From 4251fa5fc3bbe3e1df99f60a738d367373ee335f Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Mon, 4 Mar 2019 19:37:40 +0100 Subject: drm/vmwgfx: Assign eviction priorities to resources TTM provides a means to assign eviction priorities to buffer object. This means that all buffer objects with a lower priority will be evicted first on memory pressure. Use this to make sure surfaces and in particular non-dirty surfaces are evicted first. Evicting in particular shaders, cotables and contexts imply a significant performance hit on vmwgfx, so make sure these resources are evicted last. Some buffer objects are sub-allocated in user-space which means we can have many resources attached to a single buffer object or resource. In that case the buffer object is given the highest priority of the attached resources. Signed-off-by: Thomas Hellstrom Reviewed-by: Deepak Rawat Reviewed-by: Emil Velikov --- drivers/gpu/drm/vmwgfx/vmwgfx_bo.c | 2 + drivers/gpu/drm/vmwgfx/vmwgfx_context.c | 4 ++ drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c | 13 +++-- drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 72 +++++++++++++++++++++++++++ drivers/gpu/drm/vmwgfx/vmwgfx_resource.c | 56 ++++++++++++++++----- drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h | 2 + drivers/gpu/drm/vmwgfx/vmwgfx_shader.c | 8 ++- drivers/gpu/drm/vmwgfx/vmwgfx_surface.c | 4 ++ 8 files changed, 141 insertions(+), 20 deletions(-) (limited to 'drivers/gpu/drm') diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 5d5c2bce01f3..c0829d50eecc 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -510,6 +510,8 @@ int vmw_bo_init(struct vmw_private *dev_priv, acc_size = vmw_bo_acc_size(dev_priv, size, user); memset(vmw_bo, 0, sizeof(*vmw_bo)); + BUILD_BUG_ON(TTM_MAX_BO_PRIORITY <= 3); + vmw_bo->base.priority = 3; INIT_LIST_HEAD(&vmw_bo->res_list); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c index 63f111068a44..a56c9d802382 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c @@ -88,6 +88,8 @@ static const struct vmw_res_func vmw_gb_context_func = { .res_type = vmw_res_context, .needs_backup = true, .may_evict = true, + .prio = 3, + .dirty_prio = 3, .type_name = "guest backed contexts", .backup_placement = &vmw_mob_placement, .create = vmw_gb_context_create, @@ -100,6 +102,8 @@ static const struct vmw_res_func vmw_dx_context_func = { .res_type = vmw_res_dx_context, .needs_backup = true, .may_evict = true, + .prio = 3, + .dirty_prio = 3, .type_name = "dx contexts", .backup_placement = &vmw_mob_placement, .create = vmw_dx_context_create, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c index b4f6e1217c9d..8c699cb2565b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c @@ -116,6 +116,8 @@ static const struct vmw_res_func vmw_cotable_func = { .res_type = vmw_res_cotable, .needs_backup = true, .may_evict = true, + .prio = 3, + .dirty_prio = 3, .type_name = "context guest backed object tables", .backup_placement = &vmw_mob_placement, .create = vmw_cotable_create, @@ -307,7 +309,7 @@ static int vmw_cotable_unbind(struct vmw_resource *res, struct ttm_buffer_object *bo = val_buf->bo; struct vmw_fence_obj *fence; - if (list_empty(&res->mob_head)) + if (!vmw_resource_mob_attached(res)) return 0; WARN_ON_ONCE(bo->mem.mem_type != VMW_PL_MOB); @@ -453,6 +455,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) goto out_wait; } + vmw_resource_mob_detach(res); res->backup = buf; res->backup_size = new_size; vcotbl->size_read_back = cur_size_read_back; @@ -467,12 +470,12 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) res->backup = old_buf; res->backup_size = old_size; vcotbl->size_read_back = old_size_read_back; + vmw_resource_mob_attach(res); goto out_wait; } + vmw_resource_mob_attach(res); /* Let go of the old mob. */ - list_del(&res->mob_head); - list_add_tail(&res->mob_head, &buf->res_list); vmw_bo_unreference(&old_buf); res->id = vcotbl->type; @@ -496,7 +499,7 @@ out_wait: * is called before bind() in the validation sequence is instead used for two * things. * 1) Unscrub the cotable if it is scrubbed and still attached to a backup - * buffer, that is, if @res->mob_head is non-empty. + * buffer. * 2) Resize the cotable if needed. */ static int vmw_cotable_create(struct vmw_resource *res) @@ -512,7 +515,7 @@ static int vmw_cotable_create(struct vmw_resource *res) new_size *= 2; if (likely(new_size <= res->backup_size)) { - if (vcotbl->scrubbed && !list_empty(&res->mob_head)) { + if (vcotbl->scrubbed && vmw_resource_mob_attached(res)) { ret = vmw_cotable_unscrub(res); if (ret) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 366dcfc1f9bb..7c935c72d368 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -86,6 +86,15 @@ struct vmw_fpriv { bool gb_aware; /* user-space is guest-backed aware */ }; +/** + * struct vmw_buffer_object - TTM buffer object with vmwgfx additions + * @base: The TTM buffer object + * @res_list: List of resources using this buffer object as a backing MOB + * @pin_count: pin depth + * @dx_query_ctx: DX context if this buffer object is used as a DX query MOB + * @map: Kmap object for semi-persistent mappings + * @res_prios: Eviction priority counts for attached resources + */ struct vmw_buffer_object { struct ttm_buffer_object base; struct list_head res_list; @@ -94,6 +103,7 @@ struct vmw_buffer_object { struct vmw_resource *dx_query_ctx; /* Protected by reservation */ struct ttm_bo_kmap_obj map; + u32 res_prios[TTM_MAX_BO_PRIORITY]; }; /** @@ -145,6 +155,7 @@ struct vmw_resource { struct kref kref; struct vmw_private *dev_priv; int id; + u32 used_prio; unsigned long backup_size; bool res_dirty; bool backup_dirty; @@ -709,6 +720,19 @@ extern void vmw_query_move_notify(struct ttm_buffer_object *bo, extern int vmw_query_readback_all(struct vmw_buffer_object *dx_query_mob); extern void vmw_resource_evict_all(struct vmw_private *dev_priv); extern void vmw_resource_unbind_list(struct vmw_buffer_object *vbo); +void vmw_resource_mob_attach(struct vmw_resource *res); +void vmw_resource_mob_detach(struct vmw_resource *res); + +/** + * vmw_resource_mob_attached - Whether a resource currently has a mob attached + * @res: The resource + * + * Return: true if the resource has a mob attached, false otherwise. + */ +static inline bool vmw_resource_mob_attached(const struct vmw_resource *res) +{ + return !list_empty(&res->mob_head); +} /** * vmw_user_resource_noref_release - release a user resource pointer looked up @@ -787,6 +811,54 @@ static inline void vmw_user_bo_noref_release(void) ttm_base_object_noref_release(); } +/** + * vmw_bo_adjust_prio - Adjust the buffer object eviction priority + * according to attached resources + * @vbo: The struct vmw_buffer_object + */ +static inline void vmw_bo_prio_adjust(struct vmw_buffer_object *vbo) +{ + int i = ARRAY_SIZE(vbo->res_prios); + + while (i--) { + if (vbo->res_prios[i]) { + vbo->base.priority = i; + return; + } + } + + vbo->base.priority = 3; +} + +/** + * vmw_bo_prio_add - Notify a buffer object of a newly attached resource + * eviction priority + * @vbo: The struct vmw_buffer_object + * @prio: The resource priority + * + * After being notified, the code assigns the highest resource eviction priority + * to the backing buffer object (mob). + */ +static inline void vmw_bo_prio_add(struct vmw_buffer_object *vbo, int prio) +{ + if (vbo->res_prios[prio]++ == 0) + vmw_bo_prio_adjust(vbo); +} + +/** + * vmw_bo_prio_del - Notify a buffer object of a resource with a certain + * priority being removed + * @vbo: The struct vmw_buffer_object + * @prio: The resource priority + * + * After being notified, the code assigns the highest resource eviction priority + * to the backing buffer object (mob). + */ +static inline void vmw_bo_prio_del(struct vmw_buffer_object *vbo, int prio) +{ + if (--vbo->res_prios[prio] == 0) + vmw_bo_prio_adjust(vbo); +} /** * Misc Ioctl functionality - vmwgfx_ioctl.c diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 1d38a8b2f2ec..be7d4149a129 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -34,6 +34,37 @@ #define VMW_RES_EVICT_ERR_COUNT 10 +/** + * vmw_resource_mob_attach - Mark a resource as attached to its backing mob + * @res: The resource + */ +void vmw_resource_mob_attach(struct vmw_resource *res) +{ + struct vmw_buffer_object *backup = res->backup; + + lockdep_assert_held(&backup->base.resv->lock.base); + res->used_prio = (res->res_dirty) ? res->func->dirty_prio : + res->func->prio; + list_add_tail(&res->mob_head, &backup->res_list); + vmw_bo_prio_add(backup, res->used_prio); +} + +/** + * vmw_resource_mob_detach - Mark a resource as detached from its backing mob + * @res: The resource + */ +void vmw_resource_mob_detach(struct vmw_resource *res) +{ + struct vmw_buffer_object *backup = res->backup; + + lockdep_assert_held(&backup->base.resv->lock.base); + if (vmw_resource_mob_attached(res)) { + list_del_init(&res->mob_head); + vmw_bo_prio_del(backup, res->used_prio); + } +} + + struct vmw_resource *vmw_resource_reference(struct vmw_resource *res) { kref_get(&res->kref); @@ -80,7 +111,7 @@ static void vmw_resource_release(struct kref *kref) struct ttm_buffer_object *bo = &res->backup->base; ttm_bo_reserve(bo, false, false, NULL); - if (!list_empty(&res->mob_head) && + if (vmw_resource_mob_attached(res) && res->func->unbind != NULL) { struct ttm_validate_buffer val_buf; @@ -89,7 +120,7 @@ static void vmw_resource_release(struct kref *kref) res->func->unbind(res, false, &val_buf); } res->backup_dirty = false; - list_del_init(&res->mob_head); + vmw_resource_mob_detach(res); ttm_bo_unreserve(bo); vmw_bo_unreference(&res->backup); } @@ -179,6 +210,7 @@ int vmw_resource_init(struct vmw_private *dev_priv, struct vmw_resource *res, res->backup_offset = 0; res->backup_dirty = false; res->res_dirty = false; + res->used_prio = 3; if (delay_id) return 0; else @@ -355,14 +387,14 @@ static int vmw_resource_do_validate(struct vmw_resource *res, } if (func->bind && - ((func->needs_backup && list_empty(&res->mob_head) && + ((func->needs_backup && !vmw_resource_mob_attached(res) && val_buf->bo != NULL) || (!func->needs_backup && val_buf->bo != NULL))) { ret = func->bind(res, val_buf); if (unlikely(ret != 0)) goto out_bind_failed; if (func->needs_backup) - list_add_tail(&res->mob_head, &res->backup->res_list); + vmw_resource_mob_attach(res); } return 0; @@ -402,15 +434,13 @@ void vmw_resource_unreserve(struct vmw_resource *res, if (switch_backup && new_backup != res->backup) { if (res->backup) { - lockdep_assert_held(&res->backup->base.resv->lock.base); - list_del_init(&res->mob_head); + vmw_resource_mob_detach(res); vmw_bo_unreference(&res->backup); } if (new_backup) { res->backup = vmw_bo_reference(new_backup); - lockdep_assert_held(&new_backup->base.resv->lock.base); - list_add_tail(&res->mob_head, &new_backup->res_list); + vmw_resource_mob_attach(res); } else { res->backup = NULL; } @@ -469,7 +499,7 @@ vmw_resource_check_buffer(struct ww_acquire_ctx *ticket, if (unlikely(ret != 0)) goto out_no_reserve; - if (res->func->needs_backup && list_empty(&res->mob_head)) + if (res->func->needs_backup && !vmw_resource_mob_attached(res)) return 0; backup_dirty = res->backup_dirty; @@ -574,11 +604,11 @@ static int vmw_resource_do_evict(struct ww_acquire_ctx *ticket, return ret; if (unlikely(func->unbind != NULL && - (!func->needs_backup || !list_empty(&res->mob_head)))) { + (!func->needs_backup || vmw_resource_mob_attached(res)))) { ret = func->unbind(res, res->res_dirty, &val_buf); if (unlikely(ret != 0)) goto out_no_unbind; - list_del_init(&res->mob_head); + vmw_resource_mob_detach(res); } ret = func->destroy(res); res->backup_dirty = true; @@ -660,7 +690,7 @@ int vmw_resource_validate(struct vmw_resource *res, bool intr) if (unlikely(ret != 0)) goto out_no_validate; else if (!res->func->needs_backup && res->backup) { - list_del_init(&res->mob_head); + WARN_ON_ONCE(vmw_resource_mob_attached(res)); vmw_bo_unreference(&res->backup); } @@ -699,7 +729,7 @@ void vmw_resource_unbind_list(struct vmw_buffer_object *vbo) (void) res->func->unbind(res, res->res_dirty, &val_buf); res->backup_dirty = true; res->res_dirty = false; - list_del_init(&res->mob_head); + vmw_resource_mob_detach(res); } (void) ttm_bo_wait(&vbo->base, false, false); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h index 7e19eba0b0b8..984e588c62ca 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h @@ -78,6 +78,8 @@ struct vmw_res_func { const char *type_name; struct ttm_placement *backup_placement; bool may_evict; + u32 prio; + u32 dirty_prio; int (*create) (struct vmw_resource *res); int (*destroy) (struct vmw_resource *res); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index d310d21f0d54..e139fdfd1635 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -95,6 +95,8 @@ static const struct vmw_res_func vmw_gb_shader_func = { .res_type = vmw_res_shader, .needs_backup = true, .may_evict = true, + .prio = 3, + .dirty_prio = 3, .type_name = "guest backed shaders", .backup_placement = &vmw_mob_placement, .create = vmw_gb_shader_create, @@ -106,7 +108,9 @@ static const struct vmw_res_func vmw_gb_shader_func = { static const struct vmw_res_func vmw_dx_shader_func = { .res_type = vmw_res_shader, .needs_backup = true, - .may_evict = false, + .may_evict = true, + .prio = 3, + .dirty_prio = 3, .type_name = "dx shaders", .backup_placement = &vmw_mob_placement, .create = vmw_dx_shader_create, @@ -423,7 +427,7 @@ static int vmw_dx_shader_create(struct vmw_resource *res) WARN_ON_ONCE(!shader->committed); - if (!list_empty(&res->mob_head)) { + if (vmw_resource_mob_attached(res)) { mutex_lock(&dev_priv->binding_mutex); ret = vmw_dx_shader_unscrub(res); mutex_unlock(&dev_priv->binding_mutex); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 219471903bc1..c40d44f4d9af 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -112,6 +112,8 @@ static const struct vmw_res_func vmw_legacy_surface_func = { .res_type = vmw_res_surface, .needs_backup = false, .may_evict = true, + .prio = 1, + .dirty_prio = 1, .type_name = "legacy surfaces", .backup_placement = &vmw_srf_placement, .create = &vmw_legacy_srf_create, @@ -124,6 +126,8 @@ static const struct vmw_res_func vmw_gb_surface_func = { .res_type = vmw_res_surface, .needs_backup = true, .may_evict = true, + .prio = 1, + .dirty_prio = 2, .type_name = "guest backed surfaces", .backup_placement = &vmw_mob_placement, .create = vmw_gb_surface_create, -- cgit v1.2.3 From 32d1f6985ceb6b9099bc9e02dc04e58660f28c16 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Fri, 12 Oct 2018 17:16:39 +0200 Subject: drm/ttm: Allow the driver to provide the ttm struct vm_operations_struct MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a pointer to the struct vm_operations_struct in the bo_device, and assign that pointer to the default value currently used. The driver can then optionally modify that pointer and the new value can be used for each new vma created. Cc: "Christian König" Signed-off-by: Thomas Hellstrom Reviewed-by: Christian König --- drivers/gpu/drm/ttm/ttm_bo.c | 1 + drivers/gpu/drm/ttm/ttm_bo_vm.c | 6 +++--- include/drm/ttm/ttm_bo_driver.h | 6 ++++++ 3 files changed, 10 insertions(+), 3 deletions(-) (limited to 'drivers/gpu/drm') diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index c7de667d482a..6953dd264172 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1739,6 +1739,7 @@ int ttm_bo_device_init(struct ttm_bo_device *bdev, mutex_lock(&ttm_global_mutex); list_add_tail(&bdev->device_list, &glob->device_list); mutex_unlock(&ttm_global_mutex); + bdev->vm_ops = &ttm_bo_vm_ops; return 0; out_no_sys: diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 6dacff49c1cc..196e13a0adad 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -395,7 +395,7 @@ static int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr, return ret; } -static const struct vm_operations_struct ttm_bo_vm_ops = { +const struct vm_operations_struct ttm_bo_vm_ops = { .fault = ttm_bo_vm_fault, .open = ttm_bo_vm_open, .close = ttm_bo_vm_close, @@ -448,7 +448,7 @@ int ttm_bo_mmap(struct file *filp, struct vm_area_struct *vma, if (unlikely(ret != 0)) goto out_unref; - vma->vm_ops = &ttm_bo_vm_ops; + vma->vm_ops = bdev->vm_ops; /* * Note: We're transferring the bo reference to @@ -480,7 +480,7 @@ int ttm_fbdev_mmap(struct vm_area_struct *vma, struct ttm_buffer_object *bo) ttm_bo_get(bo); - vma->vm_ops = &ttm_bo_vm_ops; + vma->vm_ops = bo->bdev->vm_ops; vma->vm_private_data = bo; vma->vm_flags |= VM_MIXEDMAP; vma->vm_flags |= VM_IO | VM_DONTEXPAND; diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index c9b8ba492f24..a2d810a2504d 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -442,6 +442,9 @@ extern struct ttm_bo_global { * @driver: Pointer to a struct ttm_bo_driver struct setup by the driver. * @man: An array of mem_type_managers. * @vma_manager: Address space manager + * @vm_ops: Pointer to the struct vm_operations_struct used for this + * device's VM operations. The driver may override this before the first + * mmap() call. * lru_lock: Spinlock that protects the buffer+device lru lists and * ddestroy lists. * @dev_mapping: A pointer to the struct address_space representing the @@ -460,6 +463,7 @@ struct ttm_bo_device { struct ttm_bo_global *glob; struct ttm_bo_driver *driver; struct ttm_mem_type_manager man[TTM_NUM_MEM_TYPES]; + const struct vm_operations_struct *vm_ops; /* * Protected by internal locks. @@ -488,6 +492,8 @@ struct ttm_bo_device { bool no_retry; }; +extern const struct vm_operations_struct ttm_bo_vm_ops; + /** * struct ttm_lru_bulk_move_pos * -- cgit v1.2.3 From 7a39f35ce43f96ff293cc90f845416d03566b14b Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Wed, 6 Feb 2019 12:55:08 +0100 Subject: drm/ttm: TTM fault handler helpers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With the vmwgfx dirty tracking, the default TTM fault handler is not completely sufficient (vmwgfx need to modify the vma->vm_flags member, and also needs to restrict the number of prefaults). We also want to replicate the new ttm_bo_vm_reserve() functionality So start turning the TTM vm code into helpers: ttm_bo_vm_fault_reserved() and ttm_bo_vm_reserve(), and provide a default TTM fault handler for other drivers to use. Cc: "Christian König" Signed-off-by: Thomas Hellstrom Reviewed-by: "Christian König" #v1 --- drivers/gpu/drm/ttm/ttm_bo_vm.c | 163 +++++++++++++++++++++++++--------------- include/drm/ttm/ttm_bo_api.h | 10 +++ 2 files changed, 111 insertions(+), 62 deletions(-) (limited to 'drivers/gpu/drm') diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 196e13a0adad..0c4576cbafcf 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -42,8 +42,6 @@ #include #include -#define TTM_BO_VM_NUM_PREFAULT 16 - static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo, struct vm_fault *vmf) { @@ -106,25 +104,30 @@ static unsigned long ttm_bo_io_mem_pfn(struct ttm_buffer_object *bo, + page_offset; } -static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf) +/** + * ttm_bo_vm_reserve - Reserve a buffer object in a retryable vm callback + * @bo: The buffer object + * @vmf: The fault structure handed to the callback + * + * vm callbacks like fault() and *_mkwrite() allow for the mm_sem to be dropped + * during long waits, and after the wait the callback will be restarted. This + * is to allow other threads using the same virtual memory space concurrent + * access to map(), unmap() completely unrelated buffer objects. TTM buffer + * object reservations sometimes wait for GPU and should therefore be + * considered long waits. This function reserves the buffer object interruptibly + * taking this into account. Starvation is avoided by the vm system not + * allowing too many repeated restarts. + * This function is intended to be used in customized fault() and _mkwrite() + * handlers. + * + * Return: + * 0 on success and the bo was reserved. + * VM_FAULT_RETRY if blocking wait. + * VM_FAULT_NOPAGE if blocking wait and retrying was not allowed. + */ +vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo, + struct vm_fault *vmf) { - struct vm_area_struct *vma = vmf->vma; - struct ttm_buffer_object *bo = (struct ttm_buffer_object *) - vma->vm_private_data; - struct ttm_bo_device *bdev = bo->bdev; - unsigned long page_offset; - unsigned long page_last; - unsigned long pfn; - struct ttm_tt *ttm = NULL; - struct page *page; - int err; - int i; - vm_fault_t ret = VM_FAULT_NOPAGE; - unsigned long address = vmf->address; - struct ttm_mem_type_manager *man = - &bdev->man[bo->mem.mem_type]; - struct vm_area_struct cvma; - /* * Work around locking order reversal in fault / nopfn * between mmap_sem and bo_reserve: Perform a trylock operation @@ -151,14 +154,55 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf) return VM_FAULT_NOPAGE; } + return 0; +} +EXPORT_SYMBOL(ttm_bo_vm_reserve); + +/** + * ttm_bo_vm_fault_reserved - TTM fault helper + * @vmf: The struct vm_fault given as argument to the fault callback + * @prot: The page protection to be used for this memory area. + * @num_prefault: Maximum number of prefault pages. The caller may want to + * specify this based on madvice settings and the size of the GPU object + * backed by the memory. + * + * This function inserts one or more page table entries pointing to the + * memory backing the buffer object, and then returns a return code + * instructing the caller to retry the page access. + * + * Return: + * VM_FAULT_NOPAGE on success or pending signal + * VM_FAULT_SIGBUS on unspecified error + * VM_FAULT_OOM on out-of-memory + * VM_FAULT_RETRY if retryable wait + */ +vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, + pgprot_t prot, + pgoff_t num_prefault) +{ + struct vm_area_struct *vma = vmf->vma; + struct vm_area_struct cvma = *vma; + struct ttm_buffer_object *bo = (struct ttm_buffer_object *) + vma->vm_private_data; + struct ttm_bo_device *bdev = bo->bdev; + unsigned long page_offset; + unsigned long page_last; + unsigned long pfn; + struct ttm_tt *ttm = NULL; + struct page *page; + int err; + pgoff_t i; + vm_fault_t ret = VM_FAULT_NOPAGE; + unsigned long address = vmf->address; + struct ttm_mem_type_manager *man = + &bdev->man[bo->mem.mem_type]; + /* * Refuse to fault imported pages. This should be handled * (if at all) by redirecting mmap to the exporter. */ - if (bo->ttm && (bo->ttm->page_flags & TTM_PAGE_FLAG_SG)) { - ret = VM_FAULT_SIGBUS; - goto out_unlock; - } + if (bo->ttm && (bo->ttm->page_flags & TTM_PAGE_FLAG_SG)) + return VM_FAULT_SIGBUS; if (bdev->driver->fault_reserve_notify) { struct dma_fence *moving = dma_fence_get(bo->moving); @@ -169,11 +213,9 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf) break; case -EBUSY: case -ERESTARTSYS: - ret = VM_FAULT_NOPAGE; - goto out_unlock; + return VM_FAULT_NOPAGE; default: - ret = VM_FAULT_SIGBUS; - goto out_unlock; + return VM_FAULT_SIGBUS; } if (bo->moving != moving) { @@ -189,21 +231,12 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf) * move. */ ret = ttm_bo_vm_fault_idle(bo, vmf); - if (unlikely(ret != 0)) { - if (ret == VM_FAULT_RETRY && - !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) { - /* The BO has already been unreserved. */ - return ret; - } - - goto out_unlock; - } + if (unlikely(ret != 0)) + return ret; err = ttm_mem_io_lock(man, true); - if (unlikely(err != 0)) { - ret = VM_FAULT_NOPAGE; - goto out_unlock; - } + if (unlikely(err != 0)) + return VM_FAULT_NOPAGE; err = ttm_mem_io_reserve_vm(bo); if (unlikely(err != 0)) { ret = VM_FAULT_SIGBUS; @@ -220,18 +253,8 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf) goto out_io_unlock; } - /* - * Make a local vma copy to modify the page_prot member - * and vm_flags if necessary. The vma parameter is protected - * by mmap_sem in write mode. - */ - cvma = *vma; - cvma.vm_page_prot = vm_get_page_prot(cvma.vm_flags); - - if (bo->mem.bus.is_iomem) { - cvma.vm_page_prot = ttm_io_prot(bo->mem.placement, - cvma.vm_page_prot); - } else { + cvma.vm_page_prot = ttm_io_prot(bo->mem.placement, prot); + if (!bo->mem.bus.is_iomem) { struct ttm_operation_ctx ctx = { .interruptible = false, .no_wait_gpu = false, @@ -240,24 +263,21 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf) }; ttm = bo->ttm; - cvma.vm_page_prot = ttm_io_prot(bo->mem.placement, - cvma.vm_page_prot); - - /* Allocate all page at once, most common usage */ - if (ttm_tt_populate(ttm, &ctx)) { + if (ttm_tt_populate(bo->ttm, &ctx)) { ret = VM_FAULT_OOM; goto out_io_unlock; } + } else { + /* Iomem should not be marked encrypted */ + cvma.vm_page_prot = pgprot_decrypted(cvma.vm_page_prot); } /* * Speculatively prefault a number of pages. Only error on * first page. */ - for (i = 0; i < TTM_BO_VM_NUM_PREFAULT; ++i) { + for (i = 0; i < num_prefault; ++i) { if (bo->mem.bus.is_iomem) { - /* Iomem should not be marked encrypted */ - cvma.vm_page_prot = pgprot_decrypted(cvma.vm_page_prot); pfn = ttm_bo_io_mem_pfn(bo, page_offset); } else { page = ttm->pages[page_offset]; @@ -295,7 +315,26 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf) ret = VM_FAULT_NOPAGE; out_io_unlock: ttm_mem_io_unlock(man); -out_unlock: + return ret; +} +EXPORT_SYMBOL(ttm_bo_vm_fault_reserved); + +static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + pgprot_t prot; + struct ttm_buffer_object *bo = vma->vm_private_data; + vm_fault_t ret; + + ret = ttm_bo_vm_reserve(bo, vmf); + if (ret) + return ret; + + prot = vm_get_page_prot(vma->vm_flags); + ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT); + if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) + return ret; + reservation_object_unlock(bo->resv); return ret; } diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 49d9cdfc58f2..435d02f719a8 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -768,4 +768,14 @@ int ttm_bo_swapout(struct ttm_bo_global *glob, struct ttm_operation_ctx *ctx); void ttm_bo_swapout_all(struct ttm_bo_device *bdev); int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo); + +/* Default number of pre-faulted pages in the TTM fault handler */ +#define TTM_BO_VM_NUM_PREFAULT 16 + +vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo, + struct vm_fault *vmf); + +vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, + pgprot_t prot, + pgoff_t num_prefault); #endif -- cgit v1.2.3 From 93392217066d9fb5f05188d05afa9ea56829a61c Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Wed, 27 Mar 2019 10:56:08 +0100 Subject: drm/vmwgfx: Implement an infrastructure for write-coherent resources This infrastructure will, for coherent resources, make sure that from the user-space point of view, data written by the CPU is immediately automatically available to the GPU at resource validation time. Signed-off-by: Thomas Hellstrom Reviewed-by: Deepak Rawat --- drivers/gpu/drm/vmwgfx/Kconfig | 1 + drivers/gpu/drm/vmwgfx/Makefile | 2 +- drivers/gpu/drm/vmwgfx/vmwgfx_bo.c | 5 +- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 5 + drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 26 +- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 1 - drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c | 409 ++++++++++++++++++++++++++ drivers/gpu/drm/vmwgfx/vmwgfx_resource.c | 57 ++++ drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h | 11 + drivers/gpu/drm/vmwgfx/vmwgfx_validation.c | 71 +++++ drivers/gpu/drm/vmwgfx/vmwgfx_validation.h | 16 +- 11 files changed, 584 insertions(+), 20 deletions(-) create mode 100644 drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c (limited to 'drivers/gpu/drm') diff --git a/drivers/gpu/drm/vmwgfx/Kconfig b/drivers/gpu/drm/vmwgfx/Kconfig index 6b28a326f8bb..d5fd81a521f6 100644 --- a/drivers/gpu/drm/vmwgfx/Kconfig +++ b/drivers/gpu/drm/vmwgfx/Kconfig @@ -8,6 +8,7 @@ config DRM_VMWGFX select FB_CFB_IMAGEBLIT select DRM_TTM select FB + select AS_DIRTY_HELPERS # Only needed for the transitional use of drm_crtc_init - can be removed # again once vmwgfx sets up the primary plane itself. select DRM_KMS_HELPER diff --git a/drivers/gpu/drm/vmwgfx/Makefile b/drivers/gpu/drm/vmwgfx/Makefile index 8841bd30e1e5..c877a21a0739 100644 --- a/drivers/gpu/drm/vmwgfx/Makefile +++ b/drivers/gpu/drm/vmwgfx/Makefile @@ -8,7 +8,7 @@ vmwgfx-y := vmwgfx_execbuf.o vmwgfx_gmr.o vmwgfx_kms.o vmwgfx_drv.o \ vmwgfx_cmdbuf_res.o vmwgfx_cmdbuf.o vmwgfx_stdu.o \ vmwgfx_cotable.o vmwgfx_so.o vmwgfx_binding.o vmwgfx_msg.o \ vmwgfx_simple_resource.o vmwgfx_va.o vmwgfx_blit.o \ - vmwgfx_validation.o \ + vmwgfx_validation.o vmwgfx_page_dirty.o \ ttm_object.o ttm_lock.o obj-$(CONFIG_DRM_VMWGFX) := vmwgfx.o diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index c0829d50eecc..90ca866640fe 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -463,6 +463,7 @@ void vmw_bo_bo_free(struct ttm_buffer_object *bo) { struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo); + WARN_ON(vmw_bo->dirty); vmw_bo_unmap(vmw_bo); kfree(vmw_bo); } @@ -476,8 +477,10 @@ void vmw_bo_bo_free(struct ttm_buffer_object *bo) static void vmw_user_bo_destroy(struct ttm_buffer_object *bo) { struct vmw_user_buffer_object *vmw_user_bo = vmw_user_buffer_object(bo); + struct vmw_buffer_object *vbo = &vmw_user_bo->vbo; - vmw_bo_unmap(&vmw_user_bo->vbo); + WARN_ON(vbo->dirty); + vmw_bo_unmap(vbo); ttm_prime_object_kfree(vmw_user_bo, prime); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 4ff11a0077e1..d59c474be38e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -833,6 +833,11 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) DRM_ERROR("Failed initializing TTM buffer object driver.