From 09ea0dfbf972c63dfea8cf46f2fb67f39e4d833b Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Tue, 29 May 2018 15:59:18 +0200 Subject: dma-buf: make map_atomic and map function pointers optional So drivers don't need dummy functions just returning NULL. Cc: Daniel Vetter Signed-off-by: Gerd Hoffmann Reviewed-by: Daniel Vetter Reviewed-by: Oleksandr Andrushchenko Link: http://patchwork.freedesktop.org/patch/msgid/20180529135918.19729-1-kraxel@redhat.com --- include/linux/dma-buf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 085db2fee2d7..88917fa796e4 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -39,12 +39,12 @@ struct dma_buf_attachment; /** * struct dma_buf_ops - operations possible on struct dma_buf - * @map_atomic: maps a page from the buffer into kernel address + * @map_atomic: [optional] maps a page from the buffer into kernel address * space, users may not block until the subsequent unmap call. * This callback must not sleep. * @unmap_atomic: [optional] unmaps a atomically mapped page from the buffer. * This Callback must not sleep. - * @map: maps a page from the buffer into kernel address space. + * @map: [optional] maps a page from the buffer into kernel address space. * @unmap: [optional] unmaps a page from the buffer. * @vmap: [optional] creates a virtual mapping for the buffer into kernel * address space. Same restrictions as for vmap and friends apply. -- cgit v1.2.3-71-gd317 From a19741e5e5a9f1f02f8e3c037bde7d73d4bfae9c Mon Sep 17 00:00:00 2001 From: Christian König Date: Mon, 28 May 2018 11:47:52 +0200 Subject: dma_buf: remove device parameter from attach callback v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The device parameter is completely unused because it is available in the attachment structure as well. v2: fix kerneldoc as well Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/226643/ --- drivers/dma-buf/dma-buf.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c | 3 +-- drivers/gpu/drm/drm_prime.c | 3 +-- drivers/gpu/drm/udl/udl_dmabuf.c | 1 - drivers/gpu/drm/vmwgfx/vmwgfx_prime.c | 1 - drivers/media/common/videobuf2/videobuf2-dma-contig.c | 2 +- drivers/media/common/videobuf2/videobuf2-dma-sg.c | 2 +- drivers/media/common/videobuf2/videobuf2-vmalloc.c | 2 +- include/drm/drm_prime.h | 2 +- include/linux/dma-buf.h | 13 ++++++------- 10 files changed, 13 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 4c45e31258f0..50771063c617 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -568,7 +568,7 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, mutex_lock(&dmabuf->lock); if (dmabuf->ops->attach) { - ret = dmabuf->ops->attach(dmabuf, dev, attach); + ret = dmabuf->ops->attach(dmabuf, attach); if (ret) goto err_attach; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c index 4b584cb75bf4..bbbb4f9578db 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c @@ -127,7 +127,6 @@ error: } static int amdgpu_gem_map_attach(struct dma_buf *dma_buf, - struct device *target_dev, struct dma_buf_attachment *attach) { struct drm_gem_object *obj = dma_buf->priv; @@ -135,7 +134,7 @@ static int amdgpu_gem_map_attach(struct dma_buf *dma_buf, struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); long r; - r = drm_gem_map_attach(dma_buf, target_dev, attach); + r = drm_gem_map_attach(dma_buf, attach); if (r) return r; diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 397b46b33739..0055d919070c 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -186,7 +186,6 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri /** * drm_gem_map_attach - dma_buf attach implementation for GEM * @dma_buf: buffer to attach device to - * @target_dev: not used * @attach: buffer attachment data * * Allocates &drm_prime_attachment and calls &drm_driver.gem_prime_pin for @@ -195,7 +194,7 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri * * Returns 0 on success, negative error code on failure. */ -int drm_gem_map_attach(struct dma_buf *dma_buf, struct device *target_dev, +int drm_gem_map_attach(struct dma_buf *dma_buf, struct dma_buf_attachment *attach) { struct drm_prime_attachment *prime_attach; diff --git a/drivers/gpu/drm/udl/udl_dmabuf.c b/drivers/gpu/drm/udl/udl_dmabuf.c index 0a20695eb120..91ae60309d3e 