From c1c9cad50c5c35cd4de1b54af59a28bf07451593 Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Sun, 23 Mar 2025 05:49:06 -0700 Subject: [PATCH 1/6] drm/xe/svm: fix dereferencing error pointer in drm_gpusvm_range_alloc() xe_svm_range_alloc() returns ERR_PTR(-ENOMEM) on failure and there is a dereference of "range" after that: --> range->gpusvm = gpusvm; In xe_svm_range_alloc(), when memory allocation fails return NULL instead to handle this situation. Fixes: 99624bdff867 ("drm/gpusvm: Add support for GPU Shared Virtual Memory") Reported-by: Dan Carpenter Closes: https://lore.kernel.org/all/adaef4dd-5866-48ca-bc22-4a1ddef20381@stanley.mountain/ Signed-off-by: Harshit Mogalapalli Reviewed-by: Matthew Brost Signed-off-by: Matthew Brost Link: https://lore.kernel.org/r/20250323124907.3946370-1-harshit.m.mogalapalli@oracle.com (cherry picked from commit 7a0322122cfdd9a6f10fc7701023d75c98eb3d22) Signed-off-by: Lucas De Marchi --- drivers/gpu/drm/xe/xe_svm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c index f8c128524d9f..0b6547c06961 100644 --- a/drivers/gpu/drm/xe/xe_svm.c +++ b/drivers/gpu/drm/xe/xe_svm.c @@ -79,7 +79,7 @@ xe_svm_range_alloc(struct drm_gpusvm *gpusvm) range = kzalloc(sizeof(*range), GFP_KERNEL); if (!range) - return ERR_PTR(-ENOMEM); + return NULL; INIT_LIST_HEAD(&range->garbage_collector_link); xe_vm_get(gpusvm_to_vm(gpusvm)); From 5e639707ddb8f080fbde805a1bfa6668a1b45298 Mon Sep 17 00:00:00 2001 From: John Harrison Date: Thu, 17 Apr 2025 12:52:12 -0700 Subject: [PATCH 2/6] drm/xe/guc: Fix capture of steering registers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The list of registers to capture on a GPU hang includes some that require steering. Unfortunately, the flag to say this was being wiped to due a missing OR on the assignment of the next flag field. Fix that. Fixes: b170d696c1e2 ("drm/xe/guc: Add XE_LP steered register lists") Cc: Zhanjun Dong Cc: Alan Previn Cc: Matt Roper Cc: Lucas De Marchi Cc: "Thomas Hellström" Cc: Rodrigo Vivi Cc: intel-xe@lists.freedesktop.org Signed-off-by: John Harrison Reviewed-by: Matt Roper Reviewed-by: Zhanjun Dong Link: https://lore.kernel.org/r/20250417195215.3002210-2-John.C.Harrison@Intel.com (cherry picked from commit 532da44b54a10d50ebad14a8a02bd0b78ec23e8b) Signed-off-by: Lucas De Marchi --- drivers/gpu/drm/xe/xe_guc_capture.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_guc_capture.c b/drivers/gpu/drm/xe/xe_guc_capture.c index f6d523e4c5fe..9095618648bc 100644 --- a/drivers/gpu/drm/xe/xe_guc_capture.c +++ b/drivers/gpu/drm/xe/xe_guc_capture.c @@ -359,7 +359,7 @@ static void __fill_ext_reg(struct __guc_mmio_reg_descr *ext, ext->reg = XE_REG(extlist->reg.__reg.addr); ext->flags = FIELD_PREP(GUC_REGSET_STEERING_NEEDED, 1); - ext->flags = FIELD_PREP(GUC_REGSET_STEERING_GROUP, slice_id); + ext->flags |= FIELD_PREP(GUC_REGSET_STEERING_GROUP, slice_id); ext->flags |= FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, subslice_id); ext->regname = extlist->name; } From 5a295bad38b1057dd13811242ac981bb674ab190 Mon Sep 17 00:00:00 2001 From: Harish Chegondi Date: Thu, 17 Apr 2025 17:07:17 -0700 Subject: [PATCH 3/6] drm/xe/eustall: Resolve a possible circular locking dependency Use a separate lock in the polling function eu_stall_data_buf_poll() instead of eu_stall->stream_lock. This would prevent a possible circular