From 9020be114a47bf7ff33e179b3bb0016b91a098e6 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 14 Dec 2021 10:05:27 +0300 Subject: scsi: lpfc: Terminate string in lpfc_debugfs_nvmeio_trc_write() The "mybuf" string comes from the user, so we need to ensure that it is NUL terminated. Link: https://lore.kernel.org/r/20211214070527.GA27934@kili Fixes: bd2cdd5e400f ("scsi: lpfc: NVME Initiator: Add debugfs support") Reviewed-by: James Smart Signed-off-by: Dan Carpenter Signed-off-by: Martin K. Petersen --- drivers/scsi/lpfc/lpfc_debugfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index bd6d459afce5..08b2e85dcd7d 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -2954,8 +2954,8 @@ lpfc_debugfs_nvmeio_trc_write(struct file *file, const char __user *buf, char mybuf[64]; char *pbuf; - if (nbytes > 64) - nbytes = 64; + if (nbytes > 63) + nbytes = 63; memset(mybuf, 0, sizeof(mybuf)); -- cgit v1.2.3 From fc74881c28d314b10efac016ef49df4ff40b8b97 Mon Sep 17 00:00:00 2001 From: Christian König Date: Fri, 10 Dec 2021 09:39:27 +0100 Subject: drm/amdgpu: fix dropped backing store handling in amdgpu_dma_buf_move_notify bo->tbo.resource can now be NULL. Signed-off-by: Christian König Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1811 Acked-by: Alex Deucher Link: https://patchwork.freedesktop.org/patch/msgid/20211210083927.1754-1-christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index ae6ab93c868b..7444484a12bf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -384,7 +384,7 @@ amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach) struct amdgpu_vm_bo_base *bo_base; int r; - if (bo->tbo.resource->mem_type == TTM_PL_SYSTEM) + if (!bo->tbo.resource || bo->tbo.resource->mem_type == TTM_PL_SYSTEM) return; r = ttm_bo_validate(&bo->tbo, &placement, &ctx); -- cgit v1.2.3 From bf67014d6bda16a72deea11dbbff2a97c705ca92 Mon Sep 17 00:00:00 2001 From: Huang Rui Date: Thu, 16 Dec 2021 13:35:27 -0500 Subject: drm/amdgpu: introduce new amdgpu_fence object to indicate the job embedded fence The job embedded fence donesn't initialize the flags at dma_fence_init(). Then we will go a wrong way in amdgpu_fence_get_timeline_name callback and trigger a null pointer panic once we enabled the trace event here. So introduce new amdgpu_fence object to indicate the job embedded fence. [ 156.131790] BUG: kernel NULL pointer dereference, address: 00000000000002a0 [ 156.131804] #PF: supervisor read access in kernel mode [ 156.131811] #PF: error_code(0x0000) - not-present page [ 156.131817] PGD 0 P4D 0 [ 156.131824] Oops: 0000 [#1] PREEMPT SMP PTI [ 156.131832] CPU: 6 PID: 1404 Comm: sdma0 Tainted: G OE 5.16.0-rc1-custom #1 [ 156.131842] Hardware name: Gigabyte Technology Co., Ltd. Z170XP-SLI/Z170XP-SLI-CF, BIOS F20 11/04/2016 [ 156.131848] RIP: 0010:strlen+0x0/0x20 [ 156.131859] Code: 89 c0 c3 0f 1f 80 00 00 00 00 48 01 fe eb 0f 0f b6 07 38 d0 74 10 48 83 c7 01 84 c0 74 05 48 39 f7 75 ec 31 c0 c3 48 89 f8 c3 <80> 3f 00 74 10 48 89 f8 48 83 c0 01 80 38 00 75 f7 48 29 f8 c3 31 [ 156.131872] RSP: 0018:ffff9bd0018dbcf8 EFLAGS: 00010206 [ 156.131880] RAX: 00000000000002a0 RBX: ffff8d0305ef01b0 RCX: 000000000000000b [ 156.131888] RDX: ffff8d03772ab924 RSI: ffff8d0305ef01b0 RDI: 00000000000002a0 [ 156.131895] RBP: ffff9bd0018dbd60 R08: ffff8d03002094d0 R09: 0000000000000000 [ 156.131901] R10: 000000000000005e R11: 0000000000000065 R12: ffff8d03002094d0 [ 156.131907] R13: 000000000000001f R14: 0000000000070018 R15: 0000000000000007 [ 156.131914] FS: 0000000000000000(0000) GS:ffff8d062ed80000(0000) knlGS:0000000000000000 [ 156.131923] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 156.131929] CR2: 00000000000002a0 CR3: 000000001120a005 CR4: 00000000003706e0 [ 156.131937] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 156.131942] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 156.131949] Call Trace: [ 156.131953] [ 156.131957] ? trace_event_raw_event_dma_fence+0xcc/0x200 [ 156.131973] ? ring_buffer_unlock_commit+0x23/0x130 [ 156.131982] dma_fence_init+0x92/0xb0 [ 156.131993] amdgpu_fence_emit+0x10d/0x2b0 [amdgpu] [ 156.132302] amdgpu_ib_schedule+0x2f9/0x580 [amdgpu] [ 156.132586] amdgpu_job_run+0xed/0x220 [amdgpu] v2: fix mismatch warning between the prototype and function name (Ray, kernel test robot) Signed-off-by: Huang Rui Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 11 +-- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 126 ++++++++++++++++++++--------- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 4 +- 3 files changed, 90 insertions(+), 51 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 1e651b959141..9dc86c5a1cad 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4461,7 +4461,7 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev) int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, struct amdgpu_reset_context *reset_context) { - int i, j, r = 0; + int i, r = 0; struct amdgpu_job *job = NULL; bool need_full_reset = test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags); @@ -4483,15 +4483,8 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, /*clear job fence from fence drv to avoid force_completion *leave NULL and vm flush fence in fence drv */ - for (j = 0; j <= ring->fence_drv.num_fences_mask; j++) { - struct dma_fence *old, **ptr; + amdgpu_fence_driver_clear_job_fences(ring); - ptr = &ring->fence_drv.fences[j]; - old = rcu_dereference_protected(*ptr, 1); - if (old && test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &old->flags)) { - RCU_INIT_POINTER(*ptr, NULL); - } - } /* after all hw jobs are reset, hw fence is meaningless, so force_completion */ amdgpu_fence_driver_force_completion(ring); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 3b7e86ea7167..9afd11ca2709 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -77,11 +77,13 @@ void amdgpu_fence_slab_fini(void) * Cast helper */ static const struct dma_fence_ops amdgpu_fence_ops; +static const struct dma_fence_ops amdgpu_job_fence_ops; static inline struct amdgpu_fence *to_amdgpu_fence(struct dma_fence *f) { struct amdgpu_fence *__f = container_of(f, struct amdgpu_fence, base); - if (__f->base.ops == &amdgpu_fence_ops) + if (__f->base.ops == &amdgpu_fence_ops || + __f->base.ops == &amdgpu_job_fence_ops) return __f; return NULL; @@ -158,19 +160,18 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd } seq = ++ring->fence_drv.sync_seq; - if (job != NULL && job->job_run_counter) { + if (job && job->job_run_counter) { /* reinit seq for resubmitted jobs */ fence->seqno = seq; } else { - dma_fence_init(fence, &amdgpu_fence_ops, - &ring->fence_drv.lock, - adev->fence_context + ring->idx, - seq); - } - - if (job != NULL) { - /* mark this fence has a parent job */ - set_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &fence->flags); + if (job) + dma_fence_init(fence, &amdgpu_job_fence_ops, + &ring->fence_drv.lock, + adev->fence_context + ring->idx, seq); + else + dma_fence_init(fence, &amdgpu_fence_ops, + &ring->fence_drv.lock, + adev->fence_context + ring->idx, seq); } amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr, @@ -620,6 +621,25 @@ void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev) } } +/** + * amdgpu_fence_driver_clear_job_fences - clear job embedded fences of ring + * + * @ring: fence of the ring to be cleared + * + */ +void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring) +{ + int i; + struct dma_fence *old, **ptr; + + for (i = 0; i <= ring->fence_drv.num_fences_mask; i++) { + ptr = &ring->fence_drv.fences[i]; + old = rcu_dereference_protected(*ptr, 1); + if (old && old->ops == &amdgpu_job_fence_ops) + RCU_INIT_POINTER(*ptr, NULL); + } +} + /** * amdgpu_fence_driver_force_completion - force signal latest fence of ring * @@ -643,16 +663,14 @@ static const char *amdgpu_fence_get_driver_name(struct dma_fence *fence) static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f) { - struct amdgpu_ring *ring; + return (const char *)to_amdgpu_fence(f)->ring->name; +} - if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) { - struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence); +static const char *amdgpu_job_fence_get_timeline_name(struct dma_fence *f) +{ + struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence); - ring = to_amdgpu_ring(job->base.sched); - } else { - ring = to_amdgpu_fence(f)->ring; - } - return (const char *)ring->name; + return (const char *)to_amdgpu_ring(job->base.sched)->name; } /** @@ -665,18 +683,25 @@ static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f) */ static bool amdgpu_fence_enable_signaling(struct dma_fence *f) { - struct amdgpu_ring *ring; + if (!timer_pending(&to_amdgpu_fence(f)->ring->fence_drv.fallback_timer)) + amdgpu_fence_schedule_fallback(to_amdgpu_fence(f)->ring); - if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) { - struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence); + return true; +} - ring = to_amdgpu_ring(job->base.sched); - } else { - ring = to_amdgpu_fence(f)->ring; - } +/** + * amdgpu_job_fence_enable_signaling - enable signalling on job fence + * @f: fence + * + * This is the simliar function with amdgpu_fence_enable_signaling above, it + * only handles the job embedded fence. + */ +static bool amdgpu_job_fence_enable_signaling(struct dma_fence *f) +{ + struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence); - if (!timer_pending(&ring->fence_drv.fallback_timer)) - amdgpu_fence_schedule_fallback(ring); + if (!timer_pending(&to_amdgpu_ring(job->base.sched)->fence_drv.fallback_timer)) + amdgpu_fence_schedule_fallback(to_amdgpu_ring(job->base.sched)); return true; } @@ -692,19 +717,23 @@ static void amdgpu_fence_free(struct rcu_head *rcu) { struct dma_fence *f = container_of(rcu, struct dma_fence, rcu); - if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) { - /* free job if fence has a parent job */ - struct amdgpu_job *job; - - job = container_of(f, struct amdgpu_job, hw_fence); - kfree(job); - } else { /* free fence_slab if it's separated fence*/ - struct amdgpu_fence *fence; + kmem_cache_free(amdgpu_fence_slab, to_amdgpu_fence(f)); +} - fence = to_amdgpu_fence(f); - kmem_cache_free(amdgpu_fence_slab, fence); - } +/** + * amdgpu_job_fence_free - free up the job with embedded fence + * + * @rcu: RCU callback head + * + * Free up the job with embedded fence after the RCU grace period. + */ +static void amdgpu_job_fence_free(struct rcu_head *rcu) +{ + struct dma_fence *f = container_of(rcu, struct dma_fence, rcu); + + /* free job if fence has a parent job */ + kfree(container_of(f, struct amdgpu_job, hw_fence)); } /** @@ -720,6 +749,19 @@ static void amdgpu_fence_release(struct dma_fence *f) call_rcu(&f->rcu, amdgpu_fence_free); } +/** + * amdgpu_job_fence_release - callback that job embedded fence can be freed + * + * @f: fence + * + * This is the simliar function with amdgpu_fence_release above, it + * only handles the job embedded fence. + */ +static void amdgpu_job_fence_release(struct dma_fence *f) +{ + call_rcu(&f->rcu, amdgpu_job_fence_free); +} + static const struct dma_fence_ops amdgpu_fence_ops = { .get_driver_name = amdgpu_fence_get_driver_name, .get_timeline_name = amdgpu_fence_get_timeline_name, @@ -727,6 +769,12 @@ static const struct dma_fence_ops amdgpu_fence_ops = { .release = amdgpu_fence_release, }; +static const struct dma_fence_ops amdgpu_job_fence_ops = { + .get_driver_name = amdgpu_fence_get_driver_name, + .get_timeline_name = amdgpu_job_fence_get_timeline_name, + .enable_signaling = amdgpu_job_fence_enable_signaling, + .release = amdgpu_job_fence_release, +}; /* * Fence debugfs diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 4d380e79752c..fae7d185ad0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -53,9 +53,6 @@ enum amdgpu_ring_priority_level { #define AMDGPU_FENCE_FLAG_INT (1 << 1) #define AMDGPU_FENCE_FLAG_TC_WB_ONLY (1 << 2) -/* fence flag bit to indicate the face is embedded in job*/ -#define AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT (DMA_FENCE_FLAG_USER_BITS + 1) - #define to_amdgpu_ring(s) container_of((s), struct amdgpu_ring, sched) #define AMDGPU_IB_POOL_SIZE (1024 * 1024) @@ -114,6 +111,7 @@ struct amdgpu_fence_driver { struct dma_fence **fences; }; +void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring); void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring); int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring, -- cgit v1.2.3 From 19e66d512e4182a0461530fa3159638e0f55d97e Mon Sep 17 00:00:00 2001 From: Lijo Lazar Date: Wed, 15 Dec 2021 23:37:03 +0800 Subject: drm/amd/pm: Fix xgmi link control on aldebaran Fix the message argument. 0: Allow power down 1: Disallow power down Signed-off-by: Lijo Lazar Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index 59a7d276541d..7d50827cf0a8 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -1621,7 +1621,7 @@ static int aldebaran_allow_xgmi_power_down(struct smu_context *smu, bool en) { return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GmiPwrDnControl, - en ? 1 : 0, + en ? 0 : 1, NULL); } -- cgit v1.2.3 From b7865173cf6ae59942e2c69326a06e1c1df5ecf6 Mon Sep 17 00:00:00 2001 From: chen gong Date: Thu, 9 Dec 2021 19:47:10 +0800 Subject: drm/amdgpu: When the VCN(1.0) block is suspended, powergating is explicitly enabled Play a video on the raven (or PCO, raven2) platform, and then do the S3 test. When resume, the following error will be reported: amdgpu 0000:02:00.0: [drm:amdgpu_ring_test_helper [amdgpu]] *ERROR* ring vcn_dec test failed (-110) [drm:amdgpu_device_ip_resume_phase2 [amdgpu]] *ERROR* resume of IP block failed -110 amdgpu 0000:02:00.0: amdgpu: amdgpu_device_ip_resume failed (-110). PM: dpm_run_callback(): pci_pm_resume+0x0/0x90 returns -110 [why] When playing the video: The power state flag of the vcn block is set to POWER_STATE_ON. When doing suspend: There is no change to the power state flag of the vcn block, it is still POWER_STATE_ON. When doing resume: Need to open the power gate of the vcn block and set the power state flag of the VCN block to POWER_STATE_ON. But at this time, the power state flag of the vcn block is already POWER_STATE_ON. The power status flag check in the "8f2cdef drm/amd/pm: avoid duplicate powergate/ungate setting" patch will return the amdgpu_dpm_set_powergating_by_smu function directly. As a result, the gate of the power was not opened, causing the subsequent ring test to fail. [how] In the suspend function of the vcn block, explicitly change the power state flag of the vcn block to POWER_STATE_OFF. BugLink: https://gitlab.freedesktop.org/drm/amd/-/issues/1828 Signed-off-by: chen gong Reviewed-by: Evan Quan Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index d54d720b3cf6..3799226defc0 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -246,6 +246,13 @@ static int vcn_v1_0_suspend(void *handle) { int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; + bool idle_work_unexecuted; + + idle_work_unexecuted = cancel_delayed_work_sync(&adev->vcn.idle_work); + if (idle_work_unexecuted) { + if (adev->pm.dpm_enabled) + amdgpu_dpm_enable_uvd(adev, false); + } r = vcn_v1_0_hw_fini(adev); if (r) -- cgit v1.2.3 From 5e713c6afa34c0fd6f113bf7bb1c2847172d7b20 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 15 Dec 2021 22:13:56 -0500 Subject: drm/amdgpu: add support for IP discovery gc_info table v2 Used on gfx9 based systems. Fixes incorrect CU counts reported in the kernel log. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1833 Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 76 +++++++++++++++++++-------- drivers/gpu/drm/amd/include/discovery.h | 49 +++++++++++++++++ 2 files changed, 103 insertions(+), 22 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index ea00090b3fb3..bcc9343353b5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -526,10 +526,15 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev) } } +union gc_info { + struct gc_info_v1_0 v1; + struct gc_info_v2_0 v2; +}; + int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev) { struct binary_header *bhdr; - struct gc_info_v1_0 *gc_info; + union gc_info *gc_info; if (!adev->mman.discovery_bin) { DRM_ERROR("ip discovery uninitialized\n"); @@ -537,28 +542,55 @@ int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev) } bhdr = (struct binary_header *)adev->mman.discovery_bin; - gc_info = (struct gc_info_v1_0 *)(adev->mman.discovery_bin + + gc_info = (union gc_info *)(adev->mman.discovery_bin + le16_to_cpu(bhdr->table_list[GC].offset)); - - adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->gc_num_se); - adev->gfx.config.max_cu_per_sh = 2 * (le32_to_cpu(gc_info->gc_num_wgp0_per_sa) + - le32_to_cpu(gc_info->gc_num_wgp1_per_sa)); - adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->gc_num_sa_per_se); - adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->gc_num_rb_per_se); - adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->gc_num_gl2c); - adev->gfx.config.max_gprs = le32_to_cpu(gc_info->gc_num_gprs); - adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->gc_num_max_gs_thds); - adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->gc_gs_table_depth); - adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->gc_gsprim_buff_depth); - adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->gc_double_offchip_lds_buffer); - adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->gc_wave_size); - adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->gc_max_waves_per_simd); - adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->gc_max_scratch_slots_per_cu); - adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->gc_lds_size); - adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->gc_num_sc_per_se) / - le32_to_cpu(gc_info->gc_num_sa_per_se); - adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->gc_num_packer_per_sc); - + switch (gc_info->v1.header.version_major) { + case 1: + adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->v1.gc_num_se); + adev->gfx.config.max_cu_per_sh = 2 * (le32_to_cpu(gc_info->v1.gc_num_wgp0_per_sa) + + le32_to_cpu(gc_info->v1.gc_num_wgp1_per_sa)); + adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->v1.gc_num_sa_per_se); + adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->v1.gc_num_rb_per_se); + adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->v1.gc_num_gl2c); + adev->gfx.config.max_gprs = le32_to_cpu(gc_info->v1.gc_num_gprs); + adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->v1.gc_num_max_gs_thds); + adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->v1.gc_gs_table_depth); + adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->v1.gc_gsprim_buff_depth); + adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->v1.gc_double_offchip_lds_buffer); + adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->v1.gc_wave_size); + adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->v1.gc_max_waves_per_simd); + adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->v1.gc_max_scratch_slots_per_cu); + adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->v1.gc_lds_size); + adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->v1.gc_num_sc_per_se) / + le32_to_cpu(gc_info->v1.gc_num_sa_per_se); + adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->v1.gc_num_packer_per_sc); + break; + case 2: + adev->gfx.config.max_shader_engines = le32_to_cpu(gc_info->v2.gc_num_se); + adev->gfx.config.max_cu_per_sh = le32_to_cpu(gc_info->v2.gc_num_cu_per_sh); + adev->gfx.config.max_sh_per_se = le32_to_cpu(gc_info->v2.gc_num_sh_per_se); + adev->gfx.config.max_backends_per_se = le32_to_cpu(gc_info->v2.gc_num_rb_per_se); + adev->gfx.config.max_texture_channel_caches = le32_to_cpu(gc_info->v2.gc_num_tccs); + adev->gfx.config.max_gprs = le32_to_cpu(gc_info->v2.gc_num_gprs); + adev->gfx.config.max_gs_threads = le32_to_cpu(gc_info->v2.gc_num_max_gs_thds); + adev->gfx.config.gs_vgt_table_depth = le32_to_cpu(gc_info->v2.gc_gs_table_depth); + adev->gfx.config.gs_prim_buffer_depth = le32_to_cpu(gc_info->v2.gc_gsprim_buff_depth); + adev->gfx.config.double_offchip_lds_buf = le32_to_cpu(gc_info->v2.gc_double_offchip_lds_buffer); + adev->gfx.cu_info.wave_front_size = le32_to_cpu(gc_info->v2.gc_wave_size); + adev->gfx.cu_info.max_waves_per_simd = le32_to_cpu(gc_info->v2.gc_max_waves_per_simd); + adev->gfx.cu_info.max_scratch_slots_per_cu = le32_to_cpu(gc_info->v2.gc_max_scratch_slots_per_cu); + adev->gfx.cu_info.lds_size = le32_to_cpu(gc_info->v2.gc_lds_size); + adev->gfx.config.num_sc_per_sh = le32_to_cpu(gc_info->v2.gc_num_sc_per_se) / + le32_to_cpu(gc_info->v2.gc_num_sh_per_se); + adev->gfx.config.num_packer_per_sc = le32_to_cpu(gc_info->v2.gc_num_packer_per_sc); + break; + default: + dev_err(adev->dev, + "Unhandled GC info table %d.