100644 --- a/drivers/gpu/drm/udl/udl_dmabuf.c +++ b/drivers/gpu/drm/udl/udl_dmabuf.c @@ -29,7 +29,6 @@ struct udl_drm_dmabuf_attachment { }; static int udl_attach_dma_buf(struct dma_buf *dmabuf, - struct device *dev, struct dma_buf_attachment *attach) { struct udl_drm_dmabuf_attachment *udl_attach; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c index 0d42a46521fc..fbffb37ccf42 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c @@ -40,7 +40,6 @@ */ static int vmw_prime_map_attach(struct dma_buf *dma_buf, - struct device *target_dev, struct dma_buf_attachment *attach) { return -ENOSYS; diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c index f1178f6f434d..12d0072c52c2 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c @@ -222,7 +222,7 @@ struct vb2_dc_attachment { enum dma_data_direction dma_dir; }; -static int vb2_dc_dmabuf_ops_attach(struct dma_buf *dbuf, struct device *dev, +static int vb2_dc_dmabuf_ops_attach(struct dma_buf *dbuf, struct dma_buf_attachment *dbuf_attach) { struct vb2_dc_attachment *attach; diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c index 753ed3138dcc..cf94765e593f 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c @@ -371,7 +371,7 @@ struct vb2_dma_sg_attachment { enum dma_data_direction dma_dir; }; -static int vb2_dma_sg_dmabuf_ops_attach(struct dma_buf *dbuf, struct device *dev, +static int vb2_dma_sg_dmabuf_ops_attach(struct dma_buf *dbuf, struct dma_buf_attachment *dbuf_attach) { struct vb2_dma_sg_attachment *attach; diff --git a/drivers/media/common/videobuf2/videobuf2-vmalloc.c b/drivers/media/common/videobuf2/videobuf2-vmalloc.c index 359fb9804d16..cdec023a918d 100644 --- a/drivers/media/common/videobuf2/videobuf2-vmalloc.c +++ b/drivers/media/common/videobuf2/videobuf2-vmalloc.c @@ -209,7 +209,7 @@ struct vb2_vmalloc_attachment { enum dma_data_direction dma_dir; }; -static int vb2_vmalloc_dmabuf_ops_attach(struct dma_buf *dbuf, struct device *dev, +static int vb2_vmalloc_dmabuf_ops_attach(struct dma_buf *dbuf, struct dma_buf_attachment *dbuf_attach) { struct vb2_vmalloc_attachment *attach; diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h index 4d5f5d6cf6a6..ef338151cea8 100644 --- a/include/drm/drm_prime.h +++ b/include/drm/drm_prime.h @@ -82,7 +82,7 @@ int drm_gem_prime_fd_to_handle(struct drm_device *dev, struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev, struct dma_buf_export_info *exp_info); void drm_gem_dmabuf_release(struct dma_buf *dma_buf); -int drm_gem_map_attach(struct dma_buf *dma_buf, struct device *target_dev, +int drm_gem_map_attach(struct dma_buf *dma_buf, struct dma_buf_attachment *attach); void drm_gem_map_detach(struct dma_buf *dma_buf, struct dma_buf_attachment *attach); diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 88917fa796e4..c0ad5bf61188 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -55,11 +55,11 @@ struct dma_buf_ops { * @attach: * * This is called from dma_buf_attach() to make sure that a given - * &device can access the provided &dma_buf. Exporters which support - * buffer objects in special locations like VRAM or device-specific - * carveout areas should check whether the buffer could be move to - * system memory (or directly accessed by the provided device), and - * otherwise need to fail the attach operation. + * &dma_buf_attachment.dev can access the provided &dma_buf. Exporters + * which support buffer objects in special locations like VRAM or + * device-specific carveout areas should check whether the buffer could + * be move to system memory (or directly accessed by the provided + * device), and otherwise need to fail the attach operation. * * The exporter should also in general check whether the current * allocation fullfills the DMA constraints of the new device. If this @@ -77,8 +77,7 @@ struct dma_buf_ops { * to signal that backing storage is already allocated and incompatible * with the requirements of requesting device. */ - int (*attach)(struct dma_buf *, struct device *, - struct dma_buf_attachment *); + int (*attach)(struct dma_buf *, struct dma_buf_attachment *); /** * @detach: -- cgit v1.2.3-71-gd317 From f664a52695429b68afb4e130a0f69cd5fd1fec86 Mon Sep 17 00:00:00 2001 From: Christian König Date: Mon, 28 May 2018 13:34:01 +0200 Subject: dma-buf: remove kmap_atomic interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Neither used nor correctly implemented anywhere. Just completely remove the interface. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Acked-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/226645/ --- drivers/dma-buf/dma-buf.c | 54 +--------------------- drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c | 2 - drivers/gpu/drm/armada/armada_gem.c | 2 - drivers/gpu/drm/drm_prime.c | 31 ------------- drivers/gpu/drm/i915/i915_gem_dmabuf.c | 11 ----- drivers/gpu/drm/i915/selftests/mock_dmabuf.c | 2 - drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c | 2 - drivers/gpu/drm/tegra/gem.c | 14 ------ drivers/gpu/drm/udl/udl_dmabuf.c | 17 ------- drivers/gpu/drm/vmwgfx/vmwgfx_prime.c | 13 ------ .../media/common/videobuf2/videobuf2-dma-contig.c | 1 - drivers/media/common/videobuf2/videobuf2-dma-sg.c | 1 - drivers/media/common/videobuf2/videobuf2-vmalloc.c | 1 - drivers/staging/android/ion/ion.c | 2 - drivers/tee/tee_shm.c | 6 --- include/drm/drm_prime.h | 4 -- include/linux/dma-buf.h | 4 -- 17 files changed, 2 insertions(+), 165 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 50771063c617..13884474d158 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -405,7 +405,6 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) || !exp_info->ops->map_dma_buf || !exp_info->ops->unmap_dma_buf || !exp_info->ops->release - || !exp_info->ops->map_atomic || !exp_info->ops->map || !exp_info->ops->mmap)) { return ERR_PTR(-EINVAL); @@ -687,26 +686,14 @@ EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment); * void \*dma_buf_kmap(struct dma_buf \*, unsigned long); * void dma_buf_kunmap(struct dma_buf \*, unsigned long, void \*); * - * There are also atomic variants of these interfaces. Like for kmap they - * facilitate non-blocking fast-paths. Neither the importer nor the exporter - * (in the callback) is allowed to block when using these. - * - * Interfaces:: - * void \*dma_buf_kmap_atomic(struct dma_buf \*, unsigned long); - * void dma_buf_kunmap_atomic(struct dma_buf \*, unsigned long, void \*); - * - * For importers all the restrictions of using kmap apply, like the limited - * supply of kmap_atomic slots. Hence an importer shall only hold onto at - * max 2 atomic dma_buf kmaps at the same time (in any given process context). + * Implementing the functions is optional for exporters and for importers all + * the restrictions of using kmap apply. * * dma_buf kmap calls outside of the range specified in begin_cpu_access are * undefined. If the range is not PAGE_SIZE aligned, kmap needs to succeed on * the partial chunks at the beginning and end but may return stale or bogus * data outside of the range (in these partial chunks). * - * Note that these calls need to always succeed. The exporter needs to - * complete any preparations that might fail in begin_cpu_access. - * * For some cases the overhead of kmap can be too high, a vmap interface * is introduced. This interface should be used very carefully, as vmalloc * space is a limited resources on many architectures. @@ -859,43 +846,6 @@ int dma_buf_end_cpu_access(struct dma_buf *dmabuf, } EXPORT_SYMBOL_GPL(dma_buf_end_cpu_access); -/** - * dma_buf_kmap_atomic - Map a page of the buffer object into kernel address - * space. The same restrictions as for kmap_atomic and friends apply. - * @dmabuf: [in] buffer to map page from. - * @page_num: [in] page in PAGE_SIZE units to map. - * - * This call must always succeed, any necessary preparations that might fail - * need to be done in begin_cpu_access. - */ -void *dma_buf_kmap_atomic(struct dma_buf *dmabuf, unsigned long page_num) -{ - WARN_ON(!dmabuf); - - if (!dmabuf->ops->map_atomic) - return NULL; - return dmabuf->ops->map_atomic(dmabuf, page_num); -} -EXPORT_SYMBOL_GPL(dma_buf_kmap_atomic); - -/** - * dma_buf_kunmap_atomic - Unmap a page obtained by dma_buf_kmap_atomic. - * @dmabuf: [in] buffer to unmap page from. - * @page_num: [in] page in PAGE_SIZE units to unmap. - * @vaddr: [in] kernel space pointer obtained from dma_buf_kmap_atomic. - * - * This call must always succeed. - */ -void dma_buf_kunmap_atomic(struct dma_buf *dmabuf, unsigned long page_num, - void *vaddr) -{ - WARN_ON(!dmabuf); - - if (dmabuf->ops->unmap_atomic) - dmabuf->ops->unmap_atomic(dmabuf, page_num, vaddr); -} -EXPORT_SYMBOL_GPL(dma_buf_kunmap_atomic); - /** * dma_buf_kmap - Map a page of the buffer object into kernel address space. The * same restrictions as for kmap and friends apply. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c index bbbb4f9578db..0558da049827 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c @@ -238,9 +238,7 @@ static const struct dma_buf_ops amdgpu_dmabuf_ops = { .release = drm_gem_dmabuf_release, .begin_cpu_access = amdgpu_gem_begin_cpu_access, .map = drm_gem_dmabuf_kmap, - .map_atomic = drm_gem_dmabuf_kmap_atomic, .unmap = drm_gem_dmabuf_kunmap, - .unmap_atomic = drm_gem_dmabuf_kunmap_atomic, .mmap = drm_gem_dmabuf_mmap, .vmap = drm_gem_dmabuf_vmap, .vunmap = drm_gem_dmabuf_vunmap, diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c index a97f509743a5..3fb37c75c065 100644 --- a/drivers/gpu/drm/armada/armada_gem.c +++ b/drivers/gpu/drm/armada/armada_gem.c @@ -490,8 +490,6 @@ static const struct dma_buf_ops armada_gem_prime_dmabuf_ops = { .map_dma_buf = armada_gem_prime_map_dma_buf, .unmap_dma_buf = armada_gem_prime_unmap_dma_buf, .release = drm_gem_dmabuf_release, - .map_atomic = armada_gem_dmabuf_no_kmap, - .unmap_atomic = armada_gem_dmabuf_no_kunmap, .map = armada_gem_dmabuf_no_kmap, .unmap = armada_gem_dmabuf_no_kunmap, .mmap = armada_gem_dmabuf_mmap, diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 0055d919070c..186db2e4c57a 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -433,35 +433,6 @@ void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr) } EXPORT_SYMBOL(drm_gem_dmabuf_vunmap); -/** - * drm_gem_dmabuf_kmap_atomic - map_atomic implementation for GEM - * @dma_buf: buffer to be mapped - * @page_num: page number within the buffer - * - * Not implemented. This can be used as the &dma_buf_ops.map_atomic callback. - */ -void *drm_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num) -{ - return NULL; -} -EXPORT_SYMBOL(drm_gem_dmabuf_kmap_atomic); - -/** - * drm_gem_dmabuf_kunmap_atomic - unmap_atomic implementation for GEM - * @dma_buf: buffer to be unmapped - * @page_num: page number within the buffer - * @addr: virtual address of the buffer - * - * Not implemented. This can be used as the &dma_buf_ops.unmap_atomic callback. - */ -void drm_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num, void *addr) -{ - -} -EXPORT_SYMBOL(drm_gem_dmabuf_kunmap_atomic); - /** * drm_gem_dmabuf_kmap - map implementation for GEM * @dma_buf: buffer to be mapped @@ -519,9 +490,7 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops = { .unmap_dma_buf = drm_gem_unmap_dma_buf, .release = drm_gem_dmabuf_release, .map = drm_gem_dmabuf_kmap, - .map_atomic = drm_gem_dmabuf_kmap_atomic, .unmap = drm_gem_dmabuf_kunmap, - .unmap_atomic = drm_gem_dmabuf_kunmap_atomic, .mmap = drm_gem_dmabuf_mmap, .vmap = drm_gem_dmabuf_vmap, .vunmap = drm_gem_dmabuf_vunmap, diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c index 69a7aec49e84..82e2ca17a441 100644 --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c @@ -111,15 +111,6 @@ static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr) i915_gem_object_unpin_map(obj); } -static void *i915_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf, unsigned long page_num) -{ - return NULL; -} - -static void i915_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, unsigned long page_num, void *addr) -{ - -} static void *i915_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num) { struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf); @@ -225,9 +216,7 @@ static const struct dma_buf_ops i915_dmabuf_ops = { .unmap_dma_buf = i915_gem_unmap_dma_buf, .release = drm_gem_dmabuf_release, .map = i915_gem_dmabuf_kmap, - .map_atomic = i915_gem_dmabuf_kmap_atomic, .unmap = i915_gem_dmabuf_kunmap, - .unmap_atomic = i915_gem_dmabuf_kunmap_atomic, .mmap = i915_gem_dmabuf_mmap, .vmap = i915_gem_dmabuf_vmap, .vunmap = i915_gem_dmabuf_vunmap, diff --git a/drivers/gpu/drm/i915/selftests/mock_dmabuf.c b/drivers/gpu/drm/i915/selftests/mock_dmabuf.c index 302f7d103635..f81fda8ea45e 100644 --- a/drivers/gpu/drm/i915/selftests/mock_dmabuf.c +++ b/drivers/gpu/drm/i915/selftests/mock_dmabuf.c @@ -130,9 +130,7 @@ static const struct dma_buf_ops mock_dmabuf_ops = { .unmap_dma_buf = mock_unmap_dma_buf, .release = mock_dmabuf_release, .map = mock_dmabuf_kmap, - .map_atomic = mock_dmabuf_kmap_atomic, .unmap = mock_dmabuf_kunmap, - .unmap_atomic = mock_dmabuf_kunmap_atomic, .mmap = mock_dmabuf_mmap, .vmap = mock_dmabuf_vmap, .vunmap = mock_dmabuf_vunmap, diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c index 8e41d649e248..1a073f9b2834 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c +++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c @@ -148,8 +148,6 @@ static const struct dma_buf_ops omap_dmabuf_ops = { .release = drm_gem_dmabuf_release, .begin_cpu_access = omap_gem_dmabuf_begin_cpu_access, .end_cpu_access = omap_gem_dmabuf_end_cpu_access, - .map_atomic = omap_gem_dmabuf_kmap_atomic, - .unmap_atomic = omap_gem_dmabuf_kunmap_atomic, .map = omap_gem_dmabuf_kmap, .unmap = omap_gem_dmabuf_kunmap, .mmap = omap_gem_dmabuf_mmap, diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index 8b0b4ff64bb4..d7661702c11c 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -596,18 +596,6 @@ static int tegra_gem_prime_end_cpu_access(struct dma_buf *buf, return 0; } -static void *tegra_gem_prime_kmap_atomic(struct dma_buf *buf, - unsigned long page) -{ - return NULL; -} - -static void tegra_gem_prime_kunmap_atomic(struct dma_buf *buf, - unsigned long page, - void *addr) -{ -} - static void *tegra_gem_prime_kmap(struct dma_buf *buf, unsigned long page) { return NULL; @@ -648,8 +636,6 @@ static const struct dma_buf_ops tegra_gem_prime_dmabuf_ops = { .release = tegra_gem_prime_release, .begin_cpu_access = tegra_gem_prime_begin_cpu_access, .end_cpu_access = tegra_gem_prime_end_cpu_access, - .map_atomic = tegra_gem_prime_kmap_atomic, - .unmap_atomic = tegra_gem_prime_kunmap_atomic, .map = tegra_gem_prime_kmap, .unmap = tegra_gem_prime_kunmap, .mmap = tegra_gem_prime_mmap, diff --git a/drivers/gpu/drm/udl/udl_dmabuf.c b/drivers/gpu/drm/udl/udl_dmabuf.c index 91ae60309d3e..556f62662aa9 100644 --- a/drivers/gpu/drm/udl/udl_dmabuf.c +++ b/drivers/gpu/drm/udl/udl_dmabuf.c @@ -157,27 +157,12 @@ static void *udl_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num) return NULL; } -static void *udl_dmabuf_kmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num) -{ - /* TODO */ - - return NULL; -} - static void udl_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num, void *addr) { /* TODO */ } -static void udl_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num, - void *addr) -{ - /* TODO */ -} - static int udl_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma) { @@ -192,9 +177,7 @@ static const struct dma_buf_ops udl_dmabuf_ops = { .map_dma_buf = udl_map_dma_buf, .unmap_dma_buf = udl_unmap_dma_buf, .map = udl_dmabuf_kmap, - .map_atomic = udl_dmabuf_kmap_atomic, .unmap = udl_dmabuf_kunmap, - .unmap_atomic = udl_dmabuf_kunmap_atomic, .mmap = udl_dmabuf_mmap, .release = drm_gem_dmabuf_release, }; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c index fbffb37ccf42..373bc6da2f84 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c @@ -71,17 +71,6 @@ static void vmw_prime_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr) { } -static void *vmw_prime_dmabuf_kmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num) -{ - return NULL; -} - -static void vmw_prime_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num, void *addr) -{ - -} static void *vmw_prime_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num) { @@ -108,9 +97,7 @@ const struct dma_buf_ops vmw_prime_dmabuf_ops = { .unmap_dma_buf = vmw_prime_unmap_dma_buf, .release = NULL, .map = vmw_prime_dmabuf_kmap, - .map_atomic = vmw_prime_dmabuf_kmap_atomic, .unmap = vmw_prime_dmabuf_kunmap, - .unmap_atomic = vmw_prime_dmabuf_kunmap_atomic, .mmap = vmw_prime_dmabuf_mmap, .vmap = vmw_prime_dmabuf_vmap, .vunmap = vmw_prime_dmabuf_vunmap, diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c index 12d0072c52c2..aff0ab7bf83d 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c @@ -358,7 +358,6 @@ static const struct dma_buf_ops vb2_dc_dmabuf_ops = { .map_dma_buf = vb2_dc_dmabuf_ops_map, .unmap_dma_buf = vb2_dc_dmabuf_ops_unmap, .map = vb2_dc_dmabuf_ops_kmap, - .map_atomic = vb2_dc_dmabuf_ops_kmap, .vmap = vb2_dc_dmabuf_ops_vmap, .mmap = vb2_dc_dmabuf_ops_mmap, .release = vb2_dc_dmabuf_ops_release, diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c index cf94765e593f..015e737095cd 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c @@ -507,7 +507,6 @@ static const struct dma_buf_ops vb2_dma_sg_dmabuf_ops = { .map_dma_buf = vb2_dma_sg_dmabuf_ops_map, .unmap_dma_buf = vb2_dma_sg_dmabuf_ops_unmap, .map = vb2_dma_sg_dmabuf_ops_kmap, - .map_atomic = vb2_dma_sg_dmabuf_ops_kmap, .vmap = vb2_dma_sg_dmabuf_ops_vmap, .mmap = vb2_dma_sg_dmabuf_ops_mmap, .release = vb2_dma_sg_dmabuf_ops_release, diff --git a/drivers/media/common/videobuf2/videobuf2-vmalloc.c b/drivers/media/common/videobuf2/videobuf2-vmalloc.c index cdec023a918d..6dfbd5b05907 100644 --- a/drivers/media/common/videobuf2/videobuf2-vmalloc.c +++ b/drivers/media/common/videobuf2/videobuf2-vmalloc.c @@ -346,7 +346,6 @@ static const struct dma_buf_ops vb2_vmalloc_dmabuf_ops = { .map_dma_buf = vb2_vmalloc_dmabuf_ops_map, .unmap_dma_buf = vb2_vmalloc_dmabuf_ops_unmap, .map = vb2_vmalloc_dmabuf_ops_kmap, - .map_atomic = vb2_vmalloc_dmabuf_ops_kmap, .vmap = vb2_vmalloc_dmabuf_ops_vmap, .mmap = vb2_vmalloc_dmabuf_ops_mmap, .release = vb2_vmalloc_dmabuf_ops_release, diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c index e74db7902549..a5220445b5e8 100644 --- a/drivers/staging/android/ion/ion.c +++ b/drivers/staging/android/ion/ion.c @@ -369,8 +369,6 @@ static const struct dma_buf_ops dma_buf_ops = { .detach = ion_dma_buf_detatch, .begin_cpu_access = ion_dma_buf_begin_cpu_access, .end_cpu_access = ion_dma_buf_end_cpu_access, - .map_atomic = ion_dma_buf_kmap, - .unmap_atomic = ion_dma_buf_kunmap, .map = ion_dma_buf_kmap, .unmap = ion_dma_buf_kunmap, }; diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index 556960a1bab3..df4a1553b78b 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -80,11 +80,6 @@ static void tee_shm_op_release(struct dma_buf *dmabuf) tee_shm_release(shm); } -static void *tee_shm_op_map_atomic(struct dma_buf *dmabuf, unsigned long pgnum) -{ - return NULL; -} - static void *tee_shm_op_map(struct dma_buf *dmabuf, unsigned long pgnum) { return NULL; @@ -107,7 +102,6 @@ static const struct dma_buf_ops tee_shm_dma_buf_ops = { .map_dma_buf = tee_shm_op_map_dma_buf, .unmap_dma_buf = tee_shm_op_unmap_dma_buf, .release = tee_shm_op_release, - .map_atomic = tee_shm_op_map_atomic, .map = tee_shm_op_map, .mmap = tee_shm_op_mmap, }; diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h index ef338151cea8..d716d653b096 100644 --- a/include/drm/drm_prime.h +++ b/include/drm/drm_prime.h @@ -93,10 +93,6 @@ void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach, enum dma_data_direction dir); void *drm_gem_dmabuf_vmap(struct dma_buf *dma_buf); void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr); -void *drm_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num); -void drm_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, - unsigned long page_num, void *addr); void *drm_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num); void drm_gem_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num, void *addr); diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index c0ad5bf61188..58725f890b5b 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -205,8 +205,6 @@ struct dma_buf_ops { * to be restarted. */ int (*end_cpu_access)(struct dma_buf *, enum dma_data_direction); - void *(*map_atomic)(struct dma_buf *, unsigned long); - void (*unmap_atomic)(struct dma_buf *, unsigned long, void *); void *(*map)(struct dma_buf *, unsigned long); void (*unmap)(struct dma_buf *, unsigned long, void *); @@ -394,8 +392,6 @@ int dma_buf_begin_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); int dma_buf_end_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); -void *dma_buf_kmap_atomic(struct dma_buf *, unsigned long); -void dma_buf_kunmap_atomic(struct dma_buf *, unsigned long, void *); void *dma_buf_kmap(struct dma_buf *, unsigned long); void dma_buf_kunmap(struct dma_buf *, unsigned long, void *); -- cgit v1.2.3-71-gd317 From 