diff options
Diffstat (limited to 'drivers/gpu')
26 files changed, 139 insertions, 54 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 86cff30d5c4e..f57411ed2dc2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2931,6 +2931,7 @@ static const struct file_operations amdgpu_driver_kms_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = drm_show_fdinfo, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; int amdgpu_file_to_fpriv(struct file *filp, struct amdgpu_fpriv **fpriv) diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c index 67b8d17a722a..221e9a4edb40 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c @@ -8,6 +8,7 @@ #include <linux/interrupt.h> #include <linux/module.h> #include <linux/platform_device.h> +#include <linux/vmalloc.h> #include <drm/bridge/dw_hdmi.h> #include <drm/drm_edid.h> @@ -388,15 +389,36 @@ static int dw_hdmi_close(struct snd_pcm_substream *substream) static int dw_hdmi_hw_free(struct snd_pcm_substream *substream) { - return snd_pcm_lib_free_vmalloc_buffer(substream); + struct snd_pcm_runtime *runtime = substream->runtime; + + vfree(runtime->dma_area); + runtime->dma_area = NULL; + return 0; } static int dw_hdmi_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) { + struct snd_pcm_runtime *runtime = substream->runtime; + size_t size = params_buffer_bytes(params); + /* Allocate the PCM runtime buffer, which is exposed to userspace. */ - return snd_pcm_lib_alloc_vmalloc_buffer(substream, - params_buffer_bytes(params)); + if (runtime->dma_area) { + if (runtime->dma_bytes >= size) + return 0; /* already large enough */ + vfree(runtime->dma_area); + } + runtime->dma_area = vzalloc(size); + if (!runtime->dma_area) + return -ENOMEM; + runtime->dma_bytes = size; + return 1; +} + +static struct page *dw_hdmi_get_page(struct snd_pcm_substream *substream, + unsigned long offset) +{ + return vmalloc_to_page(substream->runtime->dma_area + offset); } static int dw_hdmi_prepare(struct snd_pcm_substream *substream) @@ -515,7 +537,7 @@ static const struct snd_pcm_ops snd_dw_hdmi_ops = { .prepare = dw_hdmi_prepare, .trigger = dw_hdmi_trigger, .pointer = dw_hdmi_pointer, - .page = snd_pcm_lib_get_vmalloc_page, + .page = dw_hdmi_get_page, }; static int snd_dw_hdmi_probe(struct platform_device *pdev) diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 01fde94fe2a9..07e493d14d0c 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -310,6 +310,8 @@ int drm_open_helper(struct file *filp, struct drm_minor *minor) if (dev->switch_power_state != DRM_SWITCH_POWER_ON && dev->switch_power_state != DRM_SWITCH_POWER_DYNAMIC_OFF) return -EINVAL; + if (WARN_ON_ONCE(!(filp->f_op->fop_flags & FOP_UNSIGNED_OFFSET))) + return -EINVAL; drm_dbg_core(dev, "comm=\"%s\", pid=%d, minor=%d\n", current->comm, task_pid_nr(current), minor->index); @@ -327,7 +329,6 @@ int drm_open_helper(struct file *filp, struct drm_minor *minor) } filp->private_data = priv; - filp->f_mode |= FMODE_UNSIGNED_OFFSET; priv->filp = filp; mutex_lock(&dev->filelist_mutex); diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index a0e94217b511..4fcfc0b9b386 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -1464,6 +1464,7 @@ drm_syncobj_eventfd_ioctl(struct drm_device *dev, void *data, struct drm_syncobj *syncobj; struct eventfd_ctx *ev_fd_ctx; struct syncobj_eventfd_entry *entry; + int ret; if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) return -EOPNOTSUPP; @@ -1479,13 +1480,15 @@ drm_syncobj_eventfd_ioctl(struct drm_device *dev, void *data, return -ENOENT; ev_fd_ctx = eventfd_ctx_fdget(args->fd); - if (IS_ERR(ev_fd_ctx)) - return PTR_ERR(ev_fd_ctx); + if (IS_ERR(ev_fd_ctx)) { + ret = PTR_ERR(ev_fd_ctx); + goto err_fdget; + } entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) { - eventfd_ctx_put(ev_fd_ctx); - return -ENOMEM; + ret = -ENOMEM; + goto err_kzalloc; } entry->syncobj = syncobj; entry->ev_fd_ctx = ev_fd_ctx; @@ -1496,6 +1499,12 @@ drm_syncobj_eventfd_ioctl(struct drm_device *dev, void *data, drm_syncobj_put(syncobj); return 0; + +err_kzalloc: + eventfd_ctx_put(ev_fd_ctx); +err_fdget: + drm_syncobj_put(syncobj); + return ret; } int diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c index e2c7373f20c6..6a6761935224 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dma.