diff options
| author | Dave Airlie <airlied@redhat.com> | 2026-10-11 04:47:12 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2026-10-11 04:47:37 +1000 |
| commit | a8013cbe8d403051aae151f9e35e5f3c8af89a02 (patch) | |
| tree | 8f8fb8b8a41b99f6fba07efdcd146c3289f5dd9c | |
| parent | 5a768f5f76d8833b02b00f99d246cba6c463760b (diff) | |
| parent | 611857adc9e7b0ee1239a0baf38498922ca5a12e (diff) | |
| download | linux-a8013cbe8d403051aae151f9e35e5f3c8af89a02.tar.gz linux-a8013cbe8d403051aae151f9e35e5f3c8af89a02.zip | |
Merge tag 'drm-xe-fixes-2026-10-08' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes
Fixes on:
- i2c removal (Fan)
- system Controller Maibox header handling (Mallesh)
- two bo pin/unpin accounting bugs (Thomas)
- not emitting a w/a twice (Tvrtko)
- xe_mmio_wait32() to honor delay/sleep maximums (Alan)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patch.msgid.link/asfEfgbIjs0GJ-RF@intel.com
| -rw-r--r-- | drivers/gpu/drm/xe/display/xe_fb_pin.c | 6 | ||||
| -rw-r--r-- | drivers/gpu/drm/xe/xe_bo.c | 139 | ||||
| -rw-r--r-- | drivers/gpu/drm/xe/xe_bo.h | 2 | ||||
| -rw-r--r-- | drivers/gpu/drm/xe/xe_i2c.c | 5 | ||||
| -rw-r--r-- | drivers/gpu/drm/xe/xe_lrc.c | 38 | ||||
| -rw-r--r-- | drivers/gpu/drm/xe/xe_mmio.c | 5 | ||||
| -rw-r--r-- | drivers/gpu/drm/xe/xe_sysctrl_mailbox.c | 16 |
7 files changed, 150 insertions, 61 deletions
diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c index 73469ea5f333..f1dbdc802df8 100644 --- a/drivers/gpu/drm/xe/display/xe_fb_pin.c +++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c @@ -356,7 +356,7 @@ static struct i915_vma *__xe_pin_fb_vma(struct drm_gem_object *obj, bool is_dpt, drm_exec_retry_on_contention(&exec); xe_validation_retry_on_oom(&ctx, &ret); if (!ret) - ttm_bo_pin(&bo->ttm); + xe_bo_pin_account(bo); } if (ret) goto err; @@ -373,7 +373,7 @@ static struct i915_vma *__xe_pin_fb_vma(struct drm_gem_object *obj, bool is_dpt, err_unpin: ttm_bo_reserve(&bo->ttm, false, false, NULL); - ttm_bo_unpin(&bo->ttm); + xe_bo_unpin_account(bo); ttm_bo_unreserve(&bo->ttm); err: kfree(vma); @@ -393,7 +393,7 @@ static void __xe_unpin_fb_vma(struct i915_vma *vma) xe_ggtt_node_remove(vma->node, false); ttm_bo_reserve(&vma->bo->ttm, false, false, NULL); - ttm_bo_unpin(&vma->bo->ttm); + xe_bo_unpin_account(vma->bo); ttm_bo_unreserve(&vma->bo->ttm); kfree(vma); } diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index b4921a627ff3..7b95ce0445a9 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -455,6 +455,100 @@ static void xe_ttm_tt_account_subtract(struct xe_device *xe, struct ttm_tt *tt) xe_shrinker_mod_pages(xe->mem.shrinker, -(long)tt->num_pages, 0); } +static bool xe_ttm_bo_is_imported(struct ttm_buffer_object *tbo) +{ + dma_resv_assert_held(tbo->base.resv); + + return tbo->ttm && + (tbo->ttm->page_flags & (TTM_TT_FLAG_EXTERNAL | TTM_TT_FLAG_EXTERNAL_MAPPABLE)) == + TTM_TT_FLAG_EXTERNAL; +} + +/* + * Account @bo's pages as pinned for the shrinker. Removes @bo's pages + * from the shrinker's shrinkable / purgeable counts on the transition + * from unpinned to pinned. Must be called with @bo's dma-resv held, + * after &ttm_buffer_object.pin_count has been incremented by + * ttm_bo_pin(). Safe to call unconditionally regardless of which pin + * path (kernel, external, framebuffer, backup object, ...) is pinning + * @bo, since it only acts on the true 0->1 pin_count transition. + * + * Imported bos (xe_ttm_bo_is_imported()) are excluded: for those, + * xe_ttm_tt_populate() never actually populates the tt or calls + * xe_ttm_tt_account_add(), but TTM core's ttm_tt_populate() still + * unconditionally marks the tt as populated on driver-hook success. + * Relying on ttm_tt_is_populated() for these would subtract pages that + * were never added, underflowing the shrinker's counts. + */ +static void xe_bo_account_pin(struct xe_bo *bo) +{ + struct xe_device *xe = xe_bo_device(bo); + + if (bo->ttm.pin_count == 1 && bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm) && + !xe_ttm_bo_is_imported(&bo->ttm)) + xe_ttm_tt_account_subtract(xe, bo->ttm.ttm); +} + +/* + * Counterpart to xe_bo_account_pin(). Must be called with @bo's dma-resv + * held, before &ttm_buffer_object.pin_count is decremented by + * ttm_bo_unpin(), so that the check against the true 1->0 transition sees + * the pin count that is about to be released. See xe_bo_account_pin() for + * why imported bos are excluded. + * + * On the true last unpin, also removes @bo from whichever pinned-bo list + * (external or kernel_bo_present) it may currently be linked on, since a + * bo's final unpin can happen through a pin path (e.g. framebuffer, + * backup object) that has no notion of, or ownership over, that list. + * This is safe and list-agnostic: list_del_init() only needs the node + * itself, not knowledge of which list it is threaded through, and is a + * no-op if @bo is not linked. + */ +static void xe_bo_account_unpin(struct xe_bo *bo) +{ + struct xe_device *xe = xe_bo_device(bo); + bool last_unpin = bo->ttm.pin_count == 1; + + if (last_unpin && !list_empty(&bo->pinned_link)) { + spin_lock(&xe->pinned.lock); + list_del_init(&bo->pinned_link); + spin_unlock(&xe->pinned.lock); + } + + if (last_unpin && bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm) && + !xe_ttm_bo_is_imported(&bo->ttm)) + xe_ttm_tt_account_add(xe, bo->ttm.ttm); +} + +/** + * xe_bo_pin_account() - Pin a bo and account its pages for the shrinker + * @bo: The buffer object to pin. + * + * Pins @bo via ttm_bo_pin() and updates the shrinker's shrinkable / + * purgeable page accounting to match. Must be called with @bo's dma-resv + * held. Safe to call regardless of which pin path (kernel, external, + * framebuffer, backup object, ...) is pinning @bo. + */ +void xe_bo_pin_account(struct xe_bo *bo) +{ + ttm_bo_pin(&bo->ttm); + xe_bo_account_pin(bo); +} + +/** + * xe_bo_unpin_account() - Unpin a bo and account its pages for the shrinker + * @bo: The buffer object to unpin. + * + * Counterpart to xe_bo_pin_account(). Updates the shrinker's shrinkable / + * purgeable page accounting to match, then unpins @bo via ttm_bo_unpin(). + * Must be called with @bo's dma-resv held. + */ +void xe_bo_unpin_account(struct xe_bo *bo) +{ + xe_bo_account_unpin(bo); + ttm_bo_unpin(&bo->ttm); +} + static void update_global_total_pages(struct ttm_device *ttm_dev, long num_pages) { @@ -1389,7 +1483,8 @@ int xe_bo_notifier_prepare_pinned(struct xe_bo *bo) } backup->parent_obj = xe_bo_get(bo); /* Released by bo_destroy */ - ttm_bo_pin(&backup->ttm); + /* Note: XE_BO_FLAG_SYSTEM resolves to XE_PL_TT so already populated. */ + xe_bo_pin_account(backup); bo->backup_obj = backup; } @@ -1409,7 +1504,7 @@ int xe_bo_notifier_unprepare_pinned(struct xe_bo *bo) { xe_bo_lock(bo, false); if (bo->backup_obj) { - ttm_bo_unpin(&bo->backup_obj->ttm); + xe_bo_unpin_account(bo->backup_obj); xe_bo_put(bo->backup_obj); bo->backup_obj = NULL; } @@ -1620,7 +1715,7 @@ out_backup: xe_bo_vunmap(backup); if (!bo->backup_obj) { if (xe_bo_is_pinned(backup)) - ttm_bo_unpin(&backup->ttm); + xe_bo_unpin_account(backup); xe_bo_put(backup); } out_unlock_bo: @@ -2012,15 +2107,6 @@ static vm_fault_t xe_err_to_fault_t(int err) return VM_FAULT_SIGBUS; } -static bool xe_ttm_bo_is_imported(struct ttm_buffer_object *tbo) -{ - dma_resv_assert_held(tbo->base.resv); - - return tbo->ttm && - (tbo->ttm->page_flags & (TTM_TT_FLAG_EXTERNAL | TTM_TT_FLAG_EXTERNAL_MAPPABLE)) == - TTM_TT_FLAG_EXTERNAL; -} - static vm_fault_t xe_bo_cpu_fault_fastpath(struct vm_fault *vmf, struct xe_device *xe, struct xe_bo *bo, bool needs_rpm) { @@ -3141,12 +3227,13 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res) int xe_bo_pin_external(struct xe_bo *bo, bool in_place, struct drm_exec *exec) { struct xe_device *xe = xe_bo_device(bo); + bool first_pin = !xe_bo_is_pinned(bo); int err; xe_assert(xe, !bo->vm); xe_assert(xe, xe_bo_is_user(bo)); - if (!xe_bo_is_pinned(bo)) { + if (first_pin) { if (!in_place) { err = xe_bo_validate(bo, NULL, false, exec); if (err) @@ -3158,9 +3245,7 @@ int xe_bo_pin_external(struct xe_bo *bo, bool in_place, struct drm_exec *exec) spin_unlock(&xe->pinned.lock); } - ttm_bo_pin(&bo->ttm); - if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm)) - xe_ttm_tt_account_subtract(xe, bo->ttm.ttm); + xe_bo_pin_account(bo); /* * FIXME: If we always use the reserve / unreserve functions for locking @@ -3216,9 +3301,7 @@ int xe_bo_pin(struct xe_bo *bo, struct drm_exec *exec) spin_unlock(&xe->pinned.lock); } - ttm_bo_pin(&bo->ttm); - if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm)) - xe_ttm_tt_account_subtract(xe, bo->ttm.ttm); + xe_bo_pin_account(bo); /* * FIXME: If we always use the reserve / unreserve functions for locking @@ -3247,14 +3330,7 @@ void xe_bo_unpin_external(struct xe_bo *bo) xe_assert(xe, xe_bo_is_pinned(bo)); xe_assert(xe, xe_bo_is_user(bo)); - spin_lock(&xe->pinned.lock); - if (bo->ttm.pin_count == 1 && !list_empty(&bo->pinned_link)) - list_del_init(&bo->pinned_link); - spin_unlock(&xe->pinned.lock); - - ttm_bo_unpin(&bo->ttm); - if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm)) - xe_ttm_tt_account_add(xe, bo->ttm.ttm); + xe_bo_unpin_account(bo); /* * FIXME: If we always use the reserve / unreserve functions for locking @@ -3272,21 +3348,16 @@ void xe_bo_unpin(struct xe_bo *bo) xe_assert(xe, xe_bo_is_pinned(bo)); if (mem_type_is_vram(place->mem_type) || bo->flags & XE_BO_FLAG_GGTT) { - spin_lock(&xe->pinned.lock); xe_assert(xe, !list_empty(&bo->pinned_link)); - list_del_init(&bo->pinned_link); - spin_unlock(&xe->pinned.lock); if (bo->backup_obj) { if (xe_bo_is_pinned(bo->backup_obj)) - ttm_bo_unpin(&bo->backup_obj->ttm); + xe_bo_unpin_account(bo->backup_obj); xe_bo_put(bo->backup_obj); bo->backup_obj = NULL; } } - ttm_bo_unpin(&bo->ttm); - if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm)) - xe_ttm_tt_account_add(xe, bo->ttm.ttm); + xe_bo_unpin_account(bo); } /** diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 152bfcffe399..53a701d3d242 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -229,6 +229,8 @@ int xe_bo_pin_external(struct xe_bo *bo, bool in_place, struct drm_exec *exec); int xe_bo_pin(struct xe_bo *bo, struct drm_exec *exec); void xe_bo_unpin_external(struct xe_bo *bo); void xe_bo_unpin(struct xe_bo *bo); +void xe_bo_pin_account(struct xe_bo *bo); +void xe_bo_unpin_account(struct xe_bo *bo); int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict, struct drm_exec *exec); diff --git a/drivers/gpu/drm/xe/xe_i2c.c b/drivers/gpu/drm/xe/xe_i2c.c index f4f381988289..b82caaff80d7 100644 --- a/drivers/gpu/drm/xe/xe_i2c.c +++ b/drivers/gpu/drm/xe/xe_i2c.c @@ -324,12 +324,15 @@ static void xe_i2c_remove(void *data) xe_i2c_irq_reset(xe); xe_amc_exit(i2c); + /* Stop the notifier from arming the client work before teardown. */ + bus_unregister_notifier(&i2c_bus_type, &i2c->bus_notifier); + cancel_work_sync(&i2c->work); + for (i = 0; i < XE_I2C_MAX_CLIENTS; i++) { i2c_unregister_device(i2c->client[i]); i2c->client[i] = NULL; } - bus_unregister_notifier(&i2c_bus_type, &i2c->bus_notifier); xe_i2c_unregister_adapter(i2c); xe->i2c = NULL; } diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index 35b4e8289b5f..e4388a960490 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -1099,8 +1099,7 @@ static void xe_lrc_finish(struct xe_lrc *lrc) #define CONTEXT_ACTIVE XE_LRC_CTX_TIMESTAMP_ACTIVE static ssize_t setup_utilization_wa(struct xe_lrc *lrc, struct xe_hw_engine *hwe, - u32 *batch, - size_t max_len) + u32 *batch, size_t max_len, bool indirect) { u32 *cmd = batch; @@ -1131,19 +1130,25 @@ static ssize_t setup_utilization_wa(struct xe_lrc *lrc, } static ssize_t setup_timestamp_wa(struct xe_lrc *lrc, struct xe_hw_engine *hwe, - u32 *batch, size_t max_len) + u32 *batch, size_t max_len, bool indirect) { const u32 ts_addr = __xe_lrc_ctx_timestamp_ggtt_addr(lrc); u32 *cmd = batch; - if (!XE_GT_WA(lrc->gt, 16010904313) || - !(hwe->class == XE_ENGINE_CLASS_RENDER || - hwe->class == XE_ENGINE_CLASS_COMPUTE || - hwe->class == XE_ENGINE_CLASS_COPY || + if (!XE_GT_WA(lrc->gt, 16010904313)) + return 0; + + if (!indirect && + !(hwe->class == XE_ENGINE_CLASS_COPY || hwe->class == XE_ENGINE_CLASS_VIDEO_DECODE || hwe->class == XE_ENGINE_CLASS_VIDEO_ENHANCE)) return 0; + if (indirect && + !(hwe->class == XE_ENGINE_CLASS_RENDER || + hwe->class == XE_ENGINE_CLASS_COMPUTE)) + return 0; + if (xe_gt_WARN_ON(lrc->gt, max_len < 12)) return -ENOSPC; @@ -1169,7 +1174,8 @@ static ssize_t setup_timestamp_wa(struct xe_lrc *lrc, struct xe_hw_engine *hwe, static ssize_t setup_configfs_post_ctx_restore_bb(struct xe_lrc *lrc, struct xe_hw_engine *hwe, - u32 *batch, size_t max_len) + u32 *batch, size_t max_len, + bool indirect) { struct xe_device *xe = gt_to_xe(lrc->gt); const u32 *user_batch; @@ -1198,7 +1204,8 @@ static ssize_t setup_configfs_post_ctx_restore_bb(struct xe_lrc *lrc, static ssize_t setup_configfs_mid_ctx_restore_bb(struct xe_lrc *lrc, struct xe_hw_engine *hwe, - u32 *batch, size_t max_len) + u32 *batch, size_t max_len, + bool indirect) { struct xe_device *xe = gt_to_xe(lrc->gt); const u32 *user_batch; @@ -1227,7 +1234,8 @@ static ssize_t setup_configfs_mid_ctx_restore_bb(struct xe_lrc *lrc, static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc, struct xe_hw_engine *hwe, - u32 *batch, size_t max_len) + u32 *batch, size_t max_len, + bool indirect) { u32 *cmd = batch; @@ -1247,7 +1255,8 @@ static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc, static ssize_t setup_invalidate_auxccs_wa(struct xe_lrc *lrc, struct xe_hw_engine *hwe, - u32 *batch, size_t max_len) + u32 *batch, size_t max_len, + bool indirect) { struct xe_gt *gt = lrc->gt; u32 *(*emit)(struct xe_gt *gt, u32 *cmd) = @@ -1264,7 +1273,7 @@ static ssize_t setup_invalidate_auxccs_wa(struct xe_lrc *lrc, struct bo_setup { ssize_t (*setup)(struct xe_lrc *lrc, struct xe_hw_engine *hwe, - u32 *batch, size_t max_size); + u32 *batch, size_t max_size, bool indirect); }; struct bo_setup_state { @@ -1273,6 +1282,7 @@ struct bo_setup_state { struct xe_hw_engine *hwe; size_t max_size; size_t reserve_dw; + bool indirect; unsigned int offset; const struct bo_setup *funcs; unsigned int num_funcs; @@ -1298,7 +1308,8 @@ static int setup_bo(struct bo_setup_state *state) for (size_t i = 0; i < state->num_funcs; i++) { ssize_t len = state->funcs[i].setup(state->lrc, state->hwe, - state->ptr, remain); + state->ptr, remain, + state->indirect); remain -= len; @@ -1404,6 +1415,7 @@ setup_indirect_ctx(struct xe_lrc *lrc, struct xe_hw_engine *hwe) struct bo_setup_state state = { .lrc = lrc, .hwe = hwe, + .indirect = true, .max_size = (63 * 64) /* max 63 cachelines */, .buffer = NULL, .offset = __xe_lrc_indirect_ctx_offset(lrc), diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c index 7fa18dfcb5a2..455a07d79cd9 100644 --- a/drivers/gpu/drm/xe/xe_mmio.c +++ b/drivers/gpu/drm/xe/xe_mmio.c @@ -320,6 +320,7 @@ u64 xe_mmio_read64_2x32(struct xe_mmio *mmio, struct xe_reg reg) return (u64)udw << 32 | ldw; } +#define __XE_MMIO_WAIT_MAX_BACKOFF_100MS (100 * USEC_PER_MSEC) static int __xe_mmio_wait32(struct xe_mmio *mmio, struct xe_reg reg, u32 mask, u32 val, u32 timeout_us, u32 *out_val, bool atomic, bool expect_match) { @@ -350,10 +351,10 @@ static int __xe_mmio_wait32(struct xe_mmio *mmio, struct xe_reg reg, u32 mask, u wait = ktime_us_delta(end, cur); if (atomic) - udelay(wait); + udelay(min_t(s64, wait, (MAX_UDELAY_MS * 1000))); else usleep_range(wait, wait << 1); - wait <<= 1; + wait = min_t(s64, wait << 1, __XE_MMIO_WAIT_MAX_BACKOFF_100MS); } if (ret != 0) { diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c b/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c index 72baf1aa4b3a..a0179e62abaa 100644 --- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c +++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox.c @@ -19,20 +19,20 @@ #include "xe_sysctrl_mailbox_types.h" struct xe_sysctrl_mailbox_msg_hdr { - __le32 data; -} __packed; + u32 data; +}; #define XE_SYSCTRL_HDR_GROUP_ID(hdr) \ - FIELD_GET(SYSCTRL_HDR_GROUP_ID_MASK, le32_to_cpu((hdr)->data)) + FIELD_GET(SYSCTRL_HDR_GROUP_ID_MASK, (hdr)->data) #define XE_SYSCTRL_HDR_COMMAND(hdr) \ - FIELD_GET(SYSCTRL_HDR_COMMAND_MASK, le32_to_cpu((hdr)->data)) + FIELD_GET(SYSCTRL_HDR_COMMAND_MASK, (hdr)->data) #define XE_SYSCTRL_HDR_IS_RESPONSE(hdr) \ - FIELD_GET(SYSCTRL_HDR_IS_RESPONSE, le32_to_cpu((hdr)->data)) + FIELD_GET(SYSCTRL_HDR_IS_RESPONSE, (hdr)->data) #define XE_SYSCTRL_HDR_RESULT(hdr) \ - FIELD_GET(SYSCTRL_HDR_RESULT_MASK, le32_to_cpu((hdr)->data)) + FIELD_GET(SYSCTRL_HDR_RESULT_MASK, (hdr)->data) static bool sysctrl_wait_bit_clear(struct xe_sysctrl *sc, u32 bit_mask, unsigned int timeout_ms) @@ -126,8 +126,8 @@ static int sysctrl_prepare_command(struct xe_device *xe, return -ENOMEM; hdr = (struct xe_sysctrl_mailbox_msg_hdr *)buffer; - hdr->data = cpu_to_le32(FIELD_PREP(SYSCTRL_HDR_GROUP_ID_MASK, group_id) | - FIELD_PREP(SYSCTRL_HDR_COMMAND_MASK, command)); + hdr->data = FIELD_PREP(SYSCTRL_HDR_GROUP_ID_MASK, group_id) | + FIELD_PREP(SYSCTRL_HDR_COMMAND_MASK, command); if (data_in && data_in_len) memcpy(buffer + sizeof(*hdr), data_in, data_in_len); |