locking dependency leading to a deadlock as described below. This would also require additional locking with the new lock in the read function. <4> [787.192986] ====================================================== <4> [787.192988] WARNING: possible circular locking dependency detected <4> [787.192991] 6.14.0-rc7-xe+ #1 Tainted: G U <4> [787.192993] ------------------------------------------------------ <4> [787.192994] xe_eu_stall/20093 is trying to acquire lock: <4> [787.192996] ffff88819847e2c0 ((work_completion) (&(&stream->buf_poll_work)->work)), at: __flush_work+0x1f8/0x5e0 <4> [787.193005] but task is already holding lock: <4> [787.193007] ffff88814ce83ba8 (>->eu_stall->stream_lock){3:3}, at: xe_eu_stall_stream_ioctl+0x41/0x6a0 [xe] <4> [787.193090] which lock already depends on the new lock. <4> [787.193093] the existing dependency chain (in reverse order) is: <4> [787.193095] -> #1 (>->eu_stall->stream_lock){+.+.}-{3:3}: <4> [787.193099] __mutex_lock+0xb4/0xe40 <4> [787.193104] mutex_lock_nested+0x1b/0x30 <4> [787.193106] eu_stall_data_buf_poll_work_fn+0x44/0x1d0 [xe] <4> [787.193155] process_one_work+0x21c/0x740 <4> [787.193159] worker_thread+0x1db/0x3c0 <4> [787.193161] kthread+0x10d/0x270 <4> [787.193164] ret_from_fork+0x44/0x70 <4> [787.193168] ret_from_fork_asm+0x1a/0x30 <4> [787.193172] -> #0 ((work_completion)(&(&stream->buf_poll_work)->work)){+.+.}-{0:0}: <4> [787.193176] __lock_acquire+0x1637/0x2810 <4> [787.193180] lock_acquire+0xc9/0x300 <4> [787.193183] __flush_work+0x219/0x5e0 <4> [787.193186] cancel_delayed_work_sync+0x87/0x90 <4> [787.193189] xe_eu_stall_disable_locked+0x9a/0x260 [xe] <4> [787.193237] xe_eu_stall_stream_ioctl+0x5b/0x6a0 [xe] <4> [787.193285] __x64_sys_ioctl+0xa4/0xe0 <4> [787.193289] x64_sys_call+0x131e/0x2650 <4> [787.193292] do_syscall_64+0x91/0x180 <4> [787.193295] entry_SYSCALL_64_after_hwframe+0x76/0x7e <4> [787.193299] other info that might help us debug this: <4> [787.193302] Possible unsafe locking scenario: <4> [787.193304] CPU0 CPU1 <4> [787.193305] ---- ---- <4> [787.193306] lock(>->eu_stall->stream_lock); <4> [787.193308] lock((work_completion) (&(&stream->buf_poll_work)->work)); <4> [787.193311] lock(>->eu_stall->stream_lock); <4> [787.193313] lock((work_completion) (&(&stream->buf_poll_work)->work)); <4> [787.193315] *** DEADLOCK *** Fixes: 760edec939685 ("drm/xe/eustall: Add support to read() and poll() EU stall data") Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/4598 Signed-off-by: Harish Chegondi Reviewed-by: Ashutosh Dixit Signed-off-by: Ashutosh Dixit Link: https://lore.kernel.org/r/c896932fca84f79db2df5942911997ed77b2b9b6.1744934656.git.harish.chegondi@intel.com (cherry picked from commit c2b1f1b8641372bb2e563c49eb25632623a860fc) Signed-off-by: Lucas De Marchi --- drivers/gpu/drm/xe/xe_eu_stall.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_eu_stall.c b/drivers/gpu/drm/xe/xe_eu_stall.c index f2bb9168967c..78f28f3c5e5c 100644 --- a/drivers/gpu/drm/xe/xe_eu_stall.c +++ b/drivers/gpu/drm/xe/xe_eu_stall.c @@ -52,6 +52,8 @@ struct xe_eu_stall_data_stream { struct xe_gt *gt; struct xe_bo *bo; + /* Lock to protect data buffer pointers */ + struct mutex xecore_buf_lock; struct per_xecore_buf *xecore_buf; struct { bool reported_to_user; @@ -378,7 +380,7 @@ static bool eu_stall_data_buf_poll(struct xe_eu_stall_data_stream *stream) u16 