diff options
Diffstat (limited to 'drivers/gpu/drm/i915/i915_gem_execbuffer.c')
| -rw-r--r-- | drivers/gpu/drm/i915/i915_gem_execbuffer.c | 2742 |
1 files changed, 1631 insertions, 1111 deletions
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 4ee2dc38b7c9..eb46dfa374a7 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -40,143 +40,726 @@ #include "intel_drv.h" #include "intel_frontbuffer.h" -#define DBG_USE_CPU_RELOC 0 /* -1 force GTT relocs; 1 force CPU relocs */ +enum { + FORCE_CPU_RELOC = 1, + FORCE_GTT_RELOC, + FORCE_GPU_RELOC, +#define DBG_FORCE_RELOC 0 /* choose one of the above! */ +}; + +#define __EXEC_OBJECT_HAS_REF BIT(31) +#define __EXEC_OBJECT_HAS_PIN BIT(30) +#define __EXEC_OBJECT_HAS_FENCE BIT(29) +#define __EXEC_OBJECT_NEEDS_MAP BIT(28) +#define __EXEC_OBJECT_NEEDS_BIAS BIT(27) +#define __EXEC_OBJECT_INTERNAL_FLAGS (~0u << 27) /* all of the above */ +#define __EXEC_OBJECT_RESERVED (__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_FENCE) -#define __EXEC_OBJECT_HAS_PIN (1<<31) -#define __EXEC_OBJECT_HAS_FENCE (1<<30) -#define __EXEC_OBJECT_NEEDS_MAP (1<<29) -#define __EXEC_OBJECT_NEEDS_BIAS (1<<28) -#define __EXEC_OBJECT_INTERNAL_FLAGS (0xf<<28) /* all of the above */ +#define __EXEC_HAS_RELOC BIT(31) +#define __EXEC_VALIDATED BIT(30) +#define UPDATE PIN_OFFSET_FIXED #define BATCH_OFFSET_BIAS (256*1024) -struct i915_execbuffer_params { - struct drm_device *dev; - struct drm_file *file; - struct i915_vma *batch; - u32 dispatch_flags; - u32 args_batch_start_offset; - struct intel_engine_cs *engine; - struct i915_gem_context *ctx; - struct drm_i915_gem_request *request; -}; +#define __I915_EXEC_ILLEGAL_FLAGS \ + (__I915_EXEC_UNKNOWN_FLAGS | I915_EXEC_CONSTANTS_MASK) + +/** + * DOC: User command execution + * + * Userspace submits commands to be executed on the GPU as an instruction + * stream within a GEM object we call a batchbuffer. This instructions may + * refer to other GEM objects containing auxiliary state such as kernels, + * samplers, render targets and even secondary batchbuffers. Userspace does + * not know where in the GPU memory these objects reside and so before the + * batchbuffer is passed to the GPU for execution, those addresses in the + * batchbuffer and auxiliary objects are updated. This is known as relocation, + * or patching. To try and avoid having to relocate each object on the next + * execution, userspace is told the location of those objects in this pass, + * but this remains just a hint as the kernel may choose a new location for + * any object in the future. + * + * Processing an execbuf ioctl is conceptually split up into a few phases. + * + * 1. Validation - Ensure all the pointers, handles and flags are valid. + * 2. Reservation - Assign GPU address space for every object + * 3. Relocation - Update any addresses to point to the final locations + * 4. Serialisation - Order the request with respect to its dependencies + * 5. Construction - Construct a request to execute the batchbuffer + * 6. Submission (at some point in the future execution) + * + * Reserving resources for the execbuf is the most complicated phase. We + * neither want to have to migrate the object in the address space, nor do + * we want to have to update any relocations pointing to this object. Ideally, + * we want to leave the object where it is and for all the existing relocations + * to match. If the object is given a new address, or if userspace thinks the + * object is elsewhere, we have to parse all the relocation entries and update + * the addresses. Userspace can set the I915_EXEC_NORELOC flag to hint that + * all the target addresses in all of its objects match the value in the + * relocation entries and that they all match the presumed offsets given by the + * list of execbuffer objects. Using this knowledge, we know that if we haven't + * moved any buffers, all the relocation entries are valid and we can skip + * the update. (If userspace is wrong, the likely outcome is an impromptu GPU + * hang.) The requirement for using I915_EXEC_NO_RELOC are: + * + * The addresses written in the objects must match the corresponding + * reloc.presumed_offset which in turn must match the corresponding + * execobject.offset. + * + * Any render targets written to in the batch must be flagged with + * EXEC_OBJECT_WRITE. + * + * To avoid stalling, execobject.offset should match the current + * address of that object within the active context. + * + * The reservation is done is multiple phases. First we try and keep any + * object already bound in its current location - so as long as meets the + * constraints imposed by the new execbuffer. Any object left unbound after the + * first pass is then fitted into any available idle space. If an object does + * not fit, all objects are removed from the reservation and the process rerun + * after sorting the objects into a priority order (more difficult to fit + * objects are tried first). Failing that, the entire VM is cleared and we try + * to fit the execbuf once last time before concluding that it simply will not + * fit. + * + * A small complication to all of this is that we allow userspace not only to + * specify an alignment and a size for the object in the address space, but + * we also allow userspace to specify the exact offset. This objects are + * simpler to place (the location is known a priori) all we have to do is make + * sure the space is available. + * + * Once all the objects are in place, patching up the buried pointers to point + * to the final locations is a fairly simple job of walking over the relocation + * entry arrays, looking up the right address and rewriting the value into + * the object. Simple! ... The relocation entries are stored in user memory + * and so to access them we have to copy them into a local buffer. That copy + * has to avoid taking any pagefaults as they may lead back to a GEM object + * requiring the struct_mutex (i.e. recursive deadlock). So once again we split + * the relocation into multiple passes. First we try to do everything within an + * atomic context (avoid the pagefaults) which requires that we never wait. If + * we detect that we may wait, or if we need to fault, then we have to fallback + * to a slower path. The slowpath has to drop the mutex. (Can you hear alarm + * bells yet?) Dropping the mutex means that we lose all the state we have + * built up so far for the execbuf and we must reset any global data. However, + * we do leave the objects pinned in their final locations - which is a + * potential issue for concurrent execbufs. Once we have left the mutex, we can + * allocate and copy all the relocation entries into a large array at our + * leisure, reacquire the mutex, reclaim all the objects and other state and + * then proceed to update any incorrect addresses with the objects. + * + * As we process the relocation entries, we maintain a record of whether the + * object is being written to. Using NORELOC, we expect userspace to provide + * this information instead. We also check whether we can skip the relocation + * by comparing the expected value inside the relocation entry with the target's + * final address. If they differ, we have to map the current object and rewrite + * the 4 or 8 byte pointer within. + * + * Serialising an execbuf is quite simple according to the rules of the GEM + * ABI. Execution within each context is ordered by the order of submission. + * Writes to any GEM object are in order of submission and are exclusive. Reads + * from a GEM object are unordered with respect to other reads, but ordered by + * writes. A write submitted after a read cannot occur before the read, and + * similarly any read submitted after a write cannot occur before the write. + * Writes are ordered between engines such that only one write occurs at any + * time (completing any reads beforehand) - using semaphores where available + * and CPU serialisation otherwise. Other GEM access obey the same rules, any + * write (either via mmaps using set-domain, or via pwrite) must flush all GPU + * reads before starting, and any read (either using set-domain or pread) must + * flush all GPU writes before starting. (Note we only employ a barrier before, + * we currently rely on userspace not concurrently starting a new execution + * whilst reading or writing to an object. This may be an advantage or not + * depending on how much you trust userspace not to shoot themselves in the + * foot.) Serialisation may just result in the request being inserted into + * a DAG awaiting its turn, but most simple is to wait on the CPU until + * all dependencies are resolved. + * + * After all of that, is just a matter of closing the request and handing it to + * the hardware (well, leaving it in a queue to be executed). However, we also + * offer the ability for batchbuffers to be run with elevated privileges so + * that they access otherwise hidden registers. (Used to adjust L3 cache etc.) + * Before any batch is given extra privileges we first must check that it + * contains no nefarious instructions, we check that each instruction is from + * our whitelist and all registers are also from an allowed list. We first + * copy the user's batchbuffer to a shadow (so that the user doesn't have + * access to it, either by the CPU or GPU as we scan it) and then parse each + * instruction. If everything is ok, we set a flag telling the hardware to run + * the batchbuffer in trusted mode, otherwise the ioctl is rejected. + */ + +struct i915_execbuffer { + struct drm_i915_private *i915; /** i915 backpointer */ + struct drm_file *file; /** per-file lookup tables and limits */ + struct drm_i915_gem_execbuffer2 *args; /** ioctl parameters */ + struct drm_i915_gem_exec_object2 *exec; /** ioctl execobj[] */ + + struct intel_engine_cs *engine; /** engine to queue the request to */ + struct i915_gem_context *ctx; /** context for building the request */ + struct i915_address_space *vm; /** GTT and vma for the request */ + + struct drm_i915_gem_request *request; /** our request to build */ + struct i915_vma *batch; /** identity of the batch obj/vma */ + + /** actual size of execobj[] as we may extend it for the cmdparser */ + unsigned int buffer_count; + + /** list of vma not yet bound during reservation phase */ + struct list_head unbound; + + /** list of vma that have execobj.relocation_count */ + struct list_head relocs; -struct eb_vmas { - struct drm_i915_private *i915; - struct list_head vmas; - int and; - union { - struct i915_vma *lut[0]; - struct hlist_head buckets[0]; - }; + /** + * Track the most recently used object for relocations, as we + * frequently have to perform multiple relocations within the same + * obj/page + */ + struct reloc_cache { + struct drm_mm_node node; /** temporary GTT binding */ + unsigned long vaddr; /** Current kmap address */ + unsigned long page; /** Currently mapped page index */ + unsigned int gen; /** Cached value of INTEL_GEN */ + bool use_64bit_reloc : 1; + bool has_llc : 1; + bool has_fence : 1; + bool needs_unfenced : 1; + + struct drm_i915_gem_request *rq; + u32 *rq_cmd; + unsigned int rq_size; + } reloc_cache; + + u64 invalid_flags; /** Set of execobj.flags that are invalid */ + u32 context_flags; /** Set of execobj.flags to insert from the ctx */ + + u32 batch_start_offset; /** Location within object of batch */ + u32 batch_len; /** Length of batch within object */ + u32 batch_flags; /** Flags composed for emit_bb_start() */ + + /** + * Indicate either the size of the hastable used to resolve + * relocation handles, or if negative that we are using a direct + * index into the execobj[]. + */ + int lut_size; + struct hlist_head *buckets; /** ht for relocation handles */ }; -static struct eb_vmas * -eb_create(struct drm_i915_private *i915, - struct drm_i915_gem_execbuffer2 *args) +/* + * As an alternative to creating a hashtable of handle-to-vma for a batch, + * we used the last available reserved field in the execobject[] and stash + * a link from the execobj to its vma. + */ +#define __exec_to_vma(ee) (ee)->rsvd2 +#define exec_to_vma(ee) u64_to_ptr(struct i915_vma, __exec_to_vma(ee)) + +/* + * Used to convert any address to canonical form. + * Starting from gen8, some commands (e.g. STATE_BASE_ADDRESS, + * MI_LOAD_REGISTER_MEM and others, see Broadwell PRM Vol2a) require the + * addresses to be in a canonical form: + * "GraphicsAddress[63:48] are ignored by the HW and assumed to be in correct + * canonical form [63:48] == [47]." + */ +#define GEN8_HIGH_ADDRESS_BIT 47 +static inline u64 gen8_canonical_addr(u64 address) { - struct eb_vmas *eb = NULL; - - if (args->flags & I915_EXEC_HANDLE_LUT) { - unsigned size = args->buffer_count; - size *= sizeof(struct i915_vma *); - size += sizeof(struct eb_vmas); - eb = kmalloc(size, GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); - } - - if (eb == NULL) { - unsigned size = args->buffer_count; - unsigned count = PAGE_SIZE / sizeof(struct hlist_head) / 2; - BUILD_BUG_ON_NOT_POWER_OF_2(PAGE_SIZE / sizeof(struct hlist_head)); - while (count > 2*size) - count >>= 1; - eb = kzalloc(count*sizeof(struct hlist_head) + - sizeof(struct eb_vmas), - GFP_TEMPORARY); - if (eb == NULL) - return eb; - - eb->and = count - 1; - } else - eb->and = -args->buffer_count; + return sign_extend64(address, GEN8_HIGH_ADDRESS_BIT); +} - eb->i915 = i915; - INIT_LIST_HEAD(&eb->vmas); - return eb; +static inline u64 gen8_noncanonical_addr(u64 address) +{ + return address & GENMASK_ULL(GEN8_HIGH_ADDRESS_BIT, 0); } -static void -eb_reset(struct eb_vmas *eb) +static int eb_create(struct i915_execbuffer *eb) { - if (eb->and >= 0) - memset(eb->buckets, 0, (eb->and+1)*sizeof(struct hlist_head)); + if (!