%d\n", + gc_info->v1.header.version_major, + gc_info->v1.header.version_minor); + return -EINVAL; + } return 0; } diff --git a/drivers/gpu/drm/amd/include/discovery.h b/drivers/gpu/drm/amd/include/discovery.h index 7ec4331e67f2..a486769b66c6 100644 --- a/drivers/gpu/drm/amd/include/discovery.h +++ b/drivers/gpu/drm/amd/include/discovery.h @@ -143,6 +143,55 @@ struct gc_info_v1_0 { uint32_t gc_num_gl2a; }; +struct gc_info_v1_1 { + struct gpu_info_header header; + + uint32_t gc_num_se; + uint32_t gc_num_wgp0_per_sa; + uint32_t gc_num_wgp1_per_sa; + uint32_t gc_num_rb_per_se; + uint32_t gc_num_gl2c; + uint32_t gc_num_gprs; + uint32_t gc_num_max_gs_thds; + uint32_t gc_gs_table_depth; + uint32_t gc_gsprim_buff_depth; + uint32_t gc_parameter_cache_depth; + uint32_t gc_double_offchip_lds_buffer; + uint32_t gc_wave_size; + uint32_t gc_max_waves_per_simd; + uint32_t gc_max_scratch_slots_per_cu; + uint32_t gc_lds_size; + uint32_t gc_num_sc_per_se; + uint32_t gc_num_sa_per_se; + uint32_t gc_num_packer_per_sc; + uint32_t gc_num_gl2a; + uint32_t gc_num_tcp_per_sa; + uint32_t gc_num_sdp_interface; + uint32_t gc_num_tcps; +}; + +struct gc_info_v2_0 { + struct gpu_info_header header; + + uint32_t gc_num_se; + uint32_t gc_num_cu_per_sh; + uint32_t gc_num_sh_per_se; + uint32_t gc_num_rb_per_se; + uint32_t gc_num_tccs; + uint32_t gc_num_gprs; + uint32_t gc_num_max_gs_thds; + uint32_t gc_gs_table_depth; + uint32_t gc_gsprim_buff_depth; + uint32_t gc_parameter_cache_depth; + uint32_t gc_double_offchip_lds_buffer; + uint32_t gc_wave_size; + uint32_t gc_max_waves_per_simd; + uint32_t gc_max_scratch_slots_per_cu; + uint32_t gc_lds_size; + uint32_t gc_num_sc_per_se; + uint32_t gc_num_packer_per_sc; +}; + typedef struct harvest_info_header { uint32_t signature; /* Table Signature */ uint32_t version; /* Table Version */ -- cgit v1.2.3 From 0706a78f31c4217ca144f630063ec9561a21548d Mon Sep 17 00:00:00 2001 From: Magnus Karlsson Date: Fri, 17 Dec 2021 15:56:46 +0100 Subject: Revert "xsk: Do not sleep in poll() when need_wakeup set" This reverts commit bd0687c18e635b63233dc87f38058cd728802ab4. This patch causes a Tx only workload to go to sleep even when it does not have to, leading to misserable performance in skb mode. It fixed one rare problem but created a much worse one, so this need to be reverted while I try to craft a proper solution to the original problem. Fixes: bd0687c18e63 ("xsk: Do not sleep in poll() when need_wakeup set") Signed-off-by: Magnus Karlsson Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211217145646.26449-1-magnus.karlsson@gmail.com --- net/xdp/xsk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 7a466ea962c5..f16074eb53c7 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -677,6 +677,8 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, struct xdp_sock *xs = xdp_sk(sk); struct xsk_buff_pool *pool; + sock_poll_wait(file, sock, wait); + if (unlikely(!xsk_is_bound(xs))) return mask; @@ -688,8 +690,6 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, else /* Poll needs to drive Tx also in copy mode */ __xsk_sendmsg(sk); - } else { - sock_poll_wait(file, sock, wait); } if (xs->rx && !xskq_prod_is_empty(xs->rx)) -- cgit v1.2.3 From 819d11507f6637731947836e6308f5966d64cf9d Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 17 Dec 2021 18:24:00 +0000 Subject: bpf, selftests: Fix spelling mistake "tained" -> "tainted" There appears to be a spelling mistake in a bpf test message. Fix it. Signed-off-by: Colin Ian King Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211217182400.39296-1-colin.i.king@gmail.com --- tools/testing/selftests/bpf/verifier/value_ptr_arith.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index 4d347bc53aa2..359f3e8f8b60 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -1078,7 +1078,7 @@ .errstr_unpriv = "R0 pointer -= pointer prohibited", }, { - "map access: trying to leak tained dst reg", + "map access: trying to leak tainted dst reg", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), -- cgit v1.2.3 From 67f74302f45d5d862f22ced3297624e50ac352f0 Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 7 Dec 2021 10:10:15 +0100 Subject: drm/nouveau: wait for the exclusive fence after the shared ones v2 Always waiting for the exclusive fence resulted on some performance regressions. So try to wait for the shared fences first, then the exclusive fence should always be signaled already. v2: fix incorrectly placed "(", add some comment why we do this. Signed-off-by: Christian König Tested-by: Stefan Fritsch Tested-by: Dan Moulding Acked-by: Ben Skeggs Signed-off-by: Christian König Cc: Link: https://patchwork.freedesktop.org/patch/msgid/20211209102335.18321-1-christian.koenig@amd.com --- drivers/gpu/drm/nouveau/nouveau_fence.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 05d0b3eb3690..0ae416aa76dc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -353,15 +353,22 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, bool e if (ret) return ret; - } - fobj = dma_resv_shared_list(resv); - fence = dma_resv_excl_fence(resv); + fobj = NULL; + } else { + fobj = dma_resv_shared_list(resv); + } - if (fence) { + /* Waiting for the exclusive fence first causes performance regressions + * under some circumstances. So manually wait for the shared ones first. + */ + for (i = 0; i < (fobj ? fobj->shared_count : 0) && !ret; ++i) { struct nouveau_channel *prev = NULL; bool must_wait = true; + fence = rcu_dereference_protected(fobj->shared[i], + dma_resv_held(resv)); + f = nouveau_local_fence(fence, chan->drm); if (f) { rcu_read_lock(); @@ -373,20 +380,13 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, bool e if (must_wait) ret = dma_fence_wait(fence, intr); - - return ret; } - if (!exclusive || !fobj) - return ret; - - for (i = 0; i < fobj->shared_count && !ret; ++i) { + fence = dma_resv_excl_fence(resv); + if (fence) { struct nouveau_channel *prev = NULL; bool must_wait = true; - fence = rcu_dereference_protected(fobj->shared[i], - dma_resv_held(resv)); - f = nouveau_local_fence(fence, chan->drm); if (f) { rcu_read_lock(); @@ -398,6 +398,8 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, bool e if (must_wait) ret = dma_fence_wait(fence, intr); + + return ret; } return ret; -- cgit v1.2.3 From 4d625a97a7e96be016382e3bb0a3cead05fec153 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 21 Dec 2021 09:54:40 -0500 Subject: drm/amdgpu: fix runpm documentation It's not only supported by HG/PX laptops. It's supported by all dGPUs which supports BOCO/BACO functionality (runtime D3). BOCO - Bus Off, Chip Off. The entire chip is powered off. This is controlled by ACPI. BACO - Bus Active, Chip Off. The chip still shows up on the PCI bus, but the device itself is powered down. v2: fix missed HG/PX reference Reviewed-by: Evan Quan Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index ad95de6399af..73ac02372827 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -328,10 +328,11 @@ module_param_named(aspm, amdgpu_aspm, int, 0444); /** * DOC: runpm (int) - * Override for runtime power management control for dGPUs in PX/HG laptops. The amdgpu driver can dynamically power down - * the dGPU on PX/HG laptops when it is idle. The default is -1 (auto enable). Setting the value to 0 disables this functionality. + * Override for runtime power management control for dGPUs. The amdgpu driver can dynamically power down + * the dGPUs when they are idle if supported. The default is -1 (auto enable). + * Setting the value to 0 disables this functionality. */ -MODULE_PARM_DESC(runpm, "PX runtime pm (2 = force enable with BAMACO, 1 = force enable with BACO, 0 = disable, -1 = PX only default)"); +MODULE_PARM_DESC(runpm, "PX runtime pm (2 = force enable with BAMACO, 1 = force enable with BACO, 0 = disable, -1 = auto)"); module_param_named(runpm, amdgpu_runtime_pm, int, 0444); /** -- cgit v1.2.3 From 1b8d0300a3e9f216ae4901bab886db7299899ec6 Mon Sep 17 00:00:00 2001 From: Lixiaokeng Date: Mon, 20 Dec 2021 19:39:06 +0800 Subject: scsi: libiscsi: Fix UAF in iscsi_conn_get_param()/iscsi_conn_teardown() |- iscsi_if_destroy_conn |-dev_attr_show |-iscsi_conn_teardown |-spin_lock_bh |-iscsi_sw_tcp_conn_get_param |-kfree(conn->persistent_address) |-iscsi_conn_get_param |-kfree(conn->local_ipaddr) ==>|-read persistent_address ==>|-read local_ipaddr |-spin_unlock_bh When iscsi_conn_teardown() and iscsi_conn_get_param() happen in parallel, a UAF may be triggered. Link: https://lore.kernel.org/r/046ec8a0-ce95-d3fc-3235-666a7c65b224@huawei.com Reported-by: Lu Tixiong Reviewed-by: Mike Christie Reviewed-by: Lee Duncan Signed-off-by: Lixiaokeng Signed-off-by: Linfeilong Signed-off-by: Martin K. Petersen --- drivers/scsi/libiscsi.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 284b939fb1ea..059dae8909ee 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -3100,6 +3100,8 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn) { struct iscsi_conn *conn = cls_conn->dd_data; struct iscsi_session *session = conn->session; + char *tmp_persistent_address = conn->persistent_address; + char *tmp_local_ipaddr = conn->local_ipaddr; del_timer_sync(&conn->transport_timer); @@ -3121,8 +3123,6 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn) spin_lock_bh(&session->frwd_lock); free_pages((unsigned long) conn->data, get_order(ISCSI_DEF_MAX_RECV_SEG_LEN)); - kfree(conn->persistent_address); - kfree(conn->local_ipaddr); /* regular RX path uses back_lock */ spin_lock_bh(&session->back_lock); kfifo_in(&session->cmdpool.queue, (void*)&conn->login_task, @@ -3134,6 +3134,8 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn) mutex_unlock(&session->eh_mutex); iscsi_destroy_conn(cls_conn); + kfree(tmp_persistent_address); + kfree(tmp_local_ipaddr); } EXPORT_SYMBOL_GPL(iscsi_conn_teardown); -- cgit v1.2.3 From 142c779d05d1fef75134c3cb63f52ccbc96d9e1f Mon Sep 17 00:00:00 2001 From: Alexey Makhalov Date: Mon, 20 Dec 2021 11:05:14 -0800 Subject: scsi: vmw_pvscsi: Set residual data length conditionally The PVSCSI implementation in the VMware hypervisor under specific configuration ("SCSI Bus Sharing" set to "Physical") returns zero dataLen in the completion descriptor for READ CAPACITY(16). As a result, the kernel can not detect proper disk geometry. This can be recognized by the kernel message: [ 0.776588] sd 1:0:0:0: [sdb] Sector size 0 reported, assuming 512. The PVSCSI implementation in QEMU does not set dataLen at all, keeping it zeroed. This leads to a boot hang as was reported by Shmulik Ladkani. It is likely that the controller returns the garbage at the end of the buffer. Residual length should be set by the driver in that case. The SCSI layer will erase corresponding data. See commit bdb2b8cab439 ("[SCSI] erase invalid data returned by device") for details. Commit e662502b3a78 ("scsi: vmw_pvscsi: Set correct residual data length") introduced the issue by setting residual length unconditionally, causing the SCSI layer to erase the useful payload beyond dataLen when this value is returned as 0. As a result, considering existing issues in implementations of PVSCSI controllers, we do not want to call scsi_set_resid() when dataLen == 0. Calling scsi_set_resid() has no effect if dataLen equals buffer length. Link: https://lore.kernel.org/lkml/20210824120028.30d9c071@blondie/ Link: https://lore.kernel.org/r/20211220190514.55935-1-amakhalov@vmware.com Fixes: e662502b3a78 ("scsi: vmw_pvscsi: Set correct residual data length") Cc: Matt Wang Cc: Martin K. Petersen Cc: Vishal Bhakta Cc: VMware PV-Drivers Cc: James E.J. Bottomley Cc: linux-scsi@vger.kernel.org Cc: stable@vger.kernel.org Reported-and-suggested-by: Shmulik Ladkani Signed-off-by: Alexey Makhalov Signed-off-by: Martin K. Petersen --- drivers/scsi/vmw_pvscsi.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c index c2ba65224633..1f037b8ab904 100644 --- a/drivers/scsi/vmw_pvscsi.c +++ b/drivers/scsi/vmw_pvscsi.c @@ -586,9 +586,12 @@ static void pvscsi_complete_request(struct pvscsi_adapter *adapter, * Commands like INQUIRY may transfer less data than * requested by the initiator via bufflen. Set residual * count to make upper layer aware of the actual amount - * of data returned. + * of data returned. There are cases when controller + * returns zero dataLen with non zero data - do not set + * residual count in that case. */ - scsi_set_resid(cmd, scsi_bufflen(cmd) - e->dataLen); + if (e->dataLen && (e->dataLen < scsi_bufflen(cmd))) + scsi_set_resid(cmd, scsi_bufflen(cmd) - e->dataLen); cmd->result = (DID_OK << 16); break; -- cgit v1.2.3 From 0f9d36af8f211d296ffd23bdce61a72cdfbb1a3c Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Sat, 18 Dec 2021 16:19:09 -0800 Subject: drm/i915: Fix possible uninitialized variable in parallel extension 'prev_engine' was declared inside the output loop and checked in the inner after at least 1 pass of either loop. The variable should be declared outside both loops as it needs to be persistent across the entire loop structure. Fixes: e5e32171a2cf ("drm/i915/guc: Connect UAPI to GuC multi-lrc interface") Signed-off-by: Matthew Brost Reviewed-by: Lucas De Marchi Signed-off-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20211219001909.24348-1-matthew.brost@intel.com (cherry picked from commit cbffbac9c14220b8716b0a9c29d72243f6b14ef3) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gem/i915_gem_context.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index fb33d0322960..c37c9f0d8167 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -564,6 +564,7 @@ set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base, container_of_user(base, typeof(*ext), base); const struct set_proto_ctx_engines *set = data; struct drm_i915_private *i915 = set->i915; + struct i915_engine_class_instance prev_engine; u64 flags; int err = 0, n, i, j; u16 slot, width, num_siblings; @@ -629,7 +630,6 @@ set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base, /* Create contexts / engines */ for (i = 0; i < width; ++i) { intel_engine_mask_t current_mask = 0; - struct i915_engine_class_instance prev_engine; for (j = 0; j < num_siblings; ++j) { struct i915_engine_class_instance ci; -- cgit v1.2.3 From d46f329a3f6048e04736e86cb13c880645048792 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Tue, 14 Dec 2021 11:59:13 -0800 Subject: drm/i915: Increment composite fence seqno Increment composite fence seqno on each fence creation. Fixes: 544460c33821 ("drm/i915: Multi-BB execbuf") Signed-off-by: Matthew Brost Reviewed-by: John Harrison Signed-off-by: John Harrison Link: https://patchwork.freedesktop.org/patch/msgid/20211214195913.35735-1-matthew.brost@intel.com (cherry picked from commit 62eeb9ae1364cd96991ccc6e3c5c69d66b8c64df) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 9b24d9b5ade1..cb0bf6ffd0e3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -3017,7 +3017,7 @@ eb_composite_fence_create(struct i915_execbuffer *eb, int out_fence_fd) fence_array = dma_fence_array_create(eb->num_batches, fences, eb->context->parallel.fence_context, - eb->context->parallel.seqno, + eb->context->parallel.seqno++, false); if (!fence_array) { kfree(fences); -- cgit v1.2.3 From 8c45096c60d6ce6341c374636100ed1b2c1c33a1 Mon Sep 17 00:00:00 2001 From: Prike Liang Date: Mon, 13 Dec 2021 16:17:02 +0800 Subject: drm/amd/pm: skip setting gfx cgpg in the s0ix suspend-resume In the s0ix entry need retain gfx in the gfxoff state,so here need't set gfx cgpg in the S0ix suspend-resume process. Moreover move the S0ix check into SMU12 can simplify the code condition check. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1712 Signed-off-by: Prike Liang Reviewed-by: Evan Quan Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c | 7 ++----- drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c | 3 ++- 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 8a3244585d80..8a817932acdf 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1568,9 +1568,7 @@ static int smu_suspend(void *handle) smu->watermarks_bitmap &= ~(WATERMARKS_LOADED); - /* skip CGPG when in S0ix */ - if (smu->is_apu && !adev->in_s0ix) - smu_set_gfx_cgpg(&adev->smu, false); + smu_set_gfx_cgpg(&adev->smu, false); return 0; } @@ -1601,8 +1599,7 @@ static int smu_resume(void *handle) return ret; } - if (smu->is_apu) - smu_set_gfx_cgpg(&adev->smu, true); + smu_set_gfx_cgpg(&adev->smu, true); smu->disable_uclk_switch = 0; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c index 43028f2cd28b..9c91e79c955f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c @@ -120,7 +120,8 @@ int smu_v12_0_powergate_sdma(struct smu_context *smu, bool gate) int smu_v12_0_set_gfx_cgpg(struct smu_context *smu, bool enable) { - if (!(smu->adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) + /* Until now the SMU12 only implemented for Renoir series so here neen't do APU check. */ + if (!(smu->adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) || smu->adev->in_s0ix) return 0; return smu_cmn_send_smc_msg_with_param(smu, -- cgit v1.2.3 From daf8de0874ab5b74b38a38726fdd3d07ef98a7ee Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 12 Nov 2021 11:25:30 -0500 Subject: drm/amdgpu: always reset the asic in suspend (v2) If the platform suspend happens to fail and the power rail is not turned off, the GPU will be in an unknown state on resume, so reset the asic so that it will be in a known good state on resume even if the platform suspend failed. v2: handle s0ix Acked-by: Luben Tuikov Acked-by: Evan Quan Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 73ac02372827..1a97b8b237d5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2154,7 +2154,10 @@ static int amdgpu_pmops_suspend(struct device *dev) adev->in_s3 = true; r = amdgpu_device_suspend(drm_dev, true); adev->in_s3 = false; - + if (r) + return r; + if (!adev->in_s0ix) + r = amdgpu_asic_reset(adev); return r; } -- cgit v1.2.3 From 7be3be2b027c12e84833b3dc9597d3bb7e4c5464 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Fri, 17 Dec 2021 19:05:06 +0800 Subject: drm/amdgpu: put SMU into proper state on runpm suspending for BOCO capable platform By setting mp1_state as PP_MP1_STATE_UNLOAD, MP1 will do some proper cleanups and put itself into a state ready for PNP. That can workaround some random resuming failure observed on BOCO capable platforms. Signed-off-by: Evan Quan Acked-by: Alex Deucher Reviewed-by: Guchun Chen Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 1a97b8b237d5..86ca80da9eea 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2238,12 +2238,27 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) if (amdgpu_device_supports_px(drm_dev)) drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; + /* + * By setting mp1_state as PP_MP1_STATE_UNLOAD, MP1 will do some + * proper cleanups and put itself into a state ready for PNP. That + * can address some random resuming failure observed on BOCO capable + * platforms. + * TODO: this may be also needed for PX capable platform. + */ + if (amdgpu_device_supports_boco(drm_dev)) + adev->mp1_state = PP_MP1_STATE_UNLOAD; + ret = amdgpu_device_suspend(drm_dev, false); if (ret) { adev->in_runpm = false; + if (amdgpu_device_supports_boco(drm_dev)) + adev->mp1_state = PP_MP1_STATE_NONE; return ret; } + if (amdgpu_device_supports_boco(drm_dev)) + adev->mp1_state = PP_MP1_STATE_NONE; + if (amdgpu_device_supports_px(drm_dev)) { /* Only need to handle PCI state in the driver for ATPX * PCI core handles it for _PR3. -- cgit v1.2.3 From ebae8973884ee9ac703b3bfe34cabbb118b18538 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 23 Dec 2021 14:13:02 -0500 Subject: drm/amdgpu: no DC support for headless chips Chips with no display hardware should return false for DC support. v2: drop Arcturus and Aldebaran Fixes: f7f12b25823c0d ("drm/amdgpu: default to true in amdgpu_device_asic_has_dc_support") Reviewed-by: Evan Quan Reviewed-by: Guchun Chen Reported-by: Tareque Md.Hanif Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 9dc86c5a1cad..694c3726e0f4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3166,6 +3166,12 @@ static void amdgpu_device_detect_sriov_bios(struct amdgpu_device *adev) bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type) { switch (asic_type) { +#ifdef CONFIG_DRM_AMDGPU_SI + case CHIP_HAINAN: +#endif + case CHIP_TOPAZ: + /* chips with no display hardware */ + return false; #if defined(CONFIG_DRM_AMD_DC) case CHIP_TAHITI: case CHIP_PITCAIRN: -- cgit v1.2.3 From 9f3c16a430e8ac6b8211da106f4e4841d896ec99 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Tue, 14 Dec 2021 01:10:27 +0000 Subject: perf expr: Fix return value of ids__new() callers of ids__new() function only do NULL checking for the return value. ids__new() calles hashmap__new(), which may return ERR_PTR(-ENOMEM). Instead of changing the checking one-by-one return NULL instead of ERR_PTR(-ENOMEM) to keep it consistent. Signed-off-by: Miaoqian Lin Reviewed-by: German Gomez Tested-by: German Gomez Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: Ian Rogers Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20211214011030.20200-1-linmq006@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/expr.