/*
 * SPDX-License-Identifier: MIT
 *
 * Copyright © 2008,2010 Intel Corporation
 */

#include <linux/intel-iommu.h>
#include <linux/dma-resv.h>
#include <linux/sync_file.h>
#include <linux/uaccess.h>

#include <drm/drm_syncobj.h>

#include "display/intel_frontbuffer.h"

#include "gem/i915_gem_ioctls.h"
#include "gt/intel_context.h"
#include "gt/intel_gpu_commands.h"
#include "gt/intel_gt.h"
#include "gt/intel_gt_buffer_pool.h"
#include "gt/intel_gt_pm.h"
#include "gt/intel_ring.h"

#include "i915_drv.h"
#include "i915_gem_clflush.h"
#include "i915_gem_context.h"
#include "i915_gem_ioctls.h"
#include "i915_trace.h"
#include "i915_user_extensions.h"

struct eb_vma {
        struct i915_vma *vma;
        unsigned int flags;

        /** This vma's place in the execbuf reservation list */
        struct drm_i915_gem_exec_object2 *exec;
        struct list_head bind_link;
        struct list_head reloc_link;

        struct hlist_node node;
        u32 handle;
};

enum {
        FORCE_CPU_RELOC = 1,
        FORCE_GTT_RELOC,
        FORCE_GPU_RELOC,
#define DBG_FORCE_RELOC 0 /* choose one of the above! */
};

/* __EXEC_OBJECT_NO_RESERVE is BIT(31), defined in i915_vma.h */
#define __EXEC_OBJECT_HAS_PIN           BIT(30)
#define __EXEC_OBJECT_HAS_FENCE         BIT(29)
#define __EXEC_OBJECT_USERPTR_INIT      BIT(28)
#define __EXEC_OBJECT_NEEDS_MAP         BIT(27)
#define __EXEC_OBJECT_NEEDS_BIAS        BIT(26)
#define __EXEC_OBJECT_INTERNAL_FLAGS    (~0u << 26) /* all of the above + */
#define __EXEC_OBJECT_RESERVED (__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_FENCE)

#define __EXEC_HAS_RELOC        BIT(31)
#define __EXEC_ENGINE_PINNED    BIT(30)
#define __EXEC_USERPTR_USED     BIT(29)
#define __EXEC_INTERNAL_FLAGS   (~0u << 29)
#define UPDATE                  PIN_OFFSET_FIXED

#define BATCH_OFFSET_BIAS (256*1024)

#define __I915_EXEC_ILLEGAL_FLAGS \
        (__I915_EXEC_UNKNOWN_FLAGS | \
         I915_EXEC_CONSTANTS_MASK  | \
         I915_EXEC_RESOURCE_STREAMER)

/* Catch emission of unexpected errors for CI! */
#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
#undef EINVAL
#define EINVAL ({ \
        DRM_DEBUG_DRIVER("EINVAL at %s:%d\n", __func__, __LINE__); \
        22; \
})
#endif

/**
 * 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.
 *
 * At the level of talking to the hardware, submitting a batchbuffer for the
 * GPU to execute is to add content to a buffer from which the HW
 * command streamer is reading.
 *
 * 1. Add a command to load the HW context. For Logical Ring Contexts, i.e.
 *    Execlists, this command is not placed on the same buffer as the
 *    remaining items.
 *
 * 2. Add a command to invalidate caches to the buffer.
 *
 * 3. Add a batchbuffer start command to the buffer; the start command is
 *    essentially a token together with the GPU address of the batchbuffer
 *    to be executed.
 *
 * 4. Add a pipeline flush to the buffer.
 *
 * 5. Add a memory write command to the buffer to record when the GPU
 *    is done executing the batchbuffer. The memory write writes the
 *    global sequence number of the request, ``i915_request::global_seqno``;
 *    the i915 driver uses the current value in the register to determine
 *    if the GPU has completed the batchbuffer.
 *
 * 6. Add a user interrupt command to the buffer. This command instructs
 *    the GPU to issue an interrupt when the command, pipeline flush and
 *    memory write are completed.
 *
 * 7. Inform the hardware of the additional commands added to the buffer
 *    (by updating the tail pointer).
 *
 * 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 eb_fence {
        struct drm_syncobj *syncobj; /* Use with ptr_mask_bits() */
        struct dma_fence *dma_fence;
        u64 value;
        struct dma_fence_chain *chain_fence;
};

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 eb_vma *vma;

        struct intel_engine_cs *engine; /** engine to queue the request to */
        struct intel_context *context; /* logical state for the request */
        struct i915_gem_context *gem_context; /** caller's context */

        struct i915_request *request; /** our request to build */
        struct eb_vma *batch; /** identity of the batch obj/vma */
        struct i915_vma *trampoline; /** trampoline used for chaining */

        /** 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 i915_gem_ww_ctx ww;

        /**
         * 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 graphics_ver; /** Cached value of GRAPHICS_VER */
                bool use_64bit_reloc : 1;
                bool has_llc : 1;
                bool has_fence : 1;
                bool needs_unfenced : 1;

                struct i915_request *rq;
                u32 *rq_cmd;
                unsigned int rq_size;
                struct intel_gt_buffer_pool_node *pool;
        } reloc_cache;

        struct intel_gt_buffer_pool_node *reloc_pool; /** relocation pool for -EDEADLK handling */
        struct intel_context *reloc_context;

        u64 invalid_flags; /** Set of execobj.flags that are invalid */
        u32 context_flags; /** Set of execobj.flags to insert from the ctx */

        u64 batch_len; /** Length of batch within object */
        u32 batch_start_offset; /** Location within object of batch */
        u32 batch_flags; /** Flags composed for emit_bb_start() */
        struct intel_gt_buffer_pool_node *batch_pool; /** pool node for batch buffer */

        /**
         * 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 */

        struct eb_fence *fences;
        unsigned long num_fences;
};

static int eb_parse(struct i915_execbuffer *eb);
static struct i915_request *eb_pin_engine(struct i915_execbuffer *eb,
                                          bool throttle);
static void eb_unpin_engine(struct i915_execbuffer *eb);

static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
{
        return intel_engine_requires_cmd_parser(eb->engine) ||
                (intel_engine_using_cmd_parser(eb->engine) &&
                 eb->args->batch_len);
}

static int eb_create(struct i915_execbuffer *eb)
{
        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 {
                        gfp_t flags;