(eb->args->flags & I915_EXEC_HANDLE_LUT)) { + unsigned int size = 1 + ilog2(eb->buffer_count); + + /* + * Without a 1:1 association between relocation handles and + * the execobject[] index, we instead create a hashtable. + * We size it dynamically based on available memory, starting + * first with 1:1 assocative hash and scaling back until + * the allocation succeeds. + * + * Later on we use a positive lut_size to indicate we are + * using this hashtable, and a negative value to indicate a + * direct lookup. + */ + do { + eb->buckets = kzalloc(sizeof(struct hlist_head) << size, + GFP_TEMPORARY | + __GFP_NORETRY | + __GFP_NOWARN); + if (eb->buckets) + break; + } while (--size); + + if (unlikely(!eb->buckets)) { + eb->buckets = kzalloc(sizeof(struct hlist_head), + GFP_TEMPORARY); + if (unlikely(!eb->buckets)) + return -ENOMEM; + } + + eb->lut_size = size; + } else { + eb->lut_size = -eb->buffer_count; + } + + return 0; } -static struct i915_vma * -eb_get_batch(struct eb_vmas *eb) +static bool +eb_vma_misplaced(const struct drm_i915_gem_exec_object2 *entry, + const struct i915_vma *vma) { - struct i915_vma *vma = list_entry(eb->vmas.prev, typeof(*vma), exec_list); + if (!(entry->flags & __EXEC_OBJECT_HAS_PIN)) + return true; + + if (vma->node.size < entry->pad_to_size) + return true; + + if (entry->alignment && !IS_ALIGNED(vma->node.start, entry->alignment)) + return true; + + if (entry->flags & EXEC_OBJECT_PINNED && + vma->node.start != entry->offset) + return true; + + if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS && + vma->node.start < BATCH_OFFSET_BIAS) + return true; + + if (!(entry->flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) && + (vma->node.start + vma->node.size - 1) >> 32) + return true; + + return false; +} + +static inline void +eb_pin_vma(struct i915_execbuffer *eb, + struct drm_i915_gem_exec_object2 *entry, + struct i915_vma *vma) +{ + u64 flags; + + if (vma->node.size) + flags = vma->node.start; + else + flags = entry->offset & PIN_OFFSET_MASK; + + flags |= PIN_USER | PIN_NOEVICT | PIN_OFFSET_FIXED; + if (unlikely(entry->flags & EXEC_OBJECT_NEEDS_GTT)) + flags |= PIN_GLOBAL; + + if (unlikely(i915_vma_pin(vma, 0, 0, flags))) + return; + + if (unlikely(entry->flags & EXEC_OBJECT_NEEDS_FENCE)) { + if (unlikely(i915_vma_get_fence(vma))) { + i915_vma_unpin(vma); + return; + } + + if (i915_vma_pin_fence(vma)) + entry->flags |= __EXEC_OBJECT_HAS_FENCE; + } + + entry->flags |= __EXEC_OBJECT_HAS_PIN; +} + +static inline void +__eb_unreserve_vma(struct i915_vma *vma, + const struct drm_i915_gem_exec_object2 *entry) +{ + GEM_BUG_ON(!(entry->flags & __EXEC_OBJECT_HAS_PIN)); + + if (unlikely(entry->flags & __EXEC_OBJECT_HAS_FENCE)) + i915_vma_unpin_fence(vma); + + __i915_vma_unpin(vma); +} + +static inline void +eb_unreserve_vma(struct i915_vma *vma, + struct drm_i915_gem_exec_object2 *entry) +{ + if (!(entry->flags & __EXEC_OBJECT_HAS_PIN)) + return; + + __eb_unreserve_vma(vma, entry); + entry->flags &= ~__EXEC_OBJECT_RESERVED; +} + +static int +eb_validate_vma(struct i915_execbuffer *eb, + struct drm_i915_gem_exec_object2 *entry, + struct i915_vma *vma) +{ + if (unlikely(entry->flags & eb->invalid_flags)) + return -EINVAL; + + if (unlikely(entry->alignment && !is_power_of_2(entry->alignment))) + return -EINVAL; /* - * SNA is doing fancy tricks with compressing batch buffers, which leads - * to negative relocation deltas. Usually that works out ok since the - * relocate address is still positive, except when the batch is placed - * very low in the GTT. Ensure this doesn't happen. - * - * Note that actual hangs have only been observed on gen7, but for - * paranoia do it everywhere. + * Offset can be used as input (EXEC_OBJECT_PINNED), reject + * any non-page-aligned or non-canonical addresses. */ - if ((vma->exec_entry->flags & EXEC_OBJECT_PINNED) == 0) - vma->exec_entry->flags |= __EXEC_OBJECT_NEEDS_BIAS; + if (unlikely(entry->flags & EXEC_OBJECT_PINNED && + entry->offset != gen8_canonical_addr(entry->offset & PAGE_MASK))) + return -EINVAL; - return vma; + /* pad_to_size was once a reserved field, so sanitize it */ + if (entry->flags & EXEC_OBJECT_PAD_TO_SIZE) { + if (unlikely(offset_in_page(entry->pad_to_size))) + return -EINVAL; + } else { + entry->pad_to_size = 0; + } + + if (unlikely(vma->exec_entry)) { + DRM_DEBUG("Object [handle %d, index %d] appears more than once in object list\n", + entry->handle, (int)(entry - eb->exec)); + return -EINVAL; + } + + /* + * From drm_mm perspective address space is continuous, + * so from this point we're always using non-canonical + * form internally. + */ + entry->offset = gen8_noncanonical_addr(entry->offset); + + return 0; } static int -eb_lookup_vmas(struct eb_vmas *eb, - struct drm_i915_gem_exec_object2 *exec, - const struct drm_i915_gem_execbuffer2 *args, - struct i915_address_space *vm, - struct drm_file *file) +eb_add_vma(struct i915_execbuffer *eb, + struct drm_i915_gem_exec_object2 *entry, + struct i915_vma *vma) { - struct drm_i915_gem_object *obj; - struct list_head objects; - int i, ret; + int err; - INIT_LIST_HEAD(&objects); - spin_lock(&file->table_lock); - /* Grab a reference to the object and release the lock so we can lookup - * or create the VMA without using GFP_ATOMIC */ - for (i = 0; i < args->buffer_count; i++) { - obj = to_intel_bo(idr_find(&file->object_idr, exec[i].handle)); - if (obj == NULL) { - spin_unlock(&file->table_lock); - DRM_DEBUG("Invalid object handle %d at index %d\n", - exec[i].handle, i); - ret = -ENOENT; - goto err; + GEM_BUG_ON(i915_vma_is_closed(vma)); + + if (!(eb->args->flags & __EXEC_VALIDATED)) { + err = eb_validate_vma(eb, entry, vma); + if (unlikely(err)) + return err; + } + + if (eb->lut_size >= 0) { + vma->exec_handle = entry->handle; + hlist_add_head(&vma->exec_node, + &eb->buckets[hash_32(entry->handle, + eb->lut_size)]); + } + + if (entry->relocation_count) + list_add_tail(&vma->reloc_link, &eb->relocs); + + if (!eb->reloc_cache.has_fence) { + entry->flags &= ~EXEC_OBJECT_NEEDS_FENCE; + } else { + if ((entry->flags & EXEC_OBJECT_NEEDS_FENCE || + eb->reloc_cache.needs_unfenced) && + i915_gem_object_is_tiled(vma->obj)) + entry->flags |= EXEC_OBJECT_NEEDS_GTT | __EXEC_OBJECT_NEEDS_MAP; + } + + if (!(entry->flags & EXEC_OBJECT_PINNED)) + entry->flags |= eb->context_flags; + + /* + * Stash a pointer from the vma to execobj, so we can query its flags, + * size, alignment etc as provided by the user. Also we stash a pointer + * to the vma inside the execobj so that we can use a direct lookup + * to find the right target VMA when doing relocations. + */ + vma->exec_entry = entry; + __exec_to_vma(entry) = (uintptr_t)vma; + + err = 0; + eb_pin_vma(eb, entry, vma); + if (eb_vma_misplaced(entry, vma)) { + eb_unreserve_vma(vma, entry); + + list_add_tail(&vma->exec_link, &eb->unbound); + if (drm_mm_node_allocated(&vma->node)) + err = i915_vma_unbind(vma); + } else { + if (entry->offset != vma->node.start) { + entry->offset = vma->node.start | UPDATE; + eb->args->flags |= __EXEC_HAS_RELOC; } + } + return err; +} + +static inline int use_cpu_reloc(const struct reloc_cache *cache, + const struct drm_i915_gem_object *obj) +{ + if (!i915_gem_object_has_struct_page(obj)) + return false; + + if (DBG_FORCE_RELOC == FORCE_CPU_RELOC) + return true; + + if (DBG_FORCE_RELOC == FORCE_GTT_RELOC) + return false; + + return (cache->has_llc || + obj->cache_dirty || + obj->cache_level != I915_CACHE_NONE); +} + +static int eb_reserve_vma(const struct i915_execbuffer *eb, + struct i915_vma *vma) +{ + struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; + u64 flags; + int err; + + flags = PIN_USER | PIN_NONBLOCK; + if (entry->flags & EXEC_OBJECT_NEEDS_GTT) + flags |= PIN_GLOBAL; + + /* + * Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset, + * limit address to the first 4GBs for unflagged objects. + */ + if (!(entry->flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS)) + flags |= PIN_ZONE_4G; - if (!list_empty(&obj->obj_exec_link)) { - spin_unlock(&file->table_lock); - DRM_DEBUG("Object %p [handle %d, index %d] appears more than once in object list\n", - obj, exec[i].handle, i); - ret = -EINVAL; + if (entry->flags & __EXEC_OBJECT_NEEDS_MAP) + flags |= PIN_MAPPABLE; + + if (entry->flags & EXEC_OBJECT_PINNED) { + flags |= entry->offset | PIN_OFFSET_FIXED; + flags &= ~PIN_NONBLOCK; /* force overlapping PINNED checks */ + } else if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS) { + flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS; + } + + err = i915_vma_pin(vma, entry->pad_to_size, entry->alignment, flags); + if (err) + return err; + + if (entry->offset != vma->node.start) { + entry->offset = vma->node.start | UPDATE; + eb->args->flags |= __EXEC_HAS_RELOC; + } + + entry->flags |= __EXEC_OBJECT_HAS_PIN; + GEM_BUG_ON(eb_vma_misplaced(entry, vma)); + + if (unlikely(entry->flags & EXEC_OBJECT_NEEDS_FENCE)) { + err = i915_vma_get_fence(vma); + if (unlikely(err)) { + i915_vma_unpin(vma); + return err; + } + + if (i915_vma_pin_fence(vma)) + entry->flags |= __EXEC_OBJECT_HAS_FENCE; + } + + return 0; +} + +static int eb_reserve(struct i915_execbuffer *eb) +{ + const unsigned int count = eb->buffer_count; + struct list_head last; + struct i915_vma *vma; + unsigned int i, pass; + int err; + + /* + * Attempt to pin all of the buffers into the GTT. + * This is done in 3 phases: + * + * 1a. Unbind all objects that do not match the GTT constraints for + * the execbuffer (fenceable, mappable, alignment etc). + * 1b. Increment pin count for already bound objects. + * 2. Bind new objects. + * 3. Decrement pin count. + * + * This avoid unnecessary unbinding of later objects in order to make + * room for the earlier objects *unless* we need to defragment. + */ + + pass = 0; + err = 0; + do { + list_for_each_entry(vma, &eb->unbound, exec_link) { + err = eb_reserve_vma(eb, vma); + if (err) + break; + } + if (err != -ENOSPC) + return err; + + /* Resort *all* the objects into priority order */ + INIT_LIST_HEAD(&eb->unbound); + INIT_LIST_HEAD(&last); + for (i = 0; i < count; i++) { + struct drm_i915_gem_exec_object2 *entry = &eb->exec[i]; + + if (entry->flags & EXEC_OBJECT_PINNED && + entry->flags & __EXEC_OBJECT_HAS_PIN) + continue; + + vma = exec_to_vma(entry); + eb_unreserve_vma(vma, entry); + + if (entry->flags & EXEC_OBJECT_PINNED) + list_add(&vma->exec_link, &eb->unbound); + else if (entry->flags & __EXEC_OBJECT_NEEDS_MAP) + list_add_tail(&vma->exec_link, &eb->unbound); + else + list_add_tail(&vma->exec_link, &last); + } + list_splice_tail(&last, &eb->unbound); + + switch (pass++) { + case 0: + break; + + case 1: + /* Too fragmented, unbind everything and retry */ + err = i915_gem_evict_vm(eb->vm); + if (err) + return err; + break; + + default: + return -ENOSPC; + } + } while (1); +} + +static inline struct hlist_head * +ht_head(const struct i915_gem_context_vma_lut *lut, u32 handle) +{ + return &lut->ht[hash_32(handle, lut->ht_bits)]; +} + +static inline bool +ht_needs_resize(const struct i915_gem_context_vma_lut *lut) +{ + return (4*lut->ht_count > 3*lut->ht_size || + 4*lut->ht_count + 1 < lut->ht_size); +} + +static unsigned int eb_batch_index(const struct i915_execbuffer *eb) +{ + if (eb->args->flags & I915_EXEC_BATCH_FIRST) + return 0; + else + return eb->buffer_count - 