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index 254601060b39..666b59baeb70 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -66,7 +66,12 @@ static bool key_equal(const void *key1, const void *key2, struct hashmap *ids__new(void) { - return hashmap__new(key_hash, key_equal, NULL); + struct hashmap *hash; + + hash = hashmap__new(key_hash, key_equal, NULL); + if (IS_ERR(hash)) + return NULL; + return hash; } void ids__free(struct hashmap *ids) -- cgit v1.2.3 From a78abde220243d6f44a265fe36c49957f6fa9851 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 15 Dec 2021 10:06:34 +0200 Subject: perf intel-pt: Fix parsing of VM time correlation arguments Parser did not take ':' into account. Example: Before: $ perf record -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.026 MB perf.data ] $ perf inject -i perf.data --vm-time-correlation="dry-run 123" $ perf inject -i perf.data --vm-time-correlation="dry-run 123:456" Failed to parse VM Time Correlation options 0x620 [0x98]: failed to process type: 70 [Invalid argument] $ After: $ perf inject -i perf.data --vm-time-correlation="dry-run 123:456" $ Fixes: e3ff42bdebcfeb5f ("perf intel-pt: Parse VM Time Correlation options and set up decoding") Signed-off-by: Adrian Hunter Acked-by: Namhyung Kim Cc: Jiri Olsa Cc: Riccardo Mancini Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211215080636.149562-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/intel-pt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 10c3187e4c5a..e8613cbda331 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -3625,6 +3625,7 @@ static int intel_pt_parse_vm_tm_corr_arg(struct intel_pt *pt, char **args) *args = p; return 0; } + p += 1; while (1) { vmcs = strtoull(p, &p, 0); if (errno) -- cgit v1.2.3 From 5e0c325cdb714409a5b242c9e73a1b61157abb36 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 15 Dec 2021 10:06:35 +0200 Subject: perf script: Fix CPU filtering of a script's switch events CPU filtering was not being applied to a script's switch events. Fixes: 5bf83c29a0ad2e78 ("perf script: Add scripting operation process_switch()") Signed-off-by: Adrian Hunter Acked-by: Namhyung Kim Cc: Jiri Olsa Cc: Riccardo Mancini Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211215080636.149562-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 9434367af166..c82b033e8942 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2473,7 +2473,7 @@ static int process_switch_event(struct perf_tool *tool, if (perf_event__process_switch(tool, event, sample, machine) < 0) return -1; - if (scripting_ops && scripting_ops->process_switch) + if (scripting_ops && scripting_ops->process_switch && !filter_cpu(sample)) scripting_ops->process_switch(event, sample, machine); if (!script->show_switch_events) -- cgit v1.2.3 From 0f80bfbf4919e32f52fe1312c3900ff4fbb7eeb9 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 15 Dec 2021 10:06:36 +0200 Subject: perf scripts python: intel-pt-events.py: Fix printing of switch events The intel-pt-events.py script displays only the last of consecutive switch statements but that may not be the last switch event for the CPU. Fix by keeping a dictionary of last context switch keyed by CPU, and make it possible to see all switch events by adding option --all-switch-events. Fixes: a92bf335fd82eeee ("perf scripts python: intel-pt-events.py: Add branches to script") Signed-off-by: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211215080636.149562-4-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/intel-pt-events.py | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/tools/perf/scripts/python/intel-pt-events.py b/tools/perf/scripts/python/intel-pt-events.py index 1d3a189a9a54..66452a8ec358 100644 --- a/tools/perf/scripts/python/intel-pt-events.py +++ b/tools/perf/scripts/python/intel-pt-events.py @@ -32,8 +32,7 @@ try: except: broken_pipe_exception = IOError -glb_switch_str = None -glb_switch_printed = True +glb_switch_str = {} glb_insn = False glb_disassembler = None glb_src = False @@ -70,6 +69,7 @@ def trace_begin(): ap = argparse.ArgumentParser(usage = "", add_help = False) ap.add_argument("--insn-trace", action='store_true') ap.add_argument("--src-trace", action='store_true') + ap.add_argument("--all-switch-events", action='store_true') global glb_args global glb_insn global glb_src @@ -256,10 +256,6 @@ def print_srccode(comm, param_dict, sample, symbol, dso, with_insn): print(start_str, src_str) def do_process_event(param_dict): - global glb_switch_printed - if not glb_switch_printed: - print(glb_switch_str) - glb_switch_printed = True event_attr = param_dict["attr"] sample = param_dict["sample"] raw_buf = param_dict["raw_buf"] @@ -274,6 +270,11 @@ def do_process_event(param_dict): dso = get_optional(param_dict, "dso") symbol = get_optional(param_dict, "symbol") + cpu = sample["cpu"] + if cpu in glb_switch_str: + print(glb_switch_str[cpu]) + del glb_switch_str[cpu] + if name[0:12] == "instructions": if glb_src: print_srccode(comm, param_dict, sample, symbol, dso, True) @@ -336,8 +337,6 @@ def auxtrace_error(typ, code, cpu, pid, tid, ip, ts, msg, cpumode, *x): sys.exit(1) def context_switch(ts, cpu, pid, tid, np_pid, np_tid, machine_pid, out, out_preempt, *x): - global glb_switch_printed - global glb_switch_str if out: out_str = "Switch out " else: @@ -350,6 +349,10 @@ def context_switch(ts, cpu, pid, tid, np_pid, np_tid, machine_pid, out, out_pree machine_str = "" else: machine_str = "machine PID %d" % machine_pid - glb_switch_str = "%16s %5d/%-5d [%03u] %9u.%09u %5d/%-5d %s %s" % \ + switch_str = "%16s %5d/%-5d [%03u] %9u.%09u %5d/%-5d %s %s" % \ (out_str, pid, tid, cpu, ts / 1000000000, ts %1000000000, np_pid, np_tid, machine_str, preempt_str) - glb_switch_printed = False + if glb_args.all_switch_events: + print(switch_str); + else: + global glb_switch_str + glb_switch_str[cpu] = switch_str -- cgit v1.2.3 From 2eb82577a16d4c8eb31e4ed520649850bb95b223 Mon Sep 17 00:00:00 2001 From: Charlene Liu Date: Sun, 5 Dec 2021 21:19:30 -0500 Subject: drm/amd/display: fix B0 TMDS deepcolor no dislay issue [why] B0 PHY C map to F, D map to G driver use logic instance, dmub does the remap. Driver still need use the right PHY instance to access right HW. [how] use phyical instance when program PHY register. [note] could move resync_control programming to dmub next. Tested-by: Daniel Wheeler Reviewed-by: Dmytro Laktyushkin Reviewed-by: Jun Lei Acked-by: Rodrigo Siqueira Signed-off-by: Charlene Liu Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/dcn31/dcn31_resource.c | 25 +++++++++++++++-- .../gpu/drm/amd/display/dc/dcn31/dcn31_resource.h | 31 ++++++++++++++++++++++ 2 files changed, 54 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 18896294ae12..2cc55ef97ec4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -355,6 +355,14 @@ static const struct dce110_clk_src_regs clk_src_regs[] = { clk_src_regs(3, D), clk_src_regs(4, E) }; +/*pll_id being rempped in dmub, in driver it is logical instance*/ +static const struct dce110_clk_src_regs clk_src_regs_b0[] = { + clk_src_regs(0, A), + clk_src_regs(1, B), + clk_src_regs(2, F), + clk_src_regs(3, G), + clk_src_regs(4, E) +}; static const struct dce110_clk_src_shift cs_shift = { CS_COMMON_MASK_SH_LIST_DCN2_0(__SHIFT) @@ -2276,14 +2284,27 @@ static bool dcn31_resource_construct( dcn30_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL1, &clk_src_regs[1], false); - pool->base.clock_sources[DCN31_CLK_SRC_PLL2] = + /*move phypllx_pixclk_resync to dmub next*/ + if (dc->ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0) { + pool->base.clock_sources[DCN31_CLK_SRC_PLL2] = + dcn30_clock_source_create(ctx, ctx->dc_bios, + CLOCK_SOURCE_COMBO_PHY_PLL2, + &clk_src_regs_b0[2], false); + pool->base.clock_sources[DCN31_CLK_SRC_PLL3] = + dcn30_clock_source_create(ctx, ctx->dc_bios, + CLOCK_SOURCE_COMBO_PHY_PLL3, + &clk_src_regs_b0[3], false); + } else { + pool->base.clock_sources[DCN31_CLK_SRC_PLL2] = dcn30_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL2, &clk_src_regs[2], false); - pool->base.clock_sources[DCN31_CLK_SRC_PLL3] = + pool->base.clock_sources[DCN31_CLK_SRC_PLL3] = dcn30_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL3, &clk_src_regs[3], false); + } + pool->base.clock_sources[DCN31_CLK_SRC_PLL4] = dcn30_clock_source_create(ctx, ctx->dc_bios, CLOCK_SOURCE_COMBO_PHY_PLL4, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h index 416fe7a721d8..a513363b3326 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.h @@ -49,4 +49,35 @@ struct resource_pool *dcn31_create_resource_pool( const struct dc_init_data *init_data, struct dc *dc); +/*temp: B0 specific before switch to dcn313 headers*/ +#ifndef regPHYPLLF_PIXCLK_RESYNC_CNTL +#define regPHYPLLF_PIXCLK_RESYNC_CNTL 0x007e +#define regPHYPLLF_PIXCLK_RESYNC_CNTL_BASE_IDX 1 +#define regPHYPLLG_PIXCLK_RESYNC_CNTL 0x005f +#define regPHYPLLG_PIXCLK_RESYNC_CNTL_BASE_IDX 1 + +//PHYPLLF_PIXCLK_RESYNC_CNTL +#define PHYPLLF_PIXCLK_RESYNC_CNTL__PHYPLLF_PIXCLK_RESYNC_ENABLE__SHIFT 0x0 +#define PHYPLLF_PIXCLK_RESYNC_CNTL__PHYPLLF_DEEP_COLOR_DTO_ENABLE_STATUS__SHIFT 0x1 +#define PHYPLLF_PIXCLK_RESYNC_CNTL__PHYPLLF_DCCG_DEEP_COLOR_CNTL__SHIFT 0x4 +#define PHYPLLF_PIXCLK_RESYNC_CNTL__PHYPLLF_PIXCLK_ENABLE__SHIFT 0x8 +#define PHYPLLF_PIXCLK_RESYNC_CNTL__PHYPLLF_PIXCLK_DOUBLE_RATE_ENABLE__SHIFT 0x9 +#define PHYPLLF_PIXCLK_RESYNC_CNTL__PHYPLLF_PIXCLK_RESYNC_ENABLE_MASK 0x00000001L +#define PHYPLLF_PIXCLK_RESYNC_CNTL__PHYPLLF_DEEP_COLOR_DTO_ENABLE_STATUS_MASK 0x00000002L +#define PHYPLLF_PIXCLK_RESYNC_CNTL__PHYPLLF_DCCG_DEEP_COLOR_CNTL_MASK 0x00000030L +#define PHYPLLF_PIXCLK_RESYNC_CNTL__PHYPLLF_PIXCLK_ENABLE_MASK 0x00000100L +#define PHYPLLF_PIXCLK_RESYNC_CNTL__PHYPLLF_PIXCLK_DOUBLE_RATE_ENABLE_MASK 0x00000200L + +//PHYPLLG_PIXCLK_RESYNC_CNTL +#define PHYPLLG_PIXCLK_RESYNC_CNTL__PHYPLLG_PIXCLK_RESYNC_ENABLE__SHIFT 0x0 +#define PHYPLLG_PIXCLK_RESYNC_CNTL__PHYPLLG_DEEP_COLOR_DTO_ENABLE_STATUS__SHIFT 0x1 +#define PHYPLLG_PIXCLK_RESYNC_CNTL__PHYPLLG_DCCG_DEEP_COLOR_CNTL__SHIFT 0x4 +#define PHYPLLG_PIXCLK_RESYNC_CNTL__PHYPLLG_PIXCLK_ENABLE__SHIFT 0x8 +#define PHYPLLG_PIXCLK_RESYNC_CNTL__PHYPLLG_PIXCLK_DOUBLE_RATE_ENABLE__SHIFT 0x9 +#define PHYPLLG_PIXCLK_RESYNC_CNTL__PHYPLLG_PIXCLK_RESYNC_ENABLE_MASK 0x00000001L +#define PHYPLLG_PIXCLK_RESYNC_CNTL__PHYPLLG_DEEP_COLOR_DTO_ENABLE_STATUS_MASK 0x00000002L +#define PHYPLLG_PIXCLK_RESYNC_CNTL__PHYPLLG_DCCG_DEEP_COLOR_CNTL_MASK 0x00000030L +#define PHYPLLG_PIXCLK_RESYNC_CNTL__PHYPLLG_PIXCLK_ENABLE_MASK 0x00000100L +#define PHYPLLG_PIXCLK_RESYNC_CNTL__PHYPLLG_PIXCLK_DOUBLE_RATE_ENABLE_MASK 0x00000200L +#endif #endif /* _DCN31_RESOURCE_H_ */ -- cgit v1.2.3 From d97e631af2db84c8c9d63abf68d487d0bb559e4c Mon Sep 17 00:00:00 2001 From: Lai, Derek Date: Mon, 6 Dec 2021 17:10:59 +0800 Subject: drm/amd/display: Added power down for DCN10 [Why] The change of setting a timer callback on boot for 10 seconds is still working, just lacked power down for DCN10. [How] Added power down for DCN10. Tested-by: Daniel Wheeler Reviewed-by: Anthony Koo Acked-by: Rodrigo Siqueira Signed-off-by: Derek Lai Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c index 34001a30d449..10e613ec7d24 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c @@ -78,6 +78,7 @@ static const struct hw_sequencer_funcs dcn10_funcs = { .get_clock = dcn10_get_clock, .get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync, .calc_vupdate_position = dcn10_calc_vupdate_position, + .power_down = dce110_power_down, .set_backlight_level = dce110_set_backlight_level, .set_abm_immediate_disable = dce110_set_abm_immediate_disable, .set_pipe = dce110_set_pipe, -- cgit v1.2.3 From a07f8b9983543d465b50870ab4f845d4d710ed3f Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Thu, 9 Dec 2021 13:53:36 -0500 Subject: drm/amd/display: Send s0i2_rdy in stream_count == 0 optimization [Why] Otherwise SMU won't mark Display as idle when trying to perform s2idle. [How] Mark the bit in the dcn31 codepath, doesn't apply to older ASIC. It needed to be split from phy refclk off to prevent entering s2idle when PSR was engaged but driver was not ready. Fixes: 118a33151658 ("drm/amd/display: Add DCN3.1 clock manager support") Tested-by: Daniel Wheeler Reviewed-by: Eric Yang Acked-by: Rodrigo Siqueira Signed-off-by: Nicholas Kazlauskas Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c index f4c9a458ace8..9df38e2ee4f4 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c @@ -158,6 +158,7 @@ static void dcn31_update_clocks(struct clk_mgr *clk_mgr_base, union display_idle_optimization_u idle_info = { 0 }; idle_info.idle_info.df_request_disabled = 1; idle_info.idle_info.phy_ref_clk_off = 1; + idle_info.idle_info.s0i2_rdy = 1; dcn31_smu_set_display_idle_optimization(clk_mgr, idle_info.data); /* update power state */ clk_mgr_base->clks.pwr_state = DCN_PWR_STATE_LOW_POWER; -- cgit v1.2.3 From 33735c1c8d0223170d79dbe166976d9cd7339c7a Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Thu, 9 Dec 2021 16:05:36 -0500 Subject: drm/amd/display: Set optimize_pwr_state for DCN31 [Why] We'll exit optimized power state to do link detection but we won't enter back into the optimized power state. This could potentially block s2idle entry depending on the sequencing, but it also means we're losing some power during the transition period. [How] Hook up the handler like DCN21. It was also missed like the exit_optimized_pwr_state callback. Fixes: 64b1d0e8d500 ("drm/amd/display: Add DCN3.1 HWSEQ") Tested-by: Daniel Wheeler Reviewed-by: Eric Yang Acked-by: Rodrigo Siqueira Signed-off-by: Nicholas Kazlauskas Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c index 4f6e639e9353..17e2f2bb29ec 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c @@ -101,6 +101,7 @@ static const struct hw_sequencer_funcs dcn31_funcs = { .z10_restore = dcn31_z10_restore, .z10_save_init = dcn31_z10_save_init, .set_disp_pattern_generator = dcn30_set_disp_pattern_generator, + .optimize_pwr_state = dcn21_optimize_pwr_state, .exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state, .update_visual_confirm_color = dcn20_update_visual_confirm_color, }; -- cgit v1.2.3 From 33bb63915fee190102cae7d6576bc51a0bc342b2 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Fri, 17 Dec 2021 14:18:59 -0500 Subject: drm/amd/display: Fix USB4 null pointer dereference in update_psp_stream_config [Why] A porting error on a previous patch left the block of code that causes the crash from a NULL pointer dereference. More specifically, we try to access link_enc before it's assigned in the USB4 case in the following assignment: config.dio_output_idx = link_enc->transmitter - TRANSMITTER_UNIPHY_A; [How] That assignment occurs later depending on the ASIC version. It's only needed on DCN31 and only after link_enc is already assigned. Fixes: 986430446c917b ("drm/amd/display: fix a crash on USB4 over C20 PHY") Reviewed-by: Harry Wentland Signed-off-by: Nicholas Kazlauskas Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index c8457babfdea..c0bdc23702c8 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -3945,12 +3945,9 @@ static void update_psp_stream_config(struct pipe_ctx *pipe_ctx, bool dpms_off) config.dig_be = pipe_ctx->stream->link->link_enc_hw_inst; #if defined(CONFIG_DRM_AMD_DC_DCN) config.stream_enc_idx = pipe_ctx->stream_res.stream_enc->id - ENGINE_ID_DIGA; - + if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_PHY || pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) { - link_enc = pipe_ctx->stream->link->link_enc; - config.dio_output_type = pipe_ctx->stream->link->ep_type; - config.dio_output_idx = link_enc->transmitter - TRANSMITTER_UNIPHY_A; if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_PHY) link_enc = pipe_ctx->stream->link->link_enc; else if (pipe_ctx->stream->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) -- cgit v1.2.3 From ee2698cf79cc759a397c61086c758d4cc85938bf Mon Sep 17 00:00:00 2001 From: Angus Wang Date: Thu, 9 Dec 2021 17:27:01 -0500 Subject: drm/amd/display: Changed pipe split policy to allow for multi-display pipe split [WHY] Current implementation of pipe split policy prevents pipe split with multiple displays connected, which caused the MCLK speed to be stuck at max [HOW] Changed the pipe split policies so that pipe split is allowed for multi-display configurations Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1522 Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1709 Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1655 Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1403 Note this is a backport of this commit from amdgpu drm-next for 5.16. Tested-by: Daniel Wheeler Reviewed-by: Aric Cyr Acked-by: Rodrigo Siqueira Signed-off-by: Angus Wang Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 2 +- drivers/gpu/drm/amd/display/dc/dcn201/dcn201_resource.c | 2 +- drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c | 2 +- drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c | 2 +- drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c | 2 +- drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c | 2 +- drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c | 2 +- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 3883f918b3bb..83f5d9aaffcb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -1069,7 +1069,7 @@ static const struct dc_debug_options debug_defaults_drv = { .timing_trace = false, .clock_trace = true, .disable_pplib_clock_request = true, - .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, + .pipe_split_policy = MPC_SPLIT_DYNAMIC, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_resource.c b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_resource.c index 0fa381088d1d..faec0297ec0a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_resource.c @@ -603,7 +603,7 @@ static const struct dc_debug_options debug_defaults_drv = { .timing_trace = false, .clock_trace = true, .disable_pplib_clock_request = true, - .pipe_split_policy = MPC_SPLIT_AVOID, + .pipe_split_policy = MPC_SPLIT_DYNAMIC, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index d452a0d1777e..79313d1ab5d9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -874,7 +874,7 @@ static const struct dc_debug_options debug_defaults_drv = { .clock_trace = true, .disable_pplib_clock_request = true, .min_disp_clk_khz = 100000, - .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, + .pipe_split_policy = MPC_SPLIT_DYNAMIC, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 79a66e0c4303..98852b586295 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -840,7 +840,7 @@ static const struct dc_debug_options debug_defaults_drv = { .timing_trace = false, .clock_trace = true, .disable_pplib_clock_request = true, - .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, + .pipe_split_policy = MPC_SPLIT_DYNAMIC, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c index fbaa03f26d8b..e472b729d869 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c @@ -686,7 +686,7 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_clock_gate = true, .disable_pplib_clock_request = true, .disable_pplib_wm_range = true, - .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, + .pipe_split_policy = MPC_SPLIT_DYNAMIC, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c index fcf96cf08c76..16e7059393fa 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c @@ -211,7 +211,7 @@ static const struct dc_debug_options debug_defaults_drv = { .timing_trace = false, .clock_trace = true, .disable_pplib_clock_request = true, - .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, + .pipe_split_policy = MPC_SPLIT_DYNAMIC, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c index 4a9b64023675..87cec14b7870 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c @@ -193,7 +193,7 @@ static const struct dc_debug_options debug_defaults_drv = { .timing_trace = false, .clock_trace = true, .disable_pplib_clock_request = true, - .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, + .pipe_split_policy = MPC_SPLIT_DYNAMIC, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 2cc55ef97ec4..27afbe6ec0fe 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -1002,7 +1002,7 @@ static const struct dc_debug_options debug_defaults_drv = { .timing_trace = false, .clock_trace = true, .disable_pplib_clock_request = false, - .pipe_split_policy = MPC_SPLIT_AVOID, + .pipe_split_policy = MPC_SPLIT_DYNAMIC, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, -- cgit v1.2.3 From d6f12f83989bb356ac6880a954f62c7667e35066 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Wed, 29 Dec 2021 12:15:53 +0100 Subject: x86/build: Use the proper name CONFIG_FW_LOADER Commit in Fixes intends to add the expression regex only when FW_LOADER is enabled - not FW_LOADER_BUILTIN. Latter is a leftover from a previous patchset and not a valid config item. So, adjust the condition to the actual name of the config. [ bp: Cleanup commit message. ] Fixes: c8dcf655ec81 ("x86/build: Tuck away built-in firmware under FW_LOADER") Signed-off-by: Lukas Bulwahn Signed-off-by: Borislav Petkov Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20211229111553.5846-1-lukas.bulwahn@gmail.com --- arch/x86/tools/relocs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index c736cf2ac76b..e2c5b296120d 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -68,7 +68,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "(__parainstructions|__alt_instructions)(_end)?|" "(__iommu_table|__apicdrivers|__smp_locks)(_end)?|" "__(start|end)_pci_.*|" -#if CONFIG_FW_LOADER_BUILTIN +#if CONFIG_FW_LOADER "__(start|end)_builtin_fw|" #endif "__(start|stop)___ksymtab(_gpl)?|" -- cgit v1.2.3 From 012e332286e2bb9f6ac77d195f17e74b2963d663 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 30 Dec 2021 20:23:09 +0100 Subject: fs/mount_setattr: always cleanup mount_kattr Make sure that finish_mount_kattr() is called after mount_kattr was succesfully built in both the success and failure case to prevent leaking any references we took when we built it. We returned early if path lookup failed thereby risking to leak an additional reference we took when building mount_kattr when an idmapped mount was requested. Cc: linux-fsdevel@vger.kernel.org Cc: stable@vger.kernel.org Fixes: 9caccd41541a ("fs: introduce MOUNT_ATTR_IDMAP") Signed-off-by: Christian Brauner Signed-off-by: Linus Torvalds --- fs/namespace.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/fs/namespace.c b/fs/namespace.c index 659a8f39c61a..b696543adab8 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4263,12 +4263,11 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, return err; err = user_path_at(dfd, path, kattr.lookup_flags, &target); - if (err) - return err; - - err = do_mount_setattr(&target, &kattr); + if (!err) { + err = do_mount_setattr(&target, &kattr); + path_put(&target); + } finish_mount_kattr(&kattr); - path_put(&target); return err; } -- cgit v1.2.3 From 9f3ccdc3f6ef10084ceb3a47df0961bec6196fd0 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Thu, 30 Dec 2021 20:57:46 -0800 Subject: Input: appletouch - initialize work before device registration Syzbot has reported warning in __flush_work(). This warning is caused by work->func == NULL, which means missing work initialization. This may happen, since input_dev->close() calls cancel_work_sync(&dev->work), but dev->work initalization happens _after_ input_register_device() call. So this patch moves dev->work initialization before registering input device Fixes: 5a6eb676d3bc ("Input: appletouch - improve powersaving for Geyser3 devices") Reported-and-tested-by: syzbot+b88c5eae27386b252bbd@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin Link: https://lore.kernel.org/r/20211230141151.17300-1-paskripkin@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/mouse/appletouch.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/input/mouse/appletouch.c b/drivers/input/mouse/appletouch.c index bfa26651c0be..627048bc6a12 100644 --- a/drivers/input/mouse/appletouch.c +++ b/drivers/input/mouse/appletouch.c @@ -916,6 +916,8 @@ static int atp_probe(struct usb_interface *iface, set_bit(BTN_TOOL_TRIPLETAP, input_dev->keybit); set_bit(BTN_LEFT, input_dev->keybit); + INIT_WORK(&dev->work, atp_reinit); + error = input_register_device(dev->input); if (error) goto err_free_buffer; @@ -923,8 +925,6 @@ static int atp_probe(struct usb_interface *iface, /* save our data pointer in this interface device */ usb_set_intfdata(iface, dev); - INIT_WORK(&dev->work, atp_reinit); - return 0; err_free_buffer: -- cgit v1.2.3 From bc7ec91718c49d938849697cfad98fcd9877cc26 Mon Sep 17 00:00:00 2001 From: Leo L. Schwab Date: Thu, 30 Dec 2021 21:05:00 -0800 Subject: Input: spaceball - fix parsing of movement data packets The spaceball.c module was not properly parsing the movement reports coming from the device. The code read axis data as signed 16-bit little-endian values starting at offset 2. In fact, axis data in Spaceball movement reports are signed 16-bit big-endian values starting at offset 3. This was determined first by visually inspecting the data packets, and later verified by consulting: http://spacemice.org/pdf/SpaceBall_2003-3003_Protocol.pdf If this ever worked properly, it was in the time before Git... Signed-off-by: Leo L. Schwab Link: https://lore.kernel.org/r/20211221101630.1146385-1-ewhac@ewhac.org Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/joystick/spaceball.