probe(), 'iidev->intf' is not set before ipmi_register_smi() success. And in the error handling case, ipmi_ipmb_remove() is called to release resources, ipmi_unregister_smi() is called without check 'iidev->intf', this will cause KASAN null-ptr-deref issue. General kernel style is to allow NULL to be passed into unregister calls, so fix it that way. This allows a NULL check to be removed in other code. Fixes: 57c9e3c9a374 ("ipmi:ipmi_ipmb: Unregister the SMI on remove") Reported-by: Hulk Robot Cc: stable@vger.kernel.org # v5.17+ Cc: Wei Yongjun Signed-off-by: Corey Minyard --- drivers/char/ipmi/ipmi_msghandler.c | 5 ++++- drivers/char/ipmi/ipmi_si_intf.c | 5 +---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 5f7abf456a17..f1827257ef0e 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -3677,8 +3677,11 @@ static void cleanup_smi_msgs(struct ipmi_smi *intf) void ipmi_unregister_smi(struct ipmi_smi *intf) { struct ipmi_smi_watcher *w; - int intf_num = intf->intf_num, index; + int intf_num, index; + if (!intf) + return; + intf_num = intf->intf_num; mutex_lock(&ipmi_interfaces_mutex); intf->intf_num = -1; intf->in_shutdown = true; diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 64dedb3ef8ec..5604a810fb3d 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -2220,10 +2220,7 @@ static void cleanup_one_si(struct smi_info *smi_info) return; list_del(&smi_info->link); - - if (smi_info->intf) - ipmi_unregister_smi(smi_info->intf); - + ipmi_unregister_smi(smi_info->intf); kfree(smi_info); } From 892de36fd4a98fab3298d417c051d9099af5448d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 29 Apr 2022 12:22:10 -0400 Subject: [PATCH 065/192] SUNRPC: Ensure gss-proxy connects on setup For reasons best known to the author, gss-proxy does not implement a NULL procedure, and returns RPC_PROC_UNAVAIL. However we still want to ensure that we connect to the service at setup time. So add a quirk-flag specially for this case. Fixes: 1d658336b05f ("SUNRPC: Add RPC based upcall mechanism for RPCGSS auth") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 + net/sunrpc/auth_gss/gss_rpc_upcall.c | 2 +- net/sunrpc/clnt.c | 3 +++ 3 files changed, 5 insertions(+), 1 deletion(-) diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 267b7aeaf1a6..db5149567305 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -160,6 +160,7 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) #define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) +#define RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL (1UL << 12) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index 61c276bddaf2..8ca1d809b78d 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -97,7 +97,7 @@ static int gssp_rpc_create(struct net *net, struct rpc_clnt **_clnt) * timeout, which would result in reconnections being * done without the correct namespace: */ - .flags = RPC_CLNT_CREATE_NOPING | + .flags = RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL | RPC_CLNT_CREATE_NO_IDLE_TIMEOUT }; struct rpc_clnt *clnt; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 98133aa54f19..22c28cf43eba 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -479,6 +479,9 @@ static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, if (!(args->flags & RPC_CLNT_CREATE_NOPING)) { int err = rpc_ping(clnt); + if ((args->flags & RPC_CLNT_CREATE_IGNORE_NULL_UNAVAIL) && + err == -EOPNOTSUPP) + err = 0; if (err != 0) { rpc_shutdown_client(clnt); return ERR_PTR(err); From 2bfed7d2ffa5d86c462d3e2067f2832eaf8c04c7 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Sat, 19 Mar 2022 02:00:11 +0100 Subject: [PATCH 066/192] selftests/seccomp: Don't call read() on TTY from background pgrp Since commit 92d25637a3a4 ("kselftest: signal all child processes"), tests are executed in background process groups. This means that trying to read from stdin now throws SIGTTIN when stdin is a TTY, which breaks some seccomp selftests that try to use read(0, NULL, 0) as a dummy syscall. The simplest way to fix that is probably to just use -1 instead of 0 as the dummy read()'s FD. Fixes: 92d25637a3a4 ("kselftest: signal all child processes") Signed-off-by: Jann Horn Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20220319010011.1374622-1-jannh@google.com --- tools/testing/selftests/seccomp/seccomp_bpf.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 9d126d7fabdb..313bb0cbfb1e 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -955,7 +955,7 @@ TEST(ERRNO_valid) ASSERT_EQ(0, ret); EXPECT_EQ(parent, syscall(__NR_getppid)); - EXPECT_EQ(-1, read(0, NULL, 0)); + EXPECT_EQ(-1, read(-1, NULL, 0)); EXPECT_EQ(E2BIG, errno); } @@ -974,7 +974,7 @@ TEST(ERRNO_zero) EXPECT_EQ(parent, syscall(__NR_getppid)); /* "errno" of 0 is ok. */ - EXPECT_EQ(0, read(0, NULL, 0)); + EXPECT_EQ(0, read(-1, NULL, 0)); } /* @@ -995,7 +995,7 @@ TEST(ERRNO_capped) ASSERT_EQ(0, ret); EXPECT_EQ(parent, syscall(__NR_getppid)); - EXPECT_EQ(-1, read(0, NULL, 0)); + EXPECT_EQ(-1, read(-1, NULL, 0)); EXPECT_EQ(4095, errno); } @@ -1026,7 +1026,7 @@ TEST(ERRNO_order) ASSERT_EQ(0, ret); EXPECT_EQ(parent, syscall(__NR_getppid)); - EXPECT_EQ(-1, read(0, NULL, 0)); + EXPECT_EQ(-1, read(-1, NULL, 0)); EXPECT_EQ(12, errno); } @@ -2623,7 +2623,7 @@ void *tsync_sibling(void *data) ret = prctl(PR_GET_NO_NEW_PRIVS, 0, 0, 0, 0); if (!ret) return (void *)SIBLING_EXIT_NEWPRIVS; - read(0, NULL, 0); + read(-1, NULL, 0); return (void *)SIBLING_EXIT_UNKILLED; } From a3d0562d4dc039bca39445e1cddde7951662e17d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 29 Apr 2022 12:27:30 -0400 Subject: [PATCH 067/192] Revert "SUNRPC: attempt AF_LOCAL connect on setup" This reverts commit 7073ea8799a8cf73db60270986f14e4aae20fa80. We must not try to connect the socket while the transport is under construction, because the mechanisms to safely tear it down are not in place. As the code stands, we end up leaking the sockets on a connection error. Reported-by: wanghai (M) Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust --- net/sunrpc/xprtsock.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 25b8a8ead56b..650102a9c86a 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2875,9 +2875,6 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args) } xprt_set_bound(xprt); xs_format_peer_addresses(xprt, "local", RPCBIND_NETID_LOCAL); - ret = ERR_PTR(xs_local_setup_socket(transport)); - if (ret) - goto out_err; break; default: ret = ERR_PTR(-EAFNOSUPPORT); From 38dcd9570d6fced1dcfee226d5b29722b070ce90 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Thu, 28 Apr 2022 12:45:10 +0800 Subject: [PATCH 068/192] selftests/net: add missing tests to Makefile When generating the selftests to another folder, the fixed tests are missing as they are not in Makefile, e.g. make -C tools/testing/selftests/ install \ TARGETS="net" INSTALL_PATH=/tmp/kselftests Signed-off-by: Hangbin Liu Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 3fe2515aa616..0f2ebc38d893 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -30,7 +30,7 @@ TEST_PROGS += ioam6.sh TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh TEST_PROGS += cmsg_so_mark.sh -TEST_PROGS += cmsg_time.sh +TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh @@ -54,6 +54,7 @@ TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls TEST_GEN_FILES += toeplitz TEST_GEN_FILES += cmsg_sender +TEST_PROGS += test_vxlan_vnifiltering.sh TEST_FILES := settings From f62c5acc800eebfe25bf6738b2cc8aa5d6aa7598 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Thu, 28 Apr 2022 12:45:11 +0800 Subject: [PATCH 069/192] selftests/net/forwarding: add missing tests to Makefile When generating the selftests to another folder, the fixed tests are missing as they are not in Makefile, e.g. make -C tools/testing/selftests/ install \ TARGETS="net/forwarding" INSTALL_PATH=/tmp/kselftests Signed-off-by: Hangbin Liu Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/forwarding/Makefile | 33 +++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 8fa97ae9af9e..c87e674b61b1 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -2,15 +2,31 @@ TEST_PROGS = bridge_igmp.sh \ bridge_locked_port.sh \ + bridge_mld.sh \ bridge_port_isolation.sh \ bridge_sticky_fdb.sh \ bridge_vlan_aware.sh \ + bridge_vlan_mcast.sh \ bridge_vlan_unaware.sh \ + custom_multipath_hash.sh \ + dual_vxlan_bridge.sh \ + ethtool_extended_state.sh \ ethtool.sh \ + gre_custom_multipath_hash.sh \ gre_inner_v4_multipath.sh \ gre_inner_v6_multipath.sh \ + gre_multipath_nh_res.sh \ + gre_multipath_nh.sh \ gre_multipath.sh \ + hw_stats_l3.sh \ ip6_forward_instats_vrf.sh \ + ip6gre_custom_multipath_hash.sh \ + ip6gre_flat_key.sh \ + ip6gre_flat_keys.sh \ + ip6gre_flat.sh \ + ip6gre_hier_key.sh \ + ip6gre_hier_keys.sh \ + ip6gre_hier.sh \ ip6gre_inner_v4_multipath.sh \ ip6gre_inner_v6_multipath.sh \ ipip_flat_gre_key.sh \ @@ -34,36 +50,53 @@ TEST_PROGS = bridge_igmp.sh \ mirror_gre_vlan_bridge_1q.sh \ mirror_gre_vlan.sh \ mirror_vlan.sh \ + pedit_dsfield.sh \ + pedit_ip.sh \ + pedit_l4port.sh \ + q_in_vni_ipv6.sh \ + q_in_vni.sh \ router_bridge.sh \ router_bridge_vlan.sh \ router_broadcast.sh \ + router_mpath_nh_res.sh \ router_mpath_nh.sh \ router_multicast.sh \ router_multipath.sh \ + router_nh.sh \ router.sh \ router_vid_1.sh \ sch_ets.sh \ + sch_red.sh \ sch_tbf_ets.sh \ sch_tbf_prio.sh \ sch_tbf_root.sh \ + skbedit_priority.sh \ tc_actions.sh \ tc_chains.sh \ tc_flower_router.sh \ tc_flower.sh \ tc_mpls_l2vpn.sh \ + tc_police.sh \ tc_shblocks.sh \ tc_vlan_modify.sh \ + vxlan_asymmetric_ipv6.sh \ vxlan_asymmetric.sh \ + vxlan_bridge_1d_ipv6.sh \ + vxlan_bridge_1d_port_8472_ipv6.sh \ vxlan_bridge_1d_port_8472.sh \ vxlan_bridge_1d.sh \ + vxlan_bridge_1q_ipv6.sh \ + vxlan_bridge_1q_port_8472_ipv6.sh vxlan_bridge_1q_port_8472.sh \ vxlan_bridge_1q.sh \ + vxlan_symmetric_ipv6.sh \ vxlan_symmetric.sh TEST_PROGS_EXTENDED := devlink_lib.sh \ ethtool_lib.sh \ fib_offload_lib.sh \ forwarding.config.sample \ + ip6gre_lib.sh \ ipip_lib.sh \ lib.sh \ mirror_gre_lib.sh \ From ff5265d45345d01fefc98fcb9ae891b59633c919 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 28 Apr 2022 14:25:43 +0800 Subject: [PATCH 070/192] net: ethernet: mediatek: add missing of_node_put() in mtk_sgmii_init() The node pointer returned by of_parse_phandle() with refcount incremented, so add of_node_put() after using it in mtk_sgmii_init(). Fixes: 9ffee4a8276c ("net: ethernet: mediatek: Extend SGMII related functions") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20220428062543.64883-1-yangyingliang@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mediatek/mtk_sgmii.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mediatek/mtk_sgmii.c b/drivers/net/ethernet/mediatek/mtk_sgmii.c index 32d83421226a..5897940a418b 100644 --- a/drivers/net/ethernet/mediatek/mtk_sgmii.c +++ b/drivers/net/ethernet/mediatek/mtk_sgmii.c @@ -26,6 +26,7 @@ int mtk_sgmii_init(struct mtk_sgmii *ss, struct device_node *r, u32 ana_rgc3) break; ss->regmap[i] = syscon_node_to_regmap(np); + of_node_put(np); if (IS_ERR(ss->regmap[i])) return PTR_ERR(ss->regmap[i]); } From e87f66b38e66dffdec9daa9f8f0eb044e9a62e3b Mon Sep 17 00:00:00 2001 From: Niels Dossche Date: Thu, 28 Apr 2022 23:19:32 +0200 Subject: [PATCH 071/192] net: mdio: Fix ENOMEM return value in BCM6368 mux bus controller Error values inside the probe function must be < 0. The ENOMEM return value has the wrong sign: it is positive instead of negative. Add a minus sign. Fixes: e239756717b5 ("net: mdio: Add BCM6368 MDIO mux bus controller") Signed-off-by: Niels Dossche Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20220428211931.8130-1-dossche.niels@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/mdio/mdio-mux-bcm6368.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/mdio/mdio-mux-bcm6368.c b/drivers/net/mdio/mdio-mux-bcm6368.c index 6dcbf987d61b..8b444a8eb6b5 100644 --- a/drivers/net/mdio/mdio-mux-bcm6368.c +++ b/drivers/net/mdio/mdio-mux-bcm6368.c @@ -115,7 +115,7 @@ static int bcm6368_mdiomux_probe(struct platform_device *pdev) md->mii_bus = devm_mdiobus_alloc(&pdev->dev); if (!md->mii_bus) { dev_err(&pdev->dev, "mdiomux bus alloc failed\n"); - return ENOMEM; + return -ENOMEM; } bus = md->mii_bus; From 52b2abef450a78e25d485ac61e32f4ce86a87701 Mon Sep 17 00:00:00 2001 From: Qiao Ma Date: Thu, 28 Apr 2022 20:30:16 +0800 Subject: [PATCH 072/192] hinic: fix bug of wq out of bound access If wq has only one page, we need to check wqe rolling over page by compare end_idx and curr_idx, and then copy wqe to shadow wqe to avoid out of bound access. This work has been done in hinic_get_wqe, but missed for hinic_read_wqe. This patch fixes it, and removes unnecessary MASKED_WQE_IDX(). Fixes: 7dd29ee12865 ("hinic: add sriov feature support") Signed-off-by: Qiao Ma Reviewed-by: Xunlei Pang Link: https://lore.kernel.org/r/282817b0e1ae2e28fdf3ed8271a04e77f57bf42e.1651148587.git.mqaio@linux.alibaba.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c index 2d9b06d7caad..f7dc7d825f63 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c @@ -771,7 +771,7 @@ struct hinic_hw_wqe *hinic_get_wqe(struct hinic_wq *wq, unsigned int wqe_size, /* If we only have one page, still need to get shadown wqe when * wqe rolling-over page */ - if (curr_pg != end_pg || MASKED_WQE_IDX(wq, end_prod_idx) < *prod_idx) { + if (curr_pg != end_pg || end_prod_idx < *prod_idx) { void *shadow_addr = &wq->shadow_wqe[curr_pg * wq->max_wqe_size]; copy_wqe_to_shadow(wq, shadow_addr, num_wqebbs, *prod_idx); @@ -841,7 +841,10 @@ struct hinic_hw_wqe *hinic_read_wqe(struct hinic_wq *wq, unsigned int wqe_size, *cons_idx = curr_cons_idx; - if (curr_pg != end_pg) { + /* If we only have one page, still need to get shadown wqe when + * wqe rolling-over page + */ + if (curr_pg != end_pg || end_cons_idx < curr_cons_idx) { void *shadow_addr = &wq->shadow_wqe[curr_pg * wq->max_wqe_size]; copy_wqe_to_shadow(wq, shadow_addr, num_wqebbs, *cons_idx); From fee34dd199384a483f84806a5cbcf8d657a481cc Mon Sep 17 00:00:00 2001 From: Arun Ramadoss Date: Thu, 28 Apr 2022 12:37:09 +0530 Subject: [PATCH 073/192] net: dsa: ksz9477: port mirror sniffing limited to one port This patch limits the sniffing to only one port during the mirror add. And during the mirror_del it checks for all the ports using the sniff, if and only if no other ports are referring, sniffing is disabled. The code is updated based on the review comments of LAN937x port mirror patch. Link: https://patchwork.kernel.org/project/netdevbpf/patch/20210422094257.1641396-8-prasanna.vengateshan@microchip.com/ Fixes: b987e98e50ab ("dsa: add DSA switch driver for Microchip KSZ9477") Signed-off-by: Prasanna Vengateshan Signed-off-by: Arun Ramadoss Link: https://lore.kernel.org/r/20220428070709.7094-1-arun.ramadoss@microchip.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/microchip/ksz9477.c | 38 ++++++++++++++++++++++++++--- 1 file changed, 34 insertions(+), 4 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 8222c8a6c5ec..7310d19d1f06 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -1021,14 +1021,32 @@ static int ksz9477_port_mirror_add(struct dsa_switch *ds, int port, bool ingress, struct netlink_ext_ack *extack) { struct ksz_device *dev = ds->priv; + u8 data; + int p; + + /* Limit to one sniffer port + * Check if any of the port is already set for sniffing + * If yes, instruct the user to remove the previous entry & exit + */ + for (p = 0; p < dev->port_cnt; p++) { + /* Skip the current sniffing port */ + if (p == mirror->to_local_port) + continue; + + ksz_pread8(dev, p, P_MIRROR_CTRL, &data); + + if (data & PORT_MIRROR_SNIFFER) { + NL_SET_ERR_MSG_MOD(extack, + "Sniffer port is already configured, delete existing rules & retry"); + return -EBUSY; + } + } if (ingress) ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, true); else ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, true); - ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_SNIFFER, false); - /* configure mirror port */ ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL, PORT_MIRROR_SNIFFER, true); @@ -1042,16 +1060,28 @@ static void ksz9477_port_mirror_del(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror) { struct ksz_device *dev = ds->priv; + bool in_use = false; u8 data; + int p; if (mirror->ingress) ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, false); else ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, false); - ksz_pread8(dev, port, P_MIRROR_CTRL, &data); - if (!(data & (PORT_MIRROR_RX | PORT_MIRROR_TX))) + /* Check if any of the port is still referring to sniffer port */ + for (p = 0; p < dev->port_cnt; p++) { + ksz_pread8(dev, p, P_MIRROR_CTRL, &data); + + if ((data & (PORT_MIRROR_RX | PORT_MIRROR_TX))) { + in_use = true; + break; + } + } + + /* delete sniffing if there are no other mirroring rules */ + if (!in_use) ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL, PORT_MIRROR_SNIFFER, false); } From a9e9b091a1c14ecd8bd9d3214a62142a1786fe30 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 28 Apr 2022 17:53:17 +0800 Subject: [PATCH 074/192] net: dsa: mt7530: add missing of_node_put() in mt7530_setup() Add of_node_put() if of_get_phy_mode() fails in mt7530_setup() Fixes: 0c65b2b90d13 ("net: of_get_phy_mode: Change API to solve int/unit warnings") Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20220428095317.538829-1-yangyingliang@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/dsa/mt7530.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 19f0035d4410..fe3cb26f4287 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2229,6 +2229,7 @@ mt7530_setup(struct dsa_switch *ds) ret = of_get_phy_mode(mac_np, &interface); if (ret && ret != -ENODEV) { of_node_put(mac_np); + of_node_put(phy_node); return ret; } id = of_mdio_parse_addr(ds->dev, phy_node); From 1a15267b7be77e0792cf0c7b36ca65c8eb2df0d8 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 28 Apr 2022 17:57:16 +0800 Subject: [PATCH 075/192] net: stmmac: dwmac-sun8i: add missing of_node_put() in sun8i_dwmac_register_mdio_mux() The node pointer returned by of_get_child_by_name() with refcount incremented, so add of_node_put() after using it. Fixes: 634db83b8265 ("net: stmmac: dwmac-sun8i: Handle integrated/external MDIOs") Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20220428095716.540452-1-yangyingliang@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index f86cc83003f2..f834472599f7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -907,6 +907,7 @@ static int sun8i_dwmac_register_mdio_mux(struct stmmac_priv *priv) ret = mdio_mux_init(priv->device, mdio_mux, mdio_mux_syscon_switch_fn, &gmac->mux_handle, priv, priv->mii); + of_node_put(mdio_mux); return ret; } From 95098d5ac2551769807031444e55a0da5d4f0952 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Fri, 29 Apr 2022 09:53:37 +0800 Subject: [PATCH 076/192] net: cpsw: add missing of_node_put() in cpsw_probe_dt() 'tmp_node' need be put before returning from cpsw_probe_dt(), so add missing of_node_put() in error path. Fixes: ed3525eda4c4 ("net: ethernet: ti: introduce cpsw switchdev based driver part 1 - dual-emac") Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/cpsw_new.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index bd4b1528cf99..79e850fe4621 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1246,8 +1246,10 @@ static int cpsw_probe_dt(struct cpsw_common *cpsw) data->slave_data = devm_kcalloc(dev, CPSW_SLAVE_PORTS_NUM, sizeof(struct cpsw_slave_data), GFP_KERNEL); - if (!data->slave_data) + if (!data->slave_data) { + of_node_put(tmp_node); return -ENOMEM; + } /* Populate all the child nodes here... */ @@ -1341,6 +1343,7 @@ static int cpsw_probe_dt(struct cpsw_common *cpsw) err_node_put: of_node_put(port_np); + of_node_put(tmp_node); return ret; } From 39cb9faa5d46d0d0694f4b594ef905f517600c8e Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 29 Apr 2022 21:05:16 +0100 Subject: [PATCH 077/192] rxrpc: Enable IPv6 checksums on transport socket AF_RXRPC doesn't currently enable IPv6 UDP Tx checksums on the transport socket it opens and the checksums in the packets it generates end up 0. It probably should also enable IPv6 UDP Rx checksums and IPv4 UDP checksums. The latter only seem to be applied if the socket family is AF_INET and don't seem to apply if it's AF_INET6. IPv4 packets from an IPv6 socket seem to have checksums anyway. What seems to have happened is that the inet_inv_convert_csum() call didn't get converted to the appropriate udp_port_cfg parameters - and udp_sock_create() disables checksums unless explicitly told not too. Fix this by enabling the three udp_port_cfg checksum options. Fixes: 1a9b86c9fd95 ("rxrpc: use udp tunnel APIs instead of open code in rxrpc_open_socket") Reported-by: Marc Dionne Signed-off-by: David Howells Reviewed-by: Xin Long Reviewed-by: Marc Dionne cc: Vadim Fedorenko cc: David S. Miller cc: linux-afs@lists.infradead.org Signed-off-by: David S. Miller --- net/rxrpc/local_object.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index a4111408ffd0..6a1611b0e303 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -117,6 +117,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) local, srx->transport_type, srx->transport.family); udp_conf.family = srx->transport.family; + udp_conf.use_udp_checksums = true; if (udp_conf.family == AF_INET) { udp_conf.local_ip = srx->transport.sin.sin_addr; udp_conf.local_udp_port = srx->transport.sin.sin_port; @@ -124,6 +125,8 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) } else { udp_conf.local_ip6 = srx->transport.sin6.sin6_addr; udp_conf.local_udp_port = srx->transport.sin6.sin6_port; + udp_conf.use_udp6_tx_checksums = true; + udp_conf.use_udp6_rx_checksums = true; #endif } ret = udp_sock_create(net, &udp_conf, &local->socket); From dba5bdd57bea587ea4f0b79b03c71135f84a7e8b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 29 Apr 2022 08:42:57 -0700 Subject: [PATCH 078/192] net: igmp: respect RCU rules in ip_mc_source() and ip_mc_msfilter() syzbot reported an UAF in ip_mc_sf_allow() [1] Whenever RCU protected list replaces an object, the pointer to the new object needs to be updated _before_ the call to kfree_rcu() or call_rcu() Because kfree_rcu(ptr, rcu) got support for NULL ptr only recently in commit 12edff045bc6 ("rcu: Make kfree_rcu() ignore NULL pointers"), I chose to use the conditional to make sure stable backports won't miss this detail. if (psl) kfree_rcu(psl, rcu); net/ipv6/mcast.c has similar issues, addressed in a separate patch. [1] BUG: KASAN: use-after-free in ip_mc_sf_allow+0x6bb/0x6d0 net/ipv4/igmp.c:2655 Read of size 4 at addr ffff88807d37b904 by task syz-executor.5/908 CPU: 0 PID: 908 Comm: syz-executor.5 Not tainted 5.18.0-rc4-syzkaller-00064-g8f4dd16603ce #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description.constprop.0.cold+0xeb/0x467 mm/kasan/report.c:313 print_report mm/kasan/report.c:429 [inline] kasan_report.cold+0xf4/0x1c6 mm/kasan/report.c:491 ip_mc_sf_allow+0x6bb/0x6d0 net/ipv4/igmp.c:2655 raw_v4_input net/ipv4/raw.c:190 [inline] raw_local_deliver+0x4d1/0xbe0 net/ipv4/raw.c:218 ip_protocol_deliver_rcu+0xcf/0xb30 net/ipv4/ip_input.c:193 ip_local_deliver_finish+0x2ee/0x4c0 net/ipv4/ip_input.c:233 NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] ip_local_deliver+0x1b3/0x200 net/ipv4/ip_input.c:254 dst_input include/net/dst.h:461 [inline] ip_rcv_finish+0x1cb/0x2f0 net/ipv4/ip_input.c:437 NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] ip_rcv+0xaa/0xd0 net/ipv4/ip_input.c:556 __netif_receive_skb_one_core+0x114/0x180 net/core/dev.c:5405 __netif_receive_skb+0x24/0x1b0 net/core/dev.c:5519 netif_receive_skb_internal net/core/dev.c:5605 [inline] netif_receive_skb+0x13e/0x8e0 net/core/dev.c:5664 tun_rx_batched.isra.0+0x460/0x720 drivers/net/tun.c:1534 tun_get_user+0x28b7/0x3e30 drivers/net/tun.c:1985 tun_chr_write_iter+0xdb/0x200 drivers/net/tun.c:2015 call_write_iter include/linux/fs.h:2050 [inline] new_sync_write+0x38a/0x560 fs/read_write.c:504 vfs_write+0x7c0/0xac0 fs/read_write.c:591 ksys_write+0x127/0x250 fs/read_write.c:644 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f3f12c3bbff Code: 89 54 24 18 48 89 74 24 10 89 7c 24 08 e8 99 fd ff ff 48 8b 54 24 18 48 8b 74 24 10 41 89 c0 8b 7c 24 08 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 31 44 89 c7 48 89 44 24 08 e8 cc fd ff ff 48 RSP: 002b:00007f3f13ea9130 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 00007f3f12d9bf60 RCX: 00007f3f12c3bbff RDX: 0000000000000036 RSI: 0000000020002ac0 RDI: 00000000000000c8 RBP: 00007f3f12ce308d R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000036 R11: 0000000000000293 R12: 0000000000000000 R13: 00007fffb68dd79f R14: 00007f3f13ea9300 R15: 0000000000022000 Allocated by task 908: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:45 [inline] set_alloc_info mm/kasan/common.c:436 [inline] ____kasan_kmalloc mm/kasan/common.c:515 [inline] ____kasan_kmalloc mm/kasan/common.c:474 [inline] __kasan_kmalloc+0xa6/0xd0 mm/kasan/common.c:524 kasan_kmalloc include/linux/kasan.h:234 [inline] __do_kmalloc mm/slab.c:3710 [inline] __kmalloc+0x209/0x4d0 mm/slab.c:3719 kmalloc include/linux/slab.h:586 [inline] sock_kmalloc net/core/sock.c:2501 [inline] sock_kmalloc+0xb5/0x100 net/core/sock.c:2492 ip_mc_source+0xba2/0x1100 net/ipv4/igmp.c:2392 do_ip_setsockopt net/ipv4/ip_sockglue.c:1296 [inline] ip_setsockopt+0x2312/0x3ab0 net/ipv4/ip_sockglue.c:1432 raw_setsockopt+0x274/0x2c0 net/ipv4/raw.c:861 __sys_setsockopt+0x2db/0x6a0 net/socket.c:2180 __do_sys_setsockopt net/socket.c:2191 [inline] __se_sys_setsockopt net/socket.c:2188 [inline] __x64_sys_setsockopt+0xba/0x150 net/socket.c:2188 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Freed by task 753: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 kasan_set_track+0x21/0x30 mm/kasan/common.c:45 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:370 ____kasan_slab_free mm/kasan/common.c:366 [inline] ____kasan_slab_free+0x13d/0x180 mm/kasan/common.c:328 kasan_slab_free include/linux/kasan.h:200 [inline] __cache_free mm/slab.c:3439 [inline] kmem_cache_free_bulk+0x69/0x460 mm/slab.c:3774 kfree_bulk include/linux/slab.h:437 [inline] kfree_rcu_work+0x51c/0xa10 kernel/rcu/tree.c:3318 process_one_work+0x996/0x1610 kernel/workqueue.c:2289 worker_thread+0x665/0x1080 kernel/workqueue.c:2436 kthread+0x2e9/0x3a0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:298 Last potentially related work creation: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 __kasan_record_aux_stack+0x7e/0x90 mm/kasan/generic.c:348 kvfree_call_rcu+0x74/0x990 kernel/rcu/tree.c:3595 ip_mc_msfilter+0x712/0xb60 net/ipv4/igmp.c:2510 do_ip_setsockopt net/ipv4/ip_sockglue.c:1257 [inline] ip_setsockopt+0x32e1/0x3ab0 net/ipv4/ip_sockglue.c:1432 raw_setsockopt+0x274/0x2c0 net/ipv4/raw.c:861 __sys_setsockopt+0x2db/0x6a0 net/socket.c:2180 __do_sys_setsockopt net/socket.c:2191 [inline] __se_sys_setsockopt net/socket.c:2188 [inline] __x64_sys_setsockopt+0xba/0x150 net/socket.c:2188 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Second to last potentially related work creation: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 __kasan_record_aux_stack+0x7e/0x90 mm/kasan/generic.c:348 call_rcu+0x99/0x790 kernel/rcu/tree.c:3074 mpls_dev_notify+0x552/0x8a0 net/mpls/af_mpls.c:1656 notifier_call_chain+0xb5/0x200 kernel/notifier.c:84 call_netdevice_notifiers_info+0xb5/0x130 net/core/dev.c:1938 call_netdevice_notifiers_extack net/core/dev.c:1976 [inline] call_netdevice_notifiers net/core/dev.c:1990 [inline] unregister_netdevice_many+0x92e/0x1890 net/core/dev.c:10751 default_device_exit_batch+0x449/0x590 net/core/dev.c:11245 ops_exit_list+0x125/0x170 net/core/net_namespace.c:167 cleanup_net+0x4ea/0xb00 net/core/net_namespace.c:594 process_one_work+0x996/0x1610 kernel/workqueue.c:2289 worker_thread+0x665/0x1080 kernel/workqueue.c:2436 kthread+0x2e9/0x3a0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:298 The buggy address belongs to the object at ffff88807d37b900 which belongs to the cache kmalloc-64 of size 64 The buggy address is located 4 bytes inside of 64-byte region [ffff88807d37b900, ffff88807d37b940) The buggy address belongs to the physical page: page:ffffea0001f4dec0 refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88807d37b180 pfn:0x7d37b flags: 0xfff00000000200(slab|node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000000200 ffff888010c41340 ffffea0001c795c8 ffff888010c40200 raw: ffff88807d37b180 ffff88807d37b000 000000010000001f 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 0, migratetype Unmovable, gfp_mask 0x342040(__GFP_IO|__GFP_NOWARN|__GFP_COMP|__GFP_HARDWALL|__GFP_THISNODE), pid 2963, tgid 2963 (udevd), ts 139732238007, free_ts 139730893262 prep_new_page mm/page_alloc.c:2441 [inline] get_page_from_freelist+0xba2/0x3e00 mm/page_alloc.c:4182 __alloc_pages+0x1b2/0x500 mm/page_alloc.c:5408 __alloc_pages_node include/linux/gfp.h:587 [inline] kmem_getpages mm/slab.c:1378 [inline] cache_grow_begin+0x75/0x350 mm/slab.c:2584 cache_alloc_refill+0x27f/0x380 mm/slab.c:2957 ____cache_alloc mm/slab.c:3040 [inline] ____cache_alloc mm/slab.c:3023 [inline] __do_cache_alloc mm/slab.c:3267 [inline] slab_alloc mm/slab.c:3309 [inline] __do_kmalloc mm/slab.c:3708 [inline] __kmalloc+0x3b3/0x4d0 mm/slab.c:3719 kmalloc include/linux/slab.h:586 [inline] kzalloc include/linux/slab.h:714 [inline] tomoyo_encode2.part.0+0xe9/0x3a0 security/tomoyo/realpath.c:45 tomoyo_encode2 security/tomoyo/realpath.c:31 [inline] tomoyo_encode+0x28/0x50 security/tomoyo/realpath.c:80 tomoyo_realpath_from_path+0x186/0x620 security/tomoyo/realpath.c:288 tomoyo_get_realpath security/tomoyo/file.c:151 [inline] tomoyo_path_perm+0x21b/0x400 security/tomoyo/file.c:822 security_inode_getattr+0xcf/0x140 security/security.c:1350 vfs_getattr fs/stat.c:157 [inline] vfs_statx+0x16a/0x390 fs/stat.c:232 vfs_fstatat+0x8c/0xb0 fs/stat.c:255 __do_sys_newfstatat+0x91/0x110 fs/stat.c:425 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae page last free stack trace: reset_page_owner include/linux/page_owner.h:24 [inline] free_pages_prepare mm/page_alloc.c:1356 [inline] free_pcp_prepare+0x549/0xd20 mm/page_alloc.c:1406 free_unref_page_prepare mm/page_alloc.c:3328 [inline] free_unref_page+0x19/0x6a0 mm/page_alloc.c:3423 __vunmap+0x85d/0xd30 mm/vmalloc.c:2667 __vfree+0x3c/0xd0 mm/vmalloc.c:2715 vfree+0x5a/0x90 mm/vmalloc.c:2746 __do_replace+0x16b/0x890 net/ipv6/netfilter/ip6_tables.c:1117 do_replace net/ipv6/netfilter/ip6_tables.c:1157 [inline] do_ip6t_set_ctl+0x90d/0xb90 net/ipv6/netfilter/ip6_tables.c:1639 nf_setsockopt+0x83/0xe0 net/netfilter/nf_sockopt.c:101 ipv6_setsockopt+0x122/0x180 net/ipv6/ipv6_sockglue.c:1026 tcp_setsockopt+0x136/0x2520 net/ipv4/tcp.c:3696 __sys_setsockopt+0x2db/0x6a0 net/socket.c:2180 __do_sys_setsockopt net/socket.c:2191 [inline] __se_sys_setsockopt net/socket.c:2188 [inline] __x64_sys_setsockopt+0xba/0x150 net/socket.c:2188 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Memory state around the buggy address: ffff88807d37b800: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc ffff88807d37b880: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc >ffff88807d37b900: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc ^ ffff88807d37b980: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc ffff88807d37ba00: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc Fixes: c85bb41e9318 ("igmp: fix ip_mc_sf_allow race [v5]") Signed-off-by: Eric Dumazet Reported-by: syzbot Cc: Flavio Leitner Signed-off-by: David S. Miller --- net/ipv4/igmp.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 2ad3c7b42d6d..1d9e6d5e9a76 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2403,9 +2403,10 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); - kfree_rcu(psl, rcu); } rcu_assign_pointer(pmc->sflist, newpsl); + if (psl) + kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ @@ -2507,11 +2508,13 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); - kfree_rcu(psl, rcu); - } else + } else { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); + } rcu_assign_pointer(pmc->sflist, newpsl); + if (psl) + kfree_rcu(psl, rcu); pmc->sfmode = msf->imsf_fmode; err = 0; done: From a9384a4c1d250cb40cebf50e41459426d160b08e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 29 Apr 2022 09:20:36 -0700 Subject: [PATCH 079/192] mld: respect RCU rules in ip6_mc_source() and ip6_mc_msfilter() Whenever RCU protected list replaces an object, the pointer to the new object needs to be updated _before_ the call to kfree_rcu() or call_rcu() Also ip6_mc_msfilter() needs to update the pointer before releasing the mc_lock mutex. Note that linux-5.13 was supporting kfree_rcu(NULL, rcu), so this fix does not need the conditional test I was forced to use in the equivalent patch for IPv4. Fixes: 882ba1f73c06 ("mld: convert ipv6_mc_socklist->sflist to RCU") Signed-off-by: Eric Dumazet Cc: Taehee Yoo Signed-off-by: David S. Miller --- net/ipv6/mcast.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 909f937befd7..7f695c39d9a8 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -460,10 +460,10 @@ int ip6_mc_source(int add, int omode, struct sock *sk, newpsl->sl_addr[i] = psl->sl_addr[i]; atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); - kfree_rcu(psl, rcu); } + rcu_assign_pointer(pmc->sflist, newpsl); + kfree_rcu(psl, rcu); psl = newpsl; - rcu_assign_pointer(pmc->sflist, psl); } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { @@ -565,12 +565,12 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, psl->sl_count, psl->sl_addr, 0); atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); - kfree_rcu(psl, rcu); } else { ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); } - mutex_unlock(&idev->mc_lock); rcu_assign_pointer(pmc->sflist, newpsl); + mutex_unlock(&idev->mc_lock); + kfree_rcu(psl, rcu); pmc->sfmode = gsf->gf_fmode; err = 0; done: From 2667ed10d9f01e250ba806276740782c89d77fda Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Thu, 28 Apr 2022 11:00:41 -0700 Subject: [PATCH 080/192] mm: Fix PASID use-after-free issue The PASID is being freed too early. It needs to stay around until after device drivers that might be using it have had a chance to clear it out of the hardware. The relevant refcounts are: mmget() /mmput() refcount the mm's address space mmgrab()/mmdrop() refcount the mm itself The PASID is currently tied to the life of the mm's address space and freed in __mmput(). This makes logical sense because the PASID can't be used once the address space is gone. But, this misses an important point: even after the address space is gone, the PASID will still be programmed into a device. Device drivers might, for instance, still need to flush operations that are outstanding and need to use that PASID. They do this at file->release() time. Device drivers call the IOMMU driver to hold a reference on the mm itself and drop it at file->release() time. But, the IOMMU driver holds a reference on the mm itself, not the address space. The address space (and the PASID) is long gone by the time the driver tries to clean up. This is effectively a use-after-free bug on the PASID. To fix this, move the PASID free operation from __mmput() to __mmdrop(). This ensures that the IOMMU driver's existing mmgrab() keeps the PASID allocated until it drops its mm reference. Fixes: 701fac40384f ("iommu/sva: Assign a PASID to mm on PASID allocation and free it on mm exit") Reported-by: Zhangfei Gao Suggested-by: Jean-Philippe Brucker Suggested-by: Jacob Pan Signed-off-by: Fenghua Yu Signed-off-by: Thomas Gleixner Tested-by: Zhangfei Gao Reviewed-by: Jean-Philippe Brucker Link: https://lore.kernel.org/r/20220428180041.806809-1-fenghua.yu@intel.com --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/fork.c b/kernel/fork.c index 9796897560ab..35a3beff140b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -792,6 +792,7 @@ void __mmdrop(struct mm_struct *mm) mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); + mm_pasid_drop(mm); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); @@ -1190,7 +1191,6 @@ static inline void __mmput(struct mm_struct *mm) } if (mm->binfmt) module_put(mm->binfmt->module); - mm_pasid_drop(mm); mmdrop(mm); } From 47f753c1108e287edb3e27fad8a7511a9d55578e Mon Sep 17 00:00:00 2001 From: Tan Tee Min Date: Fri, 29 Apr 2022 19:58:07 +0800 Subject: [PATCH 081/192] net: stmmac: disable Split Header (SPH) for Intel platforms Based on DesignWare Ethernet QoS datasheet, we are seeing the limitation of Split Header (SPH) feature is not supported for Ipv4 fragmented packet. This SPH limitation will cause ping failure when the packets size exceed the MTU size. For example, the issue happens once the basic ping packet size is larger than the configured MTU size and the data is lost inside the fragmented packet, replaced by zeros/corrupted values, and leads to ping fail. So, disable the Split Header for Intel platforms. v2: Add fixes tag in commit message. Fixes: 67afd6d1cfdf("net: stmmac: Add Split Header support and enable it in XGMAC cores") Cc: # 5.10.x Suggested-by: Ong, Boon Leong Signed-off-by: Mohammad Athari Bin Ismail Signed-off-by: Wong Vee Khee Signed-off-by: Tan Tee Min Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 1 + drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- include/linux/stmmac.h | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 63754a9c4ba7..0b0be0898ac5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -454,6 +454,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->has_gmac4 = 1; plat->force_sf_dma_mode = 0; plat->tso_en = 1; + plat->sph_disable = 1; /* Multiplying factor to the clk_eee_i clock time * period to make it closer to 100 ns. This value diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 4a4b3651ab3e..2525a80353b7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -7021,7 +7021,7 @@ int stmmac_dvr_probe(struct device *device, dev_info(priv->device, "TSO feature enabled\n"); } - if (priv->dma_cap.sphen) { + if (priv->dma_cap.sphen && !priv->plat->sph_disable) { ndev->hw_features |= NETIF_F_GRO; priv->sph_cap = true; priv->sph = priv->sph_cap; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 24eea1b05ca2..29917850f079 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -270,5 +270,6 @@ struct plat_stmmacenet_data { int msi_rx_base_vec; int msi_tx_base_vec; bool use_phy_wol; + bool sph_disable; }; #endif From da5c0f119203ad9728920456a0f52a6d850c01cd Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Fri, 29 Apr 2022 20:45:50 +0800 Subject: [PATCH 082/192] nfc: replace improper check device_is_registered() in netlink related functions The device_is_registered() in nfc core is used to check whether nfc device is registered in netlink related functions such as nfc_fw_download(), nfc_dev_up() and so on. Although device_is_registered() is protected by device_lock, there is still a race condition between device_del() and device_is_registered(). The root cause is that kobject_del() in device_del() is not protected by device_lock. (cleanup task) | (netlink task) | nfc_unregister_device | nfc_fw_download device_del | device_lock ... | if (!device_is_registered)//(1) kobject_del//(2) | ... ... | device_unlock The device_is_registered() returns the value of state_in_sysfs and the state_in_sysfs is set to zero in kobject_del(). If we pass check in position (1), then set zero in position (2). As a result, the check in position (1) is useless. This patch uses bool variable instead of device_is_registered() to judge whether the nfc device is registered, which is well synchronized. Fixes: 3e256b8f8dfa ("NFC: add nfc subsystem core") Signed-off-by: Duoming Zhou Signed-off-by: David S. Miller --- net/nfc/core.c | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-) diff --git a/net/nfc/core.c b/net/nfc/core.c index dc7a2404efdf..5b286e1e0a6f 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -38,7 +38,7 @@ int nfc_fw_download(struct nfc_dev *dev, const char *firmware_name) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -94,7 +94,7 @@ int nfc_dev_up(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -142,7 +142,7 @@ int nfc_dev_down(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -207,7 +207,7 @@ int nfc_start_poll(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -246,7 +246,7 @@ int nfc_stop_poll(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -291,7 +291,7 @@ int nfc_dep_link_up(struct nfc_dev *dev, int target_index, u8 comm_mode) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -335,7 +335,7 @@ int nfc_dep_link_down(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -401,7 +401,7 @@ int nfc_activate_target(struct nfc_dev *dev, u32 target_idx, u32 protocol) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -448,7 +448,7 @@ int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx, u8 mode) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -495,7 +495,7 @@ int nfc_data_exchange(struct nfc_dev *dev, u32 target_idx, struct sk_buff *skb, device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; kfree_skb(skb); goto error; @@ -552,7 +552,7 @@ int nfc_enable_se(struct nfc_dev *dev, u32 se_idx) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -601,7 +601,7 @@ int nfc_disable_se(struct nfc_dev *dev, u32 se_idx) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -1134,6 +1134,7 @@ int nfc_register_device(struct nfc_dev *dev) dev->rfkill = NULL; } } + dev->shutting_down = false; device_unlock(&dev->dev); rc = nfc_genl_device_added(dev); @@ -1166,12 +1167,10 @@ void nfc_unregister_device(struct nfc_dev *dev) rfkill_unregister(dev->rfkill); rfkill_destroy(dev->rfkill); } + dev->shutting_down = true; device_unlock(&dev->dev); if (dev->ops->check_presence) { - device_lock(&dev->dev); - dev->shutting_down = true; - device_unlock(&dev->dev); del_timer_sync(&dev->check_pres_timer); cancel_work_sync(&dev->check_pres_work); } From d270453a0d9ec10bb8a802a142fb1b3601a83098 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Fri, 29 Apr 2022 20:45:51 +0800 Subject: [PATCH 083/192] nfc: nfcmrvl: main: reorder destructive operations in nfcmrvl_nci_unregister_dev to avoid bugs There are destructive operations such as nfcmrvl_fw_dnld_abort and gpio_free in nfcmrvl_nci_unregister_dev. The resources such as firmware, gpio and so on could be destructed while the upper layer functions such as nfcmrvl_fw_dnld_start and nfcmrvl_nci_recv_frame is executing, which leads to double-free, use-after-free and null-ptr-deref bugs. There are three situations that could lead to double-free bugs. The first situation is shown below: (Thread 1) | (Thread 2) nfcmrvl_fw_dnld_start | ... | nfcmrvl_nci_unregister_dev release_firmware() | nfcmrvl_fw_dnld_abort kfree(fw) //(1) | fw_dnld_over | release_firmware ... | kfree(fw) //(2) | ... The second situation is shown below: (Thread 1) | (Thread 2) nfcmrvl_fw_dnld_start | ... | mod_timer | (wait a time) | fw_dnld_timeout | nfcmrvl_nci_unregister_dev fw_dnld_over | nfcmrvl_fw_dnld_abort release_firmware | fw_dnld_over kfree(fw) //(1) | release_firmware ... | kfree(fw) //(2) The third situation is shown below: (Thread 1) | (Thread 2) nfcmrvl_nci_recv_frame | if(..