From: Thomas Hellström thomas.hellstrom@linux.intel.com
If our exported dma-bufs are imported by another instance of our driver, that instance will typically have the imported dma-bufs locked during dma_buf_map_attachment(). But the exporter also locks the same reservation object in the map_dma_buf() callback, which leads to recursive locking.
So taking the lock inside _pin_pages_unlocked() is incorrect.
Additionally, the current pinning code path is contrary to the defined way that pinning should occur.
Remove the explicit pin/unpin from the map/umap functions and move them to the attach/detach allowing correct locking to occur, and to match the static dma-buf drm_prime pattern.
Add a live selftest to exercise both dynamic and non-dynamic exports.
v2: - Extend the selftest with a fake dynamic importer. - Provide real pin and unpin callbacks to not abuse the interface. v3: (ruhl) - Remove the dynamic export support and move the pinning into the attach/detach path. v4: (ruhl) - Put pages does not need to assert on the dma-resv
Reported-by: Michael J. Ruhl michael.j.ruhl@intel.com Signed-off-by: Thomas Hellström thomas.hellstrom@linux.intel.com Signed-off-by: Michael J. Ruhl michael.j.ruhl@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c | 44 +++++-- .../drm/i915/gem/selftests/i915_gem_dmabuf.c | 116 +++++++++++++++++- 2 files changed, 146 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c index 616c3a2f1baf..ccae17d5f441 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c @@ -12,6 +12,8 @@ #include "i915_gem_object.h" #include "i915_scatterlist.h"
+I915_SELFTEST_DECLARE(static bool force_different_devices;) + static struct drm_i915_gem_object *dma_buf_to_obj(struct dma_buf *buf) { return to_intel_bo(buf->priv); @@ -25,15 +27,11 @@ static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachme struct scatterlist *src, *dst; int ret, i;
- ret = i915_gem_object_pin_pages_unlocked(obj); - if (ret) - goto err; - /* Copy sg so that we make an independent mapping */ st = kmalloc(sizeof(struct sg_table), GFP_KERNEL); if (st == NULL) { ret = -ENOMEM; - goto err_unpin_pages; + goto err; }
ret = sg_alloc_table(st, obj->mm.pages->nents, GFP_KERNEL); @@ -58,8 +56,6 @@ static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachme sg_free_table(st); err_free: kfree(st); -err_unpin_pages: - i915_gem_object_unpin_pages(obj); err: return ERR_PTR(ret); } @@ -68,13 +64,9 @@ static void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment, struct sg_table *sg, enum dma_data_direction dir) { - struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf); - dma_unmap_sgtable(attachment->dev, sg, dir, DMA_ATTR_SKIP_CPU_SYNC); sg_free_table(sg); kfree(sg); - - i915_gem_object_unpin_pages(obj); }
static int i915_gem_dmabuf_vmap(struct dma_buf *dma_buf, struct dma_buf_map *map) @@ -168,7 +160,32 @@ static int i915_gem_end_cpu_access(struct dma_buf *dma_buf, enum dma_data_direct return err; }
+/** + * i915_gem_dmabuf_attach - Do any extra attach work necessary + * @dmabuf: imported dma-buf + * @attach: new attach to do work on + * + */ +static int i915_gem_dmabuf_attach(struct dma_buf *dmabuf, + struct dma_buf_attachment *attach) +{ + struct drm_i915_gem_object *obj = dma_buf_to_obj(dmabuf); + + assert_object_held(obj); + return i915_gem_object_pin_pages(obj); +} + +static void i915_gem_dmabuf_detach(struct dma_buf *dmabuf, + struct dma_buf_attachment *attach) +{ + struct drm_i915_gem_object *obj = dma_buf_to_obj(dmabuf); + + i915_gem_object_unpin_pages(obj); +} + static const struct dma_buf_ops i915_dmabuf_ops = { + .attach = i915_gem_dmabuf_attach, + .detach = i915_gem_dmabuf_detach, .map_dma_buf = i915_gem_map_dma_buf, .unmap_dma_buf = i915_gem_unmap_dma_buf, .release = drm_gem_dmabuf_release, @@ -204,6 +221,8 @@ static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj) struct sg_table *pages; unsigned int sg_page_sizes;