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c @@ -110,7 +110,7 @@ int exynos_drm_register_dma(struct drm_device *drm, struct device *dev, void *mapping = NULL; if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) - mapping = arm_iommu_create_mapping(&platform_bus_type, + mapping = arm_iommu_create_mapping(dev, EXYNOS_DEV_ADDR_START, EXYNOS_DEV_ADDR_SIZE); else if (IS_ENABLED(CONFIG_IOMMU_DMA)) mapping = iommu_get_domain_for_dev(priv->dma_dev); diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index 8b64f61ffaf9..d67c2b3ad901 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -498,6 +498,7 @@ static const struct file_operations psb_gem_fops = { .mmap = drm_gem_mmap, .poll = drm_poll, .read = drm_read, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static const struct drm_driver driver = { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index c5e1c718a6d2..fe69f2c8527d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -424,7 +424,8 @@ shmem_pwrite(struct drm_i915_gem_object *obj, struct address_space *mapping = obj->base.filp->f_mapping; const struct address_space_operations *aops = mapping->a_ops; char __user *user_data = u64_to_user_ptr(arg->data_ptr); - u64 remain, offset; + u64 remain; + loff_t pos; unsigned int pg; /* Caller already validated user args */ @@ -457,12 +458,12 @@ shmem_pwrite(struct drm_i915_gem_object *obj, */ remain = arg->size; - offset = arg->offset; - pg = offset_in_page(offset); + pos = arg->offset; + pg = offset_in_page(pos); do { unsigned int len, unwritten; - struct page *page; + struct folio *folio; void *data, *vaddr; int err; char __maybe_unused c; @@ -480,21 +481,19 @@ shmem_pwrite(struct drm_i915_gem_object *obj, if (err) return err; - err = aops->write_begin(obj->base.filp, mapping, offset, len, - &page, &data); + err = aops->write_begin(obj->base.filp, mapping, pos, len, + &folio, &data); if (err < 0) return err; - vaddr = kmap_local_page(page); + vaddr = kmap_local_folio(folio, offset_in_folio(folio, pos)); pagefault_disable(); - unwritten = __copy_from_user_inatomic(vaddr + pg, - user_data, - len); + unwritten = __copy_from_user_inatomic(vaddr, user_data, len); pagefault_enable(); kunmap_local(vaddr); - err = aops->write_end(obj->base.filp, mapping, offset, len, - len - unwritten, page, data); + err = aops->write_end(obj->base.filp, mapping, pos, len, + len - unwritten, folio, data); if (err < 0) return err; @@ -504,7 +503,7 @@ shmem_pwrite(struct drm_i915_gem_object *obj, remain -= len; user_data += len; - offset += len; + pos += len; pg = 0; } while (remain); @@ -660,7 +659,7 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915, struct drm_i915_gem_object *obj; struct file *file; const struct address_space_operations *aops; - resource_size_t offset; + loff_t pos; int err; GEM_WARN_ON(IS_DGFX(i915)); @@ -672,29 +671,27 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915, file = obj->base.filp; aops = file->f_mapping->a_ops; - offset = 0; + pos = 0; do { unsigned int len = min_t(typeof(size), size, PAGE_SIZE); - struct page *page; - void *pgdata, *vaddr; + struct folio *folio; + void *fsdata; - err = aops->write_begin(file, file->f_mapping, offset, len, - &page, &pgdata); + err = aops->write_begin(file, file->f_mapping, pos, len, + &folio, &fsdata); if (err < 0) goto fail; - vaddr = kmap(page); - memcpy(vaddr, data, len); - kunmap(page); + memcpy_to_folio(folio, offset_in_folio(folio, pos), data, len); - err = aops->write_end(file, file->f_mapping, offset, len, len, - page, pgdata); + err = aops->write_end(file, file->f_mapping, pos, len, len, + folio, fsdata); if (err < 0) goto fail; size -= len; data += len; - offset += len; + pos += len; } while (size); return obj; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c index d4b918fb11ce..1f55e62044a4 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c @@ -266,7 +266,7 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) if (ret == -ETIME && !nsecs_to_jiffies(args->timeout_ns)) args->timeout_ns = 0; - /* Asked to wait beyond the jiffie/scheduler precision? */ + /* Asked to wait beyond the jiffy/scheduler precision? */ if (ret == -ETIME && args->timeout_ns) ret = -EAGAIN; } diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c index 4202df5b8c12..222ca7c44951 100644 --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c @@ -93,7 +93,7 @@ static int wait_for_reset(struct intel_engine_cs *engine, return -EINVAL; } - /* Give the request a jiffie to complete after flushing the worker */ + /* Give the request a jiffy to complete after flushing the worker */ if (i915_request_wait(rq, 0, max(0l, (long)(timeout - jiffies)) + 1) < 0) { pr_err("%s: hanging request %llx:%lld did not complete\n", @@ -3426,7 +3426,7 @@ static int live_preempt_timeout(void *arg) cpu_relax(); saved_timeout = engine->props.preempt_timeout_ms; - engine->props.preempt_timeout_ms = 1; /* in ms, -> 1 jiffie */ + engine->props.preempt_timeout_ms = 1; /* in ms, -> 1 jiffy */ i915_request_get(rq); i915_request_add(rq); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 8322c913bc3c..ed979847187f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -2843,9 +2843,9 @@ static void prepare_context_registration_info_v70(struct intel_context *ce, ce->parallel.guc.wqi_tail = 0; ce->parallel.guc.wqi_head = 0; - wq_desc_offset = i915_ggtt_offset(ce->state) + + wq_desc_offset = (u64)i915_ggtt_offset(ce->state) + __get_parent_scratch_offset(ce); - wq_base_offset = i915_ggtt_offset(ce->state) + + wq_base_offset = (u64)i915_ggtt_offset(ce->state) + __get_wq_offset(ce); info->wq_desc_lo = lower_32_bits(wq_desc_offset); info->wq_desc_hi = upper_32_bits(wq_desc_offset); diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index fe905d65ddf7..a40f05b993da 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -1675,6 +1675,7 @@ static const struct file_operations i915_driver_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = drm_show_fdinfo, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; static int diff --git a/drivers/gpu/drm/i915/i915_utils.c b/drivers/gpu/drm/i915/i915_utils.c index b34a2d3d331d..2576f8f6c0f6 100644 --- a/drivers/gpu/drm/i915/i915_utils.c +++ b/drivers/gpu/drm/i915/i915_utils.c @@ -69,7 +69,7 @@ void set_timer_ms(struct timer_list *t, unsigned long timeout) * Paranoia to make sure the compiler computes the timeout before * loading 'jiffies' as jiffies is volatile and may be updated in * the background by a timer tick. All to reduce the complexity - * of the addition and reduce the risk of losing a jiffie. + * of the addition and reduce the risk of losing a jiffy. */ barrier(); diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 4a9a9b9c3935..f6e78dba594f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -1292,6 +1292,7 @@ nouveau_driver_fops = { .compat_ioctl = nouveau_compat_ioctl, #endif .llseek = noop_llseek, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static struct drm_driver diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h index 50f0c1914f58..4c3f74396579 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h @@ -46,6 +46,8 @@ u32 gm107_ram_probe_fbp(const struct nvkm_ram_func *, u32 gm200_ram_probe_fbp_amount(const struct nvkm_ram_func *, u32, struct nvkm_device *, int, int *); +int gp100_ram_init(struct nvkm_ram *); + /* RAM type-specific MR calculation routines */ int nvkm_sddr2_calc(struct nvkm_ram *); int nvkm_sddr3_calc(struct nvkm_ram *); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c index 