->fw_download_in_progress)| nfcmrvl_fw_dnld_recv_frame | queue_work | | fw_dnld_rx_work | nfcmrvl_nci_unregister_dev fw_dnld_over | nfcmrvl_fw_dnld_abort release_firmware | fw_dnld_over kfree(fw) //(1) | release_firmware | kfree(fw) //(2) The firmware struct is deallocated in position (1) and deallocated in position (2) again. The crash trace triggered by POC is like below: BUG: KASAN: double-free or invalid-free in fw_dnld_over Call Trace: kfree fw_dnld_over nfcmrvl_nci_unregister_dev nci_uart_tty_close tty_ldisc_kill tty_ldisc_hangup __tty_hangup.part.0 tty_release ... What's more, there are also use-after-free and null-ptr-deref bugs in nfcmrvl_fw_dnld_start. If we deallocate firmware struct, gpio or set null to the members of priv->fw_dnld in nfcmrvl_nci_unregister_dev, then, we dereference firmware, gpio or the members of priv->fw_dnld in nfcmrvl_fw_dnld_start, the UAF or NPD bugs will happen. This patch reorders destructive operations after nci_unregister_device in order to synchronize between cleanup routine and firmware download routine. The nci_unregister_device is well synchronized. If the device is detaching, the firmware download routine will goto error. If firmware download routine is executing, nci_unregister_device will wait until firmware download routine is finished. Fixes: 3194c6870158 ("NFC: nfcmrvl: add firmware download support") Signed-off-by: Duoming Zhou Signed-off-by: David S. Miller --- drivers/nfc/nfcmrvl/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nfc/nfcmrvl/main.c b/drivers/nfc/nfcmrvl/main.c index 2fcf545012b1..1a5284de4341 100644 --- a/drivers/nfc/nfcmrvl/main.c +++ b/drivers/nfc/nfcmrvl/main.c @@ -183,6 +183,7 @@ void nfcmrvl_nci_unregister_dev(struct nfcmrvl_private *priv) { struct nci_dev *ndev = priv->ndev; + nci_unregister_device(ndev); if (priv->ndev->nfc_dev->fw_download_in_progress) nfcmrvl_fw_dnld_abort(priv); @@ -191,7 +192,6 @@ void nfcmrvl_nci_unregister_dev(struct nfcmrvl_private *priv) if (gpio_is_valid(priv->config.reset_n_io)) gpio_free(priv->config.reset_n_io); - nci_unregister_device(ndev); nci_free_device(ndev); kfree(priv); } From 6b292a04c694573a302686323fe15b1c7e673e5b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 29 Apr 2022 15:54:24 +0200 Subject: [PATCH 084/192] pci_irq_vector() can't be used in atomic context any longer. This conflicts with the usage of this function in nic_mbx_intr_handler(). Cache the Linux interrupt numbers in struct nicpf and use that cache in the interrupt handler to select the mailbox. Fixes: 495c66aca3da ("genirq/msi: Convert to new functions") Reported-by: Ondrej Mosnacek Signed-off-by: Thomas Gleixner Cc: Sunil Goutham Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Paolo Abeni Cc: netdev@vger.kernel.org Cc: stable@vger.kernel.org Link: https://bugzilla.redhat.com/show_bug.cgi?id=2041772 Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nic_main.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index f2f1ce81fd9c..0ec65ec634df 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -59,7 +59,7 @@ struct nicpf { /* MSI-X */ u8 num_vec; - bool irq_allocated[NIC_PF_MSIX_VECTORS]; + unsigned int irq_allocated[NIC_PF_MSIX_VECTORS]; char irq_name[NIC_PF_MSIX_VECTORS][20]; }; @@ -1150,7 +1150,7 @@ static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq) u64 intr; u8 vf; - if (irq == pci_irq_vector(nic->pdev, NIC_PF_INTR_ID_MBOX0)) + if (irq == nic->irq_allocated[NIC_PF_INTR_ID_MBOX0]) mbx = 0; else mbx = 1; @@ -1176,14 +1176,14 @@ static void nic_free_all_interrupts(struct nicpf *nic) for (irq = 0; irq < nic->num_vec; irq++) { if (nic->irq_allocated[irq]) - free_irq(pci_irq_vector(nic->pdev, irq), nic); - nic->irq_allocated[irq] = false; + free_irq(nic->irq_allocated[irq], nic); + nic->irq_allocated[irq] = 0; } } static int nic_register_interrupts(struct nicpf *nic) { - int i, ret; + int i, ret, irq; nic->num_vec = pci_msix_vec_count(nic->pdev); /* Enable MSI-X */ @@ -1201,13 +1201,13 @@ static int nic_register_interrupts(struct nicpf *nic) sprintf(nic->irq_name[i], "NICPF Mbox%d", (i - NIC_PF_INTR_ID_MBOX0)); - ret = request_irq(pci_irq_vector(nic->pdev, i), - nic_mbx_intr_handler, 0, + irq = pci_irq_vector(nic->pdev, i); + ret = request_irq(irq, nic_mbx_intr_handler, 0, nic->irq_name[i], nic); if (ret) goto fail; - nic->irq_allocated[i] = true; + nic->irq_allocated[i] = irq; } /* Enable mailbox interrupt */ From 79396934e289dbc501316c1d1f975bb4c88ae460 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 29 Apr 2022 09:43:03 -0700 Subject: [PATCH 085/192] net: dsa: b53: convert to phylink_pcs Convert B53 to use phylink_pcs for the serdes rather than hooking it into the MAC-layer callbacks. Fixes: 81c1681cbb9f ("net: dsa: b53: mark as non-legacy") Reviewed-by: Florian Fainelli Tested-by: Florian Fainelli Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_common.c | 36 +++------------- drivers/net/dsa/b53/b53_priv.h | 24 ++++++----- drivers/net/dsa/b53/b53_serdes.c | 74 ++++++++++++++++++++++---------- drivers/net/dsa/b53/b53_serdes.h | 9 ++-- drivers/net/dsa/b53/b53_srab.c | 4 +- 5 files changed, 75 insertions(+), 72 deletions(-) diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 77501f9c5915..fbb32aa49b24 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1354,46 +1354,25 @@ static void b53_phylink_get_caps(struct dsa_switch *ds, int port, config->legacy_pre_march2020 = false; } -int b53_phylink_mac_link_state(struct dsa_switch *ds, int port, - struct phylink_link_state *state) +static struct phylink_pcs *b53_phylink_mac_select_pcs(struct dsa_switch *ds, + int port, + phy_interface_t interface) { struct b53_device *dev = ds->priv; - int ret = -EOPNOTSUPP; - if ((phy_interface_mode_is_8023z(state->interface) || - state->interface == PHY_INTERFACE_MODE_SGMII) && - dev->ops->serdes_link_state) - ret = dev->ops->serdes_link_state(dev, port, state); + if (!dev->ops->phylink_mac_select_pcs) + return NULL; - return ret; + return dev->ops->phylink_mac_select_pcs(dev, port, interface); } -EXPORT_SYMBOL(b53_phylink_mac_link_state); void b53_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state) { - struct b53_device *dev = ds->priv; - - if (mode == MLO_AN_PHY || mode == MLO_AN_FIXED) - return; - - if ((phy_interface_mode_is_8023z(state->interface) || - state->interface == PHY_INTERFACE_MODE_SGMII) && - dev->ops->serdes_config) - dev->ops->serdes_config(dev, port, mode, state); } EXPORT_SYMBOL(b53_phylink_mac_config); -void b53_phylink_mac_an_restart(struct dsa_switch *ds, int port) -{ - struct b53_device *dev = ds->priv; - - if (dev->ops->serdes_an_restart) - dev->ops->serdes_an_restart(dev, port); -} -EXPORT_SYMBOL(b53_phylink_mac_an_restart); - void b53_phylink_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface) @@ -2269,9 +2248,8 @@ static const struct dsa_switch_ops b53_switch_ops = { .phy_write = b53_phy_write16, .adjust_link = b53_adjust_link, .phylink_get_caps = b53_phylink_get_caps, - .phylink_mac_link_state = b53_phylink_mac_link_state, + .phylink_mac_select_pcs = b53_phylink_mac_select_pcs, .phylink_mac_config = b53_phylink_mac_config, - .phylink_mac_an_restart = b53_phylink_mac_an_restart, .phylink_mac_link_down = b53_phylink_mac_link_down, .phylink_mac_link_up = b53_phylink_mac_link_up, .port_enable = b53_enable_port, diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 3085b6cc7d40..795cbffd5c2b 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -21,7 +21,7 @@ #include #include -#include +#include #include #include @@ -29,7 +29,6 @@ struct b53_device; struct net_device; -struct phylink_link_state; struct b53_io_ops { int (*read8)(struct b53_device *dev, u8 page, u8 reg, u8 *value); @@ -48,13 +47,10 @@ struct b53_io_ops { void (*irq_disable)(struct b53_device *dev, int port); void (*phylink_get_caps)(struct b53_device *dev, int port, struct phylink_config *config); + struct phylink_pcs *(*phylink_mac_select_pcs)(struct b53_device *dev, + int port, + phy_interface_t interface); u8 (*serdes_map_lane)(struct b53_device *dev, int port); - int (*serdes_link_state)(struct b53_device *dev, int port, - struct phylink_link_state *state); - void (*serdes_config)(struct b53_device *dev, int port, - unsigned int mode, - const struct phylink_link_state *state); - void (*serdes_an_restart)(struct b53_device *dev, int port); void (*serdes_link_set)(struct b53_device *dev, int port, unsigned int mode, phy_interface_t interface, bool link_up); @@ -85,8 +81,15 @@ enum { BCM7278_DEVICE_ID = 0x7278, }; +struct b53_pcs { + struct phylink_pcs pcs; + struct b53_device *dev; + u8 lane; +}; + #define B53_N_PORTS 9 #define B53_N_PORTS_25 6 +#define B53_N_PCS 2 struct b53_port { u16 vlan_ctl_mask; @@ -143,6 +146,8 @@ struct b53_device { bool vlan_enabled; unsigned int num_ports; struct b53_port *ports; + + struct b53_pcs pcs[B53_N_PCS]; }; #define b53_for_each_port(dev, i) \ @@ -336,12 +341,9 @@ int b53_br_flags(struct dsa_switch *ds, int port, struct netlink_ext_ack *extack); int b53_setup_devlink_resources(struct dsa_switch *ds); void b53_port_event(struct dsa_switch *ds, int port); -int b53_phylink_mac_link_state(struct dsa_switch *ds, int port, - struct phylink_link_state *state); void b53_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state); -void b53_phylink_mac_an_restart(struct dsa_switch *ds, int port); void b53_phylink_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface); diff --git a/drivers/net/dsa/b53/b53_serdes.c b/drivers/net/dsa/b53/b53_serdes.c index 555e5b372321..0690210770ff 100644 --- a/drivers/net/dsa/b53/b53_serdes.c +++ b/drivers/net/dsa/b53/b53_serdes.c @@ -17,6 +17,11 @@ #include "b53_serdes.h" #include "b53_regs.h" +static inline struct b53_pcs *pcs_to_b53_pcs(struct phylink_pcs *pcs) +{ + return container_of(pcs, struct b53_pcs, pcs); +} + static void b53_serdes_write_blk(struct b53_device *dev, u8 offset, u16 block, u16 value) { @@ -60,51 +65,47 @@ static u16 b53_serdes_read(struct b53_device *dev, u8 lane, return b53_serdes_read_blk(dev, offset, block); } -void b53_serdes_config(struct b53_device *dev, int port, unsigned int mode, - const struct phylink_link_state *state) +static int b53_serdes_config(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) { - u8 lane = b53_serdes_map_lane(dev, port); + struct b53_device *dev = pcs_to_b53_pcs(pcs)->dev; + u8 lane = pcs_to_b53_pcs(pcs)->lane; u16 reg; - if (lane == B53_INVALID_LANE) - return; - reg = b53_serdes_read(dev, lane, B53_SERDES_DIGITAL_CONTROL(1), SERDES_DIGITAL_BLK); - if (state->interface == PHY_INTERFACE_MODE_1000BASEX) + if (interface == PHY_INTERFACE_MODE_1000BASEX) reg |= FIBER_MODE_1000X; else reg &= ~FIBER_MODE_1000X; b53_serdes_write(dev, lane, B53_SERDES_DIGITAL_CONTROL(1), SERDES_DIGITAL_BLK, reg); + + return 0; } -EXPORT_SYMBOL(b53_serdes_config); -void b53_serdes_an_restart(struct b53_device *dev, int port) +static void b53_serdes_an_restart(struct phylink_pcs *pcs) { - u8 lane = b53_serdes_map_lane(dev, port); + struct b53_device *dev = pcs_to_b53_pcs(pcs)->dev; + u8 lane = pcs_to_b53_pcs(pcs)->lane; u16 reg; - if (lane == B53_INVALID_LANE) - return; - reg = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_BMCR), SERDES_MII_BLK); reg |= BMCR_ANRESTART; b53_serdes_write(dev, lane, B53_SERDES_MII_REG(MII_BMCR), SERDES_MII_BLK, reg); } -EXPORT_SYMBOL(b53_serdes_an_restart); -int b53_serdes_link_state(struct b53_device *dev, int port, - struct phylink_link_state *state) +static void b53_serdes_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) { - u8 lane = b53_serdes_map_lane(dev, port); + struct b53_device *dev = pcs_to_b53_pcs(pcs)->dev; + u8 lane = pcs_to_b53_pcs(pcs)->lane; u16 dig, bmsr; - if (lane == B53_INVALID_LANE) - return 1; - dig = b53_serdes_read(dev, lane, B53_SERDES_DIGITAL_STATUS, SERDES_DIGITAL_BLK); bmsr = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_BMSR), @@ -133,10 +134,7 @@ int b53_serdes_link_state(struct b53_device *dev, int port, state->pause |= MLO_PAUSE_RX; if (dig & PAUSE_RESOLUTION_TX_SIDE) state->pause |= MLO_PAUSE_TX; - - return 0; } -EXPORT_SYMBOL(b53_serdes_link_state); void b53_serdes_link_set(struct b53_device *dev, int port, unsigned int mode, phy_interface_t interface, bool link_up) @@ -158,6 +156,12 @@ void b53_serdes_link_set(struct b53_device *dev, int port, unsigned int mode, } EXPORT_SYMBOL(b53_serdes_link_set); +static const struct phylink_pcs_ops b53_pcs_ops = { + .pcs_get_state = b53_serdes_get_state, + .pcs_config = b53_serdes_config, + .pcs_an_restart = b53_serdes_an_restart, +}; + void b53_serdes_phylink_get_caps(struct b53_device *dev, int port, struct phylink_config *config) { @@ -187,9 +191,28 @@ void b53_serdes_phylink_get_caps(struct b53_device *dev, int port, } EXPORT_SYMBOL(b53_serdes_phylink_get_caps); +struct phylink_pcs *b53_serdes_phylink_mac_select_pcs(struct b53_device *dev, + int port, + phy_interface_t interface) +{ + u8 lane = b53_serdes_map_lane(dev, port); + + if (lane == B53_INVALID_LANE || lane >= B53_N_PCS || + !dev->pcs[lane].dev) + return NULL; + + if (!phy_interface_mode_is_8023z(interface) && + interface != PHY_INTERFACE_MODE_SGMII) + return NULL; + + return &dev->pcs[lane].pcs; +} +EXPORT_SYMBOL(b53_serdes_phylink_mac_select_pcs); + int b53_serdes_init(struct b53_device *dev, int port) { u8 lane = b53_serdes_map_lane(dev, port); + struct b53_pcs *pcs; u16 id0, msb, lsb; if (lane == B53_INVALID_LANE) @@ -212,6 +235,11 @@ int b53_serdes_init(struct b53_device *dev, int port) (id0 >> SERDES_ID0_REV_NUM_SHIFT) & SERDES_ID0_REV_NUM_MASK, (u32)msb << 16 | lsb); + pcs = &dev->pcs[lane]; + pcs->dev = dev; + pcs->lane = lane; + pcs->pcs.ops = &b53_pcs_ops; + return 0; } EXPORT_SYMBOL(b53_serdes_init); diff --git a/drivers/net/dsa/b53/b53_serdes.h b/drivers/net/dsa/b53/b53_serdes.h index f47d5caa7557..ef81f5da5f81 100644 --- a/drivers/net/dsa/b53/b53_serdes.h +++ b/drivers/net/dsa/b53/b53_serdes.h @@ -107,14 +107,11 @@ static inline u8 b53_serdes_map_lane(struct b53_device *dev, int port) return dev->ops->serdes_map_lane(dev, port); } -int b53_serdes_get_link(struct b53_device *dev, int port); -int b53_serdes_link_state(struct b53_device *dev, int port, - struct phylink_link_state *state); -void b53_serdes_config(struct b53_device *dev, int port, unsigned int mode, - const struct phylink_link_state *state); -void b53_serdes_an_restart(struct b53_device *dev, int port); void b53_serdes_link_set(struct b53_device *dev, int port, unsigned int mode, phy_interface_t interface, bool link_up); +struct phylink_pcs *b53_serdes_phylink_mac_select_pcs(struct b53_device *dev, + int port, + phy_interface_t interface); void b53_serdes_phylink_get_caps(struct b53_device *dev, int port, struct phylink_config *config); #if IS_ENABLED(CONFIG_B53_SERDES) diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c index c51b716657db..da0b889880f6 100644 --- a/drivers/net/dsa/b53/b53_srab.c +++ b/drivers/net/dsa/b53/b53_srab.c @@ -491,10 +491,8 @@ static const struct b53_io_ops b53_srab_ops = { .irq_disable = b53_srab_irq_disable, .phylink_get_caps = b53_srab_phylink_get_caps, #if IS_ENABLED(CONFIG_B53_SERDES) + .phylink_mac_select_pcs = b53_serdes_phylink_mac_select_pcs, .serdes_map_lane = b53_srab_serdes_map_lane, - .serdes_link_state = b53_serdes_link_state, - .serdes_config = b53_serdes_config, - .serdes_an_restart = b53_serdes_an_restart, .serdes_link_set = b53_serdes_link_set, #endif }; From e75f88efac05bf4e107e4171d8db6d8c3937252d Mon Sep 17 00:00:00 2001 From: Andrei Lalaev Date: Fri, 15 Apr 2022 10:07:11 +0300 Subject: [PATCH 086/192] gpiolib: of: fix bounds check for 'gpio-reserved-ranges' Gpiolib interprets the elements of "gpio-reserved-ranges" as "start,size" because it clears "size" bits starting from the "start" bit in the according bitmap. So it has to use "greater" instead of "greater or equal" when performs bounds check to make sure that GPIOs are in the available range. Previous implementation skipped ranges that include the last GPIO in the range. I wrote the mail to the maintainers (https://lore.kernel.org/linux-gpio/20220412115554.159435-1-andrei.lalaev@emlid.com/T/#u) of the questioned DTSes (because I couldn't understand how the maintainers interpreted this property), but I haven't received a response. Since the questioned DTSes use "gpio-reserved-ranges = <0 4>" (i.e., the beginning of the range), this patch doesn't affect these DTSes at all. TBH this patch doesn't break any existing DTSes because none of them reserve gpios at the end of range. Fixes: 726cb3ba4969 ("gpiolib: Support 'gpio-reserved-ranges' property") Signed-off-by: Andrei Lalaev Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Cc: stable@vger.kernel.org Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpiolib-of.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index ae1ce319cd78..7e5e51d49d09 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -910,7 +910,7 @@ static void of_gpiochip_init_valid_mask(struct gpio_chip *chip) i, &start); of_property_read_u32_index(np, "gpio-reserved-ranges", i + 1, &count); - if (start >= chip->ngpio || start + count >= chip->ngpio) + if (start >= chip->ngpio || start + count > chip->ngpio) continue; bitmap_clear(chip->valid_mask, start, count); From e5f6e5d554ac274f9c8ba60078103d0425b93c19 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Mon, 11 Apr 2022 09:23:40 +0300 Subject: [PATCH 087/192] gpio: mvebu: drop pwm base assignment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit pwmchip_add() unconditionally assigns the base ID dynamically. Commit f9a8ee8c8bcd1 ("pwm: Always allocate PWM chip base ID dynamically") dropped all base assignment from drivers under drivers/pwm/. It missed this driver. Fix that. Fixes: f9a8ee8c8bcd1 ("pwm: Always allocate PWM chip base ID dynamically") Signed-off-by: Baruch Siach Reviewed-by: Uwe Kleine-König Acked-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-mvebu.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index 4c1f9e1091b7..a2c8dd329b31 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -871,13 +871,6 @@ static int mvebu_pwm_probe(struct platform_device *pdev, mvpwm->chip.dev = dev; mvpwm->chip.ops = &mvebu_pwm_ops; mvpwm->chip.npwm = mvchip->chip.ngpio; - /* - * There may already be some PWM allocated, so we can't force - * mvpwm->chip.base to a fixed point like mvchip->chip.base. - * So, we let pwmchip_add() do the numbering and take the next free - * region. - */ - mvpwm->chip.base = -1; spin_lock_init(&mvpwm->lock); From a196c78b5443fc61af2c0490213b9d125482cbd1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 1 May 2022 21:19:50 -0600 Subject: [PATCH 088/192] io_uring: assign non-fixed early for async work We defer file assignment to ensure that fixed files work with links between a direct accept/open and the links that follow it. But this has the side effect that normal file assignment is then not complete by the time that request submission has been done. For deferred execution, if the file is a regular file, assign it when we do the async prep anyway. Signed-off-by: Jens Axboe --- fs/io_uring.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index e01f595f5b7d..91de361ea9ab 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6947,7 +6947,12 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) static int io_req_prep_async(struct io_kiocb *req) { - if (!io_op_defs[req->opcode].needs_async_setup) + const struct io_op_def *def = &io_op_defs[req->opcode]; + + /* assign early for deferred execution for non-fixed file */ + if (def->needs_file && !(req->flags & REQ_F_FIXED_FILE)) + req->file = io_file_get_normal(req, req->fd); + if (!def->needs_async_setup) return 0; if (WARN_ON_ONCE(req_has_async_data(req))) return -EFAULT; From 7b8943b821bafab492f43aafbd006b57c6b65845 Mon Sep 17 00:00:00 2001 From: Tatyana Nikolova Date: Mon, 25 Apr 2022 13:17:01 -0500 Subject: [PATCH 089/192] RDMA/irdma: Flush iWARP QP if modified to ERR from RTR state When connection establishment fails in iWARP mode, an app can drain the QPs and hang because flush isn't issued when the QP is modified from RTR state to error. Issue a flush in this case using function irdma_cm_disconn(). Update irdma_cm_disconn() to do flush when cm_id is NULL, which is the case when the QP is in RTR state and there is an error in the connection establishment. Fixes: b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs") Link: https://lore.kernel.org/r/20220425181703.1634-2-shiraz.saleem@intel.com Signed-off-by: Tatyana Nikolova Signed-off-by: Shiraz Saleem Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/cm.c | 16 +++++----------- drivers/infiniband/hw/irdma/verbs.c | 4 ++-- 2 files changed, 7 insertions(+), 13 deletions(-) diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c index a98d962e5efb..90b4113e7071 100644 --- a/drivers/infiniband/hw/irdma/cm.c +++ b/drivers/infiniband/hw/irdma/cm.c @@ -3462,12 +3462,6 @@ static void irdma_cm_disconn_true(struct irdma_qp *iwqp) } cm_id = iwqp->cm_id; - /* make sure we havent already closed this connection */ - if (!cm_id) { - spin_unlock_irqrestore(&iwqp->lock, flags); - return; - } - original_hw_tcp_state = iwqp->hw_tcp_state; original_ibqp_state = iwqp->ibqp_state; last_ae = iwqp->last_aeq; @@ -3489,11 +3483,11 @@ static void irdma_cm_disconn_true(struct irdma_qp *iwqp) disconn_status = -ECONNRESET; } - if ((original_hw_tcp_state == IRDMA_TCP_STATE_CLOSED || - original_hw_tcp_state == IRDMA_TCP_STATE_TIME_WAIT || - last_ae == IRDMA_AE_RDMAP_ROE_BAD_LLP_CLOSE || - last_ae == IRDMA_AE_BAD_CLOSE || - last_ae == IRDMA_AE_LLP_CONNECTION_RESET || iwdev->rf->reset)) { + if (original_hw_tcp_state == IRDMA_TCP_STATE_CLOSED || + original_hw_tcp_state == IRDMA_TCP_STATE_TIME_WAIT || + last_ae == IRDMA_AE_RDMAP_ROE_BAD_LLP_CLOSE || + last_ae == IRDMA_AE_BAD_CLOSE || + last_ae == IRDMA_AE_LLP_CONNECTION_RESET || iwdev->rf->reset || !cm_id) { issue_close = 1; iwqp->cm_id = NULL; qp->term_flags = 0; diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 46f475394af5..52f3e88f8569 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -1618,13 +1618,13 @@ int irdma_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask, if (issue_modify_qp && iwqp->ibqp_state > IB_QPS_RTS) { if (dont_wait) { - if (iwqp->cm_id && iwqp->hw_tcp_state) { + if (iwqp->hw_tcp_state) { spin_lock_irqsave(&iwqp->lock, flags); iwqp->hw_tcp_state = IRDMA_TCP_STATE_CLOSED; iwqp->last_aeq = IRDMA_AE_RESET_SENT; spin_unlock_irqrestore(&iwqp->lock, flags); - irdma_cm_disconn(iwqp); } + irdma_cm_disconn(iwqp); } else { int close_timer_started; From 2df6d895907b2f5dfbc558cbff7801bba82cb3cc Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Mon, 25 Apr 2022 13:17:02 -0500 Subject: [PATCH 090/192] RDMA/irdma: Reduce iWARP QP destroy time QP destroy is synchronous and waits for its refcnt to be decremented in irdma_cm_node_free_cb (for iWARP) which fires after the RCU grace period elapses. Applications running a large number of connections are exposed to high wait times on destroy QP for events like SIGABORT. The long pole for this wait time is the firing of the call_rcu callback during a CM node destroy which can be slow. It holds the QP reference count and blocks the destroy QP from completing. call_rcu only needs to make sure that list walkers have a reference to the cm_node object before freeing it and thus need to wait for grace period elapse. The rest of the connection teardown in irdma_cm_node_free_cb is moved out of the grace period wait in irdma_destroy_connection. Also, replace call_rcu with a simple kfree_rcu as it just needs to do a kfree on the cm_node Fixes: 146b9756f14c ("RDMA/irdma: Add connection manager") Link: https://lore.kernel.org/r/20220425181703.1634-3-shiraz.saleem@intel.com Signed-off-by: Shiraz Saleem Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/cm.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c index 90b4113e7071..638bf4a1ed94 100644 --- a/drivers/infiniband/hw/irdma/cm.c +++ b/drivers/infiniband/hw/irdma/cm.c @@ -2308,10 +2308,8 @@ err: return NULL; } -static void irdma_cm_node_free_cb(struct rcu_head *rcu_head) +static void irdma_destroy_connection(struct irdma_cm_node *cm_node) { - struct irdma_cm_node *cm_node = - container_of(rcu_head, struct irdma_cm_node, rcu_head); struct irdma_cm_core *cm_core = cm_node->cm_core; struct irdma_qp *iwqp; struct irdma_cm_info nfo; @@ -2359,7 +2357,6 @@ static void irdma_cm_node_free_cb(struct rcu_head *rcu_head) } cm_core->cm_free_ah(cm_node); - kfree(cm_node); } /** @@ -2387,8 +2384,9 @@ void irdma_rem_ref_cm_node(struct irdma_cm_node *cm_node) spin_unlock_irqrestore(&cm_core->ht_lock, flags); - /* wait for all list walkers to exit their grace period */ - call_rcu(&cm_node->rcu_head, irdma_cm_node_free_cb); + irdma_destroy_connection(cm_node); + + kfree_rcu(cm_node, rcu_head); } /** From 1c9043ae0667a43bd87beeebbdd4bed674713629 Mon Sep 17 00:00:00 2001 From: Mustafa Ismail Date: Mon, 25 Apr 2022 13:17:03 -0500 Subject: [PATCH 091/192] RDMA/irdma: Fix possible crash due to NULL netdev in notifier For some net events in irdma_net_event notifier, the netdev can be NULL which will cause a crash in rdma_vlan_dev_real_dev. Fix this by moving all processing to the NETEVENT_NEIGH_UPDATE case where the netdev is guaranteed to not be NULL. Fixes: 6702bc147448 ("RDMA/irdma: Fix netdev notifications for vlan's") Link: https://lore.kernel.org/r/20220425181703.1634-4-shiraz.saleem@intel.com Signed-off-by: Mustafa Ismail Signed-off-by: Shiraz Saleem Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/utils.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index 346c2c5dabdf..81760415d66c 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -258,18 +258,16 @@ int irdma_net_event(struct notifier_block *notifier, unsigned long event, u32 local_ipaddr[4] = {}; bool ipv4 = true; - real_dev = rdma_vlan_dev_real_dev(netdev); - if (!real_dev) - real_dev = netdev; - - ibdev = ib_device_get_by_netdev(real_dev, RDMA_DRIVER_IRDMA); - if (!ibdev) - return NOTIFY_DONE; - - iwdev = to_iwdev(ibdev); - switch (event) { case NETEVENT_NEIGH_UPDATE: + real_dev = rdma_vlan_dev_real_dev(netdev); + if (!real_dev) + real_dev = netdev; + ibdev = ib_device_get_by_netdev(real_dev, RDMA_DRIVER_IRDMA); + if (!ibdev) + return NOTIFY_DONE; + + iwdev = to_iwdev(ibdev); p = (__be32 *)neigh->primary_key; if (neigh->tbl->family == AF_INET6) { ipv4 = false; @@ -290,13 +288,12 @@ int irdma_net_event(struct notifier_block *notifier, unsigned long event, irdma_manage_arp_cache(iwdev->rf, neigh->ha, local_ipaddr, ipv4, IRDMA_ARP_DELETE); + ib_device_put(ibdev); break; default: break; } - ib_device_put(ibdev); - return NOTIFY_DONE; } From 285d5731a0cb2dd3a12ddf34d67be4e4965e64da Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 26 Apr 2022 10:49:36 +0800 Subject: [PATCH 092/192] Revert "block: release rq qos structures for queue without disk" This reverts commit daaca3522a8e67c46e39ef09c1d542e866f85f3b. Commit daaca3522a8e ("block: release rq qos structures for queue without disk") is only needed for v5.15~v5.17, and isn't needed for v5.18, so revert it. Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20220426024936.3321341-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- block/blk-core.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 937bb6b86331..bc0506772152 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -50,7 +50,6 @@ #include "blk-pm.h" #include "blk-cgroup.h" #include "blk-throttle.h" -#include "blk-rq-qos.h" struct dentry *blk_debugfs_root; @@ -315,9 +314,6 @@ void blk_cleanup_queue(struct request_queue *q) */ blk_freeze_queue(q); - /* cleanup rq qos structures for queue without disk */ - rq_qos_exit(q); - blk_queue_flag_set(QUEUE_FLAG_DEAD, q); blk_sync_queue(q); From b5d1274409d0eec6d826f65d6dafebf9d77a1b99 Mon Sep 17 00:00:00 2001 From: Janis Schoetterl-Glausch Date: Fri, 11 Mar 2022 18:00:40 +0100 Subject: [PATCH 093/192] KVM: s390: Fix lockdep issue in vm memop Issuing a memop on a protected vm does not make sense, neither is the memory readable/writable, nor does it make sense to check storage keys. This is why the ioctl will return -EINVAL when it detects the vm to be protected. However, in order to ensure that the vm cannot become protected during the memop, the kvm->lock would need to be taken for the duration of the ioctl. This is also required because kvm_s390_pv_is_protected asserts that the lock must be held. Instead, don't try to prevent this. If user space enables secure execution concurrently with a memop it must accecpt the possibility of the memop failing. Still check if the vm is currently protected, but without locking and consider it a heuristic. Fixes: ef11c9463ae0 ("KVM: s390: Add vm IOCTL for key checked guest absolute memory access") Signed-off-by: Janis Schoetterl-Glausch Reviewed-by: Janosch Frank Reviewed-by: Claudio Imbrenda Link: https://lore.kernel.org/r/20220322153204.2637400-1-scgl@linux.ibm.com Signed-off-by: Christian Borntraeger Signed-off-by: Heiko Carstens --- arch/s390/kvm/kvm-s390.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index da3dabda1a12..76ad6408cb2c 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2384,7 +2384,16 @@ static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop) return -EINVAL; if (mop->size > MEM_OP_MAX_SIZE) return -E2BIG; - if (kvm_s390_pv_is_protected(kvm)) + /* + * This is technically a heuristic only, if the kvm->lock is not + * taken, it is not guaranteed that the vm is/remains non-protected. + * This is ok from a kernel perspective, wrongdoing is detected + * on the access, -EFAULT is returned and the vm may crash the + * next time it accesses the memory in question. + * There is no sane usecase to do switching and a memop on two + * different CPUs at the same time. + */ + if (kvm_s390_pv_get_handle(kvm)) return -EINVAL; if (mop->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION) { if (access_key_invalid(mop->key)) From b800528b97d0adc3a5ba42d78a8b0d3f07a31f44 Mon Sep 17 00:00:00 2001 From: Shravya Kumbham Date: Mon, 2 May 2022 12:57:49 +0530 Subject: [PATCH 094/192] net: emaclite: Don't advertise 1000BASE-T and do auto negotiation In xemaclite_open() function we are setting the max speed of emaclite to 100Mb using phy_set_max_speed() function so, there is no need to write the advertising registers to stop giga-bit speed and the phy_start() function starts the auto-negotiation so, there is no need to handle it separately using advertising registers. Remove the phy_read and phy_write of advertising registers in xemaclite_open() function. Signed-off-by: Shravya Kumbham Signed-off-by: Radhey Shyam Pandey Reviewed-by: Andrew Lunn Signed-off-by: Paolo Abeni --- drivers/net/ethernet/xilinx/xilinx_emaclite.c | 15 --------------- 1 file changed, 15 deletions(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 57a24f62e353..f7394a5160cf 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -926,8 +926,6 @@ static int xemaclite_open(struct net_device *dev) xemaclite_disable_interrupts(lp); if (lp->phy_node) { - u32 bmcr; - lp->phy_dev = of_phy_connect(lp->ndev, lp->phy_node, xemaclite_adjust_link, 0, PHY_INTERFACE_MODE_MII); @@ -938,19 +936,6 @@ static int xemaclite_open(struct net_device *dev) /* EmacLite doesn't support giga-bit speeds */ phy_set_max_speed(lp->phy_dev, SPEED_100); - - /* Don't advertise 1000BASE-T Full/Half duplex speeds */ - phy_write(lp->phy_dev, MII_CTRL1000, 0); - - /* Advertise only 10 and 100mbps full/half duplex speeds */ - phy_write(lp->phy_dev, MII_ADVERTISE, ADVERTISE_ALL | - ADVERTISE_CSMA); - - /* Restart auto negotiation */ - bmcr = phy_read(lp->phy_dev, MII_BMCR); - bmcr |= (BMCR_ANENABLE | BMCR_ANRESTART); - phy_write(lp->phy_dev, MII_BMCR, bmcr); - phy_start(lp->phy_dev); } From 7a6bc33ab54923d325d9a1747ec9652c4361ebd1 Mon Sep 17 00:00:00 2001 From: Shravya Kumbham Date: Mon, 2 May 2022 12:57:50 +0530 Subject: [PATCH 095/192] net: emaclite: Add error handling for of_address_to_resource() check the return value of of_address_to_resource() and also add missing of_node_put() for np and npp nodes. Fixes: e0a3bc65448c ("net: emaclite: Support multiple phys connected to one MDIO bus") Addresses-Coverity: Event check_return value. Signed-off-by: Shravya Kumbham Signed-off-by: Radhey Shyam Pandey Signed-off-by: Paolo Abeni --- drivers/net/ethernet/xilinx/xilinx_emaclite.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index f7394a5160cf..d770b3ac3f74 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -823,10 +823,10 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg, static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) { struct mii_bus *bus; - int rc; struct resource res; struct device_node *np = of_get_parent(lp->phy_node); struct device_node *npp; + int rc, ret; /* Don't register the MDIO bus if the phy_node or its parent node * can't be found. @@ -836,8 +836,14 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) return -ENODEV; } npp = of_get_parent(np); - - of_address_to_resource(npp, 0, &res); + ret = of_address_to_resource(npp, 0, &res); + of_node_put(npp); + if (ret) { + dev_err(dev, "%s resource error!\n", + dev->of_node->full_name); + of_node_put(np); + return ret; + } if (lp->ndev->mem_start != res.start) { struct phy_device *phydev; phydev = of_phy_find_device(lp->phy_node); @@ -846,6 +852,7 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) "MDIO of the phy is not registered yet\n"); else put_device(&phydev->mdio.dev); + of_node_put(np); return 0; } @@ -858,6 +865,7 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) bus = mdiobus_alloc(); if (!bus) { dev_err(dev, "Failed to allocate mdiobus\n"); + of_node_put(np); return -ENOMEM; } @@ -870,6 +878,7 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) bus->parent = dev; rc = of_mdiobus_register(bus, np); + of_node_put(np); if (rc) { dev_err(dev, "Failed to register mdio bus.\n"); goto err_register; From 3122257c02afd9f199a8fc84ae981e1fc4958532 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 2 May 2022 11:45:07 +0300 Subject: [PATCH 096/192] selftests: mirror_gre_bridge_1q: Avoid changing PVID while interface is operational In emulated environments, the bridge ports enslaved to br1 get a carrier before changing br1's PVID. This means that by the time the PVID is changed, br1 is already operational and configured with an IPv6 link-local address. When the test is run with netdevs registered by mlxsw, changing the PVID is vetoed, as changing the VID associated with an existing L3 interface is forbidden. This restriction is similar to the 8021q driver's restriction of changing the VID of an existing interface. Fix this by taking br1 down and bringing it back up when it is fully configured. With this fix, the test reliably passes on top of both the SW and HW data paths (emulated or not). Fixes: 239e754af854 ("selftests: forwarding: Test mirror-to-gretap w/ UL 802.1q") Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Link: https://lore.kernel.org/r/20220502084507.364774-1-idosch@nvidia.com Signed-off-by: Paolo Abeni --- tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh index a3402cd8d5b6..9ff22f28032d 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh @@ -61,9 +61,12 @@ setup_prepare() vrf_prepare mirror_gre_topo_create + # Avoid changing br1's PVID while it is operational as a L3 interface. + ip link set dev br1 down ip link set dev $swp3 master br1 bridge vlan add dev br1 vid 555 pvid untagged self + ip link set dev br1 up ip address add dev br1 192.0.2.129/28 ip address add dev br1 2001:db8:2::1/64 From 97926d5a847ca1758ad8702ce591e3b05a701e0d Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 2 May 2022 11:46:37 +0200 Subject: [PATCH 097/192] selftests/net: so_txtime: fix parsing of start time stamp on 32 bit systems This patch fixes the parsing of the cmd line supplied start time on 32 bit systems. A "long" on 32 bit systems is only 32 bit wide and cannot hold a timestamp in nano second resolution. Fixes: 040806343bb4 ("selftests/net: so_txtime multi-host support") Cc: Carlos Llamas Cc: Willem de Bruijn Signed-off-by: Marc Kleine-Budde Acked-by: Willem de Bruijn Reviewed-by: Carlos Llamas Link: https://lore.kernel.org/r/20220502094638.1921702-2-mkl@pengutronix.de Signed-off-by: Paolo Abeni --- tools/testing/selftests/net/so_txtime.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index 59067f64b775..103f6bf28e35 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -475,7 +475,7 @@ static void parse_opts(int argc, char **argv) cfg_rx = true; break; case 't': - cfg_start_time_ns = strtol(optarg, NULL, 0); + cfg_start_time_ns = strtoll(optarg, NULL, 0); break; case 'm': cfg_mark = strtol(optarg, NULL, 0); From f5c2174a3775491e890ce285df52f5715fbef875 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 2 May 2022 11:46:38 +0200 Subject: [PATCH 098/192] selftests/net: so_txtime: usage(): fix documentation of default clock The program uses CLOCK_TAI as default clock since it was added to the Linux repo. In commit: | 040806343bb4 ("selftests/net: so_txtime multi-host support") a help text stating the wrong default clock was added. This patch fixes the help text. Fixes: 040806343bb4 ("selftests/net: so_txtime multi-host support") Cc: Carlos Llamas Cc: Willem de Bruijn Signed-off-by: Marc Kleine-Budde Acked-by: Willem de Bruijn Reviewed-by: Carlos Llamas Link: https://lore.kernel.org/r/20220502094638.1921702-3-mkl@pengutronix.de Signed-off-by: Paolo Abeni --- tools/testing/selftests/net/so_txtime.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index 103f6bf28e35..2672ac0b6d1f 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -421,7 +421,7 @@ static void usage(const char *progname) "Options:\n" " -4 only IPv4\n" " -6 only IPv6\n" - " -c monotonic (default) or tai\n" + " -c monotonic or tai (default)\n" " -D destination IP address (server)\n" " -S source IP address (client)\n" " -r run rx mode\n" From 706c9c55e5a32800605eb6a864ef6e1ca0c6c179 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Sat, 23 Apr 2022 03:47:41 +0000 Subject: [PATCH 099/192] KVM: x86/mmu: Don't treat fully writable SPTEs as volatile (modulo A/D) Don't treat SPTEs that are truly writable, i.e. writable in hardware, as being volatile (unless they're volatile for other reasons, e.g. A/D bits). KVM _sets_ the WRITABLE bit out of mmu_lock, but never _clears_ the bit out of mmu_lock, so if the WRITABLE bit is set, it cannot magically get cleared just because the SPTE is MMU-writable. Rename the wrapper of MMU-writable to be more literal, the previous name of spte_can_locklessly_be_made_writable() is wrong and misleading. Fixes: c7ba5b48cc8d ("KVM: MMU: fast path of handling guest page fault") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20220423034752.1161007-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 17 +++++++++-------- arch/x86/kvm/mmu/spte.h | 2 +- 2 files changed, 10 insertions(+), 9 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 64a2a7e2be90..48dcb6a782f4 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -484,13 +484,15 @@ static bool spte_has_volatile_bits(u64 spte) * also, it can help us to get a stable is_writable_pte() * to ensure tlb flush is not missed. */ - if (spte_can_locklessly_be_made_writable(spte) || - is_access_track_spte(spte)) + if (!is_writable_pte(spte) && is_mmu_writable_spte(spte)) + return true; + + if (is_access_track_spte(spte)) return true; if (spte_ad_enabled(spte)) { - if ((spte & shadow_accessed_mask) == 0 || - (is_writable_pte(spte) && (spte & shadow_dirty_mask) == 0)) + if (!(spte & shadow_accessed_mask) || + (is_writable_pte(spte) && !(spte & shadow_dirty_mask))) return true; } @@ -557,7 +559,7 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) * we always atomically update it, see the comments in * spte_has_volatile_bits(). */ - if (spte_can_locklessly_be_made_writable(old_spte) && + if (is_mmu_writable_spte(old_spte) && !is_writable_pte(new_spte)) flush = true; @@ -1187,7 +1189,7 @@ static bool spte_write_protect(u64 *sptep, bool pt_protect) u64 spte = *sptep; if (!is_writable_pte(spte) && - !(pt_protect && spte_can_locklessly_be_made_writable(spte))) + !(pt_protect && is_mmu_writable_spte(spte))) return false; rmap_printk("spte %p %llx\n", sptep, *sptep); @@ -3196,8 +3198,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) * be removed in the fast path only if the SPTE was * write-protected for dirty-logging or access tracking. */ - if (fault->write && - spte_can_locklessly_be_made_writable(spte)) { + if (fault->write && is_mmu_writable_spte(spte)) { new_spte |= PT_WRITABLE_MASK; /* diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index e4abeb5df1b1..c571784cb567 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -390,7 +390,7 @@ static inline void check_spte_writable_invariants(u64 spte) "kvm: Writable SPTE is not MMU-writable: %llx", spte); } -static inline bool spte_can_locklessly_be_made_writable(u64 spte) +static inline bool is_mmu_writable_spte(u64 spte) { return spte & shadow_mmu_writable_mask; } From 54eb3ef56f36827aad90915df33387d4c2b5df5a Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Sat, 23 Apr 2022 03:47:42 +0000 Subject: [PATCH 100/192] KVM: x86/mmu: Move shadow-present check out of spte_has_volatile_bits() Move the is_shadow_present_pte() check out of spte_has_volatile_bits() and into its callers. Well, caller, since only one of its two callers doesn't already do the shadow-present check. Opportunistically move the helper to spte.c/h so that it can be used by the TDP MMU, which is also the primary motivation for the shadow-present change. Unlike the legacy MMU, the TDP MMU uses a single path for clear leaf and non-leaf SPTEs, and to avoid unnecessary atomic updates, the TDP MMU will need to check is_last_spte() prior to calling spte_has_volatile_bits(), and calling is_last_spte() without first calling is_shadow_present_spte() is at best odd, and at worst a violation of KVM's loosely defines SPTE rules. Note, mmu_spte_clear_track_bits() could likely skip the write entirely for SPTEs that are not shadow-present. Leave that cleanup for a future patch to avoid introducing a functional change, and because the shadow-present check can likely be moved further up the stack, e.g. drop_large_spte() appears to be the only path that doesn't already explicitly check for a shadow-present SPTE. No functional change intended. Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Message-Id: <20220423034752.1161007-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 29 ++--------------------------- arch/x86/kvm/mmu/spte.c | 28 ++++++++++++++++++++++++++++ arch/x86/kvm/mmu/spte.h | 2 ++ 3 files changed, 32 insertions(+), 27 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 48dcb6a782f4..311e4e1d7870 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -473,32 +473,6 @@ retry: } #endif -static bool spte_has_volatile_bits(u64 spte) -{ - if (!is_shadow_present_pte(spte)) - return false; - - /* - * Always atomically update spte if it can be updated - * out of mmu-lock, it can ensure dirty bit is not lost, - * also, it can help us to get a stable is_writable_pte() - * to ensure tlb flush is not missed. - */ - if (!is_writable_pte(spte) && is_mmu_writable_spte(spte)) - return true; - - if (is_access_track_spte(spte)) - return true; - - if (spte_ad_enabled(spte)) { - if (!(spte & shadow_accessed_mask) || - (is_writable_pte(spte) && !