\n"); goto out_no_bdev; } + dev_priv->vm_ops = *dev_priv->bdev.vm_ops; + dev_priv->vm_ops.fault = vmw_bo_vm_fault; + dev_priv->vm_ops.pfn_mkwrite = vmw_bo_vm_mkwrite; + dev_priv->vm_ops.page_mkwrite = vmw_bo_vm_mkwrite; + dev_priv->bdev.vm_ops = &dev_priv->vm_ops; /* * Enable VRAM, but initially don't use it until SVGA is enabled and diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 7c935c72d368..27c259395790 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -94,6 +94,7 @@ struct vmw_fpriv { * @dx_query_ctx: DX context if this buffer object is used as a DX query MOB * @map: Kmap object for semi-persistent mappings * @res_prios: Eviction priority counts for attached resources + * @dirty: structure for user-space dirty-tracking */ struct vmw_buffer_object { struct ttm_buffer_object base; @@ -104,6 +105,7 @@ struct vmw_buffer_object { /* Protected by reservation */ struct ttm_bo_kmap_obj map; u32 res_prios[TTM_MAX_BO_PRIORITY]; + struct vmw_bo_dirty *dirty; }; /** @@ -134,7 +136,8 @@ struct vmw_res_func; * @res_dirty: Resource contains data not yet in the backup buffer. Protected * by resource reserved. * @backup_dirty: Backup buffer contains data not yet in the HW resource. - * Protecte by resource reserved. + * Protected by resource reserved. + * @coherent: Emulate coherency by tracking vm accesses. * @backup: The backup buffer if any. Protected by resource reserved. * @backup_offset: Offset into the backup buffer if any. Protected by resource * reserved. Note that only a few resource types can have a @backup_offset @@ -151,14 +154,16 @@ struct vmw_res_func; * @hw_destroy: Callback to destroy the resource on the device, as part of * resource destruction. */ +struct vmw_resource_dirty; struct vmw_resource { struct kref kref; struct vmw_private *dev_priv; int id; u32 used_prio; unsigned long backup_size; - bool res_dirty; - bool backup_dirty; + u32 res_dirty : 1; + u32 backup_dirty : 1; + u32 coherent : 1; struct vmw_buffer_object *backup; unsigned long backup_offset; unsigned long pin_count; @@ -166,6 +171,7 @@ struct vmw_resource { struct list_head lru_head; struct list_head mob_head; struct list_head binding_head; + struct vmw_resource_dirty *dirty; void (*res_free) (struct vmw_resource *res); void (*hw_destroy) (struct vmw_resource *res); }; @@ -606,6 +612,9 @@ struct vmw_private { /* Validation memory reservation */ struct vmw_validation_mem vvm; + + /* VM operations */ + struct vm_operations_struct vm_ops; }; static inline struct vmw_surface *vmw_res_to_srf(struct vmw_resource *res) @@ -722,6 +731,8 @@ extern void vmw_resource_evict_all(struct vmw_private *dev_priv); extern void vmw_resource_unbind_list(struct vmw_buffer_object *vbo); void vmw_resource_mob_attach(struct vmw_resource *res); void vmw_resource_mob_detach(struct vmw_resource *res); +void vmw_resource_dirty_update(struct vmw_resource *res, pgoff_t start, + pgoff_t end); /** * vmw_resource_mob_attached - Whether a resource currently has a mob attached @@ -1410,6 +1421,15 @@ int vmw_host_log(const char *log); #define VMW_DEBUG_USER(fmt, ...) \ DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__) +/* Resource dirtying - vmwgfx_page_dirty.c */ +void vmw_bo_dirty_scan(struct vmw_buffer_object *vbo); +int vmw_bo_dirty_add(struct vmw_buffer_object *vbo); +void vmw_bo_dirty_transfer_to_res(struct vmw_resource *res); +void vmw_bo_dirty_clear_res(struct vmw_resource *res); +void vmw_bo_dirty_release(struct vmw_buffer_object *vbo); +vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf); +vm_fault_t vmw_bo_vm_mkwrite(struct vm_fault *vmf); + /** * Inline helper functions */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 33533d126277..319c1ca35663 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -2560,7 +2560,6 @@ static int vmw_cmd_dx_check_subresource(struct vmw_private *dev_priv, offsetof(typeof(*cmd), sid)); cmd = container_of(header, typeof(*cmd), header); - return vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface, VMW_RES_DIRTY_NONE, user_surface_converter, &cmd->sid, NULL); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c new file mode 100644 index 000000000000..8d154f90bdc0 --- /dev/null +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c @@ -0,0 +1,409 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/************************************************************************** + * + * Copyright 2019 VMware, Inc., Palo Alto, CA., USA + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + **************************************************************************/ +#include "vmwgfx_drv.h" + +/* + * Different methods for tracking dirty: + * VMW_BO_DIRTY_PAGETABLE - Scan the pagetable for hardware dirty bits + * VMW_BO_DIRTY_MKWRITE - Write-protect page table entries and record write- + * accesses in the VM mkwrite() callback + */ +enum vmw_bo_dirty_method { + VMW_BO_DIRTY_PAGETABLE, + VMW_BO_DIRTY_MKWRITE, +}; + +/* + * No dirtied pages at scan trigger a transition to the _MKWRITE method, + * similarly a certain percentage of dirty pages trigger a transition to + * the _PAGETABLE method. How many triggers should we wait for before + * changing method? + */ +#define VMW_DIRTY_NUM_CHANGE_TRIGGERS 2 + +/* Percentage to trigger a transition to the _PAGETABLE method */ +#define VMW_DIRTY_PERCENTAGE 10 + +/** + * struct vmw_bo_dirty - Dirty information for buffer objects + * @start: First currently dirty bit + * @end: Last currently dirty bit + 1 + * @method: The currently used dirty method + * @change_count: Number of consecutive method change triggers + * @ref_count: Reference count for this structure + * @bitmap_size: The size of the bitmap in bits. Typically equal to the + * nuber of pages in the bo. + * @size: The accounting size for this struct. + * @bitmap: A bitmap where each bit represents a page. A set bit means a + * dirty page. + */ +struct vmw_bo_dirty { + unsigned long start; + unsigned long end; + enum vmw_bo_dirty_method method; + unsigned int change_count; + unsigned int ref_count; + unsigned long bitmap_size; + size_t size; + unsigned long bitmap[0]; +}; + +/** + * vmw_bo_dirty_scan_pagetable - Perform a pagetable scan for dirty bits + * @vbo: The buffer object to scan + * + * Scans the pagetable for dirty bits. Clear those bits and modify the + * dirty structure with the results. This function may change the + * dirty-tracking method. + */ +static void vmw_bo_dirty_scan_pagetable(struct vmw_buffer_object *vbo) +{ + struct vmw_bo_dirty *dirty = vbo->dirty; + pgoff_t offset = drm_vma_node_start(&vbo->base.vma_node); + struct address_space *mapping = vbo->base.bdev->dev_mapping; + pgoff_t num_marked; + + num_marked = apply_as_clean(mapping, + offset, dirty->bitmap_size, + offset, &dirty->bitmap[0], + &dirty->start, &dirty->end); + if (num_marked == 0) + dirty->change_count++; + else + dirty->change_count = 0; + + if (dirty->change_count > VMW_DIRTY_NUM_CHANGE_TRIGGERS) { + dirty->change_count = 0; + dirty->method = VMW_BO_DIRTY_MKWRITE; + apply_as_wrprotect(mapping, + offset, dirty->bitmap_size); + apply_as_clean(mapping, + offset, dirty->bitmap_size, + offset, &dirty->bitmap[0], + &dirty->start, &dirty->end); + } +} + +/** + * vmw_bo_dirty_scan_mkwrite - Reset the mkwrite dirty-tracking method + * @vbo: The buffer object to scan + * + * Write-protect pages written to so that consecutive write accesses will + * trigger a call to mkwrite. + * + * This function may change the dirty-tracking method. + */ +static void vmw_bo_dirty_scan_mkwrite(struct vmw_buffer_object *vbo) +{ + struct vmw_bo_dirty *dirty = vbo->dirty; + unsigned long offset = drm_vma_node_start(&vbo->base.vma_node); + struct address_space *mapping = vbo->base.bdev->dev_mapping; + pgoff_t num_marked; + + if (dirty->end <= dirty->start) + return; + + num_marked = apply_as_wrprotect(vbo->base.bdev->dev_mapping, + dirty->start + offset, + dirty->end - dirty->start); + + if (100UL * num_marked / dirty->bitmap_size > + VMW_DIRTY_PERCENTAGE) { + dirty->change_count++; + } else { + dirty->change_count = 0; + } + + if (dirty->change_count > VMW_DIRTY_NUM_CHANGE_TRIGGERS) { + pgoff_t start = 0; + pgoff_t end = dirty->bitmap_size; + + dirty->method = VMW_BO_DIRTY_PAGETABLE; + apply_as_clean(mapping, offset, end, offset, &dirty->bitmap[0], + &start, &end); + bitmap_clear(&dirty->bitmap[0], 0, dirty->bitmap_size); + if (dirty->start < dirty->end) + bitmap_set(&dirty->bitmap[0], dirty->start, + dirty->end - dirty->start); + dirty->change_count = 0; + } +} + + +/** + * vmw_bo_dirty_scan - Scan for dirty pages and add them to the dirty + * tracking structure + * @vbo: The buffer object to scan + * + * This function may change the dirty tracking method. + */ +void vmw_bo_dirty_scan(struct vmw_buffer_object *vbo) +{ + struct vmw_bo_dirty *dirty = vbo->dirty; + + if (dirty->method == VMW_BO_DIRTY_PAGETABLE) + vmw_bo_dirty_scan_pagetable(vbo); + else + vmw_bo_dirty_scan_mkwrite(vbo); +} + +/** + * vmw_bo_dirty_add - Add a dirty-tracking user to a buffer object + * @vbo: The buffer object + * + * This function registers a dirty-tracking user to a buffer object. + * A user can be for example a resource or a vma in a special user-space + * mapping. + * + * Return: Zero on success, -ENOMEM on memory allocation failure. + */ +int vmw_bo_dirty_add(struct vmw_buffer_object *vbo) +{ + struct vmw_bo_dirty *dirty = vbo->dirty; + pgoff_t num_pages = vbo->base.num_pages; + size_t size, acc_size; + int ret; + static struct ttm_operation_ctx ctx = { + .interruptible = false, + .no_wait_gpu = false + }; + + if (dirty) { + dirty->ref_count++; + return 0; + } + + size = sizeof(*dirty) + BITS_TO_LONGS(num_pages) * sizeof(long); + acc_size = ttm_round_pot(size); + ret = ttm_mem_global_alloc(&ttm_mem_glob, acc_size, &ctx); + if (ret) { + VMW_DEBUG_USER("Out of graphics memory for buffer object " + "dirty tracker.\n"); + return ret; + } + dirty = kvzalloc(size, GFP_KERNEL); + if (!dirty) { + ret = -ENOMEM; + goto out_no_dirty; + } + + dirty->size = acc_size; + dirty->bitmap_size = num_pages; + dirty->start = dirty->bitmap_size; + dirty->end = 0; + dirty->ref_count = 1; + if (num_pages < PAGE_SIZE / sizeof(pte_t)) { + dirty->method = VMW_BO_DIRTY_PAGETABLE; + } else { + struct address_space *mapping = vbo->base.bdev->dev_mapping; + pgoff_t offset = drm_vma_node_start(&vbo->base.vma_node); + + dirty->method = VMW_BO_DIRTY_MKWRITE; + + /* Write-protect and then pick up already dirty bits */ + apply_as_wrprotect(mapping, offset, num_pages); + apply_as_clean(mapping, offset, num_pages, offset, + &dirty->bitmap[0], &dirty->start, &dirty->end); + } + + vbo->dirty = dirty; + + return 0; + +out_no_dirty: + ttm_mem_global_free(&ttm_mem_glob, acc_size); + return ret; +} + +/** + * vmw_bo_dirty_release - Release a dirty-tracking user from a buffer object + * @vbo: The buffer object + * + * This function releases a dirty-tracking user from a buffer object. + * If the reference count reaches zero, then the dirty-tracking object is + * freed and the pointer to it cleared. + * + * Return: Zero on success, -ENOMEM on memory allocation failure. + */ +void vmw_bo_dirty_release(struct vmw_buffer_object *vbo) +{ + struct vmw_bo_dirty *dirty = vbo->dirty; + + if (dirty && --dirty->ref_count == 0) { + size_t acc_size = dirty->size; + + kvfree(dirty); + ttm_mem_global_free(&ttm_mem_glob, acc_size); + vbo->dirty = NULL; + } +} + +/** + * vmw_bo_dirty_transfer_to_res - Pick up a resource's dirty region from + * its backing mob. + * @res: The resource + * + * This function will pick up all dirty ranges affecting the resource from + * it's backup mob, and call vmw_resource_dirty_update() once for each + * range. The transferred ranges will be cleared from the backing mob's + * dirty tracking. + */ +void vmw_bo_dirty_transfer_to_res(struct vmw_resource *res) +{ + struct vmw_buffer_object *vbo = res->backup; + struct vmw_bo_dirty *dirty = vbo->dirty; + pgoff_t start, cur, end; + unsigned long res_start = res->backup_offset; + unsigned long res_end = res->backup_offset + res->backup_size; + + WARN_ON_ONCE(res_start & ~PAGE_MASK); + res_start >>= PAGE_SHIFT; + res_end = DIV_ROUND_UP(res_end, PAGE_SIZE); + + if (res_start >= dirty->end || res_end <= dirty->start) + return; + + cur = max(res_start, dirty->start); + res_end = max(res_end, dirty->end); + while (cur < res_end) { + unsigned long num; + + start = find_next_bit(&dirty->bitmap[0], res_end, cur); + if (start >= res_end) + break; + + end = find_next_zero_bit(&dirty->bitmap[0], res_end, start + 1); + cur = end + 1; + num = end - start; + bitmap_clear(&dirty->bitmap[0], start, num); + vmw_resource_dirty_update(res, start, end); + } + + if (res_start <= dirty->start && res_end > dirty->start) + dirty->start = res_end; + if (res_start < dirty->end && res_end >= dirty->end) + dirty->end = res_start; +} + +/** + * vmw_bo_dirty_clear_res - Clear a resource's dirty region from + * its backing mob. + * @res: The resource + * + * This function will clear all dirty ranges affecting the resource from + * it's backup mob's dirty tracking. + */ +void vmw_bo_dirty_clear_res(struct vmw_resource *res) +{ + unsigned long res_start = res->backup_offset; + unsigned long res_end = res->backup_offset + res->backup_size; + struct vmw_buffer_object *vbo = res->backup; + struct vmw_bo_dirty *dirty = vbo->dirty; + + res_start >>= PAGE_SHIFT; + res_end = DIV_ROUND_UP(res_end, PAGE_SIZE); + + if (res_start >= dirty->end || res_end <= dirty->start) + return; + + res_start = max(res_start, dirty->start); + res_end = min(res_end, dirty->end); + bitmap_clear(&dirty->bitmap[0], res_start, res_end - res_start); + + if (res_start <= dirty->start && res_end > dirty->start) + dirty->start = res_end; + if (res_start < dirty->end && res_end >= dirty->end) + dirty->end = res_start; +} + +vm_fault_t vmw_bo_vm_mkwrite(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct ttm_buffer_object *bo = (struct ttm_buffer_object *) + vma->vm_private_data; + vm_fault_t ret; + unsigned long page_offset; + struct vmw_buffer_object *vbo = + container_of(bo, typeof(*vbo), base); + + ret = ttm_bo_vm_reserve(bo, vmf); + if (ret) + return ret; + + page_offset = vmf->pgoff - drm_vma_node_start(&bo->vma_node); + if (unlikely(page_offset >= bo->num_pages)) { + ret = VM_FAULT_SIGBUS; + goto out_unlock; + } + + if (vbo->dirty && vbo->dirty->method == VMW_BO_DIRTY_MKWRITE && + !test_bit(page_offset, &vbo->dirty->bitmap[0])) { + struct vmw_bo_dirty *dirty = vbo->dirty; + + __set_bit(page_offset, &dirty->bitmap[0]); + dirty->start = min(dirty->start, page_offset); + dirty->end = max(dirty->end, page_offset + 1); + } + +out_unlock: + reservation_object_unlock(bo->resv); + return ret; +} + +vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct ttm_buffer_object *bo = (struct ttm_buffer_object *) + vma->vm_private_data; + struct vmw_buffer_object *vbo = + container_of(bo, struct vmw_buffer_object, base); + pgoff_t num_prefault; + pgprot_t prot; + vm_fault_t ret; + + ret = ttm_bo_vm_reserve(bo, vmf); + if (ret) + return ret; + + /* + * This will cause mkwrite() to be called for each pte on + * write-enable vmas. + */ + if (vbo->dirty && vbo->dirty->method == VMW_BO_DIRTY_MKWRITE) + prot = vma->vm_page_prot; + else + prot = vm_get_page_prot(vma->vm_flags); + + num_prefault = (vma->vm_flags & VM_RAND_READ) ? 0 : + TTM_BO_VM_NUM_PREFAULT; + ret = ttm_bo_vm_fault_reserved(vmf, prot, num_prefault); + if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) + return ret; + + reservation_object_unlock(bo->resv); + return ret; +} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index be7d4149a129..da9afa83fb4f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -121,6 +121,10 @@ static void vmw_resource_release(struct kref *kref) } res->backup_dirty = false; vmw_resource_mob_detach(res); + if (res->dirty) + res->func->dirty_free(res); + if (res->coherent) + vmw_bo_dirty_release(res->backup); ttm_bo_unreserve(bo); vmw_bo_unreference(&res->backup); } @@ -210,7 +214,9 @@ int vmw_resource_init(struct vmw_private *dev_priv, struct vmw_resource *res, res->backup_offset = 0; res->backup_dirty = false; res->res_dirty = false; + res->coherent = false; res->used_prio = 3; + res->dirty = NULL; if (delay_id) return 0; else @@ -397,6 +403,30 @@ static int vmw_resource_do_validate(struct vmw_resource *res, vmw_resource_mob_attach(res); } + /* + * Handle the case where the backup mob is marked coherent but + * the resource isn't. + */ + if (func->dirty_alloc && vmw_resource_mob_attached(res) && + !res->coherent) { + if (res->backup->dirty && !res->dirty) { + ret = func->dirty_alloc(res); + if (ret) + return ret; + } else if (!res->backup->dirty && res->dirty) { + func->dirty_free(res); + } + } + + /* + * Transfer the dirty regions to the resource and update + * the resource. + */ + if (res->dirty) { + vmw_bo_dirty_transfer_to_res(res); + return func->dirty_sync(res); + } + return 0; out_bind_failed: @@ -435,16 +465,28 @@ void vmw_resource_unreserve(struct vmw_resource *res, if (switch_backup && new_backup != res->backup) { if (res->backup) { vmw_resource_mob_detach(res); + if (res->coherent) + vmw_bo_dirty_release(res->backup); vmw_bo_unreference(&res->backup); } if (new_backup) { res->backup = vmw_bo_reference(new_backup); + + /* + * The validation code should already have added a + * dirty tracker here. + */ + WARN_ON(res->coherent && !new_backup->dirty); + vmw_resource_mob_attach(res); } else { res->backup = NULL; } + } else if (switch_backup && res->coherent) { + vmw_bo_dirty_release(res->backup); } + if (switch_backup) res->backup_offset = new_backup_offset; @@ -1010,3 +1052,18 @@ enum vmw_res_type vmw_res_type(const struct vmw_resource *res) { return res->func->res_type; } + +/** + * vmw_resource_update_dirty - Update a resource's dirty tracker with a + * sequential range of touched backing store memory. + * @res: The resource. + * @start: The first page touched. + * @end: The last page touched + 1. + */ +void vmw_resource_dirty_update(struct vmw_resource *res, pgoff_t start, + pgoff_t end) +{ + if (res->dirty) + res->func->dirty_range_add(res, start << PAGE_SHIFT, + end << PAGE_SHIFT); +} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h index 984e588c62ca..c85144286cfe 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h @@ -71,6 +71,12 @@ struct vmw_user_resource_conv { * @commit_notify: If the resource is a command buffer managed resource, * callback to notify that a define or remove command * has been committed to the device. + * @dirty_alloc: Allocate a dirty tracker. NULL if dirty-tracking is not + * supported. + * @dirty_free: Free the dirty tracker. + * @dirty_sync: Upload the dirty mob contents to the resource. + * @dirty_add_range: Add a sequential dirty range to the resource + * dirty tracker. */ struct vmw_res_func { enum vmw_res_type res_type; @@ -90,6 +96,11 @@ struct vmw_res_func { struct ttm_validate_buffer *val_buf); void (*commit_notify)(struct vmw_resource *res, enum vmw_cmdbuf_res_state state); + int (*dirty_alloc)(struct vmw_resource *res); + void (*dirty_free)(struct vmw_resource *res); + int (*dirty_sync)(struct vmw_resource *res); + void (*dirty_range_add)(struct vmw_resource *res, size_t start, + size_t end); }; /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c index f611b2290a1b..71349a7bae90 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c @@ -33,6 +33,8 @@ * struct vmw_validation_bo_node - Buffer object validation metadata. * @base: Metadata used for TTM reservation- and validation. * @hash: A hash entry used for the duplicate detection hash table. + * @coherent_count: If switching backup buffers, number of new coherent + * resources that will have this buffer as a backup buffer. * @as_mob: Validate as mob. * @cpu_blit: Validate for cpu blit access. * @@ -42,6 +44,7 @@ struct vmw_validation_bo_node { struct ttm_validate_buffer base; struct drm_hash_item hash; + unsigned int coherent_count; u32 as_mob : 1; u32 cpu_blit : 1; }; @@ -459,6 +462,19 @@ int vmw_validation_res_reserve(struct vmw_validation_context *ctx, if (ret) goto out_unreserve; } + + if (val->switching_backup && val->new_backup && + res->coherent) { + struct vmw_validation_bo_node *bo_node = + vmw_validation_find_bo_dup(ctx, + val->new_backup); + + if (WARN_ON(!bo_node)) { + ret = -EINVAL; + goto out_unreserve; + } + bo_node->coherent_count++; + } } return 0; @@ -562,6 +578,9 @@ int vmw_validation_bo_validate(struct vmw_validation_context *ctx, bool intr) int ret; list_for_each_entry(entry, &ctx->bo_list, base.head) { + struct vmw_buffer_object *vbo = + container_of(entry->base.bo, typeof(*vbo), base); + if (entry->cpu_blit) { struct ttm_operation_ctx ctx = { .interruptible = intr, @@ -576,6 +595,27 @@ int vmw_validation_bo_validate(struct vmw_validation_context *ctx, bool intr) } if (ret) return ret; + + /* + * Rather than having the resource code allocating the bo + * dirty tracker in resource_unreserve() where we can't fail, + * Do it here when validating the buffer object. + */ + if (entry->coherent_count) { + unsigned int coherent_count = entry->coherent_count; + + while (coherent_count) { + ret = vmw_bo_dirty_add(vbo); + if (ret) + return ret; + + coherent_count--; + } + entry->coherent_count -= coherent_count; + } + + if (vbo->dirty) + vmw_bo_dirty_scan(vbo); } return 0; } @@ -828,3 +868,34 @@ int vmw_validation_preload_res(struct vmw_validation_context *ctx, ctx->mem_size_left += size; return 0; } + +/** + * vmw_validation_bo_backoff - Unreserve buffer objects registered with a + * validation context + * @ctx: The validation context + * + * This function unreserves the buffer objects previously reserved using + * vmw_validation_bo_reserve. It's typically used as part of an error path + */ +void vmw_validation_bo_backoff(struct vmw_validation_context *ctx) +{ + struct vmw_validation_bo_node *entry; + + /* + * Switching coherent resource backup buffers failed. + * Release corresponding buffer object dirty trackers. + */ + list_for_each_entry(entry, &ctx->bo_list, base.head) { + if (entry->coherent_count) { + unsigned int coherent_count = entry->coherent_count; + struct vmw_buffer_object *vbo = + container_of(entry->base.bo, typeof(*vbo), + base); + + while (coherent_count--) + vmw_bo_dirty_release(vbo); + } + } + + ttm_eu_backoff_reservation(&ctx->ticket, &ctx->bo_list); +} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h index 1d2322ad6fd5..fd83e017c2a5 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h @@ -172,20 +172,6 @@ vmw_validation_bo_reserve(struct vmw_validation_context *ctx, NULL, true); } -/** - * vmw_validation_bo_backoff - Unreserve buffer objects registered with a - * validation context - * @ctx: The validation context - * - * This function unreserves the buffer objects previously reserved using - * vmw_validation_bo_reserve. It's typically used as part of an error path - */ -static inline void -vmw_validation_bo_backoff(struct vmw_validation_context *ctx) -{ - ttm_eu_backoff_reservation(&ctx->ticket, &ctx->bo_list); -} - /** * vmw_validation_bo_fence - Unreserve and fence buffer objects registered * with a validation context @@ -268,4 +254,6 @@ int vmw_validation_preload_res(struct vmw_validation_context *ctx, unsigned int size); void vmw_validation_res_set_dirty(struct vmw_validation_context *ctx, void *val_private, u32 dirty); +void vmw_validation_bo_backoff(struct vmw_validation_context *ctx); + #endif -- cgit v1.2.3 From 86aeaa09f3dfc43c89ae45e62f9b1b7f705c90e4 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Tue, 5 Mar 2019 08:24:35 +0100 Subject: drm/vmwgfx: Use an RBtree instead of linked list for MOB resources With emulated coherent memory we need to be able to quickly look up a resource from the MOB offset. Instead of traversing a linked list with O(n) worst case, use an RBtree with O(log n) worst case complexity. Signed-off-by: Thomas Hellstrom Reviewed-by: Deepak Rawat --- drivers/gpu/drm/vmwgfx/vmwgfx_bo.c | 5 +++-- drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 10 +++++----- drivers/gpu/drm/vmwgfx/vmwgfx_resource.c | 33 +++++++++++++++++++++++--------- 3 files changed, 32 insertions(+), 16 deletions(-) (limited to 'drivers/gpu/drm') diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 90ca866640fe..e8bc7a7ac031 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -464,6 +464,7 @@ void vmw_bo_bo_free(struct ttm_buffer_object *bo) struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo); WARN_ON(vmw_bo->dirty); + WARN_ON(!RB_EMPTY_ROOT(&vmw_bo->res_tree)); vmw_bo_unmap(vmw_bo); kfree(vmw_bo); } @@ -480,6 +481,7 @@ static void vmw_user_bo_destroy(struct ttm_buffer_object *bo) struct vmw_buffer_object *vbo = &vmw_user_bo->vbo; WARN_ON(vbo->dirty); + WARN_ON(!RB_EMPTY_ROOT(&vbo->res_tree)); vmw_bo_unmap(vbo); ttm_prime_object_kfree(vmw_user_bo, prime); } @@ -515,8 +517,7 @@ int vmw_bo_init(struct vmw_private *dev_priv, memset(vmw_bo, 0, sizeof(*vmw_bo)); BUILD_BUG_ON(TTM_MAX_BO_PRIORITY <= 3); vmw_bo->base.priority = 3; - - INIT_LIST_HEAD(&vmw_bo->res_list); + vmw_bo->res_tree = RB_ROOT; ret = ttm_bo_init(bdev, &vmw_bo->base, size, ttm_bo_type_device, placement, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 27c259395790..9b347923196f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -89,7 +89,7 @@ struct vmw_fpriv { /** * struct vmw_buffer_object - TTM buffer object with vmwgfx additions * @base: The TTM buffer object - * @res_list: List of resources using this buffer object as a backing MOB + * @res_tree: RB tree of resources using this buffer object as a backing MOB * @pin_count: pin depth * @dx_query_ctx: DX context if this buffer object is used as a DX query MOB * @map: Kmap object for semi-persistent mappings @@ -98,7 +98,7 @@ struct vmw_fpriv { */ struct vmw_buffer_object { struct ttm_buffer_object base; - struct list_head res_list; + struct rb_root res_tree; s32 pin_count; /* Not ref-counted. Protected by binding_mutex */ struct vmw_resource *dx_query_ctx; @@ -146,8 +146,8 @@ struct vmw_res_func; * pin-count greater than zero. It is not on the resource LRU lists and its * backup buffer is pinned. Hence it can't be evicted. * @func: Method vtable for this resource. Immutable. + * @mob_node; Node for the MOB backup rbtree. Protected by @backup reserved. * @lru_head: List head for the LRU list. Protected by @dev_priv::resource_lock. - * @mob_head: List head for the MOB backup list. Protected by @backup reserved. * @binding_head: List head for the context binding list. Protected by * the @dev_priv::binding_mutex * @res_free: The resource destructor. @@ -168,8 +168,8 @@ struct vmw_resource { unsigned long backup_offset; unsigned long pin_count; const struct vmw_res_func *func; + struct rb_node mob_node; struct list_head lru_head; - struct list_head mob_head; struct list_head binding_head; struct vmw_resource_dirty *dirty; void (*res_free) (struct vmw_resource *res); @@ -742,7 +742,7 @@ void vmw_resource_dirty_update(struct vmw_resource *res, pgoff_t start, */ static inline bool vmw_resource_mob_attached(const struct vmw_resource *res) { - return !list_empty(&res->mob_head); + return !RB_EMPTY_NODE(&res->mob_node); } /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index da9afa83fb4f..b84dd5953886 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -41,11 +41,24 @@ void vmw_resource_mob_attach(struct vmw_resource *res) { struct vmw_buffer_object *backup = res->backup; + struct rb_node **new = &backup->res_tree.rb_node, *parent = NULL; lockdep_assert_held(&backup->base.resv->lock.base); res->used_prio = (res->res_dirty) ? res->func->dirty_prio : res->func->prio; - list_add_tail(&res->mob_head, &backup->res_list); + + while (*new) { + struct vmw_resource *this = + container_of(*new, struct vmw_resource, mob_node); + + parent = *new; + new = (res->backup_offset < this->backup_offset) ? + &((*new)->rb_left) : &((*new)->rb_right); + } + + rb_link_node(&res->mob_node, parent, new); + rb_insert_color(&res->mob_node, &backup->res_tree); + vmw_bo_prio_add(backup, res->used_prio); } @@ -59,7 +72,8 @@ void vmw_resource_mob_detach(struct vmw_resource *res) lockdep_assert_held(&backup->base.resv->lock.base); if (vmw_resource_mob_attached(res)) { - list_del_init(&res->mob_head); + rb_erase(&res->mob_node, &backup->res_tree); + RB_CLEAR_NODE(&res->mob_node); vmw_bo_prio_del(backup, res->used_prio); } } @@ -206,8 +220,8 @@ int vmw_resource_init(struct vmw_private *dev_priv, struct vmw_resource *res, res->res_free = res_free; res->dev_priv = dev_priv; res->func = func; + RB_CLEAR_NODE(&res->mob_node); INIT_LIST_HEAD(&res->lru_head); - INIT_LIST_HEAD(&res->mob_head); INIT_LIST_HEAD(&res->binding_head); res->id = -1; res->backup = NULL; @@ -756,19 +770,20 @@ out_no_validate: */ void vmw_resource_unbind_list(struct vmw_buffer_object *vbo) { - - struct vmw_resource *res, *next; struct ttm_validate_buffer val_buf = { .bo = &vbo->base, .num_shared = 0 }; lockdep_assert_held(&vbo->base.resv->lock.base); - list_for_each_entry_safe(res, next, &vbo->res_list, mob_head) { - if (!res->func->unbind) - continue; + while (!RB_EMPTY_ROOT(&vbo->res_tree)) { + struct rb_node *node = vbo->res_tree.rb_node; + struct vmw_resource *res = + container_of(node, struct vmw_resource, mob_node); + + if (!WARN_ON_ONCE(!res->func->unbind)) + (void) res->func->unbind(res, res->res_dirty, &val_buf); - (void) res->func->unbind(res, res->res_dirty, &val_buf); res->backup_dirty = true; res->res_dirty = false; vmw_resource_mob_detach(res); -- cgit v1.2.3 From d58e3b087b76381ab8460a5bbfa6bd60047df860 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Thu, 28 Mar 2019 11:36:25 +0100 Subject: drm/vmwgfx: Implement an infrastructure for read-coherent resources Similar to write-coherent resources, make sure that from the user-space point of view, GPU rendered contents is automatically available for reading by the CPU. Signed-off-by: Thomas Hellstrom Reviewed-by: Deepak Rawat --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 7 +- drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c | 73 ++++++++++++++++-- drivers/gpu/drm/vmwgfx/vmwgfx_resource.c | 103 +++++++++++++++++++++++++- drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h | 2 + drivers/gpu/drm/vmwgfx/vmwgfx_validation.c | 3 +- 5 files changed, 177 insertions(+), 11 deletions(-) (limited to 'drivers/gpu/drm') diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 9b347923196f..dae3a39bf402 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -689,7 +689,8 @@ extern void vmw_resource_unreference(struct vmw_resource **p_res); extern struct vmw_resource *vmw_resource_reference(struct vmw_resource *res); extern struct vmw_resource * vmw_resource_reference_unless_doomed(struct vmw_resource *res); -extern int vmw_resource_validate(struct vmw_resource *res, bool intr); +extern int vmw_resource_validate(struct vmw_resource *res, bool intr, + bool dirtying); extern int vmw_resource_reserve(struct vmw_resource *res, bool interruptible, bool no_backup); extern bool vmw_resource_needs_backup(const struct vmw_resource *res); @@ -733,6 +734,8 @@ void vmw_resource_mob_attach(struct vmw_resource *res); void vmw_resource_mob_detach(struct vmw_resource *res); void vmw_resource_dirty_update(struct vmw_resource *res, pgoff_t start, pgoff_t end); +int vmw_resources_clean(struct vmw_buffer_object *vbo, pgoff_t start, + pgoff_t end, pgoff_t *num_prefault); /** * vmw_resource_mob_attached - Whether a resource currently has a mob attached @@ -1427,6 +1430,8 @@ int vmw_bo_dirty_add(struct vmw_buffer_object *vbo); void vmw_bo_dirty_transfer_to_res(struct vmw_resource *res); void vmw_bo_dirty_clear_res(struct vmw_resource *res); void vmw_bo_dirty_release(struct vmw_buffer_object *vbo); +void vmw_bo_dirty_unmap(struct vmw_buffer_object *vbo, + pgoff_t start, pgoff_t end); vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf); vm_fault_t vmw_bo_vm_mkwrite(struct vm_fault *vmf); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c index 8d154f90bdc0..730c51e397dd 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c @@ -153,7 +153,6 @@ static void vmw_bo_dirty_scan_mkwrite(struct vmw_buffer_object *vbo) } } - /** * vmw_bo_dirty_scan - Scan for dirty pages and add them to the dirty * tracking structure @@ -171,6 +170,51 @@ void vmw_bo_dirty_scan(struct vmw_buffer_object *vbo) vmw_bo_dirty_scan_mkwrite(vbo); } +/** + * vmw_bo_dirty_pre_unmap - write-protect and pick up dirty pages before + * an unmap_mapping_range operation. + * @vbo: The buffer object, + * @start: First page of the range within the buffer object. + * @end: Last page of the range within the buffer object + 1. + * + * If we're using the _PAGETABLE scan method, we may leak dirty pages + * when calling unmap_mapping_range(). This function makes sure we pick + * up all dirty pages. + */ +static void vmw_bo_dirty_pre_unmap(struct vmw_buffer_object *vbo, + pgoff_t start, pgoff_t end) +{ + struct vmw_bo_dirty *dirty = vbo->dirty; + unsigned long offset = drm_vma_node_start(&vbo->base.vma_node); + struct address_space *mapping = vbo->base.bdev->dev_mapping; + + if (dirty->method != VMW_BO_DIRTY_PAGETABLE || start >= end) + return; + + apply_as_wrprotect(mapping, start + offset, end - start); + apply_as_clean(mapping, start + offset, end - start, offset, + &dirty->bitmap[0], &dirty->start, &dirty->end); +} + +/** + * vmw_bo_dirty_unmap - Clear all ptes pointing to a range within a bo + * @vbo: The buffer object, + * @start: First page of the range within the buffer object. + * @end: Last page of the range within the buffer object + 1. + * + * This is similar to ttm_bo_unmap_virtual_locked() except it takes a subrange. + */ +void vmw_bo_dirty_unmap(struct vmw_buffer_object *vbo, + pgoff_t start, pgoff_t end) +{ + unsigned long offset = drm_vma_node_start(&vbo->base.vma_node); + struct address_space *mapping = vbo->base.bdev->dev_mapping; + + vmw_bo_dirty_pre_unmap(vbo, start, end); + unmap_shared_mapping_range(mapping, (offset + start) << PAGE_SHIFT, + (loff_t) (end - start) << PAGE_SHIFT); +} + /** * vmw_bo_dirty_add - Add a dirty-tracking user to a buffer object * @vbo: The buffer object @@ -389,21 +433,40 @@ vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf) if (ret) return ret; + num_prefault = (vma->vm_flags & VM_RAND_READ) ? 1 : + TTM_BO_VM_NUM_PREFAULT; + + if (vbo->dirty) { + pgoff_t allowed_prefault; + unsigned long page_offset; + + page_offset = vmf->pgoff - drm_vma_node_start(&bo->vma_node); + if (page_offset >= bo->num_pages || + vmw_resources_clean(vbo, page_offset, + page_offset + PAGE_SIZE, + &allowed_prefault)) { + ret = VM_FAULT_SIGBUS; + goto out_unlock; + } + + num_prefault = min(num_prefault, allowed_prefault); + } + /* - * This will cause mkwrite() to be called for each pte on - * write-enable vmas. + * If we don't track dirty using the MKWRITE method, make sure + * sure the page protection is write-enabled so we don't get + * a lot of unnecessary write faults. */ if (vbo->dirty && vbo->dirty->method == VMW_BO_DIRTY_MKWRITE) prot = vma->vm_page_prot; else prot = vm_get_page_prot(vma->vm_flags); - num_prefault = (vma->vm_flags & VM_RAND_READ) ? 0 : - TTM_BO_VM_NUM_PREFAULT; ret = ttm_bo_vm_fault_reserved(vmf, prot, num_prefault); if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) return ret; +out_unlock: reservation_object_unlock(bo->resv); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index b84dd5953886..d70ee0df5c13 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -395,7 +395,8 @@ out_no_bo: * should be retried once resources have been freed up. */ static int vmw_resource_do_validate(struct vmw_resource *res, - struct ttm_validate_buffer *val_buf) + struct ttm_validate_buffer *val_buf, + bool dirtying) { int ret = 0; const struct vmw_res_func *func = res->func; @@ -437,6 +438,15 @@ static int vmw_resource_do_validate(struct vmw_resource *res, * the resource. */ if (res->dirty) { + if (dirtying && !res->res_dirty) { + pgoff_t start = res->backup_offset >> PAGE_SHIFT; + pgoff_t end = __KERNEL_DIV_ROUND_UP + (res->backup_offset + res->backup_size, + PAGE_SIZE); + + vmw_bo_dirty_unmap(res->backup, start, end); + } + vmw_bo_dirty_transfer_to_res(res); return func->dirty_sync(res); } @@ -681,6 +691,7 @@ out_no_unbind: * to the device. * @res: The resource to make visible to the device. * @intr: Perform waits interruptible if possible. + * @dirtying: Pending GPU operation will dirty the resource * * On succesful return, any backup DMA buffer pointed to by @res->backup will * be reserved and validated. @@ -690,7 +701,8 @@ out_no_unbind: * Return: Zero on success, -ERESTARTSYS if interrupted, negative error code * on failure. */ -int vmw_resource_validate(struct vmw_resource *res, bool intr) +int vmw_resource_validate(struct vmw_resource *res, bool intr, + bool dirtying) { int ret; struct vmw_resource *evict_res; @@ -707,7 +719,7 @@ int vmw_resource_validate(struct vmw_resource *res, bool intr) if (res->backup) val_buf.bo = &res->backup->base; do { - ret = vmw_resource_do_validate(res, &val_buf); + ret = vmw_resource_do_validate(res, &val_buf, dirtying); if (likely(ret != -EBUSY)) break; @@ -1007,7 +1019,7 @@ int vmw_resource_pin(struct vmw_resource *res, bool interruptible) /* Do we really need to pin the MOB as well? */ vmw_bo_pin_reserved(vbo, true); } - ret = vmw_resource_validate(res, interruptible); + ret = vmw_resource_validate(res, interruptible, true); if (vbo) ttm_bo_unreserve(&vbo->base); if (ret) @@ -1082,3 +1094,86 @@ void vmw_resource_dirty_update(struct vmw_resource *res, pgoff_t start, res->func->dirty_range_add(res, start << PAGE_SHIFT, end << PAGE_SHIFT); } + +/** + * vmw_resources_clean - Clean resources intersecting a mob range + * @vbo: The mob buffer object + * @start: The mob page offset starting the range + * @end: The mob page offset ending the range + * @num_prefault: Returns how many pages including the first have been + * cleaned and are ok to prefault + */ +int vmw_resources_clean(struct vmw_buffer_object *vbo, pgoff_t start, + pgoff_t end, pgoff_t *num_prefault) +{ + struct rb_node *cur = vbo->res_tree.rb_node; + struct vmw_resource *found = NULL; + unsigned long res_start = start << PAGE_SHIFT; + unsigned long res_end = end << PAGE_SHIFT; + unsigned long last_cleaned = 0; + + /* + * Find the resource with lowest backup_offset that intersects the + * range. + */ + while (cur) { + struct vmw_resource *cur_res = + container_of(cur, struct vmw_resource, mob_node); + + if (cur_res->backup_offset >= res_end) { + cur = cur->rb_left; + } else if (cur_res->backup_offset + cur_res->backup_size <= + res_start) { + cur = cur->rb_right; + } else { + found = cur_res; + cur = cur->rb_left; + /* Continue to look for resources with lower offsets */ + } + } + + /* + * In order of increasing backup_offset, clean dirty resorces + * intersecting the range. + */ + while (found) { + if (found->res_dirty) { + int ret; + + if (!found->func->clean) + return -EINVAL; + + ret = found->func->clean(found); + if (ret) + return ret; + + found->res_dirty = false; + } + last_cleaned = found->backup_offset + found->backup_size; + cur = rb_next(&found->mob_node); + if (!cur) + break; + + found = container_of(cur, struct vmw_resource, mob_node); + if (found->backup_offset >= res_end) + break; + } + + /* + * Set number of pages allowed prefaulting and fence the buffer object + */ + *num_prefault = 1; + if (last_cleaned > res_start) { + struct ttm_buffer_object *bo = &vbo->base; + + *num_prefault = __KERNEL_DIV_ROUND_UP(last_cleaned - res_start, + PAGE_SIZE); + vmw_bo_fence_single(bo, NULL); + if (bo->moving) + dma_fence_put(bo->moving); + bo->moving = dma_fence_get + (reservation_object_get_excl(bo->resv)); + } + + return 0; +} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h index c85144286cfe..3b7438b2d289 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h @@ -77,6 +77,7 @@ struct vmw_user_resource_conv { * @dirty_sync: Upload the dirty mob contents to the resource. * @dirty_add_range: Add a sequential dirty range to the resource * dirty tracker. + * @clean: Clean the resource. */ struct vmw_res_func { enum vmw_res_type res_type; @@ -101,6 +102,7 @@ struct vmw_res_func { int (*dirty_sync)(struct vmw_resource *res); void (*dirty_range_add)(struct vmw_resource *res, size_t start, size_t end); + int (*clean)(struct vmw_resource *res); }; /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c index 71349a7bae90..9aaf807ed73c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c @@ -641,7 +641,8 @@ int vmw_validation_res_validate(struct vmw_validation_context *ctx, bool intr) struct vmw_resource *res = val->res; struct vmw_buffer_object *backup = res->backup; - ret = vmw_resource_validate(res, intr); + ret = vmw_resource_validate(res, intr, val->dirty_set && + val->dirty); if (ret) { if (ret != -ERESTARTSYS) DRM_ERROR("Failed to validate resource.