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/input/joystick/spaceball.c b/drivers/input/joystick/spaceball.c index 429411c6c0a8..a85a4f33aea8 100644 --- a/drivers/input/joystick/spaceball.c +++ b/drivers/input/joystick/spaceball.c @@ -19,6 +19,7 @@ #include #include #include +#include #define DRIVER_DESC "SpaceTec SpaceBall 2003/3003/4000 FLX driver" @@ -75,9 +76,15 @@ static void spaceball_process_packet(struct spaceball* spaceball) case 'D': /* Ball data */ if (spaceball->idx != 15) return; - for (i = 0; i < 6; i++) + /* + * Skip first three bytes; read six axes worth of data. + * Axis values are signed 16-bit big-endian. + */ + data += 3; + for (i = 0; i < ARRAY_SIZE(spaceball_axes); i++) { input_report_abs(dev, spaceball_axes[i], - (__s16)((data[2 * i + 3] << 8) | data[2 * i + 2])); + (__s16)get_unaligned_be16(&data[i * 2])); + } break; case 'K': /* Button data */ -- cgit v1.2.3 From bb436283e25aaf1533ce061605d23a9564447bdf Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Fri, 31 Dec 2021 01:47:50 +0300 Subject: i2c: validate user data in compat ioctl Wrong user data may cause warning in i2c_transfer(), ex: zero msgs. Userspace should not be able to trigger warnings, so this patch adds validation checks for user data in compact ioctl to prevent reported warnings Reported-and-tested-by: syzbot+e417648b303855b91d8a@syzkaller.appspotmail.com Fixes: 7d5cb45655f2 ("i2c compat ioctls: move to ->compat_ioctl()") Signed-off-by: Pavel Skripkin Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-dev.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index bce0e8bb7852..cf5d049342ea 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -535,6 +535,9 @@ static long compat_i2cdev_ioctl(struct file *file, unsigned int cmd, unsigned lo sizeof(rdwr_arg))) return -EFAULT; + if (!rdwr_arg.msgs || rdwr_arg.nmsgs == 0) + return -EINVAL; + if (rdwr_arg.nmsgs > I2C_RDWR_IOCTL_MAX_MSGS) return -EINVAL; -- cgit v1.2.3 From c116fe1e1883ad3eda0a1938a9e3275a98aa51a5 Mon Sep 17 00:00:00 2001 From: Deep Majumder Date: Fri, 19 Nov 2021 11:44:01 +0530 Subject: Docs: Fixes link to I2C specification The link to the I2C specification is broken. Although "https://www.nxp.com" hosts Rev 7 (2021) of this specification, it is behind a login-wall. Thus, an additional link has been added (which doesn't require a login) and the NXP official docs link has been updated. Signed-off-by: Deep Majumder [wsa: minor updates to text and commit message] Signed-off-by: Wolfram Sang --- Documentation/i2c/summary.rst | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/Documentation/i2c/summary.rst b/Documentation/i2c/summary.rst index 136c4e333be7..786c618ba3be 100644 --- a/Documentation/i2c/summary.rst +++ b/Documentation/i2c/summary.rst @@ -11,9 +11,11 @@ systems. Some systems use variants that don't meet branding requirements, and so are not advertised as being I2C but come under different names, e.g. TWI (Two Wire Interface), IIC. -The official I2C specification is the `"I2C-bus specification and user -manual" (UM10204) `_ -published by NXP Semiconductors. +The latest official I2C specification is the `"I2C-bus specification and user +manual" (UM10204) `_ +published by NXP Semiconductors. However, you need to log-in to the site to +access the PDF. An older version of the specification (revision 6) is archived +`here `_. SMBus (System Management Bus) is based on the I2C protocol, and is mostly a subset of I2C protocols and signaling. Many I2C devices will work on an -- cgit v1.2.3 From 7a3429bace0e08d94c39245631ea6bc109dafa49 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 30 Dec 2021 17:36:31 -0700 Subject: ipv4: Check attribute length for RTA_GATEWAY in multipath route syzbot reported uninit-value: ============================================================ BUG: KMSAN: uninit-value in fib_get_nhs+0xac4/0x1f80 net/ipv4/fib_semantics.c:708 fib_get_nhs+0xac4/0x1f80 net/ipv4/fib_semantics.c:708 fib_create_info+0x2411/0x4870 net/ipv4/fib_semantics.c:1453 fib_table_insert+0x45c/0x3a10 net/ipv4/fib_trie.c:1224 inet_rtm_newroute+0x289/0x420 net/ipv4/fib_frontend.c:886 Add helper to validate RTA_GATEWAY length before using the attribute. Fixes: 4e902c57417c ("[IPv4]: FIB configuration using struct fib_config") Reported-by: syzbot+d4b9a2851cc3ce998741@syzkaller.appspotmail.com Signed-off-by: David Ahern Cc: Thomas Graf Signed-off-by: David S. Miller --- net/ipv4/fib_semantics.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index fde7797b5806..f1caa2c1c041 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -662,6 +662,19 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining, return nhs; } +static int fib_gw_from_attr(__be32 *gw, struct nlattr *nla, + struct netlink_ext_ack *extack) +{ + if (nla_len(nla) < sizeof(*gw)) { + NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_GATEWAY"); + return -EINVAL; + } + + *gw = nla_get_in_addr(nla); + + return 0; +} + /* only called when fib_nh is integrated into fib_info */ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, int remaining, struct fib_config *cfg, @@ -704,7 +717,11 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, return -EINVAL; } if (nla) { - fib_cfg.fc_gw4 = nla_get_in_addr(nla); + ret = fib_gw_from_attr(&fib_cfg.fc_gw4, nla, + extack); + if (ret) + goto errout; + if (fib_cfg.fc_gw4) fib_cfg.fc_gw_family = AF_INET; } else if (nlav) { @@ -902,6 +919,7 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh); + int err; nla = nla_find(attrs, attrlen, RTA_GATEWAY); nlav = nla_find(attrs, attrlen, RTA_VIA); @@ -912,12 +930,17 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, } if (nla) { + __be32 gw; + + err = fib_gw_from_attr(&gw, nla, extack); + if (err) + return err; + if (nh->fib_nh_gw_family != AF_INET || - nla_get_in_addr(nla) != nh->fib_nh_gw4) + gw != nh->fib_nh_gw4) return 1; } else if (nlav) { struct fib_config cfg2; - int err; err = fib_gw_from_via(&cfg2, nlav, extack); if (err) -- cgit v1.2.3 From 664b9c4b7392ce723b013201843264bf95481ce5 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 30 Dec 2021 17:36:32 -0700 Subject: ipv4: Check attribute length for RTA_FLOW in multipath route Make sure RTA_FLOW is at least 4B before using. Fixes: 4e902c57417c ("[IPv4]: FIB configuration using struct fib_config") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/fib_semantics.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f1caa2c1c041..36bc429f1635 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -731,8 +731,13 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, } nla = nla_find(attrs, attrlen, RTA_FLOW); - if (nla) + if (nla) { + if (nla_len(nla) < sizeof(u32)) { + NL_SET_ERR_MSG(extack, "Invalid RTA_FLOW"); + return -EINVAL; + } fib_cfg.fc_flow = nla_get_u32(nla); + } fib_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); @@ -963,8 +968,14 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, #ifdef CONFIG_IP_ROUTE_CLASSID nla = nla_find(attrs, attrlen, RTA_FLOW); - if (nla && nla_get_u32(nla) != nh->nh_tclassid) - return 1; + if (nla) { + if (nla_len(nla) < sizeof(u32)) { + NL_SET_ERR_MSG(extack, "Invalid RTA_FLOW"); + return -EINVAL; + } + if (nla_get_u32(nla) != nh->nh_tclassid) + return 1; + } #endif } -- cgit v1.2.3 From 4619bcf91399f00a40885100fb61d594d8454033 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 30 Dec 2021 17:36:33 -0700 Subject: ipv6: Check attribute length for RTA_GATEWAY in multipath route Commit referenced in the Fixes tag used nla_memcpy for RTA_GATEWAY as does the current nla_get_in6_addr. nla_memcpy protects against accessing memory greater than what is in the attribute, but there is no check requiring the attribute to have an IPv6 address. Add it. Fixes: 51ebd3181572 ("ipv6: add support of equal cost multipath (ECMP)") Signed-off-by: David Ahern Cc: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv6/route.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 42d60c76d30a..d16599c225b8 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5224,6 +5224,19 @@ out: return should_notify; } +static int fib6_gw_from_attr(struct in6_addr *gw, struct nlattr *nla, + struct netlink_ext_ack *extack) +{ + if (nla_len(nla) < sizeof(*gw)) { + NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_GATEWAY"); + return -EINVAL; + } + + *gw = nla_get_in6_addr(nla); + + return 0; +} + static int ip6_route_multipath_add(struct fib6_config *cfg, struct netlink_ext_ack *extack) { @@ -5264,7 +5277,13 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { - r_cfg.fc_gateway = nla_get_in6_addr(nla); + int ret; + + ret = fib6_gw_from_attr(&r_cfg.fc_gateway, nla, + extack); + if (ret) + return ret; + r_cfg.fc_flags |= RTF_GATEWAY; } r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); -- cgit v1.2.3 From 1ff15a710a862db1101b97810af14aedc835a86a Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 30 Dec 2021 17:36:34 -0700 Subject: ipv6: Check attribute length for RTA_GATEWAY when deleting multipath route Make sure RTA_GATEWAY for IPv6 multipath route has enough bytes to hold an IPv6 address. Fixes: 6b9ea5a64ed5 ("ipv6: fix multipath route replace error recovery") Signed-off-by: David Ahern Cc: Roopa Prabhu Signed-off-by: David S. Miller --- net/ipv6/route.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d16599c225b8..b311c0bc9983 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5453,7 +5453,11 @@ static int ip6_route_multipath_del(struct fib6_config *cfg, nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { - nla_memcpy(&r_cfg.fc_gateway, nla, 16); + err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla, + extack); + if (err) + return err; + r_cfg.fc_flags |= RTF_GATEWAY; } } -- cgit v1.2.3 From 8bda81a4d400cf8a72e554012f0d8c45e07a3904 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 30 Dec 2021 17:36:35 -0700 Subject: lwtunnel: Validate RTA_ENCAP_TYPE attribute length lwtunnel_valid_encap_type_attr is used to validate encap attributes within a multipath route. Add length validation checking to the type. lwtunnel_valid_encap_type_attr is called converting attributes to fib{6,}_config struct which means it is used before fib_get_nhs, ip6_route_multipath_add, and ip6_route_multipath_del - other locations that use rtnh_ok and then nla_get_u16 on RTA_ENCAP_TYPE attribute. Fixes: 9ed59592e3e3 ("lwtunnel: fix autoload of lwt modules") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/core/lwtunnel.c | 4 ++++ net/ipv4/fib_semantics.c | 3 +++ net/ipv6/route.c | 4 ++++ 3 files changed, 11 insertions(+) diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 2820aca2173a..9ccd64e8a666 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -197,6 +197,10 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining, nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla_entype) { + if (nla_len(nla_entype) < sizeof(u16)) { + NL_SET_ERR_MSG(extack, "Invalid RTA_ENCAP_TYPE"); + return -EINVAL; + } encap_type = nla_get_u16(nla_entype); if (lwtunnel_valid_encap_type(encap_type, diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 36bc429f1635..92c29ab3d042 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -740,6 +740,9 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, } fib_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); + /* RTA_ENCAP_TYPE length checked in + * lwtunnel_valid_encap_type_attr + */ nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla) fib_cfg.fc_encap_type = nla_get_u16(nla); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b311c0bc9983..d2ff8a7e1709 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5287,6 +5287,10 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, r_cfg.fc_flags |= RTF_GATEWAY; } r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); + + /* RTA_ENCAP_TYPE length checked in + * lwtunnel_valid_encap_type_attr + */ nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla) r_cfg.fc_encap_type = nla_get_u16(nla); -- cgit v1.2.3 From f5c73297181c6b3ad76537bad98eaad6d29b9333 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Thu, 30 Dec 2021 20:12:31 -0800 Subject: userfaultfd/selftests: fix hugetlb area allocations Currently, userfaultfd selftest for hugetlb as run from run_vmtests.sh or any environment where there are 'just enough' hugetlb pages will always fail with: testing events (fork, remap, remove): ERROR: UFFDIO_COPY error: -12 (errno=12, line=616) The ENOMEM error code implies there are not enough hugetlb pages. However, there are free hugetlb pages but they are all reserved. There is a basic problem with the way the test allocates hugetlb pages which has existed since the test was originally written. Due to the way 'cleanup' was done between different phases of the test, this issue was masked until recently. The issue was uncovered by commit 8ba6e8640844 ("userfaultfd/selftests: reinitialize test context in each test"). For the hugetlb test, src and dst areas are allocated as PRIVATE mappings of a hugetlb file. This means that at mmap time, pages are reserved for the src and dst areas. At the start of event testing (and other tests) the src area is populated which results in allocation of huge pages to fill the area and consumption of reserves associated with the area. Then, a child is forked to fault in the dst area. Note that the dst area was allocated in the parent and hence the parent owns the reserves associated with the mapping. The child has normal access to the dst area, but can not use the reserves created/owned by the parent. Thus, if there are no other huge pages available allocation of a page for the dst by the child will fail. Fix by not creating reserves for the dst area. In this way the child can use free (non-reserved) pages. Also, MAP_PRIVATE of a file only makes sense if you are interested in the contents of the file before making a COW copy. The test does not do this. So, just use MAP_ANONYMOUS | MAP_HUGETLB to create an anonymous hugetlb mapping. There is no need to create a hugetlb file in the non-shared case. Link: https://lkml.kernel.org/r/20211217172919.7861-1-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Cc: Axel Rasmussen Cc: Peter Xu Cc: Andrea Arcangeli Cc: Mina Almasry Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/testing/selftests/vm/userfaultfd.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 8a09057d2f22..9354a5e0321c 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -87,7 +87,7 @@ static bool test_uffdio_minor = false; static bool map_shared; static int shm_fd; -static int huge_fd; +static int huge_fd = -1; /* only used for hugetlb_shared test */ static char *huge_fd_off0; static unsigned long long *count_verify; static int uffd = -1; @@ -223,6 +223,9 @@ static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) static void hugetlb_release_pages(char *rel_area) { + if (huge_fd == -1) + return; + if (fallocate(huge_fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, rel_area == huge_fd_off0 ? 0 : nr_pages * page_size, nr_pages * page_size)) @@ -235,16 +238,17 @@ static void hugetlb_allocate_area(void **alloc_area) char **alloc_area_alias; *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - (map_shared ? MAP_SHARED : MAP_PRIVATE) | - MAP_HUGETLB, - huge_fd, *alloc_area == area_src ? 0 : - nr_pages * page_size); + map_shared ? MAP_SHARED : + MAP_PRIVATE | MAP_HUGETLB | + (*alloc_area == area_src ? 0 : MAP_NORESERVE), + huge_fd, + *alloc_area == area_src ? 0 : nr_pages * page_size); if (*alloc_area == MAP_FAILED) err("mmap of hugetlbfs file failed"); if (map_shared) { area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_HUGETLB, + MAP_SHARED, huge_fd, *alloc_area == area_src ? 0 : nr_pages * page_size); if (area_alias == MAP_FAILED) -- cgit v1.2.3 From ebb3f994dd92f8fb4d70c7541091216c1e10cb71 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Thu, 30 Dec 2021 20:12:34 -0800 Subject: mm/damon/dbgfs: fix 'struct pid' leaks in 'dbgfs_target_ids_write()' DAMON debugfs interface increases the reference counts of 'struct pid's for targets from the 'target_ids' file write callback ('dbgfs_target_ids_write()'), but decreases the counts only in DAMON monitoring termination callback ('dbgfs_before_terminate()'). Therefore, when 'target_ids' file is repeatedly written without DAMON monitoring start/termination, the reference count is not decreased and therefore memory for the 'struct pid' cannot be freed. This commit fixes this issue by decreasing the reference counts when 'target_ids' is written. Link: https://lkml.kernel.org/r/20211229124029.23348-1-sj@kernel.org Fixes: 4bc05954d007 ("mm/damon: implement a debugfs-based user space interface") Signed-off-by: SeongJae Park Cc: [5.15+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/dbgfs.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 4fbd729edc9e..ad65436756af 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -353,6 +353,7 @@ static ssize_t dbgfs_target_ids_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct damon_ctx *ctx = file->private_data; + struct damon_target *t, *next_t; bool id_is_pid = true; char *kbuf, *nrs; unsigned long *targets; @@ -397,8 +398,12 @@ static ssize_t dbgfs_target_ids_write(struct file *file, goto unlock_out; } - /* remove targets with previously-set primitive */ - damon_set_targets(ctx, NULL, 0); + /* remove previously set targets */ + damon_for_each_target_safe(t, next_t, ctx) { + if (targetid_is_pid(ctx)) + put_pid((struct pid *)t->id); + damon_destroy_target(t); + } /* Configure the context for the address space type */ if (id_is_pid) -- cgit v1.2.3 From 1b4e3f26f9f7553b260b8aed43967500961448a6 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 2 Dec 2021 15:06:14 +0000 Subject: mm: vmscan: Reduce throttling due to a failure to make progress Mike Galbraith, Alexey Avramov and Darrick Wong all reported similar problems due to reclaim throttling for excessive lengths of time. In Alexey's case, a memory hog that should go OOM quickly stalls for several minutes before stalling. In Mike and Darrick's cases, a small memcg environment stalled excessively even though the system had enough memory overall. Commit 69392a403f49 ("mm/vmscan: throttle reclaim when no progress is being made") introduced the problem although commit a19594ca4a8b ("mm/vmscan: increase the timeout if page reclaim is not making progress") made it worse. Systems at or near an OOM state that cannot be recovered must reach OOM quickly and memcg should kill tasks if a memcg is near OOM. To address this, only stall for the first zone in the zonelist, reduce the timeout to 1 tick for VMSCAN_THROTTLE_NOPROGRESS and only stall if the scan control nr_reclaimed is 0, kswapd is still active and there were excessive pages pending for writeback. If kswapd has stopped reclaiming due to excessive failures, do not stall at all so that OOM triggers relatively quickly. Similarly, if an LRU is simply congested, only lightly throttle similar to NOPROGRESS. Alexey's original case was the most straight forward for i in {1..3}; do tail /dev/zero; done On vanilla 5.16-rc1, this test stalled heavily, after the patch the test completes in a few seconds similar to 5.15. Alexey's second test case added watching a youtube video while tail runs 10 times. On 5.15, playback only jitters slightly, 5.16-rc1 stalls a lot with lots of frames missing and numerous audio glitches. With this patch applies, the video plays similarly to 5.15. [lkp@intel.com: Fix W=1 build warning] Link: https://lore.kernel.org/r/99e779783d6c7fce96448a3402061b9dc1b3b602.camel@gmx.de Link: https://lore.kernel.org/r/20211124011954.7cab9bb4@mail.inbox.lv Link: https://lore.kernel.org/r/20211022144651.19914-1-mgorman@techsingularity.net Link: https://lore.kernel.org/r/20211202150614.22440-1-mgorman@techsingularity.net Link: https://linux-regtracking.leemhuis.info/regzbot/regression/20211124011954.7cab9bb4@mail.inbox.lv/ Reported-and-tested-by: Alexey Avramov Reported-and-tested-by: Mike Galbraith Reported-and-tested-by: Darrick J. Wong Reported-by: kernel test robot Acked-by: Hugh Dickins Tracked-by: Thorsten Leemhuis Fixes: 69392a403f49 ("mm/vmscan: throttle reclaim when no progress is being made") Signed-off-by: Mel Gorman Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + include/trace/events/vmscan.h | 4 ++- mm/vmscan.c | 64 +++++++++++++++++++++++++++++++++++++------ 3 files changed, 59 insertions(+), 10 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 58e744b78c2c..936dc0b6c226 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -277,6 +277,7 @@ enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, VMSCAN_THROTTLE_NOPROGRESS, + VMSCAN_THROTTLE_CONGESTED, NR_VMSCAN_THROTTLE, }; diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index f25a6149d3ba..ca2e9009a651 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -30,12 +30,14 @@ #define _VMSCAN_THROTTLE_WRITEBACK (1 << VMSCAN_THROTTLE_WRITEBACK) #define _VMSCAN_THROTTLE_ISOLATED (1 << VMSCAN_THROTTLE_ISOLATED) #define _VMSCAN_THROTTLE_NOPROGRESS (1 << VMSCAN_THROTTLE_NOPROGRESS) +#define _VMSCAN_THROTTLE_CONGESTED (1 << VMSCAN_THROTTLE_CONGESTED) #define show_throttle_flags(flags) \ (flags) ? __print_flags(flags, "|", \ {_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"}, \ {_VMSCAN_THROTTLE_ISOLATED, "VMSCAN_THROTTLE_ISOLATED"}, \ - {_VMSCAN_THROTTLE_NOPROGRESS, "VMSCAN_THROTTLE_NOPROGRESS"} \ + {_VMSCAN_THROTTLE_NOPROGRESS, "VMSCAN_THROTTLE_NOPROGRESS"}, \ + {_VMSCAN_THROTTLE_CONGESTED, "VMSCAN_THROTTLE_CONGESTED"} \ ) : "VMSCAN_THROTTLE_NONE" diff --git a/mm/vmscan.c b/mm/vmscan.c index fb9584641ac7..4c4d5f6cd8a3 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1021,6 +1021,39 @@ static void handle_write_error(struct address_space *mapping, unlock_page(page); } +static bool skip_throttle_noprogress(pg_data_t *pgdat) +{ + int reclaimable = 0, write_pending = 0; + int i; + + /* + * If kswapd is disabled, reschedule if necessary but do not + * throttle as the system is likely near OOM. + */ + if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) + return true; + + /* + * If there are a lot of dirty/writeback pages then do not + * throttle as throttling will occur when the pages cycle + * towards the end of the LRU if still under writeback. + */ + for (i = 0; i < MAX_NR_ZONES; i++) { + struct zone *zone = pgdat->node_zones + i; + + if (!populated_zone(zone)) + continue; + + reclaimable += zone_reclaimable_pages(zone); + write_pending += zone_page_state_snapshot(zone, + NR_ZONE_WRITE_PENDING); + } + if (2 * write_pending <= reclaimable) + return true; + + return false; +} + void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) { wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; @@ -1056,8 +1089,16 @@ void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) } break; + case VMSCAN_THROTTLE_CONGESTED: + fallthrough; case VMSCAN_THROTTLE_NOPROGRESS: - timeout = HZ/2; + if (skip_throttle_noprogress(pgdat)) { + cond_resched(); + return; + } + + timeout = 1; + break; case VMSCAN_THROTTLE_ISOLATED: timeout = HZ/50; @@ -3321,7 +3362,7 @@ again: if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) - reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED); if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc)) @@ -3386,16 +3427,16 @@ static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc) } /* - * Do not throttle kswapd on NOPROGRESS as it will throttle on - * VMSCAN_THROTTLE_WRITEBACK if there are too many pages under - * writeback and marked for immediate reclaim at the tail of - * the LRU. + * Do not throttle kswapd or cgroup reclaim on NOPROGRESS as it will + * throttle on VMSCAN_THROTTLE_WRITEBACK if there are too many pages + * under writeback and marked for immediate reclaim at the tail of the + * LRU. */ - if (current_is_kswapd()) + if (current_is_kswapd() || cgroup_reclaim(sc)) return; /* Throttle if making no progress at high prioities. */ - if (sc->priority < DEF_PRIORITY - 2) + if (sc->priority == 1 && !sc->nr_reclaimed) reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS); } @@ -3415,6 +3456,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) unsigned long nr_soft_scanned; gfp_t orig_mask; pg_data_t *last_pgdat = NULL; + pg_data_t *first_pgdat = NULL; /* * If the number of buffer_heads in the machine exceeds the maximum @@ -3478,14 +3520,18 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) /* need some check for avoid more shrink_zone() */ } + if (!first_pgdat) + first_pgdat = zone->zone_pgdat; + /* See comment about same check for global reclaim above */ if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; shrink_node(zone->zone_pgdat, sc); - consider_reclaim_throttle(zone->zone_pgdat, sc); } + consider_reclaim_throttle(first_pgdat, sc); + /* * Restore to original mask to avoid the impact on the caller if we * promoted it to __GFP_HIGHMEM. -- cgit v1.2.3 From 8008293888188c3923f5bd8a69370dae25ed14e5 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 31 Dec 2021 13:10:09 -0800 Subject: mm: vmscan: reduce throttling due to a failure to make progress -fix Hugh Dickins reported the following My tmpfs swapping load (tweaked to use huge pages more heavily than in real life) is far from being a realistic load: but it was notably slowed down by your throttling mods in 5.16-rc, and this patch makes it well again - thanks. But: it very quickly hit NULL pointer until I changed that last line to if (first_pgdat) consider_reclaim_throttle(first_pgdat, sc); The likely issue is that huge pages are a major component of the test workload. When this is the case, first_pgdat may never get set if compaction is ready to continue due to this check if (IS_ENABLED(CONFIG_COMPACTION) && sc->order > PAGE_ALLOC_COSTLY_ORDER && compaction_ready(zone, sc)) { sc->compaction_ready = true; continue; } If this was true for every zone in the zonelist, first_pgdat would never get set resulting in a NULL pointer exception. Link: https://lkml.kernel.org/r/20211209095453.GM3366@techsingularity.net Fixes: 1b4e3f26f9f75 ("mm: vmscan: Reduce throttling due to a failure to make progress") Signed-off-by: Mel Gorman Reported-by: Hugh Dickins Cc: Michal Hocko Cc: Vlastimil Babka Cc: Rik van Riel Cc: Mike Galbraith Cc: Darrick J. Wong Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 4c4d5f6cd8a3..700434db5735 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3530,7 +3530,8 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) shrink_node(zone->zone_pgdat, sc); } - consider_reclaim_throttle(first_pgdat, sc); + if (first_pgdat) + consider_reclaim_throttle(first_pgdat, sc); /* * Restore to original mask to avoid the impact on the caller if we -- cgit v1.2.3 From 5e75d0b215b868337e7a193f28a543ec00e858b1 Mon Sep 17 00:00:00 2001 From: Jianguo Wu Date: Fri, 31 Dec 2021 10:01:08 +0800 Subject: selftests: net: udpgro_fwd.sh: explicitly checking the available ping feature As Paolo pointed out, the result of ping IPv6 address depends on the running distro. So explicitly checking the available ping feature, as e.g. do the bareudp.sh self-tests. Fixes: 8b3170e07539 ("selftests: net: using ping6 for IPv6 in udpgro_fwd.sh") Signed-off-by: Jianguo Wu Link: https://lore.kernel.org/r/825ee22b-4245-dbf7-d2f7-a230770d6e21@163.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/udpgro_fwd.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index 3ea73013d956..6f05e06f6761 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -193,7 +193,8 @@ for family in 4 6; do SUFFIX="64 nodad" VXDEV=vxlan6 IPT=ip6tables - PING="ping6" + # Use ping6 on systems where ping doesn't handle IPv6 + ping -w 1 -c 1 ::1 > /dev/null 2>&1 || PING="ping6" fi echo "IPv$family" -- cgit v1.2.3 From d6d86830705f173fca6087a3e67ceaf68db80523 Mon Sep 17 00:00:00 2001 From: Haimin Zhang Date: Fri, 31 Dec 2021 10:35:23 +0800 Subject: net ticp:fix a kernel-infoleak in __tipc_sendmsg() struct tipc_socket_addr.ref has a 4-byte hole,and __tipc_getname() currently copying it to user space,causing kernel-infoleak. BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:121 [inline] BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:121 [inline] lib/usercopy.c:33 BUG: KMSAN: kernel-infoleak in _copy_to_user+0x1c9/0x270 lib/usercopy.c:33 lib/usercopy.c:33 instrument_copy_to_user include/linux/instrumented.h:121 [inline] instrument_copy_to_user include/linux/instrumented.h:121 [inline] lib/usercopy.c:33 _copy_to_user+0x1c9/0x270 lib/usercopy.c:33 lib/usercopy.c:33 copy_to_user include/linux/uaccess.h:209 [inline] copy_to_user include/linux/uaccess.h:209 [inline] net/socket.c:287 move_addr_to_user+0x3f6/0x600 net/socket.c:287 net/socket.c:287 __sys_getpeername+0x470/0x6b0 net/socket.c:1987 net/socket.c:1987 __do_sys_getpeername net/socket.c:1997 [inline] __se_sys_getpeername net/socket.c:1994 [inline] __do_sys_getpeername net/socket.c:1997 [inline] net/socket.c:1994 __se_sys_getpeername net/socket.c:1994 [inline] net/socket.c:1994 __x64_sys_getpeername+0xda/0x120 net/socket.c:1994 net/socket.c:1994 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_x64 arch/x86/entry/common.c:51 [inline] arch/x86/entry/common.c:82 do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:82 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x44/0xae Uninit was stored to memory at: tipc_getname+0x575/0x5e0 net/tipc/socket.c:757 net/tipc/socket.c:757 __sys_getpeername+0x3b3/0x6b0 net/socket.c:1984 net/socket.c:1984 __do_sys_getpeername net/socket.c:1997 [inline] __se_sys_getpeername net/socket.c:1994 [inline] __do_sys_getpeername net/socket.c:1997 [inline] net/socket.c:1994 __se_sys_getpeername net/socket.c:1994 [inline] net/socket.c:1994 __x64_sys_getpeername+0xda/0x120 net/socket.c:1994 net/socket.c:1994 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_x64 arch/x86/entry/common.c:51 [inline] arch/x86/entry/common.c:82 do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:82 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x44/0xae Uninit was stored to memory at: msg_set_word net/tipc/msg.h:212 [inline] msg_set_destport net/tipc/msg.h:619 [inline] msg_set_word net/tipc/msg.h:212 [inline] net/tipc/socket.c:1486 msg_set_destport net/tipc/msg.h:619 [inline] net/tipc/socket.c:1486 __tipc_sendmsg+0x44fa/0x5890 net/tipc/socket.c:1486 net/tipc/socket.c:1486 tipc_sendmsg+0xeb/0x140 net/tipc/socket.c:1402 net/tipc/socket.c:1402 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg net/socket.c:724 [inline] sock_sendmsg_nosec net/socket.c:704 [inline] net/socket.c:2409 sock_sendmsg net/socket.c:724 [inline] net/socket.c:2409 ____sys_sendmsg+0xe11/0x12c0 net/socket.c:2409 net/socket.c:2409 ___sys_sendmsg net/socket.c:2463 [inline] ___sys_sendmsg net/socket.c:2463 [inline] net/socket.c:2492 __sys_sendmsg+0x704/0x840 net/socket.c:2492 net/socket.c:2492 __do_sys_sendmsg net/socket.c:2501 [inline] __se_sys_sendmsg net/socket.c:2499 [inline] __do_sys_sendmsg net/socket.c:2501 [inline] net/socket.c:2499 __se_sys_sendmsg net/socket.c:2499 [inline] net/socket.c:2499 __x64_sys_sendmsg+0xe2/0x120 net/socket.c:2499 net/socket.c:2499 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_x64 arch/x86/entry/common.c:51 [inline] arch/x86/entry/common.c:82 do_syscall_64+0x54/0xd0 arch/x86/entry/common.c:82 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x44/0xae Local variable skaddr created at: __tipc_sendmsg+0x2d0/0x5890 net/tipc/socket.c:1419 net/tipc/socket.c:1419 tipc_sendmsg+0xeb/0x140 net/tipc/socket.c:1402 net/tipc/socket.c:1402 Bytes 4-7 of 16 are uninitialized Memory access of size 16 starts at ffff888113753e00 Data copied to user address 0000000020000280 Reported-by: syzbot+cdbd40e0c3ca02cae3b7@syzkaller.appspotmail.com Signed-off-by: Haimin Zhang Acked-by: Jon Maloy Link: https://lore.kernel.org/r/1640918123-14547-1-git-send-email-tcs.kernel@gmail.com Signed-off-by: Jakub Kicinski --- net/tipc/socket.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index ad570c2450be..3e63c83e641c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1461,6 +1461,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) msg_set_syn(hdr, 1); } + memset(&skaddr, 0, sizeof(skaddr)); + /* Determine destination */ if (atype == TIPC_SERVICE_RANGE) { return tipc_sendmcast(sock, ua, m, dlen, timeout); -- cgit v1.2.3 From 938f2e0b57ffe8a6df71e1e177b2978b1b33fe5e Mon Sep 17 00:00:00 2001 From: Linus Lüssing Date: Sat, 1 Jan 2022 06:27:13 +0100 Subject: batman-adv: mcast: don't send link-local multicast to mcast routers The addition of routable multicast TX handling introduced a bug/regression for packets with a link-local multicast destination: These packets would be sent to all batman-adv nodes with a multicast router and to all batman-adv nodes with an old version without multicast router detection. This even disregards the batman-adv multicast fanout setting, which can potentially lead to an unwanted, high number of unicast transmissions or even congestion. Fixing this by avoiding to send link-local multicast packets to nodes in the multicast router list. Fixes: 11d458c1cb9b ("batman-adv: mcast: apply optimizations for routable packets, too") Signed-off-by: Linus Lüssing Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- net/batman-adv/multicast.c | 15 ++++++++++----- net/batman-adv/multicast.h | 10 ++++++---- net/batman-adv/soft-interface.c | 7 +++++-- 3 files changed, 21 insertions(+), 11 deletions(-) diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 433901dcf0c3..f4004cf0ff6f 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1339,6 +1339,7 @@ batadv_mcast_forw_rtr_node_get(struct batadv_priv *bat_priv, * @bat_priv: the bat priv with all the soft interface information * @skb: The multicast packet to check * @orig: an originator to be set to forward the skb to + * @is_routable: stores whether the destination is routable * * Return: the forwarding mode as enum batadv_forw_mode and in case of * BATADV_FORW_SINGLE set the orig to the single originator the skb @@ -1346,17 +1347,16 @@ batadv_mcast_forw_rtr_node_get(struct batadv_priv *bat_priv, */ enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, - struct batadv_orig_node **orig) + struct batadv_orig_node **orig, int *is_routable) { int ret, tt_count, ip_count, unsnoop_count, total_count; bool is_unsnoopable = false; unsigned int mcast_fanout; struct ethhdr *ethhdr; - int is_routable = 0; int rtr_count = 0; ret = batadv_mcast_forw_mode_check(bat_priv, skb, &is_unsnoopable, - &is_routable); + is_routable); if (ret == -ENOMEM) return BATADV_FORW_NONE; else if (ret < 0) @@ -1369,7 +1369,7 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, ip_count = batadv_mcast_forw_want_all_ip_count(bat_priv, ethhdr); unsnoop_count = !is_unsnoopable ? 0 : atomic_read(&bat_priv->mcast.num_want_all_unsnoopables); - rtr_count = batadv_mcast_forw_rtr_count(bat_priv, is_routable); + rtr_count = batadv_mcast_forw_rtr_count(bat_priv, *is_routable); total_count = tt_count + ip_count + unsnoop_count + rtr_count; @@ -1689,6 +1689,7 @@ batadv_mcast_forw_want_rtr(struct batadv_priv *bat_priv, * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit * @vid: the vlan identifier + * @is_routable: stores whether the destination is routable * * Sends copies of a frame with multicast destination to any node that signaled * interest in it, that is either via the translation table or the according @@ -1701,7 +1702,7 @@ batadv_mcast_forw_want_rtr(struct batadv_priv *bat_priv, * is neither IPv4 nor IPv6. NET_XMIT_SUCCESS otherwise. */ int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, - unsigned short vid) + unsigned short vid, int is_routable) { int ret; @@ -1717,12 +1718,16 @@ int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, return ret; } + if (!is_routable) + goto skip_mc_router; + ret = batadv_mcast_forw_want_rtr(bat_priv, skb, vid); if (ret != NET_XMIT_SUCCESS) { kfree_skb(skb); return ret; } +skip_mc_router: consume_skb(skb); return ret; } diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 9fee5da08311..8aec818d0bf6 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -43,7 +43,8 @@ enum batadv_forw_mode { enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, - struct batadv_orig_node **mcast_single_orig); + struct batadv_orig_node **mcast_single_orig, + int *is_routable); int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, struct sk_buff *skb, @@ -51,7 +52,7 @@ int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node); int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, - unsigned short vid); + unsigned short vid, int is_routable); void batadv_mcast_init(struct batadv_priv *bat_priv); @@ -68,7 +69,8 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node); static inline enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, - struct batadv_orig_node **mcast_single_orig) + struct batadv_orig_node **mcast_single_orig, + int *is_routable) { return BATADV_FORW_ALL; } @@ -85,7 +87,7 @@ batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, static inline int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, - unsigned short vid) + unsigned short vid, int is_routable) { kfree_skb(skb); return NET_XMIT_DROP; diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 7ee09337fc40..2dbbe6c19609 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -198,6 +198,7 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, int gw_mode; enum batadv_forw_mode forw_mode = BATADV_FORW_SINGLE; struct batadv_orig_node *mcast_single_orig = NULL; + int mcast_is_routable = 0; int network_offset = ETH_HLEN; __be16 proto; @@ -300,7 +301,8 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, send: if (do_bcast && !is_broadcast_ether_addr(ethhdr->h_dest)) { forw_mode = batadv_mcast_forw_mode(bat_priv, skb, - &mcast_single_orig); + &mcast_single_orig, + &mcast_is_routable); if (forw_mode == BATADV_FORW_NONE) goto dropped; @@ -359,7 +361,8 @@ send: ret = batadv_mcast_forw_send_orig(bat_priv, skb, vid, mcast_single_orig); } else if (forw_mode == BATADV_FORW_SOME) { - ret = batadv_mcast_forw_send(bat_priv, skb, vid); + ret = batadv_mcast_forw_send(bat_priv, skb, vid, + mcast_is_routable); } else { if (batadv_dat_snoop_outgoing_arp_request(bat_priv, skb)) -- cgit v1.2.3 From ae81de737885820616f9c67c2e7935998b523d58 Mon Sep 17 00:00:00 2001 From: Gagan Kumar Date: Sat, 1 Jan 2022 11:11:25 +0530 Subject: mctp: Remove only static neighbour on RTM_DELNEIGH Add neighbour source flag in mctp_neigh_remove(...) to allow removal of only static neighbours. This should be a no-op change and might be useful later when mctp can have MCTP_NEIGH_DISCOVER neighbours. Signed-off-by: Gagan Kumar Signed-off-by: David S. Miller --- net/mctp/neigh.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/net/mctp/neigh.c b/net/mctp/neigh.c index 5cc042121493..6ad3e33bd4d4 100644 --- a/net/mctp/neigh.c +++ b/net/mctp/neigh.c @@ -85,8 +85,8 @@ void mctp_neigh_remove_dev(struct mctp_dev *mdev) mutex_unlock(&net->mctp.neigh_lock); } -// TODO: add a "source" flag so netlink can only delete static neighbours? -static int mctp_neigh_remove(struct mctp_dev *mdev, mctp_eid_t eid) +static int mctp_neigh_remove(struct mctp_dev *mdev, mctp_eid_t eid, + enum mctp_neigh_source source) { struct net *net = dev_net(mdev->dev); struct mctp_neigh *neigh, *tmp; @@ -94,7 +94,8 @@ static int mctp_neigh_remove(struct mctp_dev *mdev, mctp_eid_t eid) mutex_lock(&net->mctp.neigh_lock); list_for_each_entry_safe(neigh, tmp, &net->mctp.neighbours, list) { - if (neigh->dev == mdev && neigh->eid == eid) { + if (neigh->dev == mdev && neigh->eid == eid && + neigh->source == source) { list_del_rcu(&neigh->list); /* TODO: immediate RTM_DELNEIGH */ call_rcu(&neigh->rcu, __mctp_neigh_free); @@ -202,7 +203,7 @@ static int mctp_rtm_delneigh(struct sk_buff *skb, struct nlmsghdr *nlh, if (!mdev) return -ENODEV; - return mctp_neigh_remove(mdev, eid); + return mctp_neigh_remove(mdev, eid, MCTP_NEIGH_STATIC); } static int mctp_fill_neigh(struct sk_buff *skb, u32 portid, u32 seq, int event, -- cgit v1.2.3 From c255a34e02efb1393d23ffb205ba1a11320aeffb Mon Sep 17 00:00:00 2001 From: Arthur Kiyanovski Date: Sun, 2 Jan 2022 07:37:26 +0000 Subject: net: ena: Fix undefined state when tx request id is out of bounds ena_com_tx_comp_req_id_get() checks the req_id of a received completion, and if it is out of bounds returns -EINVAL. This is a sign that something is wrong with the device and it needs to be reset. The current code does not reset the device in this case, which leaves the driver in an undefined state, where this completion is not properly handled. This commit adds a call to handle_invalid_req_id() in ena_clean_tx_irq() and ena_clean_xdp_irq() which resets the device to fix the issue. This commit also removes unnecessary request id checks from validate_tx_req_id() and validate_xdp_req_id(). This check is unneeded because it was already performed in ena_com_tx_comp_req_id_get(), which is called right before these functions. Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action") Signed-off-by: Shay Agroskin Signed-off-by: Arthur Kiyanovski Signed-off-by: David S. Miller --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 34 ++++++++++++++++------------ 1 file changed, 20 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 7d5d885d85d5..2274063e34cc 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1288,26 +1288,22 @@ static int handle_invalid_req_id(struct ena_ring *ring, u16 req_id, static int validate_tx_req_id(struct ena_ring *tx_ring, u16 req_id) { - struct ena_tx_buffer *tx_info = NULL; + struct ena_tx_buffer *tx_info; - if (likely(req_id < tx_ring->ring_size)) { - tx_info = &tx_ring->tx_buffer_info[req_id]; - if (likely(tx_info->skb)) - return 0; - } + tx_info = &tx_ring->tx_buffer_info[req_id]; + if (likely(tx_info->skb)) + return 0; return handle_invalid_req_id(tx_ring, req_id, tx_info, false); } static int validate_xdp_req_id(struct ena_ring *xdp_ring, u16 req_id) { - struct ena_tx_buffer *tx_info = NULL; + struct ena_tx_buffer *tx_info; - if (likely(req_id < xdp_ring->ring_size)) { - tx_info = &xdp_ring->tx_buffer_info[req_id]; - if (likely(tx_info->xdpf)) - return 0; - } + tx_info = &xdp_ring->tx_buffer_info[req_id]; + if (likely(tx_info->xdpf)) + return 0; return handle_invalid_req_id(xdp_ring, req_id, tx_info, true); } @@ -1332,9 +1328,14 @@ static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget) rc = ena_com_tx_comp_req_id_get(tx_ring->ena_com_io_cq, &req_id); - if (rc) + if (rc) { + if (unlikely(rc == -EINVAL)) + handle_invalid_req_id(tx_ring, req_id, NULL, + false); break; + } + /* validate that the request id points to a valid skb */ rc = validate_tx_req_id(tx_ring, req_id); if (rc) break; @@ -1896,9 +1897,14 @@ static int ena_clean_xdp_irq(struct ena_ring *xdp_ring, u32 budget) rc = ena_com_tx_comp_req_id_get(xdp_ring->ena_com_io_cq, &req_id); - if (rc) + if (rc) { + if (unlikely(rc == -EINVAL)) + handle_invalid_req_id(xdp_ring, req_id, NULL, + true); break; + } + /* validate that the request id points to a valid xdp_frame */ rc = validate_xdp_req_id(xdp_ring, req_id); if (rc) break; -- cgit v1.2.3 From cb3d4f98f0b26eafa0b913ac3716e4714254a747 Mon Sep 17 00:00:00 2001 From: Arthur Kiyanovski Date: Sun, 2 Jan 2022 07:37:27 +0000 Subject: net: ena: Fix wrong rx request id by resetting device A wrong request id received from the device is a sign that something is wrong with it, therefore trigger a device reset. Also add some debug info to the "Page is NULL" print to make it easier to debug. Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)") Signed-off-by: Arthur Kiyanovski Signed-off-by: David S. Miller --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 2274063e34cc..52a8c60b7e29 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1428,6 +1428,7 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, u16 *next_to_clean) { struct ena_rx_buffer *rx_info; + struct ena_adapter *adapter; u16 len, req_id, buf = 0; struct sk_buff *skb; void *page_addr; @@ -1440,8 +1441,14 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, rx_info = &rx_ring->rx_buffer_info[req_id]; if (unlikely(!rx_info->page)) { - netif_err(rx_ring->adapter, rx_err, rx_ring->netdev, - "Page is NULL\n"); + adapter = rx_ring->adapter; + netif_err(adapter, rx_err, rx_ring->netdev, + "Page is NULL. qid %u req_id %u\n", rx_ring->qid, req_id); + ena_increase_stat(&rx_ring->rx_stats.bad_req_id, 1, &rx_ring->syncp); + adapter->reset_reason = ENA_REGS_RESET_INV_RX_REQ_ID; + /* Make sure reset reason is set before triggering the reset */ + smp_mb__before_atomic(); + set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); return NULL; } -- cgit v1.2.3 From 5055dc0348b8b7c168e3296044bccd724e1ae6cd Mon Sep 17 00:00:00 2001 From: Arthur Kiyanovski Date: Sun, 2 Jan 2022 07:37:28 +0000 Subject: net: ena: Fix error handling when calculating max IO queues number The role of ena_calc_max_io_queue_num() is to return the number of queues supported by the device, which means the return value should be >=0. The function that calls ena_calc_max_io_queue_num(), checks the return value. If it is 0, it means the device reported it supports 0 IO queues. This case is considered an error and is handled by the calling function accordingly. However the current implementation of ena_calc_max_io_queue_num() is wrong, since when it detects the device supports 0 IO queues, it returns -EFAULT. In such a case the calling function doesn't detect the error, and therefore doesn't handle it. This commit changes ena_calc_max_io_queue_num() to return 0 in case the device reported it supports 0 queues, allowing the calling function to properly handle the error case. Fixes: 736ce3f414cc ("net: ena: make ethtool -l show correct max number of queues") Signed-off-by: Shay Agroskin Signed-off-by: Arthur Kiyanovski Signed-off-by: David S. Miller --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 52a8c60b7e29..c72f0c7ff4aa 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -4026,10 +4026,6 @@ static u32 ena_calc_max_io_queue_num(struct pci_dev *pdev, max_num_io_queues = min_t(u32, max_num_io_queues, io_tx_cq_num); /* 1 IRQ for mgmnt and 1 IRQs for each IO direction */ max_num_io_queues = min_t(u32, max_num_io_queues, pci_msix_vec_count(pdev) - 1); - if (unlikely(!max_num_io_queues)) { - dev_err(&pdev->dev, "The device doesn't have io queues\n"); - return -EFAULT; - } return max_num_io_queues; } -- cgit v1.2.3 From f9d31c4cf4c11ff10317f038b9c6f7c3bda6cdd4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 31 Dec 2021 18:37:37 -0500 Subject: sctp: hold endpoint before calling cb in sctp_transport_lookup_process The same fix in commit 5ec7d18d1813 ("sctp: use call_rcu to free endpoint") is also needed for dumping one asoc and sock after the lookup. Fixes: 86fdb3448cc1 ("sctp: ensure ep is not destroyed before doing the dump") Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/sctp.h | 3 +-- net/sctp/diag.c | 46 +++++++++++++++++++++------------------------- net/sctp/socket.c | 22 +++++++++++++++------- 3 files changed, 37 insertions(+), 34 deletions(-) diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index d314a180ab93..3ae61ce2eabd 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -112,8 +112,7 @@ struct sctp_transport *sctp_transport_get_next(struct net *net, struct rhashtable_iter *iter); struct sctp_transport *sctp_transport_get_idx(struct net *net, struct rhashtable_iter *iter, int pos); -int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *), - struct net *net, +int sctp_transport_lookup_process(sctp_callback_t cb, struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, void *p); int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done, diff --git a/net/sctp/diag.c b/net/sctp/diag.c index a7d623171501..034e2c74497d 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -245,48 +245,44 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc) + 64; } -static int sctp_tsp_dump_one(struct sctp_transport *tsp, void *p) +static int sctp_sock_dump_one(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p) { struct sctp_association *assoc = tsp->asoc; - struct sock *sk = tsp->asoc->base.sk; struct sctp_comm_param *commp = p; - struct sk_buff *in_skb = commp->skb; + struct sock *sk = ep->base.sk; const struct inet_diag_req_v2 *req = commp->r; - const struct nlmsghdr *nlh = commp->nlh; - struct net *net = sock_net(in_skb->sk); + struct sk_buff *skb = commp->skb; struct sk_buff *rep; int err; err = sock_diag_check_cookie(sk, req->id.idiag_cookie); if (err) - goto out; + return err; - err = -ENOMEM; rep = nlmsg_new(inet_assoc_attr_size(assoc), GFP_KERNEL); if (!rep) - goto out; + return -ENOMEM; lock_sock(sk); - if (sk != assoc->base.sk) { - release_sock(sk); - sk = assoc->base.sk; - lock_sock(sk); + if (ep != assoc->ep) { + err = -EAGAIN; + goto out; } - err = inet_sctp_diag_fill(sk, assoc, rep, req, - sk_user_ns(NETLINK_CB(in_skb).sk), - NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh, - commp->net_admin); - release_sock(sk); + + err = inet_sctp_diag_fill(sk, assoc, rep, req, sk_user_ns(NETLINK_CB(skb).sk), + NETLINK_CB(skb).portid, commp->nlh->nlmsg_seq, 0, + commp->nlh, commp->net_admin); if (err < 0) { WARN_ON(err == -EMSGSIZE); - kfree_skb(rep); goto out; } + release_sock(sk); - err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); + return nlmsg_unicast(sock_net(skb->sk)->diag_nlsk, rep, NETLINK_CB(skb).portid); out: + release_sock(sk); + kfree_skb(rep); return err; } @@ -429,15 +425,15 @@ static void sctp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, static int sctp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { - struct sk_buff *in_skb = cb->skb; - struct net *net = sock_net(in_skb->sk); + struct sk_buff *skb = cb->skb; + struct net *net = sock_net(skb->sk); const struct nlmsghdr *nlh = cb->nlh; union sctp_addr laddr, paddr; struct sctp_comm_param commp = { - .skb = in_skb, + .skb = skb, .r = req, .nlh = nlh, - .net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN), + .net_admin = netlink_net_capable(skb, CAP_NET_ADMIN), }; if (req->sdiag_family == AF_INET) { @@ -460,7 +456,7 @@ static int sctp_diag_dump_one(struct netlink_callback *cb, paddr.v6.sin6_family = AF_INET6; } - return sctp_transport_lookup_process(sctp_tsp_dump_one, + return sctp_transport_lookup_process(sctp_sock_dump_one, net, &laddr, &paddr, &commp); } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ad5028a07b18..da08671a3f80 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5317,23 +5317,31 @@ int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), } EXPORT_SYMBOL_GPL(sctp_for_each_endpoint); -int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *), - struct net *net, +int sctp_transport_lookup_process(sctp_callback_t cb, struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, void *p) { struct sctp_transport *transport; - int err; + struct sctp_endpoint *ep; + int err = -ENOENT; rcu_read_lock(); transport = sctp_addrs_lookup_transport(net, laddr, paddr); + if (!transport) { + rcu_read_unlock(); + return err; + } + ep = transport->asoc->ep; + if (!sctp_endpoint_hold(ep)) { /* asoc can be peeled off */ + sctp_transport_put(transport); + rcu_read_unlock(); + return err; + } rcu_read_unlock(); - if (!transport) - return -ENOENT; - err = cb(transport, p); + err = cb(ep, transport, p); + sctp_endpoint_put(ep); sctp_transport_put(transport); - return err; } EXPORT_SYMBOL_GPL(sctp_transport_lookup_process); -- cgit v1.2.3 From e0257a01d6689c273a019756ed5e13911cc1bfed Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 22 Dec 2021 00:11:30 +0800 Subject: perf pmu: Fix alias events list Commit 0e0ae8742207c3b4 ("perf list: Display hybrid PMU events with cpu type") changes the event list for uncore PMUs or arm64 heterogeneous CPU systems, such that duplicate aliases are incorrectly listed per PMU (which they should not be), like: # perf list ... unc_cbo_cache_lookup.any_es [Unit: uncore_cbox L3 Lookup any request that access cache and found line in E or S-state] unc_cbo_cache_lookup.any_es [Unit: uncore_cbox L3 Lookup any request that access cache and found line in E or S-state] unc_cbo_cache_lookup.any_i [Unit: uncore_cbox L3 Lookup any request that access cache and found line in I-state] unc_cbo_cache_lookup.any_i [Unit: uncore_cbox L3 Lookup any request that access cache and found line in I-state] ... Notice how the events are listed twice. The named commit changed how we remove duplicate events, in that events for different PMUs are not treated as duplicates. I suppose this is to handle how "Each hybrid pmu event has been assigned with a pmu name". Fix PMU alias listing by restoring behaviour to remove duplicates for non-hybrid PMUs. Fixes: 0e0ae8742207c3b4 ("perf list: Display hybrid PMU events with cpu type") Signed-off-by: John Garry Tested-by: Zhengjun Xing Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/1640103090-140490-1-git-send-email-john.garry@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 6ae58406f4fc..8dfbba15aeb8 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1659,6 +1659,21 @@ bool is_pmu_core(const char *name) return !strcmp(name, "cpu") || is_arm_pmu_core(name); } +static bool pmu_alias_is_duplicate(struct sevent *alias_a, + struct sevent *alias_b) +{ + /* Different names -> never duplicates */ + if (strcmp(alias_a->name, alias_b->name)) + return false; + + /* Don't remove duplicates for hybrid PMUs */ + if (perf_pmu__is_hybrid(alias_a->pmu) && + perf_pmu__is_hybrid(alias_b->pmu)) + return false; + + return true; +} + void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, bool long_desc, bool details_flag, bool deprecated, const char *pmu_name) @@ -1744,12 +1759,8 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag, qsort(aliases, len, sizeof(struct sevent), cmp_sevent); for (j = 0; j < len; j++) { /* Skip duplicates */ - if (j > 0 && !strcmp(aliases[j].name, aliases[j - 1].name)) { - if (!aliases[j].pmu || !aliases[j - 1].pmu || - !strcmp(aliases[j].pmu, aliases[j - 1].pmu)) { - continue; - } - } + if (j > 0 && pmu_alias_is_duplicate(&aliases[j], &aliases[j - 1])) + continue; if (name_only) { printf("%s ", aliases[j].name); -- cgit v1.2.3 From 64f18d2d043015b3f835ce4c9f3beb97cfd19b6e Mon Sep 17 00:00:00 2001 From: yaowenbin Date: Wed, 29 Dec 2021 16:55:19 +0800 Subject: perf top: Fix TUI exit screen refresh race condition When the following command is executed several times, a coredump file is generated. $ timeout -k 9 5 perf top -e task-clock ******* ******* ******* 0.01% [kernel] [k] __do_softirq 0.01% libpthread-2.28.so [.] __pthread_mutex_lock 0.01% [kernel] [k] __ll_sc_atomic64_sub_return double free or corruption (!prev) perf top --sort comm,dso timeout: the monitored command dumped core When we terminate "perf top" using sending signal method, SLsmg_reset_smg() called. SLsmg_reset_smg() resets the SLsmg screen management routines by freeing all memory allocated while it was active. However SLsmg_reinit_smg() maybe be called by another thread. SLsmg_reinit_smg() will free the same memory accessed by SLsmg_reset_smg(), thus it results in a double free. SLsmg_reinit_smg() is called already protected by ui__lock, so we fix the problem by adding pthread_mutex_trylock of ui__lock when calling SLsmg_reset_smg(). Signed-off-by: Wenyu Liu Tested-by: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: wuxu.wu@huawei.com Link: http://lore.kernel.org/lkml/a91e3943-7ddc-f5c0-a7f5-360f073c20e6@huawei.com Signed-off-by: Hewenliang Signed-off-by: yaowenbin Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/tui/setup.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index e9bfe856a5de..b1be59b4e2a4 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -170,9 +170,11 @@ void ui__exit(bool wait_for_ok) "Press any key...", 0); SLtt_set_cursor_visibility(1); - SLsmg_refresh(); - SLsmg_reset_smg(); + if (!pthread_mutex_trylock(&ui__lock)) { + SLsmg_refresh(); + SLsmg_reset_smg(); + pthread_mutex_unlock(&ui__lock); + } SLang_reset_tty(); - perf_error__unregister(&perf_tui_eops); } -- cgit v1.2.3 From 29262e1f773b4b6a43711120be564c57fca07cfb Mon Sep 17 00:00:00 2001 From: Thomas Toye Date: Sat, 1 Jan 2022 18:22:07 +0100 Subject: rndis_host: support Hytera digital radios Hytera makes a range of digital (DMR) radios. These radios can be programmed to a allow a computer to control them over Ethernet over USB, either using NCM or RNDIS. This commit adds support for RNDIS for Hytera radios. I tested with a Hytera PD785 and a Hytera MD785G. When these radios are programmed to set up a Radio to PC Network using RNDIS, an USB interface will be added with class 2 (Communications), subclass 2 (Abstract Modem Control) and an interface protocol of 255 ("vendor specific" - lsusb even hints "MSFT RNDIS?"). This patch is similar to the solution of this StackOverflow user, but that only works for the Hytera MD785: https://stackoverflow.com/a/53550858 To use the "Radio to PC Network" functionality of Hytera DMR radios, the radios need to be programmed correctly in CPS (Hytera's Customer Programming Software). "Forward to PC" should be checked in "Network" (under "General Setting" in "Conventional") and the "USB Network Communication Protocol" should be set to RNDIS. Signed-off-by: Thomas Toye Signed-off-by: David S. Miller --- drivers/net/usb/rndis_host.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c index 4a84f90e377c..247f58cb0f84 100644 --- a/drivers/net/usb/rndis_host.c +++ b/drivers/net/usb/rndis_host.c @@ -608,6 +608,11 @@ static const struct usb_device_id products [] = { USB_DEVICE_AND_INTERFACE_INFO(0x1630, 0x0042, USB_CLASS_COMM, 2 /* ACM */, 0x0ff), .driver_info = (unsigned long) &rndis_poll_status_info, +}, { + /* Hytera Communications DMR radios' "Radio to PC Network" */ + USB_VENDOR_AND_INTERFACE_INFO(0x238b, + USB_CLASS_COMM, 2 /* ACM */, 0x0ff), + .driver_info = (unsigned long)&rndis_info, }, { /* RNDIS is MSFT's un-official variant of CDC ACM */ USB_INTERFACE_INFO(USB_CLASS_COMM, 2 /* ACM */, 0x0ff), -- cgit v1.2.3 From 1ef5e1d0dca5b4ffd49d7dec4a83660882f1fda4 Mon Sep 17 00:00:00 2001 From: Markus Koch Date: Sun, 2 Jan 2022 17:54:08 +0100 Subject: net/fsl: Remove leftover definition in xgmac_mdio commit 26eee0210ad7 ("net/fsl: fix a bug in xgmac_mdio") fixed a bug in the QorIQ mdio driver but left the (now unused) incorrect bit definition for MDIO_DATA_BSY in the code. This commit removes it. Signed-off-by: Markus Koch Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/xgmac_mdio.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c index 0b68852379da..5b8b9bcf41a2 100644 --- a/drivers/net/ethernet/freescale/xgmac_mdio.c +++ b/drivers/net/ethernet/freescale/xgmac_mdio.c @@ -47,7 +47,6 @@ struct tgec_mdio_controller { #define MDIO_CTL_READ BIT(15) #define MDIO_DATA(x) (x & 0xffff) -#define MDIO_DATA_BSY BIT(31) struct mdio_fsl_priv { struct tgec_mdio_controller __iomem *mdio_base; -- cgit v1.2.3 From c9e6606c7fe92b50a02ce51dda82586ebdf99b48 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 2 Jan 2022 14:23:25 -0800 Subject: Linux 5.16-rc8 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 17b4319ad2ff..16d7f83ac368 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = -rc8 NAME = Gobble Gobble # *DOCUMENTATION* -- cgit v1.2.3 From e5a7431f5a2d6dcff7d516ee9d178a3254b17b87 Mon Sep 17 00:00:00 2001 From: Steven Lee Date: Tue, 14 Dec 2021 12:02:38 +0800 Subject: gpio: gpio-aspeed-sgpio: Fix wrong hwirq base in irq handler Each aspeed sgpio bank has 64 gpio pins(32 input pins and 32 output pins). The hwirq base for each sgpio bank should be multiples of 64 rather than multiples of 32. Signed-off-by: Steven Lee Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-aspeed-sgpio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-aspeed-sgpio.c b/drivers/gpio/gpio-aspeed-sgpio.c index 3d6ef37a7702..b3a9b8488f11 100644 --- a/drivers/gpio/gpio-aspeed-sgpio.c +++ b/drivers/gpio/gpio-aspeed-sgpio.c @@ -395,7 +395,7 @@ static void aspeed_sgpio_irq_handler(struct irq_desc *desc) reg = ioread32(bank_reg(data, bank, reg_irq_status)); for_each_set_bit(p, ®, 32) - generic_handle_domain_irq(gc->irq.domain, i * 32 + p * 2); + generic_handle_domain_irq(gc->irq.domain, (i * 32 + p) * 2); } chained_irq_exit(ic, desc); -- cgit v1.2.3 From 32e246b02f53b2fdaa81ea9f2ca6ff068c017fcb Mon Sep 17 00:00:00 2001 From: Gregory Fong Date: Mon, 3 Jan 2022 10:53:02 +0100 Subject: MAINTAINERS: update gpio-brcmstb maintainers Add Doug and Florian as maintainers for gpio-brcmstb, and remove myself. Signed-off-by: Gregory Fong Signed-off-by: Bartosz Golaszewski --- MAINTAINERS | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index fb18ce7168aa..dd36acc87ce6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3769,7 +3769,8 @@ S: Supported F: drivers/net/wireless/broadcom/brcm80211/ BROADCOM BRCMSTB GPIO DRIVER -M: Gregory Fong +M: Doug Berger +M: Florian Fainelli L: bcm-kernel-feedback-list@broadcom.com S: Supported F: Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt -- cgit v1.2.3 From e30a845b0376eb51c9c94f56bbd53b2e08ba822f Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 3 Jan 2022 10:19:11 -0700 Subject: ipv6: Continue processing multipath route even if gateway attribute is invalid ip6_route_multipath_del loop continues processing the multipath attribute even if delete of a nexthop path fails. For consistency, do the same if the gateway attribute is invalid. Fixes: 1ff15a710a86 ("ipv6: Check attribute length for RTA_GATEWAY when deleting multipath route") Signed-off-by: David Ahern Acked-by: Nicolas Dichtel Link: https://lore.kernel.org/r/20220103171911.94739-1-dsahern@kernel.org Signed-off-by: Jakub Kicinski --- net/ipv6/route.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d2ff8a7e1709..087df86c15d1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5459,8 +5459,10 @@ static int ip6_route_multipath_del(struct fib6_config *cfg, if (nla) { err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla, extack); - if (err) - return err; + if (err) { + last_err = err; + goto next_rtnh; + } r_cfg.fc_flags |= RTF_GATEWAY; } @@ -5469,6 +5471,7 @@ static int ip6_route_multipath_del(struct fib6_config *cfg, if (err) last_err = err; +next_rtnh: rtnh = rtnh_next(rtnh, &remaining); } -- cgit v1.2.3 From 95bdba23b5b4aa75fe3e6c84335e638641c707bb Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 3 Jan 2022 10:05:55 -0700 Subject: ipv6: Do cleanup if attribute validation fails in multipath route As Nicolas noted, if gateway validation fails walking the multipath attribute the code should jump to the cleanup to free previously allocated memory. Fixes: 1ff15a710a86 ("ipv6: Check attribute length for RTA_GATEWAY when deleting multipath route") Signed-off-by: David Ahern Acked-by: Nicolas Dichtel Link: https://lore.kernel.org/r/20220103170555.94638-1-dsahern@kernel.org Signed-off-by: Jakub Kicinski --- net/ipv6/route.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 087df86c15d1..1deb6297aab6 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5277,12 +5277,10 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { - int ret; - - ret = fib6_gw_from_attr(&r_cfg.fc_gateway, nla, + err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla, extack); - if (ret) - return ret; + if (err) + goto cleanup; r_cfg.fc_flags |= RTF_GATEWAY; } -- cgit v1.2.3 From 065e1ae02fbe5f56f4aa118414d45fc30647acd4 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 3 Jan 2022 11:34:52 -0800 Subject: Revert "net: phy: fixed_phy: Fix NULL vs IS_ERR() checking in __fixed_phy_register" This reverts commit b45396afa4177f2b1ddfeff7185da733fade1dc3 ("net: phy: fixed_phy: Fix NULL vs IS_ERR() checking in __fixed_phy_register") since it prevents any system that uses a fixed PHY without a GPIO descriptor from properly working: [ 5.971952] brcm-systemport 9300000.ethernet: failed to register fixed PHY [ 5.978854] brcm-systemport: probe of 9300000.ethernet failed with error -22 [ 5.986047] brcm-systemport 9400000.ethernet: failed to register fixed PHY [ 5.992947] brcm-systemport: probe of 9400000.ethernet failed with error -22 Fixes: b45396afa417 ("net: phy: fixed_phy: Fix NULL vs IS_ERR() checking in __fixed_phy_register") Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20220103193453.1214961-1-f.fainelli@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/fixed_phy.