(spte & shadow_dirty_mask))) - return true; - } - - return false; -} - /* Rules for using mmu_spte_set: * Set the sptep from nonpresent to present. * Note: the sptep being assigned *must* be either not present @@ -593,7 +567,8 @@ static int mmu_spte_clear_track_bits(struct kvm *kvm, u64 *sptep) u64 old_spte = *sptep; int level = sptep_to_sp(sptep)->role.level; - if (!spte_has_volatile_bits(old_spte)) + if (!is_shadow_present_pte(old_spte) || + !spte_has_volatile_bits(old_spte)) __update_clear_spte_fast(sptep, 0ull); else old_spte = __update_clear_spte_slow(sptep, 0ull); diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 4739b53c9734..e5c0b6db6f2c 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -90,6 +90,34 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) E820_TYPE_RAM); } +/* + * Returns true if the SPTE has bits that may be set without holding mmu_lock. + * The caller is responsible for checking if the SPTE is shadow-present, and + * for determining whether or not the caller cares about non-leaf SPTEs. + */ +bool spte_has_volatile_bits(u64 spte) +{ + /* + * Always atomically update spte if it can be updated + * out of mmu-lock, it can ensure dirty bit is not lost, + * also, it can help us to get a stable is_writable_pte() + * to ensure tlb flush is not missed. + */ + if (!is_writable_pte(spte) && is_mmu_writable_spte(spte)) + return true; + + if (is_access_track_spte(spte)) + return true; + + if (spte_ad_enabled(spte)) { + if (!(spte & shadow_accessed_mask) || + (is_writable_pte(spte) && !(spte & shadow_dirty_mask))) + return true; + } + + return false; +} + bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index c571784cb567..80ab0f5cff01 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -404,6 +404,8 @@ static inline u64 get_mmio_spte_generation(u64 spte) return gen; } +bool spte_has_volatile_bits(u64 spte); + bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, From ba3a6120a4e7efc13d19fe43eb6c5caf1da05b72 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Sat, 23 Apr 2022 03:47:43 +0000 Subject: [PATCH 101/192] KVM: x86/mmu: Use atomic XCHG to write TDP MMU SPTEs with volatile bits Use an atomic XCHG to write TDP MMU SPTEs that have volatile bits, even if mmu_lock is held for write, as volatile SPTEs can be written by other tasks/vCPUs outside of mmu_lock. If a vCPU uses the to-be-modified SPTE to write a page, the CPU can cache the translation as WRITABLE in the TLB despite it being seen by KVM as !WRITABLE, and/or KVM can clobber the Accessed/Dirty bits and not properly tag the backing page. Exempt non-leaf SPTEs from atomic updates as KVM itself doesn't modify non-leaf SPTEs without holding mmu_lock, they do not have Dirty bits, and KVM doesn't consume the Accessed bit of non-leaf SPTEs. Dropping the Dirty and/or Writable bits is most problematic for dirty logging, as doing so can result in a missed TLB flush and eventually a missed dirty page. In the unlikely event that the only dirty page(s) is a clobbered SPTE, clear_dirty_gfn_range() will see the SPTE as not dirty (based on the Dirty or Writable bit depending on the method) and so not update the SPTE and ultimately not flush. If the SPTE is cached in the TLB as writable before it is clobbered, the guest can continue writing the associated page without ever taking a write-protect fault. For most (all?) file back memory, dropping the Dirty bit is a non-issue. The primary MMU write-protects its PTEs on writeback, i.e. KVM's dirty bit is effectively ignored because the primary MMU will mark that page dirty when the write-protection is lifted, e.g. when KVM faults the page back in for write. The Accessed bit is a complete non-issue. Aside from being unused for non-leaf SPTEs, KVM doesn't do a TLB flush when aging SPTEs, i.e. the Accessed bit may be dropped anyways. Lastly, the Writable bit is also problematic as an extension of the Dirty bit, as KVM (correctly) treats the Dirty bit as volatile iff the SPTE is !DIRTY && WRITABLE. If KVM fixes an MMU-writable, but !WRITABLE, SPTE out of mmu_lock, then it can allow the CPU to set the Dirty bit despite the SPTE being !WRITABLE when it is checked by KVM. But that all depends on the Dirty bit being problematic in the first place. Fixes: 2f2fad0897cb ("kvm: x86/mmu: Add functions to handle changed TDP SPTEs") Cc: stable@vger.kernel.org Cc: Ben Gardon Cc: David Matlack Cc: Venkatesh Srinivas Signed-off-by: Sean Christopherson Message-Id: <20220423034752.1161007-4-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_iter.h | 34 ++++++++++++++- arch/x86/kvm/mmu/tdp_mmu.c | 82 ++++++++++++++++++++++++------------- 2 files changed, 85 insertions(+), 31 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index b1eaf6ec0e0b..f0af385c56e0 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -6,6 +6,7 @@ #include #include "mmu.h" +#include "spte.h" /* * TDP MMU SPTEs are RCU protected to allow paging structures (non-leaf SPTEs) @@ -17,9 +18,38 @@ static inline u64 kvm_tdp_mmu_read_spte(tdp_ptep_t sptep) { return READ_ONCE(*rcu_dereference(sptep)); } -static inline void kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 val) + +static inline u64 kvm_tdp_mmu_write_spte_atomic(tdp_ptep_t sptep, u64 new_spte) { - WRITE_ONCE(*rcu_dereference(sptep), val); + return xchg(rcu_dereference(sptep), new_spte); +} + +static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte) +{ + WRITE_ONCE(*rcu_dereference(sptep), new_spte); +} + +static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte, + u64 new_spte, int level) +{ + /* + * Atomically write the SPTE if it is a shadow-present, leaf SPTE with + * volatile bits, i.e. has bits that can be set outside of mmu_lock. + * The Writable bit can be set by KVM's fast page fault handler, and + * Accessed and Dirty bits can be set by the CPU. + * + * Note, non-leaf SPTEs do have Accessed bits and those bits are + * technically volatile, but KVM doesn't consume the Accessed bit of + * non-leaf SPTEs, i.e. KVM doesn't care if it clobbers the bit. This + * logic needs to be reassessed if KVM were to use non-leaf Accessed + * bits, e.g. to skip stepping down into child SPTEs when aging SPTEs. + */ + if (is_shadow_present_pte(old_spte) && is_last_spte(old_spte, level) && + spte_has_volatile_bits(old_spte)) + return kvm_tdp_mmu_write_spte_atomic(sptep, new_spte); + + __kvm_tdp_mmu_write_spte(sptep, new_spte); + return old_spte; } /* diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index edc68538819b..922b06bf4b94 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -426,9 +426,9 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) tdp_mmu_unlink_sp(kvm, sp, shared); for (i = 0; i < PT64_ENT_PER_PAGE; i++) { - u64 *sptep = rcu_dereference(pt) + i; + tdp_ptep_t sptep = pt + i; gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level); - u64 old_child_spte; + u64 old_spte; if (shared) { /* @@ -440,8 +440,8 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) * value to the removed SPTE value. */ for (;;) { - old_child_spte = xchg(sptep, REMOVED_SPTE); - if (!is_removed_spte(old_child_spte)) + old_spte = kvm_tdp_mmu_write_spte_atomic(sptep, REMOVED_SPTE); + if (!is_removed_spte(old_spte)) break; cpu_relax(); } @@ -455,23 +455,43 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) * are guarded by the memslots generation, not by being * unreachable. */ - old_child_spte = READ_ONCE(*sptep); - if (!is_shadow_present_pte(old_child_spte)) + old_spte = kvm_tdp_mmu_read_spte(sptep); + if (!is_shadow_present_pte(old_spte)) continue; /* - * Marking the SPTE as a removed SPTE is not - * strictly necessary here as the MMU lock will - * stop other threads from concurrently modifying - * this SPTE. Using the removed SPTE value keeps - * the two branches consistent and simplifies - * the function. + * Use the common helper instead of a raw WRITE_ONCE as + * the SPTE needs to be updated atomically if it can be + * modified by a different vCPU outside of mmu_lock. + * Even though the parent SPTE is !PRESENT, the TLB + * hasn't yet been flushed, and both Intel and AMD + * document that A/D assists can use upper-level PxE + * entries that are cached in the TLB, i.e. the CPU can + * still access the page and mark it dirty. + * + * No retry is needed in the atomic update path as the + * sole concern is dropping a Dirty bit, i.e. no other + * task can zap/remove the SPTE as mmu_lock is held for + * write. Marking the SPTE as a removed SPTE is not + * strictly necessary for the same reason, but using + * the remove SPTE value keeps the shared/exclusive + * paths consistent and allows the handle_changed_spte() + * call below to hardcode the new value to REMOVED_SPTE. + * + * Note, even though dropping a Dirty bit is the only + * scenario where a non-atomic update could result in a + * functional bug, simply checking the Dirty bit isn't + * sufficient as a fast page fault could read the upper + * level SPTE before it is zapped, and then make this + * target SPTE writable, resume the guest, and set the + * Dirty bit between reading the SPTE above and writing + * it here. */ - WRITE_ONCE(*sptep, REMOVED_SPTE); + old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, + REMOVED_SPTE, level); } handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn, - old_child_spte, REMOVED_SPTE, level, - shared); + old_spte, REMOVED_SPTE, level, shared); } call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); @@ -667,14 +687,13 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, KVM_PAGES_PER_HPAGE(iter->level)); /* - * No other thread can overwrite the removed SPTE as they - * must either wait on the MMU lock or use - * tdp_mmu_set_spte_atomic which will not overwrite the - * special removed SPTE value. No bookkeeping is needed - * here since the SPTE is going from non-present - * to non-present. + * No other thread can overwrite the removed SPTE as they must either + * wait on the MMU lock or use tdp_mmu_set_spte_atomic() which will not + * overwrite the special removed SPTE value. No bookkeeping is needed + * here since the SPTE is going from non-present to non-present. Use + * the raw write helper to avoid an unnecessary check on volatile bits. */ - kvm_tdp_mmu_write_spte(iter->sptep, 0); + __kvm_tdp_mmu_write_spte(iter->sptep, 0); return 0; } @@ -699,10 +718,13 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, * unless performing certain dirty logging operations. * Leaving record_dirty_log unset in that case prevents page * writes from being double counted. + * + * Returns the old SPTE value, which _may_ be different than @old_spte if the + * SPTE had voldatile bits. */ -static void __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, - u64 old_spte, u64 new_spte, gfn_t gfn, int level, - bool record_acc_track, bool record_dirty_log) +static u64 __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, + u64 old_spte, u64 new_spte, gfn_t gfn, int level, + bool record_acc_track, bool record_dirty_log) { lockdep_assert_held_write(&kvm->mmu_lock); @@ -715,7 +737,7 @@ static void __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, */ WARN_ON(is_removed_spte(old_spte) || is_removed_spte(new_spte)); - kvm_tdp_mmu_write_spte(sptep, new_spte); + old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level); __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false); @@ -724,6 +746,7 @@ static void __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, if (record_dirty_log) handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte, new_spte, level); + return old_spte; } static inline void _tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, @@ -732,9 +755,10 @@ static inline void _tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, { WARN_ON_ONCE(iter->yielded); - __tdp_mmu_set_spte(kvm, iter->as_id, iter->sptep, iter->old_spte, - new_spte, iter->gfn, iter->level, - record_acc_track, record_dirty_log); + iter->old_spte = __tdp_mmu_set_spte(kvm, iter->as_id, iter->sptep, + iter->old_spte, new_spte, + iter->gfn, iter->level, + record_acc_track, record_dirty_log); } static inline void tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, From 3a58f13a881ed351198ffab4cf9953cf19d2ab3a Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 2 May 2022 10:40:18 +0900 Subject: [PATCH 102/192] net: rds: acquire refcount on TCP sockets syzbot is reporting use-after-free read in tcp_retransmit_timer() [1], for TCP socket used by RDS is accessing sock_net() without acquiring a refcount on net namespace. Since TCP's retransmission can happen after a process which created net namespace terminated, we need to explicitly acquire a refcount. Link: https://syzkaller.appspot.com/bug?extid=694120e1002c117747ed [1] Reported-by: syzbot Fixes: 26abe14379f8e2fa ("net: Modify sk_alloc to not reference count the netns of kernel sockets.") Fixes: 8a68173691f03661 ("net: sk_clone_lock() should only do get_net() if the parent is not a kernel socket") Signed-off-by: Tetsuo Handa Tested-by: syzbot Link: https://lore.kernel.org/r/a5fb1fc4-2284-3359-f6a0-e4e390239d7b@I-love.SAKURA.ne.jp Signed-off-by: Paolo Abeni --- net/rds/tcp.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 5327d130c4b5..2f638f8b7b1e 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -495,6 +495,14 @@ void rds_tcp_tune(struct socket *sock) tcp_sock_set_nodelay(sock->sk); lock_sock(sk); + /* TCP timer functions might access net namespace even after + * a process which created this net namespace terminated. + */ + if (!sk->sk_net_refcnt) { + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); + } if (rtn->sndbuf_size > 0) { sk->sk_sndbuf = rtn->sndbuf_size; sk->sk_userlocks |= SOCK_SNDBUF_LOCK; From 5eb849322d7f7ae9d5c587c7bc3b4f7c6872cd2f Mon Sep 17 00:00:00 2001 From: Kyle Huey Date: Mon, 2 May 2022 22:01:36 -0700 Subject: [PATCH 103/192] KVM: x86/svm: Account for family 17h event renumberings in amd_pmc_perf_hw_id Zen renumbered some of the performance counters that correspond to the well known events in perf_hw_id. This code in KVM was never updated for that, so guest that attempt to use counters on Zen that correspond to the pre-Zen perf_hw_id values will silently receive the wrong values. This has been observed in the wild with rr[0] when running in Zen 3 guests. rr uses the retired conditional branch counter 00d1 which is incorrectly recognized by KVM as PERF_COUNT_HW_STALLED_CYCLES_BACKEND. [0] https://rr-project.org/ Signed-off-by: Kyle Huey Message-Id: <20220503050136.86298-1-khuey@kylehuey.com> Cc: stable@vger.kernel.org [Check guest family, not host. - Paolo] Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/pmu.c | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 24eb935b6f85..311cbaa0c3dd 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -45,6 +45,22 @@ static struct kvm_event_hw_type_mapping amd_event_mapping[] = { [7] = { 0xd1, 0x00, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, }; +/* duplicated from amd_f17h_perfmon_event_map. */ +static struct kvm_event_hw_type_mapping amd_f17h_event_mapping[] = { + [0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x60, 0xff, PERF_COUNT_HW_CACHE_REFERENCES }, + [3] = { 0x64, 0x09, PERF_COUNT_HW_CACHE_MISSES }, + [4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [6] = { 0x87, 0x02, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + [7] = { 0x87, 0x01, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, +}; + +/* amd_pmc_perf_hw_id depends on these being the same size */ +static_assert(ARRAY_SIZE(amd_event_mapping) == + ARRAY_SIZE(amd_f17h_event_mapping)); + static unsigned int get_msr_base(struct kvm_pmu *pmu, enum pmu_type type) { struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); @@ -140,6 +156,7 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc) { + struct kvm_event_hw_type_mapping *event_mapping; u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT; u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; int i; @@ -148,15 +165,20 @@ static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc) if (WARN_ON(pmc_is_fixed(pmc))) return PERF_COUNT_HW_MAX; + if (guest_cpuid_family(pmc->vcpu) >= 0x17) + event_mapping = amd_f17h_event_mapping; + else + event_mapping = amd_event_mapping; + for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++) - if (amd_event_mapping[i].eventsel == event_select - && amd_event_mapping[i].unit_mask == unit_mask) + if (event_mapping[i].eventsel == event_select + && event_mapping[i].unit_mask == unit_mask) break; if (i == ARRAY_SIZE(amd_event_mapping)) return PERF_COUNT_HW_MAX; - return amd_event_mapping[i].event_type; + return event_mapping[i].event_type; } /* check if a PMC is enabled by comparing it against global_ctrl bits. Because From 5a1bde46f98b893cda6122b00e94c0c40a6ead3c Mon Sep 17 00:00:00 2001 From: Sandipan Das Date: Wed, 27 Apr 2022 17:01:49 +0530 Subject: [PATCH 104/192] kvm: x86/cpuid: Only provide CPUID leaf 0xA if host has architectural PMU On some x86 processors, CPUID leaf 0xA provides information on Architectural Performance Monitoring features. It advertises a PMU version which Qemu uses to determine the availability of additional MSRs to manage the PMCs. Upon receiving a KVM_GET_SUPPORTED_CPUID ioctl request for the same, the kernel constructs return values based on the x86_pmu_capability irrespective of the vendor. This leaf and the additional MSRs are not supported on AMD and Hygon processors. If AMD PerfMonV2 is detected, the PMU version is set to 2 and guest startup breaks because of an attempt to access a non-existent MSR. Return zeros to avoid this. Fixes: a6c06ed1a60a ("KVM: Expose the architectural performance monitoring CPUID leaf") Reported-by: Vasant Hegde Signed-off-by: Sandipan Das Message-Id: <3fef83d9c2b2f7516e8ff50d60851f29a4bcb716.1651058600.git.sandipan.das@amd.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index b24ca7f4ed7c..732724ea5b10 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -887,6 +887,11 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) union cpuid10_eax eax; union cpuid10_edx edx; + if (!static_cpu_has(X86_FEATURE_ARCH_PERFMON)) { + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + perf_get_x86_pmu_capability(&cap); /* From a06afe8383080c630a7a528b8382fc6bb4925b61 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Fri, 29 Apr 2022 17:15:26 +0200 Subject: [PATCH 105/192] KVM: s390: vsie/gmap: reduce gmap_rmap overhead there are cases that trigger a 2nd shadow event for the same vmaddr/raddr combination. (prefix changes, reboots, some known races) This will increase memory usages and it will result in long latencies when cleaning up, e.g. on shutdown. To avoid cases with a list that has hundreds of identical raddrs we check existing entries at insert time. As this measurably reduces the list length this will be faster than traversing the list at shutdown time. In the long run several places will be optimized to create less entries and a shrinker might be necessary. Fixes: 4be130a08420 ("s390/mm: add shadow gmap support") Signed-off-by: Christian Borntraeger Acked-by: David Hildenbrand Link: https://lore.kernel.org/r/20220429151526.1560-1-borntraeger@linux.ibm.com Signed-off-by: Heiko Carstens --- arch/s390/mm/gmap.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index af03cacf34ec..1ac73917a8d3 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -1183,6 +1183,7 @@ EXPORT_SYMBOL_GPL(gmap_read_table); static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr, struct gmap_rmap *rmap) { + struct gmap_rmap *temp; void __rcu **slot; BUG_ON(!gmap_is_shadow(sg)); @@ -1190,6 +1191,12 @@ static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr, if (slot) { rmap->next = radix_tree_deref_slot_protected(slot, &sg->guest_table_lock); + for (temp = rmap->next; temp; temp = temp->next) { + if (temp->raddr == rmap->raddr) { + kfree(rmap); + return; + } + } radix_tree_replace_slot(&sg->host_to_rmap, slot, rmap); } else { rmap->next = NULL; From aafa025c76dcc7d1a8c8f0bdefcbe4eb480b2f6a Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Mon, 2 May 2022 15:50:14 +0200 Subject: [PATCH 106/192] fbdev: Make fb_release() return -ENODEV if fbdev was unregistered A reference to the framebuffer device struct fb_info is stored in the file private data, but this reference could no longer be valid and must not be accessed directly. Instead, the file_fb_info() accessor function must be used since it does sanity checking to make sure that the fb_info is valid. This can happen for example if the registered framebuffer device is for a driver that just uses a framebuffer provided by the system firmware. In that case, the fbdev core would unregister the framebuffer device when a real video driver is probed and ask to remove conflicting framebuffers. The bug has been present for a long time but commit 27599aacbaef ("fbdev: Hot-unplug firmware fb devices on forced removal") unmasked it since the fbdev core started unregistering the framebuffers' devices associated. Fixes: 27599aacbaef ("fbdev: Hot-unplug firmware fb devices on forced removal") Reported-by: Maxime Ripard Reported-by: Junxiao Chang Signed-off-by: Javier Martinez Canillas Reviewed-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20220502135014.377945-1-javierm@redhat.com --- drivers/video/fbdev/core/fbmem.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index a6bb0e438216..97eb0dee411c 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1434,7 +1434,10 @@ fb_release(struct inode *inode, struct file *file) __acquires(&info->lock) __releases(&info->lock) { - struct fb_info * const info = file->private_data; + struct fb_info * const info = file_fb_info(file); + + if (!info) + return -ENODEV; lock_fb_info(info); if (info->fbops->fb_release) From 2069624dac19d62c558bb6468fe03678553ab01d Mon Sep 17 00:00:00 2001 From: Matthew Hagan Date: Mon, 2 May 2022 23:33:15 +0100 Subject: [PATCH 107/192] net: sfp: Add tx-fault workaround for Huawei MA5671A SFP ONT As noted elsewhere, various GPON SFP modules exhibit non-standard TX-fault behaviour. In the tested case, the Huawei MA5671A, when used in combination with a Marvell mv88e6085 switch, was found to persistently assert TX-fault, resulting in the module being disabled. This patch adds a quirk to ignore the SFP_F_TX_FAULT state, allowing the module to function. Change from v1: removal of erroneous return statment (Andrew Lunn) Signed-off-by: Matthew Hagan Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20220502223315.1973376-1-mnhagan88@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/sfp.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 4dfb79807823..9a5d5a10560f 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -250,6 +250,7 @@ struct sfp { struct sfp_eeprom_id id; unsigned int module_power_mW; unsigned int module_t_start_up; + bool tx_fault_ignore; #if IS_ENABLED(CONFIG_HWMON) struct sfp_diag diag; @@ -1956,6 +1957,12 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report) else sfp->module_t_start_up = T_START_UP; + if (!memcmp(id.base.vendor_name, "HUAWEI ", 16) && + !memcmp(id.base.vendor_pn, "MA5671A ", 16)) + sfp->tx_fault_ignore = true; + else + sfp->tx_fault_ignore = false; + return 0; } @@ -2409,7 +2416,10 @@ static void sfp_check_state(struct sfp *sfp) mutex_lock(&sfp->st_mutex); state = sfp_get_state(sfp); changed = state ^ sfp->state; - changed &= SFP_F_PRESENT | SFP_F_LOS | SFP_F_TX_FAULT; + if (sfp->tx_fault_ignore) + changed &= SFP_F_PRESENT | SFP_F_LOS; + else + changed &= SFP_F_PRESENT | SFP_F_LOS | SFP_F_TX_FAULT; for (i = 0; i < GPIO_MAX; i++) if (changed & BIT(i)) From 5ef9b803a4af0f5e42012176889b40bb2a978b18 Mon Sep 17 00:00:00 2001 From: Sergey Shtylyov Date: Mon, 2 May 2022 23:14:09 +0300 Subject: [PATCH 108/192] smsc911x: allow using IRQ0 The AlphaProject AP-SH4A-3A/AP-SH4AD-0A SH boards use IRQ0 for their SMSC LAN911x Ethernet chip, so the networking on them must have been broken by commit 965b2aa78fbc ("net/smsc911x: fix irq resource allocation failure") which filtered out 0 as well as the negative error codes -- it was kinda correct at the time, as platform_get_irq() could return 0 on of_irq_get() failure and on the actual 0 in an IRQ resource. This issue was fixed by me (back in 2016!), so we should be able to fix this driver to allow IRQ0 usage again... When merging this to the stable kernels, make sure you also merge commit e330b9a6bb35 ("platform: don't return 0 from platform_get_irq[_byname]() on error") -- that's my fix to platform_get_irq() for the DT platforms... Fixes: 965b2aa78fbc ("net/smsc911x: fix irq resource allocation failure") Signed-off-by: Sergey Shtylyov Link: https://lore.kernel.org/r/656036e4-6387-38df-b8a7-6ba683b16e63@omp.ru Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/smsc/smsc911x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index 7a50ba00f8ae..c854efdf1f25 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -2431,7 +2431,7 @@ static int smsc911x_drv_probe(struct platform_device *pdev) if (irq == -EPROBE_DEFER) { retval = -EPROBE_DEFER; goto out_0; - } else if (irq <= 0) { + } else if (irq < 0) { pr_warn("Could not allocate irq resource\n"); retval = -ENODEV; goto out_0; From 13ba794397e45e52893cfc21d7a69cb5f341b407 Mon Sep 17 00:00:00 2001 From: Somnath Kotur Date: Mon, 2 May 2022 21:13:10 -0400 Subject: [PATCH 109/192] bnxt_en: Fix possible bnxt_open() failure caused by wrong RFS flag bnxt_open() can fail in this code path, especially on a VF when it fails to reserve default rings: bnxt_open() __bnxt_open_nic() bnxt_clear_int_mode() bnxt_init_dflt_ring_mode() RX rings would be set to 0 when we hit this error path. It is possible for a subsequent bnxt_open() call to potentially succeed with a code path like this: bnxt_open() bnxt_hwrm_if_change() bnxt_fw_init_one() bnxt_fw_init_one_p3() bnxt_set_dflt_rfs() bnxt_rfs_capable() bnxt_hwrm_reserve_rings() On older chips, RFS is capable if we can reserve the number of vnics that is equal to RX rings + 1. But since RX rings is still set to 0 in this code path, we may mistakenly think that RFS is supported for 0 RX rings. Later, when the default RX rings are reserved and we try to enable RFS, it would fail and cause bnxt_open() to fail unnecessarily. We fix this in 2 places. bnxt_rfs_capable() will always return false if RX rings is not yet set. bnxt_init_dflt_ring_mode() will call bnxt_set_dflt_rfs() which will always clear the RFS flags if RFS is not supported. Fixes: 20d7d1c5c9b1 ("bnxt_en: reliably allocate IRQ table on reset to avoid crash") Signed-off-by: Somnath Kotur Signed-off-by: Michael Chan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 874fad0a5cf8..2818cfef42f8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -10983,7 +10983,7 @@ static bool bnxt_rfs_capable(struct bnxt *bp) if (bp->flags & BNXT_FLAG_CHIP_P5) return bnxt_rfs_supported(bp); - if (!(bp->flags & BNXT_FLAG_MSIX_CAP) || !bnxt_can_reserve_rings(bp)) + if (!(bp->flags & BNXT_FLAG_MSIX_CAP) || !bnxt_can_reserve_rings(bp) || !bp->rx_nr_rings) return false; vnics = 1 + bp->rx_nr_rings; @@ -13234,10 +13234,9 @@ static int bnxt_init_dflt_ring_mode(struct bnxt *bp) goto init_dflt_ring_err; bp->tx_nr_rings_per_tc = bp->tx_nr_rings; - if (bnxt_rfs_supported(bp) && bnxt_rfs_capable(bp)) { - bp->flags |= BNXT_FLAG_RFS; - bp->dev->features |= NETIF_F_NTUPLE; - } + + bnxt_set_dflt_rfs(bp); + init_dflt_ring_err: bnxt_ulp_irq_restart(bp, rc); return rc; From 2b156fb57d8f0d28f2207edc646751f4717cf20d Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Mon, 2 May 2022 21:13:11 -0400 Subject: [PATCH 110/192] bnxt_en: Initiallize bp->ptp_lock first before using it bnxt_ptp_init() calls bnxt_ptp_init_rtc() which will acquire the ptp_lock spinlock. The spinlock is not initialized until later. Move the bnxt_ptp_init_rtc() call after the spinlock is initialized. Fixes: 24ac1ecd5240 ("bnxt_en: Add driver support to use Real Time Counter for PTP") Reviewed-by: Pavan Chebbi Reviewed-by: Saravanan Vajravel Reviewed-by: Andy Gospodarek Reviewed-by: Somnath Kotur Reviewed-by: Damodharam Ammepalli Signed-off-by: Michael Chan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 9c2ad5e67a5d..00f2f80c0073 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -846,13 +846,6 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg) if (rc) return rc; - if (bp->fw_cap & BNXT_FW_CAP_PTP_RTC) { - bnxt_ptp_timecounter_init(bp, false); - rc = bnxt_ptp_init_rtc(bp, phc_cfg); - if (rc) - goto out; - } - if (ptp->ptp_clock && bnxt_pps_config_ok(bp)) return 0; @@ -861,8 +854,14 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg) atomic_set(&ptp->tx_avail, BNXT_MAX_TX_TS); spin_lock_init(&ptp->ptp_lock); - if (!(bp->fw_cap & BNXT_FW_CAP_PTP_RTC)) + if (bp->fw_cap & BNXT_FW_CAP_PTP_RTC) { + bnxt_ptp_timecounter_init(bp, false); + rc = bnxt_ptp_init_rtc(bp, phc_cfg); + if (rc) + goto out; + } else { bnxt_ptp_timecounter_init(bp, true); + } ptp->ptp_info = bnxt_ptp_caps; if ((bp->fw_cap & BNXT_FW_CAP_PTP_PPS)) { From 195af57914d15229186658ed26dab24b9ada4122 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Mon, 2 May 2022 21:13:12 -0400 Subject: [PATCH 111/192] bnxt_en: Fix unnecessary dropping of RX packets In bnxt_poll_p5(), we first check cpr->has_more_work. If it is true, we are in NAPI polling mode and we will call __bnxt_poll_cqs() to continue polling. It is possible to exhanust the budget again when __bnxt_poll_cqs() returns. We then enter the main while loop to check for new entries in the NQ. If we had previously exhausted the NAPI budget, we may call __bnxt_poll_work() to process an RX entry with zero budget. This will cause packets to be dropped unnecessarily, thinking that we are in the netpoll path. Fix it by breaking out of the while loop if we need to process an RX NQ entry with no budget left. We will then exit NAPI and stay in polling mode. Fixes: 389a877a3b20 ("bnxt_en: Process the NQ under NAPI continuous polling.") Reviewed-by: Andy Gospodarek Signed-off-by: Michael Chan Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 2818cfef42f8..1d69fe0737a1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2707,6 +2707,10 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget) u32 idx = le32_to_cpu(nqcmp->cq_handle_low); struct bnxt_cp_ring_info *cpr2; + /* No more budget for RX work */ + if (budget && work_done >= budget && idx == BNXT_RX_HDL) + break; + cpr2 = cpr->cp_ring_arr[idx]; work_done += __bnxt_poll_work(bp, cpr2, budget - work_done); From cb0d54cbf94866b48a73e10a73a55655f808cc7c Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Tue, 15 Mar 2022 18:20:48 +0200 Subject: [PATCH 112/192] net/mlx5e: Fix wrong source vport matching on tunnel rule When OVS internal port is the vtep device, the first decap rule is matching on the internal port's vport metadata value and then changes the metadata to be the uplink's value. Therefore, following rules on the tunnel, in chain > 0, should avoid matching on internal port metadata and use the uplink vport metadata instead. Select the uplink's metadata value for the source vport match in case the rule is in chain greater than zero, even if the tunnel route device is internal port. Fixes: 166f431ec6be ("net/mlx5e: Add indirect tc offload of ovs internal port") Signed-off-by: Ariel Levkovich Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 3f63df127091..3b151332e2f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -139,7 +139,7 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, if (mlx5_esw_indir_table_decap_vport(attr)) vport = mlx5_esw_indir_table_decap_vport(attr); - if (esw_attr->int_port) + if (attr && !attr->chain && esw_attr->int_port) metadata = mlx5e_tc_int_port_get_metadata_for_match(esw_attr->int_port); else From 7ba2d9d8de96696c1451fee1b01da11f45bdc2b9 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Thu, 3 Mar 2022 19:02:03 +0200 Subject: [PATCH 113/192] net/mlx5: Fix slab-out-of-bounds while reading resource dump menu Resource dump menu may span over more than a single page, support it. Otherwise, menu read may result in a memory access violation: reading outside of the allocated page. Note that page format of the first menu page contains menu headers while the proceeding menu pages contain only records. The KASAN logs are as follows: BUG: KASAN: slab-out-of-bounds in strcmp+0x9b/0xb0 Read of size 1 at addr ffff88812b2e1fd0 by task systemd-udevd/496 CPU: 5 PID: 496 Comm: systemd-udevd Tainted: G B 5.16.0_for_upstream_debug_2022_01_10_23_12 #1 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack_lvl+0x57/0x7d print_address_description.constprop.0+0x1f/0x140 ? strcmp+0x9b/0xb0 ? strcmp+0x9b/0xb0 kasan_report.cold+0x83/0xdf ? strcmp+0x9b/0xb0 strcmp+0x9b/0xb0 mlx5_rsc_dump_init+0x4ab/0x780 [mlx5_core] ? mlx5_rsc_dump_destroy+0x80/0x80 [mlx5_core] ? lockdep_hardirqs_on_prepare+0x286/0x400 ? raw_spin_unlock_irqrestore+0x47/0x50 ? aomic_notifier_chain_register+0x32/0x40 mlx5_load+0x104/0x2e0 [mlx5_core] mlx5_init_one+0x41b/0x610 [mlx5_core] .... The buggy address belongs to the object at ffff88812b2e0000 which belongs to the cache kmalloc-4k of size 4096 The buggy address is located 4048 bytes to the right of 4096-byte region [ffff88812b2e0000, ffff88812b2e1000) The buggy address belongs to the page: page:000000009d69807a refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88812b2e6000 pfn:0x12b2e0 head:000000009d69807a order:3 compound_mapcount:0 compound_pincount:0 flags: 0x8000000000010200(slab|head|zone=2) raw: 8000000000010200 0000000000000000 dead000000000001 ffff888100043040 raw: ffff88812b2e6000 0000000080040000 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff88812b2e1e80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff88812b2e1f00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff88812b2e1f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffff88812b2e2000: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff88812b2e2080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Fixes: 12206b17235a ("net/mlx5: Add support for resource dump") Signed-off-by: Aya Levin Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- .../mellanox/mlx5/core/diag/rsc_dump.c | 31 +++++++++++++++---- 1 file changed, 25 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c index 538adab6878b..c5b560a8b026 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c @@ -31,6 +31,7 @@ static const char *const mlx5_rsc_sgmt_name[] = { struct mlx5_rsc_dump { u32 pdn; u32 mkey; + u32 number_of_menu_items; u16 fw_segment_type[MLX5_SGMT_TYPE_NUM]; }; @@ -50,21 +51,37 @@ static int mlx5_rsc_dump_sgmt_get_by_name(char *name) return -EINVAL; } -static void mlx5_rsc_dump_read_menu_sgmt(struct mlx5_rsc_dump *rsc_dump, struct page *page) +#define MLX5_RSC_DUMP_MENU_HEADER_SIZE (MLX5_ST_SZ_BYTES(resource_dump_info_segment) + \ + MLX5_ST_SZ_BYTES(resource_dump_command_segment) + \ + MLX5_ST_SZ_BYTES(resource_dump_menu_segment)) + +static int mlx5_rsc_dump_read_menu_sgmt(struct mlx5_rsc_dump *rsc_dump, struct page *page, + int read_size, int start_idx) { void *data = page_address(page); enum mlx5_sgmt_type sgmt_idx; int num_of_items; char *sgmt_name; void *member; + int size = 0; void *menu; int i; - menu = MLX5_ADDR_OF(menu_resource_dump_response, data, menu); - num_of_items = MLX5_GET(resource_dump_menu_segment, menu, num_of_records); + if (!start_idx) { + menu = MLX5_ADDR_OF(menu_resource_dump_response, data, menu); + rsc_dump->number_of_menu_items = MLX5_GET(resource_dump_menu_segment, menu, + num_of_records); + size = MLX5_RSC_DUMP_MENU_HEADER_SIZE; + data += size; + } + num_of_items = rsc_dump->number_of_menu_items; - for (i = 0; i < num_of_items; i++) { - member = MLX5_ADDR_OF(resource_dump_menu_segment, menu, record[i]); + for (i = 0; start_idx + i < num_of_items; i++) { + size += MLX5_ST_SZ_BYTES(resource_dump_menu_record); + if (size >= read_size) + return start_idx + i; + + member = data + MLX5_ST_SZ_BYTES(resource_dump_menu_record) * i; sgmt_name = MLX5_ADDR_OF(resource_dump_menu_record, member, segment_name); sgmt_idx = mlx5_rsc_dump_sgmt_get_by_name(sgmt_name); if (sgmt_idx == -EINVAL) @@ -72,6 +89,7 @@ static void mlx5_rsc_dump_read_menu_sgmt(struct mlx5_rsc_dump *rsc_dump, struct rsc_dump->fw_segment_type[sgmt_idx] = MLX5_GET(resource_dump_menu_record, member, segment_type); } + return 0; } static int mlx5_rsc_dump_trigger(struct mlx5_core_dev *dev, struct mlx5_rsc_dump_cmd *cmd, @@ -168,6 +186,7 @@ static int mlx5_rsc_dump_menu(struct mlx5_core_dev *dev) struct mlx5_rsc_dump_cmd *cmd = NULL; struct mlx5_rsc_key key = {}; struct page *page; + int start_idx = 0; int size; int err; @@ -189,7 +208,7 @@ static int mlx5_rsc_dump_menu(struct mlx5_core_dev *dev) if (err < 0) goto destroy_cmd; - mlx5_rsc_dump_read_menu_sgmt(dev->rsc_dump, page); + start_idx = mlx5_rsc_dump_read_menu_sgmt(dev->rsc_dump, page, size, start_idx); } while (err > 0); From ada09af92e621ab500dd80a16d1d0299a18a1180 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 28 Mar 2022 15:54:52 +0300 Subject: [PATCH 114/192] net/mlx5e: Don't match double-vlan packets if cvlan is not set Currently, match VLAN rule also matches packets that have multiple VLAN headers. This behavior is similar to buggy flower classifier behavior that has recently been fixed. Fix the issue by matching on outer_second_cvlan_tag with value 0 which will cause the HW to verify the packet doesn't contain second vlan header. Fixes: 699e96ddf47f ("net/mlx5e: Support offloading tc double vlan headers match") Signed-off-by: Vlad Buslov Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index e3fc15ae7bb1..ac0f73074f7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2459,6 +2459,17 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, match.key->vlan_priority); *match_level = MLX5_MATCH_L2; + + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN) && + match.mask->vlan_eth_type && + MLX5_CAP_FLOWTABLE_TYPE(priv->mdev, + ft_field_support.outer_second_vid, + fs_type)) { + MLX5_SET(fte_match_set_misc, misc_c, + outer_second_cvlan_tag, 1); + spec->match_criteria_enable |= + MLX5_MATCH_MISC_PARAMETERS; + } } } else if (*match_level != MLX5_MATCH_NONE) { /* cvlan_tag enabled in match criteria and From c4d963a588a6e7c4ef31160e80697ae8e5a47746 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Wed, 6 Apr 2022 10:30:21 +0300 Subject: [PATCH 115/192] net/mlx5e: Fix the calling of update_buffer_lossy() API The arguments of update_buffer_lossy() is in a wrong order. Fix it. Fixes: 88b3d5c90e96 ("net/mlx5e: Fix port buffers cell size value") Signed-off-by: Mark Zhang Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index 673f1c82d381..c9d5d8d93994 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -309,8 +309,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (err) return err; - err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer, port_buff_cell_sz, - xoff, &port_buffer, &update_buffer); + err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer, xoff, + port_buff_cell_sz, &port_buffer, &update_buffer); if (err) return err; } From 27b0420fd959e38e3500e60b637d39dfab065645 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 18 Apr 2022 17:32:19 +0300 Subject: [PATCH 116/192] net/mlx5e: Lag, Fix use-after-free in fib event handler Recent commit that modified fib route event handler to handle events according to their priority introduced use-after-free[0] in mp->mfi pointer usage. The pointer now is not just cached in order to be compared to following fib_info instances, but is also dereferenced to obtain fib_priority. However, since mlx5 lag code doesn't hold the reference to fin_info during whole mp->mfi lifetime, it could be used after fib_info instance has already been freed be kernel infrastructure code. Don't ever dereference mp->mfi pointer. Refactor it to be 'const void*' type and cache fib_info priority in dedicated integer. Group fib_info-related data into dedicated 'fib' structure that will be further extended by following patches in the series. [0]: [ 203.588029] ================================================================== [ 203.590161] BUG: KASAN: use-after-free in mlx5_lag_fib_update+0xabd/0xd60 [mlx5_core] [ 203.592386] Read of size 4 at addr ffff888144df2050 by task kworker/u20:4/138 [ 203.594766] CPU: 3 PID: 138 Comm: kworker/u20:4 Tainted: G B 5.17.0-rc7+ #6 [ 203.596751] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 203.598813] Workqueue: mlx5_lag_mp mlx5_lag_fib_update [mlx5_core] [ 203.600053] Call Trace: [ 203.600608] [ 203.601110] dump_stack_lvl+0x48/0x5e [ 203.601860] print_address_description.constprop.0+0x1f/0x160 [ 203.602950] ? mlx5_lag_fib_update+0xabd/0xd60 [mlx5_core] [ 203.604073] ? mlx5_lag_fib_update+0xabd/0xd60 [mlx5_core] [ 203.605177] kasan_report.cold+0x83/0xdf [ 203.605969] ? mlx5_lag_fib_update+0xabd/0xd60 [mlx5_core] [ 203.607102] mlx5_lag_fib_update+0xabd/0xd60 [mlx5_core] [ 203.608199] ? mlx5_lag_init_fib_work+0x1c0/0x1c0 [mlx5_core] [ 203.609382] ? read_word_at_a_time+0xe/0x20 [ 203.610463] ? strscpy+0xa0/0x2a0 [ 203.611463] process_one_work+0x722/0x1270 [ 203.612344] worker_thread+0x540/0x11e0 [ 203.613136] ? rescuer_thread+0xd50/0xd50 [ 203.613949] kthread+0x26e/0x300 [ 203.614627] ? kthread_complete_and_exit+0x20/0x20 [ 203.615542] ret_from_fork+0x1f/0x30 [ 203.616273] [ 203.617174] Allocated by task 3746: [ 203.617874] kasan_save_stack+0x1e/0x40 [ 203.618644] __kasan_kmalloc+0x81/0xa0 [ 203.619394] fib_create_info+0xb41/0x3c50 [ 203.620213] fib_table_insert+0x190/0x1ff0 [ 203.621020] fib_magic.isra.0+0x246/0x2e0 [ 203.621803] fib_add_ifaddr+0x19f/0x670 [ 203.622563] fib_inetaddr_event+0x13f/0x270 [ 203.623377] blocking_notifier_call_chain+0xd4/0x130 [ 203.624355] __inet_insert_ifa+0x641/0xb20 [ 203.625185] inet_rtm_newaddr+0xc3d/0x16a0 [ 203.626009] rtnetlink_rcv_msg+0x309/0x880 [ 203.626826] netlink_rcv_skb+0x11d/0x340 [ 203.627626] netlink_unicast+0x4cc/0x790 [ 203.628430] netlink_sendmsg+0x762/0xc00 [ 203.629230] sock_sendmsg+0xb2/0xe0 [ 203.629955] ____sys_sendmsg+0x58a/0x770 [ 203.630756] ___sys_sendmsg+0xd8/0x160 [ 203.631523] __sys_sendmsg+0xb7/0x140 [ 203.632294] do_syscall_64+0x35/0x80 [ 203.633045] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 203.634427] Freed by task 0: [ 203.635063] kasan_save_stack+0x1e/0x40 [ 203.635844] kasan_set_track+0x21/0x30 [ 203.636618] kasan_set_free_info+0x20/0x30 [ 203.637450] __kasan_slab_free+0xfc/0x140 [ 203.638271] kfree+0x94/0x3b0 [ 203.638903] rcu_core+0x5e4/0x1990 [ 203.639640] __do_softirq+0x1ba/0x5d3 [ 203.640828] Last potentially related work creation: [ 203.641785] kasan_save_stack+0x1e/0x40 [ 203.642571] __kasan_record_aux_stack+0x9f/0xb0 [ 203.643478] call_rcu+0x88/0x9c0 [ 203.644178] fib_release_info+0x539/0x750 [ 203.644997] fib_table_delete+0x659/0xb80 [ 203.645809] fib_magic.isra.0+0x1a3/0x2e0 [ 203.646617] fib_del_ifaddr+0x93f/0x1300 [ 203.647415] fib_inetaddr_event+0x9f/0x270 [ 203.648251] blocking_notifier_call_chain+0xd4/0x130 [ 203.649225] __inet_del_ifa+0x474/0xc10 [ 203.650016] devinet_ioctl+0x781/0x17f0 [ 203.650788] inet_ioctl+0x1ad/0x290 [ 203.651533] sock_do_ioctl+0xce/0x1c0 [ 203.652315] sock_ioctl+0x27b/0x4f0 [ 203.653058] __x64_sys_ioctl+0x124/0x190 [ 203.653850] do_syscall_64+0x35/0x80 [ 203.654608] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 203.666952] The buggy address belongs to the object at ffff888144df2000 which belongs to the cache kmalloc-256 of size 256 [ 203.669250] The buggy address is located 80 bytes inside of 256-byte region [ffff888144df2000, ffff888144df2100) [ 203.671332] The buggy address belongs to the page: [ 203.672273] page:00000000bf6c9314 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x144df0 [ 203.674009] head:00000000bf6c9314 order:2 compound_mapcount:0 compound_pincount:0 [ 203.675422] flags: 0x2ffff800010200(slab|head|node=0|zone=2|lastcpupid=0x1ffff) [ 203.676819] raw: 002ffff800010200 0000000000000000 dead000000000122 ffff888100042b40 [ 203.678384] raw: 0000000000000000 0000000080200020 00000001ffffffff 0000000000000000 [ 203.679928] page dumped because: kasan: bad access detected [ 203.681455] Memory state around the buggy address: [ 203.682421] ffff888144df1f00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 203.683863] ffff888144df1f80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 203.685310] >ffff888144df2000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 203.686701] ^ [ 203.687820] ffff888144df2080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 203.689226] ffff888144df2100: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 203.690620] ================================================================== Fixes: ad11c4f1d8fd ("net/mlx5e: Lag, Only handle events from highest priority multipath entry") Signed-off-by: Vlad Buslov Reviewed-by: Maor Dickman Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/lag/mp.c | 26 ++++++++++++------- .../net/ethernet/mellanox/mlx5/core/lag/mp.h | 5 +++- 2 files changed, 20 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index 4a6ec15ef046..bc77aba97ac1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -100,6 +100,12 @@ static void mlx5_lag_fib_event_flush(struct notifier_block *nb) flush_workqueue(mp->wq); } +static void mlx5_lag_fib_set(struct lag_mp *mp, struct fib_info *fi) +{ + mp->fib.mfi = fi; + mp->fib.priority = fi->fib_priority; +} + struct mlx5_fib_event_work { struct work_struct work; struct mlx5_lag *ldev; @@ -121,13 +127,13 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, /* Handle delete event */ if (event == FIB_EVENT_ENTRY_DEL) { /* stop track */ - if (mp->mfi == fi) - mp->mfi = NULL; + if (mp->fib.mfi == fi) + mp->fib.mfi = NULL; return; } /* Handle multipath entry with lower priority value */ - if (mp->mfi && mp->mfi != fi && fi->fib_priority >= mp->mfi->fib_priority) + if (mp->fib.mfi && mp->fib.mfi != fi && fi->fib_priority >= mp->fib.priority) return; /* Handle add/replace event */ @@ -145,7 +151,7 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, mlx5_lag_set_port_affinity(ldev, i); } - mp->mfi = fi; + mlx5_lag_fib_set(mp, fi); return; } @@ -165,7 +171,7 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, } /* First time we see multipath route */ - if (!mp->mfi && !