1; +} + +static int eb_select_context(struct i915_execbuffer *eb) +{ + struct i915_gem_context *ctx; + + ctx = i915_gem_context_lookup(eb->file->driver_priv, eb->args->rsvd1); + if (unlikely(IS_ERR(ctx))) + return PTR_ERR(ctx); + + if (unlikely(i915_gem_context_is_banned(ctx))) { + DRM_DEBUG("Context %u tried to submit while banned\n", + ctx->user_handle); + return -EIO; + } + + eb->ctx = i915_gem_context_get(ctx); + eb->vm = ctx->ppgtt ? &ctx->ppgtt->base : &eb->i915->ggtt.base; + + eb->context_flags = 0; + if (ctx->flags & CONTEXT_NO_ZEROMAP) + eb->context_flags |= __EXEC_OBJECT_NEEDS_BIAS; + + return 0; +} + +static int eb_lookup_vmas(struct i915_execbuffer *eb) +{ +#define INTERMEDIATE BIT(0) + const unsigned int count = eb->buffer_count; + struct i915_gem_context_vma_lut *lut = &eb->ctx->vma_lut; + struct i915_vma *vma; + struct idr *idr; + unsigned int i; + int slow_pass = -1; + int err; + + INIT_LIST_HEAD(&eb->relocs); + INIT_LIST_HEAD(&eb->unbound); + + if (unlikely(lut->ht_size & I915_CTX_RESIZE_IN_PROGRESS)) + flush_work(&lut->resize); + GEM_BUG_ON(lut->ht_size & I915_CTX_RESIZE_IN_PROGRESS); + + for (i = 0; i < count; i++) { + __exec_to_vma(&eb->exec[i]) = 0; + + hlist_for_each_entry(vma, + ht_head(lut, eb->exec[i].handle), + ctx_node) { + if (vma->ctx_handle != eb->exec[i].handle) + continue; + + err = eb_add_vma(eb, &eb->exec[i], vma); + if (unlikely(err)) + return err; + + goto next_vma; + } + + if (slow_pass < 0) + slow_pass = i; +next_vma: ; + } + + if (slow_pass < 0) + goto out; + + spin_lock(&eb->file->table_lock); + /* + * Grab a reference to the object and release the lock so we can lookup + * or create the VMA without using GFP_ATOMIC + */ + idr = &eb->file->object_idr; + for (i = slow_pass; i < count; i++) { + struct drm_i915_gem_object *obj; + + if (__exec_to_vma(&eb->exec[i])) + continue; + + obj = to_intel_bo(idr_find(idr, eb->exec[i].handle)); + if (unlikely(!obj)) { + spin_unlock(&eb->file->table_lock); + DRM_DEBUG("Invalid object handle %d at index %d\n", + eb->exec[i].handle, i); + err = -ENOENT; goto err; } - i915_gem_object_get(obj); - list_add_tail(&obj->obj_exec_link, &objects); + __exec_to_vma(&eb->exec[i]) = INTERMEDIATE | (uintptr_t)obj; } - spin_unlock(&file->table_lock); + spin_unlock(&eb->file->table_lock); - i = 0; - while (!list_empty(&objects)) { - struct i915_vma *vma; + for (i = slow_pass; i < count; i++) { + struct drm_i915_gem_object *obj; - obj = list_first_entry(&objects, - struct drm_i915_gem_object, - obj_exec_link); + if (!(__exec_to_vma(&eb->exec[i]) & INTERMEDIATE)) + continue; /* * NOTE: We can leak any vmas created here when something fails @@ -186,59 +769,93 @@ eb_lookup_vmas(struct eb_vmas *eb, * from the (obj, vm) we don't run the risk of creating * duplicated vmas for the same vm. */ - vma = i915_vma_instance(obj, vm, NULL); + obj = u64_to_ptr(typeof(*obj), + __exec_to_vma(&eb->exec[i]) & ~INTERMEDIATE); + vma = i915_vma_instance(obj, eb->vm, NULL); if (unlikely(IS_ERR(vma))) { DRM_DEBUG("Failed to lookup VMA\n"); - ret = PTR_ERR(vma); + err = PTR_ERR(vma); goto err; } - /* Transfer ownership from the objects list to the vmas list. */ - list_add_tail(&vma->exec_list, &eb->vmas); - list_del_init(&obj->obj_exec_link); + /* First come, first served */ + if (!vma->ctx) { + vma->ctx = eb->ctx; + vma->ctx_handle = eb->exec[i].handle; + hlist_add_head(&vma->ctx_node, + ht_head(lut, eb->exec[i].handle)); + lut->ht_count++; + lut->ht_size |= I915_CTX_RESIZE_IN_PROGRESS; + if (i915_vma_is_ggtt(vma)) { + GEM_BUG_ON(obj->vma_hashed); + obj->vma_hashed = vma; + } - vma->exec_entry = &exec[i]; - if (eb->and < 0) { - eb->lut[i] = vma; - } else { - uint32_t handle = args->flags & I915_EXEC_HANDLE_LUT ? i : exec[i].handle; - vma->exec_handle = handle; - hlist_add_head(&vma->exec_node, - &eb->buckets[handle & eb->and]); + i915_vma_get(vma); } - ++i; - } - return 0; + err = eb_add_vma(eb, &eb->exec[i], vma); + if (unlikely(err)) + goto err; + /* Only after we validated the user didn't use our bits */ + if (vma->ctx != eb->ctx) { + i915_vma_get(vma); + eb->exec[i].flags |= __EXEC_OBJECT_HAS_REF; + } + } -err: - while (!list_empty(&objects)) { - obj = list_first_entry(&objects, - struct drm_i915_gem_object, - obj_exec_link); - list_del_init(&obj->obj_exec_link); - i915_gem_object_put(obj); + if (lut->ht_size & I915_CTX_RESIZE_IN_PROGRESS) { + if (ht_needs_resize(lut)) + queue_work(system_highpri_wq, &lut->resize); + else + lut->ht_size &= ~I915_CTX_RESIZE_IN_PROGRESS; } + +out: + /* take note of the batch buffer before we might reorder the lists */ + i = eb_batch_index(eb); + eb->batch = exec_to_vma(&eb->exec[i]); + /* - * Objects already transfered to the vmas list will be unreferenced by - * eb_destroy. + * SNA is doing fancy tricks with compressing batch buffers, which leads + * to negative relocation deltas. Usually that works out ok since the + * relocate address is still positive, except when the batch is placed + * very low in the GTT. Ensure this doesn't happen. + * + * Note that actual hangs have only been observed on gen7, but for + * paranoia do it everywhere. */ + if (!(eb->exec[i].flags & EXEC_OBJECT_PINNED)) + eb->exec[i].flags |= __EXEC_OBJECT_NEEDS_BIAS; + if (eb->reloc_cache.has_fence) + eb->exec[i].flags |= EXEC_OBJECT_NEEDS_FENCE; - return ret; + eb->args->flags |= __EXEC_VALIDATED; + return eb_reserve(eb); + +err: + for (i = slow_pass; i < count; i++) { + if (__exec_to_vma(&eb->exec[i]) & INTERMEDIATE) + __exec_to_vma(&eb->exec[i]) = 0; + } + lut->ht_size &= ~I915_CTX_RESIZE_IN_PROGRESS; + return err; +#undef INTERMEDIATE } -static struct i915_vma *eb_get_vma(struct eb_vmas *eb, unsigned long handle) +static struct i915_vma * +eb_get_vma(const struct i915_execbuffer *eb, unsigned long handle) { - if (eb->and < 0) { - if (handle >= -eb->and) + if (eb->lut_size < 0) { + if (handle >= -eb->lut_size) return NULL; - return eb->lut[handle]; + return exec_to_vma(&eb->exec[handle]); } else { struct hlist_head *head; struct i915_vma *vma; - head = &eb->buckets[handle & eb->and]; + head = &eb->buckets[hash_32(handle, eb->lut_size)]; hlist_for_each_entry(vma, head, exec_node) { if (vma->exec_handle == handle) return vma; @@ -247,96 +864,69 @@ static struct i915_vma *eb_get_vma(struct eb_vmas *eb, unsigned long handle) } } -static void -i915_gem_execbuffer_unreserve_vma(struct i915_vma *vma) +static void eb_release_vmas(const struct i915_execbuffer *eb) { - struct drm_i915_gem_exec_object2 *entry; - - if (!drm_mm_node_allocated(&vma->node)) - return; + const unsigned int count = eb->buffer_count; + unsigned int i; - entry = vma->exec_entry; + for (i = 0; i < count; i++) { + struct drm_i915_gem_exec_object2 *entry = &eb->exec[i]; + struct i915_vma *vma = exec_to_vma(entry); - if (entry->flags & __EXEC_OBJECT_HAS_FENCE) - i915_vma_unpin_fence(vma); + if (!vma) + continue; - if (entry->flags & __EXEC_OBJECT_HAS_PIN) - __i915_vma_unpin(vma); + GEM_BUG_ON(vma->exec_entry != entry); + vma->exec_entry = NULL; - entry->flags &= ~(__EXEC_OBJECT_HAS_FENCE | __EXEC_OBJECT_HAS_PIN); -} + if (entry->flags & __EXEC_OBJECT_HAS_PIN) + __eb_unreserve_vma(vma, entry); -static void eb_destroy(struct eb_vmas *eb) -{ - while (!list_empty(&eb->vmas)) { - struct i915_vma *vma; + if (entry->flags & __EXEC_OBJECT_HAS_REF) + i915_vma_put(vma); - vma = list_first_entry(&eb->vmas, - struct i915_vma, - exec_list); - list_del_init(&vma->exec_list); - i915_gem_execbuffer_unreserve_vma(vma); - vma->exec_entry = NULL; - i915_vma_put(vma); + entry->flags &= + ~(__EXEC_OBJECT_RESERVED | __EXEC_OBJECT_HAS_REF); } - kfree(eb); } -static inline int use_cpu_reloc(struct drm_i915_gem_object *obj) +static void eb_reset_vmas(const struct i915_execbuffer *eb) { - if (!i915_gem_object_has_struct_page(obj)) - return false; - - if (DBG_USE_CPU_RELOC) - return DBG_USE_CPU_RELOC > 0; - - return (HAS_LLC(to_i915(obj->base.dev)) || - obj->base.write_domain == I915_GEM_DOMAIN_CPU || - obj->cache_level != I915_CACHE_NONE); + eb_release_vmas(eb); + if (eb->lut_size >= 0) + memset(eb->buckets, 0, + sizeof(struct hlist_head) << eb->lut_size); } -/* Used to convert any address to canonical form. - * Starting from gen8, some commands (e.g. STATE_BASE_ADDRESS, - * MI_LOAD_REGISTER_MEM and others, see Broadwell PRM Vol2a) require the - * addresses to be in a canonical form: - * "GraphicsAddress[63:48] are ignored by the HW and assumed to be in correct - * canonical form [63:48] == [47]." - */ -#define GEN8_HIGH_ADDRESS_BIT 47 -static inline uint64_t gen8_canonical_addr(uint64_t address) +static void eb_destroy(const struct i915_execbuffer *eb) { - return sign_extend64(address, GEN8_HIGH_ADDRESS_BIT); -} + GEM_BUG_ON(eb->reloc_cache.rq); -static inline uint64_t gen8_noncanonical_addr(uint64_t address) -{ - return address & ((1ULL << (GEN8_HIGH_ADDRESS_BIT + 1)) - 1); + if (eb->lut_size >= 0) + kfree(eb->buckets); } -static inline uint64_t +static inline u64 relocation_target(const struct drm_i915_gem_relocation_entry *reloc, - uint64_t target_offset) + const struct i915_vma *target) { - return gen8_canonical_addr((int)reloc->delta + target_offset); + return gen8_canonical_addr((int)reloc->delta + target->node.start); } -struct reloc_cache { - struct drm_i915_private *i915; - struct drm_mm_node node; - unsigned long vaddr; - unsigned int page; - bool use_64bit_reloc; -}; - static void reloc_cache_init(struct reloc_cache *cache, struct drm_i915_private *i915) { cache->page = -1; cache->vaddr = 0; - cache->i915 = i915; /* Must be a variable in the struct to allow GCC to unroll. */ + cache->gen = INTEL_GEN(i915); + cache->has_llc = HAS_LLC(i915); cache->use_64bit_reloc = HAS_64BIT_RELOC(i915); + cache->has_fence = cache->gen < 4; + cache->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment; cache->node.allocated = false; + cache->rq = NULL; + cache->rq_size = 0; } static inline void *unmask_page(unsigned long p) @@ -351,10 +941,31 @@ static inline unsigned int unmask_flags(unsigned long p) #define KMAP 0x4 /* after CLFLUSH_FLAGS */ -static void reloc_cache_fini(struct reloc_cache *cache) +static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache) +{ + struct drm_i915_private *i915 = + container_of(cache, struct i915_execbuffer, reloc_cache)->i915; + return &i915->ggtt; +} + +static void reloc_gpu_flush(struct reloc_cache *cache) +{ + GEM_BUG_ON(cache->rq_size >= cache->rq->batch->obj->base.size / sizeof(u32)); + cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END; + i915_gem_object_unpin_map(cache->rq->batch->obj); + i915_gem_chipset_flush(cache->rq->i915); + + __i915_add_request(cache->rq, true); + cache->rq = NULL; +} + +static void reloc_cache_reset(struct reloc_cache *cache) { void *vaddr; + if (cache->rq) + reloc_gpu_flush(cache); + if (!cache->vaddr) return; @@ -369,7 +980,7 @@ static void reloc_cache_fini(struct reloc_cache *cache) wmb(); io_mapping_unmap_atomic((void __iomem *)vaddr); if (cache->node.allocated) { - struct i915_ggtt *ggtt = &cache->i915->ggtt; + struct i915_ggtt *ggtt = cache_to_ggtt(cache); ggtt->base.clear_range(&ggtt->base, cache->node.start, @@ -379,11 +990,14 @@ static void reloc_cache_fini(struct reloc_cache *cache) i915_vma_unpin((struct i915_vma *)cache->node.mm); } } + + cache->vaddr = 0; + cache->page = -1; } static void *reloc_kmap(struct drm_i915_gem_object *obj, struct reloc_cache *cache, - int page) + unsigned long page) { void *vaddr; @@ -391,11 +1005,11 @@ static void *reloc_kmap(struct drm_i915_gem_object *obj, kunmap_atomic(unmask_page(cache->vaddr)); } else { unsigned int flushes; - int ret; + int err; - ret = i915_gem_obj_prepare_shmem_write(obj, &flushes); - if (ret) - return ERR_PTR(ret); + err = i915_gem_obj_prepare_shmem_write(obj, &flushes); + if (err) + return ERR_PTR(err); BUILD_BUG_ON(KMAP & CLFLUSH_FLAGS); BUILD_BUG_ON((KMAP | CLFLUSH_FLAGS) & PAGE_MASK); @@ -415,9 +1029,9 @@ static void *reloc_kmap(struct drm_i915_gem_object *obj, static void *reloc_iomap(struct drm_i915_gem_object *obj, struct reloc_cache *cache, - int page) + unsigned long page) { - struct i915_ggtt *ggtt = &cache->i915->ggtt; + struct i915_ggtt *ggtt = cache_to_ggtt(cache); unsigned long offset; void *vaddr; @@ -425,31 +1039,31 @@ static void *reloc_iomap(struct drm_i915_gem_object *obj, io_mapping_unmap_atomic((void __force __iomem *) unmask_page(cache->vaddr)); } else { struct i915_vma *vma; - int ret; + int err; - if (use_cpu_reloc(obj)) + if (use_cpu_reloc(cache, obj)) return NULL; - ret = i915_gem_object_set_to_gtt_domain(obj, true); - if (ret) - return ERR_PTR(ret); + err = i915_gem_object_set_to_gtt_domain(obj, true); + if (err) + return ERR_PTR(err); vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE | PIN_NONBLOCK); if (IS_ERR(vma)) { memset(&cache->node, 0, sizeof(cache->node)); - ret = drm_mm_insert_node_in_range + err = drm_mm_insert_node_in_range (&ggtt->base.mm, &cache->node, PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE, 0, ggtt->mappable_end, DRM_MM_INSERT_LOW); - if (ret) /* no inactive aperture space, use cpu reloc */ + if (err) /* no inactive aperture space, use cpu reloc */ return NULL; } else { - ret = i915_vma_put_fence(vma); - if (ret) { + err = i915_vma_put_fence(vma); + if (err) { i915_vma_unpin(vma); - return ERR_PTR(ret); + return ERR_PTR(err); } cache->node.start = vma->node.start; @@ -467,7 +1081,8 @@ static void *reloc_iomap(struct drm_i915_gem_object *obj, offset += page << PAGE_SHIFT; } - vaddr = (void __force *) io_mapping_map_atomic_wc(&cache->i915->ggtt.mappable, offset); + vaddr = (void __force *)io_mapping_map_atomic_wc(&ggtt->mappable, + offset); cache->page = page; cache->vaddr = (unsigned long)vaddr; @@ -476,7 +1091,7 @@ static void *reloc_iomap(struct drm_i915_gem_object *obj, static void *reloc_vaddr(struct drm_i915_gem_object *obj, struct reloc_cache *cache, - int page) + unsigned long page) { void *vaddr; @@ -503,7 +1118,8 @@ static void clflush_write32(u32 *addr, u32 value, unsigned int flushes) *addr = value; - /* Writes to the same cacheline are serialised by the CPU + /* + * Writes to the same cacheline are serialised by the CPU * (including clflush). On the write path, we only require * that it hits memory in an orderly fashion and place * mb barriers at the start and end of the relocation phase @@ -515,25 +1131,201 @@ static void clflush_write32(u32 *addr, u32 value, unsigned int flushes) *addr = value; } -static int -relocate_entry(struct drm_i915_gem_object *obj, +static int __reloc_gpu_alloc(struct i915_execbuffer *eb, + struct i915_vma *vma, + unsigned int len) +{ + struct reloc_cache *cache = &eb->reloc_cache; + struct drm_i915_gem_object *obj; + struct drm_i915_gem_request *rq; + struct i915_vma *batch; + u32 *cmd; + int err; + + GEM_BUG_ON(vma->obj->base.write_domain & I915_GEM_DOMAIN_CPU); + + obj = i915_gem_batch_pool_get(&eb->engine->batch_pool, PAGE_SIZE); + if (IS_ERR(obj)) + return PTR_ERR(obj); + + cmd = i915_gem_object_pin_map(obj, + cache->has_llc ? I915_MAP_WB : I915_MAP_WC); + i915_gem_object_unpin_pages(obj); + if (IS_ERR(cmd)) + return PTR_ERR(cmd); + + err = i915_gem_object_set_to_wc_domain(obj, false); + if (err) + goto err_unmap; + + batch = i915_vma_instance(obj, vma->vm, NULL); + if (IS_ERR(batch)) { + err = PTR_ERR(batch); + goto err_unmap; + } + + err = i915_vma_pin(batch, 0, 0, PIN_USER | PIN_NONBLOCK); + if (err) + goto err_unmap; + + rq = i915_gem_request_alloc(eb->engine, eb->ctx); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto err_unpin; + } + + err = i915_gem_request_await_object(rq, vma->obj, true); + if (err) + goto err_request; + + err = eb->engine->emit_flush(rq, EMIT_INVALIDATE); + if (err) + goto err_request; + + err = i915_switch_context(rq); + if (err) + goto err_request; + + err = eb->engine->emit_bb_start(rq, + batch->node.start, PAGE_SIZE, + cache->gen > 5 ? 0 : I915_DISPATCH_SECURE); + if (err) + goto err_request; + + GEM_BUG_ON(!reservation_object_test_signaled_rcu(batch->resv, true)); + i915_vma_move_to_active(batch, rq, 0); + reservation_object_lock(batch->resv, NULL); + reservation_object_add_excl_fence(batch->resv, &rq->fence); + reservation_object_unlock(batch->resv); + i915_vma_unpin(batch); + + i915_vma_move_to_active(vma, rq, true); + reservation_object_lock(vma->resv, NULL); + reservation_object_add_excl_fence(vma->resv, &rq->fence); + reservation_object_unlock(vma->resv); + + rq->batch = batch; + + cache->rq = rq; + cache->rq_cmd = cmd; + cache->rq_size = 0; + + /* Return with batch mapping (cmd) still pinned */ + return 0; + +err_request: + i915_add_request(rq); +err_unpin: + i915_vma_unpin(batch); +err_unmap: + i915_gem_object_unpin_map(obj); + return err; +} + +static u32 *reloc_gpu(struct i915_execbuffer *eb, + struct i915_vma *vma, + unsigned int len) +{ + struct reloc_cache *cache = &eb->reloc_cache; + u32 *cmd; + + if (cache->rq_size > PAGE_SIZE/sizeof(u32) - (len + 1)) + reloc_gpu_flush(cache); + + if (unlikely(!cache->rq)) { + int err; + + err = __reloc_gpu_alloc(eb, vma, len); + if (unlikely(err)) + return ERR_PTR(err); + } + + cmd = cache->rq_cmd + cache->rq_size; + cache->rq_size += len; + + return cmd; +} + +static u64 +relocate_entry(struct i915_vma *vma, const struct drm_i915_gem_relocation_entry *reloc, - struct reloc_cache *cache, - u64 target_offset) + struct i915_execbuffer *eb, + const struct i915_vma *target) { u64 offset = reloc->offset; - bool wide = cache->use_64bit_reloc; + u64 target_offset = relocation_target(reloc, target); + bool wide = eb->reloc_cache.use_64bit_reloc; void *vaddr; - target_offset = relocation_target(reloc, target_offset); + if (!eb->reloc_cache.vaddr && + (DBG_FORCE_RELOC == FORCE_GPU_RELOC || + !reservation_object_test_signaled_rcu(vma->resv, true))) { + const unsigned int gen = eb->reloc_cache.gen; + unsigned int len; + u32 *batch; + u64 addr; + + if (wide) + len = offset & 7 ? 8 : 5; + else if (gen >= 4) + len = 4; + else if (gen >= 3) + len = 3; + else /* On gen2 MI_STORE_DWORD_IMM uses a physical address */ + goto repeat; + + batch = reloc_gpu(eb, vma, len); + if (IS_ERR(batch)) + goto repeat; + + addr = gen8_canonical_addr(vma->node.start + offset); + if (wide) { + if (offset & 7) { + *batch++ = MI_STORE_DWORD_IMM_GEN4; + *batch++ = lower_32_bits(addr); + *batch++ = upper_32_bits(addr); + *batch++ = lower_32_bits(target_offset); + + addr = gen8_canonical_addr(addr + 4); + + *batch++ = MI_STORE_DWORD_IMM_GEN4; + *batch++ = lower_32_bits(addr); + *batch++ = upper_32_bits(addr); + *batch++ = upper_32_bits(target_offset); + } else { + *batch++ = (MI_STORE_DWORD_IMM_GEN4 | (1 << 21)) + 1; + *batch++ = lower_32_bits(addr); + *batch++ = upper_32_bits(addr); + *batch++ = lower_32_bits(target_offset); + *batch++ = upper_32_bits(target_offset); + } + } else if (gen >= 6) { + *batch++ = MI_STORE_DWORD_IMM_GEN4; + *batch++ = 0; + *batch++ = addr; + *batch++ = target_offset; + } else if (gen >= 4) { + *batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT; + *batch++ = 0; + *batch++ = addr; + *batch++ = target_offset; + } else { + *batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL; + *batch++ = addr; + *batch++ = target_offset; + } + + goto out; + } + repeat: - vaddr = reloc_vaddr(obj, cache, offset >> PAGE_SHIFT); + vaddr = reloc_vaddr(vma->obj, &eb->reloc_cache, offset >> PAGE_SHIFT); if (IS_ERR(vaddr)) return PTR_ERR(vaddr); clflush_write32(vaddr + offset_in_page(offset), lower_32_bits(target_offset), - cache->vaddr); + eb->reloc_cache.vaddr); if (wide) { offset += sizeof(u32); @@ -542,48 +1334,29 @@ repeat: goto repeat; } - return 0; +out: + return target->node.start | UPDATE; } -static int -i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, - struct eb_vmas *eb, - struct drm_i915_gem_relocation_entry *reloc, - struct reloc_cache *cache) +static u64 +eb_relocate_entry(struct i915_execbuffer *eb, + struct i915_vma *vma, + const struct drm_i915_gem_relocation_entry *reloc) { - struct drm_i915_private *dev_priv = to_i915(obj->base.dev); - struct drm_gem_object *target_obj; - struct drm_i915_gem_object *target_i915_obj; - struct i915_vma *target_vma; - uint64_t target_offset; - int ret; + struct i915_vma *target; + int err; /* we've already hold a reference to all valid objects */ - target_vma = eb_get_vma(eb, reloc->target_handle); - if (unlikely(target_vma == NULL)) + target = eb_get_vma(eb, reloc->target_handle); + if (unlikely(!target)) return -ENOENT; - target_i915_obj = target_vma->obj; - target_obj = &target_vma->obj->base; - - target_offset = gen8_canonical_addr(target_vma->node.start); - - /* Sandybridge PPGTT errata: We need a global gtt mapping for MI and - * pipe_control writes because the gpu doesn't properly redirect them - * through the ppgtt for non_secure batchbuffers. */ - if (unlikely(IS_GEN6(dev_priv) && - reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION)) { - ret = i915_vma_bind(target_vma, target_i915_obj->cache_level, - PIN_GLOBAL); - if (WARN_ONCE(ret, "Unexpected failure to bind target VMA!")) - return ret; - } /* Validate that the target is in a valid r/w GPU domain */ if (unlikely(reloc->write_domain & (reloc->write_domain - 1))) { DRM_DEBUG("reloc with multiple write domains: " - "obj %p target %d offset %d " + "target %d offset %d " "read %08x write %08x", - obj, reloc->target_handle, + reloc->target_handle, (int) reloc->offset, reloc->read_domains, reloc->write_domain); @@ -592,75 +1365,103 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, if (unlikely((reloc->write_domain | reloc->read_domains) & ~I915_GEM_GPU_DOMAINS)) { DRM_DEBUG("reloc with read/write non-GPU domains: " - "obj %p target %d offset %d " + "target %d offset %d " "read %08x write %08x", - obj, reloc->target_handle, + reloc->target_handle, (int) reloc->offset, reloc->read_domains, reloc->write_domain); return -EINVAL; } - target_obj->pending_read_domains |= reloc->read_domains; - target_obj->pending_write_domain |= reloc->write_domain; + if (reloc->write_domain) { + target->exec_entry->flags |= EXEC_OBJECT_WRITE; + + /* + * Sandybridge PPGTT errata: We need a global gtt mapping + * for MI and pipe_control writes because the gpu doesn't + * properly redirect them through the ppgtt for non_secure + * batchbuffers. + */ + if (reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION && + IS_GEN6(eb->i915)) { + err = i915_vma_bind(target, target->obj->cache_level, + PIN_GLOBAL); + if (WARN_ONCE(err, + "Unexpected failure to bind target VMA!")) + return err; + } + } - /* If the relocation already has the right value in it, no + /* + * If the relocation already has the right value in it, no * more work needs to be done. */ - if (target_offset == reloc->presumed_offset) + if (!DBG_FORCE_RELOC && + gen8_canonical_addr(target->node.start) == reloc->presumed_offset) return 0; /* Check that the relocation address is valid... */ if (unlikely(reloc->offset > - obj->base.size - (cache->use_64bit_reloc ? 8 : 4))) { + vma->size - (eb->reloc_cache.use_64bit_reloc ? 8 : 4))) { DRM_DEBUG("Relocation beyond object bounds: " - "obj %p target %d offset %d size %d.\n", - obj, reloc->target_handle, - (int) reloc->offset, - (int) obj->base.size); + "target %d offset %d size %d.\n", + reloc->target_handle, + (int)reloc->offset, + (int)vma->size); return -EINVAL; } if (unlikely(reloc->offset & 3)) { DRM_DEBUG("Relocation not 4-byte aligned: " - "obj %p target %d offset %d.\n", - obj, reloc->target_handle, - (int) reloc->offset); + "target %d offset %d.