\n"); -- cgit v1.2.3 From 4ba397671237784a212378c271f700e99c66cf39 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Tue, 19 Mar 2019 13:27:50 +0100 Subject: drm/vmwgfx: Add surface dirty-tracking callbacks Add the callbacks necessary to implement emulated coherent memory for surfaces. Add a flag to the gb_surface_create ioctl to indicate that surface memory should be coherent. Also bump the drm minor version to signal the availability of coherent surfaces. Signed-off-by: Thomas Hellstrom Reviewed-by: Deepak Rawat --- .../drm/vmwgfx/device_include/svga3d_surfacedefs.h | 233 +++++++++++- drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 4 +- drivers/gpu/drm/vmwgfx/vmwgfx_surface.c | 395 ++++++++++++++++++++- include/uapi/drm/vmwgfx_drm.h | 4 +- 4 files changed, 629 insertions(+), 7 deletions(-) (limited to 'drivers/gpu/drm') diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h index f2bfd3d80598..61414f105c67 100644 --- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h +++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h @@ -1280,7 +1280,6 @@ svga3dsurface_get_pixel_offset(SVGA3dSurfaceFormat format, return offset; } - static inline u32 svga3dsurface_get_image_offset(SVGA3dSurfaceFormat format, surf_size_struct baseLevelSize, @@ -1375,4 +1374,236 @@ svga3dsurface_is_screen_target_format(SVGA3dSurfaceFormat format) return svga3dsurface_is_dx_screen_target_format(format); } +/** + * struct svga3dsurface_mip - Mimpmap level information + * @bytes: Bytes required in the backing store of this mipmap level. + * @img_stride: Byte stride per image. + * @row_stride: Byte stride per block row. + * @size: The size of the mipmap. + */ +struct svga3dsurface_mip { + size_t bytes; + size_t img_stride; + size_t row_stride; + struct drm_vmw_size size; + +}; + +/** + * struct svga3dsurface_cache - Cached surface information + * @desc: Pointer to the surface descriptor + * @mip: Array of mipmap level information. Valid size is @num_mip_levels. + * @mip_chain_bytes: Bytes required in the backing store for the whole chain + * of mip levels. + * @sheet_bytes: Bytes required in the backing store for a sheet + * representing a single sample. + * @num_mip_levels: Valid size of the @mip array. Number of mipmap levels in + * a chain. + * @num_layers: Number of slices in an array texture or number of faces in + * a cubemap texture. + */ +struct svga3dsurface_cache { + const struct svga3d_surface_desc *desc; + struct svga3dsurface_mip mip[DRM_VMW_MAX_MIP_LEVELS]; + size_t mip_chain_bytes; + size_t sheet_bytes; + u32 num_mip_levels; + u32 num_layers; +}; + +/** + * struct svga3dsurface_loc - Surface location + * @sub_resource: Surface subresource. Defined as layer * num_mip_levels + + * mip_level. + * @x: X coordinate. + * @y: Y coordinate. + * @z: Z coordinate. + */ +struct svga3dsurface_loc { + u32 sub_resource; + u32 x, y, z; +}; + +/** + * svga3dsurface_subres - Compute the subresource from layer and mipmap. + * @cache: Surface layout data. + * @mip_level: The mipmap level. + * @layer: The surface layer (face or array slice). + * + * Return: The subresource. + */ +static inline u32 svga3dsurface_subres(const struct svga3dsurface_cache *cache, + u32 mip_level, u32 layer) +{ + return cache->num_mip_levels * layer + mip_level; +} + +/** + * svga3dsurface_setup_cache - Build a surface cache entry + * @size: The surface base level dimensions. + * @format: The surface format. + * @num_mip_levels: Number of mipmap levels. + * @num_layers: Number of layers. + * @cache: Pointer to a struct svga3dsurface_cach object to be filled in. + * + * Return: Zero on success, -EINVAL on invalid surface layout. + */ +static inline int svga3dsurface_setup_cache(const struct drm_vmw_size *size, + SVGA3dSurfaceFormat format, + u32 num_mip_levels, + u32 num_layers, + u32 num_samples, + struct svga3dsurface_cache *cache) +{ + const struct svga3d_surface_desc *desc; + u32 i; + + memset(cache, 0, sizeof(*cache)); + cache->desc = desc = svga3dsurface_get_desc(format); + cache->num_mip_levels = num_mip_levels; + cache->num_layers = num_layers; + for (i = 0; i < cache->num_mip_levels; i++) { + struct svga3dsurface_mip *mip = &cache->mip[i]; + + mip->size = svga3dsurface_get_mip_size(*size, i); + mip->bytes = svga3dsurface_get_image_buffer_size + (desc, &mip->size, 0); + mip->row_stride = + __KERNEL_DIV_ROUND_UP(mip->size.width, + desc->block_size.width) * + desc->bytes_per_block * num_samples; + if (!mip->row_stride) + goto invalid_dim; + + mip->img_stride = + __KERNEL_DIV_ROUND_UP(mip->size.height, + desc->block_size.height) * + mip->row_stride; + if (!mip->img_stride) + goto invalid_dim; + + cache->mip_chain_bytes += mip->bytes; + } + cache->sheet_bytes = cache->mip_chain_bytes * num_layers; + if (!cache->sheet_bytes) + goto invalid_dim; + + return 0; + +invalid_dim: + VMW_DEBUG_USER("Invalid surface layout for dirty tracking.\n"); + return -EINVAL; +} + +/** + * svga3dsurface_get_loc - Get a surface location from an offset into the + * backing store + * @cache: Surface layout data. + * @loc: Pointer to a struct svga3dsurface_loc to be filled in. + * @offset: Offset into the surface backing store. + */ +static inline void +svga3dsurface_get_loc(const struct svga3dsurface_cache *cache, + struct svga3dsurface_loc *loc, + size_t offset) +{ + const struct svga3dsurface_mip *mip = &cache->mip[0]; + const struct svga3d_surface_desc *desc = cache->desc; + u32 layer; + int i; + + if (offset >= cache->sheet_bytes) + offset %= cache->sheet_bytes; + + layer = offset / cache->mip_chain_bytes; + offset -= layer * cache->mip_chain_bytes; + for (i = 0; i < cache->num_mip_levels; ++i, ++mip) { + if (mip->bytes > offset) + break; + offset -= mip->bytes; + } + + loc->sub_resource = svga3dsurface_subres(cache, i, layer); + loc->z = offset / mip->img_stride; + offset -= loc->z * mip->img_stride; + loc->z *= desc->block_size.depth; + loc->y = offset / mip->row_stride; + offset -= loc->y * mip->row_stride; + loc->y *= desc->block_size.height; + loc->x = offset / desc->bytes_per_block; + loc->x *= desc->block_size.width; +} + +/** + * svga3dsurface_inc_loc - Clamp increment a surface location with one block + * size + * in each dimension. + * @loc: Pointer to a struct svga3dsurface_loc to be incremented. + * + * When computing the size of a range as size = end - start, the range does not + * include the end element. However a location representing the last byte + * of a touched region in the backing store *is* included in the range. + * This function modifies such a location to match the end definition + * given as start + size which is the one used in a SVGA3dBox. + */ +static inline void +svga3dsurface_inc_loc(const struct svga3dsurface_cache *cache, + struct svga3dsurface_loc *loc) +{ + const struct svga3d_surface_desc *desc = cache->desc; + u32 mip = loc->sub_resource % cache->num_mip_levels; + const struct drm_vmw_size *size = &cache->mip[mip].size; + + loc->sub_resource++; + loc->x += desc->block_size.width; + if (loc->x > size->width) + loc->x = size->width; + loc->y += desc->block_size.height; + if (loc->y > size->height) + loc->y = size->height; + loc->z += desc->block_size.depth; + if (loc->z > size->depth) + loc->z = size->depth; +} + +/** + * svga3dsurface_min_loc - The start location in a subresource + * @cache: Surface layout data. + * @sub_resource: The subresource. + * @loc: Pointer to a struct svga3dsurface_loc to be filled in. + */ +static inline void +svga3dsurface_min_loc(const struct svga3dsurface_cache *cache, + u32 sub_resource, + struct svga3dsurface_loc *loc) +{ + loc->sub_resource = sub_resource; + loc->x = loc->y = loc->z = 0; +} + +/** + * svga3dsurface_min_loc - The end location in a subresource + * @cache: Surface layout data. + * @sub_resource: The subresource. + * @loc: Pointer to a struct svga3dsurface_loc to be filled in. + * + * Following the end definition given in svga3dsurface_inc_loc(), + * Compute the end location of a surface subresource. + */ +static inline void +svga3dsurface_max_loc(const struct svga3dsurface_cache *cache, + u32 sub_resource, + struct svga3dsurface_loc *loc) +{ + const struct drm_vmw_size *size; + u32 mip; + + loc->sub_resource = sub_resource + 1; + mip = sub_resource % cache->num_mip_levels; + size = &cache->mip[mip].size; + loc->x = size->width; + loc->y = size->height; + loc->z = size->depth; +} + #endif /* _SVGA3D_SURFACEDEFS_H_ */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index dae3a39bf402..5971c0d47507 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -44,9 +44,9 @@ #include #define VMWGFX_DRIVER_NAME "vmwgfx" -#define VMWGFX_DRIVER_DATE "20180704" +#define VMWGFX_DRIVER_DATE "20190328" #define VMWGFX_DRIVER_MAJOR 2 -#define VMWGFX_DRIVER_MINOR 15 +#define VMWGFX_DRIVER_MINOR 16 #define VMWGFX_DRIVER_PATCHLEVEL 0 #define VMWGFX_FIFO_STATIC_SIZE (1024*1024) #define VMWGFX_MAX_RELOCATIONS 2048 diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index c40d44f4d9af..637043f1befa 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -68,6 +68,20 @@ struct vmw_surface_offset { uint32_t bo_offset; }; +/** + * vmw_surface_dirty - Surface dirty-tracker + * @cache: Cached layout information of the surface. + * @size: Accounting size for the struct vmw_surface_dirty. + * @num_subres: Number of subresources. + * @boxes: Array of SVGA3dBoxes indicating dirty regions. One per subresource. + */ +struct vmw_surface_dirty { + struct svga3dsurface_cache cache; + size_t size; + u32 num_subres; + SVGA3dBox boxes[0]; +}; + static void vmw_user_surface_free(struct vmw_resource *res); static struct vmw_resource * vmw_user_surface_base_to_res(struct ttm_base_object *base); @@ -96,6 +110,13 @@ vmw_gb_surface_reference_internal(struct drm_device *dev, struct drm_vmw_gb_surface_ref_ext_rep *rep, struct drm_file *file_priv); +static void vmw_surface_dirty_free(struct vmw_resource *res); +static int vmw_surface_dirty_alloc(struct vmw_resource *res); +static int vmw_surface_dirty_sync(struct vmw_resource *res); +static void vmw_surface_dirty_range_add(struct vmw_resource *res, size_t start, + size_t end); +static int vmw_surface_clean(struct vmw_resource *res); + static const struct vmw_user_resource_conv user_surface_conv = { .object_type = VMW_RES_SURFACE, .base_obj_to_res = vmw_user_surface_base_to_res, @@ -133,7 +154,12 @@ static const struct vmw_res_func vmw_gb_surface_func = { .create = vmw_gb_surface_create, .destroy = vmw_gb_surface_destroy, .bind = vmw_gb_surface_bind, - .unbind = vmw_gb_surface_unbind + .unbind = vmw_gb_surface_unbind, + .dirty_alloc = vmw_surface_dirty_alloc, + .dirty_free = vmw_surface_dirty_free, + .dirty_sync = vmw_surface_dirty_sync, + .dirty_range_add = vmw_surface_dirty_range_add, + .clean = vmw_surface_clean, }; /** @@ -641,6 +667,7 @@ static void vmw_user_surface_free(struct vmw_resource *res) struct vmw_private *dev_priv = srf->res.dev_priv; uint32_t size = user_srf->size; + WARN_ON_ONCE(res->dirty); if (user_srf->master) drm_master_put(&user_srf->master); kfree(srf->offsets); @@ -1174,10 +1201,16 @@ static int vmw_gb_surface_bind(struct vmw_resource *res, cmd2->header.id = SVGA_3D_CMD_UPDATE_GB_SURFACE; cmd2->header.size = sizeof(cmd2->body); cmd2->body.sid = res->id; - res->backup_dirty = false; } vmw_fifo_commit(dev_priv, submit_size); + if (res->backup->dirty && res->backup_dirty) { + /* We've just made a full upload. Cear dirty regions. */ + vmw_bo_dirty_clear_res(res); + } + + res->backup_dirty = false; + return 0; } @@ -1642,7 +1675,8 @@ vmw_gb_surface_define_internal(struct drm_device *dev, } } } else if (req->base.drm_surface_flags & - drm_vmw_surface_flag_create_buffer) + (drm_vmw_surface_flag_create_buffer | + drm_vmw_surface_flag_coherent)) ret = vmw_user_bo_alloc(dev_priv, tfile, res->backup_size, req->base.drm_surface_flags & @@ -1656,6 +1690,26 @@ vmw_gb_surface_define_internal(struct drm_device *dev, goto out_unlock; } + if (req->base.drm_surface_flags & drm_vmw_surface_flag_coherent) { + struct vmw_buffer_object *backup = res->backup; + + ttm_bo_reserve(&backup->base, false, false, NULL); + if (!res->func->dirty_alloc) + ret = -EINVAL; + if (!ret) + ret = vmw_bo_dirty_add(backup); + if (!ret) { + res->coherent = true; + ret = res->func->dirty_alloc(res); + } + ttm_bo_unreserve(&backup->base); + if (ret) { + vmw_resource_unreference(&res); + goto out_unlock; + } + + } + tmp = vmw_resource_reference(res); ret = ttm_prime_object_init(tfile, res->backup_size, &user_srf->prime, req->base.drm_surface_flags & @@ -1764,3 +1818,338 @@ out_bad_resource: return ret; } + +/** + * vmw_subres_dirty_add - Add a dirty region to a subresource + * @dirty: The surfaces's dirty tracker. + * @loc_start: The location corresponding to the start of the region. + * @loc_end: The location corresponding to the end of the region. + * + * As we are assuming that @loc_start and @loc_end represent a sequential + * range of backing store memory, if the region spans multiple lines then + * regardless of the x coordinate, the full lines are dirtied. + * Correspondingly if the region spans multiple z slices, then full rather + * than partial z slices are dirtied. + */ +static void vmw_subres_dirty_add(struct vmw_surface_dirty *dirty, + const struct svga3dsurface_loc *loc_start, + const struct svga3dsurface_loc *loc_end) +{ + const struct svga3dsurface_cache *cache = &dirty->cache; + SVGA3dBox *box = &dirty->boxes[loc_start->sub_resource]; + u32 mip = loc_start->sub_resource % cache->num_mip_levels; + const struct drm_vmw_size *size = &cache->mip[mip].size; + u32 box_c2 = box->z + box->d; + + if (WARN_ON(loc_start->sub_resource >= dirty->num_subres)) + return; + + if (box->d == 0 || box->z > loc_start->z) + box->z = loc_start->z; + if (box_c2 < loc_end->z) + box->d = loc_end->z - box->z; + + if (loc_start->z + 1 == loc_end->z) { + box_c2 = box->y + box->h; + if (box->h == 0 || box->y > loc_start->y) + box->y = loc_start->y; + if (box_c2 < loc_end->y) + box->h = loc_end->y - box->y; + + if (loc_start->y + 1 == loc_end->y) { + box_c2 = box->x + box->w; + if (box->w == 0 || box->x > loc_start->x) + box->x = loc_start->x; + if (box_c2 < loc_end->x) + box->w = loc_end->x - box->x; + } else { + box->x = 0; + box->w = size->width; + } + } else { + box->y = 0; + box->h = size->height; + box->x = 0; + box->w = size->width; + } +} + +/** + * vmw_subres_dirty_full - Mark a full subresource as dirty + * @dirty: The surface's dirty tracker. + * @subres: The subresource + */ +static void vmw_subres_dirty_full(struct vmw_surface_dirty *dirty, u32 subres) +{ + const struct svga3dsurface_cache *cache = &dirty->cache; + u32 mip = subres % cache->num_mip_levels; + const struct drm_vmw_size *size = &cache->mip[mip].size; + SVGA3dBox *box = &dirty->boxes[subres]; + + box->x = 0; + box->y = 0; + box->z = 0; + box->w = size->width; + box->h = size->height; + box->d = size->depth; +} + +/* + * vmw_surface_tex_dirty_add_range - The dirty_add_range callback for texture + * surfaces. + */ +static void vmw_surface_tex_dirty_range_add(struct vmw_resource *res, + size_t start, size_t end) +{ + struct vmw_surface_dirty *dirty = + (struct vmw_surface_dirty *) res->dirty; + size_t backup_end = res->backup_offset + res->backup_size; + struct svga3dsurface_loc loc1, loc2; + const struct svga3dsurface_cache *cache; + + start = max_t(size_t, start, res->backup_offset) - res->backup_offset; + end = min(end, backup_end) - res->backup_offset; + cache = &dirty->cache; + svga3dsurface_get_loc(cache, &loc1, start); + svga3dsurface_get_loc(cache, &loc2, end - 1); + svga3dsurface_inc_loc(cache, &loc2); + + if (loc1.sub_resource + 1 == loc2.sub_resource) { + /* Dirty range covers a single sub-resource */ + vmw_subres_dirty_add(dirty, &loc1, &loc2); + } else { + /* Dirty range covers multiple sub-resources */ + struct svga3dsurface_loc loc_min, loc_max; + u32 sub_res = loc1.sub_resource; + + svga3dsurface_max_loc(cache, loc1.sub_resource, &loc_max); + vmw_subres_dirty_add(dirty, &loc1, &loc_max); + svga3dsurface_min_loc(cache, loc2.sub_resource - 1, &loc_min); + vmw_subres_dirty_add(dirty, &loc_min, &loc2); + for (sub_res = loc1.sub_resource + 1; + sub_res < loc2.sub_resource - 1; ++sub_res) + vmw_subres_dirty_full(dirty, sub_res); + } +} + +/* + * vmw_surface_tex_dirty_add_range - The dirty_add_range callback for buffer + * surfaces. + */ +static void vmw_surface_buf_dirty_range_add(struct vmw_resource *res, + size_t start, size_t end) +{ + struct vmw_surface_dirty *dirty = + (struct vmw_surface_dirty *) res->dirty; + const struct svga3dsurface_cache *cache = &dirty->cache; + size_t backup_end = res->backup_offset + cache->mip_chain_bytes; + SVGA3dBox *box = &dirty->boxes[0]; + u32 box_c2; + + box->h = box->d = 1; + start = max_t(size_t, start, res->backup_offset) - res->backup_offset; + end = min(end, backup_end) - res->backup_offset; + box_c2 = box->x + box->w; + if (box->w == 0 || box->x > start) + box->x = start; + if (box_c2 < end) + box->w = end - box->x; +} + +/* + * vmw_surface_tex_dirty_add_range - The dirty_add_range callback for surfaces + */ +static void vmw_surface_dirty_range_add(struct vmw_resource *res, size_t start, + size_t end) +{ + struct vmw_surface *srf = vmw_res_to_srf(res); + + if (WARN_ON(end <= res->backup_offset || + start >= res->backup_offset + res->backup_size)) + return; + + if (srf->format == SVGA3D_BUFFER) + vmw_surface_buf_dirty_range_add(res, start, end); + else + vmw_surface_tex_dirty_range_add(res, start, end); +} + +/* + * vmw_surface_dirty_sync - The surface's dirty_sync callback. + */ +static int vmw_surface_dirty_sync(struct vmw_resource *res) +{ + struct vmw_private *dev_priv = res->dev_priv; + bool has_dx = 0; + u32 i, num_dirty; + struct vmw_surface_dirty *dirty = + (struct vmw_surface_dirty *) res->dirty; + size_t alloc_size; + const struct svga3dsurface_cache *cache = &dirty->cache; + struct { + SVGA3dCmdHeader header; + SVGA3dCmdDXUpdateSubResource body; + } *cmd1; + struct { + SVGA3dCmdHeader header; + SVGA3dCmdUpdateGBImage body; + } *cmd2; + void *cmd; + + num_dirty = 0; + for (i = 0; i < dirty->num_subres; ++i) { + const SVGA3dBox *box = &dirty->boxes[i]; + + if (box->d) + num_dirty++; + } + + if (!num_dirty) + goto out; + + alloc_size = num_dirty * ((has_dx) ? sizeof(*cmd1) : sizeof(*cmd2)); + cmd = VMW_FIFO_RESERVE(dev_priv, alloc_size); + if (!cmd) + return -ENOMEM; + + cmd1 = cmd; + cmd2 = cmd; + + for (i = 0; i < dirty->num_subres; ++i) { + const SVGA3dBox *box = &dirty->boxes[i]; + + if (!box->d) + continue; + + /* + * DX_UPDATE_SUBRESOURCE is aware of array surfaces. + * UPDATE_GB_IMAGE is not. + */ + if (has_dx) { + cmd1->header.id = SVGA_3D_CMD_DX_UPDATE_SUBRESOURCE; + cmd1->header.size = sizeof(cmd1->body); + cmd1->body.sid = res->id; + cmd1->body.subResource = i; + cmd1->body.box = *box; + cmd1++; + } else { + cmd2->header.id = SVGA_3D_CMD_UPDATE_GB_IMAGE; + cmd2->header.size = sizeof(cmd2->body); + cmd2->body.image.sid = res->id; + cmd2->body.image.face = i / cache->num_mip_levels; + cmd2->body.image.mipmap = i - + (cache->num_mip_levels * cmd2->body.image.face); + cmd2->body.box = *box; + cmd2++; + } + + } + vmw_fifo_commit(dev_priv, alloc_size); + out: + memset(&dirty->boxes[0], 0, sizeof(dirty->boxes[0]) * + dirty->num_subres); + + return 0; +} + +/* + * vmw_surface_dirty_alloc - The surface's dirty_alloc callback. + */ +static int vmw_surface_dirty_alloc(struct vmw_resource *res) +{ + struct vmw_surface *srf = vmw_res_to_srf(res); + struct vmw_surface_dirty *dirty; + u32 num_layers = 1; + u32 num_mip; + u32 num_subres; + u32 num_samples; + size_t dirty_size, acc_size; + static struct ttm_operation_ctx ctx = { + .interruptible = false, + .no_wait_gpu = false + }; + int ret; + + if (srf->array_size) + num_layers = srf->array_size; + else if (srf->flags & SVGA3D_SURFACE_CUBEMAP) + num_layers *= SVGA3D_MAX_SURFACE_FACES; + + num_mip = srf->mip_levels[0]; + if (!num_mip) + num_mip = 1; + + num_subres = num_layers * num_mip; + dirty_size = sizeof(*dirty) + num_subres * sizeof(dirty->boxes[0]); + acc_size = ttm_round_pot(dirty_size); + ret = ttm_mem_global_alloc(vmw_mem_glob(res->dev_priv), + acc_size, &ctx); + if (ret) { + VMW_DEBUG_USER("Out of graphics memory for surface " + "dirty tracker.\n"); + return ret; + } + + dirty = kvzalloc(dirty_size, GFP_KERNEL); + if (!dirty) { + ret = -ENOMEM; + goto out_no_dirty; + } + + num_samples = max_t(u32, 1, srf->multisample_count); + ret = svga3dsurface_setup_cache(&srf->base_size, srf->format, num_mip, + num_layers, num_samples, &dirty->cache); + if (ret) + goto out_no_cache; + + dirty->num_subres = num_subres; + dirty->size = acc_size; + res->dirty = (struct vmw_resource_dirty *) dirty; + + return 0; + +out_no_cache: + kvfree(dirty); +out_no_dirty: + ttm_mem_global_free(vmw_mem_glob(res->dev_priv), acc_size); + return ret; +} + +/* + * vmw_surface_dirty_free - The surface's dirty_free callback + */ +static void vmw_surface_dirty_free(struct vmw_resource *res) +{ + struct vmw_surface_dirty *dirty = + (struct vmw_surface_dirty *) res->dirty; + size_t acc_size = dirty->size; + + kvfree(dirty); + ttm_mem_global_free(vmw_mem_glob(res->dev_priv), acc_size); + res->dirty = NULL; +} + +/* + * vmw_surface_clean - The surface's clean callback + */ +static int vmw_surface_clean(struct vmw_resource *res) +{ + struct vmw_private *dev_priv = res->dev_priv; + size_t alloc_size; + struct { + SVGA3dCmdHeader header; + SVGA3dCmdReadbackGBSurface body; + } *cmd; + + alloc_size = sizeof(*cmd); + cmd = VMW_FIFO_RESERVE(dev_priv, alloc_size); + if (!cmd) + return -ENOMEM; + + cmd->header.id = SVGA_3D_CMD_READBACK_GB_SURFACE; + cmd->header.size = sizeof(cmd->body); + cmd->body.sid = res->id; + vmw_fifo_commit(dev_priv, alloc_size); + + return 0; +} diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 399f58317cff..02cab33f2f25 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -891,11 +891,13 @@ struct drm_vmw_shader_arg { * surface. * @drm_vmw_surface_flag_create_buffer: Create a backup buffer if none is * given. + * @drm_vmw_surface_flag_coherent: Back surface with coherent memory. */ enum drm_vmw_surface_flags { drm_vmw_surface_flag_shareable = (1 << 0), drm_vmw_surface_flag_scanout = (1 << 1), - drm_vmw_surface_flag_create_buffer = (1 << 2) + drm_vmw_surface_flag_create_buffer = (1 << 2), + drm_vmw_surface_flag_coherent = (1 << 3), }; /** -- cgit v1.2.3 From 03583e503de624b0672d1a1c16e66b39324db509 Mon Sep 17 00:00:00 2001 From: Deepak Rawat Date: Thu, 9 May 2019 11:47:40 -0700 Subject: drm/vmwgfx: Add debug message for layout change ioctl Add debug code to check user-space layout change request. Signed-off-by: Deepak Rawat Reviewed-by: Thomas Hellstrom Reviewed-by: Emil Velikov Signed-off-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 8 ++++++++ drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 8 ++++++++ 2 files changed, 16 insertions(+) (limited to 'drivers/gpu/drm') diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 5971c0d47507..b4c8817dc267 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1424,6 +1424,14 @@ int vmw_host_log(const char *log); #define VMW_DEBUG_USER(fmt, ...) \ DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__) +/** + * VMW_DEBUG_KMS - Debug output for kernel mode-setting + * + * This macro is for debugging vmwgfx mode-setting code. + */ +#define VMW_DEBUG_KMS(fmt, ...) \ + DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__) + /* Resource dirtying - vmwgfx_page_dirty.c */ void vmw_bo_dirty_scan(struct vmw_buffer_object *vbo); int vmw_bo_dirty_add(struct vmw_buffer_object *vbo); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index b97bc8e5944b..7f9264a72e1d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -2347,6 +2347,9 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data, if (!arg->num_outputs) { struct drm_rect def_rect = {0, 0, 800, 600}; + VMW_DEBUG_KMS("Default layout x1 = %d y1 = %d x2 = %d y2 = %d\n", + def_rect.x1, def_rect.y1, + def_rect.x2, def_rect.y2); vmw_du_update_layout(dev_priv, 1, &def_rect); return 0; } @@ -2367,6 +2370,7 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data, drm_rects = (struct drm_rect *)rects; + VMW_DEBUG_KMS("Layout count = %u\n", arg->num_outputs); for (i = 0; i < arg->num_outputs; i++) { struct drm_vmw_rect curr_rect; @@ -2383,6 +2387,10 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data, drm_rects[i].x2 = curr_rect.x + curr_rect.w; drm_rects[i].y2 = curr_rect.y + curr_rect.h; + VMW_DEBUG_KMS(" x1 = %d y1 = %d x2 = %d y2 = %d\n", + drm_rects[i].x1, drm_rects[i].y1, + drm_rects[i].x2, drm_rects[i].y2); + /* * Currently this check is limiting the topology within * mode_config->max (which actually is max texture size -- cgit v1.2.3 From 358d76d9b577aefba973aea9a50dbfcbaac25d6e Mon Sep 17 00:00:00 2001 From: Deepak Rawat Date: Thu, 9 May 2019 12:42:58 -0700 Subject: drm/vmwgfx: Use VMW_DEBUG_KMS for vmwgfx mode-setting user errors For errors during layout change ioctl use VMW_DEBUG_KMS instead of DRM_ERROR. Signed-off-by: Deepak Rawat Reviewed-by: Thomas Hellstrom Reviewed-by: Emil Velikov Signed-off-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'drivers/gpu/drm') diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 7f9264a72e1d..e7222fa2cfdf 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1462,7 +1462,7 @@ static int vmw_kms_check_display_memory(struct drm_device *dev, if (dev_priv->active_display_unit == vmw_du_screen_target && (drm_rect_width(&rects[i]) > dev_priv->stdu_max_width || drm_rect_height(&rects[i]) > dev_priv->stdu_max_height)) { - DRM_ERROR("Screen size not supported.\n"); + VMW_DEBUG_KMS("Screen size not supported.\n"); return -EINVAL; } @@ -1486,7 +1486,7 @@ static int vmw_kms_check_display_memory(struct drm_device *dev, * limit on primary bounding box */ if (pixel_mem > dev_priv->prim_bb_mem) { - DRM_ERROR("Combined output size too large.\n"); + VMW_DEBUG_KMS("Combined output size too large.\n"); return -EINVAL; } @@ -1496,7 +1496,7 @@ static int vmw_kms_check_display_memory(struct drm_device *dev, bb_mem = (u64) bounding_box.x2 * bounding_box.y2 * 4; if (bb_mem > dev_priv->prim_bb_mem) { - DRM_ERROR("Topology is beyond supported limits.\n"); + VMW_DEBUG_KMS("Topology is beyond supported limits.\n"); return -EINVAL; } } @@ -1645,6 +1645,7 @@ static int vmw_kms_check_topology(struct drm_device *dev, struct vmw_connector_state *vmw_conn_state; if (!du->pref_active && new_crtc_state->enable) { + VMW_DEBUG_KMS("Enabling a disabled display unit\n"); ret = -EINVAL; goto clean; } @@ -1701,8 +1702,10 @@ vmw_kms_atomic_check_modeset(struct drm_device *dev, return ret; ret = vmw_kms_check_implicit(dev, state); - if (ret) + if (ret) { + VMW_DEBUG_KMS("Invalid implicit state\n"); return ret; + } if (!state->allow_modeset) return ret; @@ -2401,7 +2404,9 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data, if (drm_rects[i].x1 < 0 || drm_rects[i].y1 < 0 || drm_rects[i].x2 > mode_config->max_width || drm_rects[i].y2 > mode_config->max_height) { - DRM_ERROR("Invalid GUI layout.