__mlx5_lag_is_active(ldev)) { + if (!mp->fib.mfi && !__mlx5_lag_is_active(ldev)) { struct lag_tracker tracker; tracker = ldev->tracker; @@ -173,7 +179,7 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, } mlx5_lag_set_port_affinity(ldev, MLX5_LAG_NORMAL_AFFINITY); - mp->mfi = fi; + mlx5_lag_fib_set(mp, fi); } static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev, @@ -184,7 +190,7 @@ static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev, struct lag_mp *mp = &ldev->lag_mp; /* Check the nh event is related to the route */ - if (!mp->mfi || mp->mfi != fi) + if (!mp->fib.mfi || mp->fib.mfi != fi) return; /* nh added/removed */ @@ -313,7 +319,7 @@ void mlx5_lag_mp_reset(struct mlx5_lag *ldev) /* Clear mfi, as it might become stale when a route delete event * has been missed, see mlx5_lag_fib_route_event(). */ - ldev->lag_mp.mfi = NULL; + ldev->lag_mp.fib.mfi = NULL; } int mlx5_lag_mp_init(struct mlx5_lag *ldev) @@ -324,7 +330,7 @@ int mlx5_lag_mp_init(struct mlx5_lag *ldev) /* always clear mfi, as it might become stale when a route delete event * has been missed */ - mp->mfi = NULL; + mp->fib.mfi = NULL; if (mp->fib_nb.notifier_call) return 0; @@ -354,5 +360,5 @@ void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) unregister_fib_notifier(&init_net, &mp->fib_nb); destroy_workqueue(mp->wq); mp->fib_nb.notifier_call = NULL; - mp->mfi = NULL; + mp->fib.mfi = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h index 57af962cad29..143226753c3a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h @@ -15,7 +15,10 @@ enum mlx5_lag_port_affinity { struct lag_mp { struct notifier_block fib_nb; - struct fib_info *mfi; /* used in tracking fib events */ + struct { + const void *mfi; /* used in tracking fib events */ + u32 priority; + } fib; struct workqueue_struct *wq; }; From a6589155ec9847918e00e7279b8aa6d4c272bea7 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 18 Apr 2022 17:32:54 +0300 Subject: [PATCH 117/192] net/mlx5e: Lag, Fix fib_info pointer assignment Referenced change incorrectly sets single path fib_info even when LAG is not active. Fix it by moving call to mlx5_lag_fib_set() into conditional that verifies LAG state. Fixes: ad11c4f1d8fd ("net/mlx5e: Lag, Only handle events from highest priority multipath entry") Signed-off-by: Vlad Buslov Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index bc77aba97ac1..9a5884e8a8bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -149,9 +149,9 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, i++; mlx5_lag_set_port_affinity(ldev, i); + mlx5_lag_fib_set(mp, fi); } - mlx5_lag_fib_set(mp, fi); return; } From 4a2a664ed87962c4ddb806a84b5c9634820bcf55 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Mon, 18 Apr 2022 17:40:37 +0300 Subject: [PATCH 118/192] net/mlx5e: Lag, Don't skip fib events on current dst Referenced change added check to skip updating fib when new fib instance has same or lower priority. However, new fib instance can be an update on same dst address as existing one even though the structure is another instance that has different address. Ignoring events on such instances causes multipath LAG state to not be correctly updated. Track 'dst' and 'dst_len' fields of fib event fib_entry_notifier_info structure and don't skip events that have the same value of that fields. Fixes: ad11c4f1d8fd ("net/mlx5e: Lag, Only handle events from highest priority multipath entry") Signed-off-by: Vlad Buslov Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/lag/mp.c | 20 +++++++++++-------- .../net/ethernet/mellanox/mlx5/core/lag/mp.h | 2 ++ 2 files changed, 14 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index 9a5884e8a8bf..d6c3e6dfd71f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -100,10 +100,12 @@ static void mlx5_lag_fib_event_flush(struct notifier_block *nb) flush_workqueue(mp->wq); } -static void mlx5_lag_fib_set(struct lag_mp *mp, struct fib_info *fi) +static void mlx5_lag_fib_set(struct lag_mp *mp, struct fib_info *fi, u32 dst, int dst_len) { mp->fib.mfi = fi; mp->fib.priority = fi->fib_priority; + mp->fib.dst = dst; + mp->fib.dst_len = dst_len; } struct mlx5_fib_event_work { @@ -116,10 +118,10 @@ struct mlx5_fib_event_work { }; }; -static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, - unsigned long event, - struct fib_info *fi) +static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, unsigned long event, + struct fib_entry_notifier_info *fen_info) { + struct fib_info *fi = fen_info->fi; struct lag_mp *mp = &ldev->lag_mp; struct fib_nh *fib_nh0, *fib_nh1; unsigned int nhs; @@ -133,7 +135,9 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, } /* Handle multipath entry with lower priority value */ - if (mp->fib.mfi && mp->fib.mfi != fi && fi->fib_priority >= mp->fib.priority) + if (mp->fib.mfi && mp->fib.mfi != fi && + (mp->fib.dst != fen_info->dst || mp->fib.dst_len != fen_info->dst_len) && + fi->fib_priority >= mp->fib.priority) return; /* Handle add/replace event */ @@ -149,7 +153,7 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, i++; mlx5_lag_set_port_affinity(ldev, i); - mlx5_lag_fib_set(mp, fi); + mlx5_lag_fib_set(mp, fi, fen_info->dst, fen_info->dst_len); } return; @@ -179,7 +183,7 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, } mlx5_lag_set_port_affinity(ldev, MLX5_LAG_NORMAL_AFFINITY); - mlx5_lag_fib_set(mp, fi); + mlx5_lag_fib_set(mp, fi, fen_info->dst, fen_info->dst_len); } static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev, @@ -220,7 +224,7 @@ static void mlx5_lag_fib_update(struct work_struct *work) case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_DEL: mlx5_lag_fib_route_event(ldev, fib_work->event, - fib_work->fen_info.fi); + &fib_work->fen_info); fib_info_put(fib_work->fen_info.fi); break; case FIB_EVENT_NH_ADD: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h index 143226753c3a..056a066da604 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.h @@ -18,6 +18,8 @@ struct lag_mp { struct { const void *mfi; /* used in tracking fib events */ u32 priority; + u32 dst; + int dst_len; } fib; struct workqueue_struct *wq; }; From 087032ee7021a22e4c7557c0ed16bfd792c3f6fe Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Wed, 23 Feb 2022 21:29:17 +0200 Subject: [PATCH 119/192] net/mlx5e: TC, Fix ct_clear overwriting ct action metadata ct_clear action is translated to clearing reg_c metadata which holds ct state and zone information using mod header actions. These actions are allocated during the actions parsing, as part of the flow attributes main mod header action list. If ct action exists in the rule, the flow's main mod header is used only in the post action table rule, after the ct tables which set the ct info in the reg_c as part of the ct actions. Therefore, if the original rule has a ct_clear action followed by a ct action, the ct action reg_c setting will be done first and will be followed by the ct_clear resetting reg_c and overwriting the ct info. Fix this by moving the ct_clear mod header actions allocation from the ct action parsing stage to the ct action post parsing stage where it is already known if ct_clear is followed by a ct action. In such case, we skip the mod header actions allocation for the ct clear since the ct action will write to reg_c anyway after clearing it. Fixes: 806401c20a0f ("net/mlx5e: CT, Fix multiple allocations and memleak of mod acts") Signed-off-by: Ariel Levkovich Reviewed-by: Paul Blakey Reviewed-by: Roi Dayan Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- .../mellanox/mlx5/core/en/tc/act/ct.c | 34 +++++++++++++++++-- .../ethernet/mellanox/mlx5/core/en/tc_ct.c | 20 ++++------- .../ethernet/mellanox/mlx5/core/en/tc_ct.h | 11 ++++++ 3 files changed, 49 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c index b9d38fe807df..a829c94289c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c @@ -45,12 +45,41 @@ tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state, if (mlx5e_is_eswitch_flow(parse_state->flow)) attr->esw_attr->split_count = attr->esw_attr->out_count; - if (!clear_action) { + if (clear_action) { + parse_state->ct_clear = true; + } else { attr->flags |= MLX5_ATTR_FLAG_CT; flow_flag_set(parse_state->flow, CT); parse_state->ct = true; } - parse_state->ct_clear = clear_action; + + return 0; +} + +static int +tc_act_post_parse_ct(struct mlx5e_tc_act_parse_state *parse_state, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + struct mlx5e_tc_mod_hdr_acts *mod_acts = &attr->parse_attr->mod_hdr_acts; + int err; + + /* If ct action exist, we can ignore previous ct_clear actions */ + if (parse_state->ct) + return 0; + + if (parse_state->ct_clear) { + err = mlx5_tc_ct_set_ct_clear_regs(parse_state->ct_priv, mod_acts); + if (err) { + NL_SET_ERR_MSG_MOD(parse_state->extack, + "Failed to set registers for ct clear"); + return err; + } + attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + + /* Prevent handling of additional, redundant clear actions */ + parse_state->ct_clear = false; + } return 0; } @@ -70,5 +99,6 @@ struct mlx5e_tc_act mlx5e_tc_act_ct = { .can_offload = tc_act_can_offload_ct, .parse_action = tc_act_parse_ct, .is_multi_table_act = tc_act_is_multi_table_act_ct, + .post_parse = tc_act_post_parse_ct, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index e49f51124c74..73a1e0a4818d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -582,6 +582,12 @@ mlx5_tc_ct_entry_set_registers(struct mlx5_tc_ct_priv *ct_priv, return 0; } +int mlx5_tc_ct_set_ct_clear_regs(struct mlx5_tc_ct_priv *priv, + struct mlx5e_tc_mod_hdr_acts *mod_acts) +{ + return mlx5_tc_ct_entry_set_registers(priv, mod_acts, 0, 0, 0, 0); +} + static int mlx5_tc_ct_parse_mangle_to_mod_act(struct flow_action_entry *act, char *modact) @@ -1410,9 +1416,6 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, const struct flow_action_entry *act, struct netlink_ext_ack *extack) { - bool clear_action = act->ct.action & TCA_CT_ACT_CLEAR; - int err; - if (!priv) { NL_SET_ERR_MSG_MOD(extack, "offload of ct action isn't available"); @@ -1423,17 +1426,6 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, attr->ct_attr.ct_action = act->ct.action; attr->ct_attr.nf_ft = act->ct.flow_table; - if (!clear_action) - goto out; - - err = mlx5_tc_ct_entry_set_registers(priv, mod_acts, 0, 0, 0, 0); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "Failed to set registers for ct clear"); - return err; - } - attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - -out: return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 36d3652bf829..00a3ba862afb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -129,6 +129,10 @@ bool mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv, struct sk_buff *skb, u8 zone_restore_id); +int +mlx5_tc_ct_set_ct_clear_regs(struct mlx5_tc_ct_priv *priv, + struct mlx5e_tc_mod_hdr_acts *mod_acts); + #else /* CONFIG_MLX5_TC_CT */ static inline struct mlx5_tc_ct_priv * @@ -170,6 +174,13 @@ mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec) return 0; } +static inline int +mlx5_tc_ct_set_ct_clear_regs(struct mlx5_tc_ct_priv *priv, + struct mlx5e_tc_mod_hdr_acts *mod_acts) +{ + return -EOPNOTSUPP; +} + static inline int mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *attr, From e3fdc71bcb6ffe1d4870a89252ba296a9558e294 Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Mon, 25 Apr 2022 17:12:12 +0300 Subject: [PATCH 120/192] net/mlx5e: TC, fix decap fallback to uplink when int port not supported When resolving the decap route device for a tunnel decap rule, the result may be an OVS internal port device. Prior to adding the support for internal port offload, such case would result in using the uplink as the default decap route device which allowed devices that can't support internal port offload to offload this decap rule. This behavior got broken by adding the internal port offload which will fail in case the device can't support internal port offload. To restore the old behavior, use the uplink device as the decap route as before when internal port offload is not supported. Fixes: b16eb3c81fe2 ("net/mlx5: Support internal port as decap route device") Signed-off-by: Ariel Levkovich Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 378fc8e3bd97..d87bbb0be7c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -713,6 +713,7 @@ int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv, struct net_device *filter_dev) { struct mlx5_esw_flow_attr *esw_attr = flow_attr->esw_attr; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_int_port *int_port; TC_TUN_ROUTE_ATTR_INIT(attr); u16 vport_num; @@ -747,7 +748,7 @@ int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv, esw_attr->rx_tun_attr->vni = MLX5_GET(fte_match_param, spec->match_value, misc_parameters.vxlan_vni); esw_attr->rx_tun_attr->decap_vport = vport_num; - } else if (netif_is_ovs_master(attr.route_dev)) { + } else if (netif_is_ovs_master(attr.route_dev) && mlx5e_tc_int_port_supported(esw)) { int_port = mlx5e_tc_int_port_get(mlx5e_get_int_port_priv(priv), attr.route_dev->ifindex, MLX5E_TC_INT_PORT_INGRESS); From b069e14fff46c8da9fcc79957f8acaa3e2dfdb6b Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 29 Mar 2022 17:42:46 +0300 Subject: [PATCH 121/192] net/mlx5e: CT: Fix queued up restore put() executing after relevant ft release __mlx5_tc_ct_entry_put() queues release of tuple related to some ct FT, if that is the last reference to that tuple, the actual deletion of the tuple can happen after the FT is already destroyed and freed. Flush the used workqueue before destroying the ct FT. Fixes: a2173131526d ("net/mlx5e: CT: manage the lifetime of the ct entry object") Reviewed-by: Oz Shlomo Signed-off-by: Paul Blakey Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 73a1e0a4818d..ab4b0f3ee2a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -1741,6 +1741,8 @@ mlx5_tc_ct_flush_ft_entry(void *ptr, void *arg) static void mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) { + struct mlx5e_priv *priv; + if (!refcount_dec_and_test(&ft->refcount)) return; @@ -1750,6 +1752,8 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) rhashtable_free_and_destroy(&ft->ct_entries_ht, mlx5_tc_ct_flush_ft_entry, ct_priv); + priv = netdev_priv(ct_priv->netdev); + flush_workqueue(priv->wq); mlx5_tc_ct_free_pre_ct_tables(ft); mapping_remove(ct_priv->zone_mapping, ft->zone_restore_id); kfree(ft); From 0e322efd64d2ad11a773f7a314512086ebbe000c Mon Sep 17 00:00:00 2001 From: Ariel Levkovich Date: Mon, 28 Mar 2022 18:29:13 +0300 Subject: [PATCH 122/192] net/mlx5e: Avoid checking offload capability in post_parse action During TC action parsing, the can_offload callback is called before calling the action's main parsing callback. Later on, the can_offload callback is called again before handling the action's post_parse callback if exists. Since the main parsing callback might have changed and set parsing params for the rule, following can_offload checks might fail because some parsing params were already set. Specifically, the ct action main parsing sets the ct param in the parsing status structure and when the second can_offload for ct action is called, before handling the ct post parsing, it will return an error since it checks this ct param to indicate multiple ct actions which are not supported. Therefore, the can_offload call is removed from the post parsing handling to prevent such cases. This is allowed since the first can_offload call will ensure that the action can be offloaded and the fact the code reached the post parsing handling already means that the action can be offloaded. Fixes: 8300f225268b ("net/mlx5e: Create new flow attr for multi table actions") Signed-off-by: Ariel Levkovich Reviewed-by: Paul Blakey Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c index af37a8d247a1..2755c25ba324 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c @@ -145,8 +145,7 @@ mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state, flow_action_for_each(i, act, flow_action) { tc_act = mlx5e_tc_act_get(act->id, ns_type); - if (!tc_act || !tc_act->post_parse || - !tc_act->can_offload(parse_state, act, i, attr)) + if (!tc_act || !tc_act->post_parse) continue; err = tc_act->post_parse(parse_state, priv, attr); From b781bff882d16175277ca129c382886cb4c74a2c Mon Sep 17 00:00:00 2001 From: Moshe Tal Date: Wed, 9 Feb 2022 19:23:56 +0200 Subject: [PATCH 123/192] net/mlx5e: Fix trust state reset in reload Setting dscp2prio during the driver reload can cause dcb ieee app list to be not empty after the reload finish and as a result to a conflict between the priority trust state reported by the app and the state in the device register. Reset the dcb ieee app list on initialization in case this is conflicting with the register status. Fixes: 2a5e7a1344f4 ("net/mlx5e: Add dcbnl dscp to priority support") Signed-off-by: Moshe Tal Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index d659fe07d464..8ead2c82a52a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -1200,6 +1200,16 @@ static int mlx5e_trust_initialize(struct mlx5e_priv *priv) return err; WRITE_ONCE(priv->dcbx_dp.trust_state, trust_state); + if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_PCP && priv->dcbx.dscp_app_cnt) { + /* + * Align the driver state with the register state. + * Temporary state change is required to enable the app list reset. + */ + priv->dcbx_dp.trust_state = MLX5_QPTS_TRUST_DSCP; + mlx5e_dcbnl_delete_app(priv); + priv->dcbx_dp.trust_state = MLX5_QPTS_TRUST_PCP; + } + mlx5e_params_calc_trust_tx_min_inline_mode(priv->mdev, &priv->channels.params, priv->dcbx_dp.trust_state); From cb7786a76ea39f394f0a059787fe24fa8e340fb6 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Mon, 11 Apr 2022 21:31:06 +0300 Subject: [PATCH 124/192] net/mlx5: Fix deadlock in sync reset flow The sync reset flow can lead to the following deadlock when poll_sync_reset() is called by timer softirq and waiting on del_timer_sync() for the same timer. Fix that by moving the part of the flow that waits for the timer to reset_reload_work. It fixes the following kernel Trace: RIP: 0010:del_timer_sync+0x32/0x40 ... Call Trace: mlx5_sync_reset_clear_reset_requested+0x26/0x50 [mlx5_core] poll_sync_reset.cold+0x36/0x52 [mlx5_core] call_timer_fn+0x32/0x130 __run_timers.part.0+0x180/0x280 ? tick_sched_handle+0x33/0x60 ? tick_sched_timer+0x3d/0x80 ? ktime_get+0x3e/0xa0 run_timer_softirq+0x2a/0x50 __do_softirq+0xe1/0x2d6 ? hrtimer_interrupt+0x136/0x220 irq_exit+0xae/0xb0 smp_apic_timer_interrupt+0x7b/0x140 apic_timer_interrupt+0xf/0x20 Fixes: 3c5193a87b0f ("net/mlx5: Use del_timer_sync in fw reset flow of halting poll") Signed-off-by: Moshe Shemesh Reviewed-by: Maher Sanalla Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/fw_reset.c | 34 +++++++++---------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 4aa22dce9b77..ec18d4ccbc11 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -155,22 +155,6 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev) } } -static void mlx5_sync_reset_reload_work(struct work_struct *work) -{ - struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset, - reset_reload_work); - struct mlx5_core_dev *dev = fw_reset->dev; - int err; - - mlx5_enter_error_state(dev, true); - mlx5_unload_one(dev); - err = mlx5_health_wait_pci_up(dev); - if (err) - mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n"); - fw_reset->ret = err; - mlx5_fw_reset_complete_reload(dev); -} - static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; @@ -188,6 +172,23 @@ static void mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, boo mlx5_start_health_poll(dev); } +static void mlx5_sync_reset_reload_work(struct work_struct *work) +{ + struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset, + reset_reload_work); + struct mlx5_core_dev *dev = fw_reset->dev; + int err; + + mlx5_sync_reset_clear_reset_requested(dev, false); + mlx5_enter_error_state(dev, true); + mlx5_unload_one(dev); + err = mlx5_health_wait_pci_up(dev); + if (err) + mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n"); + fw_reset->ret = err; + mlx5_fw_reset_complete_reload(dev); +} + #define MLX5_RESET_POLL_INTERVAL (HZ / 10) static void poll_sync_reset(struct timer_list *t) { @@ -202,7 +203,6 @@ static void poll_sync_reset(struct timer_list *t) if (fatal_error) { mlx5_core_warn(dev, "Got Device Reset\n"); - mlx5_sync_reset_clear_reset_requested(dev, false); queue_work(fw_reset->wq, &fw_reset->reset_reload_work); return; } From fc3d3db07b35885f238e1fa06b9f04a8fa7a62d0 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Mon, 11 Apr 2022 20:38:44 +0300 Subject: [PATCH 125/192] net/mlx5: Avoid double clear or set of sync reset requested Double clear of reset requested state can lead to NULL pointer as it will try to delete the timer twice. This can happen for example on a race between abort from FW and pci error or reset. Avoid such case using test_and_clear_bit() to verify only one time reset requested state clear flow. Similarly use test_and_set_bit() to verify only one time reset requested state set flow. Fixes: 7dd6df329d4c ("net/mlx5: Handle sync reset abort event") Signed-off-by: Moshe Shemesh Reviewed-by: Maher Sanalla Reviewed-by: Shay Drory Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/fw_reset.c | 28 +++++++++++++------ 1 file changed, 19 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index ec18d4ccbc11..ca1aba845dd6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -162,14 +162,19 @@ static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev) del_timer_sync(&fw_reset->timer); } -static void mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool poll_health) +static int mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool poll_health) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (!test_and_clear_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags)) { + mlx5_core_warn(dev, "Reset request was already cleared\n"); + return -EALREADY; + } + mlx5_stop_sync_reset_poll(dev); - clear_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags); if (poll_health) mlx5_start_health_poll(dev); + return 0; } static void mlx5_sync_reset_reload_work(struct work_struct *work) @@ -229,13 +234,17 @@ static int mlx5_fw_reset_set_reset_sync_nack(struct mlx5_core_dev *dev) return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL3, 0, 2, false); } -static void mlx5_sync_reset_set_reset_requested(struct mlx5_core_dev *dev) +static int mlx5_sync_reset_set_reset_requested(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (test_and_set_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags)) { + mlx5_core_warn(dev, "Reset request was already set\n"); + return -EALREADY; + } mlx5_stop_health_poll(dev, true); - set_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags); mlx5_start_sync_reset_poll(dev); + return 0; } static void mlx5_fw_live_patch_event(struct work_struct *work) @@ -264,7 +273,9 @@ static void mlx5_sync_reset_request_event(struct work_struct *work) err ? "Failed" : "Sent"); return; } - mlx5_sync_reset_set_reset_requested(dev); + if (mlx5_sync_reset_set_reset_requested(dev)) + return; + err = mlx5_fw_reset_set_reset_sync_ack(dev); if (err) mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack Failed. Error code: %d\n", err); @@ -362,7 +373,8 @@ static void mlx5_sync_reset_now_event(struct work_struct *work) struct mlx5_core_dev *dev = fw_reset->dev; int err; - mlx5_sync_reset_clear_reset_requested(dev, false); + if (mlx5_sync_reset_clear_reset_requested(dev, false)) + return; mlx5_core_warn(dev, "Sync Reset now. Device is going to reset.\n"); @@ -391,10 +403,8 @@ static void mlx5_sync_reset_abort_event(struct work_struct *work) reset_abort_work); struct mlx5_core_dev *dev = fw_reset->dev; - if (!test_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags)) + if (mlx5_sync_reset_clear_reset_requested(dev, true)) return; - - mlx5_sync_reset_clear_reset_requested(dev, true); mlx5_core_warn(dev, "PCI Sync FW Update Reset Aborted.\n"); } From a042d7f5bb68c47f6e0e546ca367d14e1e4b25ba Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Sun, 10 Apr 2022 11:58:05 +0000 Subject: [PATCH 126/192] net/mlx5: Fix matching on inner TTC The cited commits didn't use proper matching on inner TTC as a result distribution of encapsulated packets wasn't symmetric between the physical ports. Fixes: 4c71ce50d2fe ("net/mlx5: Support partial TTC rules") Fixes: 8e25a2bc6687 ("net/mlx5: Lag, add support to create TTC tables for LAG port selection") Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c index a6592f9c3c05..5be322528279 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c @@ -505,7 +505,7 @@ static int mlx5_lag_create_inner_ttc_table(struct mlx5_lag *ldev) struct ttc_params ttc_params = {}; mlx5_lag_set_inner_ttc_params(ldev, &ttc_params); - port_sel->inner.ttc = mlx5_create_ttc_table(dev, &ttc_params); + port_sel->inner.ttc = mlx5_create_inner_ttc_table(dev, &ttc_params); if (IS_ERR(port_sel->inner.ttc)) return PTR_ERR(port_sel->inner.ttc); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c index b63dec24747a..b78f2ba25c19 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c @@ -408,6 +408,8 @@ static int mlx5_generate_inner_ttc_table_rules(struct mlx5_core_dev *dev, for (tt = 0; tt < MLX5_NUM_TT; tt++) { struct mlx5_ttc_rule *rule = &rules[tt]; + if (test_bit(tt, params->ignore_dests)) + continue; rule->rule = mlx5_generate_inner_ttc_rule(dev, ft, ¶ms->dests[tt], ttc_rules[tt].etype, From 841e512ffb64898db6322c0619f6bbc41266d86f Mon Sep 17 00:00:00 2001 From: Fabien Parent Date: Tue, 26 Apr 2022 16:15:36 +0200 Subject: [PATCH 127/192] drm/bridge: ite-it6505: add missing Kconfig option select The IT6505 is using functions provided by the DRM_DP_HELPER driver. In order to avoid having the bridge enabled but the helper disabled, let's add a select in order to be sure that the DP helper functions are always available. Fixes: b5c84a9edcd4 ("drm/bridge: add it6505 driver") Signed-off-by: Fabien Parent Reviewed-by: Neil Armstrong Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20220426141536.274727-1-fparent@baylibre.com --- drivers/gpu/drm/bridge/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index 007e5a282f67..2145b08f9534 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -78,6 +78,7 @@ config DRM_ITE_IT6505 tristate "ITE IT6505 DisplayPort bridge" depends on OF select DRM_KMS_HELPER + select DRM_DP_HELPER select EXTCON help ITE IT6505 DisplayPort bridge chip driver. From 2ac2fab52917ae82cbca97cf6e5d2993530257ed Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Mon, 2 May 2022 18:22:38 +0900 Subject: [PATCH 128/192] iommu/dart: Add missing module owner to ops structure This is required to make loading this as a module work. Signed-off-by: Hector Martin Fixes: 46d1fb072e76 ("iommu/dart: Add DART iommu driver") Reviewed-by: Sven Peter Link: https://lore.kernel.org/r/20220502092238.30486-1-marcan@marcan.st Signed-off-by: Joerg Roedel --- drivers/iommu/apple-dart.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c index 15b77f16cfa3..8af0242a90d9 100644 --- a/drivers/iommu/apple-dart.c +++ b/drivers/iommu/apple-dart.c @@ -773,6 +773,7 @@ static const struct iommu_ops apple_dart_iommu_ops = { .get_resv_regions = apple_dart_get_resv_regions, .put_resv_regions = generic_iommu_put_resv_regions, .pgsize_bitmap = -1UL, /* Restricted during dart probe */ + .owner = THIS_MODULE, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = apple_dart_attach_dev, .detach_dev = apple_dart_detach_dev, From e9f3fb523dbf476dc86beea23f5b5ca8f9687c93 Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Sun, 24 Apr 2022 18:17:50 -0500 Subject: [PATCH 129/192] mmc: sunxi-mmc: Fix DMA descriptors allocated above 32 bits Newer variants of the MMC controller support a 34-bit physical address space by using word addresses instead of byte addresses. However, the code truncates the DMA descriptor address to 32 bits before applying the shift. This breaks DMA for descriptors allocated above the 32-bit limit. Fixes: 3536b82e5853 ("mmc: sunxi: add support for A100 mmc controller") Signed-off-by: Samuel Holland Reviewed-by: Andre Przywara Reviewed-by: Jernej Skrabec Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220424231751.32053-1-samuel@sholland.org Signed-off-by: Ulf Hansson --- drivers/mmc/host/sunxi-mmc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c index c62afd212692..46f9e2923d86 100644 --- a/drivers/mmc/host/sunxi-mmc.c +++ b/drivers/mmc/host/sunxi-mmc.c @@ -377,8 +377,9 @@ static void sunxi_mmc_init_idma_des(struct sunxi_mmc_host *host, pdes[i].buf_addr_ptr1 = cpu_to_le32(sg_dma_address(&data->sg[i]) >> host->cfg->idma_des_shift); - pdes[i].buf_addr_ptr2 = cpu_to_le32((u32)next_desc >> - host->cfg->idma_des_shift); + pdes[i].buf_addr_ptr2 = + cpu_to_le32(next_desc >> + host->cfg->idma_des_shift); } pdes[0].config |= cpu_to_le32(SDXC_IDMAC_DES0_FD); From 3e5a8e8494a8122fe4eb3f167662f406cab753b9 Mon Sep 17 00:00:00 2001 From: Shaik Sajida Bhanu Date: Sun, 24 Apr 2022 21:32:33 +0530 Subject: [PATCH 130/192] mmc: sdhci-msm: Reset GCC_SDCC_BCR register for SDHC Reset GCC_SDCC_BCR register before every fresh initilazation. This will reset whole SDHC-msm controller, clears the previous power control states and avoids, software reset timeout issues as below. [ 5.458061][ T262] mmc1: Reset 0x1 never completed. [ 5.462454][ T262] mmc1: sdhci: ============ SDHCI REGISTER DUMP =========== [ 5.469065][ T262] mmc1: sdhci: Sys addr: 0x00000000 | Version: 0x00007202 [ 5.475688][ T262] mmc1: sdhci: Blk size: 0x00000000 | Blk cnt: 0x00000000 [ 5.482315][ T262] mmc1: sdhci: Argument: 0x00000000 | Trn mode: 0x00000000 [ 5.488927][ T262] mmc1: sdhci: Present: 0x01f800f0 | Host ctl: 0x00000000 [ 5.495539][ T262] mmc1: sdhci: Power: 0x00000000 | Blk gap: 0x00000000 [ 5.502162][ T262] mmc1: sdhci: Wake-up: 0x00000000 | Clock: 0x00000003 [ 5.508768][ T262] mmc1: sdhci: Timeout: 0x00000000 | Int stat: 0x00000000 [ 5.515381][ T262] mmc1: sdhci: Int enab: 0x00000000 | Sig enab: 0x00000000 [ 5.521996][ T262] mmc1: sdhci: ACmd stat: 0x00000000 | Slot int: 0x00000000 [ 5.528607][ T262] mmc1: sdhci: Caps: 0x362dc8b2 | Caps_1: 0x0000808f [ 5.535227][ T262] mmc1: sdhci: Cmd: 0x00000000 | Max curr: 0x00000000 [ 5.541841][ T262] mmc1: sdhci: Resp[0]: 0x00000000 | Resp[1]: 0x00000000 [ 5.548454][ T262] mmc1: sdhci: Resp[2]: 0x00000000 | Resp[3]: 0x00000000 [ 5.555079][ T262] mmc1: sdhci: Host ctl2: 0x00000000 [ 5.559651][ T262] mmc1: sdhci_msm: ----------- VENDOR REGISTER DUMP----------- [ 5.566621][ T262] mmc1: sdhci_msm: DLL sts: 0x00000000 | DLL cfg: 0x6000642c | DLL cfg2: 0x0020a000 [ 5.575465][ T262] mmc1: sdhci_msm: DLL cfg3: 0x00000000 | DLL usr ctl: 0x00010800 | DDR cfg: 0x80040873 [ 5.584658][ T262] mmc1: sdhci_msm: Vndr func: 0x00018a9c | Vndr func2 : 0xf88218a8 Vndr func3: 0x02626040 Fixes: 0eb0d9f4de34 ("mmc: sdhci-msm: Initial support for Qualcomm chipsets") Signed-off-by: Shaik Sajida Bhanu Acked-by: Adrian Hunter Reviewed-by: Philipp Zabel Tested-by: Konrad Dybcio Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/1650816153-23797-1-git-send-email-quic_c_sbhanu@quicinc.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-msm.c | 42 ++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index 50c71e0ba5e4..ff9f5b63c337 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "sdhci-pltfm.h" #include "cqhci.h" @@ -2482,6 +2483,43 @@ static inline void sdhci_msm_get_of_property(struct platform_device *pdev, of_property_read_u32(node, "qcom,dll-config", &msm_host->dll_config); } +static int sdhci_msm_gcc_reset(struct device *dev, struct sdhci_host *host) +{ + struct reset_control *reset; + int ret = 0; + + reset = reset_control_get_optional_exclusive(dev, NULL); + if (IS_ERR(reset)) + return dev_err_probe(dev, PTR_ERR(reset), + "unable to acquire core_reset\n"); + + if (!reset) + return ret; + + ret = reset_control_assert(reset); + if (ret) { + reset_control_put(reset); + return dev_err_probe(dev, ret, "core_reset assert failed\n"); + } + + /* + * The hardware requirement for delay between assert/deassert + * is at least 3-4 sleep clock (32.7KHz) cycles, which comes to + * ~125us (4/32768). To be on the safe side add 200us delay. + */ + usleep_range(200, 210); + + ret = reset_control_deassert(reset); + if (ret) { + reset_control_put(reset); + return dev_err_probe(dev, ret, "core_reset deassert failed\n"); + } + + usleep_range(200, 210); + reset_control_put(reset); + + return ret; +} static int sdhci_msm_probe(struct platform_device *pdev) { @@ -2529,6 +2567,10 @@ static int sdhci_msm_probe(struct platform_device *pdev) msm_host->saved_tuning_phase = INVALID_TUNING_PHASE; + ret = sdhci_msm_gcc_reset(&pdev->dev, host); + if (ret) + goto pltfm_free; + /* Setup SDCC bus voter clock. */ msm_host->bus_clk = devm_clk_get(&pdev->dev, "bus"); if (!IS_ERR(msm_host->bus_clk)) { From 57831bfb5e78777dc399e351ed68ef77c3aee385 Mon Sep 17 00:00:00 2001 From: Haren Myneni Date: Sat, 19 Mar 2022 02:28:09 -0700 Subject: [PATCH 131/192] powerpc/pseries/vas: Use QoS credits from the userspace The user can change the QoS credits dynamically with the management console interface which notifies OS with sysfs. After returning from the OS interface successfully, the management console updates the hypervisor. Since the VAS capabilities in the hypervisor is not updated when the OS gets the update, the kernel is using the old total credits value from the hypervisor. Fix this issue by using the new QoS credits from the userspace instead of depending on VAS capabilities from the hypervisor. Signed-off-by: Haren Myneni Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/76d156f8af1e03cc09369d68e0bfad0c40031bcc.camel@linux.ibm.com --- arch/powerpc/platforms/pseries/vas-sysfs.c | 19 +++++++++++++----- arch/powerpc/platforms/pseries/vas.c | 23 +++++++++++----------- arch/powerpc/platforms/pseries/vas.h | 2 +- 3 files changed, 27 insertions(+), 17 deletions(-) diff --git a/arch/powerpc/platforms/pseries/vas-sysfs.c b/arch/powerpc/platforms/pseries/vas-sysfs.c index 909535ca513a..ec65586cbeb3 100644 --- a/arch/powerpc/platforms/pseries/vas-sysfs.c +++ b/arch/powerpc/platforms/pseries/vas-sysfs.c @@ -27,22 +27,31 @@ struct vas_caps_entry { /* * This function is used to get the notification from the drmgr when - * QoS credits are changed. Though receiving the target total QoS - * credits here, get the official QoS capabilities from the hypervisor. + * QoS credits are changed. */ -static ssize_t update_total_credits_trigger(struct vas_cop_feat_caps *caps, +static ssize_t update_total_credits_store(struct vas_cop_feat_caps *caps, const char *buf, size_t count) { int err; u16 creds; err = kstrtou16(buf, 0, &creds); + /* + * The user space interface from the management console + * notifies OS with the new QoS credits and then the + * hypervisor. So OS has to use this new credits value + * and reconfigure VAS windows (close or reopen depends + * on the credits available) instead of depending on VAS + * QoS capabilities from the hypervisor. + */ if (!err) - err = vas_reconfig_capabilties(caps->win_type); + err = vas_reconfig_capabilties(caps->win_type, creds); if (err) return -EINVAL; + pr_info("Set QoS total credits %u\n", creds); + return count; } @@ -92,7 +101,7 @@ VAS_ATTR_RO(nr_total_credits); VAS_ATTR_RO(nr_used_credits); static struct vas_sysfs_entry update_total_credits_attribute = - __ATTR(update_total_credits, 0200, NULL, update_total_credits_trigger); + __ATTR(update_total_credits, 0200, NULL, update_total_credits_store); static struct attribute *vas_def_capab_attrs[] = { &nr_total_credits_attribute.attr, diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index 1f59d78c77a1..ec643bbdb67f 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -779,10 +779,10 @@ static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds, * changes. Reconfig window configurations based on the credits * availability from this new capabilities. */ -int vas_reconfig_capabilties(u8 type) +int vas_reconfig_capabilties(u8 type, int new_nr_creds) { struct vas_cop_feat_caps *caps; - int old_nr_creds, new_nr_creds; + int old_nr_creds; struct vas_caps *vcaps; int rc = 0, nr_active_wins; @@ -795,12 +795,6 @@ int vas_reconfig_capabilties(u8 type) caps = &vcaps->caps; mutex_lock(&vas_pseries_mutex); - rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, vcaps->feat, - (u64)virt_to_phys(&hv_cop_caps)); - if (rc) - goto out; - - new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds); old_nr_creds = atomic_read(&caps->nr_total_credits); @@ -832,7 +826,6 @@ int vas_reconfig_capabilties(u8 type) false); } -out: mutex_unlock(&vas_pseries_mutex); return rc; } @@ -850,7 +843,7 @@ static int pseries_vas_notifier(struct notifier_block *nb, struct of_reconfig_data *rd = data; struct device_node *dn = rd->dn; const __be32 *intserv = NULL; - int len, rc = 0; + int new_nr_creds, len, rc = 0; if ((action == OF_RECONFIG_ATTACH_NODE) || (action == OF_RECONFIG_DETACH_NODE)) @@ -862,7 +855,15 @@ static int pseries_vas_notifier(struct notifier_block *nb, if (!intserv) return NOTIFY_OK; - rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE); + rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, + vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat, + (u64)virt_to_phys(&hv_cop_caps)); + if (!rc) { + new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds); + rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE, + new_nr_creds); + } + if (rc) pr_err("Failed reconfig VAS capabilities with DLPAR\n"); diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h index 34177881e998..333ffa2f9f42 100644 --- a/arch/powerpc/platforms/pseries/vas.h +++ b/arch/powerpc/platforms/pseries/vas.h @@ -135,7 +135,7 @@ struct pseries_vas_window { }; int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps); -int vas_reconfig_capabilties(u8 type); +int vas_reconfig_capabilties(u8 type, int new_nr_creds); int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps); #ifdef CONFIG_PPC_VAS From 6d65028eb67dbb7627651adfc460d64196d38bd8 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 2 May 2022 22:50:10 +1000 Subject: [PATCH 132/192] powerpc/vdso: Fix incorrect CFI in gettimeofday.S As reported by Alan, the CFI (Call Frame Information) in the VDSO time routines is incorrect since commit ce7d8056e38b ("powerpc/vdso: Prepare for switching VDSO to generic C implementation."). DWARF has a concept called the CFA (Canonical Frame Address), which on powerpc is calculated as an offset from the stack pointer (r1). That means when the stack pointer is changed there must be a corresponding CFI directive to update the calculation of the CFA. The current code is missing those directives for the changes to r1, which prevents gdb from being able to generate a backtrace from inside VDSO functions, eg: Breakpoint 1, 0x00007ffff7f804dc in __kernel_clock_gettime () (gdb) bt #0 0x00007ffff7f804dc in __kernel_clock_gettime () #1 0x00007ffff7d8872c in clock_gettime@@GLIBC_2.17 () from /lib64/libc.so.6 #2 0x00007fffffffd960 in ?? () #3 0x00007ffff7d8872c in clock_gettime@@GLIBC_2.17 () from /lib64/libc.so.6 Backtrace stopped: frame did not save the PC Alan helpfully describes some rules for correctly maintaining the CFI information: 1) Every adjustment to the current frame address reg (ie. r1) must be described, and exactly at the instruction where r1 changes. Why? Because stack unwinding might want to access previous frames. 