                        /* While we can still reduce the allocation size, don't
                         * raise a warning and allow the allocation to fail.
                         * On the last pass though, we want to try as hard
                         * as possible to perform the allocation and warn
                         * if it fails.
                         */
                        flags = GFP_KERNEL;
                        if (size > 1)
                                flags |= __GFP_NORETRY | __GFP_NOWARN;

                        eb->buckets = kzalloc(sizeof(struct hlist_head) << size,
                                              flags);
                        if (eb->buckets)
                                break;
                } while (--size);

                if (unlikely(!size))
                        return -ENOMEM;

                eb->lut_size = size;
        } else {
                eb->lut_size = -eb->buffer_count;
        }

        return 0;
}

static bool
eb_vma_misplaced(const struct drm_i915_gem_exec_object2 *entry,
                 const struct i915_vma *vma,
                 unsigned int flags)
{
        if (vma->node.size < entry->pad_to_size)
                return true;

        if (entry->alignment && !IS_ALIGNED(vma->node.start, entry->alignment))
                return true;

        if (flags & EXEC_OBJECT_PINNED &&
            vma->node.start != entry->offset)
                return true;

        if (flags & __EXEC_OBJECT_NEEDS_BIAS &&
            vma->node.start < BATCH_OFFSET_BIAS)
                return true;

        if (!(flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS) &&
            (vma->node.start + vma->node.size + 4095) >> 32)
                return true;

        if (flags & __EXEC_OBJECT_NEEDS_MAP &&
            !i915_vma_is_map_and_fenceable(vma))
                return true;

        return false;
}

static u64 eb_pin_flags(const struct drm_i915_gem_exec_object2 *entry,
                        unsigned int exec_flags)
{
        u64 pin_flags = 0;

        if (exec_flags & EXEC_OBJECT_NEEDS_GTT)
                pin_flags |= PIN_GLOBAL;

        /*
         * Wa32bitGeneralStateOffset & Wa32bitInstructionBaseOffset,
         * limit address to the first 4GBs for unflagged objects.
         */
        if (!(exec_flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS))
                pin_flags |= PIN_ZONE_4G;

        if (exec_flags & __EXEC_OBJECT_NEEDS_MAP)
                pin_flags |= PIN_MAPPABLE;

        if (exec_flags & EXEC_OBJECT_PINNED)
                pin_flags |= entry->offset | PIN_OFFSET_FIXED;
        else if (exec_flags & __EXEC_OBJECT_NEEDS_BIAS)
                pin_flags |= BATCH_OFFSET_BIAS | PIN_OFFSET_BIAS;

        return pin_flags;
}

static inline int
eb_pin_vma(struct i915_execbuffer *eb,
           const struct drm_i915_gem_exec_object2 *entry,
           struct eb_vma *ev)
{
        struct i915_vma *vma = ev->vma;
        u64 pin_flags;
        int err;

        if (vma->node.size)
                pin_flags = vma->node.start;
        else
                pin_flags = entry->offset & PIN_OFFSET_MASK;

        pin_flags |= PIN_USER | PIN_NOEVICT | PIN_OFFSET_FIXED;
        if (unlikely(ev->flags & EXEC_OBJECT_NEEDS_GTT))
                pin_flags |= PIN_GLOBAL;

        /* Attempt to reuse the current location if available */
        err = i915_vma_pin_ww(vma, &eb->ww, 0, 0, pin_flags);
        if (err == -EDEADLK)
                return err;

        if (unlikely(err)) {
                if (entry->flags & EXEC_OBJECT_PINNED)
                        return err;

                /* Failing that pick any _free_ space if suitable */
                err = i915_vma_pin_ww(vma, &eb->ww,
                                             entry->pad_to_size,
                                             entry->alignment,
                                             eb_pin_flags(entry, ev->flags) |
                                             PIN_USER | PIN_NOEVICT);
                if (unlikely(err))
                        return err;
        }

        if (unlikely(ev->flags & EXEC_OBJECT_NEEDS_FENCE)) {
                err = i915_vma_pin_fence(vma);
                if (unlikely(err)) {
                        i915_vma_unpin(vma);
                        return err;
                }

                if (vma->fence)
                        ev->flags |= __EXEC_OBJECT_HAS_FENCE;
        }

        ev->flags |= __EXEC_OBJECT_HAS_PIN;
        if (eb_vma_misplaced(entry, vma, ev->flags))
                return -EBADSLT;

        return 0;
}

static inline void
eb_unreserve_vma(struct eb_vma *ev)
{
        if (!(ev->flags & __EXEC_OBJECT_HAS_PIN))
                return;

        if (unlikely(ev->flags & __EXEC_OBJECT_HAS_FENCE))
                __i915_vma_unpin_fence(ev->vma);

        __i915_vma_unpin(ev->vma);
        ev->flags &= ~__EXEC_OBJECT_RESERVED;
}

static int
eb_validate_vma(struct i915_execbuffer *eb,
                struct drm_i915_gem_exec_object2 *entry,
                struct i915_vma *vma)
{
        /* Relocations are disallowed for all platforms after TGL-LP.  This
         * also covers all platforms with local memory.
         */
        if (entry->relocation_count &&
            GRAPHICS_VER(eb->i915) >= 12 && !IS_TIGERLAKE(eb->i915))
                return -EINVAL;

        if (unlikely(entry->flags & eb->invalid_flags))
                return -EINVAL;

        if (unlikely(entry->alignment &&
                     !is_power_of_2_u64(entry->alignment)))
                return -EINVAL;

        /*
         * Offset can be used as input (EXEC_OBJECT_PINNED), reject
         * any non-page-aligned or non-canonical addresses.
         */
        if (unlikely(entry->flags & EXEC_OBJECT_PINNED &&
                     entry->offset != gen8_canonical_addr(entry->offset & I915_GTT_PAGE_MASK)))
                return -EINVAL;

        /* 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;
        }
        /*
         * 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);

        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;

        return 0;
}

static void
eb_add_vma(struct i915_execbuffer *eb,
           unsigned int i, unsigned batch_idx,
           struct i915_vma *vma)
{
        struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
        struct eb_vma *ev = &eb->vma[i];

        ev->vma = vma;
        ev->exec = entry;
        ev->flags = entry->flags;

        if (eb->lut_size > 0) {
                ev->handle = entry->handle;
                hlist_add_head(&ev->node,
                               &eb->buckets[hash_32(entry->handle,
                                                    eb->lut_size)]);
        }

        if (entry->relocation_count)
                list_add_tail(&ev->reloc_link, &eb->relocs);