\n", + reloc->target_handle, + (int)reloc->offset); return -EINVAL; } - ret = relocate_entry(obj, reloc, cache, target_offset); - if (ret) - return ret; + /* + * If we write into the object, we need to force the synchronisation + * barrier, either with an asynchronous clflush or if we executed the + * patching using the GPU (though that should be serialised by the + * timeline). To be completely sure, and since we are required to + * do relocations we are already stalling, disable the user's opt + * of our synchronisation. + */ + vma->exec_entry->flags &= ~EXEC_OBJECT_ASYNC; /* and update the user's relocation entry */ - reloc->presumed_offset = target_offset; - return 0; + return relocate_entry(vma, reloc, eb, target); } -static int -i915_gem_execbuffer_relocate_vma(struct i915_vma *vma, - struct eb_vmas *eb) +static int eb_relocate_vma(struct i915_execbuffer *eb, struct i915_vma *vma) { #define N_RELOC(x) ((x) / sizeof(struct drm_i915_gem_relocation_entry)) - struct drm_i915_gem_relocation_entry stack_reloc[N_RELOC(512)]; - struct drm_i915_gem_relocation_entry __user *user_relocs; - struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; - struct reloc_cache cache; - int remain, ret = 0; - - user_relocs = u64_to_user_ptr(entry->relocs_ptr); - reloc_cache_init(&cache, eb->i915); + struct drm_i915_gem_relocation_entry stack[N_RELOC(512)]; + struct drm_i915_gem_relocation_entry __user *urelocs; + const struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; + unsigned int remain; + urelocs = u64_to_user_ptr(entry->relocs_ptr); remain = entry->relocation_count; - while (remain) { - struct drm_i915_gem_relocation_entry *r = stack_reloc; - unsigned long unwritten; - unsigned int count; + if (unlikely(remain > N_RELOC(ULONG_MAX))) + return -EINVAL; - count = min_t(unsigned int, remain, ARRAY_SIZE(stack_reloc)); - remain -= count; + /* + * We must check that the entire relocation array is safe + * to read. However, if the array is not writable the user loses + * the updated relocation values. + */ + if (unlikely(!access_ok(VERIFY_READ, urelocs, remain*sizeof(urelocs)))) + return -EFAULT; - /* This is the fast path and we cannot handle a pagefault + do { + struct drm_i915_gem_relocation_entry *r = stack; + unsigned int count = + min_t(unsigned int, remain, ARRAY_SIZE(stack)); + unsigned int copied; + + /* + * This is the fast path and we cannot handle a pagefault * whilst holding the struct mutex lest the user pass in the * relocations contained within a mmaped bo. For in such a case * we, the page fault handler would call i915_gem_fault() and @@ -668,595 +1469,425 @@ i915_gem_execbuffer_relocate_vma(struct i915_vma *vma, * this is bad and so lockdep complains vehemently. */ pagefault_disable(); - unwritten = __copy_from_user_inatomic(r, user_relocs, count*sizeof(r[0])); + copied = __copy_from_user_inatomic(r, urelocs, count * sizeof(r[0])); pagefault_enable(); - if (unlikely(unwritten)) { - ret = -EFAULT; + if (unlikely(copied)) { + remain = -EFAULT; goto out; } + remain -= count; do { - u64 offset = r->presumed_offset; + u64 offset = eb_relocate_entry(eb, vma, r); - ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, r, &cache); - if (ret) + if (likely(offset == 0)) { + } else if ((s64)offset < 0) { + remain = (int)offset; goto out; - - if (r->presumed_offset != offset) { - pagefault_disable(); - unwritten = __put_user(r->presumed_offset, - &user_relocs->presumed_offset); - pagefault_enable(); - if (unlikely(unwritten)) { - /* Note that reporting an error now - * leaves everything in an inconsistent - * state as we have *already* changed - * the relocation value inside the - * object. As we have not changed the - * reloc.presumed_offset or will not - * change the execobject.offset, on the - * call we may not rewrite the value - * inside the object, leaving it - * dangling and causing a GPU hang. - */ - ret = -EFAULT; - goto out; - } + } else { + /* + * Note that reporting an error now + * leaves everything in an inconsistent + * state as we have *already* changed + * the relocation value inside the + * object. As we have not changed the + * reloc.presumed_offset or will not + * change the execobject.offset, on the + * call we may not rewrite the value + * inside the object, leaving it + * dangling and causing a GPU hang. Unless + * userspace dynamically rebuilds the + * relocations on each execbuf rather than + * presume a static tree. + * + * We did previously check if the relocations + * were writable (access_ok), an error now + * would be a strange race with mprotect, + * having already demonstrated that we + * can read from this userspace address. + */ + offset = gen8_canonical_addr(offset & ~UPDATE); + __put_user(offset, + &urelocs[r-stack].presumed_offset); } - - user_relocs++; - r++; - } while (--count); - } - + } while (r++, --count); + urelocs += ARRAY_SIZE(stack); + } while (remain); out: - reloc_cache_fini(&cache); - return ret; -#undef N_RELOC + reloc_cache_reset(&eb->reloc_cache); + return remain; } static int -i915_gem_execbuffer_relocate_vma_slow(struct i915_vma *vma, - struct eb_vmas *eb, - struct drm_i915_gem_relocation_entry *relocs) +eb_relocate_vma_slow(struct i915_execbuffer *eb, struct i915_vma *vma) { const struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; - struct reloc_cache cache; - int i, ret = 0; + struct drm_i915_gem_relocation_entry *relocs = + u64_to_ptr(typeof(*relocs), entry->relocs_ptr); + unsigned int i; + int err; - reloc_cache_init(&cache, eb->i915); for (i = 0; i < entry->relocation_count; i++) { - ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, &relocs[i], &cache); - if (ret) - break; - } - reloc_cache_fini(&cache); - - return ret; -} + u64 offset = eb_relocate_entry(eb, vma, &relocs[i]); -static int -i915_gem_execbuffer_relocate(struct eb_vmas *eb) -{ - struct i915_vma *vma; - int ret = 0; - - list_for_each_entry(vma, &eb->vmas, exec_list) { - ret = i915_gem_execbuffer_relocate_vma(vma, eb); - if (ret) - break; + if ((s64)offset < 0) { + err = (int)offset; + goto err; + } } - - return ret; -} - -static bool only_mappable_for_reloc(unsigned int flags) -{ - return (flags & (EXEC_OBJECT_NEEDS_FENCE | __EXEC_OBJECT_NEEDS_MAP)) == - __EXEC_OBJECT_NEEDS_MAP; + err = 0; +err: + reloc_cache_reset(&eb->reloc_cache); + return err; } -static int -i915_gem_execbuffer_reserve_vma(struct i915_vma *vma, - struct intel_engine_cs *engine, - bool *need_reloc) +static int check_relocations(const struct drm_i915_gem_exec_object2 *entry) { - struct drm_i915_gem_object *obj = vma->obj; - struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; - uint64_t flags; - int ret; + const char __user *addr, *end; + unsigned long size; + char __maybe_unused c; - flags = PIN_USER; - if (entry->flags & EXEC_OBJECT_NEEDS_GTT) - flags |= PIN_GLOBAL; - - if (!drm_mm_node_allocated(&vma->node)) { - /* Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset, - * limit address to the first 4GBs for unflagged objects. - */ - if ((entry->flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) == 0) - flags |= PIN_ZONE_4G; - if (entry->flags & __EXEC_OBJECT_NEEDS_MAP) - flags |= PIN_GLOBAL | PIN_MAPPABLE; - if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS) - flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS; - if (entry->flags & EXEC_OBJECT_PINNED) - flags |= entry->offset | PIN_OFFSET_FIXED; - if ((flags & PIN_MAPPABLE) == 0) - flags |= PIN_HIGH; - } - - ret = i915_vma_pin(vma, - entry->pad_to_size, - entry->alignment, - flags); - if ((ret == -ENOSPC || ret == -E2BIG) && - only_mappable_for_reloc(entry->flags)) - ret = i915_vma_pin(vma, - entry->pad_to_size, - entry->alignment, - flags & ~PIN_MAPPABLE); - if (ret) - return ret; - - entry->flags |= __EXEC_OBJECT_HAS_PIN; - - if (entry->flags & EXEC_OBJECT_NEEDS_FENCE) { - ret = i915_vma_get_fence(vma); - if (ret) - return ret; + size = entry->relocation_count; + if (size == 0) + return 0; - if (i915_vma_pin_fence(vma)) - entry->flags |= __EXEC_OBJECT_HAS_FENCE; - } + if (size > N_RELOC(ULONG_MAX)) + return -EINVAL; - if (entry->offset != vma->node.start) { - entry->offset = vma->node.start; - *need_reloc = true; - } + addr = u64_to_user_ptr(entry->relocs_ptr); + size *= sizeof(struct drm_i915_gem_relocation_entry); + if (!access_ok(VERIFY_READ, addr, size)) + return -EFAULT; - if (entry->flags & EXEC_OBJECT_WRITE) { - obj->base.pending_read_domains = I915_GEM_DOMAIN_RENDER; - obj->base.pending_write_domain = I915_GEM_DOMAIN_RENDER; + end = addr + size; + for (; addr < end; addr += PAGE_SIZE) { + int err = __get_user(c, addr); + if (err) + return err; } - - return 0; + return __get_user(c, end - 1); } -static bool -need_reloc_mappable(struct i915_vma *vma) +static int eb_copy_relocations(const struct i915_execbuffer *eb) { - struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; - - if (entry->relocation_count == 0) - return false; - - if (!i915_vma_is_ggtt(vma)) - return false; - - /* See also use_cpu_reloc() */ - if (HAS_LLC(to_i915(vma->obj->base.dev))) - return false; + const unsigned int count = eb->buffer_count; + unsigned int i; + int err; - if (vma->obj->base.write_domain == I915_GEM_DOMAIN_CPU) - return false; + for (i = 0; i < count; i++) { + const unsigned int nreloc = eb->exec[i].relocation_count; + struct drm_i915_gem_relocation_entry __user *urelocs; + struct drm_i915_gem_relocation_entry *relocs; + unsigned long size; + unsigned long copied; - return true; -} + if (nreloc == 0) + continue; -static bool -eb_vma_misplaced(struct i915_vma *vma) -{ - struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; + err = check_relocations(&eb->exec[i]); + if (err) + goto err; - WARN_ON(entry->flags & __EXEC_OBJECT_NEEDS_MAP && - !i915_vma_is_ggtt(vma)); + urelocs = u64_to_user_ptr(eb->exec[i].relocs_ptr); + size = nreloc * sizeof(*relocs); - if (entry->alignment && !IS_ALIGNED(vma->node.start, entry->alignment)) - return true; + relocs = kvmalloc_array(size, 1, GFP_TEMPORARY); + if (!relocs) { + kvfree(relocs); + err = -ENOMEM; + goto err; + } - if (vma->node.size < entry->pad_to_size) - return true; + /* copy_from_user is limited to < 4GiB */ + copied = 0; + do { + unsigned int len = + min_t(u64, BIT_ULL(31), size - copied); + + if (__copy_from_user((char *)relocs + copied, + (char *)urelocs + copied, + len)) { + kvfree(relocs); + err = -EFAULT; + goto err; + } - if (entry->flags & EXEC_OBJECT_PINNED && - vma->node.start != entry->offset) - return true; + copied += len; + } while (copied < size); - if (entry->flags & __EXEC_OBJECT_NEEDS_BIAS && - vma->node.start < BATCH_OFFSET_BIAS) - return true; + /* + * As we do not update the known relocation offsets after + * relocating (due to the complexities in lock handling), + * we need to mark them as invalid now so that we force the + * relocation processing next time. Just in case the target + * object is evicted and then rebound into its old + * presumed_offset before the next execbuffer - if that + * happened we would make the mistake of assuming that the + * relocations were valid. + */ + user_access_begin(); + for (copied = 0; copied < nreloc; copied++) + unsafe_put_user(-1, + &urelocs[copied].presumed_offset, + end_user); +end_user: + user_access_end(); - /* avoid costly ping-pong once a batch bo ended up non-mappable */ - if (entry->flags & __EXEC_OBJECT_NEEDS_MAP && - !i915_vma_is_map_and_fenceable(vma)) - return !only_mappable_for_reloc(entry->flags); + eb->exec[i].relocs_ptr = (uintptr_t)relocs; + } - if ((entry->flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) == 0 && - (vma->node.start + vma->node.size - 1) >> 32) - return true; + return 0; - return false; +err: + while (i--) { + struct drm_i915_gem_relocation_entry *relocs = + u64_to_ptr(typeof(*relocs), eb->exec[i].relocs_ptr); + if (eb->exec[i].relocation_count) + kvfree(relocs); + } + return err; } -static int -i915_gem_execbuffer_reserve(struct intel_engine_cs *engine, - struct list_head *vmas, - struct i915_gem_context *ctx, - bool *need_relocs) +static int eb_prefault_relocations(const struct i915_execbuffer *eb) { - struct drm_i915_gem_object *obj; - struct i915_vma *vma; - struct i915_address_space *vm; - struct list_head ordered_vmas; - struct list_head pinned_vmas; - bool has_fenced_gpu_access = INTEL_GEN(engine->i915) < 4; - bool needs_unfenced_map = INTEL_INFO(engine->i915)->unfenced_needs_alignment; - int retry; - - vm = list_first_entry(vmas, struct i915_vma, exec_list)->vm; - - INIT_LIST_HEAD(&ordered_vmas); - INIT_LIST_HEAD(&pinned_vmas); - while (!list_empty(vmas)) { - struct drm_i915_gem_exec_object2 *entry; - bool need_fence, need_mappable; - - vma = list_first_entry(vmas, struct i915_vma, exec_list); - obj = vma->obj; - entry = vma->exec_entry; - - if (ctx->flags & CONTEXT_NO_ZEROMAP) - entry->flags |= __EXEC_OBJECT_NEEDS_BIAS; - - if (!has_fenced_gpu_access) - entry->flags &= ~EXEC_OBJECT_NEEDS_FENCE; - need_fence = - (entry->flags & EXEC_OBJECT_NEEDS_FENCE || - needs_unfenced_map) && - i915_gem_object_is_tiled(obj); - need_mappable = need_fence || need_reloc_mappable(vma); - - if (entry->flags & EXEC_OBJECT_PINNED) - list_move_tail(&vma->exec_list, &pinned_vmas); - else if (need_mappable) { - entry->flags |= __EXEC_OBJECT_NEEDS_MAP; - list_move(&vma->exec_list, &ordered_vmas); - } else - list_move_tail(&vma->exec_list, &ordered_vmas); - - obj->base.pending_read_domains = I915_GEM_GPU_DOMAINS & ~I915_GEM_DOMAIN_COMMAND; - obj->base.pending_write_domain = 0; - } - list_splice(&ordered_vmas, vmas); - list_splice(&pinned_vmas, vmas); - - /* Attempt to pin all of the buffers into the GTT. - * This is done in 3 phases: - * - * 1a. Unbind all objects that do not match the GTT constraints for - * the execbuffer (fenceable, mappable, alignment etc). - * 1b. Increment pin count for already bound objects. - * 2. Bind new objects. - * 3. Decrement pin count. - * - * This avoid unnecessary unbinding of later objects in order to make - * room for the earlier objects *unless* we need to defragment. - */ - retry = 0; - do { - int ret = 0; - - /* Unbind any ill-fitting objects or pin. */ - list_for_each_entry(vma, vmas, exec_list) { - if (!drm_mm_node_allocated(&vma->node)) - continue; - - if (eb_vma_misplaced(vma)) - ret = i915_vma_unbind(vma); - else - ret = i915_gem_execbuffer_reserve_vma(vma, - engine, - need_relocs); - if (ret) - goto err; - } + const unsigned int count = eb->buffer_count; + unsigned int i; - /* Bind fresh objects */ - list_for_each_entry(vma, vmas, exec_list) { - if (drm_mm_node_allocated(&vma->node)) - continue; - - ret = i915_gem_execbuffer_reserve_vma(vma, engine, - need_relocs); - if (ret) - goto err; - } + if (unlikely(i915.prefault_disable)) + return 0; -err: - if (ret != -ENOSPC || retry++) - return ret; + for (i = 0; i < count; i++) { + int err; - /* Decrement pin count for bound objects */ - list_for_each_entry(vma, vmas, exec_list) - i915_gem_execbuffer_unreserve_vma(vma); + err = check_relocations(&eb->exec[i]); + if (err) + return err; + } - ret = i915_gem_evict_vm(vm, true); - if (ret) - return ret; - } while (1); + return 0; } -static int -i915_gem_execbuffer_relocate_slow(struct drm_device *dev, - struct drm_i915_gem_execbuffer2 *args, - struct drm_file *file, - struct intel_engine_cs *engine, - struct eb_vmas *eb, - struct drm_i915_gem_exec_object2 *exec, - struct i915_gem_context *ctx) +static noinline int eb_relocate_slow(struct i915_execbuffer *eb) { - struct drm_i915_gem_relocation_entry *reloc; - struct i915_address_space *vm; + struct drm_device *dev = &eb->i915->drm; + bool have_copy = false; struct i915_vma *vma; - bool need_relocs; - int *reloc_offset; - int i, total, ret; - unsigned count = args->buffer_count; - - vm = list_first_entry(&eb->vmas, struct i915_vma, exec_list)->vm; + int err = 0; - /* We may process another execbuffer during the unlock... */ - while (!list_empty(&eb->vmas)) { - vma = list_first_entry(&eb->vmas, struct i915_vma, exec_list); - list_del_init(&vma->exec_list); - i915_gem_execbuffer_unreserve_vma(vma); - i915_vma_put(vma); +repeat: + if (signal_pending(current)) { + err = -ERESTARTSYS; + goto out; } + /* We may process another execbuffer during the unlock... */ + eb_reset_vmas(eb); mutex_unlock(&dev->struct_mutex); - total = 0; - for (i = 0; i < count; i++) - total += exec[i].relocation_count; - - reloc_offset = kvmalloc_array(count, sizeof(*reloc_offset), GFP_KERNEL); - reloc = kvmalloc_array(total, sizeof(*reloc), GFP_KERNEL); - if (reloc == NULL || reloc_offset == NULL) { - kvfree(reloc); - kvfree(reloc_offset); + /* + * We take 3 passes through the slowpatch. + * + * 1 - we try to just prefault all the user relocation entries and + * then attempt to reuse the atomic pagefault disabled fast path again. + * + * 2 - we copy the user entries to a local buffer here outside of the + * local and allow ourselves to wait upon any rendering before + * relocations + * + * 3 - we already have a local copy of the relocation entries, but + * were interrupted (EAGAIN) whilst waiting for the objects, try again. + */ + if (!err) { + err = eb_prefault_relocations(eb); + } else if (!have_copy) { + err = eb_copy_relocations(eb); + have_copy = err == 0; + } else { + cond_resched(); + err = 0; + } + if (err) { mutex_lock(&dev->struct_mutex); - return -ENOMEM; + goto out; } - total = 0; - for (i = 0; i < count; i++) { - struct drm_i915_gem_relocation_entry __user *user_relocs; - u64 invalid_offset = (u64)-1; - int j; - - user_relocs = u64_to_user_ptr(exec[i].relocs_ptr); - - if (copy_from_user(reloc+total, user_relocs, - exec[i].relocation_count * sizeof(*reloc))) { - ret = -EFAULT; - mutex_lock(&dev->struct_mutex); - goto err; - } + /* A frequent cause for EAGAIN are currently unavailable client pages */ + flush_workqueue(eb->i915->mm.userptr_wq); - /* As we do not update the known relocation offsets after - * relocating (due to the complexities in lock handling), - * we need to mark them as invalid now so that we force the - * relocation processing next time. Just in case the target - * object is evicted and then rebound into its old - * presumed_offset before the next execbuffer - if that - * happened we would make the mistake of assuming that the - * relocations were valid. - */ - for (j = 0; j < exec[i].relocation_count; j++) { - if (__copy_to_user(&user_relocs[j].presumed_offset, - &invalid_offset, - sizeof(invalid_offset))) { - ret = -EFAULT; - mutex_lock(&dev->struct_mutex); - goto err; - } - } - - reloc_offset[i] = total; - total += exec[i].relocation_count; - } - - ret = i915_mutex_lock_interruptible(dev); - if (ret) { + err = i915_mutex_lock_interruptible(dev); + if (err) { mutex_lock(&dev->struct_mutex); - goto err; + goto out; } /* reacquire the objects */ - eb_reset(eb); - ret = eb_lookup_vmas(eb, exec, args, vm, file); - if (ret) - goto err; - - need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0; - ret = i915_gem_execbuffer_reserve(engine, &eb->vmas, ctx, - &need_relocs); - if (ret) + err = eb_lookup_vmas(eb); + if (err) goto err; - list_for_each_entry(vma, &eb->vmas, exec_list) { - int offset = vma->exec_entry - exec; - ret = i915_gem_execbuffer_relocate_vma_slow(vma, eb, - reloc + reloc_offset[offset]); - if (ret) - goto err; + list_for_each_entry(vma, &eb->relocs, reloc_link) { + if (!have_copy) { + pagefault_disable(); + err = eb_relocate_vma(eb, vma); + pagefault_enable(); + if (err) + goto repeat; + } else { + err = eb_relocate_vma_slow(eb, vma); + if (err) + goto err; + } } - /* Leave the user relocations as are, this is the painfully slow path, + /* + * Leave the user relocations as are, this is the painfully slow path, * and we want to avoid the complication of dropping the lock whilst * having buffers reserved in the aperture and so causing spurious * ENOSPC for random operations. */ err: - kvfree(reloc); - kvfree(reloc_offset); - return ret; -} + if (err == -EAGAIN) + goto repeat; -static int -i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req, - struct list_head *vmas) -{ - struct i915_vma *vma; - int ret; +out: + if (have_copy) { + const unsigned int count = eb->buffer_count; + unsigned int i; - list_for_each_entry(vma, vmas, exec_list) { - struct drm_i915_gem_object *obj = vma->obj; + for (i = 0; i < count; i++) { + const struct drm_i915_gem_exec_object2 *entry = + &eb->exec[i]; + struct drm_i915_gem_relocation_entry *relocs; - if (vma->exec_entry->flags & EXEC_OBJECT_ASYNC) - continue; + if (!entry->relocation_count) + continue; - if (obj->base.write_domain & I915_GEM_DOMAIN_CPU) { - i915_gem_clflush_object(obj, 0); - obj->base.write_domain = 0; + relocs = u64_to_ptr(typeof(*relocs), entry->relocs_ptr); + kvfree(relocs); } - - ret = i915_gem_request_await_object - (req, obj, obj->base.pending_write_domain); - if (ret) - return ret; } - /* Unconditionally flush any chipset caches (for streaming writes). */ - i915_gem_chipset_flush(req->engine->i915); - - /* Unconditionally invalidate GPU caches and TLBs. */ - return req->engine->emit_flush(req, EMIT_INVALIDATE); + return err ?: have_copy; } -static bool -i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec) +static int eb_relocate(struct i915_execbuffer *eb) { - if (exec->flags & __I915_EXEC_UNKNOWN_FLAGS) - return false; + if (eb_lookup_vmas(eb)) + goto slow; - /* Kernel clipping was a DRI1 misfeature */ - if (exec->num_cliprects || exec->cliprects_ptr) - return false; + /* The objects are in their final locations, apply the relocations. */ + if (eb->args->flags & __EXEC_HAS_RELOC) { + struct i915_vma *vma; - if (exec->DR4 == 0xffffffff) { - DRM_DEBUG("UXA submitting garbage DR4, fixing up\n"); - exec->DR4 = 0; + list_for_each_entry(vma, &eb->relocs, reloc_link) { + if (eb_relocate_vma(eb, vma)) + goto slow; + } } - if (exec->DR1 || exec->DR4) - return false; - if ((exec->batch_start_offset | exec->batch_len) & 0x7) - return false; + return 0; - return true; +slow: + return eb_relocate_slow(eb); } -static int -validate_exec_list(struct drm_device *dev, - struct drm_i915_gem_exec_object2 *exec, - int count) +static void eb_export_fence(struct i915_vma *vma, + struct drm_i915_gem_request *req, + unsigned int flags) { - unsigned relocs_total = 0; - unsigned relocs_max = UINT_MAX / sizeof(struct drm_i915_gem_relocation_entry); - unsigned invalid_flags; - int i; + struct reservation_object *resv = vma->resv; - /* INTERNAL flags must not overlap with external ones */ - BUILD_BUG_ON(__EXEC_OBJECT_INTERNAL_FLAGS & ~__EXEC_OBJECT_UNKNOWN_FLAGS); + /* + * Ignore errors from failing to allocate the new fence, we can't + * handle an error right now. Worst case should be missed + * synchronisation leading to rendering corruption. + */ + reservation_object_lock(resv, NULL); + if (flags & EXEC_OBJECT_WRITE) + reservation_object_add_excl_fence(resv, &req->fence); + else if (reservation_object_reserve_shared(resv) == 0) + reservation_object_add_shared_fence(resv, &req->fence); + reservation_object_unlock(resv); +} - invalid_flags = __EXEC_OBJECT_UNKNOWN_FLAGS; - if (USES_FULL_PPGTT(dev)) - invalid_flags |= EXEC_OBJECT_NEEDS_GTT; +static int eb_move_to_gpu(struct i915_execbuffer *eb) +{ + const unsigned int count = eb->buffer_count; + unsigned int i; + int err; for (i = 0; i < count; i++) { - char __user *ptr = u64_to_user_ptr(exec[i].relocs_ptr); - int length; /* limited by fault_in_pages_readable() */ + const struct drm_i915_gem_exec_object2 *entry = &eb->exec[i]; + struct i915_vma *vma = exec_to_vma(entry); + struct drm_i915_gem_object *obj = vma->obj; - if (exec[i].flags & invalid_flags) - return -EINVAL; + if (entry->flags & EXEC_OBJECT_CAPTURE) { + struct i915_gem_capture_list *capture; - /* Offset can be used as input (EXEC_OBJECT_PINNED), reject - * any non-page-aligned or non-canonical addresses. - */ - if (exec[i].flags & EXEC_OBJECT_PINNED) { - if (exec[i].offset != - gen8_canonical_addr(exec[i].offset & PAGE_MASK)) - return -EINVAL; + capture = kmalloc(sizeof(*capture), GFP_KERNEL); + if (unlikely(!capture)) + return -ENOMEM; + + capture->next = eb->request->capture_list; + capture->vma = vma; + eb->request->capture_list = capture; } - /* From drm_mm perspective address space is continuous, - * so from this point we're always using non-canonical - * form internally. - */ - exec[i].offset = gen8_noncanonical_addr(exec[i].offset); + if (entry->flags & EXEC_OBJECT_ASYNC) + goto skip_flushes; - if (exec[i].alignment && !is_power_of_2(exec[i].alignment)) - return -EINVAL; + if (unlikely(obj->cache_dirty && !obj->cache_coherent)) + i915_gem_clflush_object(obj, 0); - /* pad_to_size was once a reserved field, so sanitize it */ - if (exec[i].flags & EXEC_OBJECT_PAD_TO_SIZE) { - if (offset_in_page(exec[i].pad_to_size)) - return -EINVAL; - } else { - exec[i].pad_to_size = 0; - } + err = i915_gem_request_await_object + (eb->request, obj, entry->flags & EXEC_OBJECT_WRITE); + if (err) + return err; - /* First check for malicious input causing overflow in - * the worst case where we need to allocate the entire - * relocation tree as a single array. - */ - if (exec[i].relocation_count > relocs_max - relocs_total) - return -EINVAL; - relocs_total += exec[i].relocation_count; +skip_flushes: + i915_vma_move_to_active(vma, eb->request, entry->flags); + __eb_unreserve_vma(vma, entry); + vma->exec_entry = NULL; + } - length = exec[i].relocation_count * - sizeof(struct drm_i915_gem_relocation_entry); - /* - * We must check that the entire relocation array is safe - * to read, but since we may need to update the presumed - * offsets during execution, check for full write access. - */ - if (!access_ok(VERIFY_WRITE, ptr, length)) - return -EFAULT; + for (i = 0; i < count; i++) { + const struct drm_i915_gem_exec_object2 *entry = &eb->exec[i]; + struct i915_vma *vma = exec_to_vma(entry); - if (likely(!i915.prefault_disable)) { - if (fault_in_pages_readable(ptr, length)) - return -EFAULT; - } + eb_export_fence(vma, eb->request, entry->flags); + if (unlikely(entry->flags & __EXEC_OBJECT_HAS_REF)) + i915_vma_put(vma); } + eb->exec = NULL; - return 0; + /* Unconditionally flush any chipset caches (for streaming writes). */ + i915_gem_chipset_flush(eb->i915); + + /* Unconditionally invalidate GPU caches and TLBs. */ + return eb->engine->emit_flush(eb->request, EMIT_INVALIDATE); } -static struct i915_gem_context * -i915_gem_validate_context(struct drm_device *dev, struct drm_file *file, - struct intel_engine_cs *engine, const u32 ctx_id) +static bool i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec) { - struct i915_gem_context *ctx; + if (exec->flags & __I915_EXEC_ILLEGAL_FLAGS) + return false; - ctx = i915_gem_context_lookup(file->driver_priv, ctx_id); - if (IS_ERR(ctx)) - return ctx; + /* Kernel clipping was a DRI1 misfeature */ + if (exec->num_cliprects || exec->cliprects_ptr) + return false; - if (i915_gem_context_is_banned(ctx)) { - DRM_DEBUG("Context %u tried to submit while banned\n", ctx_id); - return ERR_PTR(-EIO); + if (exec->DR4 == 0xffffffff) { + DRM_DEBUG("UXA submitting garbage DR4, fixing up\n"); + exec->DR4 = 0; } + if (exec->DR1 || exec->DR4) + return false; - return ctx; -} + if ((exec->batch_start_offset | exec->batch_len) & 0x7) + return false; -static bool gpu_write_needs_clflush(struct drm_i915_gem_object *obj) -{ - return !