2) If a function changes LR or any non-volatile register, the save location for those regs must be given. The CFI can be at any instruction after the saves up to the point that the reg is changed. (Exception: LR save should be described before a bl. not after) 3) If asychronous unwind info is needed then restores of LR and non-volatile regs must also be described. The CFI can be at any instruction after the reg is restored up to the point where the save location is (potentially) trashed. Fix the inability to backtrace by adding CFI directives describing the changes to r1, ie. satisfying rule 1. Also change the information for LR to point to the copy saved on the stack, not the value in r0 that will be overwritten by the function call. Finally, add CFI directives describing the save/restore of r2. With the fix gdb can correctly back trace and navigate up and down the stack: Breakpoint 1, 0x00007ffff7f804dc in __kernel_clock_gettime () (gdb) bt #0 0x00007ffff7f804dc in __kernel_clock_gettime () #1 0x00007ffff7d8872c in clock_gettime@@GLIBC_2.17 () from /lib64/libc.so.6 #2 0x0000000100015b60 in gettime () #3 0x000000010000c8bc in print_long_format () #4 0x000000010000d180 in print_current_files () #5 0x00000001000054ac in main () (gdb) up #1 0x00007ffff7d8872c in clock_gettime@@GLIBC_2.17 () from /lib64/libc.so.6 (gdb) #2 0x0000000100015b60 in gettime () (gdb) #3 0x000000010000c8bc in print_long_format () (gdb) #4 0x000000010000d180 in print_current_files () (gdb) #5 0x00000001000054ac in main () (gdb) Initial frame selected; you cannot go up. (gdb) down #4 0x000000010000d180 in print_current_files () (gdb) #3 0x000000010000c8bc in print_long_format () (gdb) #2 0x0000000100015b60 in gettime () (gdb) #1 0x00007ffff7d8872c in clock_gettime@@GLIBC_2.17 () from /lib64/libc.so.6 (gdb) #0 0x00007ffff7f804dc in __kernel_clock_gettime () (gdb) Fixes: ce7d8056e38b ("powerpc/vdso: Prepare for switching VDSO to generic C implementation.") Cc: stable@vger.kernel.org # v5.11+ Reported-by: Alan Modra Signed-off-by: Michael Ellerman Reviewed-by: Segher Boessenkool Link: https://lore.kernel.org/r/20220502125010.1319370-1-mpe@ellerman.id.au --- arch/powerpc/kernel/vdso/gettimeofday.S | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S index eb9c81e1c218..0c4ecc8fec5a 100644 --- a/arch/powerpc/kernel/vdso/gettimeofday.S +++ b/arch/powerpc/kernel/vdso/gettimeofday.S @@ -22,12 +22,15 @@ .macro cvdso_call funct call_time=0 .cfi_startproc PPC_STLU r1, -PPC_MIN_STKFRM(r1) + .cfi_adjust_cfa_offset PPC_MIN_STKFRM mflr r0 - .cfi_register lr, r0 PPC_STLU r1, -PPC_MIN_STKFRM(r1) + .cfi_adjust_cfa_offset PPC_MIN_STKFRM PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) + .cfi_rel_offset lr, PPC_MIN_STKFRM + PPC_LR_STKOFF #ifdef __powerpc64__ PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1) + .cfi_rel_offset r2, PPC_MIN_STKFRM + STK_GOT #endif get_datapage r5 .ifeq \call_time @@ -39,13 +42,15 @@ PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) #ifdef __powerpc64__ PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1) + .cfi_restore r2 #endif .ifeq \call_time cmpwi r3, 0 .endif mtlr r0 - .cfi_restore lr addi r1, r1, 2 * PPC_MIN_STKFRM + .cfi_restore lr + .cfi_def_cfa_offset 0 crclr so .ifeq \call_time beqlr+ From 392bf51946c2463436a1ba237c1ec5865b234825 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 4 May 2022 13:39:58 +0100 Subject: [PATCH 133/192] iommu: Make sysfs robust for non-API groups Groups created by VFIO backends outside the core IOMMU API should never be passed directly into the API itself, however they still expose their standard sysfs attributes, so we can still stumble across them that way. Take care to consider those cases before jumping into our normal assumptions of a fully-initialised core API group. Fixes: 3f6634d997db ("iommu: Use right way to retrieve iommu_ops") Reported-by: Jan Stancek Tested-by: Jan Stancek Reviewed-by: Jason Gunthorpe Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/86ada41986988511a8424e84746dfe9ba7f87573.1651667683.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index f2c45b85b9fc..857d4c2fd1a2 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -506,6 +506,13 @@ int iommu_get_group_resv_regions(struct iommu_group *group, list_for_each_entry(device, &group->devices, list) { struct list_head dev_resv_regions; + /* + * Non-API groups still expose reserved_regions in sysfs, + * so filter out calls that get here that way. + */ + if (!device->dev->iommu) + break; + INIT_LIST_HEAD(&dev_resv_regions); iommu_get_resv_regions(device->dev, &dev_resv_regions); ret = iommu_insert_device_resv_regions(&dev_resv_regions, head); @@ -3019,7 +3026,7 @@ static ssize_t iommu_group_store_type(struct iommu_group *group, if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) return -EACCES; - if (WARN_ON(!group)) + if (WARN_ON(!group) || !group->default_domain) return -EINVAL; if (sysfs_streq(buf, "identity")) From 19965d8259fdabc6806da92adda49684f5bcbec5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Marczykowski-G=C3=B3recki?= Date: Wed, 27 Apr 2022 01:57:15 +0200 Subject: [PATCH 134/192] drm/amdgpu: do not use passthrough mode in Xen dom0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While technically Xen dom0 is a virtual machine too, it does have access to most of the hardware so it doesn't need to be considered a "passthrough". Commit b818a5d37454 ("drm/amdgpu/gmc: use PCI BARs for APUs in passthrough") changed how FB is accessed based on passthrough mode. This breaks amdgpu in Xen dom0 with message like this: [drm:dc_dmub_srv_wait_idle [amdgpu]] *ERROR* Error waiting for DMUB idle: status=3 While the reason for this failure is unclear, the passthrough mode is not really necessary in Xen dom0 anyway. So, to unbreak booting affected kernels, disable passthrough mode in this case. Link: https://gitlab.freedesktop.org/drm/amd/-/issues/1985 Fixes: b818a5d37454 ("drm/amdgpu/gmc: use PCI BARs for APUs in passthrough") Signed-off-by: Marek Marczykowski-Górecki Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index a025f080aa6a..5e3756643da3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -24,6 +24,7 @@ #include #include +#include #include "amdgpu.h" #include "amdgpu_ras.h" @@ -710,7 +711,8 @@ void amdgpu_detect_virtualization(struct amdgpu_device *adev) adev->virt.caps |= AMDGPU_SRIOV_CAPS_ENABLE_IOV; if (!reg) { - if (is_virtual_machine()) /* passthrough mode exclus sriov mod */ + /* passthrough mode exclus sriov mod */ + if (is_virtual_machine() && !xen_initial_domain()) adev->virt.caps |= AMDGPU_PASSTHROUGH_MODE; } From 3dfe85fa87b2a26bdbd292b66653bba065cf9941 Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Tue, 19 Apr 2022 13:03:12 -0400 Subject: [PATCH 135/192] drm/amd/display: Avoid reading audio pattern past AUDIO_CHANNELS_COUNT A faulty receiver might report an erroneous channel count. We should guard against reading beyond AUDIO_CHANNELS_COUNT as that would overflow the dpcd_pattern_period array. Signed-off-by: Harry Wentland Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 22dabe596dfc..95b5b5bfa1ff 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -4440,7 +4440,7 @@ static void dp_test_get_audio_test_data(struct dc_link *link, bool disable_video &dpcd_pattern_type.value, sizeof(dpcd_pattern_type)); - channel_count = dpcd_test_mode.bits.channel_count + 1; + channel_count = min(dpcd_test_mode.bits.channel_count + 1, AUDIO_CHANNELS_COUNT); // read pattern periods for requested channels when sawTooth pattern is requested if (dpcd_pattern_type.value == AUDIO_TEST_PATTERN_SAWTOOTH || From 770fb0942c338545f93a584342b64848cff31efe Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 4 May 2022 11:07:45 -0700 Subject: [PATCH 136/192] MAINTAINERS: Update Josh Poimboeuf's email address Change to my kernel.org email address. Signed-off-by: Josh Poimboeuf Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/1abc3de4b00dc6f915ac975a2ec29ed545d96dc4.1651687652.git.jpoimboe@redhat.com --- MAINTAINERS | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index edc96cdb85e8..1e1a2264792d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7499,7 +7499,7 @@ F: Documentation/hwmon/f71805f.rst F: drivers/hwmon/f71805f.c FADDR2LINE -M: Josh Poimboeuf +M: Josh Poimboeuf S: Maintained F: scripts/faddr2line @@ -11348,7 +11348,7 @@ F: drivers/mmc/host/litex_mmc.c N: litex LIVE PATCHING -M: Josh Poimboeuf +M: Josh Poimboeuf M: Jiri Kosina M: Miroslav Benes M: Petr Mladek @@ -14224,7 +14224,7 @@ F: lib/objagg.c F: lib/test_objagg.c OBJTOOL -M: Josh Poimboeuf +M: Josh Poimboeuf M: Peter Zijlstra S: Supported F: tools/objtool/ @@ -18792,7 +18792,7 @@ F: include/dt-bindings/reset/starfive-jh7100.h STATIC BRANCH/CALL M: Peter Zijlstra -M: Josh Poimboeuf +M: Josh Poimboeuf M: Jason Baron R: Steven Rostedt R: Ard Biesheuvel @@ -21444,7 +21444,7 @@ F: arch/x86/kernel/apic/x2apic_uv_x.c F: arch/x86/platform/uv/ X86 STACK UNWINDING -M: Josh Poimboeuf +M: Josh Poimboeuf M: Peter Zijlstra S: Supported F: arch/x86/include/asm/unwind*.h From b2b701b31e1c5827957c88e5c1f0c3dde1f55b2f Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 29 Apr 2022 14:46:11 -0500 Subject: [PATCH 137/192] dt-bindings: pinctrl: Allow values for drive-push-pull and drive-open-drain A few platforms, at91 and tegra, use drive-push-pull and drive-open-drain with a 0 or 1 value. There's not really a need for values as '1' should be equivalent to no value (it wasn't treated that way) and drive-push-pull disabled is equivalent to drive-open-drain. So dropping the value can't be done without breaking existing OSs. As we don't want new cases, mark the case with values as deprecated. Cc: Arnd Bergmann Cc: Thierry Reding Cc: Jonathan Hunter Cc: Nicolas Ferre Cc: Claudiu Beznea Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20220429194610.2741437-1-robh@kernel.org --- .../devicetree/bindings/pinctrl/pincfg-node.yaml | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/pincfg-node.yaml b/Documentation/devicetree/bindings/pinctrl/pincfg-node.yaml index 4b22a9e3a447..f5a121311f61 100644 --- a/Documentation/devicetree/bindings/pinctrl/pincfg-node.yaml +++ b/Documentation/devicetree/bindings/pinctrl/pincfg-node.yaml @@ -52,11 +52,19 @@ properties: hardware supporting it the pull strength in Ohm. drive-push-pull: - type: boolean + oneOf: + - type: boolean + - $ref: /schemas/types.yaml#/definitions/uint32 + enum: [ 0, 1 ] + deprecated: true description: drive actively high and low drive-open-drain: - type: boolean + oneOf: + - type: boolean + - $ref: /schemas/types.yaml#/definitions/uint32 + const: 1 # No known cases of 0 + deprecated: true description: drive with open drain drive-open-source: From caf83e494de965dbb5f8add655c526b9af6a96cb Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 3 May 2022 11:27:38 -0500 Subject: [PATCH 138/192] dt-bindings: Drop redundant 'maxItems/minItems' in if/then schemas Another round of removing redundant minItems/maxItems when 'items' list is specified. This time it is in if/then schemas as the meta-schema was failing to check this case. If a property has an 'items' list, then a 'minItems' or 'maxItems' with the same size as the list is redundant and can be dropped. Note that is DT schema specific behavior and not standard json-schema behavior. The tooling will fixup the final schema adding any unspecified minItems/maxItems. Signed-off-by: Rob Herring Acked-By: Vinod Koul Acked-by: Marc Kleine-Budde Acked-by: Mark Brown Acked-by: Ulf Hansson # For MMC Acked-by: Jonathan Cameron #for IIO Link: https://lore.kernel.org/r/20220503162738.3827041-1-robh@kernel.org --- .../bindings/clock/imx8m-clock.yaml | 4 ---- .../bindings/display/bridge/renesas,lvds.yaml | 4 ---- .../bindings/display/renesas,du.yaml | 23 ------------------- .../bindings/iio/adc/st,stm32-adc.yaml | 2 -- .../bindings/mmc/nvidia,tegra20-sdhci.yaml | 7 +----- .../devicetree/bindings/mtd/gpmi-nand.yaml | 2 -- .../bindings/net/can/bosch,c_can.yaml | 3 --- .../bindings/phy/brcm,sata-phy.yaml | 10 ++++---- .../bindings/rtc/allwinner,sun6i-a31-rtc.yaml | 10 -------- .../bindings/serial/samsung_uart.yaml | 4 ---- .../sound/allwinner,sun4i-a10-i2s.yaml | 1 - .../bindings/sound/ti,j721e-cpb-audio.yaml | 2 -- .../bindings/thermal/rcar-gen3-thermal.yaml | 1 - 13 files changed, 5 insertions(+), 68 deletions(-) diff --git a/Documentation/devicetree/bindings/clock/imx8m-clock.yaml b/Documentation/devicetree/bindings/clock/imx8m-clock.yaml index 625f573a7b90..458c7645ee68 100644 --- a/Documentation/devicetree/bindings/clock/imx8m-clock.yaml +++ b/Documentation/devicetree/bindings/clock/imx8m-clock.yaml @@ -55,8 +55,6 @@ allOf: then: properties: clocks: - minItems: 7 - maxItems: 7 items: - description: 32k osc - description: 25m osc @@ -66,8 +64,6 @@ allOf: - description: ext3 clock input - description: ext4 clock input clock-names: - minItems: 7 - maxItems: 7 items: - const: ckil - const: osc_25m diff --git a/Documentation/devicetree/bindings/display/bridge/renesas,lvds.yaml b/Documentation/devicetree/bindings/display/bridge/renesas,lvds.yaml index a51baf8a4c76..bb9dbfb9beaf 100644 --- a/Documentation/devicetree/bindings/display/bridge/renesas,lvds.yaml +++ b/Documentation/devicetree/bindings/display/bridge/renesas,lvds.yaml @@ -95,7 +95,6 @@ then: properties: clocks: minItems: 1 - maxItems: 4 items: - description: Functional clock - description: EXTAL input clock @@ -104,7 +103,6 @@ then: clock-names: minItems: 1 - maxItems: 4 items: - const: fck # The LVDS encoder can use the EXTAL or DU_DOTCLKINx clocks. @@ -128,12 +126,10 @@ then: else: properties: clocks: - maxItems: 1 items: - description: Functional clock clock-names: - maxItems: 1 items: - const: fck diff --git a/Documentation/devicetree/bindings/display/renesas,du.yaml b/Documentation/devicetree/bindings/display/renesas,du.yaml index 56cedcd6d576..b3e588022082 100644 --- a/Documentation/devicetree/bindings/display/renesas,du.yaml +++ b/Documentation/devicetree/bindings/display/renesas,du.yaml @@ -109,7 +109,6 @@ allOf: properties: clocks: minItems: 1 - maxItems: 3 items: - description: Functional clock - description: DU_DOTCLKIN0 input clock @@ -117,7 +116,6 @@ allOf: clock-names: minItems: 1 - maxItems: 3 items: - const: du.0 - pattern: '^dclkin\.[01]$' @@ -159,7 +157,6 @@ allOf: properties: clocks: minItems: 2 - maxItems: 4 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -168,7 +165,6 @@ allOf: clock-names: minItems: 2 - maxItems: 4 items: - const: du.0 - const: du.1 @@ -216,7 +212,6 @@ allOf: properties: clocks: minItems: 2 - maxItems: 4 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -225,7 +220,6 @@ allOf: clock-names: minItems: 2 - maxItems: 4 items: - const: du.0 - const: du.1 @@ -271,7 +265,6 @@ allOf: properties: clocks: minItems: 2 - maxItems: 4 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -280,7 +273,6 @@ allOf: clock-names: minItems: 2 - maxItems: 4 items: - const: du.0 - const: du.1 @@ -327,7 +319,6 @@ allOf: properties: clocks: minItems: 2 - maxItems: 4 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -336,7 +327,6 @@ allOf: clock-names: minItems: 2 - maxItems: 4 items: - const: du.0 - const: du.1 @@ -386,7 +376,6 @@ allOf: properties: clocks: minItems: 3 - maxItems: 6 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -397,7 +386,6 @@ allOf: clock-names: minItems: 3 - maxItems: 6 items: - const: du.0 - const: du.1 @@ -448,7 +436,6 @@ allOf: properties: clocks: minItems: 4 - maxItems: 8 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -461,7 +448,6 @@ allOf: clock-names: minItems: 4 - maxItems: 8 items: - const: du.0 - const: du.1 @@ -525,7 +511,6 @@ allOf: properties: clocks: minItems: 3 - maxItems: 6 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -536,7 +521,6 @@ allOf: clock-names: minItems: 3 - maxItems: 6 items: - const: du.0 - const: du.1 @@ -596,7 +580,6 @@ allOf: properties: clocks: minItems: 3 - maxItems: 6 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -607,7 +590,6 @@ allOf: clock-names: minItems: 3 - maxItems: 6 items: - const: du.0 - const: du.1 @@ -666,14 +648,12 @@ allOf: properties: clocks: minItems: 1 - maxItems: 2 items: - description: Functional clock for DU0 - description: DU_DOTCLKIN0 input clock clock-names: minItems: 1 - maxItems: 2 items: - const: du.0 - const: dclkin.0 @@ -723,7 +703,6 @@ allOf: properties: clocks: minItems: 2 - maxItems: 4 items: - description: Functional clock for DU0 - description: Functional clock for DU1 @@ -732,7 +711,6 @@ allOf: clock-names: minItems: 2 - maxItems: 4 items: - const: du.0 - const: du.1 @@ -791,7 +769,6 @@ allOf: - description: Functional clock clock-names: - maxItems: 1 items: - const: du.0 diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml index 4d6074518b5c..fa8da42cb1e6 100644 --- a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml @@ -138,7 +138,6 @@ allOf: - const: bus - const: adc minItems: 1 - maxItems: 2 interrupts: items: @@ -170,7 +169,6 @@ allOf: - const: bus - const: adc minItems: 1 - maxItems: 2 interrupts: items: diff --git a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml index f3f4d5b02744..fe0270207622 100644 --- a/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml +++ b/Documentation/devicetree/bindings/mmc/nvidia,tegra20-sdhci.yaml @@ -202,22 +202,17 @@ allOf: clocks: items: - description: module clock - minItems: 1 - maxItems: 1 else: properties: clocks: items: - description: module clock - description: timeout clock - minItems: 2 - maxItems: 2 + clock-names: items: - const: sdhci - const: tmclk - minItems: 2 - maxItems: 2 required: - clock-names diff --git a/Documentation/devicetree/bindings/mtd/gpmi-nand.yaml b/Documentation/devicetree/bindings/mtd/gpmi-nand.yaml index 9d764e654e1d..849aeae319a9 100644 --- a/Documentation/devicetree/bindings/mtd/gpmi-nand.yaml +++ b/Documentation/devicetree/bindings/mtd/gpmi-nand.yaml @@ -147,8 +147,6 @@ allOf: - description: SoC gpmi io clock - description: SoC gpmi bch apb clock clock-names: - minItems: 2 - maxItems: 2 items: - const: gpmi_io - const: gpmi_bch_apb diff --git a/Documentation/devicetree/bindings/net/can/bosch,c_can.yaml b/Documentation/devicetree/bindings/net/can/bosch,c_can.yaml index 8bad328b184d..51aa89ac7e85 100644 --- a/Documentation/devicetree/bindings/net/can/bosch,c_can.yaml +++ b/Documentation/devicetree/bindings/net/can/bosch,c_can.yaml @@ -80,8 +80,6 @@ if: then: properties: interrupts: - minItems: 4 - maxItems: 4 items: - description: Error and status IRQ - description: Message object IRQ @@ -91,7 +89,6 @@ then: else: properties: interrupts: - maxItems: 1 items: - description: Error and status IRQ diff --git a/Documentation/devicetree/bindings/phy/brcm,sata-phy.yaml b/Documentation/devicetree/bindings/phy/brcm,sata-phy.yaml index cb1aa325336f..435b971dfd9b 100644 --- a/Documentation/devicetree/bindings/phy/brcm,sata-phy.yaml +++ b/Documentation/devicetree/bindings/phy/brcm,sata-phy.yaml @@ -102,19 +102,17 @@ if: then: properties: reg: - maxItems: 2 + minItems: 2 + reg-names: - items: - - const: "phy" - - const: "phy-ctrl" + minItems: 2 else: properties: reg: maxItems: 1 + reg-names: maxItems: 1 - items: - - const: "phy" required: - compatible diff --git a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml index 0b767fec39d8..6b38bd7eb3b4 100644 --- a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml @@ -71,7 +71,6 @@ allOf: then: properties: clock-output-names: - minItems: 1 maxItems: 1 - if: @@ -102,7 +101,6 @@ allOf: properties: clock-output-names: minItems: 3 - maxItems: 3 - if: properties: @@ -113,16 +111,12 @@ allOf: then: properties: clocks: - minItems: 3 - maxItems: 3 items: - description: Bus clock for register access - description: 24 MHz oscillator - description: 32 kHz clock from the CCU clock-names: - minItems: 3 - maxItems: 3 items: - const: bus - const: hosc @@ -142,7 +136,6 @@ allOf: properties: clocks: minItems: 3 - maxItems: 4 items: - description: Bus clock for register access - description: 24 MHz oscillator @@ -151,7 +144,6 @@ allOf: clock-names: minItems: 3 - maxItems: 4 items: - const: bus - const: hosc @@ -174,14 +166,12 @@ allOf: then: properties: interrupts: - minItems: 1 maxItems: 1 else: properties: interrupts: minItems: 2 - maxItems: 2 required: - "#clock-cells" diff --git a/Documentation/devicetree/bindings/serial/samsung_uart.yaml b/Documentation/devicetree/bindings/serial/samsung_uart.yaml index d4688e317fc5..901c1e2cea28 100644 --- a/Documentation/devicetree/bindings/serial/samsung_uart.yaml +++ b/Documentation/devicetree/bindings/serial/samsung_uart.yaml @@ -100,7 +100,6 @@ allOf: maxItems: 3 clock-names: minItems: 2 - maxItems: 3 items: - const: uart - pattern: '^clk_uart_baud[0-1]$' @@ -118,11 +117,8 @@ allOf: then: properties: clocks: - minItems: 2 maxItems: 2 clock-names: - minItems: 2 - maxItems: 2 items: - const: uart - const: clk_uart_baud0 diff --git a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-i2s.yaml b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-i2s.yaml index c21c807b667c..34f6ee9de392 100644 --- a/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-i2s.yaml +++ b/Documentation/devicetree/bindings/sound/allwinner,sun4i-a10-i2s.yaml @@ -89,7 +89,6 @@ allOf: properties: dmas: minItems: 1 - maxItems: 2 items: - description: RX DMA Channel - description: TX DMA Channel diff --git a/Documentation/devicetree/bindings/sound/ti,j721e-cpb-audio.yaml b/Documentation/devicetree/bindings/sound/ti,j721e-cpb-audio.yaml index 6806f53a4aed..20ea5883b7ff 100644 --- a/Documentation/devicetree/bindings/sound/ti,j721e-cpb-audio.yaml +++ b/Documentation/devicetree/bindings/sound/ti,j721e-cpb-audio.yaml @@ -80,7 +80,6 @@ allOf: then: properties: clocks: - minItems: 6 items: - description: AUXCLK clock for McASP used by CPB audio - description: Parent for CPB_McASP auxclk (for 48KHz) @@ -107,7 +106,6 @@ allOf: then: properties: clocks: - maxItems: 4 items: - description: AUXCLK clock for McASP used by CPB audio - description: Parent for CPB_McASP auxclk (for 48KHz) diff --git a/Documentation/devicetree/bindings/thermal/rcar-gen3-thermal.yaml b/Documentation/devicetree/bindings/thermal/rcar-gen3-thermal.yaml index f963204e0b16..1368d90da0e8 100644 --- a/Documentation/devicetree/bindings/thermal/rcar-gen3-thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/rcar-gen3-thermal.yaml @@ -67,7 +67,6 @@ then: properties: reg: minItems: 2 - maxItems: 3 items: - description: TSC1 registers - description: TSC2 registers From 5dc4630426511f641b7ac44fc550b8e21eafb237 Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Mon, 2 May 2022 18:13:08 +0900 Subject: [PATCH 139/192] dt-bindings: pci: apple,pcie: Drop max-link-speed from example We no longer use these since 111659c2a570 (and they never worked anyway); drop them from the example to avoid confusion. Fixes: 111659c2a570 ("arm64: dts: apple: t8103: Remove PCIe max-link-speed properties") Signed-off-by: Hector Martin Reviewed-by: Alyssa Rosenzweig Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20220502091308.28233-1-marcan@marcan.st --- Documentation/devicetree/bindings/pci/apple,pcie.yaml | 3 --- 1 file changed, 3 deletions(-) diff --git a/Documentation/devicetree/bindings/pci/apple,pcie.yaml b/Documentation/devicetree/bindings/pci/apple,pcie.yaml index 7f01e15fc81c..daf602ac0d0f 100644 --- a/Documentation/devicetree/bindings/pci/apple,pcie.yaml +++ b/Documentation/devicetree/bindings/pci/apple,pcie.yaml @@ -142,7 +142,6 @@ examples: device_type = "pci"; reg = <0x0 0x0 0x0 0x0 0x0>; reset-gpios = <&pinctrl_ap 152 0>; - max-link-speed = <2>; #address-cells = <3>; #size-cells = <2>; @@ -153,7 +152,6 @@ examples: device_type = "pci"; reg = <0x800 0x0 0x0 0x0 0x0>; reset-gpios = <&pinctrl_ap 153 0>; - max-link-speed = <2>; #address-cells = <3>; #size-cells = <2>; @@ -164,7 +162,6 @@ examples: device_type = "pci"; reg = <0x1000 0x0 0x0 0x0 0x0>; reset-gpios = <&pinctrl_ap 33 0>; - max-link-speed = <1>; #address-cells = <3>; #size-cells = <2>; From ef91271c65c12d36e4c2b61c61d4849fb6d11aa0 Mon Sep 17 00:00:00 2001 From: Cheng Xu Date: Sun, 24 Apr 2022 16:01:03 +0800 Subject: [PATCH 140/192] RDMA/siw: Fix a condition race issue in MPA request processing The calling of siw_cm_upcall and detaching new_cep with its listen_cep should be atomistic semantics. Otherwise siw_reject may be called in a temporary state, e,g, siw_cm_upcall is called but the new_cep->listen_cep has not being cleared. This fixes a WARN: WARNING: CPU: 7 PID: 201 at drivers/infiniband/sw/siw/siw_cm.c:255 siw_cep_put+0x125/0x130 [siw] CPU: 2 PID: 201 Comm: kworker/u16:22 Kdump: loaded Tainted: G E 5.17.0-rc7 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Workqueue: iw_cm_wq cm_work_handler [iw_cm] RIP: 0010:siw_cep_put+0x125/0x130 [siw] Call Trace: siw_reject+0xac/0x180 [siw] iw_cm_reject+0x68/0xc0 [iw_cm] cm_work_handler+0x59d/0xe20 [iw_cm] process_one_work+0x1e2/0x3b0 worker_thread+0x50/0x3a0 ? rescuer_thread+0x390/0x390 kthread+0xe5/0x110 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30 Fixes: 6c52fdc244b5 ("rdma/siw: connection management") Link: https://lore.kernel.org/r/d528d83466c44687f3872eadcb8c184528b2e2d4.1650526554.git.chengyou@linux.alibaba.com Reported-by: Luis Chamberlain Reviewed-by: Bernard Metzler Signed-off-by: Cheng Xu Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/siw/siw_cm.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index 7acdd3c3a599..17f34d584cd9 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -968,14 +968,15 @@ static void siw_accept_newconn(struct siw_cep *cep) siw_cep_set_inuse(new_cep); rv = siw_proc_mpareq(new_cep); - siw_cep_set_free(new_cep); - if (rv != -EAGAIN) { siw_cep_put(cep); new_cep->listen_cep = NULL; - if (rv) + if (rv) { + siw_cep_set_free(new_cep); goto error; + } } + siw_cep_set_free(new_cep); } return; From a926a903b7dc39a8a949150258c09290998dd812 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Wed, 4 May 2022 15:28:17 -0500 Subject: [PATCH 141/192] RDMA/rxe: Do not call dev_mc_add/del() under a spinlock These routines were not intended to be called under a spinlock and will throw debugging warnings: raw_local_irq_restore() called with IRQs enabled WARNING: CPU: 13 PID: 3107 at kernel/locking/irqflag-debug.c:10 warn_bogus_irq_restore+0x2f/0x50 CPU: 13 PID: 3107 Comm: python3 Tainted: G E 5.18.0-rc1+ #7 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 RIP: 0010:warn_bogus_irq_restore+0x2f/0x50 Call Trace: _raw_spin_unlock_irqrestore+0x75/0x80 rxe_attach_mcast+0x304/0x480 [rdma_rxe] ib_attach_mcast+0x88/0xa0 [ib_core] ib_uverbs_attach_mcast+0x186/0x1e0 [ib_uverbs] ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0xcd/0x140 [ib_uverbs] ib_uverbs_cmd_verbs+0xdb0/0xea0 [ib_uverbs] ib_uverbs_ioctl+0xd2/0x160 [ib_uverbs] do_syscall_64+0x5c/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae Move them out of the spinlock, it is OK if there is some races setting up the MC reception at the ethernet layer with rbtree lookups. Fixes: 6090a0c4c7c6 ("RDMA/rxe: Cleanup rxe_mcast.c") Link: https://lore.kernel.org/r/20220504202817.98247-1-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_mcast.c | 51 ++++++++++++--------------- 1 file changed, 23 insertions(+), 28 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_mcast.c b/drivers/infiniband/sw/rxe/rxe_mcast.c index ae8f11cb704a..77e45cabd8ea 100644 --- a/drivers/infiniband/sw/rxe/rxe_mcast.c +++ b/drivers/infiniband/sw/rxe/rxe_mcast.c @@ -38,13 +38,13 @@ static int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid) } /** - * rxe_mcast_delete - delete multicast address from rxe device + * rxe_mcast_del - delete multicast address from rxe device * @rxe: rxe device object * @mgid: multicast address as a gid * * Returns 0 on success else an error */ -static int rxe_mcast_delete(struct rxe_dev *rxe, union ib_gid *mgid) +static int rxe_mcast_del(struct rxe_dev *rxe, union ib_gid *mgid) { unsigned char ll_addr[ETH_ALEN]; @@ -159,17 +159,10 @@ struct rxe_mcg *rxe_lookup_mcg(struct rxe_dev *rxe, union ib_gid *mgid) * @mcg: new mcg object * * Context: caller should hold rxe->mcg lock - * Returns: 0 on success else an error */ -static int __rxe_init_mcg(struct rxe_dev *rxe, union ib_gid *mgid, - struct rxe_mcg *mcg) +static void __rxe_init_mcg(struct rxe_dev *rxe, union ib_gid *mgid, + struct rxe_mcg *mcg) { - int err; - - err = rxe_mcast_add(rxe, mgid); - if (unlikely(err)) - return err; - kref_init(&mcg->ref_cnt); memcpy(&mcg->mgid, mgid, sizeof(mcg->mgid)); INIT_LIST_HEAD(&mcg->qp_list); @@ -184,8 +177,6 @@ static int __rxe_init_mcg(struct rxe_dev *rxe, union ib_gid *mgid, */ kref_get(&mcg->ref_cnt); __rxe_insert_mcg(mcg); - - return 0; } /** @@ -209,6 +200,12 @@ static struct rxe_mcg *rxe_get_mcg(struct rxe_dev *rxe, union ib_gid *mgid) if (mcg) return mcg; + /* check to see if we have reached limit */ + if (atomic_inc_return(&rxe->mcg_num) > rxe->attr.max_mcast_grp) { + err = -ENOMEM; + goto err_dec; + } + /* speculative alloc of new mcg */ mcg = kzalloc(sizeof(*mcg), GFP_KERNEL); if (!mcg) @@ -218,27 +215,23 @@ static struct rxe_mcg *rxe_get_mcg(struct rxe_dev *rxe, union ib_gid *mgid) /* re-check to see if someone else just added it */ tmp = __rxe_lookup_mcg(rxe, mgid); if (tmp) { + spin_unlock_irqrestore(&rxe->mcg_lock, flags); + atomic_dec(&rxe->mcg_num); kfree(mcg); - mcg = tmp; - goto out; + return tmp; } - if (atomic_inc_return(&rxe->mcg_num) > rxe->attr.max_mcast_grp) { - err = -ENOMEM; - goto err_dec; - } - - err = __rxe_init_mcg(rxe, mgid, mcg); - if (err) - goto err_dec; -out: + __rxe_init_mcg(rxe, mgid, mcg); spin_unlock_irqrestore(&rxe->mcg_lock, flags); - return mcg; + /* add mcast address outside of lock */ + err = rxe_mcast_add(rxe, mgid); + if (!err) + return mcg; + + kfree(mcg); err_dec: atomic_dec(&rxe->mcg_num); - spin_unlock_irqrestore(&rxe->mcg_lock, flags); - kfree(mcg); return ERR_PTR(err); } @@ -268,7 +261,6 @@ static void __rxe_destroy_mcg(struct rxe_mcg *mcg) __rxe_remove_mcg(mcg); kref_put(&mcg->ref_cnt, rxe_cleanup_mcg); - rxe_mcast_delete(mcg->rxe, &mcg->mgid); atomic_dec(&rxe->mcg_num); } @@ -282,6 +274,9 @@ static void rxe_destroy_mcg(struct rxe_mcg *mcg) { unsigned long flags; + /* delete mcast address outside of lock */ + rxe_mcast_del(mcg->rxe, &mcg->mgid); + spin_lock_irqsave(&mcg->rxe->mcg_lock, flags); __rxe_destroy_mcg(mcg); spin_unlock_irqrestore(&mcg->rxe->mcg_lock, flags); From bfdc0edd11f9501b891a069b5bbd3b16731941e1 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Wed, 4 May 2022 15:28:17 -0500 Subject: [PATCH 142/192] RDMA/rxe: Change mcg_lock to a _bh lock rxe_mcast.c currently uses _irqsave spinlocks for rxe->mcg_lock while rxe_recv.c uses _bh spinlocks for the same lock. As there is no case where the mcg_lock can be taken from an IRQ, change these all to bh locks so we don't have confusing mismatched lock types on the same spinlock. Fixes: 6090a0c4c7c6 ("RDMA/rxe: Cleanup rxe_mcast.c") Link: https://lore.kernel.org/r/20220504202817.98247-1-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_mcast.c | 36 +++++++++++---------------- 1 file changed, 15 insertions(+), 21 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_mcast.c b/drivers/infiniband/sw/rxe/rxe_mcast.c index 77e45cabd8ea..873a9b10307c 100644 --- a/drivers/infiniband/sw/rxe/rxe_mcast.c +++ b/drivers/infiniband/sw/rxe/rxe_mcast.c @@ -143,11 +143,10 @@ static struct rxe_mcg *__rxe_lookup_mcg(struct rxe_dev *rxe, struct rxe_mcg *rxe_lookup_mcg(struct rxe_dev *rxe, union ib_gid *mgid) { struct rxe_mcg *mcg; - unsigned long flags; - spin_lock_irqsave(&rxe->mcg_lock, flags); + spin_lock_bh(&rxe->mcg_lock); mcg = __rxe_lookup_mcg(rxe, mgid); - spin_unlock_irqrestore(&rxe->mcg_lock, flags); + spin_unlock_bh(&rxe->mcg_lock); return mcg; } @@ -189,7 +188,6 @@ static void __rxe_init_mcg(struct rxe_dev *rxe, union ib_gid *mgid, static struct rxe_mcg *rxe_get_mcg(struct rxe_dev *rxe, union ib_gid *mgid) { struct rxe_mcg *mcg, *tmp; - unsigned long flags; int err; if (rxe->attr.max_mcast_grp == 0) @@ -211,18 +209,18 @@ static struct rxe_mcg *rxe_get_mcg(struct rxe_dev *rxe, union ib_gid *mgid) if (!mcg) return ERR_PTR(-ENOMEM); - spin_lock_irqsave(&rxe->mcg_lock, flags); + spin_lock_bh(&rxe->mcg_lock); /* re-check to see if someone else just added it */ tmp = __rxe_lookup_mcg(rxe, mgid); if (tmp) { - spin_unlock_irqrestore(&rxe->mcg_lock, flags); + spin_unlock_bh(&rxe->mcg_lock); atomic_dec(&rxe->mcg_num); kfree(mcg); return tmp; } __rxe_init_mcg(rxe, mgid, mcg); - spin_unlock_irqrestore(&rxe->mcg_lock, flags); + spin_unlock_bh(&rxe->mcg_lock); /* add mcast address outside of lock */ err = rxe_mcast_add(rxe, mgid); @@ -272,14 +270,12 @@ static void __rxe_destroy_mcg(struct rxe_mcg *mcg) */ static void rxe_destroy_mcg(struct rxe_mcg *mcg) { - unsigned long flags; - /* delete mcast address outside of lock */ rxe_mcast_del(mcg->rxe, &mcg->mgid); - spin_lock_irqsave(&mcg->rxe->mcg_lock, flags); + spin_lock_bh(&mcg->rxe->mcg_lock); __rxe_destroy_mcg(mcg); - spin_unlock_irqrestore(&mcg->rxe->mcg_lock, flags); + spin_unlock_bh(&mcg->rxe->mcg_lock); } /** @@ -334,25 +330,24 @@ static int rxe_attach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp) { struct rxe_dev *rxe = mcg->rxe; struct rxe_mca *mca, *tmp; - unsigned long flags; int err; /* check to see if the qp is already a member of the group */ - spin_lock_irqsave(&rxe->mcg_lock, flags); + spin_lock_bh(&rxe->mcg_lock); list_for_each_entry(mca, &mcg->qp_list, qp_list) { if (mca->qp == qp) { - spin_unlock_irqrestore(&rxe->mcg_lock, flags); + spin_unlock_bh(&rxe->mcg_lock); return 0; } } - spin_unlock_irqrestore(&rxe->mcg_lock, flags); + spin_unlock_bh(&rxe->mcg_lock); /* speculative alloc new mca without using GFP_ATOMIC */ mca = kzalloc(sizeof(*mca), GFP_KERNEL); if (!mca) return -ENOMEM; - spin_lock_irqsave(&rxe->mcg_lock, flags); + spin_lock_bh(&rxe->mcg_lock); /* re-check to see if someone else just attached qp */ list_for_each_entry(tmp, &mcg->qp_list, qp_list) { if (tmp->qp == qp) { @@ -366,7 +361,7 @@ static int rxe_attach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp) if (err) kfree(mca); out: - spin_unlock_irqrestore(&rxe->mcg_lock, flags); + spin_unlock_bh(&rxe->mcg_lock); return err; } @@ -400,9 +395,8 @@ static int rxe_detach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp) { struct rxe_dev *rxe = mcg->rxe; struct rxe_mca *mca, *tmp; - unsigned long flags; - spin_lock_irqsave(&rxe->mcg_lock, flags); + spin_lock_bh(&rxe->mcg_lock); list_for_each_entry_safe(mca, tmp, &mcg->qp_list, qp_list) { if (mca->qp == qp) { __rxe_cleanup_mca(mca, mcg); @@ -416,13 +410,13 @@ static int rxe_detach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp) if (atomic_read(&mcg->qp_num) <= 0) __rxe_destroy_mcg(mcg); - spin_unlock_irqrestore(&rxe->mcg_lock, flags); + spin_unlock_bh(&rxe->mcg_lock); return 0; } } /* we didn't find the qp on the list */ - spin_unlock_irqrestore(&rxe->mcg_lock, flags); + spin_unlock_bh(&rxe->mcg_lock); return -EINVAL; } From 59f5ede3bc0f00eb856425f636dab0c10feb06d8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 1 May 2022 21:31:43 +0200 Subject: [PATCH 143/192] x86/fpu: Prevent FPU state corruption The FPU usage related to task FPU management is either protected by disabling interrupts (switch_to, return to user) or via fpregs_lock() which is a wrapper around local_bh_disable(). When kernel code wants to use the FPU then it has to check whether it is possible by calling irq_fpu_usable(). But the condition in irq_fpu_usable() is wrong. It allows FPU to be used when: !in_interrupt() || interrupted_user_mode() || interrupted_kernel_fpu_idle() The latter is checking whether some other context already uses FPU in the kernel, but if that's not the case then it allows FPU to be used unconditionally even if the calling context interrupted a fpregs_lock() critical region. If that happens then the FPU state of the interrupted context becomes corrupted. Allow in kernel FPU usage only when no other context has in kernel FPU usage and either the calling context is not hard interrupt context or the hard interrupt did not interrupt a local bottomhalf disabled region. It's hard to find a proper Fixes tag as the condition was broken in one way or the other for a very long time and the eager/lazy FPU changes caused a lot of churn. Picked something remotely connected from the history. This survived undetected for quite some time as FPU usage in interrupt context is rare, but the recent changes to the random code unearthed it at least on a kernel which had FPU debugging enabled. There is probably a higher rate of silent corruption as not all issues can be detected by the FPU debugging code. This will be addressed in a subsequent change. Fixes: 5d2bd7009f30 ("x86, fpu: decouple non-lazy/eager fpu restore from xsave") Reported-by: Filipe Manana Signed-off-by: Thomas Gleixner Tested-by: Filipe Manana Reviewed-by: Borislav Petkov Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220501193102.588689270@linutronix.de --- arch/x86/kernel/fpu/core.c | 67 +++++++++++++++----------------------- 1 file changed, 26 insertions(+), 41 deletions(-) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index c049561f373a..e28ab0ecc537 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -41,17 +41,7 @@ struct fpu_state_config fpu_user_cfg __ro_after_init; */ struct fpstate init_fpstate __ro_after_init; -/* - * Track whether the kernel is using the FPU state - * currently. - * - * This flag is used: - * - * - by IRQ context code to potentially use the FPU - * if it's unused. - * - * - to debug kernel_fpu_begin()/end() correctness - */ +/* Track in-kernel FPU usage */ static DEFINE_PER_CPU(bool, in_kernel_fpu); /* @@ -59,42 +49,37 @@ static DEFINE_PER_CPU(bool, in_kernel_fpu); */ DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); -static bool kernel_fpu_disabled(void) -{ - return this_cpu_read(in_kernel_fpu); -} - -static bool interrupted_kernel_fpu_idle(void) -{ - return !kernel_fpu_disabled(); -} - -/* - * Were we in user mode (or vm86 mode) when we were - * interrupted? - * - * Doing kernel_fpu_begin/end() is ok if we are running - * in an interrupt context from user mode - we'll just - * save the FPU state as required. - */ -static bool interrupted_user_mode(void) -{ - struct pt_regs *regs = get_irq_regs(); - return regs && user_mode(regs); -} - /* * Can we use the FPU in kernel mode with the * whole "kernel_fpu_begin/end()" sequence? - * - * It's always ok in process context (ie "not interrupt") - * but it is sometimes ok even from an irq. */ bool irq_fpu_usable(void) { - return !in_interrupt() || - interrupted_user_mode() || - interrupted_kernel_fpu_idle(); + if (WARN_ON_ONCE(in_nmi())) + return false; + + /* In kernel FPU usage already active? */ + if (this_cpu_read(in_kernel_fpu)) + return false; + + /* + * When not in NMI or hard interrupt context, FPU can be used in: + * + * - Task context except from within fpregs_lock()'ed critical + * regions. + * + * - Soft interrupt processing context which cannot happen + * while in a fpregs_lock()'ed critical region. + */ + if (!in_hardirq()) + return true; + + /* + * In hard interrupt context it's safe when soft interrupts + * are enabled, which means the interrupt did not hit in + * a fpregs_lock()'ed critical region. + */ + return !softirq_count(); } EXPORT_SYMBOL(irq_fpu_usable); From ae2de669c14a18b5144cdacf49933ad400ed7e1c Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 4 May 2022 22:29:15 +0200 Subject: [PATCH 144/192] wireguard: selftests: make routing loop test non-fatal I hate to do this, but I still do not have a good solution to actually fix this bug across architectures. So just disable it for now, so that the CI can still deliver actionable results. This commit adds a large red warning, so that at least the failure isn't lost forever, and hopefully this can be revisited down the line. Link: https://lore.kernel.org/netdev/CAHmME9pv1x6C4TNdL6648HydD8r+txpV4hTUXOBVkrapBXH4QQ@mail.gmail.com/ Link: https://lore.kernel.org/netdev/YmszSXueTxYOC41G@zx2c4.com/ Link: https://lore.kernel.org/wireguard/CAHmME9rNnBiNvBstb7MPwK-7AmAN0sOfnhdR=eeLrowWcKxaaQ@mail.gmail.com/ Signed-off-by: Jason A. Donenfeld Signed-off-by: Jakub Kicinski --- tools/testing/selftests/wireguard/netns.sh | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 8a9461aa0878..8a543200a61a 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -280,7 +280,19 @@ read _ _ tx_bytes_before < <(n0 wg show wg1 transfer) ! n0 ping -W 1 -c 10 -f 192.168.241.2 || false sleep 1 read _ _ tx_bytes_after < <(n0 wg show wg1 transfer) -(( tx_bytes_after - tx_bytes_before < 70000 )) +if ! (( tx_bytes_after - tx_bytes_before < 70000 )); then + errstart=$'\x1b[37m\x1b[41m\x1b[1m' + errend=$'\x1b[0m' + echo "${errstart} ${errend}" + echo "${errstart} E R R O R ${errend}" + echo "${errstart} ${errend}" + echo "${errstart} This architecture does not do the right thing ${errend}" + echo "${errstart} with cross-namespace routing loops. This test ${errend}" + echo "${errstart} has thus technically failed but, as this issue ${errend}" + echo "${errstart} is as yet unsolved, these tests will continue ${errend}" + echo "${errstart} onward. :( ${errend}" + echo "${errstart} ${errend}" +fi ip0 link del wg1 ip1 link del wg0 From 39f02bf1e5ce9d72045de01e3d618ade1067158c Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 4 May 2022 22:29:16 +0200 Subject: [PATCH 145/192] wireguard: selftests: limit parallelism to $(nproc) tests at once The parallel tests were added to catch queueing issues from multiple cores. But what happens in reality when testing tons of processes is that these separate threads wind up fighting with the scheduler, and we wind up with contention in places we don't care about that decrease the chances of hitting a bug. So just do a test with the number of CPU cores, rather than trying to scale up arbitrarily. Signed-off-by: Jason A. Donenfeld Signed-off-by: Jakub Kicinski --- tools/testing/selftests/wireguard/netns.sh | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 8a543200a61a..69c7796c7ca9 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -22,10 +22,12 @@ # interfaces in $ns1 and $ns2. See https://www.wireguard.com/netns/ for further # details on how this is accomplished. set -e +shopt -s extglob exec 3>&1 export LANG=C export WG_HIDE_KEYS=never +NPROC=( /sys/devices/system/cpu/cpu+([0-9]) ); NPROC=${#NPROC[@]} netns0="wg-test-$$-0" netns1="wg-test-$$-1" netns2="wg-test-$$-2" @@ -143,17 +145,15 @@ tests() { n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2 # TCP over IPv4, in parallel - for max in 4 5 50; do - local pids=( ) - for ((i=0; i < max; ++i)) do - n2 iperf3 -p $(( 5200 + i )) -s -1 -B 192.168.241.2 & - pids+=( $! ); waitiperf $netns2 $! $(( 5200 + i )) - done - for ((i=0; i < max; ++i)) do - n1 iperf3 -Z -t 3 -p $(( 5200 + i )) -c 192.168.241.2 & - done - wait "${pids[@]}" + local pids=( ) i + for ((i=0; i < NPROC; ++i)) do + n2 iperf3 -p $(( 5200 + i )) -s -1 -B 192.168.241.2 & + pids+=( $! ); waitiperf $netns2 $! $(( 5200 + i )) done + for ((i=0; i < NPROC; ++i)) do + n1 iperf3 -Z -t 3 -p $(( 5200 + i )) -c 192.168.241.2 & + done + wait "${pids[@]}" } [[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}" From d5d9b29bc963cc084c5c0f3a7c28e2632a22e0c4 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 4 May 2022 22:29:17 +0200 Subject: [PATCH 146/192] wireguard: selftests: use newer toolchains to fill out architectures Rather than relying on the system to have cross toolchains available, simply download musl.cc's ones and use that libc.so, and then we use it to fill in a few missing platforms, such as riscv64, riscv64, powerpc64, and s390x. Since riscv doesn't have a second serial port in its device description, we have to use virtio's vport. This is actually the same situation on ARM, but we were previously hacking QEMU up to work around this, which required a custom QEMU. Instead just do the vport trick on ARM too. Signed-off-by: Jason A. Donenfeld Signed-off-by: Jakub Kicinski --- .../testing/selftests/wireguard/qemu/Makefile | 171 ++++++++++++------ .../wireguard/qemu/arch/aarch64.config | 5 +- .../wireguard/qemu/arch/aarch64_be.config | 5 +- .../selftests/wireguard/qemu/arch/arm.config | 5 +- .../wireguard/qemu/arch/armeb.config | 5 +- .../wireguard/qemu/arch/powerpc64.config | 13 ++ .../wireguard/qemu/arch/riscv32.config | 12 ++ .../wireguard/qemu/arch/riscv64.config | 12 ++ .../wireguard/qemu/arch/s390x.config | 6 + 9 files changed, 170 insertions(+), 64 deletions(-) create mode 100644 tools/testing/selftests/wireguard/qemu/arch/powerpc64.config create mode 100644 tools/testing/selftests/wireguard/qemu/arch/riscv32.config create mode 100644 tools/testing/selftests/wireguard/qemu/arch/riscv64.config create mode 100644 tools/testing/selftests/wireguard/qemu/arch/s390x.config diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile index 4bdd6c1a19d3..930f59c9e714 100644 --- a/tools/testing/selftests/wireguard/qemu/Makefile +++ b/tools/testing/selftests/wireguard/qemu/Makefile @@ -4,26 +4,24 @@ PWD := $(shell pwd) -CHOST := $(shell gcc -dumpmachine) -HOST_ARCH := $(firstword $(subst -, ,$(CHOST))) -ifneq (,$(ARCH)) -CBUILD := $(subst -gcc,,$(lastword $(subst /, ,$(firstword $(wildcard $(foreach bindir,$(subst :, ,$(PATH)),$(bindir)/$(ARCH)-*-gcc)))))) -ifeq (,$(CBUILD)) -$(error The toolchain for $(ARCH) is not installed) -endif -else -CBUILD := $(CHOST) -ARCH := $(firstword $(subst -, ,$(CBUILD))) -endif - # Set these from the environment to override KERNEL_PATH ?