drm/i915/gem: Excise the per-batch whitelist from the context

One does not lightly add a new hidden struct_mutex dependency deep within
the execbuf bowels! The immediate suspicion in seeing the whitelist
cached on the context, is that it is intended to be preserved between
batches, as the kernel is quite adept at caching small allocations
itself. But no, it's sole purpose is to serialise command submission in
order to save a kmalloc on a slow, slow path!

By removing the whitelist dependency from the context, our freedom to
chop the big struct_mutex is greatly augmented.

v2: s/set_bit/__set_bit/ as the whitelist shall never be accessed
concurrently.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191128113424.3885958-1-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index c94ac838401a77a5bc04c8d4d56a65670054173d..a179e170c9362d54e62973806bb75d59c04d5056 100644 (file)
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -275,8 +275,6 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
        free_engines(rcu_access_pointer(ctx->engines));
        mutex_destroy(&ctx->engines_mutex);
 
-       kfree(ctx->jump_whitelist);
-
        if (ctx->timeline)
                intel_timeline_put(ctx->timeline);
 
@@ -584,9 +582,6 @@ __create_context(struct drm_i915_private *i915)
        for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
                ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
 
-       ctx->jump_whitelist = NULL;
-       ctx->jump_whitelist_cmds = 0;
-
        spin_lock(&i915->gem.contexts.lock);
        list_add_tail(&ctx->link, &i915->gem.contexts.list);
        spin_unlock(&i915->gem.contexts.lock);

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index c060bc428f49fedfc64a4285394ecf459af98265..69df5459c350ab50aeac482e529aa9e989aec859 100644 (file)
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -168,13 +168,6 @@ struct i915_gem_context {
         */
        struct radix_tree_root handles_vma;
 
-       /** jump_whitelist: Bit array for tracking cmds during cmdparsing
-        *  Guarded by struct_mutex
-        */
-       unsigned long *jump_whitelist;
-       /** jump_whitelist_cmds: No of cmd slots available */
-       u32 jump_whitelist_cmds;
-
        /**
         * @name: arbitrary name, used for user debug
         *

diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index f24096e27bef436a31ea26af854705505cebdaa7..9125e89a9e7f45f7ad48874aeb91e64cc0d002dd 100644 (file)
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1310,13 +1310,14 @@ static int check_bbstart(const struct i915_gem_context *ctx,
                         u32 *cmd, u32 offset, u32 length,
                         u32 batch_len,
                         u64 batch_start,
-                        u64 shadow_batch_start)
+                        u64 shadow_batch_start,
+                        const unsigned long *jump_whitelist)
 {
        u64 jump_offset, jump_target;
        u32 target_cmd_offset, target_cmd_index;
 
        /* For igt compatibility on older platforms */
-       if (CMDPARSER_USES_GGTT(ctx->i915)) {
+       if (!jump_whitelist) {
                DRM_DEBUG("CMD: Rejecting BB_START for ggtt based submission\n");
                return -EACCES;
        }
@@ -1352,10 +1353,10 @@ static int check_bbstart(const struct i915_gem_context *ctx,
        if (target_cmd_index == offset)
                return 0;
 
-       if (ctx->jump_whitelist_cmds <= target_cmd_index) {
-               DRM_DEBUG("CMD: Rejecting BB_START - truncated whitelist array\n");
-               return -EINVAL;
-       } else if (!test_bit(target_cmd_index, ctx->jump_whitelist)) {
+       if (IS_ERR(jump_whitelist))
+               return PTR_ERR(jump_whitelist);
+
+       if (!test_bit(target_cmd_index, jump_whitelist)) {
                DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n",
                          jump_target);
                return -EINVAL;
@@ -1364,40 +1365,27 @@ static int check_bbstart(const struct i915_gem_context *ctx,
        return 0;
 }
 