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index a0c256bd5441..c65fb5f5d2dc 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -239,8 +239,8 @@ static struct phy_device *__fixed_phy_register(unsigned int irq, /* Check if we have a GPIO associated with this fixed phy */ if (!gpiod) { gpiod = fixed_phy_get_gpiod(np); - if (!gpiod) - return ERR_PTR(-EINVAL); + if (IS_ERR(gpiod)) + return ERR_CAST(gpiod); } /* Get the next available PHY address, up to PHY_MAX_ADDR */ -- cgit v1.2.3 From fa55a7d745de2d10489295b0674a403e2a5d490d Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 3 Jan 2022 18:11:30 +0100 Subject: seg6: export get_srh() for ICMP handling An ICMP error message can contain in its message body part of an IPv6 packet which invoked the error. Such a packet might contain a segment router header. Export get_srh() so the ICMP code can make use of it. Since his changes the scope of the function from local to global, add the seg6_ prefix to keep the namespace clean. And move it into seg6.c so it is always available, not just when IPV6_SEG6_LWTUNNEL is enabled. Signed-off-by: Andrew Lunn Reviewed-by: David Ahern Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/net/seg6.h | 1 + net/ipv6/seg6.c | 29 +++++++++++++++++++++++++++++ net/ipv6/seg6_local.c | 33 ++------------------------------- 3 files changed, 32 insertions(+), 31 deletions(-) diff --git a/include/net/seg6.h b/include/net/seg6.h index 9d19c15e8545..a6f25983670a 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -58,6 +58,7 @@ extern int seg6_local_init(void); extern void seg6_local_exit(void); extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced); +extern struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags); extern int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto); extern int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh); diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index a8b5784afb1a..5bc9bf892199 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -75,6 +75,35 @@ bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced) return true; } +struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags) +{ + struct ipv6_sr_hdr *srh; + int len, srhoff = 0; + + if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, &flags) < 0) + return NULL; + + if (!pskb_may_pull(skb, srhoff + sizeof(*srh))) + return NULL; + + srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); + + len = (srh->hdrlen + 1) << 3; + + if (!pskb_may_pull(skb, srhoff + len)) + return NULL; + + /* note that pskb_may_pull may change pointers in header; + * for this reason it is necessary to reload them when needed. + */ + srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); + + if (!seg6_validate_srh(srh, len, true)) + return NULL; + + return srh; +} + static struct genl_family seg6_genl_family; static const struct nla_policy seg6_genl_policy[SEG6_ATTR_MAX + 1] = { diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 2dc40b3f373e..ef88489c71f5 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -150,40 +150,11 @@ static struct seg6_local_lwt *seg6_local_lwtunnel(struct lwtunnel_state *lwt) return (struct seg6_local_lwt *)lwt->data; } -static struct ipv6_sr_hdr *get_srh(struct sk_buff *skb, int flags) -{ - struct ipv6_sr_hdr *srh; - int len, srhoff = 0; - - if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, &flags) < 0) - return NULL; - - if (!pskb_may_pull(skb, srhoff + sizeof(*srh))) - return NULL; - - srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); - - len = (srh->hdrlen + 1) << 3; - - if (!pskb_may_pull(skb, srhoff + len)) - return NULL; - - /* note that pskb_may_pull may change pointers in header; - * for this reason it is necessary to reload them when needed. - */ - srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); - - if (!seg6_validate_srh(srh, len, true)) - return NULL; - - return srh; -} - static struct ipv6_sr_hdr *get_and_validate_srh(struct sk_buff *skb) { struct ipv6_sr_hdr *srh; - srh = get_srh(skb, IP6_FH_F_SKIP_RH); + srh = seg6_get_srh(skb, IP6_FH_F_SKIP_RH); if (!srh) return NULL; @@ -200,7 +171,7 @@ static bool decap_and_validate(struct sk_buff *skb, int proto) struct ipv6_sr_hdr *srh; unsigned int off = 0; - srh = get_srh(skb, 0); + srh = seg6_get_srh(skb, 0); if (srh && srh->segments_left > 0) return false; -- cgit v1.2.3 From e41294408c56c68ea0f269d757527bf33b39118a Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 3 Jan 2022 18:11:31 +0100 Subject: icmp: ICMPV6: Examine invoking packet for Segment Route Headers. RFC8754 says: ICMP error packets generated within the SR domain are sent to source nodes within the SR domain. The invoking packet in the ICMP error message may contain an SRH. Since the destination address of a packet with an SRH changes as each segment is processed, it may not be the destination used by the socket or application that generated the invoking packet. For the source of an invoking packet to process the ICMP error message, the ultimate destination address of the IPv6 header may be required. The following logic is used to determine the destination address for use by protocol-error handlers. * Walk all extension headers of the invoking IPv6 packet to the routing extension header preceding the upper-layer header. - If routing header is type 4 Segment Routing Header (SRH) o The SID at Segment List[0] may be used as the destination address of the invoking packet. Mangle the skb so the network header points to the invoking packet inside the ICMP packet. The seg6 helpers can then be used on the skb to find any segment routing headers. If found, mark this fact in the IPv6 control block of the skb, and store the offset into the packet of the SRH. Then restore the skb back to its old state. Signed-off-by: Andrew Lunn Reviewed-by: David Ahern Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 ++ include/net/seg6.h | 1 + net/ipv6/icmp.c | 6 +++++- net/ipv6/seg6.c | 30 ++++++++++++++++++++++++++++++ 4 files changed, 38 insertions(+), 1 deletion(-) diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 20c1f968da7c..a59d25f19385 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -133,6 +133,7 @@ struct inet6_skb_parm { __u16 dsthao; #endif __u16 frag_max_size; + __u16 srhoff; #define IP6SKB_XFRM_TRANSFORMED 1 #define IP6SKB_FORWARDED 2 @@ -142,6 +143,7 @@ struct inet6_skb_parm { #define IP6SKB_HOPBYHOP 32 #define IP6SKB_L3SLAVE 64 #define IP6SKB_JUMBOGRAM 128 +#define IP6SKB_SEG6 256 }; #if defined(CONFIG_NET_L3_MASTER_DEV) diff --git a/include/net/seg6.h b/include/net/seg6.h index a6f25983670a..02b0cd305787 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -59,6 +59,7 @@ extern void seg6_local_exit(void); extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced); extern struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags); +extern void seg6_icmp_srh(struct sk_buff *skb, struct inet6_skb_parm *opt); extern int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto); extern int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index a7c31ab67c5d..96c5cc0f30ce 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -57,6 +57,7 @@ #include #include #include +#include #include #include #include @@ -820,6 +821,7 @@ out_bh_enable: void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) { + struct inet6_skb_parm *opt = IP6CB(skb); const struct inet6_protocol *ipprot; int inner_offset; __be16 frag_off; @@ -829,6 +831,8 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto out; + seg6_icmp_srh(skb, opt); + nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr; if (ipv6_ext_hdr(nexthdr)) { /* now skip over extension headers */ @@ -853,7 +857,7 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) ipprot = rcu_dereference(inet6_protos[nexthdr]); if (ipprot && ipprot->err_handler) - ipprot->err_handler(skb, NULL, type, code, inner_offset, info); + ipprot->err_handler(skb, opt, type, code, inner_offset, info); raw6_icmp_error(skb, nexthdr, type, code, inner_offset, info); return; diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 5bc9bf892199..73aaabf0e966 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -104,6 +104,36 @@ struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags) return srh; } +/* Determine if an ICMP invoking packet contains a segment routing + * header. If it does, extract the offset to the true destination + * address, which is in the first segment address. + */ +void seg6_icmp_srh(struct sk_buff *skb, struct inet6_skb_parm *opt) +{ + __u16 network_header = skb->network_header; + struct ipv6_sr_hdr *srh; + + /* Update network header to point to the invoking packet + * inside the ICMP packet, so we can use the seg6_get_srh() + * helper. + */ + skb_reset_network_header(skb); + + srh = seg6_get_srh(skb, 0); + if (!srh) + goto out; + + if (srh->type != IPV6_SRCRT_TYPE_4) + goto out; + + opt->flags |= IP6SKB_SEG6; + opt->srhoff = (unsigned char *)srh - skb->data; + +out: + /* Restore the network header back to the ICMP packet */ + skb->network_header = network_header; +} + static struct genl_family seg6_genl_family; static const struct nla_policy seg6_genl_policy[SEG6_ATTR_MAX + 1] = { -- cgit v1.2.3 From 222a011efc839ca1f51bf89fe7a2b3705fa55ccd Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 3 Jan 2022 18:11:32 +0100 Subject: udp6: Use Segment Routing Header for dest address if present When finding the socket to report an error on, if the invoking packet is using Segment Routing, the IPv6 destination address is that of an intermediate router, not the end destination. Extract the ultimate destination address from the segment address. This change allows traceroute to function in the presence of Segment Routing. Signed-off-by: Andrew Lunn Reviewed-by: David Ahern Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/net/seg6.h | 19 +++++++++++++++++++ net/ipv6/udp.c | 3 ++- 2 files changed, 21 insertions(+), 1 deletion(-) diff --git a/include/net/seg6.h b/include/net/seg6.h index 02b0cd305787..af668f17b398 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -65,4 +65,23 @@ extern int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, extern int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh); extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, u32 tbl_id); + +/* If the packet which invoked an ICMP error contains an SRH return + * the true destination address from within the SRH, otherwise use the + * destination address in the IP header. + */ +static inline const struct in6_addr *seg6_get_daddr(struct sk_buff *skb, + struct inet6_skb_parm *opt) +{ + struct ipv6_sr_hdr *srh; + + if (opt->flags & IP6SKB_SEG6) { + srh = (struct ipv6_sr_hdr *)(skb->data + opt->srhoff); + return &srh->segments[0]; + } + + return NULL; +} + + #endif diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 8cde9efd7919..a0871c212741 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include #include @@ -561,7 +562,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct ipv6_pinfo *np; const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct in6_addr *saddr = &hdr->saddr; - const struct in6_addr *daddr = &hdr->daddr; + const struct in6_addr *daddr = seg6_get_daddr(skb, opt) ? : &hdr->daddr; struct udphdr *uh = (struct udphdr *)(skb->data+offset); bool tunnel = false; struct sock *sk; -- cgit v1.2.3 From 3087a6f36ee028ec095c04a8531d7d33899b7fed Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 4 Jan 2022 10:21:26 +0100 Subject: netrom: fix copying in user data in nr_setsockopt This code used to copy in an unsigned long worth of data before the sockptr_t conversion, so restore that. Fixes: a7b75c5a8c41 ("net: pass a sockptr_t into ->setsockopt") Reported-by: Dan Carpenter Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- net/netrom/af_netrom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 775064cdd0ee..f1ba7dd3d253 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -306,7 +306,7 @@ static int nr_setsockopt(struct socket *sock, int level, int optname, if (optlen < sizeof(unsigned int)) return -EINVAL; - if (copy_from_sockptr(&opt, optval, sizeof(unsigned int))) + if (copy_from_sockptr(&opt, optval, sizeof(unsigned long))) return -EFAULT; switch (optname) { -- cgit v1.2.3 From 7d18a07897d07495ee140dd319b0e9265c0f68ba Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 4 Jan 2022 01:45:08 -0800 Subject: sch_qfq: prevent shift-out-of-bounds in qfq_init_qdisc tx_queue_len can be set to ~0U, we need to be more careful about overflows. __fls(0) is undefined, as this report shows: UBSAN: shift-out-of-bounds in net/sched/sch_qfq.c:1430:24 shift exponent 51770272 is too large for 32-bit type 'int' CPU: 0 PID: 25574 Comm: syz-executor.0 Not tainted 5.16.0-rc7-syzkaller #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+0x201/0x2d8 lib/dump_stack.c:106 ubsan_epilogue lib/ubsan.c:151 [inline] __ubsan_handle_shift_out_of_bounds+0x494/0x530 lib/ubsan.c:330 qfq_init_qdisc+0x43f/0x450 net/sched/sch_qfq.c:1430 qdisc_create+0x895/0x1430 net/sched/sch_api.c:1253 tc_modify_qdisc+0x9d9/0x1e20 net/sched/sch_api.c:1660 rtnetlink_rcv_msg+0x934/0xe60 net/core/rtnetlink.c:5571 netlink_rcv_skb+0x200/0x470 net/netlink/af_netlink.c:2496 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x814/0x9f0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0xaea/0xe60 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg net/socket.c:724 [inline] ____sys_sendmsg+0x5b9/0x910 net/socket.c:2409 ___sys_sendmsg net/socket.c:2463 [inline] __sys_sendmsg+0x280/0x370 net/socket.c:2492 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Fixes: 462dbc9101ac ("pkt_sched: QFQ Plus: fair-queueing service at DRR cost") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- net/sched/sch_qfq.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 0b7f9ba28deb..d4ce58c90f9f 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1421,10 +1421,8 @@ static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt, if (err < 0) return err; - if (qdisc_dev(sch)->tx_queue_len + 1 > QFQ_MAX_AGG_CLASSES) - max_classes = QFQ_MAX_AGG_CLASSES; - else - max_classes = qdisc_dev(sch)->tx_queue_len + 1; + max_classes = min_t(u64, (u64)qdisc_dev(sch)->tx_queue_len + 1, + QFQ_MAX_AGG_CLASSES); /* max_cl_shift = floor(log_2(max_classes)) */ max_cl_shift = __fls(max_classes); q->max_agg_classes = 1< Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/20211223162848.3243702-1-trix@redhat.com Signed-off-by: Johannes Berg --- net/mac80211/mlme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 37f7d975f3da..3147ca89f608 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -5265,7 +5265,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, */ if (new_sta) { u32 rates = 0, basic_rates = 0; - bool have_higher_than_11mbit; + bool have_higher_than_11mbit = false; int min_rate = INT_MAX, min_rate_index = -1; const struct cfg80211_bss_ies *ies; int shift = ieee80211_vif_get_shift(&sdata->vif); -- cgit v1.2.3 From 8b5cb7e41d9d77ffca036b0239177de123394a55 Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Thu, 30 Dec 2021 22:55:47 +0300 Subject: mac80211: mesh: embedd mesh_paths and mpp_paths into ieee80211_if_mesh Syzbot hit NULL deref in rhashtable_free_and_destroy(). The problem was in mesh_paths and mpp_paths being NULL. mesh_pathtbl_init() could fail in case of memory allocation failure, but nobody cared, since ieee80211_mesh_init_sdata() returns void. It led to leaving 2 pointers as NULL. Syzbot has found null deref on exit path, but it could happen anywhere else, because code assumes these pointers are valid. Since all ieee80211_*_setup_sdata functions are void and do not fail, let's embedd mesh_paths and mpp_paths into parent struct to avoid adding error handling on higher levels and follow the pattern of others setup_sdata functions Fixes: 60854fd94573 ("mac80211: mesh: convert path table to rhashtable") Reported-and-tested-by: syzbot+860268315ba86ea6b96b@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin Link: https://lore.kernel.org/r/20211230195547.23977-1-paskripkin@gmail.com Signed-off-by: Johannes Berg --- net/mac80211/ieee80211_i.h | 24 +++++++++++- net/mac80211/mesh.h | 22 +---------- net/mac80211/mesh_pathtbl.c | 89 ++++++++++++++++----------------------------- 3 files changed, 54 insertions(+), 81 deletions(-) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 5666bbb8860b..482c98ede19b 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -647,6 +647,26 @@ struct mesh_csa_settings { struct cfg80211_csa_settings settings; }; +/** + * struct mesh_table + * + * @known_gates: list of known mesh gates and their mpaths by the station. The + * gate's mpath may or may not be resolved and active. + * @gates_lock: protects updates to known_gates + * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr + * @walk_head: linked list containing all mesh_path objects + * @walk_lock: lock protecting walk_head + * @entries: number of entries in the table + */ +struct mesh_table { + struct hlist_head known_gates; + spinlock_t gates_lock; + struct rhashtable rhead; + struct hlist_head walk_head; + spinlock_t walk_lock; + atomic_t entries; /* Up to MAX_MESH_NEIGHBOURS */ +}; + struct ieee80211_if_mesh { struct timer_list housekeeping_timer; struct timer_list mesh_path_timer; @@ -721,8 +741,8 @@ struct ieee80211_if_mesh { /* offset from skb->data while building IE */ int meshconf_offset; - struct mesh_table *mesh_paths; - struct mesh_table *mpp_paths; /* Store paths for MPP&MAP */ + struct mesh_table mesh_paths; + struct mesh_table mpp_paths; /* Store paths for MPP&MAP */ int mesh_paths_generation; int mpp_paths_generation; }; diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 77080b4f87b8..b2b717a78114 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -127,26 +127,6 @@ struct mesh_path { u32 path_change_count; }; -/** - * struct mesh_table - * - * @known_gates: list of known mesh gates and their mpaths by the station. The - * gate's mpath may or may not be resolved and active. - * @gates_lock: protects updates to known_gates - * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr - * @walk_head: linked list containing all mesh_path objects - * @walk_lock: lock protecting walk_head - * @entries: number of entries in the table - */ -struct mesh_table { - struct hlist_head known_gates; - spinlock_t gates_lock; - struct rhashtable rhead; - struct hlist_head walk_head; - spinlock_t walk_lock; - atomic_t entries; /* Up to MAX_MESH_NEIGHBOURS */ -}; - /* Recent multicast cache */ /* RMC_BUCKETS must be a power of 2, maximum 256 */ #define RMC_BUCKETS 256 @@ -308,7 +288,7 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, void mesh_path_assign_nexthop(struct mesh_path *mpath, struct sta_info *sta); void mesh_path_flush_pending(struct mesh_path *mpath); void mesh_path_tx_pending(struct mesh_path *mpath); -int mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata); +void mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata); void mesh_pathtbl_unregister(struct ieee80211_sub_if_data *sdata); int mesh_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr); void mesh_path_timer(struct timer_list *t); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 7cab1cf09bf1..acc1c299f1ae 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -47,32 +47,24 @@ static void mesh_path_rht_free(void *ptr, void *tblptr) mesh_path_free_rcu(tbl, mpath); } -static struct mesh_table *mesh_table_alloc(void) +static void mesh_table_init(struct mesh_table *tbl) { - struct mesh_table *newtbl; + INIT_HLIST_HEAD(&tbl->known_gates); + INIT_HLIST_HEAD(&tbl->walk_head); + atomic_set(&tbl->entries, 0); + spin_lock_init(&tbl->gates_lock); + spin_lock_init(&tbl->walk_lock); - newtbl = kmalloc(sizeof(struct mesh_table), GFP_ATOMIC); - if (!newtbl) - return NULL; - - INIT_HLIST_HEAD(&newtbl->known_gates); - INIT_HLIST_HEAD(&newtbl->walk_head); - atomic_set(&newtbl->entries, 0); - spin_lock_init(&newtbl->gates_lock); - spin_lock_init(&newtbl->walk_lock); - if (rhashtable_init(&newtbl->rhead, &mesh_rht_params)) { - kfree(newtbl); - return NULL; - } - - return newtbl; + /* rhashtable_init() may fail only in case of wrong + * mesh_rht_params + */ + WARN_ON(rhashtable_init(&tbl->rhead, &mesh_rht_params)); } static void mesh_table_free(struct mesh_table *tbl) { rhashtable_free_and_destroy(&tbl->rhead, mesh_path_rht_free, tbl); - kfree(tbl); } /** @@ -238,13 +230,13 @@ static struct mesh_path *mpath_lookup(struct mesh_table *tbl, const u8 *dst, struct mesh_path * mesh_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst) { - return mpath_lookup(sdata->u.mesh.mesh_paths, dst, sdata); + return mpath_lookup(&sdata->u.mesh.mesh_paths, dst, sdata); } struct mesh_path * mpp_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst) { - return mpath_lookup(sdata->u.mesh.mpp_paths, dst, sdata); + return mpath_lookup(&sdata->u.mesh.mpp_paths, dst, sdata); } static struct mesh_path * @@ -281,7 +273,7 @@ __mesh_path_lookup_by_idx(struct mesh_table *tbl, int idx) struct mesh_path * mesh_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx) { - return __mesh_path_lookup_by_idx(sdata->u.mesh.mesh_paths, idx); + return __mesh_path_lookup_by_idx(&sdata->u.mesh.mesh_paths, idx); } /** @@ -296,7 +288,7 @@ mesh_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx) struct mesh_path * mpp_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx) { - return __mesh_path_lookup_by_idx(sdata->u.mesh.mpp_paths, idx); + return __mesh_path_lookup_by_idx(&sdata->u.mesh.mpp_paths, idx); } /** @@ -309,7 +301,7 @@ int mesh_path_add_gate(struct mesh_path *mpath) int err; rcu_read_lock(); - tbl = mpath->sdata->u.mesh.mesh_paths; + tbl = &mpath->sdata->u.mesh.mesh_paths; spin_lock_bh(&mpath->state_lock); if (mpath->is_gate) { @@ -418,7 +410,7 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata, if (!new_mpath) return ERR_PTR(-ENOMEM); - tbl = sdata->u.mesh.mesh_paths; + tbl = &sdata->u.mesh.mesh_paths; spin_lock_bh(&tbl->walk_lock); mpath = rhashtable_lookup_get_insert_fast(&tbl->rhead, &new_mpath->rhash, @@ -460,7 +452,7 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata, return -ENOMEM; memcpy(new_mpath->mpp, mpp, ETH_ALEN); - tbl = sdata->u.mesh.mpp_paths; + tbl = &sdata->u.mesh.mpp_paths; spin_lock_bh(&tbl->walk_lock); ret = rhashtable_lookup_insert_fast(&tbl->rhead, @@ -489,7 +481,7 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata, void mesh_plink_broken(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; - struct mesh_table *tbl = sdata->u.mesh.mesh_paths; + struct mesh_table *tbl = &sdata->u.mesh.mesh_paths; static const u8 bcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; struct mesh_path *mpath; @@ -548,7 +540,7 @@ static void __mesh_path_del(struct mesh_table *tbl, struct mesh_path *mpath) void mesh_path_flush_by_nexthop(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; - struct mesh_table *tbl = sdata->u.mesh.mesh_paths; + struct mesh_table *tbl = &sdata->u.mesh.mesh_paths; struct mesh_path *mpath; struct hlist_node *n; @@ -563,7 +555,7 @@ void mesh_path_flush_by_nexthop(struct sta_info *sta) static void mpp_flush_by_proxy(struct ieee80211_sub_if_data *sdata, const u8 *proxy) { - struct mesh_table *tbl = sdata->u.mesh.mpp_paths; + struct mesh_table *tbl = &sdata->u.mesh.mpp_paths; struct mesh_path *mpath; struct hlist_node *n; @@ -597,8 +589,8 @@ static void table_flush_by_iface(struct mesh_table *tbl) */ void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) { - table_flush_by_iface(sdata->u.mesh.mesh_paths); - table_flush_by_iface(sdata->u.mesh.mpp_paths); + table_flush_by_iface(&sdata->u.mesh.mesh_paths); + table_flush_by_iface(&sdata->u.mesh.mpp_paths); } /** @@ -644,7 +636,7 @@ int mesh_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr) /* flush relevant mpp entries first */ mpp_flush_by_proxy(sdata, addr); - err = table_path_del(sdata->u.mesh.mesh_paths, sdata, addr); + err = table_path_del(&sdata->u.mesh.mesh_paths, sdata, addr); sdata->u.mesh.mesh_paths_generation++; return err; } @@ -682,7 +674,7 @@ int mesh_path_send_to_gates(struct mesh_path *mpath) struct mesh_path *gate; bool copy = false; - tbl = sdata->u.mesh.mesh_paths; + tbl = &sdata->u.mesh.mesh_paths; rcu_read_lock(); hlist_for_each_entry_rcu(gate, &tbl->known_gates, gate_list) { @@ -762,29 +754,10 @@ void mesh_path_fix_nexthop(struct mesh_path *mpath, struct sta_info *next_hop) mesh_path_tx_pending(mpath); } -int mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata) +void mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata) { - struct mesh_table *tbl_path, *tbl_mpp; - int ret; - - tbl_path = mesh_table_alloc(); - if (!tbl_path) - return -ENOMEM; - - tbl_mpp = mesh_table_alloc(); - if (!tbl_mpp) { - ret = -ENOMEM; - goto free_path; - } - - sdata->u.mesh.mesh_paths = tbl_path; - sdata->u.mesh.mpp_paths = tbl_mpp; - - return 0; - -free_path: - mesh_table_free(tbl_path); - return ret; + mesh_table_init(&sdata->u.mesh.mesh_paths); + mesh_table_init(&sdata->u.mesh.mpp_paths); } static @@ -806,12 +779,12 @@ void mesh_path_tbl_expire(struct ieee80211_sub_if_data *sdata, void mesh_path_expire(struct ieee80211_sub_if_data *sdata) { - mesh_path_tbl_expire(sdata, sdata->u.mesh.mesh_paths); - mesh_path_tbl_expire(sdata, sdata->u.mesh.mpp_paths); + mesh_path_tbl_expire(sdata, &sdata->u.mesh.mesh_paths); + mesh_path_tbl_expire(sdata, &sdata->u.mesh.mpp_paths); } void mesh_pathtbl_unregister(struct ieee80211_sub_if_data *sdata) { - mesh_table_free(sdata->u.mesh.mesh_paths); - mesh_table_free(sdata->u.mesh.mpp_paths); + mesh_table_free(&sdata->u.mesh.mesh_paths); + mesh_table_free(&sdata->u.mesh.mpp_paths); } -- cgit v1.2.3 From 754e4382354f7908923a1949d8dc8d05f82f09cb Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Tue, 4 Jan 2022 21:28:06 +0300 Subject: ieee802154: atusb: fix uninit value in atusb_set_extended_addr Alexander reported a use of uninitialized value in atusb_set_extended_addr(), that is caused by reading 0 bytes via usb_control_msg(). Fix it by validating if the number of bytes transferred is actually correct, since usb_control_msg() may read less bytes, than was requested by caller. Fail log: BUG: KASAN: uninit-cmp in ieee802154_is_valid_extended_unicast_addr include/linux/ieee802154.h:310 [inline] BUG: KASAN: uninit-cmp in atusb_set_extended_addr drivers/net/ieee802154/atusb.c:1000 [inline] BUG: KASAN: uninit-cmp in atusb_probe.cold+0x29f/0x14db drivers/net/ieee802154/atusb.c:1056 Uninit value used in comparison: 311daa649a2003bd stack handle: 000000009a2003bd ieee802154_is_valid_extended_unicast_addr include/linux/ieee802154.h:310 [inline] atusb_set_extended_addr drivers/net/ieee802154/atusb.c:1000 [inline] atusb_probe.cold+0x29f/0x14db drivers/net/ieee802154/atusb.c:1056 usb_probe_interface+0x314/0x7f0 drivers/usb/core/driver.c:396 Fixes: 7490b008d123 ("ieee802154: add support for atusb transceiver") Reported-by: Alexander Potapenko Acked-by: Alexander Aring Signed-off-by: Pavel Skripkin Link: https://lore.kernel.org/r/20220104182806.7188-1-paskripkin@gmail.com Signed-off-by: Stefan Schmidt --- drivers/net/ieee802154/atusb.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c index 23ee0b14cbfa..2f5e7b31032a 100644 --- a/drivers/net/ieee802154/atusb.c +++ b/drivers/net/ieee802154/atusb.c @@ -93,7 +93,9 @@ static int atusb_control_msg(struct atusb *atusb, unsigned int pipe, ret = usb_control_msg(usb_dev, pipe, request, requesttype, value, index, data, size, timeout); - if (ret < 0) { + if (ret < size) { + ret = ret < 0 ? ret : -ENODATA; + atusb->err = ret; dev_err(&usb_dev->dev, "%s: req 0x%02x val 0x%x idx 0x%x, error %d\n", @@ -861,9 +863,9 @@ static int atusb_get_and_show_build(struct atusb *atusb) if (!build) return -ENOMEM; - ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0), - ATUSB_BUILD, ATUSB_REQ_FROM_DEV, 0, 0, - build, ATUSB_BUILD_SIZE, 1000); + /* We cannot call atusb_control_msg() here, since this request may read various length data */ + ret = usb_control_msg(atusb->usb_dev, usb_rcvctrlpipe(usb_dev, 0), ATUSB_BUILD, + ATUSB_REQ_FROM_DEV, 0, 0, build, ATUSB_BUILD_SIZE, 1000); if (ret >= 0) { build[ret] = 0; dev_info(&usb_dev->dev, "Firmware: build %s\n", build); -- cgit v1.2.3 From 01cbf50877e602e2376af89e4a51c30bc574c618 Mon Sep 17 00:00:00 2001 From: Mateusz Palczewski Date: Wed, 3 Mar 2021 11:45:33 +0000 Subject: i40e: Fix to not show opcode msg on unsuccessful VF MAC change Hide i40e opcode information sent during response to VF in case when untrusted VF tried to change MAC on the VF interface. This is implemented by adding an additional parameter 'hide' to the response sent to VF function that hides the display of error information, but forwards the error code to VF. Previously it was not possible to send response with some error code to VF without displaying opcode information. Fixes: 5c3c48ac6bf5 ("i40e: implement virtual device interface") Signed-off-by: Grzegorz Szczurek Signed-off-by: Mateusz Palczewski Reviewed-by: Paul M Stillwell Jr Reviewed-by: Aleksandr Loktionov Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 40 +++++++++++++++++----- 1 file changed, 32 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 2ea4deb8fc44..048f1678ab8a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1877,17 +1877,19 @@ sriov_configure_out: /***********************virtual channel routines******************/ /** - * i40e_vc_send_msg_to_vf + * i40e_vc_send_msg_to_vf_ex * @vf: pointer to the VF info * @v_opcode: virtual channel opcode * @v_retval: virtual channel return value * @msg: pointer to the msg buffer * @msglen: msg length + * @is_quiet: true for not printing unsuccessful return values, false otherwise * * send msg to VF **/ -static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, - u32 v_retval, u8 *msg, u16 msglen) +static int i40e_vc_send_msg_to_vf_ex(struct i40e_vf *vf, u32 v_opcode, + u32 v_retval, u8 *msg, u16 msglen, + bool is_quiet) { struct i40e_pf *pf; struct i40e_hw *hw; @@ -1903,7 +1905,7 @@ static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id; /* single place to detect unsuccessful return values */ - if (v_retval) { + if (v_retval && !is_quiet) { vf->num_invalid_msgs++; dev_info(&pf->pdev->dev, "VF %d failed opcode %d, retval: %d\n", vf->vf_id, v_opcode, v_retval); @@ -1933,6 +1935,23 @@ static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, return 0; } +/** + * i40e_vc_send_msg_to_vf + * @vf: pointer to the VF info + * @v_opcode: virtual channel opcode + * @v_retval: virtual channel return value + * @msg: pointer to the msg buffer + * @msglen: msg length + * + * send msg to VF + **/ +static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, + u32 v_retval, u8 *msg, u16 msglen) +{ + return i40e_vc_send_msg_to_vf_ex(vf, v_opcode, v_retval, + msg, msglen, false); +} + /** * i40e_vc_send_resp_to_vf * @vf: pointer to the VF info @@ -2695,6 +2714,7 @@ error_param: * i40e_check_vf_permission * @vf: pointer to the VF info * @al: MAC address list from virtchnl + * @is_quiet: set true for printing msg without opcode info, false otherwise * * Check that the given list of MAC addresses is allowed. Will return -EPERM * if any address in the list is not valid. Checks the following conditions: @@ -2709,13 +2729,15 @@ error_param: * addresses might not be accurate. **/ static inline int i40e_check_vf_permission(struct i40e_vf *vf, - struct virtchnl_ether_addr_list *al) + struct virtchnl_ether_addr_list *al, + bool *is_quiet) { struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = pf->vsi[vf->lan_vsi_idx]; int mac2add_cnt = 0; int i; + *is_quiet = false; for (i = 0; i < al->num_elements; i++) { struct i40e_mac_filter *f; u8 *addr = al->list[i].addr; @@ -2739,6 +2761,7 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, !ether_addr_equal(addr, vf->default_lan_addr.addr)) { dev_err(&pf->pdev->dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); + *is_quiet = true; return -EPERM; } @@ -2775,6 +2798,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) (struct virtchnl_ether_addr_list *)msg; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; + bool is_quiet = false; i40e_status ret = 0; int i; @@ -2791,7 +2815,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) */ spin_lock_bh(&vsi->mac_filter_hash_lock); - ret = i40e_check_vf_permission(vf, al); + ret = i40e_check_vf_permission(vf, al, &is_quiet); if (ret) { spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; @@ -2829,8 +2853,8 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) error_param: /* send the response to the VF */ - return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ADD_ETH_ADDR, - ret); + return i40e_vc_send_msg_to_vf_ex(vf, VIRTCHNL_OP_ADD_ETH_ADDR, + ret, NULL, 0, is_quiet); } /** -- cgit v1.2.3 From 3116f59c12bd24c513194cd3acb3ec1f7d468954 Mon Sep 17 00:00:00 2001 From: Di Zhu Date: Mon, 29 Nov 2021 19:52:01 +0600 Subject: i40e: fix use-after-free in i40e_sync_filters_subtask() Using ifconfig command to delete the ipv6 address will cause the i40e network card driver to delete its internal mac_filter and i40e_service_task kernel thread will concurrently access the mac_filter. These two processes are not protected by lock so causing the following use-after-free problems. print_address_description+0x70/0x360 ? vprintk_func+0x5e/0xf0 kasan_report+0x1b2/0x330 i40e_sync_vsi_filters+0x4f0/0x1850 [i40e] i40e_sync_filters_subtask+0xe3/0x130 [i40e] i40e_service_task+0x195/0x24c0 [i40e] process_one_work+0x3f5/0x7d0 worker_thread+0x61/0x6c0 ? process_one_work+0x7d0/0x7d0 kthread+0x1c3/0x1f0 ? kthread_park+0xc0/0xc0 ret_from_fork+0x35/0x40 Allocated by task 2279810: kasan_kmalloc+0xa0/0xd0 kmem_cache_alloc_trace+0xf3/0x1e0 i40e_add_filter+0x127/0x2b0 [i40e] i40e_add_mac_filter+0x156/0x190 [i40e] i40e_addr_sync+0x2d/0x40 [i40e] __hw_addr_sync_dev+0x154/0x210 i40e_set_rx_mode+0x6d/0xf0 [i40e] __dev_set_rx_mode+0xfb/0x1f0 __dev_mc_add+0x6c/0x90 igmp6_group_added+0x214/0x230 __ipv6_dev_mc_inc+0x338/0x4f0 addrconf_join_solict.part.7+0xa2/0xd0 addrconf_dad_work+0x500/0x980 process_one_work+0x3f5/0x7d0 worker_thread+0x61/0x6c0 kthread+0x1c3/0x1f0 ret_from_fork+0x35/0x40 Freed by task 2547073: __kasan_slab_free+0x130/0x180 kfree+0x90/0x1b0 __i40e_del_filter+0xa3/0xf0 [i40e] i40e_del_mac_filter+0xf3/0x130 [i40e] i40e_addr_unsync+0x85/0xa0 [i40e] __hw_addr_sync_dev+0x9d/0x210 i40e_set_rx_mode+0x6d/0xf0 [i40e] __dev_set_rx_mode+0xfb/0x1f0 __dev_mc_del+0x69/0x80 igmp6_group_dropped+0x279/0x510 __ipv6_dev_mc_dec+0x174/0x220 addrconf_leave_solict.part.8+0xa2/0xd0 __ipv6_ifa_notify+0x4cd/0x570 ipv6_ifa_notify+0x58/0x80 ipv6_del_addr+0x259/0x4a0 inet6_addr_del+0x188/0x260 addrconf_del_ifaddr+0xcc/0x130 inet6_ioctl+0x152/0x190 sock_do_ioctl+0xd8/0x2b0 sock_ioctl+0x2e5/0x4c0 do_vfs_ioctl+0x14e/0xa80 ksys_ioctl+0x7c/0xa0 __x64_sys_ioctl+0x42/0x50 do_syscall_64+0x98/0x2c0 entry_SYSCALL_64_after_hwframe+0x65/0xca Fixes: 41c445ff0f48 ("i40e: main driver core") Signed-off-by: Di Zhu Signed-off-by: Rui Zhang Tested-by: Gurucharan G Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_main.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index e118cf9265c7..e0c4d6113c02 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -99,6 +99,24 @@ MODULE_LICENSE("GPL v2"); static struct workqueue_struct *i40e_wq; +static void netdev_hw_addr_refcnt(struct i40e_mac_filter *f, + struct net_device *netdev, int delta) +{ + struct netdev_hw_addr *ha; + + if (!f || !netdev) + return; + + netdev_for_each_mc_addr(ha, netdev) { + if (ether_addr_equal(ha->addr, f->macaddr)) { + ha->refcount += delta; + if (ha->refcount <= 0) + ha->refcount = 1; + break; + } + } +} + /** * i40e_allocate_dma_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure @@ -2036,6 +2054,7 @@ static void i40e_undo_add_filter_entries(struct i40e_vsi *vsi, hlist_for_each_entry_safe(new, h, from, hlist) { /* We can simply free the wrapper structure */ hlist_del(&new->hlist); + netdev_hw_addr_refcnt(new->f, vsi->netdev, -1); kfree(new); } } @@ -2383,6 +2402,10 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) &tmp_add_list, &tmp_del_list, vlan_filters); + + hlist_for_each_entry(new, &tmp_add_list, hlist) + netdev_hw_addr_refcnt(new->f, vsi->netdev, 1); + if (retval) goto err_no_memory_locked; @@ -2515,6 +2538,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) if (new->f->state == I40E_FILTER_NEW) new->f->state = new->state; hlist_del(&new->hlist); + netdev_hw_addr_refcnt(new->f, vsi->netdev, -1); kfree(new); } spin_unlock_bh(&vsi->mac_filter_hash_lock); -- cgit v1.2.3 From 40feded8a247f95957a0de9abd100085fb320a2f Mon Sep 17 00:00:00 2001 From: Mateusz Palczewski Date: Thu, 9 Dec 2021 11:04:35 +0100 Subject: i40e: Fix for displaying message regarding NVM version When loading the i40e driver, it prints a message like: 'The driver for the device detected a newer version of the NVM image v1.x than expected v1.y. Please install the most recent version of the network driver.' This is misleading as the driver is working as expected. Fix that by removing the second part of message and changing it from dev_info to dev_dbg. Fixes: 4fb29bddb57f ("i40e: The driver now prints the API version in error message") Signed-off-by: Mateusz Palczewski Tested-by: Gurucharan G Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index e0c4d6113c02..17c3f6d69740 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -15475,8 +15475,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw)) - dev_info(&pdev->dev, - "The driver for the device detected a newer version of the NVM image v%u.%u than expected v%u.%u. Please install the most recent version of the network driver.\n", + dev_dbg(&pdev->dev, + "The driver for the device detected a newer version of the NVM image v%u.%u than v%u.%u.\n", hw->aq.api_maj_ver, hw->aq.api_min_ver, I40E_FW_API_VERSION_MAJOR, -- cgit v1.2.3 From e738451d78b2f8a9635d66c6a87f304b4d965f7a Mon Sep 17 00:00:00 2001 From: Jedrzej Jagielski Date: Fri, 17 Dec 2021 14:29:05 +0000 Subject: i40e: Fix incorrect netdev's real number of RX/TX queues There was a wrong queues representation in sysfs during driver's reinitialization in case of online cpus number is less than combined queues. It was caused by stopped NetworkManager, which is responsible for calling vsi_open function during driver's initialization. In specific situation (ex. 12 cpus online) there were 16 queues in /sys/class/net//queues. In case of modifying queues with value higher, than number of online cpus, then it caused write errors and other errors. Add updating of sysfs's queues representation during driver initialization. Fixes: 41c445ff0f48 ("i40e: main driver core") Signed-off-by: Lukasz Cieplicki Signed-off-by: Jedrzej Jagielski Tested-by: Gurucharan G Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/i40e/i40e_main.c | 32 ++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 17c3f6d69740..61afc220fc6c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -8740,6 +8740,27 @@ int i40e_open(struct net_device *netdev) return 0; } +/** + * i40e_netif_set_realnum_tx_rx_queues - Update number of tx/rx queues + * @vsi: vsi structure + * + * This updates netdev's number of tx/rx queues + * + * Returns status of setting tx/rx queues + **/ +static int i40e_netif_set_realnum_tx_rx_queues(struct i40e_vsi *vsi) +{ + int ret; + + ret = netif_set_real_num_rx_queues(vsi->netdev, + vsi->num_queue_pairs); + if (ret) + return ret; + + return netif_set_real_num_tx_queues(vsi->netdev, + vsi->num_queue_pairs); +} + /** * i40e_vsi_open - * @vsi: the VSI to open @@ -8776,13 +8797,7 @@ int i40e_vsi_open(struct i40e_vsi *vsi) goto err_setup_rx; /* Notify the stack of the actual queue counts. */ - err = netif_set_real_num_tx_queues(vsi->netdev, - vsi->num_queue_pairs); - if (err) - goto err_set_queues; - - err = netif_set_real_num_rx_queues(vsi->netdev, - vsi->num_queue_pairs); + err = i40e_netif_set_realnum_tx_rx_queues(vsi); if (err) goto err_set_queues; @@ -14173,6 +14188,9 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, case I40E_VSI_MAIN: case I40E_VSI_VMDQ2: ret = i40e_config_netdev(vsi); + if (ret) + goto err_netdev; + ret = i40e_netif_set_realnum_tx_rx_queues(vsi); if (ret) goto err_netdev; ret = register_netdev(vsi->netdev); -- cgit v1.2.3 From b712941c8085e638bb92456e866ed3de4404e3d5 Mon Sep 17 00:00:00 2001 From: Karen Sornek Date: Wed, 1 Sep 2021 09:21:46 +0200 Subject: iavf: Fix limit of total number of queues to active queues of VF In the absence of this validation, if the user requests to configure queues more than the enabled queues, it results in sending the requested number of queues to the kernel stack (due to the asynchronous nature of VF response), in which case the stack might pick a queue to transmit that is not enabled and result in Tx hang. Fix this bug by limiting the total number of queues allocated for VF to active queues of VF. Fixes: d5b33d024496 ("i40evf: add ndo_setup_tc callback to i40evf") Signed-off-by: Ashwin Vijayavel Signed-off-by: Karen Sornek Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 4e7c04047f91..e4439b095533 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2708,8 +2708,11 @@ static int iavf_validate_ch_config(struct iavf_adapter *adapter, total_max_rate += tx_rate; num_qps += mqprio_qopt->qopt.count[i]; } - if (num_qps > IAVF_MAX_REQ_QUEUES) + if (num_qps > adapter->num_active_queues) { + dev_err(&adapter->pdev->dev, + "Cannot support requested number of queues\n"); return -EINVAL; + } ret = iavf_validate_tx_bandwidth(adapter, total_max_rate); return ret; -- cgit v1.2.3 From 1d5a474240407c38ca8c7484a656ee39f585399c Mon Sep 17 00:00:00 2001 From: Martin Habets Date: Sun, 2 Jan 2022 08:41:22 +0000 Subject: sfc: The RX page_ring is optional The RX page_ring is an optional feature that improves performance. When allocation fails the driver can still function, but possibly with a lower bandwidth. Guard against dereferencing a NULL page_ring. Fixes: 2768935a4660 ("sfc: reuse pages to avoid DMA mapping/unmapping costs") Signed-off-by: Martin Habets Reported-by: Jiasheng Jiang Link: https://lore.kernel.org/r/164111288276.5798.10330502993729113868.stgit@palantir17.mph.net Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/sfc/falcon/rx.c | 5 +++++ drivers/net/ethernet/sfc/rx_common.c | 5 +++++ 2 files changed, 10 insertions(+) diff --git a/drivers/net/ethernet/sfc/falcon/rx.c b/drivers/net/ethernet/sfc/falcon/rx.c index 11a6aee852e9..0c6cc2191369 100644 --- a/drivers/net/ethernet/sfc/falcon/rx.c +++ b/drivers/net/ethernet/sfc/falcon/rx.c @@ -110,6 +110,8 @@ static struct page *ef4_reuse_page(struct ef4_rx_queue *rx_queue) struct ef4_rx_page_state *state; unsigned index; + if (unlikely(!rx_queue->page_ring)) + return NULL; index = rx_queue->page_remove & rx_queue->page_ptr_mask; page = rx_queue->page_ring[index]; if (page == NULL) @@ -293,6 +295,9 @@ static void ef4_recycle_rx_pages(struct ef4_channel *channel, { struct ef4_rx_queue *rx_queue = ef4_channel_get_rx_queue(channel); + if (unlikely(!rx_queue->page_ring)) + return; + do { ef4_recycle_rx_page(channel, rx_buf); rx_buf = ef4_rx_buf_next(rx_queue, rx_buf); diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 0983abc0cc5f..633ca77a26fd 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -45,6 +45,8 @@ static struct page *efx_reuse_page(struct efx_rx_queue *rx_queue) unsigned int index; struct page *page; + if (unlikely(!rx_queue->page_ring)) + return NULL; index = rx_queue->page_remove & rx_queue->page_ptr_mask; page = rx_queue->page_ring[index]; if (page == NULL) @@ -114,6 +116,9 @@ void efx_recycle_rx_pages(struct efx_channel *channel, { struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel); + if (unlikely(!rx_queue->page_ring)) + return; + do { efx_recycle_rx_page(channel, rx_buf); rx_buf = efx_rx_buf_next(rx_queue, rx_buf); -- cgit v1.2.3 From 00fcf8c7dd564c44448ff6a39728d2ca0c8efbd8 Mon Sep 17 00:00:00 2001 From: Aaron Ma Date: Wed, 5 Jan 2022 23:51:02 +0800 Subject: Revert "net: usb: r8152: Add MAC passthrough support for more Lenovo Docks" This reverts commit f77b83b5bbab53d2be339184838b19ed2c62c0a5. This change breaks multiple usb to ethernet dongles attached on Lenovo USB hub. Fixes: f77b83b5bbab ("net: usb: r8152: Add MAC passthrough support for more Lenovo Docks") Signed-off-by: Aaron Ma Link: https://lore.kernel.org/r/20220105155102.8557-1-aaron.ma@canonical.com Signed-off-by: Jakub Kicinski --- drivers/net/usb/r8152.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 3085e8118d7f..ef6010a3d33a 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -9638,9 +9638,12 @@ static int rtl8152_probe(struct usb_interface *intf, netdev->hw_features &= ~NETIF_F_RXCSUM; } - if (udev->parent && - le16_to_cpu(udev->parent->descriptor.idVendor) == VENDOR_ID_LENOVO) { - tp->lenovo_macpassthru = 1; + if (le16_to_cpu(udev->descriptor.idVendor) == VENDOR_ID_LENOVO) { + switch (le16_to_cpu(udev->descriptor.idProduct)) { + case DEVICE_ID_THINKPAD_THUNDERBOLT3_DOCK_GEN2: + case DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2: + tp->lenovo_macpassthru = 1; + } } if (le16_to_cpu(udev->descriptor.bcdDevice) == 0x3011 && udev->serial && -- cgit v1.2.3 From db54c12a3d7e3eedd37aa08efc9362e905f07716 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Wed, 5 Jan 2022 14:44:36 +0000 Subject: selftests: set amt.sh executable amt.sh test script will not work because it doesn't have execution permission. So, it adds execution permission. Reported-by: Hangbin Liu Fixes: c08e8baea78e ("selftests: add amt interface selftest script") Signed-off-by: Taehee Yoo Link: https://lore.kernel.org/r/20220105144436.13415-1-ap420073@gmail.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/amt.sh | 0 1 file changed, 0 insertions(+), 0 deletions(-) mode change 100644 => 100755 tools/testing/selftests/net/amt.sh diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh old mode 100644 new mode 100755 -- cgit v1.2.3