= $(PWD)/../../../../.. BUILD_PATH ?= $(PWD)/build/$(ARCH) DISTFILES_PATH ?= $(PWD)/distfiles NR_CPUS ?= 4 +ARCH ?= +CBUILD := $(shell gcc -dumpmachine) +HOST_ARCH := $(firstword $(subst -, ,$(CBUILD))) +ifeq ($(ARCH),) +ARCH := $(HOST_ARCH) +endif MIRROR := https://download.wireguard.com/qemu-test/distfiles/ +KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug) +rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d)) +WIREGUARD_SOURCES := $(call rwildcard,$(KERNEL_PATH)/drivers/net/wireguard/,*) + default: qemu # variable name, tarball project name, version, tarball extension, default URI base @@ -36,12 +34,11 @@ $(call file_download,$$($(1)_NAME)$(4),$(5),$(6)) endef define file_download = -$(DISTFILES_PATH)/$(1): +$(DISTFILES_PATH)/$(1): | $(4) mkdir -p $(DISTFILES_PATH) - flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi' + flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if ([ -n "$(4)" ] && sed -n "s#^\([a-f0-9]\{64\}\) \($(1)\)\$$$$#\1 $(DISTFILES_PATH)/\2.tmp#p" "$(4)" || echo "$(3) $$@.tmp") | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi' endef -$(eval $(call tar_download,MUSL,musl,1.2.0,.tar.gz,https://musl.libc.org/releases/,c6de7b191139142d3f9a7b5b702c9cae1b5ee6e7f57e582da9328629408fd4e8)) $(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c)) $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d)) $(eval $(call tar_download,IPROUTE2,iproute2,5.6.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,1b5b0e25ce6e23da7526ea1da044e814ad85ba761b10dd29c2b027c056b04692)) @@ -50,28 +47,20 @@ $(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a)) $(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64)) -KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug) -rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d)) -WIREGUARD_SOURCES := $(call rwildcard,$(KERNEL_PATH)/drivers/net/wireguard/,*) - -export CFLAGS ?= -O3 -pipe -export LDFLAGS ?= -export CPPFLAGS := -I$(BUILD_PATH)/include - +export CFLAGS := -O3 -pipe ifeq ($(HOST_ARCH),$(ARCH)) -CROSS_COMPILE_FLAG := --host=$(CHOST) CFLAGS += -march=native -STRIP := strip -else -$(info Cross compilation: building for $(CBUILD) using $(CHOST)) -CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST) -export CROSS_COMPILE=$(CBUILD)- -STRIP := $(CBUILD)-strip endif +export LDFLAGS := +export CPPFLAGS := + +QEMU_VPORT_RESULT := ifeq ($(ARCH),aarch64) +CHOST := aarch64-linux-musl QEMU_ARCH := aarch64 KERNEL_ARCH := arm64 KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image +QEMU_VPORT_RESULT := virtio-serial-device ifeq ($(HOST_ARCH),$(ARCH)) QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm else @@ -79,9 +68,11 @@ QEMU_MACHINE := -cpu cortex-a53 -machine virt CFLAGS += -march=armv8-a -mtune=cortex-a53 endif else ifeq ($(ARCH),aarch64_be) +CHOST := aarch64_be-linux-musl QEMU_ARCH := aarch64 KERNEL_ARCH := arm64 KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image +QEMU_VPORT_RESULT := virtio-serial-device ifeq ($(HOST_ARCH),$(ARCH)) QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm else @@ -89,9 +80,11 @@ QEMU_MACHINE := -cpu cortex-a53 -machine virt CFLAGS += -march=armv8-a -mtune=cortex-a53 endif else ifeq ($(ARCH),arm) +CHOST := arm-linux-musleabi QEMU_ARCH := arm KERNEL_ARCH := arm KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage +QEMU_VPORT_RESULT := virtio-serial-device ifeq ($(HOST_ARCH),$(ARCH)) QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm else @@ -99,9 +92,11 @@ QEMU_MACHINE := -cpu cortex-a15 -machine virt CFLAGS += -march=armv7-a -mtune=cortex-a15 -mabi=aapcs-linux endif else ifeq ($(ARCH),armeb) +CHOST := armeb-linux-musleabi QEMU_ARCH := arm KERNEL_ARCH := arm KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage +QEMU_VPORT_RESULT := virtio-serial-device ifeq ($(HOST_ARCH),$(ARCH)) QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm else @@ -110,6 +105,7 @@ CFLAGS += -march=armv7-a -mabi=aapcs-linux # We don't pass -mtune=cortex-a15 due LDFLAGS += -Wl,--be8 endif else ifeq ($(ARCH),x86_64) +CHOST := x86_64-linux-musl QEMU_ARCH := x86_64 KERNEL_ARCH := x86_64 KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage @@ -120,6 +116,7 @@ QEMU_MACHINE := -cpu Skylake-Server -machine q35 CFLAGS += -march=skylake-avx512 endif else ifeq ($(ARCH),i686) +CHOST := i686-linux-musl QEMU_ARCH := i386 KERNEL_ARCH := x86 KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage @@ -130,6 +127,7 @@ QEMU_MACHINE := -cpu coreduo -machine q35 CFLAGS += -march=prescott endif else ifeq ($(ARCH),mips64) +CHOST := mips64-linux-musl QEMU_ARCH := mips64 KERNEL_ARCH := mips KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux @@ -141,6 +139,7 @@ QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1 CFLAGS += -march=mips64r2 -EB endif else ifeq ($(ARCH),mips64el) +CHOST := mips64el-linux-musl QEMU_ARCH := mips64el KERNEL_ARCH := mips KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux @@ -152,6 +151,7 @@ QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1 CFLAGS += -march=mips64r2 -EL endif else ifeq ($(ARCH),mips) +CHOST := mips-linux-musl QEMU_ARCH := mips KERNEL_ARCH := mips KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux @@ -163,6 +163,7 @@ QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1 CFLAGS += -march=mips32r2 -EB endif else ifeq ($(ARCH),mipsel) +CHOST := mipsel-linux-musl QEMU_ARCH := mipsel KERNEL_ARCH := mips KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux @@ -173,7 +174,18 @@ else QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1 CFLAGS += -march=mips32r2 -EL endif -else ifeq ($(ARCH),powerpc64le) +else ifeq ($(ARCH),powerpc64) +CHOST := powerpc64-linux-musl +QEMU_ARCH := ppc64 +KERNEL_ARCH := powerpc +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine pseries +else +QEMU_MACHINE := -machine pseries +endif +else ifeq ($(ARCH),powerpc64le) +CHOST := powerpc64le-linux-musl QEMU_ARCH := ppc64 KERNEL_ARCH := powerpc KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux @@ -182,8 +194,8 @@ QEMU_MACHINE := -cpu host,accel=kvm -machine pseries else QEMU_MACHINE := -machine pseries endif -CFLAGS += -mcpu=powerpc64le -mlong-double-64 else ifeq ($(ARCH),powerpc) +CHOST := powerpc-linux-musl QEMU_ARCH := ppc KERNEL_ARCH := powerpc KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/powerpc/boot/uImage @@ -192,26 +204,72 @@ QEMU_MACHINE := -cpu host,accel=kvm -machine ppce500 else QEMU_MACHINE := -machine ppce500 endif -CFLAGS += -mcpu=powerpc -mlong-double-64 -msecure-plt else ifeq ($(ARCH),m68k) +CHOST := m68k-linux-musl QEMU_ARCH := m68k KERNEL_ARCH := m68k KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux KERNEL_CMDLINE := $(shell sed -n 's/CONFIG_CMDLINE=\(.*\)/\1/p' arch/m68k.config) ifeq ($(HOST_ARCH),$(ARCH)) -QEMU_MACHINE := -cpu host,accel=kvm -machine q800 -smp 1 -append $(KERNEL_CMDLINE) +QEMU_MACHINE := -cpu host,accel=kvm -machine q800 -append $(KERNEL_CMDLINE) else QEMU_MACHINE := -machine q800 -smp 1 -append $(KERNEL_CMDLINE) endif +else ifeq ($(ARCH),riscv64) +CHOST := riscv64-linux-musl +QEMU_ARCH := riscv64 +KERNEL_ARCH := riscv +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/riscv/boot/Image +QEMU_VPORT_RESULT := virtio-serial-device +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine virt else -$(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64le, powerpc, m68k) +QEMU_MACHINE := -cpu rv64 -machine virt +endif +else ifeq ($(ARCH),riscv32) +CHOST := riscv32-linux-musl +QEMU_ARCH := riscv32 +KERNEL_ARCH := riscv +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/riscv/boot/Image +QEMU_VPORT_RESULT := virtio-serial-device +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine virt +else +QEMU_MACHINE := -cpu rv32 -machine virt +endif +else ifeq ($(ARCH),s390x) +CHOST := s390x-linux-musl +QEMU_ARCH := s390x +KERNEL_ARCH := s390 +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/s390/boot/bzImage +KERNEL_CMDLINE := $(shell sed -n 's/CONFIG_CMDLINE=\(.*\)/\1/p' arch/s390x.config) +QEMU_VPORT_RESULT := virtio-serial-ccw +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine s390-ccw-virtio -append $(KERNEL_CMDLINE) +else +QEMU_MACHINE := -machine s390-ccw-virtio -append $(KERNEL_CMDLINE) +endif +else +$(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64, powerpc64le, powerpc, m68k, riscv64, riscv32, s390x) endif -REAL_CC := $(CBUILD)-gcc -MUSL_CC := $(BUILD_PATH)/musl-gcc -export CC := $(MUSL_CC) -USERSPACE_DEPS := $(MUSL_CC) $(BUILD_PATH)/include/.installed $(BUILD_PATH)/include/linux/.installed +TOOLCHAIN_FILENAME := $(CHOST)-cross.tgz +TOOLCHAIN_TAR := $(DISTFILES_PATH)/$(TOOLCHAIN_FILENAME) +TOOLCHAIN_PATH := $(BUILD_PATH)/$(CHOST)-cross +TOOLCHAIN_DIR := https://download.wireguard.com/qemu-test/toolchains/20211123/ +$(eval $(call file_download,toolchain-sha256sums-20211123,$(TOOLCHAIN_DIR)SHA256SUMS#,83da033fd8c798df476c21d9612da2dfb896ec62fbed4ceec5eefc0e56b3f0c8)) +$(eval $(call file_download,$(TOOLCHAIN_FILENAME),$(TOOLCHAIN_DIR),,$(DISTFILES_PATH)/toolchain-sha256sums-20211123)) +STRIP := $(CHOST)-strip +CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST) +$(info Building for $(CHOST) using $(CBUILD)) +export CROSS_COMPILE := $(CHOST)- +export PATH := $(TOOLCHAIN_PATH)/bin:$(PATH) +export CC := $(CHOST)-gcc + +USERSPACE_DEPS := $(TOOLCHAIN_PATH)/.installed $(TOOLCHAIN_PATH)/$(CHOST)/include/linux/.installed + +comma := , build: $(KERNEL_BZIMAGE) qemu: $(KERNEL_BZIMAGE) rm -f $(BUILD_PATH)/result @@ -222,13 +280,14 @@ qemu: $(KERNEL_BZIMAGE) $(QEMU_MACHINE) \ -m $$(grep -q CONFIG_DEBUG_KMEMLEAK=y $(KERNEL_BUILD_PATH)/.config && echo 1G || echo 256M) \ -serial stdio \ - -serial file:$(BUILD_PATH)/result \ + -chardev file,path=$(BUILD_PATH)/result,id=result \ + $(if $(QEMU_VPORT_RESULT),-device $(QEMU_VPORT_RESULT) -device virtserialport$(comma)chardev=result,-serial chardev:result) \ -no-reboot \ -monitor none \ -kernel $< grep -Fq success $(BUILD_PATH)/result -$(BUILD_PATH)/init-cpio-spec.txt: +$(BUILD_PATH)/init-cpio-spec.txt: $(TOOLCHAIN_PATH)/.installed $(BUILD_PATH)/init mkdir -p $(BUILD_PATH) echo "file /init $(BUILD_PATH)/init 755 0 0" > $@ echo "file /init.sh $(PWD)/../netns.sh 755 0 0" >> $@ @@ -246,10 +305,10 @@ $(BUILD_PATH)/init-cpio-spec.txt: echo "slink /bin/iptables xtables-legacy-multi 777 0 0" >> $@ echo "slink /bin/ping6 ping 777 0 0" >> $@ echo "dir /lib 755 0 0" >> $@ - echo "file /lib/libc.so $(MUSL_PATH)/lib/libc.so 755 0 0" >> $@ - echo "slink /lib/ld-linux.so.1 libc.so 777 0 0" >> $@ + echo "file /lib/libc.so $(TOOLCHAIN_PATH)/$(CHOST)/lib/libc.so 755 0 0" >> $@ + echo "slink $$($(CHOST)-readelf -p .interp '$(BUILD_PATH)/init'| grep -o '/lib/.*') libc.so 777 0 0" >> $@ -$(KERNEL_BUILD_PATH)/.config: kernel.config arch/$(ARCH).config +$(KERNEL_BUILD_PATH)/.config: $(TOOLCHAIN_PATH)/.installed kernel.config arch/$(ARCH).config mkdir -p $(KERNEL_BUILD_PATH) cp kernel.config $(KERNEL_BUILD_PATH)/minimal.config printf 'CONFIG_NR_CPUS=$(NR_CPUS)\nCONFIG_INITRAMFS_SOURCE="$(BUILD_PATH)/init-cpio-spec.txt"\n' >> $(KERNEL_BUILD_PATH)/minimal.config @@ -258,29 +317,20 @@ $(KERNEL_BUILD_PATH)/.config: kernel.config arch/$(ARCH).config cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config $(KERNEL_BUILD_PATH)/minimal.config $(if $(findstring yes,$(DEBUG_KERNEL)),cp debug.config $(KERNEL_BUILD_PATH) && cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config debug.config,) -$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-legacy-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES) +$(KERNEL_BZIMAGE): $(TOOLCHAIN_PATH)/.installed $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-legacy-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES) $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) -$(BUILD_PATH)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config - $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install +$(TOOLCHAIN_PATH)/$(CHOST)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config $(TOOLCHAIN_PATH)/.installed + rm -rf $(TOOLCHAIN_PATH)/$(CHOST)/include/linux + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(TOOLCHAIN_PATH)/$(CHOST) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install touch $@ -$(MUSL_PATH)/lib/libc.so: $(MUSL_TAR) +$(TOOLCHAIN_PATH)/.installed: $(TOOLCHAIN_TAR) mkdir -p $(BUILD_PATH) flock -s $<.lock tar -C $(BUILD_PATH) -xf $< - cd $(MUSL_PATH) && CC=$(REAL_CC) ./configure --prefix=/ --disable-static --build=$(CBUILD) - $(MAKE) -C $(MUSL_PATH) - $(STRIP) -s $@ - -$(BUILD_PATH)/include/.installed: $(MUSL_PATH)/lib/libc.so - $(MAKE) -C $(MUSL_PATH) DESTDIR=$(BUILD_PATH) install-headers + $(STRIP) -s $(TOOLCHAIN_PATH)/$(CHOST)/lib/libc.so touch $@ -$(MUSL_CC): $(MUSL_PATH)/lib/libc.so - sh $(MUSL_PATH)/tools/musl-gcc.specs.sh $(BUILD_PATH)/include $(MUSL_PATH)/lib /lib/ld-linux.so.1 > $(BUILD_PATH)/musl-gcc.specs - printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" "$$@"\n' > $(BUILD_PATH)/musl-gcc - chmod +x $(BUILD_PATH)/musl-gcc - $(IPERF_PATH)/.installed: $(IPERF_TAR) mkdir -p $(BUILD_PATH) flock -s $<.lock tar -C $(BUILD_PATH) -xf $< @@ -289,6 +339,7 @@ $(IPERF_PATH)/.installed: $(IPERF_TAR) touch $@ $(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS) + cd $(IPERF_PATH) && autoreconf -fi cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --with-openssl=no $(MAKE) -C $(IPERF_PATH) $(STRIP) -s $@ @@ -304,7 +355,7 @@ $(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(USERSPACE $(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS) mkdir -p $(BUILD_PATH) - $(MUSL_CC) -o $@ $(CFLAGS) $(LDFLAGS) -std=gnu11 $< + $(CC) -o $@ $(CFLAGS) $(LDFLAGS) -std=gnu11 $< $(STRIP) -s $@ $(IPUTILS_PATH)/.installed: $(IPUTILS_TAR) diff --git a/tools/testing/selftests/wireguard/qemu/arch/aarch64.config b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config index 3d063bb247bb..e9ac41f6b3ae 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/aarch64.config +++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config @@ -1,5 +1,8 @@ CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1" CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config index dbdc7e406a7b..03609a203e8c 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config +++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config @@ -1,6 +1,9 @@ CONFIG_CPU_BIG_ENDIAN=y CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1" CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/arm.config b/tools/testing/selftests/wireguard/qemu/arch/arm.config index 148f49905418..c616124fdd59 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/arm.config +++ b/tools/testing/selftests/wireguard/qemu/arch/arm.config @@ -4,6 +4,9 @@ CONFIG_ARCH_VIRT=y CONFIG_THUMB2_KERNEL=n CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1" CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/armeb.config b/tools/testing/selftests/wireguard/qemu/arch/armeb.config index bd76b07d00a2..d3a40a974e16 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/armeb.config +++ b/tools/testing/selftests/wireguard/qemu/arch/armeb.config @@ -4,7 +4,10 @@ CONFIG_ARCH_VIRT=y CONFIG_THUMB2_KERNEL=n CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1" CONFIG_CPU_BIG_ENDIAN=y CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64.config new file mode 100644 index 000000000000..c19c7b519d8b --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64.config @@ -0,0 +1,13 @@ +CONFIG_PPC64=y +CONFIG_PPC_PSERIES=y +CONFIG_ALTIVEC=y +CONFIG_VSX=y +CONFIG_PPC_OF_BOOT_TRAMPOLINE=y +CONFIG_PPC_RADIX_MMU=y +CONFIG_HVC_CONSOLE=y +CONFIG_CPU_BIG_ENDIAN=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=hvc0 wg.success=hvc1" +CONFIG_SECTION_MISMATCH_WARN_ONLY=y +CONFIG_FRAME_WARN=1280 +CONFIG_THREAD_SHIFT=14 diff --git a/tools/testing/selftests/wireguard/qemu/arch/riscv32.config b/tools/testing/selftests/wireguard/qemu/arch/riscv32.config new file mode 100644 index 000000000000..ea53e78e923e --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/riscv32.config @@ -0,0 +1,12 @@ +CONFIG_ARCH_RV32I=y +CONFIG_MMU=y +CONFIG_FPU=y +CONFIG_SOC_VIRT=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_CMDLINE="console=ttyS0 wg.success=vport0p1" +CONFIG_CMDLINE_FORCE=y diff --git a/tools/testing/selftests/wireguard/qemu/arch/riscv64.config b/tools/testing/selftests/wireguard/qemu/arch/riscv64.config new file mode 100644 index 000000000000..4a08d8c1d4af --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/riscv64.config @@ -0,0 +1,12 @@ +CONFIG_ARCH_RV64I=y +CONFIG_MMU=y +CONFIG_FPU=y +CONFIG_SOC_VIRT=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_CMDLINE="console=ttyS0 wg.success=vport0p1" +CONFIG_CMDLINE_FORCE=y diff --git a/tools/testing/selftests/wireguard/qemu/arch/s390x.config b/tools/testing/selftests/wireguard/qemu/arch/s390x.config new file mode 100644 index 000000000000..274a44f4e49c --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/s390x.config @@ -0,0 +1,6 @@ +CONFIG_SCLP_VT220_TTY=y +CONFIG_SCLP_VT220_CONSOLE=y +CONFIG_VIRTIO_MENU=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_S390_GUEST=y +CONFIG_CMDLINE="console=ttysclp0 wg.success=vport0p1" From d261ba6aa411e03c27da266b7df4bef771e8105e Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 4 May 2022 22:29:18 +0200 Subject: [PATCH 147/192] wireguard: selftests: restore support for ccache When moving to non-system toolchains, we inadvertantly killed the ability to use ccache. So instead, build ccache support into the test harness directly. Signed-off-by: Jason A. Donenfeld Signed-off-by: Jakub Kicinski --- .../selftests/wireguard/qemu/.gitignore | 1 + .../testing/selftests/wireguard/qemu/Makefile | 18 +++++++++++++++++- 2 files changed, 18 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/wireguard/qemu/.gitignore b/tools/testing/selftests/wireguard/qemu/.gitignore index bfa15e6feb2f..42ab9d72b37b 100644 --- a/tools/testing/selftests/wireguard/qemu/.gitignore +++ b/tools/testing/selftests/wireguard/qemu/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only build/ distfiles/ +ccache/ diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile index 930f59c9e714..e121ef3878af 100644 --- a/tools/testing/selftests/wireguard/qemu/Makefile +++ b/tools/testing/selftests/wireguard/qemu/Makefile @@ -266,6 +266,13 @@ $(info Building for $(CHOST) using $(CBUILD)) export CROSS_COMPILE := $(CHOST)- export PATH := $(TOOLCHAIN_PATH)/bin:$(PATH) export CC := $(CHOST)-gcc +CCACHE_PATH := $(shell which ccache 2>/dev/null) +ifneq ($(CCACHE_PATH),) +export KBUILD_BUILD_TIMESTAMP := Fri Jun 5 15:58:00 CEST 2015 +export PATH := $(TOOLCHAIN_PATH)/bin/ccache:$(PATH) +export CCACHE_SLOPPINESS := file_macro,time_macros +export CCACHE_DIR ?= $(PWD)/ccache +endif USERSPACE_DEPS := $(TOOLCHAIN_PATH)/.installed $(TOOLCHAIN_PATH)/$(CHOST)/include/linux/.installed @@ -329,6 +336,10 @@ $(TOOLCHAIN_PATH)/.installed: $(TOOLCHAIN_TAR) mkdir -p $(BUILD_PATH) flock -s $<.lock tar -C $(BUILD_PATH) -xf $< $(STRIP) -s $(TOOLCHAIN_PATH)/$(CHOST)/lib/libc.so +ifneq ($(CCACHE_PATH),) + mkdir -p $(TOOLCHAIN_PATH)/bin/ccache + ln -s $(CCACHE_PATH) $(TOOLCHAIN_PATH)/bin/ccache/$(CC) +endif touch $@ $(IPERF_PATH)/.installed: $(IPERF_TAR) @@ -421,8 +432,13 @@ clean: distclean: clean rm -rf $(DISTFILES_PATH) +cacheclean: clean +ifneq ($(CCACHE_DIR),) + rm -rf $(CCACHE_DIR) +endif + menuconfig: $(KERNEL_BUILD_PATH)/.config $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) menuconfig -.PHONY: qemu build clean distclean menuconfig +.PHONY: qemu build clean distclean cacheclean menuconfig .DELETE_ON_ERROR: From a6b8ea9144340c0aaa66c817a3bbb6bca47f0321 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 4 May 2022 22:29:19 +0200 Subject: [PATCH 148/192] wireguard: selftests: bump package deps Use newer, more reliable package dependencies. These should hopefully reduce flakes. However, we keep the old iputils package, as it accumulated bugs after resulting in flakes on slow machines. Signed-off-by: Jason A. Donenfeld Signed-off-by: Jakub Kicinski --- .../testing/selftests/wireguard/qemu/Makefile | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile index e121ef3878af..bca07b93eeb0 100644 --- a/tools/testing/selftests/wireguard/qemu/Makefile +++ b/tools/testing/selftests/wireguard/qemu/Makefile @@ -39,13 +39,13 @@ $(DISTFILES_PATH)/$(1): | $(4) flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if ([ -n "$(4)" ] && sed -n "s#^\([a-f0-9]\{64\}\) \($(1)\)\$$$$#\1 $(DISTFILES_PATH)/\2.tmp#p" "$(4)" || echo "$(3) $$@.tmp") | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi' endef -$(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c)) -$(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d)) -$(eval $(call tar_download,IPROUTE2,iproute2,5.6.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,1b5b0e25ce6e23da7526ea1da044e814ad85ba761b10dd29c2b027c056b04692)) -$(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c)) -$(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa)) +$(eval $(call tar_download,IPERF,iperf,3.11,.tar.gz,https://downloads.es.net/pub/iperf/,de8cb409fad61a0574f4cb07eb19ce1159707403ac2dc01b5d175e91240b7e5f)) +$(eval $(call tar_download,BASH,bash,5.1.16,.tar.gz,https://ftp.gnu.org/gnu/bash/,5bac17218d3911834520dad13cd1f85ab944e1c09ae1aba55906be1f8192f558)) +$(eval $(call tar_download,IPROUTE2,iproute2,5.17.0,.tar.gz,https://www.kernel.org/pub/linux/utils/net/iproute2/,bda331d5c4606138892f23a565d78fca18919b4d508a0b7ca8391c2da2db68b9)) +$(eval $(call tar_download,IPTABLES,iptables,1.8.7,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,c109c96bb04998cd44156622d36f8e04b140701ec60531a10668cfdff5e8d8f0)) +$(eval $(call tar_download,NMAP,nmap,7.92,.tgz,https://nmap.org/dist/,064183ea642dc4c12b1ab3b5358ce1cef7d2e7e11ffa2849f16d339f5b717117)) $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a)) -$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64)) +$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20210914,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,97ff31489217bb265b7ae850d3d0f335ab07d2652ba1feec88b734bc96bd05ac)) export CFLAGS := -O3 -pipe ifeq ($(HOST_ARCH),$(ARCH)) @@ -385,15 +385,15 @@ $(BASH_PATH)/.installed: $(BASH_TAR) touch $@ $(BASH_PATH)/bash: | $(BASH_PATH)/.installed $(USERSPACE_DEPS) - cd $(BASH_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --without-bash-malloc --disable-debugger --disable-help-builtin --disable-history --disable-multibyte --disable-progcomp --disable-readline --disable-mem-scramble + cd $(BASH_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --without-bash-malloc --disable-debugger --disable-help-builtin --disable-history --disable-progcomp --disable-readline --disable-mem-scramble $(MAKE) -C $(BASH_PATH) $(STRIP) -s $@ $(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR) mkdir -p $(BUILD_PATH) flock -s $<.lock tar -C $(BUILD_PATH) -xf $< - printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS\n' > $(IPROUTE2_PATH)/config.mk - printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile + printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_HANDLE_AT\n' > $(IPROUTE2_PATH)/config.mk + printf 'libutil.a.done:\n\tflock -x $$@.lock $$(MAKE) -C lib\n\ttouch $$@\nip/ip: libutil.a.done\n\t$$(MAKE) -C ip ip\nmisc/ss: libutil.a.done\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile touch $@ $(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS) From 3fc1b11e5d7278437bdfff0e01f51e777eefb222 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 4 May 2022 22:29:20 +0200 Subject: [PATCH 149/192] wireguard: selftests: set panic_on_warn=1 from cmdline Rather than setting this once init is running, set panic_on_warn from the kernel command line, so that it catches splats from WireGuard initialization code and the various crypto selftests. Signed-off-by: Jason A. Donenfeld Signed-off-by: Jakub Kicinski --- tools/testing/selftests/wireguard/qemu/arch/aarch64.config | 2 +- .../testing/selftests/wireguard/qemu/arch/aarch64_be.config | 2 +- tools/testing/selftests/wireguard/qemu/arch/arm.config | 2 +- tools/testing/selftests/wireguard/qemu/arch/armeb.config | 2 +- tools/testing/selftests/wireguard/qemu/arch/i686.config | 2 +- tools/testing/selftests/wireguard/qemu/arch/m68k.config | 2 +- tools/testing/selftests/wireguard/qemu/arch/mips.config | 2 +- tools/testing/selftests/wireguard/qemu/arch/mips64.config | 2 +- tools/testing/selftests/wireguard/qemu/arch/mips64el.config | 2 +- tools/testing/selftests/wireguard/qemu/arch/mipsel.config | 2 +- tools/testing/selftests/wireguard/qemu/arch/powerpc.config | 2 +- .../testing/selftests/wireguard/qemu/arch/powerpc64.config | 2 +- .../selftests/wireguard/qemu/arch/powerpc64le.config | 2 +- tools/testing/selftests/wireguard/qemu/arch/riscv32.config | 2 +- tools/testing/selftests/wireguard/qemu/arch/riscv64.config | 2 +- tools/testing/selftests/wireguard/qemu/arch/s390x.config | 2 +- tools/testing/selftests/wireguard/qemu/arch/x86_64.config | 2 +- tools/testing/selftests/wireguard/qemu/init.c | 6 ------ 18 files changed, 17 insertions(+), 23 deletions(-) diff --git a/tools/testing/selftests/wireguard/qemu/arch/aarch64.config b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config index e9ac41f6b3ae..09016880ce03 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/aarch64.config +++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config @@ -4,5 +4,5 @@ CONFIG_VIRTIO_MENU=y CONFIG_VIRTIO_MMIO=y CONFIG_VIRTIO_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1" +CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1 panic_on_warn=1" CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config index 03609a203e8c..19ff66e4c602 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config +++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config @@ -5,5 +5,5 @@ CONFIG_VIRTIO_MENU=y CONFIG_VIRTIO_MMIO=y CONFIG_VIRTIO_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1" +CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1 panic_on_warn=1" CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/arm.config b/tools/testing/selftests/wireguard/qemu/arch/arm.config index c616124fdd59..fc7959bef9c2 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/arm.config +++ b/tools/testing/selftests/wireguard/qemu/arch/arm.config @@ -8,5 +8,5 @@ CONFIG_VIRTIO_MENU=y CONFIG_VIRTIO_MMIO=y CONFIG_VIRTIO_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1" +CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1 panic_on_warn=1" CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/armeb.config b/tools/testing/selftests/wireguard/qemu/arch/armeb.config index d3a40a974e16..f3066be81c19 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/armeb.config +++ b/tools/testing/selftests/wireguard/qemu/arch/armeb.config @@ -8,6 +8,6 @@ CONFIG_VIRTIO_MENU=y CONFIG_VIRTIO_MMIO=y CONFIG_VIRTIO_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1" +CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1 panic_on_warn=1" CONFIG_CPU_BIG_ENDIAN=y CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/i686.config b/tools/testing/selftests/wireguard/qemu/arch/i686.config index a9b4fe795048..6d90892a85a2 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/i686.config +++ b/tools/testing/selftests/wireguard/qemu/arch/i686.config @@ -2,5 +2,5 @@ CONFIG_ACPI=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/m68k.config b/tools/testing/selftests/wireguard/qemu/arch/m68k.config index 62a15bdb877e..82c925e49beb 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/m68k.config +++ b/tools/testing/selftests/wireguard/qemu/arch/m68k.config @@ -5,5 +5,5 @@ CONFIG_MAC=y CONFIG_SERIAL_PMACZILOG=y CONFIG_SERIAL_PMACZILOG_TTYS=y CONFIG_SERIAL_PMACZILOG_CONSOLE=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips.config b/tools/testing/selftests/wireguard/qemu/arch/mips.config index df71d6b95546..d7ec63c17b30 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/mips.config +++ b/tools/testing/selftests/wireguard/qemu/arch/mips.config @@ -7,5 +7,5 @@ CONFIG_POWER_RESET_SYSCON=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips64.config b/tools/testing/selftests/wireguard/qemu/arch/mips64.config index 90c783f725c4..0994947e3392 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/mips64.config +++ b/tools/testing/selftests/wireguard/qemu/arch/mips64.config @@ -10,5 +10,5 @@ CONFIG_POWER_RESET_SYSCON=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips64el.config b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config index 435b0b43e00c..591184342f47 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/mips64el.config +++ b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config @@ -11,5 +11,5 @@ CONFIG_POWER_RESET_SYSCON=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mipsel.config b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config index 62bb50c4a85f..18a498293737 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/mipsel.config +++ b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config @@ -8,5 +8,5 @@ CONFIG_POWER_RESET_SYSCON=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config index 57957093b71b..5e04882e8e35 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/powerpc.config +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config @@ -6,5 +6,5 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_MATH_EMULATION=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64.config index c19c7b519d8b..737194b7619e 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/powerpc64.config +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64.config @@ -7,7 +7,7 @@ CONFIG_PPC_RADIX_MMU=y CONFIG_HVC_CONSOLE=y CONFIG_CPU_BIG_ENDIAN=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=hvc0 wg.success=hvc1" +CONFIG_CMDLINE="console=hvc0 wg.success=hvc1 panic_on_warn=1" CONFIG_SECTION_MISMATCH_WARN_ONLY=y CONFIG_FRAME_WARN=1280 CONFIG_THREAD_SHIFT=14 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config index f52f1e2bc7f6..8148b9d1220a 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config @@ -7,7 +7,7 @@ CONFIG_PPC_RADIX_MMU=y CONFIG_HVC_CONSOLE=y CONFIG_CPU_LITTLE_ENDIAN=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=hvc0 wg.success=hvc1" +CONFIG_CMDLINE="console=hvc0 wg.success=hvc1 panic_on_warn=1" CONFIG_SECTION_MISMATCH_WARN_ONLY=y CONFIG_FRAME_WARN=1280 CONFIG_THREAD_SHIFT=14 diff --git a/tools/testing/selftests/wireguard/qemu/arch/riscv32.config b/tools/testing/selftests/wireguard/qemu/arch/riscv32.config index ea53e78e923e..0bd0e72d95d4 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/riscv32.config +++ b/tools/testing/selftests/wireguard/qemu/arch/riscv32.config @@ -8,5 +8,5 @@ CONFIG_SERIAL_OF_PLATFORM=y CONFIG_VIRTIO_MENU=y CONFIG_VIRTIO_MMIO=y CONFIG_VIRTIO_CONSOLE=y -CONFIG_CMDLINE="console=ttyS0 wg.success=vport0p1" +CONFIG_CMDLINE="console=ttyS0 wg.success=vport0p1 panic_on_warn=1" CONFIG_CMDLINE_FORCE=y diff --git a/tools/testing/selftests/wireguard/qemu/arch/riscv64.config b/tools/testing/selftests/wireguard/qemu/arch/riscv64.config index 4a08d8c1d4af..dc266f3b1915 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/riscv64.config +++ b/tools/testing/selftests/wireguard/qemu/arch/riscv64.config @@ -8,5 +8,5 @@ CONFIG_SERIAL_OF_PLATFORM=y CONFIG_VIRTIO_MENU=y CONFIG_VIRTIO_MMIO=y CONFIG_VIRTIO_CONSOLE=y -CONFIG_CMDLINE="console=ttyS0 wg.success=vport0p1" +CONFIG_CMDLINE="console=ttyS0 wg.success=vport0p1 panic_on_warn=1" CONFIG_CMDLINE_FORCE=y diff --git a/tools/testing/selftests/wireguard/qemu/arch/s390x.config b/tools/testing/selftests/wireguard/qemu/arch/s390x.config index 274a44f4e49c..a7b44dca0b0a 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/s390x.config +++ b/tools/testing/selftests/wireguard/qemu/arch/s390x.config @@ -3,4 +3,4 @@ CONFIG_SCLP_VT220_CONSOLE=y CONFIG_VIRTIO_MENU=y CONFIG_VIRTIO_CONSOLE=y CONFIG_S390_GUEST=y -CONFIG_CMDLINE="console=ttysclp0 wg.success=vport0p1" +CONFIG_CMDLINE="console=ttysclp0 wg.success=vport0p1 panic_on_warn=1" diff --git a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config index 45dd53a0d760..efa00693e08b 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config +++ b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config @@ -2,5 +2,5 @@ CONFIG_ACPI=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1" CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/init.c b/tools/testing/selftests/wireguard/qemu/init.c index 0b45055d9de0..2a0f48fac925 100644 --- a/tools/testing/selftests/wireguard/qemu/init.c +++ b/tools/testing/selftests/wireguard/qemu/init.c @@ -110,12 +110,6 @@ static void enable_logging(void) panic("write(exception-trace)"); close(fd); } - fd = open("/proc/sys/kernel/panic_on_warn", O_WRONLY); - if (fd >= 0) { - if (write(fd, "1\n", 2) != 2) - panic("write(panic_on_warn)"); - close(fd); - } } static void kmod_selftests(void) From b2d057560b8107c633b39aabe517ff9d93f285e3 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 2 May 2022 10:46:08 +0200 Subject: [PATCH 150/192] secure_seq: use the 64 bits of the siphash for port offset calculation SipHash replaced MD5 in secure_ipv{4,6}_port_ephemeral() via commit 7cd23e5300c1 ("secure_seq: use SipHash in place of MD5"), but the output remained truncated to 32-bit only. In order to exploit more bits from the hash, let's make the functions return the full 64-bit of siphash_3u32(). We also make sure the port offset calculation in __inet_hash_connect() remains done on 32-bit to avoid the need for div_u64_rem() and an extra cost on 32-bit systems. Cc: Jason A. Donenfeld Cc: Moshe Kol Cc: Yossi Gilad Cc: Amit Klein Reviewed-by: Eric Dumazet Signed-off-by: Willy Tarreau Signed-off-by: Jakub Kicinski --- include/net/inet_hashtables.h | 2 +- include/net/secure_seq.h | 4 ++-- net/core/secure_seq.c | 4 ++-- net/ipv4/inet_hashtables.c | 10 ++++++---- net/ipv6/inet6_hashtables.c | 4 ++-- 5 files changed, 13 insertions(+), 11 deletions(-) diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index f72ec113ae56..98e1ec1a14f0 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -425,7 +425,7 @@ static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr) } int __inet_hash_connect(struct inet_timewait_death_row *death_row, - struct sock *sk, u32 port_offset, + struct sock *sk, u64 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, struct inet_timewait_sock **)); diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index d7d2495f83c2..dac91aa38c5a 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -4,8 +4,8 @@ #include -u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); -u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, +u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); +u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); u32 secure_tcp_seq(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport); diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 9b8443774449..55aa5cc258e3 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -94,7 +94,7 @@ u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, } EXPORT_SYMBOL(secure_tcpv6_seq); -u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, +u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) { const struct { @@ -142,7 +142,7 @@ u32 secure_tcp_seq(__be32 saddr, __be32 daddr, } EXPORT_SYMBOL_GPL(secure_tcp_seq); -u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) +u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { net_secret_init(); return siphash_3u32((__force u32)saddr, (__force u32)daddr, diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 17440840a791..9d24d9319f3d 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -504,7 +504,7 @@ not_unique: return -EADDRNOTAVAIL; } -static u32 inet_sk_port_offset(const struct sock *sk) +static u64 inet_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); @@ -734,7 +734,7 @@ EXPORT_SYMBOL_GPL(inet_unhash); static u32 table_perturb[1 << INET_TABLE_PERTURB_SHIFT]; int __inet_hash_connect(struct inet_timewait_death_row *death_row, - struct sock *sk, u32 port_offset, + struct sock *sk, u64 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, struct inet_timewait_sock **)) { @@ -777,7 +777,9 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, net_get_random_once(table_perturb, sizeof(table_perturb)); index = hash_32(port_offset, INET_TABLE_PERTURB_SHIFT); - offset = (READ_ONCE(table_perturb[index]) + port_offset) % remaining; + offset = READ_ONCE(table_perturb[index]) + port_offset; + offset %= remaining; + /* In first pass we try ports of @low parity. * inet_csk_get_port() does the opposite choice. */ @@ -859,7 +861,7 @@ ok: int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { - u32 port_offset = 0; + u64 port_offset = 0; if (!inet_sk(sk)->inet_num) port_offset = inet_sk_port_offset(sk); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 4740afecf7c6..32ccac10bd62 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -308,7 +308,7 @@ not_unique: return -EADDRNOTAVAIL; } -static u32 inet6_sk_port_offset(const struct sock *sk) +static u64 inet6_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); @@ -320,7 +320,7 @@ static u32 inet6_sk_port_offset(const struct sock *sk) int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { - u32 port_offset = 0; + u64 port_offset = 0; if (!inet_sk(sk)->inet_num) port_offset = inet6_sk_port_offset(sk); From 9e9b70ae923baf2b5e8a0ea4fd0c8451801ac526 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 2 May 2022 10:46:09 +0200 Subject: [PATCH 151/192] tcp: use different parts of the port_offset for index and offset Amit Klein suggests that we use different parts of port_offset for the table's index and the port offset so that there is no direct relation between them. Cc: Jason A. Donenfeld Cc: Moshe Kol Cc: Yossi Gilad Cc: Amit Klein Reviewed-by: Eric Dumazet Signed-off-by: Willy Tarreau Signed-off-by: Jakub Kicinski --- net/ipv4/inet_hashtables.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 9d24d9319f3d..29c701cd8312 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -777,7 +777,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, net_get_random_once(table_perturb, sizeof(table_perturb)); index = hash_32(port_offset, INET_TABLE_PERTURB_SHIFT); - offset = READ_ONCE(table_perturb[index]) + port_offset; + offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32); offset %= remaining; /* In first pass we try ports of @low parity. From 4dfa9b438ee34caca4e6a4e5e961641807367f6f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 2 May 2022 10:46:10 +0200 Subject: [PATCH 152/192] tcp: resalt the secret every 10 seconds In order to limit the ability for an observer to recognize the source ports sequence used to contact a set of destinations, we should periodically shuffle the secret. 10 seconds looks effective enough without causing particular issues. Cc: Moshe Kol Cc: Yossi Gilad Cc: Amit Klein Cc: Jason A. Donenfeld Tested-by: Willy Tarreau Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- net/core/secure_seq.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 55aa5cc258e3..5f85e01d4093 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -22,6 +22,8 @@ static siphash_aligned_key_t net_secret; static siphash_aligned_key_t ts_secret; +#define EPHEMERAL_PORT_SHUFFLE_PERIOD (10 * HZ) + static __always_inline void net_secret_init(void) { net_get_random_once(&net_secret, sizeof(net_secret)); @@ -100,11 +102,13 @@ u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, const struct { struct in6_addr saddr; struct in6_addr daddr; + unsigned int timeseed; __be16 dport; } __aligned(SIPHASH_ALIGNMENT) combined = { .saddr = *(struct in6_addr *)saddr, .daddr = *(struct in6_addr *)daddr, - .dport = dport + .timeseed = jiffies / EPHEMERAL_PORT_SHUFFLE_PERIOD, + .dport = dport, }; net_secret_init(); return siphash(&combined, offsetofend(typeof(combined), dport), @@ -145,8 +149,10 @@ EXPORT_SYMBOL_GPL(secure_tcp_seq); u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { net_secret_init(); - return siphash_3u32((__force u32)saddr, (__force u32)daddr, - (__force u16)dport, &net_secret); + return siphash_4u32((__force u32)saddr, (__force u32)daddr, + (__force u16)dport, + jiffies / EPHEMERAL_PORT_SHUFFLE_PERIOD, + &net_secret); } EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral); #endif From ca7af0402550f9a0b3316d5f1c30904e42ed257d Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 2 May 2022 10:46:11 +0200 Subject: [PATCH 153/192] tcp: add small random increments to the source port Here we're randomly adding between 0 and 7 random increments to the selected source port in order to add some noise in the source port selection that will make the next port less predictable. With the default port range of 32768-60999 this means a worst case reuse scenario of 14116/8=1764 connections between two consecutive uses of the same port, with an average of 14116/4.5=3137. This code was stressed at more than 800000 connections per second to a fixed target with all connections closed by the client using RSTs (worst condition) and only 2 connections failed among 13 billion, despite the hash being reseeded every 10 seconds, indicating a perfectly safe situation. Cc: Moshe Kol Cc: Yossi Gilad Cc: Amit Klein Reviewed-by: Eric Dumazet Signed-off-by: Willy Tarreau Signed-off-by: Jakub Kicinski --- net/ipv4/inet_hashtables.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 29c701cd8312..63bb4902f018 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -833,11 +833,12 @@ next_port: return -EADDRNOTAVAIL; ok: - /* If our first attempt found a candidate, skip next candidate - * in 1/16 of cases to add some noise. + /* Here we want to add a little bit of randomness to the next source + * port that will be chosen. We use a max() with a random here so that + * on low contention the randomness is maximal and on high contention + * it may be inexistent. */ - if (!i && !(prandom_u32() % 16)) - i = 2; + i = max_t(int, i, (prandom_u32() & 7) * 2); WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2); /* Head lock still held and bh's disabled */ From e9261476184be1abd486c9434164b2acbe0ed6c2 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 2 May 2022 10:46:12 +0200 Subject: [PATCH 154/192] tcp: dynamically allocate the perturb table used by source ports We'll need to further increase the size of this table and it's likely that at some point its size will not be suitable anymore for a static table. Let's allocate it on boot from inet_hashinfo2_init(), which is called from tcp_init(). Cc: Moshe Kol Cc: Yossi Gilad Cc: Amit Klein Reviewed-by: Eric Dumazet Signed-off-by: Willy Tarreau Signed-off-by: Jakub Kicinski --- net/ipv4/inet_hashtables.