-static void init_whitelist(struct i915_gem_context *ctx, u32 batch_len)
+static unsigned long *
+alloc_whitelist(struct drm_i915_private *i915, u32 batch_len)
 {
-       const u32 batch_cmds = DIV_ROUND_UP(batch_len, sizeof(u32));
-       const u32 exact_size = BITS_TO_LONGS(batch_cmds);
-       u32 next_size = BITS_TO_LONGS(roundup_pow_of_two(batch_cmds));
-       unsigned long *next_whitelist;
-
-       if (CMDPARSER_USES_GGTT(ctx->i915))
-               return;
-
-       if (batch_cmds <= ctx->jump_whitelist_cmds) {
-               bitmap_zero(ctx->jump_whitelist, batch_cmds);
-               return;
-       }
+       unsigned long *jmp;
 
-again:
-       next_whitelist = kcalloc(next_size, sizeof(long), GFP_KERNEL);
-       if (next_whitelist) {
-               kfree(ctx->jump_whitelist);
-               ctx->jump_whitelist = next_whitelist;
-               ctx->jump_whitelist_cmds =
-                       next_size * BITS_PER_BYTE * sizeof(long);
-               return;
-       }
+       /*
+        * We expect batch_len to be less than 256KiB for known users,
+        * i.e. we need at most an 8KiB bitmap allocation which should be
+        * reasonably cheap due to kmalloc caches.
+        */
 
-       if (next_size > exact_size) {
-               next_size = exact_size;
-               goto again;
-       }
+       if (CMDPARSER_USES_GGTT(i915))
+               return NULL;
 
-       DRM_DEBUG("CMD: Failed to extend whitelist. BB_START may be disallowed\n");
-       bitmap_zero(ctx->jump_whitelist, ctx->jump_whitelist_cmds);
+       /* Prefer to report transient allocation failure rather than hit oom */
+       jmp = bitmap_zalloc(DIV_ROUND_UP(batch_len, sizeof(u32)),
+                           GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
+       if (!jmp)
+               return ERR_PTR(-ENOMEM);
 
-       return;
+       return jmp;
 }
 
 #define LENGTH_BIAS 2
@@ -1433,6 +1421,7 @@ int intel_engine_cmd_parser(struct i915_gem_context *ctx,
        struct drm_i915_cmd_descriptor default_desc = noop_desc;
        const struct drm_i915_cmd_descriptor *desc = &default_desc;
        bool needs_clflush_after = false;
+       unsigned long *jump_whitelist;
        int ret = 0;
 
        cmd = copy_batch(shadow_batch_obj, batch_obj,
@@ -1443,7 +1432,8 @@ int intel_engine_cmd_parser(struct i915_gem_context *ctx,
                return PTR_ERR(cmd);
        }
 
-       init_whitelist(ctx, batch_len);
+       /* Defer failure until attempted use */
+       jump_whitelist = alloc_whitelist(ctx->i915, batch_len);
 
        /*
         * We use the batch length as size because the shadow object is as
@@ -1487,15 +1477,16 @@ int intel_engine_cmd_parser(struct i915_gem_context *ctx,
                if (desc->cmd.value == MI_BATCH_BUFFER_START) {
                        ret = check_bbstart(ctx, cmd, offset, length,
                                            batch_len, batch_start,
-                                           shadow_batch_start);
+                                           shadow_batch_start,
+                                           jump_whitelist);
 
                        if (ret)
                                goto err;
                        break;
                }
 
-               if (ctx->jump_whitelist_cmds > offset)
-                       set_bit(offset, ctx->jump_whitelist);
+               if (!IS_ERR_OR_NULL(jump_whitelist))
+                       __set_bit(offset, jump_whitelist);
 
                cmd += length;
                offset += length;
@@ -1513,6 +1504,8 @@ int intel_engine_cmd_parser(struct i915_gem_context *ctx,
        }
 
 err:
+       if (!IS_ERR_OR_NULL(jump_whitelist))
+               kfree(jump_whitelist);
        i915_gem_object_unpin_map(shadow_batch_obj);
        return ret;
 }