        /*
         * 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 (i == batch_idx) {
                if (entry->relocation_count &&
                    !(ev->flags & EXEC_OBJECT_PINNED))
                        ev->flags |= __EXEC_OBJECT_NEEDS_BIAS;
                if (eb->reloc_cache.has_fence)
                        ev->flags |= EXEC_OBJECT_NEEDS_FENCE;

                eb->batch = ev;
        }
}

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(struct i915_execbuffer *eb,
                          struct eb_vma *ev,
                          u64 pin_flags)
{
        struct drm_i915_gem_exec_object2 *entry = ev->exec;
        struct i915_vma *vma = ev->vma;
        int err;

        if (drm_mm_node_allocated(&vma->node) &&
            eb_vma_misplaced(entry, vma, ev->flags)) {
                err = i915_vma_unbind(vma);
                if (err)
                        return err;
        }

        err = i915_vma_pin_ww(vma, &eb->ww,
                           entry->pad_to_size, entry->alignment,
                           eb_pin_flags(entry, ev->flags) | pin_flags);
        if (err)
                return err;

        if (entry->offset != vma->node.start) {
                entry->offset = vma->node.start | UPDATE;
                eb->args->flags |= __EXEC_HAS_RELOC;
        }

        if (unlikely(ev->flags & EXEC_OBJECT_NEEDS_FENCE)) {
                err = i915_vma_pin_fence(vma);
                if (unlikely(err)) {
                        i915_vma_unpin(vma);
                        return err;
                }

                if (vma->fence)
                        ev->flags |= __EXEC_OBJECT_HAS_FENCE;
        }

        ev->flags |= __EXEC_OBJECT_HAS_PIN;
        GEM_BUG_ON(eb_vma_misplaced(entry, vma, ev->flags));

        return 0;
}

static int eb_reserve(struct i915_execbuffer *eb)
{
        const unsigned int count = eb->buffer_count;
        unsigned int pin_flags = PIN_USER | PIN_NONBLOCK;
        struct list_head last;
        struct eb_vma *ev;
        unsigned int i, pass;
        int err = 0;

        /*
         * 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;
        do {
                list_for_each_entry(ev, &eb->unbound, bind_link) {
                        err = eb_reserve_vma(eb, ev, pin_flags);
                        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++) {
                        unsigned int flags;

                        ev = &eb->vma[i];
                        flags = ev->flags;
                        if (flags & EXEC_OBJECT_PINNED &&
                            flags & __EXEC_OBJECT_HAS_PIN)
                                continue;

                        eb_unreserve_vma(ev);

                        if (flags & EXEC_OBJECT_PINNED)
                                /* Pinned must have their slot */
                                list_add(&ev->bind_link, &eb->unbound);
                        else if (flags & __EXEC_OBJECT_NEEDS_MAP)
                                /* Map require the lowest 256MiB (aperture) */
                                list_add_tail(&ev->bind_link, &eb->unbound);
                        else if (!(flags & EXEC_OBJECT_SUPPORTS_48B_ADDRESS))
                                /* Prioritise 4GiB region for restricted bo */
                                list_add(&ev->bind_link, &last);
                        else
                                list_add_tail(&ev->bind_link, &last);
                }
                list_splice_tail(&last, &eb->unbound);

                switch (pass++) {
                case 0:
                        break;

                case 1:
                        /* Too fragmented, unbind everything and retry */
                        mutex_lock(&eb->context->vm->mutex);
                        err = i915_gem_evict_vm(eb->context->vm);
                        mutex_unlock(&eb->context->vm->mutex);
                        if (err)
                                return err;
                        break;

                default:
                        return -ENOSPC;
                }

                pin_flags = PIN_USER;
        } while (1);
}

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(!ctx))
                return -ENOENT;

        eb->gem_context = ctx;
        if (rcu_access_pointer(ctx->vm))
                eb->invalid_flags |= EXEC_OBJECT_NEEDS_GTT;

        eb->context_flags = 0;
        if (test_bit(UCONTEXT_NO_ZEROMAP, &ctx->user_flags))
                eb->context_flags |= __EXEC_OBJECT_NEEDS_BIAS;

        return 0;
}

static int __eb_add_lut(struct i915_execbuffer *eb,
                        u32 handle, struct i915_vma *vma)
{
        struct i915_gem_context *ctx = eb->gem_context;
        struct i915_lut_handle *lut;
        int err;

        lut = i915_lut_handle_alloc();
        if (unlikely(!lut))
                return -ENOMEM;

        i915_vma_get(vma);
        if (!atomic_fetch_inc(&vma->open_count))
                i915_vma_reopen(vma);
        lut->handle = handle;
        lut->ctx = ctx;

        /* Check that the context hasn't been closed in the meantime */
        err = -EINTR;
        if (!mutex_lock_interruptible(&ctx->lut_mutex)) {
                struct i915_address_space *vm = rcu_access_pointer(ctx->vm);

                if (unlikely(vm && vma->vm != vm))
                        err = -EAGAIN; /* user racing with ctx set-vm */
                else if (likely(!i915_gem_context_is_closed(ctx)))
                        err = radix_tree_insert(&ctx->handles_vma, handle, vma);
                else
                        err = -ENOENT;
                if (err == 0) { /* And nor has this handle */
                        struct drm_i915_gem_object *obj = vma->obj;

                        spin_lock(&obj->lut_lock);
                        if (idr_find(&eb->file->object_idr, handle) == obj) {
                                list_add(&lut->obj_link, &obj->lut_list);
                        } else {
                                radix_tree_delete(&ctx->handles_vma, handle);
                                err = -ENOENT;
                        }
                        spin_unlock(&obj->lut_lock);
                }
                mutex_unlock(&ctx->lut_mutex);
        }
        if (unlikely(err))
                goto err;

        return 0;

err:
        i915_vma_close(vma);
        i915_vma_put(vma);
        i915_lut_handle_free(lut);
        return err;
}

static struct i915_vma *eb_lookup_vma(struct i915_execbuffer *eb, u32 handle)
{
        struct i915_address_space *vm = eb->context->vm;

        do {
                struct drm_i915_gem_object *obj;
                struct i915_vma *vma;
                int err;

                rcu_read_lock();
                vma = radix_tree_lookup(&eb->gem_context->handles_vma, handle);
                if (likely(vma && vma->vm == vm))
                        vma = i915_vma_tryget(vma);
                rcu_read_unlock();
                if (likely(vma))
                        return vma;

                obj = i915_gem_object_lookup(eb->file, handle);
                if (unlikely(!obj))
                        return ERR_PTR(-ENOENT);

                vma = i915_vma_instance(obj, vm, NULL);
                if (IS_ERR(vma)) {
                        i915_gem_object_put(obj);
                        return vma;
                }

                err = __eb_add_lut(eb, handle, vma);
                if (likely(!err))
                        return vma;

                i915_gem_object_put(obj);
                if (err != -EEXIST)
                        return ERR_PTR(err);
        } while (1);
}

static int eb_lookup_vmas(struct i915_execbuffer *eb)
{
        struct drm_i915_private *i915 = eb->i915;
        unsigned int batch = eb_batch_index(eb);
        unsigned int i;
        int err = 0;