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 63bb4902f018..48ca07853068 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -731,7 +731,8 @@ EXPORT_SYMBOL_GPL(inet_unhash); * privacy, this only consumes 1 KB of kernel memory. */ #define INET_TABLE_PERTURB_SHIFT 8 -static u32 table_perturb[1 << INET_TABLE_PERTURB_SHIFT]; +#define INET_TABLE_PERTURB_SIZE (1 << INET_TABLE_PERTURB_SHIFT) +static u32 *table_perturb; int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u64 port_offset, @@ -774,7 +775,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, if (likely(remaining > 1)) remaining &= ~1U; - net_get_random_once(table_perturb, sizeof(table_perturb)); + net_get_random_once(table_perturb, + INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb)); index = hash_32(port_offset, INET_TABLE_PERTURB_SHIFT); offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32); @@ -912,6 +914,12 @@ void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, low_limit, high_limit); init_hashinfo_lhash2(h); + + /* this one is used for source ports of outgoing connections */ + table_perturb = kmalloc_array(INET_TABLE_PERTURB_SIZE, + sizeof(*table_perturb), GFP_KERNEL); + if (!table_perturb) + panic("TCP: failed to alloc table_perturb"); } int inet_hashinfo2_init_mod(struct inet_hashinfo *h) From 4c2c8f03a5ab7cb04ec64724d7d176d00bcc91e5 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 2 May 2022 10:46:13 +0200 Subject: [PATCH 155/192] tcp: increase source port perturb table to 2^16 Moshe Kol, Amit Klein, and Yossi Gilad reported being able to accurately identify a client by forcing it to emit only 40 times more connections than there are entries in the table_perturb[] table. The previous two improvements consisting in resalting the secret every 10s and adding randomness to each port selection only slightly improved the situation, and the current value of 2^8 was too small as it's not very difficult to make a client emit 10k connections in less than 10 seconds. Thus we're increasing the perturb table from 2^8 to 2^16 so that the same precision now requires 2.6M connections, which is more difficult in this time frame and harder to hide as a background activity. The impact is that the table now uses 256 kB instead of 1 kB, which could mostly affect devices making frequent outgoing connections. However such components usually target a small set of destinations (load balancers, database clients, perf assessment tools), and in practice only a few entries will be visited, like before. A live test at 1 million connections per second showed no performance difference from the previous value. Reported-by: Moshe Kol Reported-by: Yossi Gilad Reported-by: Amit Klein Reviewed-by: Eric Dumazet Signed-off-by: Willy Tarreau Signed-off-by: Jakub Kicinski --- net/ipv4/inet_hashtables.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 48ca07853068..cc5f66328b47 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -726,11 +726,12 @@ EXPORT_SYMBOL_GPL(inet_unhash); * Note that we use 32bit integers (vs RFC 'short integers') * because 2^16 is not a multiple of num_ephemeral and this * property might be used by clever attacker. - * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, - * we use 256 instead to really give more isolation and - * privacy, this only consumes 1 KB of kernel memory. + * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though + * attacks were since demonstrated, thus we use 65536 instead to really + * give more isolation and privacy, at the expense of 256kB of kernel + * memory. */ -#define INET_TABLE_PERTURB_SHIFT 8 +#define INET_TABLE_PERTURB_SHIFT 16 #define INET_TABLE_PERTURB_SIZE (1 << INET_TABLE_PERTURB_SHIFT) static u32 *table_perturb; From e8161345ddbb66e449abde10d2fdce93f867eba9 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Mon, 2 May 2022 10:46:14 +0200 Subject: [PATCH 156/192] tcp: drop the hash_32() part from the index calculation In commit 190cc82489f4 ("tcp: change source port randomizarion at connect() time"), the table_perturb[] array was introduced and an index was taken from the port_offset via hash_32(). But it turns out that hash_32() performs a multiplication while the input here comes from the output of SipHash in secure_seq, that is well distributed enough to avoid the need for yet another hash. Suggested-by: Amit Klein Reviewed-by: Eric Dumazet Signed-off-by: Willy Tarreau Signed-off-by: Jakub Kicinski --- net/ipv4/inet_hashtables.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index cc5f66328b47..a5d57fa679ca 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -778,7 +778,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, net_get_random_once(table_perturb, INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb)); - index = hash_32(port_offset, INET_TABLE_PERTURB_SHIFT); + index = port_offset & (INET_TABLE_PERTURB_SIZE - 1); offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32); offset %= remaining; From 5a7c5f70c743c6cf32b44b05bd6b19d4ad82f49d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 3 May 2022 15:14:28 +0300 Subject: [PATCH 157/192] selftests: ocelot: tc_flower_chains: specify conform-exceed action for policer As discussed here with Ido Schimmel: https://patchwork.kernel.org/project/netdevbpf/patch/20220224102908.5255-2-jianbol@nvidia.com/ the default conform-exceed action is "reclassify", for a reason we don't really understand. The point is that hardware can't offload that police action, so not specifying "conform-exceed" was always wrong, even though the command used to work in hardware (but not in software) until the kernel started adding validation for it. Fix the command used by the selftest by making the policer drop on exceed, and pass the packet to the next action (goto) on conform. Fixes: 8cd6b020b644 ("selftests: ocelot: add some example VCAP IS1, IS2 and ES0 tc offloads") Signed-off-by: Vladimir Oltean Reviewed-by: Ido Schimmel Link: https://lore.kernel.org/r/20220503121428.842906-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh index eaf8a04a7ca5..10e54bcca7a9 100755 --- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh +++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh @@ -190,7 +190,7 @@ setup_prepare() tc filter add dev $eth0 ingress chain $(IS2 0 0) pref 1 \ protocol ipv4 flower skip_sw ip_proto udp dst_port 5201 \ - action police rate 50mbit burst 64k \ + action police rate 50mbit burst 64k conform-exceed drop/pipe \ action goto chain $(IS2 1 0) } From 170f37d6aa6ad4582eefd7459015de79e244536e Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 3 May 2022 00:09:31 -0400 Subject: [PATCH 158/192] block: Do not call folio_next() on an unreferenced folio It is unsafe to call folio_next() on a folio unless you hold a reference on it that prevents it from being split or freed. After returning from the iterator, iomap calls folio_end_writeback() which may drop the last reference to the page, or allow the page to be split. If that happens, the iterator will not advance far enough through the bio_vec, leading to assertion failures like the BUG() in folio_end_writeback() that checks we're not trying to end writeback on a page not currently under writeback. Other assertion failures were also seen, but they're all explained by this one bug. Fix the bug by remembering where the next folio starts before returning from the iterator. There are other ways of fixing this bug, but this seems the simplest. Reported-by: Darrick J. Wong Tested-by: Darrick J. Wong Reported-by: Brian Foster Tested-by: Brian Foster Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/bio.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/include/linux/bio.h b/include/linux/bio.h index 278cc81cc1e7..00450fd86bb4 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -269,6 +269,7 @@ struct folio_iter { size_t offset; size_t length; /* private: for use by the iterator */ + struct folio *_next; size_t _seg_count; int _i; }; @@ -283,6 +284,7 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio, PAGE_SIZE * (bvec->bv_page - &fi->folio->page); fi->_seg_count = bvec->bv_len; fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count); + fi->_next = folio_next(fi->folio); fi->_i = i; } @@ -290,9 +292,10 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) { fi->_seg_count -= fi->length; if (fi->_seg_count) { - fi->folio = folio_next(fi->folio); + fi->folio = fi->_next; fi->offset = 0; fi->length = min(folio_size(fi->folio), fi->_seg_count); + fi->_next = folio_next(fi->folio); } else if (fi->_i + 1 < bio->bi_vcnt) { bio_first_folio(fi, bio, fi->_i + 1); } else { From b9ff43dd27434dbd850b908e2e0e1f6e794efd9b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 27 Apr 2022 17:01:28 -0400 Subject: [PATCH 159/192] mm/readahead: Fix readahead with large folios Reading 100KB chunks from a big file (eg dd bs=100K) leads to poor readahead behaviour. Studying the traces in detail, I noticed two problems. The first is that we were setting the readahead flag on the folio which contains the last byte read from the block. This is wrong because we will trigger readahead at the end of the read without waiting to see if a subsequent read is going to use the pages we just read. Instead, we need to set the readahead flag on the first folio _after_ the one which contains the last byte that we're reading. The second is that we were looking for the index of the folio with the readahead flag set to exactly match the start + size - async_size. If we've rounded this, either down (as previously) or up (as now), we'll think we hit a folio marked as readahead by a different read, and try to read the wrong pages. So round the expected index to the order of the folio we hit. Reported-by: Guo Xuenan Signed-off-by: Matthew Wilcox (Oracle) --- mm/readahead.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/mm/readahead.c b/mm/readahead.c index 8e3775829513..4a60cdb64262 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -474,7 +474,8 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, if (!folio) return -ENOMEM; - if (mark - index < (1UL << order)) + mark = round_up(mark, 1UL << order); + if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); if (err) @@ -555,8 +556,9 @@ static void ondemand_readahead(struct readahead_control *ractl, struct file_ra_state *ra = ractl->ra; unsigned long max_pages = ra->ra_pages; unsigned long add_pages; - unsigned long index = readahead_index(ractl); - pgoff_t prev_index; + pgoff_t index = readahead_index(ractl); + pgoff_t expected, prev_index; + unsigned int order = folio ? folio_order(folio) : 0; /* * If the request exceeds the readahead window, allow the read to @@ -575,8 +577,9 @@ static void ondemand_readahead(struct readahead_control *ractl, * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ - if ((index == (ra->start + ra->size - ra->async_size) || - index == (ra->start + ra->size))) { + expected = round_up(ra->start + ra->size - ra->async_size, + 1UL << order); + if (index == expected || index == (ra->start + ra->size)) { ra->start += ra->size; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; @@ -662,7 +665,7 @@ readit: } ractl->_index = ra->start; - page_cache_ra_order(ractl, ra, folio ? folio_order(folio) : 0); + page_cache_ra_order(ractl, ra, order); } void page_cache_sync_ra(struct readahead_control *ractl, From 4071bf121d59944d5cd2238de0642f3d7995a997 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Wed, 4 May 2022 13:58:47 +0800 Subject: [PATCH 160/192] NFC: netlink: fix sleep in atomic bug when firmware download timeout There are sleep in atomic bug that could cause kernel panic during firmware download process. The root cause is that nlmsg_new with GFP_KERNEL parameter is called in fw_dnld_timeout which is a timer handler. The call trace is shown below: BUG: sleeping function called from invalid context at include/linux/sched/mm.h:265 Call Trace: kmem_cache_alloc_node __alloc_skb nfc_genl_fw_download_done call_timer_fn __run_timers.part.0 run_timer_softirq __do_softirq ... The nlmsg_new with GFP_KERNEL parameter may sleep during memory allocation process, and the timer handler is run as the result of a "software interrupt" that should not call any other function that could sleep. This patch changes allocation mode of netlink message from GFP_KERNEL to GFP_ATOMIC in order to prevent sleep in atomic bug. The GFP_ATOMIC flag makes memory allocation operation could be used in atomic context. Fixes: 9674da8759df ("NFC: Add firmware upload netlink command") Fixes: 9ea7187c53f6 ("NFC: netlink: Rename CMD_FW_UPLOAD to CMD_FW_DOWNLOAD") Signed-off-by: Duoming Zhou Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20220504055847.38026-1-duoming@zju.edu.cn Signed-off-by: Paolo Abeni --- net/nfc/netlink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index f184b0db79d4..7c62417ccfd7 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1244,7 +1244,7 @@ int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name, struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; @@ -1260,7 +1260,7 @@ int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name, genlmsg_end(msg, hdr); - genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); + genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); return 0; From 2d3535ed2c73fee356160aed40714b27be07442a Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 2 May 2022 11:34:16 +0200 Subject: [PATCH 161/192] MAINTAINERS: update the GPIO git tree entry My git tree has become the de facto main GPIO tree. Update the MAINTAINERS file to reflect that. Signed-off-by: Bartosz Golaszewski Reported-by: Baruch Siach Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index edc96cdb85e8..9d47c5e7c6ae 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8385,7 +8385,7 @@ M: Linus Walleij M: Bartosz Golaszewski L: linux-gpio@vger.kernel.org S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git F: Documentation/ABI/obsolete/sysfs-gpio F: Documentation/ABI/testing/gpio-cdev F: Documentation/admin-guide/gpio/ From 8707898e22fd665bc1d7b18b809be4b56ce25bdd Mon Sep 17 00:00:00 2001 From: Thomas Pfaff Date: Mon, 2 May 2022 13:28:29 +0200 Subject: [PATCH 162/192] genirq: Synchronize interrupt thread startup A kernel hang can be observed when running setserial in a loop on a kernel with force threaded interrupts. The sequence of events is: setserial open("/dev/ttyXXX") request_irq() do_stuff() -> serial interrupt -> wake(irq_thread) desc->threads_active++; close() free_irq() kthread_stop(irq_thread) synchronize_irq() <- hangs because desc->threads_active != 0 The thread is created in request_irq() and woken up, but does not get on a CPU to reach the actual thread function, which would handle the pending wake-up. kthread_stop() sets the should stop condition which makes the thread immediately exit, which in turn leaves the stale threads_active count around. This problem was introduced with commit 519cc8652b3a, which addressed a interrupt sharing issue in the PCIe code. Before that commit free_irq() invoked synchronize_irq(), which waits for the hard interrupt handler and also for associated threads to complete. To address the PCIe issue synchronize_irq() was replaced with __synchronize_hardirq(), which only waits for the hard interrupt handler to complete, but not for threaded handlers. This was done under the assumption, that the interrupt thread already reached the thread function and waits for a wake-up, which is guaranteed to be handled before acting on the stop condition. The problematic case, that the thread would not reach the thread function, was obviously overlooked. Make sure that the interrupt thread is really started and reaches thread_fn() before returning from __setup_irq(). This utilizes the existing wait queue in the interrupt descriptor. The wait queue is unused for non-shared interrupts. For shared interrupts the usage might cause a spurious wake-up of a waiter in synchronize_irq() or the completion of a threaded handler might cause a spurious wake-up of the waiter for the ready flag. Both are harmless and have no functional impact. [ tglx: Amended changelog ] Fixes: 519cc8652b3a ("genirq: Synchronize only with single thread on free_irq()") Signed-off-by: Thomas Pfaff Signed-off-by: Thomas Gleixner Reviewed-by: Marc Zyngier Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/552fe7b4-9224-b183-bb87-a8f36d335690@pcs.com --- kernel/irq/internals.h | 2 ++ kernel/irq/irqdesc.c | 2 ++ kernel/irq/manage.c | 39 +++++++++++++++++++++++++++++---------- 3 files changed, 33 insertions(+), 10 deletions(-) diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 99cbdf55a8bd..f09c60393e55 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -29,12 +29,14 @@ extern struct irqaction chained_action; * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed * IRQTF_AFFINITY - irq thread is requested to adjust affinity * IRQTF_FORCED_THREAD - irq action is force threaded + * IRQTF_READY - signals that irq thread is ready */ enum { IRQTF_RUNTHREAD, IRQTF_WARNED, IRQTF_AFFINITY, IRQTF_FORCED_THREAD, + IRQTF_READY, }; /* diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 939d21cd55c3..0099b87dd853 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -407,6 +407,7 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, lockdep_set_class(&desc->lock, &irq_desc_lock_class); mutex_init(&desc->request_mutex); init_rcu_head(&desc->rcu); + init_waitqueue_head(&desc->wait_for_threads); desc_set_defaults(irq, desc, node, affinity, owner); irqd_set(&desc->irq_data, flags); @@ -575,6 +576,7 @@ int __init early_irq_init(void) raw_spin_lock_init(&desc[i].lock); lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); mutex_init(&desc[i].request_mutex); + init_waitqueue_head(&desc[i].wait_for_threads); desc_set_defaults(i, &desc[i], node, NULL, NULL); } return arch_early_irq_init(); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index c03f71d5ec10..e3e245a4fd70 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1248,6 +1248,31 @@ static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action) raw_spin_unlock_irq(&desc->lock); } +/* + * Internal function to notify that a interrupt thread is ready. + */ +static void irq_thread_set_ready(struct irq_desc *desc, + struct irqaction *action) +{ + set_bit(IRQTF_READY, &action->thread_flags); + wake_up(&desc->wait_for_threads); +} + +/* + * Internal function to wake up a interrupt thread and wait until it is + * ready. + */ +static void wake_up_and_wait_for_irq_thread_ready(struct irq_desc *desc, + struct irqaction *action) +{ + if (!action || !action->thread) + return; + + wake_up_process(action->thread); + wait_event(desc->wait_for_threads, + test_bit(IRQTF_READY, &action->thread_flags)); +} + /* * Interrupt handler thread */ @@ -1259,6 +1284,8 @@ static int irq_thread(void *data) irqreturn_t (*handler_fn)(struct irq_desc *desc, struct irqaction *action); + irq_thread_set_ready(desc, action); + sched_set_fifo(current); if (force_irqthreads() && test_bit(IRQTF_FORCED_THREAD, @@ -1683,8 +1710,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } if (!shared) { - init_waitqueue_head(&desc->wait_for_threads); - /* Setup the type (level, edge polarity) if configured: */ if (new->flags & IRQF_TRIGGER_MASK) { ret = __irq_set_trigger(desc, @@ -1780,14 +1805,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) irq_setup_timings(desc, new); - /* - * Strictly no need to wake it up, but hung_task complains - * when no hard interrupt wakes the thread up. - */ - if (new->thread) - wake_up_process(new->thread); - if (new->secondary) - wake_up_process(new->secondary->thread); + wake_up_and_wait_for_irq_thread_ready(desc, new); + wake_up_and_wait_for_irq_thread_ready(desc, new->secondary); register_irq_proc(irq, desc); new->dir = NULL; From 171865dab096da1ab980a32eeea5d1b88cd7bc50 Mon Sep 17 00:00:00 2001 From: Nobuhiro Iwamatsu Date: Thu, 21 Apr 2022 18:42:28 +0900 Subject: [PATCH 163/192] gpio: visconti: Fix fwnode of GPIO IRQ The fwnode of GPIO IRQ must be set to its own fwnode, not the fwnode of the parent IRQ. Therefore, this sets own fwnode instead of the parent IRQ fwnode to GPIO IRQ's. Fixes: 2ad74f40dacc ("gpio: visconti: Add Toshiba Visconti GPIO support") Signed-off-by: Nobuhiro Iwamatsu Reviewed-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-visconti.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/gpio/gpio-visconti.c b/drivers/gpio/gpio-visconti.c index 47455810bdb9..e6534ea1eaa7 100644 --- a/drivers/gpio/gpio-visconti.c +++ b/drivers/gpio/gpio-visconti.c @@ -130,7 +130,6 @@ static int visconti_gpio_probe(struct platform_device *pdev) struct gpio_irq_chip *girq; struct irq_domain *parent; struct device_node *irq_parent; - struct fwnode_handle *fwnode; int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -150,14 +149,12 @@ static int visconti_gpio_probe(struct platform_device *pdev) } parent = irq_find_host(irq_parent); + of_node_put(irq_parent); if (!parent) { dev_err(dev, "No IRQ parent domain\n"); return -ENODEV; } - fwnode = of_node_to_fwnode(irq_parent); - of_node_put(irq_parent); - ret = bgpio_init(&priv->gpio_chip, dev, 4, priv->base + GPIO_IDATA, priv->base + GPIO_OSET, @@ -180,7 +177,7 @@ static int visconti_gpio_probe(struct platform_device *pdev) girq = &priv->gpio_chip.irq; girq->chip = irq_chip; - girq->fwnode = fwnode; + girq->fwnode = of_node_to_fwnode(dev->of_node); girq->parent_domain = parent; girq->child_to_parent_hwirq = visconti_gpio_child_to_parent_hwirq; girq->populate_parent_alloc_arg = visconti_gpio_populate_parent_fwspec; From 9f73f1aef98b2fa7252c0a89be64840271ce8ea0 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Fri, 1 Apr 2022 15:29:37 +0800 Subject: [PATCH 164/192] btrfs: force v2 space cache usage for subpage mount [BUG] For a 4K sector sized btrfs with v1 cache enabled and only mounted on systems with 4K page size, if it's mounted on subpage (64K page size) systems, it can cause the following warning on v1 space cache: BTRFS error (device dm-1): csum mismatch on free space cache BTRFS warning (device dm-1): failed to load free space cache for block group 84082688, rebuilding it now Although not a big deal, as kernel can rebuild it without problem, such warning will bother end users, especially if they want to switch the same btrfs seamlessly between different page sized systems. [CAUSE] V1 free space cache is still using fixed PAGE_SIZE for various bitmap, like BITS_PER_BITMAP. Such hard-coded PAGE_SIZE usage will cause various mismatch, from v1 cache size to checksum. Thus kernel will always reject v1 cache with a different PAGE_SIZE with csum mismatch. [FIX] Although we should fix v1 cache, it's already going to be marked deprecated soon. And we have v2 cache based on metadata (which is already fully subpage compatible), and it has almost everything superior than v1 cache. So just force subpage mount to use v2 cache on mount. Reported-by: Matt Corallo CC: stable@vger.kernel.org # 5.15+ Link: https://lore.kernel.org/linux-btrfs/61aa27d1-30fc-c1a9-f0f4-9df544395ec3@bluematt.me/ Reviewed-by: Josef Bacik Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 20e70eb88465..3e0acc362233 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3657,6 +3657,17 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device if (sectorsize < PAGE_SIZE) { struct btrfs_subpage_info *subpage_info; + /* + * V1 space cache has some hardcoded PAGE_SIZE usage, and is + * going to be deprecated. + * + * Force to use v2 cache for subpage case. + */ + btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE); + btrfs_set_and_info(fs_info, FREE_SPACE_TREE, + "forcing free space tree for sector size %u with page size %lu", + sectorsize, PAGE_SIZE); + btrfs_warn(fs_info, "read-write for sector size %u with page size %lu is experimental", sectorsize, PAGE_SIZE); From 549577127afeb759c29cdeeff1bdccd86e6c0dbf Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Tue, 3 May 2022 14:10:04 -0700 Subject: [PATCH 165/192] btrfs: zoned: move non-changing condition check out of the loop btrfs_zone_activate() checks if block_group->alloc_offset == block_group->zone_capacity every time it iterates the loop. But, it is not depending on the index. Move out the check and do it only once. Fixes: f9a912a3c45f ("btrfs: zoned: make zone activation multi stripe capable") Reviewed-by: Johannes Thumshirn Signed-off-by: Naohiro Aota Signed-off-by: David Sterba --- fs/btrfs/zoned.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 1b1b310c3c51..b5eb794c1e23 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1835,6 +1835,12 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) goto out_unlock; } + /* No space left */ + if (block_group->alloc_offset == block_group->zone_capacity) { + ret = false; + goto out_unlock; + } + for (i = 0; i < map->num_stripes; i++) { device = map->stripes[i].dev; physical = map->stripes[i].physical; @@ -1842,12 +1848,6 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) if (device->zone_info->max_active_zones == 0) continue; - /* No space left */ - if (block_group->alloc_offset == block_group->zone_capacity) { - ret = false; - goto out_unlock; - } - if (!btrfs_dev_set_active_zone(device, physical)) { /* Cannot activate the zone */ ret = false; From ceb4f60830a7cd38ff47b7dd54e9e06ddbaf413c Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Tue, 3 May 2022 14:10:05 -0700 Subject: [PATCH 166/192] btrfs: zoned: activate block group properly on unlimited active zone device btrfs_zone_activate() checks if it activated all the underlying zones in the loop. However, that check never hit on an unlimited activate zone device (max_active_zones == 0). Fortunately, it still works without ENOSPC because btrfs_zone_activate() returns true in the end, even if block_group->zone_is_active == 0. But, it is confusing to have non zone_is_active block group still usable for allocation. Also, we are wasting CPU time to iterate the loop every time btrfs_zone_activate() is called for the blog groups. Since error case in the loop is handled by out_unlock, we can just set zone_is_active and do the list stuff after the loop. Fixes: f9a912a3c45f ("btrfs: zoned: make zone activation multi stripe capable") Reviewed-by: Johannes Thumshirn Signed-off-by: Naohiro Aota Signed-off-by: David Sterba --- fs/btrfs/zoned.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index b5eb794c1e23..d31b0eda210f 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1853,24 +1853,18 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) ret = false; goto out_unlock; } - - /* Successfully activated all the zones */ - if (i == map->num_stripes - 1) - block_group->zone_is_active = 1; - - } + + /* Successfully activated all the zones */ + block_group->zone_is_active = 1; spin_unlock(&block_group->lock); - if (block_group->zone_is_active) { - /* For the active block group list */ - btrfs_get_block_group(block_group); + /* For the active block group list */ + btrfs_get_block_group(block_group); - spin_lock(&fs_info->zone_active_bgs_lock); - list_add_tail(&block_group->active_bg_list, - &fs_info->zone_active_bgs); - spin_unlock(&fs_info->zone_active_bgs_lock); - } + spin_lock(&fs_info->zone_active_bgs_lock); + list_add_tail(&block_group->active_bg_list, &fs_info->zone_active_bgs); + spin_unlock(&fs_info->zone_active_bgs_lock); return true; From 750ee454908e90a8792b1e2b157c2948da86e926 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 3 May 2022 11:57:02 +0100 Subject: [PATCH 167/192] btrfs: fix assertion failure when logging directory key range item When inserting a key range item (BTRFS_DIR_LOG_INDEX_KEY) while logging a directory, we don't expect the insertion to fail with -EEXIST, because we are holding the directory's log_mutex and we have dropped all existing BTRFS_DIR_LOG_INDEX_KEY keys from the log tree before we started to log the directory. However it's possible that during the logging we attempt to insert the same BTRFS_DIR_LOG_INDEX_KEY key twice, but for this to happen we need to race with insertions of items from other inodes in the subvolume's tree while we are logging a directory. Here's how this can happen: 1) We are logging a directory with inode number 1000 that has its items spread across 3 leaves in the subvolume's tree: leaf A - has index keys from the range 2 to 20 for example. The last item in the leaf corresponds to a dir item for index number 20. All these dir items were created in a past transaction. leaf B - has index keys from the range 22 to 100 for example. It has no keys from other inodes, all its keys are dir index keys for our directory inode number 1000. Its first key is for the dir item with a sequence number of 22. All these dir items were also created in a past transaction. leaf C - has index keys for our directory for the range 101 to 120 for example. This leaf also has items from other inodes, and its first item corresponds to the dir item for index number 101 for our directory with inode number 1000; 2) When we finish processing the items from leaf A at log_dir_items(), we log a BTRFS_DIR_LOG_INDEX_KEY key with an offset of 21 and a last offset of 21, meaning the log is authoritative for the index range from 21 to 21 (a single sequence number). At this point leaf B was not yet modified in the current transaction; 3) When we return from log_dir_items() we have released our read lock on leaf B, and have set *last_offset_ret to 21 (index number of the first item on leaf B minus 1); 4) Some other task inserts an item for other inode (inode number 1001 for example) into leaf C. That resulted in pushing some items from leaf C into leaf B, in order to make room for the new item, so now leaf B has dir index keys for the sequence number range from 22 to 102 and leaf C has the dir items for the sequence number range 103 to 120; 5) At log_directory_changes() we call log_dir_items() again, passing it a 'min_offset' / 'min_key' value of 22 (*last_offset_ret from step 3 plus 1, so 21 + 1). Then btrfs_search_forward() leaves us at slot 0 of leaf B, since leaf B was modified in the current transaction. We have also initialized 'last_old_dentry_offset' to 20 after calling btrfs_previous_item() at log_dir_items(), as it left us at the last item of leaf A, which refers to the dir item with sequence number 20; 6) We then call process_dir_items_leaf() to process the dir items of leaf B, and when we process the first item, corresponding to slot 0, sequence number 22, we notice the dir item was created in a past transaction and its sequence number is greater than the value of *last_old_dentry_offset + 1 (20 + 1), so we decide to log again a BTRFS_DIR_LOG_INDEX_KEY key with an offset of 21 and an end range of 21 (key.offset - 1 == 22 - 1 == 21), which results in an -EEXIST error from insert_dir_log_key(), as we have already inserted that key at step 2, triggering the assertion at process_dir_items_leaf(). The trace produced in dmesg is like the following: assertion failed: ret != -EEXIST, in fs/btrfs/tree-log.c:3857 [198255.980839][ T7460] ------------[ cut here ]------------ [198255.981666][ T7460] kernel BUG at fs/btrfs/ctree.h:3617! [198255.983141][ T7460] invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI [198255.984080][ T7460] CPU: 0 PID: 7460 Comm: repro-ghost-dir Not tainted 5.18.0-5314c78ac373-misc-next+ [198255.986027][ T7460] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 [198255.988600][ T7460] RIP: 0010:assertfail.constprop.0+0x1c/0x1e [198255.989465][ T7460] Code: 8b 4c 89 (...) [198255.992599][ T7460] RSP: 0018:ffffc90007387188 EFLAGS: 00010282 [198255.993414][ T7460] RAX: 000000000000003d RBX: 0000000000000065 RCX: 0000000000000000 [198255.996056][ T7460] RDX: 0000000000000001 RSI: ffffffff8b62b180 RDI: fffff52000e70e24 [198255.997668][ T7460] RBP: ffffc90007387188 R08: 000000000000003d R09: ffff8881f0e16507 [198255.999199][ T7460] R10: ffffed103e1c2ca0 R11: 0000000000000001 R12: 00000000ffffffef [198256.000683][ T7460] R13: ffff88813befc630 R14: ffff888116c16e70 R15: ffffc90007387358 [198256.007082][ T7460] FS: 00007fc7f7c24640(0000) GS:ffff8881f0c00000(0000) knlGS:0000000000000000 [198256.009939][ T7460] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [198256.014133][ T7460] CR2: 0000560bb16d0b78 CR3: 0000000140b34005 CR4: 0000000000170ef0 [198256.015239][ T7460] Call Trace: [198256.015674][ T7460] [198256.016313][ T7460] log_dir_items.cold+0x16/0x2c [198256.018858][ T7460] ? replay_one_extent+0xbf0/0xbf0 [198256.025932][ T7460] ? release_extent_buffer+0x1d2/0x270 [198256.029658][ T7460] ? rcu_read_lock_sched_held+0x16/0x80 [198256.031114][ T7460] ? lock_acquired+0xbe/0x660 [198256.032633][ T7460] ? rcu_read_lock_sched_held+0x16/0x80 [198256.034386][ T7460] ? lock_release+0xcf/0x8a0 [198256.036152][ T7460] log_directory_changes+0xf9/0x170 [198256.036993][ T7460] ? log_dir_items+0xba0/0xba0 [198256.037661][ T7460] ? do_raw_write_unlock+0x7d/0xe0 [198256.038680][ T7460] btrfs_log_inode+0x233b/0x26d0 [198256.041294][ T7460] ? log_directory_changes+0x170/0x170 [198256.042864][ T7460] ? btrfs_attach_transaction_barrier+0x60/0x60 [198256.045130][ T7460] ? rcu_read_lock_sched_held+0x16/0x80 [198256.046568][ T7460] ? lock_release+0xcf/0x8a0 [198256.047504][ T7460] ? lock_downgrade+0x420/0x420 [198256.048712][ T7460] ? ilookup5_nowait+0x81/0xa0 [198256.049747][ T7460] ? lock_downgrade+0x420/0x420 [198256.050652][ T7460] ? do_raw_spin_unlock+0xa9/0x100 [198256.051618][ T7460] ? __might_resched+0x128/0x1c0 [198256.052511][ T7460] ? __might_sleep+0x66/0xc0 [198256.053442][ T7460] ? __kasan_check_read+0x11/0x20 [198256.054251][ T7460] ? iget5_locked+0xbd/0x150 [198256.054986][ T7460] ? run_delayed_iput_locked+0x110/0x110 [198256.055929][ T7460] ? btrfs_iget+0xc7/0x150 [198256.056630][ T7460] ? btrfs_orphan_cleanup+0x4a0/0x4a0 [198256.057502][ T7460] ? free_extent_buffer+0x13/0x20 [198256.058322][ T7460] btrfs_log_inode+0x2654/0x26d0 [198256.059137][ T7460] ? log_directory_changes+0x170/0x170 [198256.060020][ T7460] ? rcu_read_lock_sched_held+0x16/0x80 [198256.060930][ T7460] ? rcu_read_lock_sched_held+0x16/0x80 [198256.061905][ T7460] ? lock_contended+0x770/0x770 [198256.062682][ T7460] ? btrfs_log_inode_parent+0xd04/0x1750 [198256.063582][ T7460] ? lock_downgrade+0x420/0x420 [198256.064432][ T7460] ? preempt_count_sub+0x18/0xc0 [198256.065550][ T7460] ? __mutex_lock+0x580/0xdc0 [198256.066654][ T7460] ? stack_trace_save+0x94/0xc0 [198256.068008][ T7460] ? __kasan_check_write+0x14/0x20 [198256.072149][ T7460] ? __mutex_unlock_slowpath+0x12a/0x430 [198256.073145][ T7460] ? mutex_lock_io_nested+0xcd0/0xcd0 [198256.074341][ T7460] ? wait_for_completion_io_timeout+0x20/0x20 [198256.075345][ T7460] ? lock_downgrade+0x420/0x420 [198256.076142][ T7460] ? lock_contended+0x770/0x770 [198256.076939][ T7460] ? do_raw_spin_lock+0x1c0/0x1c0 [198256.078401][ T7460] ? btrfs_sync_file+0x5e6/0xa40 [198256.080598][ T7460] btrfs_log_inode_parent+0x523/0x1750 [198256.081991][ T7460] ? wait_current_trans+0xc8/0x240 [198256.083320][ T7460] ? lock_downgrade+0x420/0x420 [198256.085450][ T7460] ? btrfs_end_log_trans+0x70/0x70 [198256.086362][ T7460] ? rcu_read_lock_sched_held+0x16/0x80 [198256.087544][ T7460] ? lock_release+0xcf/0x8a0 [198256.088305][ T7460] ? lock_downgrade+0x420/0x420 [198256.090375][ T7460] ? dget_parent+0x8e/0x300 [198256.093538][ T7460] ? do_raw_spin_lock+0x1c0/0x1c0 [198256.094918][ T7460] ? lock_downgrade+0x420/0x420 [198256.097815][ T7460] ? do_raw_spin_unlock+0xa9/0x100 [198256.101822][ T7460] ? dget_parent+0xb7/0x300 [198256.103345][ T7460] btrfs_log_dentry_safe+0x48/0x60 [198256.105052][ T7460] btrfs_sync_file+0x629/0xa40 [198256.106829][ T7460] ? start_ordered_ops.constprop.0+0x120/0x120 [198256.109655][ T7460] ? __fget_files+0x161/0x230 [198256.110760][ T7460] vfs_fsync_range+0x6d/0x110 [198256.111923][ T7460] ? start_ordered_ops.constprop.0+0x120/0x120 [198256.113556][ T7460] __x64_sys_fsync+0x45/0x70 [198256.114323][ T7460] do_syscall_64+0x5c/0xc0 [198256.115084][ T7460] ? syscall_exit_to_user_mode+0x3b/0x50 [198256.116030][ T7460] ? do_syscall_64+0x69/0xc0 [198256.116768][ T7460] ? do_syscall_64+0x69/0xc0 [198256.117555][ T7460] ? do_syscall_64+0x69/0xc0 [198256.118324][ T7460] ? sysvec_call_function_single+0x57/0xc0 [198256.119308][ T7460] ? asm_sysvec_call_function_single+0xa/0x20 [198256.120363][ T7460] entry_SYSCALL_64_after_hwframe+0x44/0xae [198256.121334][ T7460] RIP: 0033:0x7fc7fe97b6ab [198256.122067][ T7460] Code: 0f 05 48 (...) [198256.125198][ T7460] RSP: 002b:00007fc7f7c23950 EFLAGS: 00000293 ORIG_RAX: 000000000000004a [198256.126568][ T7460] RAX: ffffffffffffffda RBX: 00007fc7f7c239f0 RCX: 00007fc7fe97b6ab [198256.127942][ T7460] RDX: 0000000000000002 RSI: 000056167536bcf0 RDI: 0000000000000004 [198256.129302][ T7460] RBP: 0000000000000004 R08: 0000000000000000 R09: 000000007ffffeb8 [198256.130670][ T7460] R10: 00000000000001ff R11: 0000000000000293 R12: 0000000000000001 [198256.132046][ T7460] R13: 0000561674ca8140 R14: 00007fc7f7c239d0 R15: 000056167536dab8 [198256.133403][ T7460] Fix this by treating -EEXIST as expected at insert_dir_log_key() and have it update the item with an end offset corresponding to the maximum between the previously logged end offset and the new requested end offset. The end offsets may be different due to dir index key deletions that happened as part of unlink operations while we are logging a directory (triggered when fsyncing some other inode parented by the directory) or during renames which always attempt to log a single dir index deletion. Reported-by: Zygo Blaxell Link: https://lore.kernel.org/linux-btrfs/YmyefE9mc2xl5ZMz@hungrycats.org/ Fixes: 732d591a5d6c12 ("btrfs: stop copying old dir items when logging a directory") Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 39 +++++++++++++++++++++++++-------------- 1 file changed, 25 insertions(+), 14 deletions(-) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 11399c8eed87..e65633686378 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3721,11 +3721,29 @@ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans, key.offset = first_offset; key.type = BTRFS_DIR_LOG_INDEX_KEY; ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(*item)); - if (ret) + /* + * -EEXIST is fine and can happen sporadically when we are logging a + * directory and have concurrent insertions in the subvolume's tree for + * items from other inodes and that result in pushing off some dir items + * from one leaf to another in order to accommodate for the new items. + * This results in logging the same dir index range key. + */ + if (ret && ret != -EEXIST) return ret; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_dir_log_item); + if (ret == -EEXIST) { + const u64 curr_end = btrfs_dir_log_end(path->nodes[0], item); + + /* + * btrfs_del_dir_entries_in_log() might have been called during + * an unlink between the initial insertion of this key and the + * current update, or we might be logging a single entry deletion + * during a rename, so set the new last_offset to the max value. + */ + last_offset = max(last_offset, curr_end); + } btrfs_set_dir_log_end(path->nodes[0], item, last_offset); btrfs_mark_buffer_dirty(path->nodes[0]); btrfs_release_path(path); @@ -3849,13 +3867,6 @@ static int process_dir_items_leaf(struct btrfs_trans_handle *trans, ret = insert_dir_log_key(trans, log, dst_path, ino, *last_old_dentry_offset + 1, key.offset - 1); - /* - * -EEXIST should never happen because when we - * log a directory in full mode (LOG_INODE_ALL) - * we drop all BTRFS_DIR_LOG_INDEX_KEY keys from - * the log tree. - */ - ASSERT(ret != -EEXIST); if (ret < 0) return ret; } @@ -7031,12 +7042,12 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, /* * Other concurrent task might be logging the old directory, * as it can be triggered when logging other inode that had or - * still has a dentry in the old directory. So take the old - * directory's log_mutex to prevent getting an -EEXIST when - * logging a key to record the deletion, or having that other - * task logging the old directory get an -EEXIST if it attempts - * to log the same key after we just did it. In both cases that - * would result in falling back to a transaction commit. + * still has a dentry in the old directory. We lock the old + * directory's log_mutex to ensure the deletion of the old + * name is persisted, because during directory logging we + * delete all BTRFS_DIR_LOG_INDEX_KEY keys and the deletion of + * the old name's dir index item is in the delayed items, so + * it could be missed by an in progress directory logging. */ mutex_lock(&old_dir->log_mutex); ret = del_logged_dentry(trans, log, path, btrfs_ino(old_dir), From 3e1ad196385c65c1454aceab1226d9a4baca27d5 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Tue, 3 May 2022 17:35:25 +0200 Subject: [PATCH 168/192] btrfs: sysfs: export the balance paused state of exclusive operation The new state allowing device addition with paused balance is not exported to user space so it can't recognize it and actually start the operation. Fixes: efc0e69c2fea ("btrfs: introduce exclusive operation BALANCE_PAUSED state") CC: stable@vger.kernel.org # 5.17 Signed-off-by: David Sterba --- fs/btrfs/sysfs.