+ assert_object_held(obj); + pages = dma_buf_map_attachment(obj->base.import_attach, DMA_BIDIRECTIONAL); if (IS_ERR(pages)) @@ -241,7 +260,8 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev, if (dma_buf->ops == &i915_dmabuf_ops) { obj = dma_buf_to_obj(dma_buf); /* is it from our device? */ - if (obj->base.dev == dev) { + if (obj->base.dev == dev && + !I915_SELFTEST_ONLY(force_different_devices)) { /* * Importing dmabuf exported from out own gem increases * refcount on gem itself instead of f_count of dmabuf. diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c index dd74bc09ec88..868b3469ecbd 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c @@ -35,7 +35,7 @@ static int igt_dmabuf_export(void *arg) static int igt_dmabuf_import_self(void *arg) { struct drm_i915_private *i915 = arg; - struct drm_i915_gem_object *obj; + struct drm_i915_gem_object *obj, *import_obj; struct drm_gem_object *import; struct dma_buf *dmabuf; int err; @@ -65,14 +65,125 @@ static int igt_dmabuf_import_self(void *arg) err = -EINVAL; goto out_import; } + import_obj = to_intel_bo(import); + + i915_gem_object_lock(import_obj, NULL); + err = ____i915_gem_object_get_pages(import_obj); + i915_gem_object_unlock(import_obj); + if (err) { + pr_err("Same object dma-buf get_pages failed!\n"); + goto out_import; + }
err = 0; out_import: - i915_gem_object_put(to_intel_bo(import)); + i915_gem_object_put(import_obj); +out_dmabuf: + dma_buf_put(dmabuf); +out: + i915_gem_object_put(obj); + return err; +} + +static void igt_dmabuf_move_notify(struct dma_buf_attachment *attach) +{ + GEM_WARN_ON(1); +} + +static const struct dma_buf_attach_ops igt_dmabuf_attach_ops = { + .move_notify = igt_dmabuf_move_notify, +}; + +static int igt_dmabuf_import_same_driver(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct drm_i915_gem_object *obj, *import_obj; + struct drm_gem_object *import; + struct dma_buf *dmabuf; + struct dma_buf_attachment *import_attach; + struct sg_table *st; + long timeout; + int err; + + force_different_devices = true; + obj = i915_gem_object_create_shmem(i915, PAGE_SIZE); + if (IS_ERR(obj)) + goto out_ret; + + dmabuf = i915_gem_prime_export(&obj->base, 0); + if (IS_ERR(dmabuf)) { + pr_err("i915_gem_prime_export failed with err=%d\n", + (int)PTR_ERR(dmabuf)); + err = PTR_ERR(dmabuf); + goto out; + } + + import = i915_gem_prime_import(&i915->drm, dmabuf); + if (IS_ERR(import)) { + pr_err("i915_gem_prime_import failed with err=%d\n", + (int)PTR_ERR(import)); + err = PTR_ERR(import); + goto out_dmabuf; + } + + if (import == &obj->base) { + pr_err("i915_gem_prime_import reused gem object!\n"); + err = -EINVAL; + goto out_import; + } + + import_obj = to_intel_bo(import); + + i915_gem_object_lock(import_obj, NULL); + err = ____i915_gem_object_get_pages(import_obj); + if (err) { + pr_err("Different objects dma-buf get_pages failed!\n"); + i915_gem_object_unlock(import_obj); + goto out_import; + } + + /* + * If the exported object is not in system memory, something + * weird is going on. TODO: When p2p is supported, this is no + * longer considered weird. + */ + if (obj->mm.region != i915->mm.regions[INTEL_REGION_SMEM]) { + pr_err("Exported dma-buf is not in system memory\n"); + err = -EINVAL; + } + + i915_gem_object_unlock(import_obj); + + /* Now try a fake dynamic importer */ + import_attach = dma_buf_dynamic_attach(dmabuf, obj->base.dev->dev, + &igt_dmabuf_attach_ops, + NULL); + if (IS_ERR(import_attach)) + goto out_import; + + dma_resv_lock(dmabuf->resv, NULL); + st = dma_buf_map_attachment(import_attach, DMA_BIDIRECTIONAL); + dma_resv_unlock(dmabuf->resv); + if (IS_ERR(st)) + goto out_detach; + + timeout = dma_resv_wait_timeout(dmabuf->resv, false, true, 5 * HZ); + if (!timeout) { + pr_err("dmabuf wait for exclusive fence timed out.\n"); + timeout = -ETIME; + } + err = timeout > 0 ? 0 : timeout; + dma_buf_unmap_attachment(import_attach, st, DMA_BIDIRECTIONAL); +out_detach: + dma_buf_detach(dmabuf, import_attach); +out_import: + i915_gem_object_put(import_obj); out_dmabuf: dma_buf_put(dmabuf); out: i915_gem_object_put(obj); +out_ret: + force_different_devices = false; return err; }
@@ -286,6 +397,7 @@ int i915_gem_dmabuf_live_selftests(struct drm_i915_private *i915) { static const struct i915_subtest tests[] = { SUBTEST(igt_dmabuf_export), + SUBTEST(igt_dmabuf_import_same_driver), };
return i915_subtests(tests, i915);
From: Thomas Hellström thomas.hellstrom@linux.intel.com
Until we support p2p dma or as a complement to that, migrate data to system memory at dma-buf attach time if possible.