        INIT_LIST_HEAD(&eb->relocs);

        for (i = 0; i < eb->buffer_count; i++) {
                struct i915_vma *vma;

                vma = eb_lookup_vma(eb, eb->exec[i].handle);
                if (IS_ERR(vma)) {
                        err = PTR_ERR(vma);
                        goto err;
                }

                err = eb_validate_vma(eb, &eb->exec[i], vma);
                if (unlikely(err)) {
                        i915_vma_put(vma);
                        goto err;
                }

                eb_add_vma(eb, i, batch, vma);

                if (i915_gem_object_is_userptr(vma->obj)) {
                        err = i915_gem_object_userptr_submit_init(vma->obj);
                        if (err) {
                                if (i + 1 < eb->buffer_count) {
                                        /*
                                         * Execbuffer code expects last vma entry to be NULL,
                                         * since we already initialized this entry,
                                         * set the next value to NULL or we mess up
                                         * cleanup handling.
                                         */
                                        eb->vma[i + 1].vma = NULL;
                                }

                                return err;
                        }

                        eb->vma[i].flags |= __EXEC_OBJECT_USERPTR_INIT;
                        eb->args->flags |= __EXEC_USERPTR_USED;
                }
        }

        if (unlikely(eb->batch->flags & EXEC_OBJECT_WRITE)) {
                drm_dbg(&i915->drm,
                        "Attempting to use self-modifying batch buffer\n");
                return -EINVAL;
        }

        if (range_overflows_t(u64,
                              eb->batch_start_offset, eb->batch_len,
                              eb->batch->vma->size)) {
                drm_dbg(&i915->drm, "Attempting to use out-of-bounds batch\n");
                return -EINVAL;
        }

        if (eb->batch_len == 0)
                eb->batch_len = eb->batch->vma->size - eb->batch_start_offset;
        if (unlikely(eb->batch_len == 0)) { /* impossible! */
                drm_dbg(&i915->drm, "Invalid batch length\n");
                return -EINVAL;
        }

        return 0;

err:
        eb->vma[i].vma = NULL;
        return err;
}

static int eb_validate_vmas(struct i915_execbuffer *eb)
{
        unsigned int i;
        int err;

        INIT_LIST_HEAD(&eb->unbound);

        for (i = 0; i < eb->buffer_count; i++) {
                struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
                struct eb_vma *ev = &eb->vma[i];
                struct i915_vma *vma = ev->vma;

                err = i915_gem_object_lock(vma->obj, &eb->ww);
                if (err)
                        return err;

                err = eb_pin_vma(eb, entry, ev);
                if (err == -EDEADLK)
                        return err;

                if (!err) {
                        if (entry->offset != vma->node.start) {
                                entry->offset = vma->node.start | UPDATE;
                                eb->args->flags |= __EXEC_HAS_RELOC;
                        }
                } else {
                        eb_unreserve_vma(ev);

                        list_add_tail(&ev->bind_link, &eb->unbound);
                        if (drm_mm_node_allocated(&vma->node)) {
                                err = i915_vma_unbind(vma);
                                if (err)
                                        return err;
                        }
                }

                if (!(ev->flags & EXEC_OBJECT_WRITE)) {
                        err = dma_resv_reserve_shared(vma->resv, 1);
                        if (err)
                                return err;
                }

                GEM_BUG_ON(drm_mm_node_allocated(&vma->node) &&
                           eb_vma_misplaced(&eb->exec[i], vma, ev->flags));
        }

        if (!list_empty(&eb->unbound))
                return eb_reserve(eb);

        return 0;
}

static struct eb_vma *
eb_get_vma(const struct i915_execbuffer *eb, unsigned long handle)
{
        if (eb->lut_size < 0) {
                if (handle >= -eb->lut_size)
                        return NULL;
                return &eb->vma[handle];
        } else {
                struct hlist_head *head;
                struct eb_vma *ev;

                head = &eb->buckets[hash_32(handle, eb->lut_size)];
                hlist_for_each_entry(ev, head, node) {
                        if (ev->handle == handle)
                                return ev;
                }
                return NULL;
        }
}

static void eb_release_vmas(struct i915_execbuffer *eb, bool final, bool release_userptr)
{
        const unsigned int count = eb->buffer_count;
        unsigned int i;

        for (i = 0; i < count; i++) {

                struct eb_vma *ev = &eb->vma[i];
                struct i915_vma *vma = ev->vma;

                if (!vma)
                        break;

                eb_unreserve_vma(ev);

                if (release_userptr && ev->flags & __EXEC_OBJECT_USERPTR_INIT) {
                        ev->flags &= ~__EXEC_OBJECT_USERPTR_INIT;
                        i915_gem_object_userptr_submit_fini(vma->obj);
                }

                if (final)
                        i915_vma_put(vma);
        }

        eb_unpin_engine(eb);
}

static void eb_destroy(const struct i915_execbuffer *eb)
{
        GEM_BUG_ON(eb->reloc_cache.rq);

        if (eb->lut_size > 0)
                kfree(eb->buckets);
}

static inline u64
relocation_target(const struct drm_i915_gem_relocation_entry *reloc,
                  const struct i915_vma *target)
{
        return gen8_canonical_addr((int)reloc->delta + target->node.start);
}

static void reloc_cache_clear(struct reloc_cache *cache)
{
        cache->rq = NULL;
        cache->rq_cmd = NULL;
        cache->pool = NULL;
        cache->rq_size = 0;
}

static void reloc_cache_init(struct reloc_cache *cache,
                             struct drm_i915_private *i915)
{
        cache->page = -1;
        cache->vaddr = 0;
        /* Must be a variable in the struct to allow GCC to unroll. */
        cache->graphics_ver = GRAPHICS_VER(i915);
        cache->has_llc = HAS_LLC(i915);
        cache->use_64bit_reloc = HAS_64BIT_RELOC(i915);
        cache->has_fence = cache->graphics_ver < 4;
        cache->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment;
        cache->node.flags = 0;
        reloc_cache_clear(cache);
}

static inline void *unmask_page(unsigned long p)
{
        return (void *)(uintptr_t)(p & PAGE_MASK);
}

static inline unsigned int unmask_flags(unsigned long p)
{
        return p & ~PAGE_MASK;
}