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 17389a42a3ab..ba78ca5aabbb 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -922,6 +922,9 @@ static ssize_t btrfs_exclusive_operation_show(struct kobject *kobj, case BTRFS_EXCLOP_BALANCE: str = "balance\n"; break; + case BTRFS_EXCLOP_BALANCE_PAUSED: + str = "balance paused\n"; + break; case BTRFS_EXCLOP_DEV_ADD: str = "device add\n"; break; From 5b53a405e4658580e1faf7c217db3f55a21ba849 Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Thu, 5 May 2022 16:17:29 +0200 Subject: [PATCH 169/192] s390/dasd: fix data corruption for ESE devices For ESE devices we get an error when accessing an unformatted track. The handling of this error will return zero data for read requests and format the track on demand before writing to it. To do this the code needs to distinguish between read and write requests. This is done with data from the blocklayer request. A pointer to the blocklayer request is stored in the CQR. If there is an error on the device an ERP request is built to do error recovery. While the ERP request is mostly a copy of the original CQR the pointer to the blocklayer request is not copied to not accidentally pass it back to the blocklayer without cleanup. This leads to the error that during ESE handling after an ERP request was built it is not possible to determine the IO direction. This leads to the formatting of a track for read requests which might in turn lead to data corruption. Fixes: 5e2b17e712cf ("s390/dasd: Add dynamic formatting support for ESE volumes") Cc: stable@vger.kernel.org # 5.3+ Signed-off-by: Stefan Haberland Reviewed-by: Jan Hoeppner Link: https://lore.kernel.org/r/20220505141733.1989450-2-sth@linux.ibm.com Signed-off-by: Jens Axboe --- drivers/s390/block/dasd.c | 8 +++++++- drivers/s390/block/dasd_eckd.c | 2 +- drivers/s390/block/dasd_int.h | 12 ++++++++++++ 3 files changed, 20 insertions(+), 2 deletions(-) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 8e87a31e329d..76d13c5ff205 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -1639,6 +1639,7 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, unsigned long now; int nrf_suppressed = 0; int fp_suppressed = 0; + struct request *req; u8 *sense = NULL; int expires; @@ -1739,7 +1740,12 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, } if (dasd_ese_needs_format(cqr->block, irb)) { - if (rq_data_dir((struct request *)cqr->callback_data) == READ) { + req = dasd_get_callback_data(cqr); + if (!req) { + cqr->status = DASD_CQR_ERROR; + return; + } + if (rq_data_dir(req) == READ) { device->discipline->ese_read(cqr, irb); cqr->status = DASD_CQR_SUCCESS; cqr->stopclk = now; diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 8410a25a65c1..e3583502aca2 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -3145,7 +3145,7 @@ dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr, sector_t curr_trk; int rc; - req = cqr->callback_data; + req = dasd_get_callback_data(cqr); block = cqr->block; base = block->base; private = base->private; diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 3b7af00a7825..07f9670ea61e 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -756,6 +756,18 @@ dasd_check_blocksize(int bsize) return 0; } +/* + * return the callback data of the original request in case there are + * ERP requests build on top of it + */ +static inline void *dasd_get_callback_data(struct dasd_ccw_req *cqr) +{ + while (cqr->refers) + cqr = cqr->refers; + + return cqr->callback_data; +} + /* externals in dasd.c */ #define DASD_PROFILE_OFF 0 #define DASD_PROFILE_ON 1 From 71f3871657370dbbaf942a1c758f64e49a36c70f Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Thu, 5 May 2022 16:17:30 +0200 Subject: [PATCH 170/192] s390/dasd: prevent double format of tracks for ESE devices For ESE devices we get an error for write operations on an unformatted track. Afterwards the track will be formatted and the IO operation restarted. When using alias devices a track might be accessed by multiple requests simultaneously and there is a race window that a track gets formatted twice resulting in data loss. Prevent this by remembering the amount of formatted tracks when starting a request and comparing this number before actually formatting a track on the fly. If the number has changed there is a chance that the current track was finally formatted in between. As a result do not format the track and restart the current IO to check. The number of formatted tracks does not match the overall number of formatted tracks on the device and it might wrap around but this is no problem. It is only needed to recognize that a track has been formatted at all in between. Fixes: 5e2b17e712cf ("s390/dasd: Add dynamic formatting support for ESE volumes") Cc: stable@vger.kernel.org # 5.3+ Signed-off-by: Stefan Haberland Reviewed-by: Jan Hoeppner Link: https://lore.kernel.org/r/20220505141733.1989450-3-sth@linux.ibm.com Signed-off-by: Jens Axboe --- drivers/s390/block/dasd.c | 7 +++++++ drivers/s390/block/dasd_eckd.c | 19 +++++++++++++++++-- drivers/s390/block/dasd_int.h | 2 ++ 3 files changed, 26 insertions(+), 2 deletions(-) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 76d13c5ff205..d62a4c673962 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -1422,6 +1422,13 @@ int dasd_start_IO(struct dasd_ccw_req *cqr) if (!cqr->lpm) cqr->lpm = dasd_path_get_opm(device); } + /* + * remember the amount of formatted tracks to prevent double format on + * ESE devices + */ + if (cqr->block) + cqr->trkcount = atomic_read(&cqr->block->trkcount); + if (cqr->cpmode == 1) { rc = ccw_device_tm_start(device->cdev, cqr->cpaddr, (long) cqr, cqr->lpm); diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index e3583502aca2..649eba51e048 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -3083,13 +3083,24 @@ static int dasd_eckd_format_device(struct dasd_device *base, } static bool test_and_set_format_track(struct dasd_format_entry *to_format, - struct dasd_block *block) + struct dasd_ccw_req *cqr) { + struct dasd_block *block = cqr->block; struct dasd_format_entry *format; unsigned long flags; bool rc = false; spin_lock_irqsave(&block->format_lock, flags); + if (cqr->trkcount != atomic_read(&block->trkcount)) { + /* + * The number of formatted tracks has changed after request + * start and we can not tell if the current track was involved. + * To avoid data corruption treat it as if the current track is + * involved + */ + rc = true; + goto out; + } list_for_each_entry(format, &block->format_list, list) { if (format->track == to_format->track) { rc = true; @@ -3109,6 +3120,7 @@ static void clear_format_track(struct dasd_format_entry *format, unsigned long flags; spin_lock_irqsave(&block->format_lock, flags); + atomic_inc(&block->trkcount); list_del_init(&format->list); spin_unlock_irqrestore(&block->format_lock, flags); } @@ -3170,8 +3182,11 @@ dasd_eckd_ese_format(struct dasd_device *startdev, struct dasd_ccw_req *cqr, } format->track = curr_trk; /* test if track is already in formatting by another thread */ - if (test_and_set_format_track(format, block)) + if (test_and_set_format_track(format, cqr)) { + /* this is no real error so do not count down retries */ + cqr->retries++; return ERR_PTR(-EEXIST); + } fdata.start_unit = curr_trk; fdata.stop_unit = curr_trk; diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 07f9670ea61e..83b918b84b4a 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -187,6 +187,7 @@ struct dasd_ccw_req { void (*callback)(struct dasd_ccw_req *, void *data); void *callback_data; unsigned int proc_bytes; /* bytes for partial completion */ + unsigned int trkcount; /* count formatted tracks */ }; /* @@ -610,6 +611,7 @@ struct dasd_block { struct list_head format_list; spinlock_t format_lock; + atomic_t trkcount; }; struct dasd_attention_data { From cd68c48ea15c85f1577a442dc4c285e112ff1b37 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan=20H=C3=B6ppner?= Date: Thu, 5 May 2022 16:17:31 +0200 Subject: [PATCH 171/192] s390/dasd: Fix read for ESE with blksize < 4k MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When reading unformatted tracks on ESE devices, the corresponding memory areas are simply set to zero for each segment. This is done incorrectly for blocksizes < 4096. There are two problems. First, the increment of dst is done using the counter of the loop (off), which is increased by blksize every iteration. This leads to a much bigger increment for dst as actually intended. Second, the increment of dst is done before the memory area is set to 0, skipping a significant amount of bytes of memory. This leads to illegal overwriting of memory and ultimately to a kernel panic. This is not a problem with 4k blocksize because blk_queue_max_segment_size is set to PAGE_SIZE, always resulting in a single iteration for the inner segment loop (bv.bv_len == blksize). The incorrectly used 'off' value to increment dst is 0 and the correct memory area is used. In order to fix this for blksize < 4k, increment dst correctly using the blksize and only do it at the end of the loop. Fixes: 5e2b17e712cf ("s390/dasd: Add dynamic formatting support for ESE volumes") Cc: stable@vger.kernel.org # v5.3+ Signed-off-by: Jan Höppner Reviewed-by: Stefan Haberland Link: https://lore.kernel.org/r/20220505141733.1989450-4-sth@linux.ibm.com Signed-off-by: Jens Axboe --- drivers/s390/block/dasd_eckd.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 649eba51e048..e46461b4d8a7 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -3285,12 +3285,11 @@ static int dasd_eckd_ese_read(struct dasd_ccw_req *cqr, struct irb *irb) cqr->proc_bytes = blk_count * blksize; return 0; } - if (dst && !skip_block) { - dst += off; + if (dst && !skip_block) memset(dst, 0, blksize); - } else { + else skip_block--; - } + dst += blksize; blk_count++; } } From b9c10f68e23c13f56685559a0d6fdaca9f838324 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan=20H=C3=B6ppner?= Date: Thu, 5 May 2022 16:17:32 +0200 Subject: [PATCH 172/192] s390/dasd: Fix read inconsistency for ESE DASD devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Read requests that return with NRF error are partially completed in dasd_eckd_ese_read(). The function keeps track of the amount of processed bytes and the driver will eventually return this information back to the block layer for further processing via __dasd_cleanup_cqr() when the request is in the final stage of processing (from the driver's perspective). For this, blk_update_request() is used which requires the number of bytes to complete the request. As per documentation the nr_bytes parameter is described as follows: "number of bytes to complete for @req". This was mistakenly interpreted as "number of bytes _left_ for @req" leading to new requests with incorrect data length. The consequence are inconsistent and completely wrong read requests as data from random memory areas are read back. Fix this by correctly specifying the amount of bytes that should be used to complete the request. Fixes: 5e6bdd37c552 ("s390/dasd: fix data corruption for thin provisioned devices") Cc: stable@vger.kernel.org # 5.3+ Signed-off-by: Jan Höppner Reviewed-by: Stefan Haberland Link: https://lore.kernel.org/r/20220505141733.1989450-5-sth@linux.ibm.com Signed-off-by: Jens Axboe --- drivers/s390/block/dasd.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index d62a4c673962..ba6d78789660 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2778,8 +2778,7 @@ static void __dasd_cleanup_cqr(struct dasd_ccw_req *cqr) * complete a request partially. */ if (proc_bytes) { - blk_update_request(req, BLK_STS_OK, - blk_rq_bytes(req) - proc_bytes); + blk_update_request(req, BLK_STS_OK, proc_bytes); blk_mq_requeue_request(req, true); } else if (likely(!blk_should_fake_timeout(req->q))) { blk_mq_complete_request(req); From f1c8781ac9d87650ccf45a354c0bbfa3f9230371 Mon Sep 17 00:00:00 2001 From: Haowen Bai Date: Thu, 5 May 2022 16:17:33 +0200 Subject: [PATCH 173/192] s390/dasd: Use kzalloc instead of kmalloc/memset Use kzalloc rather than duplicating its implementation, which makes code simple and easy to understand. Signed-off-by: Haowen Bai Reviewed-by: Sven Schnelle Signed-off-by: Stefan Haberland Link: https://lore.kernel.org/r/20220505141733.1989450-6-sth@linux.ibm.com Signed-off-by: Jens Axboe --- drivers/s390/block/dasd_eckd.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index e46461b4d8a7..836838f7d686 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -1480,7 +1480,7 @@ static int dasd_eckd_pe_handler(struct dasd_device *device, { struct pe_handler_work_data *data; - data = kmalloc(sizeof(*data), GFP_ATOMIC | GFP_DMA); + data = kzalloc(sizeof(*data), GFP_ATOMIC | GFP_DMA); if (!data) { if (mutex_trylock(&dasd_pe_handler_mutex)) { data = pe_handler_worker; @@ -1488,9 +1488,6 @@ static int dasd_eckd_pe_handler(struct dasd_device *device, } else { return -ENOMEM; } - } else { - memset(data, 0, sizeof(*data)); - data->isglobal = 0; } INIT_WORK(&data->worker, do_pe_handler_work); dasd_get_device(device); From 348c71344111d7a48892e3e52264ff11956fc196 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Thu, 5 May 2022 21:04:51 +0530 Subject: [PATCH 174/192] powerpc/papr_scm: Fix buffer overflow issue with CONFIG_FORTIFY_SOURCE With CONFIG_FORTIFY_SOURCE enabled, string functions will also perform dynamic checks for string size which can panic the kernel, like incase of overflow detection. In papr_scm, papr_scm_pmu_check_events function uses stat->stat_id with string operations, to populate the nvdimm_events_map array. Since stat_id variable is not NULL terminated, the kernel panics with CONFIG_FORTIFY_SOURCE enabled at boot time. Below are the logs of kernel panic: detected buffer overflow in __fortify_strlen ------------[ cut here ]------------ kernel BUG at lib/string_helpers.c:980! Oops: Exception in kernel mode, sig: 5 [#1] NIP [c00000000077dad0] fortify_panic+0x28/0x38 LR [c00000000077dacc] fortify_panic+0x24/0x38 Call Trace: [c0000022d77836e0] [c00000000077dacc] fortify_panic+0x24/0x38 (unreliable) [c00800000deb2660] papr_scm_pmu_check_events.constprop.0+0x118/0x220 [papr_scm] [c00800000deb2cb0] papr_scm_probe+0x288/0x62c [papr_scm] [c0000000009b46a8] platform_probe+0x98/0x150 Fix this issue by using kmemdup_nul() to copy the content of stat->stat_id directly to the nvdimm_events_map array. mpe: stat->stat_id comes from the hypervisor, not userspace, so there is no security exposure. Fixes: 4c08d4bbc089 ("powerpc/papr_scm: Add perf interface support") Signed-off-by: Kajol Jain Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20220505153451.35503-1-kjain@linux.ibm.com --- arch/powerpc/platforms/pseries/papr_scm.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index f58728d5f10d..39962c905542 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -462,7 +462,6 @@ static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu { struct papr_scm_perf_stat *stat; struct papr_scm_perf_stats *stats; - char *statid; int index, rc, count; u32 available_events; @@ -493,14 +492,12 @@ static int papr_scm_pmu_check_events(struct papr_scm_priv *p, struct nvdimm_pmu for (index = 0, stat = stats->scm_statistic, count = 0; index < available_events; index++, ++stat) { - statid = kzalloc(strlen(stat->stat_id) + 1, GFP_KERNEL); - if (!statid) { + p->nvdimm_events_map[count] = kmemdup_nul(stat->stat_id, 8, GFP_KERNEL); + if (!p->nvdimm_events_map[count]) { rc = -ENOMEM; goto out_nvdimm_events_map; } - strcpy(statid, stat->stat_id); - p->nvdimm_events_map[count] = statid; count++; } p->nvdimm_events_map[count] = NULL; From dba785798526a3282cc4d0f0ea751883715dbbb4 Mon Sep 17 00:00:00 2001 From: Puyou Lu Date: Fri, 6 May 2022 16:06:30 +0800 Subject: [PATCH 175/192] gpio: pca953x: fix irq_stat not updated when irq is disabled (irq_mask not set) When one port's input state get inverted (eg. from low to hight) after pca953x_irq_setup but before setting irq_mask (by some other driver such as "gpio-keys"), the next inversion of this port (eg. from hight to low) will not be triggered any more (because irq_stat is not updated at the first time). Issue should be fixed after this commit. Fixes: 89ea8bbe9c3e ("gpio: pca953x.c: add interrupt handling capability") Signed-off-by: Puyou Lu Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-pca953x.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index d2fe76f3f34f..8726921a1129 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -762,11 +762,11 @@ static bool pca953x_irq_pending(struct pca953x_chip *chip, unsigned long *pendin bitmap_xor(cur_stat, new_stat, old_stat, gc->ngpio); bitmap_and(trigger, cur_stat, chip->irq_mask, gc->ngpio); + bitmap_copy(chip->irq_stat, new_stat, gc->ngpio); + if (bitmap_empty(trigger, gc->ngpio)) return false; - bitmap_copy(chip->irq_stat, new_stat, gc->ngpio); - bitmap_and(cur_stat, chip->irq_trig_fall, old_stat, gc->ngpio); bitmap_and(old_stat, chip->irq_trig_raise, new_stat, gc->ngpio); bitmap_or(new_stat, old_stat, cur_stat, gc->ngpio); From 0c2c7c069285374fc8feacddc0498f8ab7627117 Mon Sep 17 00:00:00 2001 From: Peter Gonda Date: Mon, 2 May 2022 09:58:07 -0700 Subject: [PATCH 176/192] KVM: SEV: Mark nested locking of vcpu->lock svm_vm_migrate_from() uses sev_lock_vcpus_for_migration() to lock all source and target vcpu->locks. Unfortunately there is an 8 subclass limit, so a new subclass cannot be used for each vCPU. Instead maintain ownership of the first vcpu's mutex.dep_map using a role specific subclass: source vs target. Release the other vcpu's mutex.dep_maps. Fixes: b56639318bb2b ("KVM: SEV: Add support for SEV intra host migration") Reported-by: John Sperbeck Suggested-by: David Rientjes Suggested-by: Sean Christopherson Suggested-by: Paolo Bonzini Cc: Hillf Danton Cc: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Peter Gonda Message-Id: <20220502165807.529624-1-pgonda@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/sev.c | 42 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 38 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 0ad70c12c7c3..7c392873626f 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1594,24 +1594,51 @@ static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) atomic_set_release(&src_sev->migration_in_progress, 0); } +/* vCPU mutex subclasses. */ +enum sev_migration_role { + SEV_MIGRATION_SOURCE = 0, + SEV_MIGRATION_TARGET, + SEV_NR_MIGRATION_ROLES, +}; -static int sev_lock_vcpus_for_migration(struct kvm *kvm) +static int sev_lock_vcpus_for_migration(struct kvm *kvm, + enum sev_migration_role role) { struct kvm_vcpu *vcpu; unsigned long i, j; + bool first = true; kvm_for_each_vcpu(i, vcpu, kvm) { - if (mutex_lock_killable(&vcpu->mutex)) + if (mutex_lock_killable_nested(&vcpu->mutex, role)) goto out_unlock; + + if (first) { + /* + * Reset the role to one that avoids colliding with + * the role used for the first vcpu mutex. + */ + role = SEV_NR_MIGRATION_ROLES; + first = false; + } else { + mutex_release(&vcpu->mutex.dep_map, _THIS_IP_); + } } return 0; out_unlock: + + first = true; kvm_for_each_vcpu(j, vcpu, kvm) { if (i == j) break; + if (first) + first = false; + else + mutex_acquire(&vcpu->mutex.dep_map, role, 0, _THIS_IP_); + + mutex_unlock(&vcpu->mutex); } return -EINTR; @@ -1621,8 +1648,15 @@ static void sev_unlock_vcpus_for_migration(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; + bool first = true; kvm_for_each_vcpu(i, vcpu, kvm) { + if (first) + first = false; + else + mutex_acquire(&vcpu->mutex.dep_map, + SEV_NR_MIGRATION_ROLES, 0, _THIS_IP_); + mutex_unlock(&vcpu->mutex); } } @@ -1748,10 +1782,10 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) charged = true; } - ret = sev_lock_vcpus_for_migration(kvm); + ret = sev_lock_vcpus_for_migration(kvm, SEV_MIGRATION_SOURCE); if (ret) goto out_dst_cgroup; - ret = sev_lock_vcpus_for_migration(source_kvm); + ret = sev_lock_vcpus_for_migration(source_kvm, SEV_MIGRATION_TARGET); if (ret) goto out_dst_vcpu; From 053d2290c0307e3642e75e0185ddadf084dc36c1 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 2 May 2022 22:18:50 +0000 Subject: [PATCH 177/192] KVM: VMX: Exit to userspace if vCPU has injected exception and invalid state Exit to userspace with an emulation error if KVM encounters an injected exception with invalid guest state, in addition to the existing check of bailing if there's a pending exception (KVM doesn't support emulating exceptions except when emulating real mode via vm86). In theory, KVM should never get to such a situation as KVM is supposed to exit to userspace before injecting an exception with invalid guest state. But in practice, userspace can intervene and manually inject an exception and/or stuff registers to force invalid guest state while a previously injected exception is awaiting reinjection. Fixes: fc4fad79fc3d ("KVM: VMX: Reject KVM_RUN if emulation is required with pending exception") Reported-by: syzbot+cfafed3bb76d3e37581b@syzkaller.appspotmail.com Signed-off-by: Sean Christopherson Message-Id: <20220502221850.131873-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d58b763df855..610355b9ccce 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -5472,7 +5472,7 @@ static bool vmx_emulation_required_with_pending_exception(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); return vmx->emulation_required && !vmx->rmode.vm86_active && - vcpu->arch.exception.pending; + (vcpu->arch.exception.pending || vcpu->arch.exception.injected); } static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) From f71f01394f742fc4558b3f9f4c7ef4c4cf3b07c8 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Sun, 8 May 2022 11:37:07 +0200 Subject: [PATCH 178/192] floppy: use a statically allocated error counter Interrupt handler bad_flp_intr() may cause a UAF on the recently freed request just to increment the error count. There's no point keeping that one in the request anyway, and since the interrupt handler uses a static pointer to the error which cannot be kept in sync with the pending request, better make it use a static error counter that's reset for each new request. This reset now happens when entering redo_fd_request() for a new request via set_next_request(). One initial concern about a single error counter was that errors on one floppy drive could be reported on another one, but this problem is not real given that the driver uses a single drive at a time, as that PC-compatible controllers also have this limitation by using shared signals. As such the error count is always for the "current" drive. Reported-by: Minh Yuan Suggested-by: Linus Torvalds Tested-by: Denis Efremov Signed-off-by: Willy Tarreau Signed-off-by: Linus Torvalds --- drivers/block/floppy.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index d5b9ff9bcbb2..015841f50f4e 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -509,8 +509,8 @@ static unsigned long fdc_busy; static DECLARE_WAIT_QUEUE_HEAD(fdc_wait); static DECLARE_WAIT_QUEUE_HEAD(command_done); -/* Errors during formatting are counted here. */ -static int format_errors; +/* errors encountered on the current (or last) request */ +static int floppy_errors; /* Format request descriptor. */ static struct format_descr format_req; @@ -530,7 +530,6 @@ static struct format_descr format_req; static char *floppy_track_buffer; static int max_buffer_sectors; -static int *errors; typedef void (*done_f)(int); static const struct cont_t { void (*interrupt)(void); @@ -1455,7 +1454,7 @@ static int interpret_errors(void) if (drive_params[current_drive].flags & FTD_MSG) DPRINT("Over/Underrun - retrying\n"); bad = 0; - } else if (*errors >= drive_params[current_drive].max_errors.reporting) { + } else if (floppy_errors >= drive_params[current_drive].max_errors.reporting) { print_errors(); } if (reply_buffer[ST2] & ST2_WC || reply_buffer[ST2] & ST2_BC) @@ -2095,7 +2094,7 @@ static void bad_flp_intr(void) if (!next_valid_format(current_drive)) return; } - err_count = ++(*errors); + err_count = ++floppy_errors; INFBOUND(write_errors[current_drive].badness, err_count); if (err_count > drive_params[current_drive].max_errors.abort) cont->done(0); @@ -2241,9 +2240,8 @@ static int do_format(int drive, struct format_descr *tmp_format_req) return -EINVAL; } format_req = *tmp_format_req; - format_errors = 0; cont = &format_cont; - errors = &format_errors; + floppy_errors = 0; ret = wait_til_done(redo_format, true); if (ret == -EINTR) return -EINTR; @@ -2759,10 +2757,11 @@ static int set_next_request(void) current_req = list_first_entry_or_null(&floppy_reqs, struct request, queuelist); if (current_req) { - current_req->error_count = 0; + floppy_errors = 0; list_del_init(¤t_req->queuelist); + return 1; } - return current_req != NULL; + return 0; } /* Starts or continues processing request. Will automatically unlock the @@ -2821,7 +2820,6 @@ do_request: _floppy = floppy_type + drive_params[current_drive].autodetect[drive_state[current_drive].probed_format]; } else probing = 0; - errors = &(current_req->error_count); tmp = make_raw_rw_request(); if (tmp < 2) { request_done(tmp); From f3b10a3c22c6a5f1d623b70eca2b4d1efafccd71 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Sun, 8 May 2022 11:37:08 +0200 Subject: [PATCH 179/192] ataflop: use a statically allocated error counters This is the last driver making use of fd_request->error_count, which is easy to get wrong as was shown in floppy.c. We don't need to keep it there, it can be moved to the atari_floppy_struct instead, so let's do this. Suggested-by: Linus Torvalds Cc: Minh Yuan Cc: Geert Uytterhoeven Signed-off-by: Willy Tarreau Signed-off-by: Linus Torvalds --- drivers/block/ataflop.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 5d819a466e2f..e232cc4fd444 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -303,6 +303,7 @@ static struct atari_floppy_struct { int ref; int type; struct blk_mq_tag_set tag_set; + int error_count; } unit[FD_MAX_UNITS]; #define UD unit[drive] @@ -705,14 +706,14 @@ static void fd_error( void ) if (!fd_request) return; - fd_request->error_count++; - if (fd_request->error_count >= MAX_ERRORS) { + unit[SelectedDrive].error_count++; + if (unit[SelectedDrive].error_count >= MAX_ERRORS) { printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive ); fd_end_request_cur(BLK_STS_IOERR); finish_fdc(); return; } - else if (fd_request->error_count == RECALIBRATE_ERRORS) { + else if (unit[SelectedDrive].error_count == RECALIBRATE_ERRORS) { printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive ); if (SelectedDrive != -1) SUD.track = -1; @@ -1491,7 +1492,7 @@ static void setup_req_params( int drive ) ReqData = ReqBuffer + 512 * ReqCnt; if (UseTrackbuffer) - read_track = (ReqCmd == READ && fd_request->error_count == 0); + read_track = (ReqCmd == READ && unit[drive].error_count == 0); else read_track = 0; @@ -1520,6 +1521,7 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_RESOURCE; } fd_request = bd->rq; + unit[drive].error_count = 0; blk_mq_start_request(fd_request); atari_disable_irq( IRQ_MFP_FDC ); From 2e3afb42dd480d755cd7d97ca04586a5616c1a5e Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Sun, 8 May 2022 11:37:09 +0200 Subject: [PATCH 180/192] blk-mq: remove the error_count from struct request The last two users were floppy.c and ataflop.c respectively, it was verified that no other drivers makes use of this, so let's remove it. Suggested-by: Linus Torvalds Cc: Minh Yuan Cc: Denis Efremov , Cc: Geert Uytterhoeven Cc: Christoph Hellwig Signed-off-by: Willy Tarreau Signed-off-by: Linus Torvalds --- include/linux/blk-mq.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 7aa5c54901a9..9f07061418db 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -163,7 +163,6 @@ struct request { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; void *completion_data; - int error_count; /* for legacy drivers, don't use */ }; From 9dc4241bb14afecd16518a0760bceb3d7359b12a Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sat, 7 May 2022 15:31:16 +0200 Subject: [PATCH 181/192] Revert "parisc: Mark cr16 CPU clocksource unstable on all SMP machines" This reverts commit afdb4a5b1d340e4afffc65daa21cc71890d7d589. It triggers RCU stalls at boot with a 32-bit kernel. Signed-off-by: Helge Deller Noticed-by: John David Anglin Cc: stable@vger.kernel.org # v5.16+ --- arch/parisc/kernel/time.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index bb27dfeeddfc..95ee9e1a364b 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -251,16 +251,30 @@ void __init time_init(void) static int __init init_cr16_clocksource(void) { /* - * The cr16 interval timers are not syncronized across CPUs, even if - * they share the same socket. + * The cr16 interval timers are not syncronized across CPUs on + * different sockets, so mark them unstable and lower rating on + * multi-socket SMP systems. */ if (num_online_cpus() > 1 && !running_on_qemu) { - /* mark sched_clock unstable */ - clear_sched_clock_stable(); + int cpu; + unsigned long cpu0_loc; + cpu0_loc = per_cpu(cpu_data, 0).cpu_loc; - clocksource_cr16.name = "cr16_unstable"; - clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; - clocksource_cr16.rating = 0; + for_each_online_cpu(cpu) { + if (cpu == 0) + continue; + if ((cpu0_loc != 0) && + (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc)) + continue; + + /* mark sched_clock unstable */ + clear_sched_clock_stable(); + + clocksource_cr16.name = "cr16_unstable"; + clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; + clocksource_cr16.rating = 0; + break; + } } /* register at clocksource framework */ From 7962c0896429af2a0e00ec6bc15d992536453b2d Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sat, 7 May 2022 15:32:38 +0200 Subject: [PATCH 182/192] Revert "parisc: Mark sched_clock unstable only if clocks are not syncronized" This reverts commit d97180ad68bdb7ee10f327205a649bc2f558741d. It triggers RCU stalls at boot with a 32-bit kernel. Signed-off-by: Helge Deller Noticed-by: John David Anglin Cc: stable@vger.kernel.org # v5.15+ --- arch/parisc/kernel/setup.c | 2 ++ arch/parisc/kernel/time.c | 7 ++++--- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index b91cb45ffd4e..f005ddedb50e 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -161,6 +161,8 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_PA11 dma_ops_init(); #endif + + clear_sched_clock_stable(); } /* diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 95ee9e1a364b..19c31a72fe76 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -267,9 +267,6 @@ static int __init init_cr16_clocksource(void) (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc)) continue; - /* mark sched_clock unstable */ - clear_sched_clock_stable(); - clocksource_cr16.name = "cr16_unstable"; clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; clocksource_cr16.rating = 0; @@ -277,6 +274,10 @@ static int __init init_cr16_clocksource(void) } } + /* XXX: We may want to mark sched_clock stable here if cr16 clocks are + * in sync: + * (clocksource_cr16.flags == CLOCK_SOURCE_IS_CONTINUOUS) */ + /* register at clocksource framework */ clocksource_register_hz(&clocksource_cr16, 100 * PAGE0->mem_10msec); From 6c800d7f55fcd78e17deae5ae4374d8e73482c13 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 8 May 2022 10:18:40 +0200 Subject: [PATCH 183/192] Revert "parisc: Fix patch code locking and flushing" This reverts commit a9fe7fa7d874a536e0540469f314772c054a0323. Leads to segfaults on 32bit kernel. Signed-off-by: Helge Deller --- arch/parisc/kernel/patch.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/arch/parisc/kernel/patch.c b/arch/parisc/kernel/patch.c index e59574f65e64..80a0ab372802 100644 --- a/arch/parisc/kernel/patch.c +++ b/arch/parisc/kernel/patch.c @@ -40,7 +40,10 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags, *need_unmap = 1; set_fixmap(fixmap, page_to_phys(page)); - raw_spin_lock_irqsave(&patch_lock, *flags); + if (flags) + raw_spin_lock_irqsave(&patch_lock, *flags); + else + __acquire(&patch_lock); return (void *) (__fix_to_virt(fixmap) + (uintaddr & ~PAGE_MASK)); } @@ -49,7 +52,10 @@ static void __kprobes patch_unmap(int fixmap, unsigned long *flags) { clear_fixmap(fixmap); - raw_spin_unlock_irqrestore(&patch_lock, *flags); + if (flags) + raw_spin_unlock_irqrestore(&patch_lock, *flags); + else + __release(&patch_lock); } void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) @@ -61,9 +67,8 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) int mapped; /* Make sure we don't have any aliases in cache */ - flush_kernel_dcache_range_asm(start, end); - flush_kernel_icache_range_asm(start, end); - flush_tlb_kernel_range(start, end); + flush_kernel_vmap_range(addr, len); + flush_icache_range(start, end); p = fixmap = patch_map(addr, FIX_TEXT_POKE0, &flags, &mapped); @@ -76,10 +81,8 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) * We're crossing a page boundary, so * need to remap */ - flush_kernel_dcache_range_asm((unsigned long)fixmap, - (unsigned long)p); - flush_tlb_kernel_range((unsigned long)fixmap, - (unsigned long)p); + flush_kernel_vmap_range((void *)fixmap, + (p-fixmap) * sizeof(*p)); if (mapped) patch_unmap(FIX_TEXT_POKE0, &flags); p = fixmap = patch_map(addr, FIX_TEXT_POKE0, &flags, @@ -87,10 +90,10 @@ void __kprobes __patch_text_multiple(void *addr, u32 *insn, unsigned int len) } } - flush_kernel_dcache_range_asm((unsigned long)fixmap, (unsigned long)p); - flush_tlb_kernel_range((unsigned long)fixmap, (unsigned long)p); + flush_kernel_vmap_range((void *)fixmap, (p-fixmap) * sizeof(*p)); if (mapped) patch_unmap(FIX_TEXT_POKE0, &flags); + flush_icache_range(start, end); } void __kprobes __patch_text(void *addr, u32 insn) From 0921244f6f4f0d05698b953fe632a99b38907226 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 1 Apr 2022 09:19:11 +0200 Subject: [PATCH 184/192] parisc: Only list existing CPUs in cpu_possible_mask The inventory knows which CPUs are in the system, so this bitmask should be in cpu_possible_mask instead of the bitmask based on CONFIG_NR_CPUS. Reset the cpu_possible_mask before scanning the system for CPUs, and mark each existing CPU as possible during initialization of that CPU. This avoids those warnings later on too: register_cpu_capacity_sysctl: too early to get CPU4 device! Signed-off-by: Helge Deller Noticed-by: John David Anglin --- arch/parisc/kernel/processor.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index d98692115221..9e92b76b0ce0 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -171,6 +171,7 @@ static int __init processor_probe(struct parisc_device *dev) p->cpu_num = cpu_info.cpu_num; p->cpu_loc = cpu_info.cpu_loc; + set_cpu_possible(cpuid, true); store_cpu_topology(cpuid); #ifdef CONFIG_SMP @@ -461,6 +462,13 @@ static struct parisc_driver cpu_driver __refdata = { */ void __init processor_init(void) { + unsigned int cpu; + reset_cpu_topology(); + + /* reset possible mask. We will mark those which are possible. */ + for_each_possible_cpu(cpu) + set_cpu_possible(cpu, false); + register_parisc_driver(&cpu_driver); } From 7e93a3dd63db2341d094ab1d9ba29b5d8d5093d1 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 1 Apr 2022 18:55:27 +0200 Subject: [PATCH 185/192] parisc: Update 32- and 64-bit defconfigs Enable CONFIG_CGROUPS=y on 32-bit defconfig for systemd-support, and enable CONFIG_NAMESPACES and CONFIG_USER_NS. Signed-off-by: Helge Deller --- arch/parisc/configs/generic-32bit_defconfig | 4 +++- arch/parisc/configs/generic-64bit_defconfig | 3 ++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig index a5fee10d76ee..8ce0ae370680 100644 --- a/arch/parisc/configs/generic-32bit_defconfig +++ b/arch/parisc/configs/generic-32bit_defconfig @@ -6,6 +6,9 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=16 +CONFIG_CGROUPS=y +CONFIG_NAMESPACES=y +CONFIG_USER_NS=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_PERF_EVENTS=y @@ -47,7 +50,6 @@ CONFIG_PARPORT=y CONFIG_PARPORT_PC=m CONFIG_PARPORT_1284=y CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_CRYPTOLOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=6144 CONFIG_BLK_DEV_SD=y diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig index 1b8fd80cbe7f..57501b0aed92 100644 --- a/arch/parisc/configs/generic-64bit_defconfig +++ b/arch/parisc/configs/generic-64bit_defconfig @@ -16,6 +16,7 @@ CONFIG_CGROUPS=y CONFIG_MEMCG=y CONFIG_CGROUP_PIDS=y CONFIG_CPUSETS=y +CONFIG_USER_NS=y CONFIG_RELAY=y CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y @@ -267,9 +268,9 @@ CONFIG_CRYPTO_DEFLATE=m CONFIG_CRC_CCITT=m CONFIG_LIBCRC32C=y CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_KERNEL=y CONFIG_STRIP_ASM_SYMS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_STACKOVERFLOW=y # CONFIG_SCHED_DEBUG is not set From 1955c4f879a130c7822f483cf593338ad747aed4 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 1 Apr 2022 22:24:20 +0200 Subject: [PATCH 186/192] parisc: Re-enable GENERIC_CPU_DEVICES for !SMP In commit 62773112acc5 ("parisc: Switch from GENERIC_CPU_DEVICES to GENERIC_ARCH_TOPOLOGY") GENERIC_CPU_DEVICES was unconditionally turned off, but this triggers a warning in topology_add_dev(). Turning it back on for the !SMP case avoids this warning. Reported-by: Guenter Roeck Tested-by: Guenter Roeck Fixes: 62773112acc5 ("parisc: Switch from GENERIC_CPU_DEVICES to GENERIC_ARCH_TOPOLOGY") Signed-off-by: Helge Deller --- arch/parisc/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 52e550b45692..bd22578859d0 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -38,6 +38,7 @@ config PARISC select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_SMP_IDLE_THREAD select GENERIC_ARCH_TOPOLOGY if SMP + select GENERIC_CPU_DEVICES if !SMP select GENERIC_LIB_DEVMEM_IS_ALLOWED select SYSCTL_ARCH_UNALIGN_ALLOW select SYSCTL_EXCEPTION_TRACE From 5b89966bc96a06f6ad65f64ae4b0461918fcc9d3 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 3 Apr 2022 21:57:51 +0200 Subject: [PATCH 187/192] parisc: Merge model and model name into one line in /proc/cpuinfo The Linux tool "lscpu" shows the double amount of CPUs if we have "model" and "model name" in two different lines in /proc/cpuinfo. This change combines the model and the model name into one line. Signed-off-by: Helge Deller Cc: stable@vger.kernel.org --- arch/parisc/kernel/processor.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 9e92b76b0ce0..26eb568f8b96 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -420,8 +420,7 @@ show_cpuinfo (struct seq_file *m, void *v) } seq_printf(m, " (0x%02lx)\n", boot_cpu_data.pdc.capabilities); - seq_printf(m, "model\t\t: %s\n" - "model name\t: %s\n", + seq_printf(m, "model\t\t: %s - %s\n", boot_cpu_data.pdc.sys_model_name, cpuinfo->dev ? cpuinfo->dev->name : "Unknown"); From 234ff4c585d704896450a3634a7c29fa4e1907e1 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Tue, 5 Apr 2022 21:28:37 +0200 Subject: [PATCH 188/192] parisc: Change MAX_ADDRESS to become unsigned long long Dave noticed that for the 32-bit kernel MAX_ADDRESS should be a ULL, otherwise this define would become 0: MAX_ADDRESS (1UL << MAX_ADDRBITS) It has no real effect on the kernel. Signed-off-by: Helge Deller Noticed-by: John David Anglin --- arch/parisc/include/asm/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 939db6fe620b..69765a6dbe89 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -160,7 +160,7 @@ extern void __update_cache(pte_t pte); #define SPACEID_SHIFT (MAX_ADDRBITS - 32) #else #define MAX_ADDRBITS (BITS_PER_LONG) -#define MAX_ADDRESS (1UL << MAX_ADDRBITS) +#define MAX_ADDRESS (1ULL << MAX_ADDRBITS) #define SPACEID_SHIFT 0 #endif From a65bcad5421507c2f6c52e1e2ca6a6ce02fd1ad6 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 30 Apr 2022 21:07:18 +0200 Subject: [PATCH 189/192] parisc: Fix typos in comments Various spelling mistakes in comments. Detected with the help of Coccinelle. Signed-off-by: Julia Lawall Signed-off-by: Helge Deller --- arch/parisc/kernel/kprobes.c | 2 +- arch/parisc/kernel/traps.c | 2 +- arch/parisc/math-emu/dfadd.c | 2 +- arch/parisc/math-emu/dfsub.c | 2 +- arch/parisc/math-emu/sfadd.c | 2 +- arch/parisc/math-emu/sfsub.c | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/parisc/kernel/kprobes.c b/arch/parisc/kernel/kprobes.c index 3343d2fb7889..6e0b86652f30 100644 --- a/arch/parisc/kernel/kprobes.c +++ b/arch/parisc/kernel/kprobes.c @@ -152,7 +152,7 @@ int __kprobes parisc_kprobe_ss_handler(struct pt_regs *regs) /* for absolute branch instructions we can copy iaoq_b. for relative * branch instructions we need to calculate the new address based on the * difference between iaoq_f and iaoq_b. We cannot use iaoq_b without - * modificationt because it's based on our ainsn.insn address. + * modifications because it's based on our ainsn.insn address. */ if (p->post_handler) diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index a6e61cf2cad0..b78f1b9d45c1 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -469,7 +469,7 @@ void parisc_terminate(char *msg, struct pt_regs *regs, int code, unsigned long o * panic notifiers, and we should call panic * directly from the location that we wish. * e.g. We should not call panic from - * parisc_terminate, but rather the oter way around. + * parisc_terminate, but rather the other way around. * This hack works, prints the panic message twice, * and it enables reboot timers! */ diff --git a/arch/parisc/math-emu/dfadd.c b/arch/parisc/math-emu/dfadd.c index ec487e07f004..00e561d4aa55 100644 --- a/arch/parisc/math-emu/dfadd.c +++ b/arch/parisc/math-emu/dfadd.c @@ -253,7 +253,7 @@ dbl_fadd( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/parisc/math-emu/dfsub.c b/arch/parisc/math-emu/dfsub.c index c4f30acf2d48..4f03782284bd 100644 --- a/arch/parisc/math-emu/dfsub.c +++ b/arch/parisc/math-emu/dfsub.c @@ -256,7 +256,7 @@ dbl_fsub( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/parisc/math-emu/sfadd.c b/arch/parisc/math-emu/sfadd.c index 838758279d5b..9b98c874dfac 100644 --- a/arch/parisc/math-emu/sfadd.c +++ b/arch/parisc/math-emu/sfadd.c @@ -249,7 +249,7 @@ sgl_fadd( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { diff --git a/arch/parisc/math-emu/sfsub.c b/arch/parisc/math-emu/sfsub.c index 583d3ace4634..29d9eed09d12 100644 --- a/arch/parisc/math-emu/sfsub.c +++ b/arch/parisc/math-emu/sfsub.c @@ -252,7 +252,7 @@ sgl_fsub( return(NOEXCEPTION); } right_exponent = 1; /* Set exponent to reflect different bias - * with denomalized numbers. */ + * with denormalized numbers. */ } else { From 340233dcc0160aafcce46ca893d1679f16acf409 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 8 May 2022 18:25:00 +0200 Subject: [PATCH 190/192] parisc: Mark cr16 clock unstable on all SMP machines The cr16 interval timers are not synchronized across CPUs, even with just one dual-core CPU. This becomes visible if the machines have a longer uptime. Signed-off-by: Helge Deller --- arch/parisc/kernel/time.c | 27 ++++----------------------- 1 file changed, 4 insertions(+), 23 deletions(-) diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 19c31a72fe76..9714fbd7c42d 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -251,33 +251,14 @@ void __init time_init(void) static int __init init_cr16_clocksource(void) { /* - * The cr16 interval timers are not syncronized across CPUs on - * different sockets, so mark them unstable and lower rating on - * multi-socket SMP systems. + * The cr16 interval timers are not synchronized across CPUs. */ if (num_online_cpus() > 1 && !running_on_qemu) { - int cpu; - unsigned long cpu0_loc; - cpu0_loc = per_cpu(cpu_data, 0).cpu_loc; - - for_each_online_cpu(cpu) { - if (cpu == 0) - continue; - if ((cpu0_loc != 0) && - (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc)) - continue; - - clocksource_cr16.name = "cr16_unstable"; - clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; - clocksource_cr16.rating = 0; - break; - } + clocksource_cr16.name = "cr16_unstable"; + clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; + clocksource_cr16.rating = 0; } - /* XXX: We may want to mark sched_clock stable here if cr16 clocks are - * in sync: - * (clocksource_cr16.flags == CLOCK_SOURCE_IS_CONTINUOUS) */ - /* register at clocksource framework */ clocksource_register_hz(&clocksource_cr16, 100 * PAGE0->mem_10msec); From ba0c04104082ca211e108dd8eec6db2ad7676528 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 8 May 2022 19:55:13 +0200 Subject: [PATCH 191/192] Revert "parisc: Increase parisc_cache_flush_threshold setting" This reverts commit a58e9d0984e8dad53f17ec73ae3c1cc7f8d88151. Triggers segfaults with 32-bit kernels on PA8500 machines. Signed-off-by: Helge Deller --- arch/parisc/kernel/cache.c | 18 +++--------------- 1 file changed, 3 insertions(+), 15 deletions(-) diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 23348199f3f8..e7911225a4f8 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -403,7 +403,7 @@ void __init parisc_setup_cache_timing(void) { unsigned long rangetime, alltime; unsigned long size; - unsigned long threshold, threshold2; + unsigned long threshold; alltime = mfctl(16); flush_data_cache(); @@ -418,20 +418,8 @@ void __init parisc_setup_cache_timing(void) alltime, size, rangetime); threshold = L1_CACHE_ALIGN(size * alltime / rangetime); - - /* - * The threshold computed above isn't very reliable since the - * flush times depend greatly on the percentage of dirty lines - * in the flush range. Further, the whole cache time doesn't - * include the time to refill lines that aren't in the mm/vma - * being flushed. By timing glibc build and checks on mako cpus, - * the following formula seems to work reasonably well. The - * value from the timing calculation is too small, and increases - * build and check times by almost a factor two. - */ - threshold2 = cache_info.dc_size * num_online_cpus(); - if (threshold2 > threshold) - threshold = threshold2; + if (threshold > cache_info.dc_size) + threshold = cache_info.dc_size; if (threshold) parisc_cache_flush_threshold = threshold; printk(KERN_INFO "Cache flush threshold set to %lu KiB\n", From c5eb0a61238dd6faf37f58c9ce61c9980aaffd7a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 8 May 2022 13:54:17 -0700 Subject: [PATCH 192/192] Linux 5.18-rc6 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 9a820c525b86..2284d1ca2503 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Superb Owl # *DOCUMENTATION*