378f6fb70990..8987a21e81d1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c @@ -27,7 +27,7 @@ #include <subdev/bios/init.h> #include <subdev/bios/rammap.h> -static int +int gp100_ram_init(struct nvkm_ram *ram) { struct nvkm_subdev *subdev = &ram->fb->subdev; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp102.c index 8550f5e47347..b6b6ee59019d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp102.c @@ -5,6 +5,7 @@ static const struct nvkm_ram_func gp102_ram = { + .init = gp100_ram_init, }; int diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index f36aa71c57c7..e5a6f3e7c75b 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -530,6 +530,7 @@ static const struct file_operations radeon_driver_kms_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = radeon_kms_compat_ioctl, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; static const struct drm_ioctl_desc radeon_ioctls_kms[] = { diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 44d769d9234d..11e5d10de4d7 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -103,13 +103,17 @@ static int rockchip_drm_init_iommu(struct drm_device *drm_dev) struct rockchip_drm_private *private = drm_dev->dev_private; struct iommu_domain_geometry *geometry; u64 start, end; + int ret; if (IS_ERR_OR_NULL(private->iommu_dev)) return 0; - private->domain = iommu_domain_alloc(private->iommu_dev->bus); - if (!private->domain) - return -ENOMEM; + private->domain = iommu_paging_domain_alloc(private->iommu_dev); + if (IS_ERR(private->domain)) { + ret = PTR_ERR(private->domain); + private->domain = NULL; + return ret; + } geometry = &private->domain->geometry; start = geometry->aperture_start; diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index d9f0728c3afd..c9eb329665ec 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -801,6 +801,7 @@ static const struct file_operations tegra_drm_fops = { .read = drm_read, .compat_ioctl = drm_compat_ioctl, .llseek = noop_llseek, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static int tegra_drm_context_cleanup(int id, void *p, void *data) @@ -1135,6 +1136,7 @@ static bool host1x_drm_wants_iommu(struct host1x_device *dev) static int host1x_drm_probe(struct host1x_device *dev) { + struct device *dma_dev = dev->dev.parent; struct tegra_drm *tegra; struct drm_device *drm; int err; @@ -1149,8 +1151,8 @@ static int host1x_drm_probe(struct host1x_device *dev) goto put; } - if (host1x_drm_wants_iommu(dev) && iommu_present(&platform_bus_type)) { - tegra->domain = iommu_domain_alloc(&platform_bus_type); + if (host1x_drm_wants_iommu(dev) && device_iommu_mapped(dma_dev)) { + tegra->domain = iommu_paging_domain_alloc(dma_dev); if (!tegra->domain) { err = -ENOMEM; goto free; diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c index ecb80fd75b1a..ebe52bef4ffb 100644 --- a/drivers/gpu/drm/v3d/v3d_bo.c +++ b/drivers/gpu/drm/v3d/v3d_bo.c @@ -291,7 +291,7 @@ v3d_wait_bo_ioctl(struct drm_device *dev, void *data, else args->timeout_ns = 0; - /* Asked to wait beyond the jiffie/scheduler precision? */ + /* Asked to wait beyond the jiffy/scheduler precision? */ if (ret == -ETIME && args->timeout_ns) ret = -EAGAIN; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 50ad3105c16e..2825dd3149ed 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -1609,6 +1609,7 @@ static const struct file_operations vmwgfx_driver_fops = { .compat_ioctl = vmw_compat_ioctl, #endif .llseek = noop_llseek, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static const struct drm_driver driver = { diff --git a/drivers/gpu/drm/xe/regs/xe_oa_regs.h b/drivers/gpu/drm/xe/regs/xe_oa_regs.h index 1189f5a540a8..a9b0091cb7ee 100644 --- a/drivers/gpu/drm/xe/regs/xe_oa_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_oa_regs.h @@ -52,6 +52,7 @@ #define OAG_OABUFFER_MEMORY_SELECT REG_BIT(0) /* 0: PPGTT, 1: GGTT */ #define OAG_OACONTROL XE_REG(0xdaf4) +#define OAG_OACONTROL_OA_PES_DISAG_EN REG_GENMASK(27, 22) #define