#define KMAP 0x4 /* after CLFLUSH_FLAGS */

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_cache_put_pool(struct i915_execbuffer *eb, struct reloc_cache *cache)
{
        if (!cache->pool)
                return;

        /*
         * This is a bit nasty, normally we keep objects locked until the end
         * of execbuffer, but we already submit this, and have to unlock before
         * dropping the reference. Fortunately we can only hold 1 pool node at
         * a time, so this should be harmless.
         */
        i915_gem_ww_unlock_single(cache->pool->obj);
        intel_gt_buffer_pool_put(cache->pool);
        cache->pool = NULL;
}

static void reloc_gpu_flush(struct i915_execbuffer *eb, struct reloc_cache *cache)
{
        struct drm_i915_gem_object *obj = cache->rq->batch->obj;

        GEM_BUG_ON(cache->rq_size >= obj->base.size / sizeof(u32));
        cache->rq_cmd[cache->rq_size] = MI_BATCH_BUFFER_END;

        i915_gem_object_flush_map(obj);
        i915_gem_object_unpin_map(obj);

        intel_gt_chipset_flush(cache->rq->engine->gt);

        i915_request_add(cache->rq);
        reloc_cache_put_pool(eb, cache);
        reloc_cache_clear(cache);

        eb->reloc_pool = NULL;
}

static void reloc_cache_reset(struct reloc_cache *cache, struct i915_execbuffer *eb)
{
        void *vaddr;

        if (cache->rq)
                reloc_gpu_flush(eb, cache);

        if (!cache->vaddr)
                return;

        vaddr = unmask_page(cache->vaddr);
        if (cache->vaddr & KMAP) {
                struct drm_i915_gem_object *obj =
                        (struct drm_i915_gem_object *)cache->node.mm;
                if (cache->vaddr & CLFLUSH_AFTER)
                        mb();

                kunmap_atomic(vaddr);
                i915_gem_object_finish_access(obj);
        } else {
                struct i915_ggtt *ggtt = cache_to_ggtt(cache);

                intel_gt_flush_ggtt_writes(ggtt->vm.gt);
                io_mapping_unmap_atomic((void __iomem *)vaddr);

                if (drm_mm_node_allocated(&cache->node)) {
                        ggtt->vm.clear_range(&ggtt->vm,
                                             cache->node.start,
                                             cache->node.size);
                        mutex_lock(&ggtt->vm.mutex);
                        drm_mm_remove_node(&cache->node);
                        mutex_unlock(&ggtt->vm.mutex);
                } else {
                        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,
                        unsigned long pageno)
{
        void *vaddr;
        struct page *page;

        if (cache->vaddr) {
                kunmap_atomic(unmask_page(cache->vaddr));
        } else {
                unsigned int flushes;
                int err;

                err = i915_gem_object_prepare_write(obj, &flushes);
                if (err)
                        return ERR_PTR(err);

                BUILD_BUG_ON(KMAP & CLFLUSH_FLAGS);
                BUILD_BUG_ON((KMAP | CLFLUSH_FLAGS) & PAGE_MASK);

                cache->vaddr = flushes | KMAP;
                cache->node.mm = (void *)obj;
                if (flushes)
                        mb();
        }

        page = i915_gem_object_get_page(obj, pageno);
        if (!obj->mm.dirty)
                set_page_dirty(page);

        vaddr = kmap_atomic(page);
        cache->vaddr = unmask_flags(cache->vaddr) | (unsigned long)vaddr;
        cache->page = pageno;

        return vaddr;
}

static void *reloc_iomap(struct drm_i915_gem_object *obj,
                         struct i915_execbuffer *eb,
                         unsigned long page)
{
        struct reloc_cache *cache = &eb->reloc_cache;
        struct i915_ggtt *ggtt = cache_to_ggtt(cache);
        unsigned long offset;
        void *vaddr;

        if (cache->vaddr) {
                intel_gt_flush_ggtt_writes(ggtt->vm.gt);
                io_mapping_unmap_atomic((void __force __iomem *) unmask_page(cache->vaddr));
        } else {
                struct i915_vma *vma;
                int err;

                if (i915_gem_object_is_tiled(obj))
                        return ERR_PTR(-EINVAL);

                if (use_cpu_reloc(cache, obj))
                        return NULL;

                err = i915_gem_object_set_to_gtt_domain(obj, true);
                if (err)
                        return ERR_PTR(err);

                vma = i915_gem_object_ggtt_pin_ww(obj, &eb->ww, NULL, 0, 0,
                                                  PIN_MAPPABLE |
                                                  PIN_NONBLOCK /* NOWARN */ |
                                                  PIN_NOEVICT);
                if (vma == ERR_PTR(-EDEADLK))
                        return vma;

                if (IS_ERR(vma)) {
                        memset(&cache->node, 0, sizeof(cache->node));
                        mutex_lock(&ggtt->vm.mutex);
                        err = drm_mm_insert_node_in_range
                                (&ggtt->vm.mm, &cache->node,
                                 PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE,
                                 0, ggtt->mappable_end,
                                 DRM_MM_INSERT_LOW);
                        mutex_unlock(&ggtt->vm.mutex);
                        if (err) /* no inactive aperture space, use cpu reloc */
                                return NULL;
                } else {
                        cache->node.start = vma->node.start;
                        cache->node.mm = (void *)vma;
                }
        }

        offset = cache->node.start;
        if (drm_mm_node_allocated(&cache->node)) {
                ggtt->vm.insert_page(&ggtt->vm,
                                     i915_gem_object_get_dma_address(obj, page),
                                     offset, I915_CACHE_NONE, 0);
        } else {
                offset += page << PAGE_SHIFT;
        }

        vaddr = (void __force *)io_mapping_map_atomic_wc(&ggtt->iomap,
                                                         offset);
        cache->page = page;
        cache->vaddr = (unsigned long)vaddr;

        return vaddr;
}

static void *reloc_vaddr(struct drm_i915_gem_object *obj,
                         struct i915_execbuffer *eb,
                         unsigned long page)
{
        struct reloc_cache *cache = &eb->reloc_cache;
        void *vaddr;

        if (cache->page == page) {
                vaddr = unmask_page(cache->vaddr);
        } else {
                vaddr = NULL;
                if ((cache->vaddr & KMAP) == 0)
                        vaddr = reloc_iomap(obj, eb, page);
                if (!vaddr)
                        vaddr = reloc_kmap(obj, cache, page);
        }

        return vaddr;
}

static void clflush_write32(u32 *addr, u32 value, unsigned int flushes)
{
        if (unlikely(flushes & (CLFLUSH_BEFORE | CLFLUSH_AFTER))) {
                if (flushes & CLFLUSH_BEFORE) {
                        clflushopt(addr);
                        mb();
                }