(obj->cache_level == I915_CACHE_NONE || - obj->cache_level == I915_CACHE_WT); + return true; } void i915_vma_move_to_active(struct i915_vma *vma, @@ -1269,7 +1900,8 @@ void i915_vma_move_to_active(struct i915_vma *vma, lockdep_assert_held(&req->i915->drm.struct_mutex); GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); - /* Add a reference if we're newly entering the active list. + /* + * Add a reference if we're newly entering the active list. * The order in which we add operations to the retirement queue is * vital here: mark_active adds to the start of the callback list, * such that subsequent callbacks are called first. Therefore we @@ -1282,61 +1914,22 @@ void i915_vma_move_to_active(struct i915_vma *vma, i915_gem_active_set(&vma->last_read[idx], req); list_move_tail(&vma->vm_link, &vma->vm->active_list); + obj->base.write_domain = 0; if (flags & EXEC_OBJECT_WRITE) { + obj->base.write_domain = I915_GEM_DOMAIN_RENDER; + if (intel_fb_obj_invalidate(obj, ORIGIN_CS)) i915_gem_active_set(&obj->frontbuffer_write, req); - /* update for the implicit flush after a batch */ - obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS; - if (!obj->cache_dirty && gpu_write_needs_clflush(obj)) - obj->cache_dirty = true; + obj->base.read_domains = 0; } + obj->base.read_domains |= I915_GEM_GPU_DOMAINS; if (flags & EXEC_OBJECT_NEEDS_FENCE) i915_gem_active_set(&vma->last_fence, req); } -static void eb_export_fence(struct drm_i915_gem_object *obj, - struct drm_i915_gem_request *req, - unsigned int flags) -{ - struct reservation_object *resv = obj->resv; - - /* Ignore errors from failing to allocate the new fence, we can't - * handle an error right now. Worst case should be missed - * synchronisation leading to rendering corruption. - */ - reservation_object_lock(resv, NULL); - if (flags & EXEC_OBJECT_WRITE) - reservation_object_add_excl_fence(resv, &req->fence); - else if (reservation_object_reserve_shared(resv) == 0) - reservation_object_add_shared_fence(resv, &req->fence); - reservation_object_unlock(resv); -} - -static void -i915_gem_execbuffer_move_to_active(struct list_head *vmas, - struct drm_i915_gem_request *req) -{ - struct i915_vma *vma; - - list_for_each_entry(vma, vmas, exec_list) { - struct drm_i915_gem_object *obj = vma->obj; - - obj->base.write_domain = obj->base.pending_write_domain; - if (obj->base.write_domain) - vma->exec_entry->flags |= EXEC_OBJECT_WRITE; - else - obj->base.pending_read_domains |= obj->base.read_domains; - obj->base.read_domains = obj->base.pending_read_domains; - - i915_vma_move_to_active(vma, req, vma->exec_entry->flags); - eb_export_fence(obj, req, vma->exec_entry->flags); - } -} - -static int -i915_reset_gen7_sol_offsets(struct drm_i915_gem_request *req) +static int i915_reset_gen7_sol_offsets(struct drm_i915_gem_request *req) { u32 *cs; int i; @@ -1346,50 +1939,43 @@ i915_reset_gen7_sol_offsets(struct drm_i915_gem_request *req) return -EINVAL; } - cs = intel_ring_begin(req, 4 * 3); + cs = intel_ring_begin(req, 4 * 2 + 2); if (IS_ERR(cs)) return PTR_ERR(cs); + *cs++ = MI_LOAD_REGISTER_IMM(4); for (i = 0; i < 4; i++) { - *cs++ = MI_LOAD_REGISTER_IMM(1); *cs++ = i915_mmio_reg_offset(GEN7_SO_WRITE_OFFSET(i)); *cs++ = 0; } - + *cs++ = MI_NOOP; intel_ring_advance(req, cs); return 0; } -static struct i915_vma * -i915_gem_execbuffer_parse(struct intel_engine_cs *engine, - struct drm_i915_gem_exec_object2 *shadow_exec_entry, - struct drm_i915_gem_object *batch_obj, - struct eb_vmas *eb, - u32 batch_start_offset, - u32 batch_len, - bool is_master) +static struct i915_vma *eb_parse(struct i915_execbuffer *eb, bool is_master) { struct drm_i915_gem_object *shadow_batch_obj; struct i915_vma *vma; - int ret; + int err; - shadow_batch_obj = i915_gem_batch_pool_get(&engine->batch_pool, - PAGE_ALIGN(batch_len)); + shadow_batch_obj = i915_gem_batch_pool_get(&eb->engine->batch_pool, + PAGE_ALIGN(eb->batch_len)); if (IS_ERR(shadow_batch_obj)) return ERR_CAST(shadow_batch_obj); - ret = intel_engine_cmd_parser(engine, - batch_obj, + err = intel_engine_cmd_parser(eb->engine, + eb->batch->obj, shadow_batch_obj, - batch_start_offset, - batch_len, + eb->batch_start_offset, + eb->batch_len, is_master); - if (ret) { - if (ret == -EACCES) /* unhandled chained batch */ + if (err) { + if (err == -EACCES) /* unhandled chained batch */ vma = NULL; else - vma = ERR_PTR(ret); + vma = ERR_PTR(err); goto out; } @@ -1397,12 +1983,11 @@ i915_gem_execbuffer_parse(struct intel_engine_cs *engine, if (IS_ERR(vma)) goto out; - memset(shadow_exec_entry, 0, sizeof(*shadow_exec_entry)); - - vma->exec_entry = shadow_exec_entry; - vma->exec_entry->flags = __EXEC_OBJECT_HAS_PIN; - i915_gem_object_get(shadow_batch_obj); - list_add_tail(&vma->exec_list, &eb->vmas); + vma->exec_entry = + memset(&eb->exec[eb->buffer_count++], + 0, sizeof(*vma->exec_entry)); + vma->exec_entry->flags = __EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_REF; + __exec_to_vma(vma->exec_entry) = (uintptr_t)i915_vma_get(vma); out: i915_gem_object_unpin_pages(shadow_batch_obj); @@ -1410,54 +1995,37 @@ out: } static void -add_to_client(struct drm_i915_gem_request *req, - struct drm_file *file) +add_to_client(struct drm_i915_gem_request *req, struct drm_file *file) { req->file_priv = file->driver_priv; list_add_tail(&req->client_link, &req->file_priv->mm.request_list); } -static int -execbuf_submit(struct i915_execbuffer_params *params, - struct drm_i915_gem_execbuffer2 *args, - struct list_head *vmas) +static int eb_submit(struct i915_execbuffer *eb) { - u64 exec_start, exec_len; - int ret; - - ret = i915_gem_execbuffer_move_to_gpu(params->request, vmas); - if (ret) - return ret; + int err; - ret = i915_switch_context(params->request); - if (ret) - return ret; + err = eb_move_to_gpu(eb); + if (err) + return err; - if (args->flags & I915_EXEC_CONSTANTS_MASK) { - DRM_DEBUG("I915_EXEC_CONSTANTS_* unsupported\n"); - return -EINVAL; - } + err = i915_switch_context(eb->request); + if (err) + return err; - if (args->flags & I915_EXEC_GEN7_SOL_RESET) { - ret = i915_reset_gen7_sol_offsets(params->request); - if (ret) - return ret; + if (eb->args->flags & I915_EXEC_GEN7_SOL_RESET) { + err = i915_reset_gen7_sol_offsets(eb->request); + if (err) + return err; } - exec_len = args->batch_len; - exec_start = params->batch->node.start + - params->args_batch_start_offset; - - if (exec_len == 0) - exec_len = params->batch->size - params->args_batch_start_offset; - - ret = params->engine->emit_bb_start(params->request, - exec_start, exec_len, - params->dispatch_flags); - if (ret) - return ret; - - i915_gem_execbuffer_move_to_active(vmas, params->request); + err = eb->engine->emit_bb_start(eb->request, + eb->batch->node.start + + eb->batch_start_offset, + eb->batch_len, + eb->batch_flags); + if (err) + return err; return 0; } @@ -1539,66 +2107,62 @@ eb_select_engine(struct drm_i915_private *dev_priv, } static int -i915_gem_do_execbuffer(struct drm_device *dev, void *data, +i915_gem_do_execbuffer(struct drm_device *dev, struct drm_file *file, struct drm_i915_gem_execbuffer2 *args, struct drm_i915_gem_exec_object2 *exec) { - struct drm_i915_private *dev_priv = to_i915(dev); - struct i915_ggtt *ggtt = &dev_priv->ggtt; - struct eb_vmas *eb; - struct drm_i915_gem_exec_object2 shadow_exec_entry; - struct intel_engine_cs *engine; - struct i915_gem_context *ctx; - struct i915_address_space *vm; - struct i915_execbuffer_params params_master; /* XXX: will be removed later */ - struct i915_execbuffer_params *params = ¶ms_master; - const u32 ctx_id = i915_execbuffer2_get_context_id(*args); - u32 dispatch_flags; + struct i915_execbuffer eb; struct dma_fence *in_fence = NULL; struct sync_file *out_fence = NULL; int out_fence_fd = -1; - int ret; - bool need_relocs; - - if (!i915_gem_check_execbuffer(args)) - return -EINVAL; - - ret = validate_exec_list(dev, exec, args->buffer_count); - if (ret) - return ret; - - dispatch_flags = 0; + int err; + + BUILD_BUG_ON(__EXEC_OBJECT_INTERNAL_FLAGS & + ~__EXEC_OBJECT_UNKNOWN_FLAGS); + + eb.i915 = to_i915(dev); + eb.file = file; + eb.args = args; + if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC)) + args->flags |= __EXEC_HAS_RELOC; + eb.exec = exec; + eb.ctx = NULL; + eb.invalid_flags = __EXEC_OBJECT_UNKNOWN_FLAGS; + if (USES_FULL_PPGTT(eb.i915)) + eb.invalid_flags |= EXEC_OBJECT_NEEDS_GTT; + reloc_cache_init(&eb.reloc_cache, eb.i915); + + eb.buffer_count = args->buffer_count; + eb.batch_start_offset = args->batch_start_offset; + eb.batch_len = args->batch_len; + + eb.batch_flags = 0; if (args->flags & I915_EXEC_SECURE) { if (!drm_is_current_master(file) || !capable(CAP_SYS_ADMIN)) return -EPERM; - dispatch_flags |= I915_DISPATCH_SECURE; + eb.batch_flags |= I915_DISPATCH_SECURE; } if (args->flags & I915_EXEC_IS_PINNED) - dispatch_flags |= I915_DISPATCH_PINNED; + eb.batch_flags |= I915_DISPATCH_PINNED; - engine = eb_select_engine(dev_priv, file, args); - if (!engine) + eb.engine = eb_select_engine(eb.i915, file, args); + if (!eb.engine) return -EINVAL; - if (args->buffer_count < 1) { - DRM_DEBUG("execbuf with %d buffers\n", args->buffer_count); - return -EINVAL; - } - if (args->flags & I915_EXEC_RESOURCE_STREAMER) { - if (!HAS_RESOURCE_STREAMER(dev_priv)) { + if (!HAS_RESOURCE_STREAMER(eb.i915)) { DRM_DEBUG("RS is only allowed for Haswell, Gen8 and above\n"); return -EINVAL; } - if (engine->id != RCS) { + if (eb.engine->id != RCS) { DRM_DEBUG("RS is not available on %s\n", - engine->name); + eb.engine->name); return -EINVAL; } - dispatch_flags |= I915_DISPATCH_RS; + eb.batch_flags |= I915_DISPATCH_RS; } if (args->flags & I915_EXEC_FENCE_IN) { @@ -1610,102 +2174,62 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, if (args->flags & I915_EXEC_FENCE_OUT) { out_fence_fd = get_unused_fd_flags(O_CLOEXEC); if (out_fence_fd < 0) { - ret = out_fence_fd; + err = out_fence_fd; goto err_in_fence; } } - /* Take a local wakeref for preparing to dispatch the execbuf as + if (eb_create(&eb)) + return -ENOMEM; + + /* + * Take a local wakeref for preparing to dispatch the execbuf as * we expect to access the hardware fairly frequently in the * process. Upon first dispatch, we acquire another prolonged * wakeref that we hold until the GPU has been idle for at least * 100ms. */ - intel_runtime_pm_get(dev_priv); - - ret = i915_mutex_lock_interruptible(dev); - if (ret) - goto pre_mutex_err; + intel_runtime_pm_get(eb.i915); + err = i915_mutex_lock_interruptible(dev); + if (err) + goto err_rpm; - ctx = i915_gem_validate_context(dev, file, engine, ctx_id); - if (IS_ERR(ctx)) { - mutex_unlock(&dev->struct_mutex); - ret = PTR_ERR(ctx); - goto pre_mutex_err; - } - - i915_gem_context_get(ctx); - - if (ctx->ppgtt) - vm = &ctx->ppgtt->base; - else - vm = &ggtt->base; - - memset(¶ms_master, 0x00, sizeof(params_master)); + err = eb_select_context(&eb); + if (unlikely(err)) + goto err_unlock; - eb = eb_create(dev_priv, args); - if (eb == NULL) { - i915_gem_context_put(ctx); - mutex_unlock(&dev->struct_mutex); - ret = -ENOMEM; - goto pre_mutex_err; - } - - /* Look up object handles */ - ret = eb_lookup_vmas(eb, exec, args, vm, file); - if (ret) - goto err; - - /* take note of the batch buffer before we might reorder the lists */ - params->batch = eb_get_batch(eb); - - /* Move the objects en-masse into the GTT, evicting if necessary. */ - need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0; - ret = i915_gem_execbuffer_reserve(engine, &eb->vmas, ctx, - &need_relocs); - if (ret) - goto err; - - /* The objects are in their final locations, apply the relocations. */ - if (need_relocs) - ret = i915_gem_execbuffer_relocate(eb); - if (ret) { - if (ret == -EFAULT) { - ret = i915_gem_execbuffer_relocate_slow(dev, args, file, - engine, - eb, exec, ctx); - BUG_ON(!mutex_is_locked(&dev->struct_mutex)); - } - if (ret) - goto err; - } + err = eb_relocate(&eb); + if (err) + /* + * If the user expects the