group, instance; unsigned int xecore; - mutex_lock(>->eu_stall->stream_lock); + mutex_lock(&stream->xecore_buf_lock); for_each_dss_steering(xecore, gt, group, instance) { xecore_buf = &stream->xecore_buf[xecore]; read_ptr = xecore_buf->read; @@ -396,7 +398,7 @@ static bool eu_stall_data_buf_poll(struct xe_eu_stall_data_stream *stream) set_bit(xecore, stream->data_drop.mask); xecore_buf->write = write_ptr; } - mutex_unlock(>->eu_stall->stream_lock); + mutex_unlock(&stream->xecore_buf_lock); return min_data_present; } @@ -511,11 +513,13 @@ static ssize_t xe_eu_stall_stream_read_locked(struct xe_eu_stall_data_stream *st unsigned int xecore; int ret = 0; + mutex_lock(&stream->xecore_buf_lock); if (bitmap_weight(stream->data_drop.mask, XE_MAX_DSS_FUSE_BITS)) { if (!stream->data_drop.reported_to_user) { stream->data_drop.reported_to_user = true; xe_gt_dbg(gt, "EU stall data dropped in XeCores: %*pb\n", XE_MAX_DSS_FUSE_BITS, stream->data_drop.mask); + mutex_unlock(&stream->xecore_buf_lock); return -EIO; } stream->data_drop.reported_to_user = false; @@ -527,6 +531,7 @@ static ssize_t xe_eu_stall_stream_read_locked(struct xe_eu_stall_data_stream *st if (ret || count == total_size) break; } + mutex_unlock(&stream->xecore_buf_lock); return total_size ?: (ret ?: -EAGAIN); } @@ -583,6 +588,7 @@ static void xe_eu_stall_stream_free(struct xe_eu_stall_data_stream *stream) { struct xe_gt *gt = stream->gt; + mutex_destroy(&stream->xecore_buf_lock); gt->eu_stall->stream = NULL; kfree(stream); } @@ -718,6 +724,7 @@ static int xe_eu_stall_stream_init(struct xe_eu_stall_data_stream *stream, } init_waitqueue_head(&stream->poll_wq); + mutex_init(&stream->xecore_buf_lock); INIT_DELAYED_WORK(&stream->buf_poll_work, eu_stall_data_buf_poll_work_fn); stream->per_xecore_buf_size = per_xecore_buf_size; stream->sampling_rate_mult = props->sampling_rate_mult; From 1d622a4fe2b9a30cd4af2e858d793d05f8a82774 Mon Sep 17 00:00:00 2001 From: Harish Chegondi Date: Sun, 20 Apr 2025 22:59:01 -0700 Subject: [PATCH 4/6] drm/xe/eustall: Do not support EU stall on SRIOV VF EU stall sampling is not supported on SRIOV VF. Do not initialize or open EU stall stream on SRIOV VF. Fixes: 9a0b11d4cf3b ("drm/xe/eustall: Add support to init, enable and disable EU stall sampling") Signed-off-by: Harish Chegondi Reviewed-by: Ashutosh Dixit Signed-off-by: Ashutosh Dixit Link: https://lore.kernel.org/r/10db5d1c7e17aadca7078ff74575b7ffc0d5d6b8.1745215022.git.harish.chegondi@intel.com (cherry picked from commit 6ed20625a4b8189a1bd6598aa58e03147ce378ee) Signed-off-by: Lucas De Marchi --- drivers/gpu/drm/xe/xe_eu_stall.c | 3 +++ drivers/gpu/drm/xe/xe_eu_stall.h | 3 ++- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_eu_stall.c b/drivers/gpu/drm/xe/xe_eu_stall.c index 78f28f3c5e5c..e2bb156c71fb 100644 --- a/drivers/gpu/drm/xe/xe_eu_stall.c +++ b/drivers/gpu/drm/xe/xe_eu_stall.c @@ -210,6 +210,9 @@ int xe_eu_stall_init(struct xe_gt *gt) struct xe_device *xe = gt_to_xe(gt); int ret; + if (!xe_eu_stall_supported_on_platform(xe)) + return 0; + gt->eu_stall = kzalloc(sizeof(*gt->eu_stall), GFP_KERNEL); if (!gt->eu_stall) { ret = -ENOMEM; diff --git a/drivers/gpu/drm/xe/xe_eu_stall.h b/drivers/gpu/drm/xe/xe_eu_stall.h index ed9d0f233566..d1c76e503799 100644 --- a/drivers/gpu/drm/xe/xe_eu_stall.h +++ b/drivers/gpu/drm/xe/xe_eu_stall.h @@ -7,6 +7,7 @@ #define __XE_EU_STALL_H__ #include "xe_gt_types.h" +#include "xe_sriov.h" size_t xe_eu_stall_get_per_xecore_buf_size(void); size_t xe_eu_stall_data_record_size(struct xe_device *xe); @@ -19,6 +20,6 @@ int xe_eu_stall_stream_open(struct drm_device *dev, static inline bool xe_eu_stall_supported_on_platform(struct xe_device *xe) { - return xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20; + return !IS_SRIOV_VF(xe) && (xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20); } #endif From 3393c90daf4e1704c6a5c3833439f461663a2e1d Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Mon, 21 Apr 2025 08:15:38 -0700 Subject: [PATCH 5/6] drm/xe/hwmon: Fix kernel version documentation for temperature The version in the sysfs attribute should correspond to the version in which this is enabled and visible for end users. It usually doesn't correspond to the version in which the patch was developed, but rather a release that will contain it. Update them to 6.15. Fixes: dac328dea701 ("drm/xe/hwmon: expose package and vram temperature") Reported-by: Ulisses Furquim Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/4840 Reviewed-by: Rodrigo Vivi Reviewed-by: Raag Jadav Link: https://lore.kernel.org/r/20250421-hwmon-doc-fix-v1-1-9f68db702249@intel.com Signed-off-by: Lucas De Marchi (cherry picked from commit 8500393a8e6c58e5e7c135133ad792fc6fd5b6f4) Signed-off-by: Lucas De Marchi --- Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon b/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon index 9bce281314df..cb207c79680d 100644 --- a/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon +++ b/Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon @@ -111,7 +111,7 @@ Description: RO. Package current voltage in millivolt. What: /sys/bus/pci/drivers/xe/.../hwmon/hwmon/temp2_input Date: March 2025 -KernelVersion: 6.14 +KernelVersion: 6.15 Contact: intel-xe@lists.freedesktop.org Description: RO. Package temperature in millidegree Celsius. @@ -119,7 +119,7 @@ Description: RO. Package temperature in millidegree Celsius. What: /sys/bus/pci/drivers/xe/.../hwmon/hwmon/temp3_input Date: March 2025 -KernelVersion: 6.14 +KernelVersion: 6.15 Contact: intel-xe@lists.freedesktop.org Description: RO. VRAM temperature in millidegree Celsius. From e8e3a804f3845a147fbdf73f910c12ddb3a2a86f Mon Sep 17 00:00:00 2001 From: Dafna Hirschfeld Date: Sun, 27 Apr 2025 19:47:52 -0700 Subject: [PATCH 6/6] drm/gpusvm: set has_dma_mapping inside mapping loop The 'has_dma_mapping' flag should be set once there is a mapping so it could be unmapped in case of error. v2: - Resend for CI Fixes: 99624bdff867 ("drm/gpusvm: Add support for GPU Shared Virtual Memory") Signed-off-by: Dafna Hirschfeld Reviewed-by: Matthew Brost Signed-off-by: Matthew Brost Link: https://lore.kernel.org/r/20250428024752.881292-1-matthew.brost@intel.com (cherry picked from commit f64cf7b681af72d3f715c0d0fd72091a54471c1a) Signed-off-by: Lucas De Marchi --- drivers/gpu/drm/drm_gpusvm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c index 38431e8360e7..de424e670995 100644 --- a/drivers/gpu/drm/drm_gpusvm.c +++ b/drivers/gpu/drm/drm_gpusvm.c @@ -1469,9 +1469,9 @@ map_pages: } i += 1 << order; num_dma_mapped = i; + range->flags.has_dma_mapping = true; } - range->flags.has_dma_mapping = true; if (zdd) { range->flags.has_devmem_pages = true; range->dpagemap = dpagemap;