                *addr = value;

                /*
                 * 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
                 * to ensure ordering of clflush wrt to the system.
                 */
                if (flushes & CLFLUSH_AFTER)
                        clflushopt(addr);
        } else
                *addr = value;
}

static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma)
{
        struct drm_i915_gem_object *obj = vma->obj;
        int err;

        assert_vma_held(vma);

        if (obj->cache_dirty & ~obj->cache_coherent)
                i915_gem_clflush_object(obj, 0);
        obj->write_domain = 0;

        err = i915_request_await_object(rq, vma->obj, true);
        if (err == 0)
                err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);

        return err;
}

static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
                             struct intel_engine_cs *engine,
                             struct i915_vma *vma,
                             unsigned int len)
{
        struct reloc_cache *cache = &eb->reloc_cache;
        struct intel_gt_buffer_pool_node *pool = eb->reloc_pool;
        struct i915_request *rq;
        struct i915_vma *batch;
        u32 *cmd;
        int err;

        if (!pool) {
                pool = intel_gt_get_buffer_pool(engine->gt, PAGE_SIZE,
                                                cache->has_llc ?
                                                I915_MAP_WB :
                                                I915_MAP_WC);
                if (IS_ERR(pool))
                        return PTR_ERR(pool);
        }
        eb->reloc_pool = NULL;

        err = i915_gem_object_lock(pool->obj, &eb->ww);
        if (err)
                goto err_pool;

        cmd = i915_gem_object_pin_map(pool->obj, pool->type);
        if (IS_ERR(cmd)) {
                err = PTR_ERR(cmd);
                goto err_pool;
        }
        intel_gt_buffer_pool_mark_used(pool);

        memset32(cmd, 0, pool->obj->base.size / sizeof(u32));

        batch = i915_vma_instance(pool->obj, vma->vm, NULL);
        if (IS_ERR(batch)) {
                err = PTR_ERR(batch);
                goto err_unmap;
        }

        err = i915_vma_pin_ww(batch, &eb->ww, 0, 0, PIN_USER | PIN_NONBLOCK);
        if (err)
                goto err_unmap;

        if (engine == eb->context->engine) {
                rq = i915_request_create(eb->context);
        } else {
                struct intel_context *ce = eb->reloc_context;

                if (!ce) {
                        ce = intel_context_create(engine);
                        if (IS_ERR(ce)) {
                                err = PTR_ERR(ce);
                                goto err_unpin;
                        }

                        i915_vm_put(ce->vm);
                        ce->vm = i915_vm_get(eb->context->vm);
                        eb->reloc_context = ce;
                }

                err = intel_context_pin_ww(ce, &eb->ww);
                if (err)
                        goto err_unpin;

                rq = i915_request_create(ce);
                intel_context_unpin(ce);
        }
        if (IS_ERR(rq)) {
                err = PTR_ERR(rq);
                goto err_unpin;
        }

        err = intel_gt_buffer_pool_mark_active(pool, rq);
        if (err)
                goto err_request;

        err = reloc_move_to_gpu(rq, vma);
        if (err)
                goto err_request;

        err = eb->engine->emit_bb_start(rq,
                                        batch->node.start, PAGE_SIZE,
                                        cache->graphics_ver > 5 ? 0 : I915_DISPATCH_SECURE);
        if (err)
                goto skip_request;

        assert_vma_held(batch);
        err = i915_request_await_object(rq, batch->obj, false);
        if (err == 0)
                err = i915_vma_move_to_active(batch, rq, 0);
        if (err)
                goto skip_request;

        rq->batch = batch;
        i915_vma_unpin(batch);

        cache->rq = rq;
        cache->rq_cmd = cmd;
        cache->rq_size = 0;
        cache->pool = pool;

        /* Return with batch mapping (cmd) still pinned */
        return 0;

skip_request:
        i915_request_set_error_once(rq, err);
err_request:
        i915_request_add(rq);
err_unpin:
        i915_vma_unpin(batch);
err_unmap:
        i915_gem_object_unpin_map(pool->obj);
err_pool:
        eb->reloc_pool = pool;
        return err;
}

static bool reloc_can_use_engine(const struct intel_engine_cs *engine)
{
        return engine->class != VIDEO_DECODE_CLASS || GRAPHICS_VER(engine->i915) != 6;
}

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(eb, cache);

        if (unlikely(!cache->rq)) {
                int err;
                struct intel_engine_cs *engine = eb->engine;

                /* If we need to copy for the cmdparser, we will stall anyway */
                if (eb_use_cmdparser(eb))
                        return ERR_PTR(-EWOULDBLOCK);

                if (!reloc_can_use_engine(engine)) {
                        engine = engine->gt->engine_class[COPY_ENGINE_CLASS][0];
                        if (!engine)
                                return ERR_PTR(-ENODEV);
                }

                err = __reloc_gpu_alloc(eb, engine, vma, len);
                if (unlikely(err))
                        return ERR_PTR(err);
        }

        cmd = cache->rq_cmd + cache->rq_size;
        cache->rq_size += len;

        return cmd;
}

static inline bool use_reloc_gpu(struct i915_vma *vma)
{
        if (DBG_FORCE_RELOC == FORCE_GPU_RELOC)
                return true;

        if (DBG_FORCE_RELOC)
                return false;

        return !dma_resv_test_signaled(vma->resv, true);
}

static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset)
{
        struct page *page;
        unsigned long addr;