OAG_OACONTROL_OA_CCS_SELECT_MASK REG_GENMASK(18, 16) #define OAG_OACONTROL_OA_COUNTER_SEL_MASK REG_GENMASK(4, 2) #define OAG_OACONTROL_OA_COUNTER_ENABLE REG_BIT(0) diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 1a0d7fdd094b..70d4e4d46c3c 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -253,6 +253,7 @@ static const struct file_operations xe_driver_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = drm_show_fdinfo, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; static struct drm_driver driver = { diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c index e64f4b645e2e..95a05c5bc897 100644 --- a/drivers/gpu/drm/xe/xe_drm_client.c +++ b/drivers/gpu/drm/xe/xe_drm_client.c @@ -10,6 +10,7 @@ #include <linux/slab.h> #include <linux/types.h> +#include "xe_assert.h" #include "xe_bo.h" #include "xe_bo_types.h" #include "xe_device_types.h" @@ -151,10 +152,13 @@ void xe_drm_client_add_bo(struct xe_drm_client *client, */ void xe_drm_client_remove_bo(struct xe_bo *bo) { + struct xe_device *xe = ttm_to_xe_device(bo->ttm.bdev); struct xe_drm_client *client = bo->client; + xe_assert(xe, !kref_read(&bo->ttm.base.refcount)); + spin_lock(&client->bos_lock); - list_del(&bo->client_link); + list_del_init(&bo->client_link); spin_unlock(&client->bos_lock); xe_drm_client_put(client); @@ -166,6 +170,8 @@ static void bo_meminfo(struct xe_bo *bo, u64 sz = bo->size; u32 mem_type; + xe_bo_assert_held(bo); + if (bo->placement.placement) mem_type = bo->placement.placement->mem_type; else @@ -196,6 +202,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file) struct xe_drm_client *client; struct drm_gem_object *obj; struct xe_bo *bo; + LLIST_HEAD(deferred); unsigned int id; u32 mem_type; @@ -206,7 +213,20 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file) idr_for_each_entry(&file->object_idr, obj, id) { struct xe_bo *bo = gem_to_xe_bo(obj); - bo_meminfo(bo, stats); + if (dma_resv_trylock(bo->ttm.base.resv)) { + bo_meminfo(bo, stats); + xe_bo_unlock(bo); + } else { + xe_bo_get(bo); + spin_unlock(&file->table_lock); + + xe_bo_lock(bo, false); + bo_meminfo(bo, stats); + xe_bo_unlock(bo); + + xe_bo_put(bo); + spin_lock(&file->table_lock); + } } spin_unlock(&file->table_lock); @@ -215,11 +235,28 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file) list_for_each_entry(bo, &client->bos_list, client_link) { if (!kref_get_unless_zero(&bo->ttm.base.refcount)) continue; - bo_meminfo(bo, stats); - xe_bo_put(bo); + + if (dma_resv_trylock(bo->ttm.base.resv)) { + bo_meminfo(bo, stats); + xe_bo_unlock(bo); + } else { + spin_unlock(&client->bos_lock); + + xe_bo_lock(bo, false); + bo_meminfo(bo, stats); + xe_bo_unlock(bo); + + spin_lock(&client->bos_lock); + /* The bo ref will prevent this bo from being removed from the list */ + xe_assert(xef->xe, !list_empty(&bo->client_link)); + } + + xe_bo_put_deferred(bo, &deferred); } spin_unlock(&client->bos_lock); + xe_bo_put_commit(&deferred); + for (mem_type = XE_PL_SYSTEM; mem_type < TTM_NUM_MEM_TYPES; ++mem_type) { if (!xe_mem_type_to_name[mem_type]) continue; diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index dd96dec95b19..f0dc2bf24c7b 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -12,8 +12,6 @@ #include <generated/xe_wa_oob.h> -#include <generated/xe_wa_oob.h> - #include "instructions/xe_gfxpipe_commands.h" #include "instructions/xe_mi_commands.h" #include "regs/xe_gt_regs.h" diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index 63286ed8457f..0369cc016f6a 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -440,6 +440,10 @@ static void xe_oa_enable(struct xe_oa_stream *stream) val = __format_to_oactrl(format, regs->oa_ctrl_counter_select_mask) | __oa_ccs_select(stream) | OAG_OACONTROL_OA_COUNTER_ENABLE; + if (GRAPHICS_VER(stream->oa->xe) >= 20 && + stream->hwe->oa_unit->type == DRM_XE_OA_UNIT_TYPE_OAG) + val |= OAG_OACONTROL_OA_PES_DISAG_EN; + xe_mmio_write32(stream->gt, regs->oa_ctrl, val); } |