83d83bebf40132e2d55ec58af666713cc76f9764 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 28 Jun 2018 15:20:30 +0200 Subject: console/fbcon: Add support for deferred console takeover Currently fbcon claims fbdevs as soon as they are registered and takes over the console as soon as the first fbdev gets registered. This behavior is undesirable in cases where a smooth graphical bootup is desired, in such cases we typically want the contents of the framebuffer (typically a vendor logo) to stay in place as is. The current solution for this problem (on embedded systems) is to not enable fbcon. This commit adds a new FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER config option, which when enabled defers fbcon taking over the console from the dummy console until the first text is displayed on the console. Together with the "quiet" kernel commandline option, this allows fbcon to still be used together with a smooth graphical bootup, having it take over the console as soon as e.g. an error message is logged. Note the choice to detect the first console output in the dummycon driver, rather then handling this entirely inside the fbcon code, was made after 2 failed attempts to handle this entirely inside the fbcon code. The fbcon code is woven quite tightly into the console code, making this to only feasible option. Reviewed-by: Daniel Vetter Signed-off-by: Hans de Goede Signed-off-by: Bartlomiej Zolnierkiewicz --- Documentation/fb/fbcon.txt | 7 ++++ drivers/video/console/Kconfig | 11 ++++++ drivers/video/console/dummycon.c | 67 ++++++++++++++++++++++++++++++++----- drivers/video/fbdev/core/fbcon.c | 72 ++++++++++++++++++++++++++++++++++++++++ include/linux/console.h | 5 +++ 5 files changed, 154 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/Documentation/fb/fbcon.txt b/Documentation/fb/fbcon.txt index 79c22d096bbc..d4d642e1ce9c 100644 --- a/Documentation/fb/fbcon.txt +++ b/Documentation/fb/fbcon.txt @@ -155,6 +155,13 @@ C. Boot options used by text. By default, this area will be black. The 'color' value is an integer number that depends on the framebuffer driver being used. +6. fbcon=nodefer + + If the kernel is compiled with deferred fbcon takeover support, normally + the framebuffer contents, left in place by the firmware/bootloader, will + be preserved until there actually is some text is output to the console. + This option causes fbcon to bind immediately to the fbdev device. + C. Attaching, Detaching and Unloading Before going on how to attach, detach and unload the framebuffer console, an diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig index 4110ba7d7ca9..e91edef98633 100644 --- a/drivers/video/console/Kconfig +++ b/drivers/video/console/Kconfig @@ -150,6 +150,17 @@ config FRAMEBUFFER_CONSOLE_ROTATION such that other users of the framebuffer will remain normally oriented. +config FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER + bool "Framebuffer Console Deferred Takeover" + depends on FRAMEBUFFER_CONSOLE=y && DUMMY_CONSOLE=y + help + If enabled this defers the framebuffer console taking over the + console from the dummy console until the first text is displayed on + the console. This is useful in combination with the "quiet" kernel + commandline option to keep the framebuffer contents initially put up + by the firmware in place, rather then replacing the contents with a + black screen as soon as fbcon loads. + config STI_CONSOLE bool "STI text console" depends on PARISC && HAS_IOMEM diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c index f2eafe2ed980..45ad925ad5f8 100644 --- a/drivers/video/console/dummycon.c +++ b/drivers/video/console/dummycon.c @@ -26,6 +26,65 @@ #define DUMMY_ROWS CONFIG_DUMMY_CONSOLE_ROWS #endif +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER +/* These are both protected by the console_lock */ +static RAW_NOTIFIER_HEAD(dummycon_output_nh); +static bool dummycon_putc_called; + +void dummycon_register_output_notifier(struct notifier_block *nb) +{ + raw_notifier_chain_register(&dummycon_output_nh, nb); + + if (dummycon_putc_called) + nb->notifier_call(nb, 0, NULL); +} + +void dummycon_unregister_output_notifier(struct notifier_block *nb) +{ + raw_notifier_chain_unregister(&dummycon_output_nh, nb); +} + +static