        GEM_BUG_ON(vma->pages != vma->obj->mm.pages);

        page = i915_gem_object_get_page(vma->obj, offset >> PAGE_SHIFT);
        addr = PFN_PHYS(page_to_pfn(page));
        GEM_BUG_ON(overflows_type(addr, u32)); /* expected dma32 */

        return addr + offset_in_page(offset);
}

static int __reloc_entry_gpu(struct i915_execbuffer *eb,
                              struct i915_vma *vma,
                              u64 offset,
                              u64 target_addr)
{
        const unsigned int ver = eb->reloc_cache.graphics_ver;
        unsigned int len;
        u32 *batch;
        u64 addr;

        if (ver >= 8)
                len = offset & 7 ? 8 : 5;
        else if (ver >= 4)
                len = 4;
        else
                len = 3;

        batch = reloc_gpu(eb, vma, len);
        if (batch == ERR_PTR(-EDEADLK))
                return -EDEADLK;
        else if (IS_ERR(batch))
                return false;

        addr = gen8_canonical_addr(vma->node.start + offset);
        if (ver >= 8) {
                if (offset & 7) {
                        *batch++ = MI_STORE_DWORD_IMM_GEN4;
                        *batch++ = lower_32_bits(addr);
                        *batch++ = upper_32_bits(addr);
                        *batch++ = lower_32_bits(target_addr);

                        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_addr);
                } 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_addr);
                        *batch++ = upper_32_bits(target_addr);
                }
        } else if (ver >= 6) {
                *batch++ = MI_STORE_DWORD_IMM_GEN4;
                *batch++ = 0;
                *batch++ = addr;
                *batch++ = target_addr;
        } else if (IS_I965G(eb->i915)) {
                *batch++ = MI_STORE_DWORD_IMM_GEN4;
                *batch++ = 0;
                *batch++ = vma_phys_addr(vma, offset);
                *batch++ = target_addr;
        } else if (ver >= 4) {
                *batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
                *batch++ = 0;
                *batch++ = addr;
                *batch++ = target_addr;
        } else if (ver >= 3 &&
                   !(IS_I915G(eb->i915) || IS_I915GM(eb->i915))) {
                *batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
                *batch++ = addr;
                *batch++ = target_addr;
        } else {
                *batch++ = MI_STORE_DWORD_IMM;
                *batch++ = vma_phys_addr(vma, offset);
                *batch++ = target_addr;
        }

        return true;
}

static int reloc_entry_gpu(struct i915_execbuffer *eb,
                            struct i915_vma *vma,
                            u64 offset,
                            u64 target_addr)
{
        if (eb->reloc_cache.vaddr)
                return false;

        if (!use_reloc_gpu(vma))
                return false;

        return __reloc_entry_gpu(eb, vma, offset, target_addr);
}

static u64
relocate_entry(struct i915_vma *vma,
               const struct drm_i915_gem_relocation_entry *reloc,
               struct i915_execbuffer *eb,
               const struct i915_vma *target)
{
        u64 target_addr = relocation_target(reloc, target);
        u64 offset = reloc->offset;
        int reloc_gpu = reloc_entry_gpu(eb, vma, offset, target_addr);

        if (reloc_gpu < 0)
                return reloc_gpu;

        if (!reloc_gpu) {
                bool wide = eb->reloc_cache.use_64bit_reloc;
                void *vaddr;

repeat:
                vaddr = reloc_vaddr(vma->obj, eb,
                                    offset >> PAGE_SHIFT);
                if (IS_ERR(vaddr))
                        return PTR_ERR(vaddr);

                GEM_BUG_ON(!IS_ALIGNED(offset, sizeof(u32)));
                clflush_write32(vaddr + offset_in_page(offset),
                                lower_32_bits(target_addr),
                                eb->reloc_cache.vaddr);

                if (wide) {
                        offset += sizeof(u32);
                        target_addr >>= 32;
                        wide = false;
                        goto repeat;
                }
        }

        return target->node.start | UPDATE;
}

static u64
eb_relocate_entry(struct i915_execbuffer *eb,
                  struct eb_vma *ev,
                  const struct drm_i915_gem_relocation_entry *reloc)
{
        struct drm_i915_private *i915 = eb->i915;
        struct eb_vma *target;
        int err;

        /* we've already hold a reference to all valid objects */
        target = eb_get_vma(eb, reloc->target_handle);
        if (unlikely(!target))
                return -ENOENT;

        /* Validate that the target is in a valid r/w GPU domain */
        if (unlikely(reloc->write_domain & (reloc->write_domain - 1))) {
                drm_dbg(&i915->drm, "reloc with multiple write domains: "
                          "target %d offset %d "
                          "read %08x write %08x",
                          reloc->target_handle,
                          (int) reloc->offset,
                          reloc->read_domains,
                          reloc->write_domain);
                return -EINVAL;
        }
        if (unlikely((reloc->write_domain | reloc->read_domains)
                     & ~I915_GEM_GPU_DOMAINS)) {
                drm_dbg(&i915->drm, "reloc with read/write non-GPU domains: "
                          "target %d offset %d "
                          "read %08x write %08x",
                          reloc->target_handle,
                          (int) reloc->offset,
                          reloc->read_domains,
                          reloc->write_domain);
                return -EINVAL;
        }

        if (reloc->write_domain) {
                target->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 &&
                    GRAPHICS_VER(eb->i915) == 6) {
                        err = i915_vma_bind(target->vma,
                                            target->vma->obj->cache_level,
                                            PIN_GLOBAL, NULL);
                        if (err)
                                return err;
                }
        }

        /*
         * If the relocation already has the right value in it, no
         * more work needs to be done.
         */
        if (!DBG_FORCE_RELOC &&
            gen8_canonical_addr(target->vma->node.start) == reloc->presumed_offset)
                return 0;

        /* Check that the relocation address is valid... */
        if (unlikely(reloc->offset >
                     ev->vma->size - (eb->reloc_cache.use_64bit_reloc ? 8 : 4))) {
                drm_dbg(&i915->drm, "Relocation beyond object bounds: "
                          "target %d offset %d size %d.\n",
                          reloc->target_handle,
                          (int)reloc->offset,
                          (int)ev->vma->size);
                return -EINVAL;
        }
        if (unlikely(reloc->offset & 3)) {
                drm_dbg(&i915->drm, "Relocation not 4-byte aligned: "
                          "target %d offset %d.\n",
                          reloc->target_handle,
                          (int)reloc->offset);
                return -EINVAL;
        }