execobject.offset and + * reloc.presumed_offset to be an exact match, + * as for using NO_RELOC, then we cannot update + * the execobject.offset until we have completed + * relocation. + */ + args->flags &= ~__EXEC_HAS_RELOC; + if (err < 0) + goto err_vma; - /* Set the pending read domains for the batch buffer to COMMAND */ - if (params->batch->obj->base.pending_write_domain) { + if (unlikely(eb.batch->exec_entry->flags & EXEC_OBJECT_WRITE)) { DRM_DEBUG("Attempting to use self-modifying batch buffer\n"); - ret = -EINVAL; - goto err; + err = -EINVAL; + goto err_vma; } - if (args->batch_start_offset > params->batch->size || - args->batch_len > params->batch->size - args->batch_start_offset) { + if (eb.batch_start_offset > eb.batch->size || + eb.batch_len > eb.batch->size - eb.batch_start_offset) { DRM_DEBUG("Attempting to use out-of-bounds batch\n"); - ret = -EINVAL; - goto err; + err = -EINVAL; + goto err_vma; } - params->args_batch_start_offset = args->batch_start_offset; - if (engine->needs_cmd_parser && args->batch_len) { + if (eb.engine->needs_cmd_parser && eb.batch_len) { struct i915_vma *vma; - vma = i915_gem_execbuffer_parse(engine, &shadow_exec_entry, - params->batch->obj, - eb, - args->batch_start_offset, - args->batch_len, - drm_is_current_master(file)); + vma = eb_parse(&eb, drm_is_current_master(file)); if (IS_ERR(vma)) { - ret = PTR_ERR(vma); - goto err; + err = PTR_ERR(vma); + goto err_vma; } if (vma) { @@ -1718,19 +2242,20 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, * specifically don't want that set on batches the * command parser has accepted. */ - dispatch_flags |= I915_DISPATCH_SECURE; - params->args_batch_start_offset = 0; - params->batch = vma; + eb.batch_flags |= I915_DISPATCH_SECURE; + eb.batch_start_offset = 0; + eb.batch = vma; } } - params->batch->obj->base.pending_read_domains |= I915_GEM_DOMAIN_COMMAND; + if (eb.batch_len == 0) + eb.batch_len = eb.batch->size - eb.batch_start_offset; - /* snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure + /* + * snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure * batch" bit. Hence we need to pin secure batches into the global gtt. * hsw should have this fixed, but bdw mucks it up again. */ - if (dispatch_flags & I915_DISPATCH_SECURE) { - struct drm_i915_gem_object *obj = params->batch->obj; + if (eb.batch_flags & I915_DISPATCH_SECURE) { struct i915_vma *vma; /* @@ -1743,66 +2268,56 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, * fitting due to fragmentation. * So this is actually safe. */ - vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, 0); + vma = i915_gem_object_ggtt_pin(eb.batch->obj, NULL, 0, 0, 0); if (IS_ERR(vma)) { - ret = PTR_ERR(vma); - goto err; + err = PTR_ERR(vma); + goto err_vma; } - params->batch = vma; + eb.batch = vma; } + /* All GPU relocation batches must be submitted prior to the user rq */ + GEM_BUG_ON(eb.reloc_cache.rq); + /* Allocate a request for this batch buffer nice and early. */ - params->request = i915_gem_request_alloc(engine, ctx); - if (IS_ERR(params->request)) { - ret = PTR_ERR(params->request); + eb.request = i915_gem_request_alloc(eb.engine, eb.ctx); + if (IS_ERR(eb.request)) { + err = PTR_ERR(eb.request); goto err_batch_unpin; } if (in_fence) { - ret = i915_gem_request_await_dma_fence(params->request, - in_fence); - if (ret < 0) + err = i915_gem_request_await_dma_fence(eb.request, in_fence); + if (err < 0) goto err_request; } if (out_fence_fd != -1) { - out_fence = sync_file_create(¶ms->request->fence); + out_fence = sync_file_create(&eb.request->fence); if (!out_fence) { - ret = -ENOMEM; + err = -ENOMEM; goto err_request; } } - /* Whilst this request exists, batch_obj will be on the + /* + * Whilst this request exists, batch_obj will be on the * active_list, and so will hold the active reference. Only when this * request is retired will the the batch_obj be moved onto the * inactive_list and lose its active reference. Hence we do not need * to explicitly hold another reference here. */ - params->request->batch = params->batch; - - /* - * Save assorted stuff away to pass through to *_submission(). - * NB: This data should be 'persistent' and not local as it will - * kept around beyond the duration of the IOCTL once the GPU - * scheduler arrives. - */ - params->dev = dev; - params->file = file; - params->engine = engine; - params->dispatch_flags = dispatch_flags; - params->ctx = ctx; - - trace_i915_gem_request_queue(params->request, dispatch_flags); + eb.request->batch = eb.batch; - ret = execbuf_submit(params, args, &eb->vmas); + trace_i915_gem_request_queue(eb.request, eb.batch_flags); + err = eb_submit(&eb); err_request: - __i915_add_request(params->request, ret == 0); - add_to_client(params->request, file); + __i915_add_request(eb.request, err == 0); + add_to_client(eb.request, file); if (out_fence) { - if (ret == 0) { + if (err == 0) { fd_install(out_fence_fd, out_fence->file); args->rsvd2 &= GENMASK_ULL(0, 31); /* keep in-fence */ args->rsvd2 |= (u64)out_fence_fd << 32; @@ -1813,30 +2328,22 @@ err_request: } err_batch_unpin: - /* - * FIXME: We crucially rely upon the active tracking for the (ppgtt) - * batch vma for correctness. For less ugly and less fragility this - * needs to be adjusted to also track the ggtt batch vma properly as - * active. - */ - if (dispatch_flags & I915_DISPATCH_SECURE) - i915_vma_unpin(params->batch); -err: - /* the request owns the ref now */ - i915_gem_context_put(ctx); - eb_destroy(eb); - + if (eb.batch_flags & I915_DISPATCH_SECURE) + i915_vma_unpin(eb.batch); +err_vma: + if (eb.exec) + eb_release_vmas(&eb); + i915_gem_context_put(eb.ctx); +err_unlock: mutex_unlock(&dev->struct_mutex); - -pre_mutex_err: - /* intel_gpu_busy should also get a ref, so it will free when the device - * is really idle. */ - intel_runtime_pm_put(dev_priv); +err_rpm: + intel_runtime_pm_put(eb.i915); + eb_destroy(&eb); if (out_fence_fd != -1) put_unused_fd(out_fence_fd); err_in_fence: dma_fence_put(in_fence); - return ret; + return err; } /* @@ -1847,20 +2354,38 @@ int i915_gem_execbuffer(struct drm_device *dev, void *data, struct drm_file *file) { + const size_t sz = sizeof(struct drm_i915_gem_exec_object2); struct drm_i915_gem_execbuffer *args = data; struct drm_i915_gem_execbuffer2 exec2; struct drm_i915_gem_exec_object *exec_list = NULL; struct drm_i915_gem_exec_object2 *exec2_list = NULL; - int ret, i; + unsigned int i; + int err; - if (args->buffer_count < 1) { - DRM_DEBUG("execbuf with %d buffers\n", args->buffer_count); + if (args->buffer_count < 1 || args->buffer_count > SIZE_MAX / sz - 1) { + DRM_DEBUG("execbuf2 with %d buffers\n", args->buffer_count); return -EINVAL; } + exec2.buffers_ptr = args->buffers_ptr; + exec2.buffer_count = args->buffer_count; + exec2.batch_start_offset = args->batch_start_offset; + exec2.batch_len = args->batch_len; + exec2.DR1 = args->DR1; + exec2.DR4 = args->DR4; + exec2.num_cliprects = args->num_cliprects; + exec2.cliprects_ptr = args->cliprects_ptr; + exec2.flags = I915_EXEC_RENDER; + i915_execbuffer2_set_context_id(exec2, 0); + + if (!i915_gem_check_execbuffer(&exec2)) + return -EINVAL; + /* Copy in the exec list from userland */ - exec_list = kvmalloc_array(sizeof(*exec_list), args->buffer_count, GFP_KERNEL); - exec2_list = kvmalloc_array(sizeof(*exec2_list), args->buffer_count, GFP_KERNEL); + exec_list = kvmalloc_array(args->buffer_count, sizeof(*exec_list), + __GFP_NOWARN | GFP_TEMPORARY); + exec2_list = kvmalloc_array(args->buffer_count + 1, sz, + __GFP_NOWARN | GFP_TEMPORARY); if (exec_list == NULL || exec2_list == NULL) { DRM_DEBUG("Failed to allocate exec list for %d buffers\n", args->buffer_count); @@ -1868,12 +2393,12 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, kvfree(exec2_list); return -ENOMEM; } - ret = copy_from_user(exec_list, + err = copy_from_user(exec_list, u64_to_user_ptr(args->buffers_ptr), sizeof(*exec_list) * args->buffer_count); - if (ret != 0) { + if (err) { DRM_DEBUG("copy %d exec entries failed %d\n", - args->buffer_count, ret); + args->buffer_count, err); kvfree(exec_list); kvfree(exec2_list); return -EFAULT; @@ -1891,99 +2416,94 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, exec2_list[i].flags = 0; } - exec2.buffers_ptr = args->buffers_ptr; - exec2.buffer_count = args->buffer_count; - exec2.batch_start_offset = args->batch_start_offset; - exec2.batch_len = args->batch_len; - exec2.DR1 = args->DR1; - exec2.DR4 = args->DR4; - exec2.num_cliprects = args->num_cliprects; - exec2.cliprects_ptr = args->cliprects_ptr; - exec2.flags = I915_EXEC_RENDER; - i915_execbuffer2_set_context_id(exec2, 0); - - ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list); - if (!ret) { + err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list); + if (exec2.flags & __EXEC_HAS_RELOC) { struct drm_i915_gem_exec_object __user *user_exec_list = u64_to_user_ptr(args->buffers_ptr); /* Copy the new buffer offsets back to the user's exec list. */ for (i = 0; i < args->buffer_count; i++) { + if (!(exec2_list[i].offset & UPDATE)) + continue; + exec2_list[i].offset = - gen8_canonical_addr(exec2_list[i].offset); - ret = __copy_to_user(&user_exec_list[i].offset, - &exec2_list[i].offset, - sizeof(user_exec_list[i].offset)); - if (ret) { - ret = -EFAULT; - DRM_DEBUG("failed to copy %d exec entries " - "back to user (%d)\n", - args->buffer_count, ret); + gen8_canonical_addr(exec2_list[i].offset & PIN_OFFSET_MASK); + exec2_list[i].offset &= PIN_OFFSET_MASK; + if (__copy_to_user(&user_exec_list[i].offset, + &exec2_list[i].offset, + sizeof(user_exec_list[i].offset))) break; - } } } kvfree(exec_list); kvfree(exec2_list); - return ret; + return err; } int i915_gem_execbuffer2(struct drm_device *dev, void *data, struct drm_file *file) { + const size_t sz = sizeof(struct drm_i915_gem_exec_object2); struct drm_i915_gem_execbuffer2 *args = data; - struct drm_i915_gem_exec_object2 *exec2_list = NULL; - int ret; + struct drm_i915_gem_exec_object2 *exec2_list; + int err; - if (args->buffer_count < 1 || - args->buffer_count > UINT_MAX / sizeof(*exec2_list)) { + if (args->buffer_count < 1 || args->buffer_count > SIZE_MAX / sz - 1) { DRM_DEBUG("execbuf2 with %d buffers\n", args->buffer_count); return -EINVAL; } - exec2_list = kvmalloc_array(args->buffer_count, - sizeof(*exec2_list), - GFP_TEMPORARY); + if (!i915_gem_check_execbuffer(args)) + return -EINVAL; + + /* Allocate an extra slot for use by the command parser */ + exec2_list = kvmalloc_array(args->buffer_count + 1, sz, + __GFP_NOWARN | GFP_TEMPORARY); if (exec2_list == NULL) { DRM_DEBUG("Failed to allocate exec list for %d buffers\n", args->buffer_count); return -ENOMEM; } - ret = copy_from_user(exec2_list, - u64_to_user_ptr(args->buffers_ptr), - sizeof(*exec2_list) * args->buffer_count); - if (ret != 0) { - DRM_DEBUG("copy %d exec entries failed %d\n", - args->buffer_count, ret); + if (copy_from_user(exec2_list, + u64_to_user_ptr(args->buffers_ptr), + sizeof(*exec2_list) * args->buffer_count)) { + DRM_DEBUG("copy %d exec entries failed\n", args->buffer_count); kvfree(exec2_list); return -EFAULT; } - ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list); - if (!ret) { - /* Copy the new buffer offsets back to the user's exec list. */ + err = i915_gem_do_execbuffer(dev, file, args, exec2_list); + + /* + * Now that we have begun execution of the batchbuffer, we ignore + * any new error after this point. Also given that we have already + * updated the associated relocations, we try to write out the current + * object locations irrespective of any error. + */ + if (args->flags & __EXEC_HAS_RELOC) { struct drm_i915_gem_exec_object2 __user *user_exec_list = - u64_to_user_ptr(args->buffers_ptr); - int i; + u64_to_user_ptr(args->buffers_ptr); + unsigned int i; + /* Copy the new buffer offsets back to the user's exec list. */ + user_access_begin(); for (i = 0; i < args->buffer_count; i++) { + if (!(exec2_list[i].offset & UPDATE)) + continue; + exec2_list[i].offset = - gen8_canonical_addr(exec2_list[i].offset); - ret = __copy_to_user(&user_exec_list[i].offset, - &exec2_list[i].offset, - sizeof(user_exec_list[i].offset)); - if (ret) { - ret = -EFAULT; - DRM_DEBUG("failed to copy %d exec entries " - "back to user\n", - args->buffer_count); - break; - } + gen8_canonical_addr(exec2_list[i].offset & PIN_OFFSET_MASK); + unsafe_put_user(exec2_list[i].offset, + &user_exec_list[i].offset, + end_user); } +end_user: + user_access_end(); } + args->flags &= ~__I915_EXEC_UNKNOWN_FLAGS; kvfree(exec2_list); - return ret; + return err; } |