v2: - Rebase on dynamic exporter. Update the igt_dmabuf_import_same_driver selftest to migrate if we are LMEM capable. v3: - Migrate also in the pin() callback. v4: - Migrate in attach
Signed-off-by: Thomas Hellström thomas.hellstrom@linux.intel.com Signed-off-by: Michael J. Ruhl michael.j.ruhl@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c | 12 +++++++++++- drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c | 4 +++- 2 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c index ccae17d5f441..280291a4a9dc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c @@ -170,9 +170,19 @@ static int i915_gem_dmabuf_attach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) { struct drm_i915_gem_object *obj = dma_buf_to_obj(dmabuf); + int ret;
assert_object_held(obj); - return i915_gem_object_pin_pages(obj); + + if (!i915_gem_object_can_migrate(obj, INTEL_REGION_SMEM)) + return -EOPNOTSUPP; + ret = i915_gem_object_migrate(obj, NULL, INTEL_REGION_SMEM); + if (!ret) + ret = i915_gem_object_wait_migration(obj, 0); + if (!ret) + ret = i915_gem_object_pin_pages(obj); + + return ret; }
static void i915_gem_dmabuf_detach(struct dma_buf *dmabuf, diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c index 868b3469ecbd..b1e87ec08741 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c @@ -106,7 +106,9 @@ static int igt_dmabuf_import_same_driver(void *arg) int err;
force_different_devices = true; - obj = i915_gem_object_create_shmem(i915, PAGE_SIZE); + obj = i915_gem_object_create_lmem(i915, PAGE_SIZE, 0); + if (IS_ERR(obj)) + obj = i915_gem_object_create_shmem(i915, PAGE_SIZE); if (IS_ERR(obj)) goto out_ret;
Hi "Michael,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on drm-intel/for-linux-next] [also build test ERROR on v5.13 next-20210701] [If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Michael-J-Ruhl/drm-i915-gem-Correct... base: git://anongit.freedesktop.org/drm-intel for-linux-next config: x86_64-randconfig-r025-20210630 (attached as .config) compiler: clang version 13.0.0 (https://github.com/llvm/llvm-project 9eb613b2de3163686b1a4bd1160f15ac56a4b083) reproduce (this is a W=1 build): wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross # install x86_64 cross compiling tool for clang build # apt-get install binutils-x86-64-linux-gnu # https://github.com/0day-ci/linux/commit/d1c1ca8d45e76fc2b9ee679c170848e6c613... git remote add linux-review https://github.com/0day-ci/linux git fetch --no-tags linux-review Michael-J-Ruhl/drm-i915-gem-Correct-the-locking-and-pin-pattern-for-dma-buf/20210702-042115 git checkout d1c1ca8d45e76fc2b9ee679c170848e6c6138f6e # save the attached .config to linux build tree COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64
If you fix the issue, kindly add following tag as appropriate Reported-by: kernel test robot lkp@intel.com
All errors (new ones prefixed by >>):
drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c:177:7: error: implicit declaration of function 'i915_gem_object_can_migrate' [-Werror,-Wimplicit-function-declaration]
if (!i915_gem_object_can_migrate(obj, INTEL_REGION_SMEM)) ^ drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c:177:7: note: did you mean 'i915_gem_object_pin_map'? drivers/gpu/drm/i915/gem/i915_gem_object.h:452:20: note: 'i915_gem_object_pin_map' declared here void *__must_check i915_gem_object_pin_map(struct drm_i915_gem_object *obj, ^
drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c:179:8: error: implicit declaration of function 'i915_gem_object_migrate' [-Werror,-Wimplicit-function-declaration]
ret = i915_gem_object_migrate(obj, NULL, INTEL_REGION_SMEM); ^ drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c:179:8: note: did you mean 'i915_gem_object_can_migrate'? drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c:177:7: note: 'i915_gem_object_can_migrate' declared here if (!i915_gem_object_can_migrate(obj, INTEL_REGION_SMEM)) ^
drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c:181:9: error: implicit declaration of function 'i915_gem_object_wait_migration' [-Werror,-Wimplicit-function-declaration]
ret = i915_gem_object_wait_migration(obj, 0); ^ drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c:181:9: note: did you mean 'i915_gem_object_can_migrate'? drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c:177:7: note: 'i915_gem_object_can_migrate' declared here if (!i915_gem_object_can_migrate(obj, INTEL_REGION_SMEM)) ^ 3 errors generated.
vim +/i915_gem_object_can_migrate +177 drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
162 163 /** 164 * i915_gem_dmabuf_attach - Do any extra attach work necessary 165 * @dmabuf: imported dma-buf 166 * @attach: new attach to do work on 167 * 168 */ 169 static int i915_gem_dmabuf_attach(struct dma_buf *dmabuf, 170 struct dma_buf_attachment *attach) 171 { 172 struct drm_i915_gem_object *obj = dma_buf_to_obj(dmabuf); 173 int ret; 174 175 assert_object_held(obj); 176
177 if (!i915_gem_object_can_migrate(obj, INTEL_REGION_SMEM))
178 return -EOPNOTSUPP;
179 ret = i915_gem_object_migrate(obj, NULL, INTEL_REGION_SMEM);
180 if (!ret)
181 ret = i915_gem_object_wait_migration(obj, 0);
182 if (!ret) 183 ret = i915_gem_object_pin_pages(obj); 184 185 return ret; 186 } 187
--- 0-DAY CI Kernel Test Service, Intel Corporation https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
dri-devel@lists.freedesktop.org