\n"); + VMW_DEBUG_KMS("Invalid layout %d %d %d %d\n", + drm_rects[i].x1, drm_rects[i].y1, + drm_rects[i].x2, drm_rects[i].y2); ret = -EINVAL; goto out_free; } -- cgit v1.2.3 From 9bbfda544ed79e8e9abde27bfe2c85428d582e7b Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Tue, 28 May 2019 08:08:55 +0200 Subject: drm/vmwgfx: Kill unneeded legacy security features At one point, the GPU command verifier and user-space handle manager couldn't properly protect GPU clients from accessing each other's data. Instead there was an elaborate mechanism to make sure only the active master's primary clients could render. The other clients were either put to sleep or even killed (if the master had exited). VRAM was evicted on master switch. With the advent of render-node functionality, we relaxed the VRAM eviction, but the other mechanisms stayed in place. Now that the GPU command verifier and ttm object manager properly isolate primary clients from different master realms we can remove the master switch related code and drop those legacy features. Signed-off-by: Thomas Hellstrom Reviewed-by: Brian Paul Reviewed-by: Deepak Rawat Acked-by: Emil Velikov --- drivers/gpu/drm/vmwgfx/ttm_lock.c | 100 -------------------- drivers/gpu/drm/vmwgfx/ttm_lock.h | 30 ------ drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 162 +------------------------------- drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 16 +--- drivers/gpu/drm/vmwgfx/vmwgfx_surface.c | 6 -- 5 files changed, 3 insertions(+), 311 deletions(-) (limited to 'drivers/gpu/drm') diff --git a/drivers/gpu/drm/vmwgfx/ttm_lock.c b/drivers/gpu/drm/vmwgfx/ttm_lock.c index 16b2083cb9d4..5971c72e6d10 100644 --- a/drivers/gpu/drm/vmwgfx/ttm_lock.c +++ b/drivers/gpu/drm/vmwgfx/ttm_lock.c @@ -29,7 +29,6 @@ * Authors: Thomas Hellstrom */ -#include #include #include #include @@ -49,8 +48,6 @@ void ttm_lock_init(struct ttm_lock *lock) init_waitqueue_head(&lock->queue); lock->rw = 0; lock->flags = 0; - lock->kill_takers = false; - lock->signal = SIGKILL; } void ttm_read_unlock(struct ttm_lock *lock) @@ -66,11 +63,6 @@ static bool __ttm_read_lock(struct ttm_lock *lock) bool locked = false; spin_lock(&lock->lock); - if (unlikely(lock->kill_takers)) { - send_sig(lock->signal, current, 0); - spin_unlock(&lock->lock); - return false; - } if (lock->rw >= 0 && lock->flags == 0) { ++lock->rw; locked = true; @@ -98,11 +90,6 @@ static bool __ttm_read_trylock(struct ttm_lock *lock, bool *locked) *locked = false; spin_lock(&lock->lock); - if (unlikely(lock->kill_takers)) { - send_sig(lock->signal, current, 0); - spin_unlock(&lock->lock); - return false; - } if (lock->rw >= 0 && lock->flags == 0) { ++lock->rw; block = false; @@ -147,11 +134,6 @@ static bool __ttm_write_lock(struct ttm_lock *lock) bool locked = false; spin_lock(&lock->lock); - if (unlikely(lock->kill_takers)) { - send_sig(lock->signal, current, 0); - spin_unlock(&lock->lock); - return false; - } if (lock->rw == 0 && ((lock->flags & ~TTM_WRITE_LOCK_PENDING) == 0)) { lock->rw = -1; lock->flags &= ~TTM_WRITE_LOCK_PENDING; @@ -182,88 +164,6 @@ int ttm_write_lock(struct ttm_lock *lock, bool interruptible) return ret; } -static int __ttm_vt_unlock(struct ttm_lock *lock) -{ - int ret = 0; - - spin_lock(&lock->lock); - if (unlikely(!(lock->flags & TTM_VT_LOCK))) - ret = -EINVAL; - lock->flags &= ~TTM_VT_LOCK; - wake_up_all(&lock->queue); - spin_unlock(&lock->lock); - - return ret; -} - -static void ttm_vt_lock_remove(struct ttm_base_object **p_base) -{ - struct ttm_base_object *base = *p_base; - struct ttm_lock *lock = container_of(base, struct ttm_lock, base); - int ret; - - *p_base = NULL; - ret = __ttm_vt_unlock(lock); - BUG_ON(ret != 0); -} - -static bool __ttm_vt_lock(struct ttm_lock *lock) -{ - bool locked = false; - - spin_lock(&lock->lock); - if (lock->rw == 0) { - lock->flags &= ~TTM_VT_LOCK_PENDING; - lock->flags |= TTM_VT_LOCK; - locked = true; - } else { - lock->flags |= TTM_VT_LOCK_PENDING; - } - spin_unlock(&lock->lock); - return locked; -} - -int ttm_vt_lock(struct ttm_lock *lock, - bool interruptible, - struct ttm_object_file *tfile) -{ - int ret = 0; - - if (interruptible) { - ret = wait_event_interruptible(lock->queue, - __ttm_vt_lock(lock)); - if (unlikely(ret != 0)) { - spin_lock(&lock->lock); - lock->flags &= ~TTM_VT_LOCK_PENDING; - wake_up_all(&lock->queue); - spin_unlock(&lock->lock); - return ret; - } - } else - wait_event(lock->queue, __ttm_vt_lock(lock)); - - /* - * Add a base-object, the destructor of which will - * make sure the lock is released if the client dies - * while holding it. - */ - - ret = ttm_base_object_init(tfile, &lock->base, false, - ttm_lock_type, &ttm_vt_lock_remove, NULL); - if (ret) - (void)__ttm_vt_unlock(lock); - else - lock->vt_holder = tfile; - - return ret; -} - -int ttm_vt_unlock(struct ttm_lock *lock) -{ - return ttm_ref_object_base_unref(lock->vt_holder, - lock->base.handle, TTM_REF_USAGE); -} - void ttm_suspend_unlock(struct ttm_lock *lock) { spin_lock(&lock->lock); diff --git a/drivers/gpu/drm/vmwgfx/ttm_lock.h b/drivers/gpu/drm/vmwgfx/ttm_lock.h index 0c3af9836863..3d454e8b491f 100644 --- a/drivers/gpu/drm/vmwgfx/ttm_lock.h +++ b/drivers/gpu/drm/vmwgfx/ttm_lock.h @@ -63,8 +63,6 @@ * @lock: Spinlock protecting some lock members. * @rw: Read-write lock counter. Protected by @lock. * @flags: Lock state. Protected by @lock. - * @kill_takers: Boolean whether to kill takers of the lock. - * @signal: Signal to send when kill_takers is true. */ struct ttm_lock { @@ -73,9 +71,6 @@ struct ttm_lock { spinlock_t lock; int32_t rw; uint32_t flags; - bool kill_takers; - int signal; - struct ttm_object_file *vt_holder; }; @@ -220,29 +215,4 @@ extern void ttm_write_unlock(struct ttm_lock *lock); */ extern int ttm_write_lock(struct ttm_lock *lock, bool interruptible); -/** - * ttm_lock_set_kill - * - * @lock: Pointer to a struct ttm_lock - * @val: Boolean whether to kill processes taking the lock. - * @signal: Signal to send to the process taking the lock. - * - * The kill-when-taking-lock functionality is used to kill processes that keep - * on using the TTM functionality when its resources has been taken down, for - * example when the X server exits. A typical sequence would look like this: - * - X server takes lock in write mode. - * - ttm_lock_set_kill() is called with @val set to true. - * - As part of X server exit, TTM resources are taken down. - * - X server releases the lock on file release. - * - Another dri client wants to render, takes the lock and is killed. - * - */ -static inline void ttm_lock_set_kill(struct ttm_lock *lock, bool val, - int signal) -{ - lock->kill_takers = val; - if (val) - lock->signal = signal; -} - #endif diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index d59c474be38e..8349a6cc126f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -254,7 +254,6 @@ static int vmw_restrict_dma_mask; static int vmw_assume_16bpp; static int vmw_probe(struct pci_dev *, const struct pci_device_id *); -static void vmw_master_init(struct vmw_master *); static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val, void *ptr); @@ -762,10 +761,6 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) DRM_INFO("MMIO at 0x%08x size is %u kiB\n", dev_priv->mmio_start, dev_priv->mmio_size / 1024); - vmw_master_init(&dev_priv->fbdev_master); - ttm_lock_set_kill(&dev_priv->fbdev_master.lock, false, SIGTERM); - dev_priv->active_master = &dev_priv->fbdev_master; - dev_priv->mmio_virt = memremap(dev_priv->mmio_start, dev_priv->mmio_size, MEMREMAP_WB); @@ -1012,18 +1007,7 @@ static void vmw_driver_unload(struct drm_device *dev) static void vmw_postclose(struct drm_device *dev, struct drm_file *file_priv) { - struct vmw_fpriv *vmw_fp; - - vmw_fp = vmw_fpriv(file_priv); - - if (vmw_fp->locked_master) { - struct vmw_master *vmaster = - vmw_master(vmw_fp->locked_master); - - ttm_lock_set_kill(&vmaster->lock, true, SIGTERM); - ttm_vt_unlock(&vmaster->lock); - drm_master_put(&vmw_fp->locked_master); - } + struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv); ttm_object_file_release(&vmw_fp->tfile); kfree(vmw_fp); @@ -1052,55 +1036,6 @@ out_no_tfile: return ret; } -static struct vmw_master *vmw_master_check(struct drm_device *dev, - struct drm_file *file_priv, - unsigned int flags) -{ - int ret; - struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv); - struct vmw_master *vmaster; - - if (!drm_is_primary_client(file_priv) || !(flags & DRM_AUTH)) - return NULL; - - ret = mutex_lock_interruptible(&dev->master_mutex); - if (unlikely(ret != 0)) - return ERR_PTR(-ERESTARTSYS); - - if (drm_is_current_master(file_priv)) { - mutex_unlock(&dev->master_mutex); - return NULL; - } - - /* - * Check if we were previously master, but now dropped. In that - * case, allow at least render node functionality. - */ - if (vmw_fp->locked_master) { - mutex_unlock(&dev->master_mutex); - - if (flags & DRM_RENDER_ALLOW) - return NULL; - - DRM_ERROR("Dropped master trying to access ioctl that " - "requires authentication.\n"); - return ERR_PTR(-EACCES); - } - mutex_unlock(&dev->master_mutex); - - /* - * Take the TTM lock. Possibly sleep waiting for the authenticating - * master to become master again, or for a SIGTERM if the - * authenticating master exits. - */ - vmaster = vmw_master(file_priv->master); - ret = ttm_read_lock(&vmaster->lock, true); - if (unlikely(ret != 0)) - vmaster = ERR_PTR(ret); - - return vmaster; -} - static long vmw_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg, long (*ioctl_func)(struct file *, unsigned int, @@ -1109,7 +1044,6 @@ static long vmw_generic_ioctl(struct file *filp, unsigned int cmd, struct drm_file *file_priv = filp->private_data; struct drm_device *dev = file_priv->minor->dev; unsigned int nr = DRM_IOCTL_NR(cmd); - struct vmw_master *vmaster; unsigned int flags; long ret; @@ -1145,21 +1079,7 @@ static long vmw_generic_ioctl(struct file *filp, unsigned int cmd, } else if (!drm_ioctl_flags(nr, &flags)) return -EINVAL; - vmaster = vmw_master_check(dev, file_priv, flags); - if (IS_ERR(vmaster)) { - ret = PTR_ERR(vmaster); - - if (ret != -ERESTARTSYS) - DRM_INFO("IOCTL ERROR Command %d, Error %ld.\n", - nr, ret); - return ret; - } - - ret = ioctl_func(filp, cmd, arg); - if (vmaster) - ttm_read_unlock(&vmaster->lock); - - return ret; + return ioctl_func(filp, cmd, arg); out_io_encoding: DRM_ERROR("Invalid command format, ioctl %d\n", @@ -1186,65 +1106,10 @@ static void vmw_lastclose(struct drm_device *dev) { } -static void vmw_master_init(struct vmw_master *vmaster) -{ - ttm_lock_init(&vmaster->lock); -} - -static int vmw_master_create(struct drm_device *dev, - struct drm_master *master) -{ - struct vmw_master *vmaster; - - vmaster = kzalloc(sizeof(*vmaster), GFP_KERNEL); - if (unlikely(!vmaster)) - return -ENOMEM; - - vmw_master_init(vmaster); - ttm_lock_set_kill(&vmaster->lock, true, SIGTERM); - master->driver_priv = vmaster; - - return 0; -} - -static void vmw_master_destroy(struct drm_device *dev, - struct drm_master *master) -{ - struct vmw_master *vmaster = vmw_master(master); - - master->driver_priv = NULL; - kfree(vmaster); -} - static int vmw_master_set(struct drm_device *dev, struct drm_file *file_priv, bool from_open) { - struct vmw_private *dev_priv = vmw_priv(dev); - struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv); - struct vmw_master *active = dev_priv->active_master; - struct vmw_master *vmaster = vmw_master(file_priv->master); - int ret = 0; - - if (active) { - BUG_ON(active != &dev_priv->fbdev_master); - ret = ttm_vt_lock(&active->lock, false, vmw_fp->tfile); - if (unlikely(ret != 0)) - return ret; - - ttm_lock_set_kill(&active->lock, true, SIGTERM); - dev_priv->active_master = NULL; - } - - ttm_lock_set_kill(&vmaster->lock, false, SIGTERM); - if (!from_open) { - ttm_vt_unlock(&vmaster->lock); - BUG_ON(vmw_fp->locked_master != file_priv->master); - drm_master_put(&vmw_fp->locked_master); - } - - dev_priv->active_master = vmaster; - /* * Inform a new master that the layout may have changed while * it was gone. @@ -1259,31 +1124,10 @@ static void vmw_master_drop(struct drm_device *dev, struct drm_file *file_priv) { struct vmw_private *dev_priv = vmw_priv(dev); - struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv); - struct vmw_master *vmaster = vmw_master(file_priv->master); - int ret; - - /** - * Make sure the master doesn't disappear while we have - * it locked. - */ - vmw_fp->locked_master = drm_master_get(file_priv->master); - ret = ttm_vt_lock(&vmaster->lock, false, vmw_fp->tfile); vmw_kms_legacy_hotspot_clear(dev_priv); - if (unlikely((ret != 0))) { - DRM_ERROR("Unable to lock TTM at VT switch.\n"); - drm_master_put(&vmw_fp->locked_master); - } - - ttm_lock_set_kill(&vmaster->lock, false, SIGTERM); - if (!dev_priv->enable_fb) vmw_svga_disable(dev_priv); - - dev_priv->active_master = &dev_priv->fbdev_master; - ttm_lock_set_kill(&dev_priv->fbdev_master.lock, false, SIGTERM); - ttm_vt_unlock(&dev_priv->fbdev_master.lock); } /** @@ -1562,8 +1406,6 @@ static struct drm_driver driver = { .disable_vblank = vmw_disable_vblank, .ioctls = vmw_ioctls, .num_ioctls = ARRAY_SIZE(vmw_ioctls), - .master_create = vmw_master_create, - .master_destroy = vmw_master_destroy, .master_set = vmw_master_set, .master_drop = vmw_master_drop, .open = vmw_driver_open, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index b4c8817dc267..3a358a5495e4 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -81,7 +81,6 @@ #define VMW_RES_SHADER ttm_driver_type4 struct vmw_fpriv { - struct drm_master *locked_master; struct ttm_object_file *tfile; bool gb_aware; /* user-space is guest-backed aware */ }; @@ -393,10 +392,6 @@ struct vmw_sw_context{ struct vmw_legacy_display; struct vmw_overlay; -struct vmw_master { - struct ttm_lock lock; -}; - struct vmw_vga_topology_state { uint32_t width; uint32_t height; @@ -559,11 +554,8 @@ struct vmw_private { spinlock_t svga_lock; /** - * Master management. + * PM management. */ - - struct vmw_master *active_master; - struct vmw_master fbdev_master; struct notifier_block pm_nb; bool refuse_hibernation; bool suspend_locked; @@ -632,11 +624,6 @@ static inline struct vmw_fpriv *vmw_fpriv(struct drm_file *file_priv) return (struct vmw_fpriv *)file_priv->driver_priv; } -static inline struct vmw_master *vmw_master(struct drm_master *master) -{ - return (struct vmw_master *) master->driver_priv; -} - /* * The locking here is fine-grained, so that it is performed once * for every read- and write operation. This is of course costly, but we @@ -1102,7 +1089,6 @@ void vmw_kms_cursor_snoop(struct vmw_surface *srf, int vmw_kms_write_svga(struct vmw_private *vmw_priv, unsigned width, unsigned height, unsigned pitch, unsigned bpp, unsigned depth); -void vmw_kms_idle_workqueues(struct vmw_master *vmaster); bool vmw_kms_validate_mode_vram(struct vmw_private *dev_priv, uint32_t pitch, uint32_t height); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 637043f1befa..862ca44680ca 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -946,12 +946,6 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv, if (unlikely(drm_is_render_client(file_priv))) require_exist = true; - if (READ_ONCE(vmw_fpriv(file_priv)->locked_master)) { - DRM_ERROR("Locked master refused legacy " - "surface reference.\n"); - return -EACCES; - } - handle = u_handle; } -- cgit v1.2.3