        /*
         * 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
         * out of our synchronisation.
         */
        ev->flags &= ~EXEC_OBJECT_ASYNC;

        /* and update the user's relocation entry */
        return relocate_entry(ev->vma, reloc, eb, target->vma);
}

static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
{
#define N_RELOC(x) ((x) / sizeof(struct drm_i915_gem_relocation_entry))
        struct drm_i915_gem_relocation_entry stack[N_RELOC(512)];
        const struct drm_i915_gem_exec_object2 *entry = ev->exec;
        struct drm_i915_gem_relocation_entry __user *urelocs =
                u64_to_user_ptr(entry->relocs_ptr);
        unsigned long remain = entry->relocation_count;

        if (unlikely(remain > N_RELOC(ULONG_MAX)))
                return -EINVAL;

        /*
         * 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(urelocs, remain * sizeof(*urelocs))))
                return -EFAULT;

        do {
                struct drm_i915_gem_relocation_entry *r = stack;
                unsigned int count =
                        min_t(unsigned long, 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
                 * we would try to acquire the struct mutex again. Obviously
                 * this is bad and so lockdep complains vehemently.
                 */
                pagefault_disable();
                copied = __copy_from_user_inatomic(r, urelocs, count * sizeof(r[0]));
                pagefault_enable();
                if (unlikely(copied)) {
                        remain = -EFAULT;
                        goto out;
                }

                remain -= count;
                do {
                        u64 offset = eb_relocate_entry(eb, ev, r);

                        if (likely(offset == 0)) {
                        } else if ((s64)offset < 0) {
                                remain = (int)offset;
                                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);
                        }
                } while (r++, --count);
                urelocs += ARRAY_SIZE(stack);
        } while (remain);
out:
        reloc_cache_reset(&eb->reloc_cache, eb);
        return remain;
}

static int
eb_relocate_vma_slow(struct i915_execbuffer *eb, struct eb_vma *ev)
{
        const struct drm_i915_gem_exec_object2 *entry = ev->exec;
        struct drm_i915_gem_relocation_entry *relocs =
                u64_to_ptr(typeof(*relocs), entry->relocs_ptr);
        unsigned int i;
        int err;

        for (i = 0; i < entry->relocation_count; i++) {
                u64 offset = eb_relocate_entry(eb, ev, &relocs[i]);

                if ((s64)offset < 0) {
                        err = (int)offset;
                        goto err;
                }
        }
        err = 0;
err:
        reloc_cache_reset(&eb->reloc_cache, eb);
        return err;
}

static int check_relocations(const struct drm_i915_gem_exec_object2 *entry)
{
        const char __user *addr, *end;
        unsigned long size;
        char __maybe_unused c;

        size = entry->relocation_count;
        if (size == 0)
                return 0;

        if (size > N_RELOC(ULONG_MAX))
                return -EINVAL;

        addr = u64_to_user_ptr(entry->relocs_ptr);
        size *= sizeof(struct drm_i915_gem_relocation_entry);
        if (!access_ok(addr, size))
                return -EFAULT;

        end = addr + size;
        for (; addr < end; addr += PAGE_SIZE) {
                int err = __get_user(c, addr);
                if (err)
                        return err;
        }
        return __get_user(c, end - 1);
}

static int eb_copy_relocations(const struct i915_execbuffer *eb)
{
        struct drm_i915_gem_relocation_entry *relocs;
        const unsigned int count = eb->buffer_count;
        unsigned int i;
        int err;

        for (i = 0; i < count; i++) {
                const unsigned int nreloc = eb->exec[i].relocation_count;
                struct drm_i915_gem_relocation_entry __user *urelocs;
                unsigned long size;
                unsigned long copied;

                if (nreloc == 0)
                        continue;

                err = check_relocations(&eb->exec[i]);
                if (err)
                        goto err;

                urelocs = u64_to_user_ptr(eb->exec[i].relocs_ptr);
                size = nreloc * sizeof(*relocs);

                relocs = kvmalloc_array(size, 1, GFP_KERNEL);
                if (!relocs) {
                        err = -ENOMEM;
                        goto err;
                }

                /* 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 __user *)urelocs + copied,
                                             len))
                                goto end;

                        copied += len;
                } while (copied < size);

                /*
                 * 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.
                 */
                if (!user_access_begin(urelocs, size))
                        goto end;

                for (copied = 0; copied < nreloc; copied++)
                        unsafe_put_user(-1,
                                        &urelocs[copied].presumed_offset,
                                        end_user);
                user_access_end();

                eb->exec[i].relocs_ptr = (uintptr_t)relocs;
        }

        return 0;

end_user:
        user_access_end();
end:
        kvfree(relocs);
        err = -EFAULT;
err:
        while (i--) {
                relocs = u64_to_ptr(typeof(*relocs), eb->exec[i].relocs_ptr);
                if (eb->exec[i].relocation_count)
                        kvfree(relocs);
        }
        return err;
}

static int eb_prefault_relocations(const struct i915_execbuffer *eb)
{
        const unsigned int count = eb->buffer_count;
        unsigned int i;

        for (i = 0; i < count; i++) {
                int err;

                err = check_relocations(&eb->exec[i]);
                if (err)
                        return err;
        }

        return 0;
}

static int eb_reinit_userptr(struct i915_execbuffer *eb)
{
        const unsigned int count = eb->buffer_count;
        unsigned int i;
        int ret;

        if (likely(!(eb->args->flags & __EXEC_USERPTR_USED)))
                return 0;

        for (i = 0; i < count; i++) {
                struct eb_vma *ev = &eb->vma[i];

                if (!i915_gem_object_is_userptr(ev->vma->obj))
                        continue;

                ret = i915_gem_object_userptr_submit_init(ev->vma->obj);
                if (ret)
                        return ret;

                ev->flags |= __EXEC_OBJECT_USERPTR_INIT;
        }

        return 0;
}

static noinline int eb_relocate_parse_slow(struct i915_execbuffer *eb,
                                           struct i915_request *rq)
{
        bool have_copy = false;
        struct eb_vma *ev;
        int err = 0;

repeat:
        if (signal_pending(current)) {
                err = -ERESTARTSYS;
                goto out;
        }

        /* We may process another execbuffer during the unlock... */
        eb_release_vmas(eb, false, true);
        i915_gem_ww_ctx_fini(&eb->ww);

        if (rq) {
                /* nonblocking is always false */
                if (i915_request_wait(rq, I915_WAIT_INTERRUPTIBLE,