void dummycon_putc(struct vc_data *vc, int c, int ypos, int xpos) +{ + dummycon_putc_called = true; + raw_notifier_call_chain(&dummycon_output_nh, 0, NULL); +} + +static void dummycon_putcs(struct vc_data *vc, const unsigned short *s, + int count, int ypos, int xpos) +{ + int i; + + if (!dummycon_putc_called) { + /* Ignore erases */ + for (i = 0 ; i < count; i++) { + if (s[i] != vc->vc_video_erase_char) + break; + } + if (i == count) + return; + + dummycon_putc_called = true; + } + + raw_notifier_call_chain(&dummycon_output_nh, 0, NULL); +} + +static int dummycon_blank(struct vc_data *vc, int blank, int mode_switch) +{ + /* Redraw, so that we get putc(s) for output done while blanked */ + return 1; +} +#else +static void dummycon_putc(struct vc_data *vc, int c, int ypos, int xpos) { } +static void dummycon_putcs(struct vc_data *vc, const unsigned short *s, + int count, int ypos, int xpos) { } +static int dummycon_blank(struct vc_data *vc, int blank, int mode_switch) +{ + return 0; +} +#endif + static const char *dummycon_startup(void) { return "dummy device"; @@ -44,9 +103,6 @@ static void dummycon_init(struct vc_data *vc, int init) static void dummycon_deinit(struct vc_data *vc) { } static void dummycon_clear(struct vc_data *vc, int sy, int sx, int height, int width) { } -static void dummycon_putc(struct vc_data *vc, int c, int ypos, int xpos) { } -static void dummycon_putcs(struct vc_data *vc, const unsigned short *s, - int count, int ypos, int xpos) { } static void dummycon_cursor(struct vc_data *vc, int mode) { } static bool dummycon_scroll(struct vc_data *vc, unsigned int top, @@ -61,11 +117,6 @@ static int dummycon_switch(struct vc_data *vc) return 0; } -static int dummycon_blank(struct vc_data *vc, int blank, int mode_switch) -{ - return 0; -} - static int dummycon_font_set(struct vc_data *vc, struct console_font *font, unsigned int flags) { diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index cd8d52a967aa..5fb156bdcf4e 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -129,6 +129,12 @@ static inline void fbcon_map_override(void) } #endif /* CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY */ +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER +static bool deferred_takeover = true; +#else +#define deferred_takeover false +#endif + /* font data */ static char fontname[40]; @@ -499,6 +505,12 @@ static int __init fb_console_setup(char *this_opt) margin_color = simple_strtoul(options, &options, 0); continue; } +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER + if (!strcmp(options, "nodefer")) { + deferred_takeover = false; + continue; + } +#endif } return 1; } @@ -3100,6 +3112,9 @@ static int fbcon_fb_unregistered(struct fb_info *info) WARN_CONSOLE_UNLOCKED(); + if (deferred_takeover) + return 0; + idx = info->node; for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map[i] == idx) @@ -3140,6 +3155,13 @@ static void fbcon_remap_all(int idx) WARN_CONSOLE_UNLOCKED(); + if (deferred_takeover) { + for (i = first_fb_vc; i <= last_fb_vc; i++) + con2fb_map_boot[i] = idx; + fbcon_map_override(); + return; + } + for (i = first_fb_vc; i <= last_fb_vc; i++) set_con2fb_map(i, idx, 0); @@ -3191,6 +3213,11 @@ static int fbcon_fb_registered(struct fb_info *info) idx = info->node; fbcon_select_primary(info); + if (deferred_takeover) { + pr_info("fbcon: Deferring console take-over\n"); + return 0; + } + if (info_idx == -1) { for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map_boot[i] == idx) { @@ -3566,8 +3593,46 @@ static int fbcon_init_device(void) return 0; } +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER +static struct notifier_block fbcon_output_nb; + +static int fbcon_output_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + int i; + + WARN_CONSOLE_UNLOCKED(); + + pr_info("fbcon: Taking over console\n"); + + dummycon_unregister_output_notifier(&fbcon_output_nb); + deferred_takeover = false; + logo_shown = FBCON_LOGO_DONTSHOW; + + for (i = 0; i < FB_MAX; i++) { + if (registered_fb[i]) + fbcon_fb_registered(registered_fb[i]); + } + + return NOTIFY_OK; +} + +static void fbcon_register_output_notifier(void) +{ + fbcon_output_nb.notifier_call = fbcon_output_notifier; + dummycon_register_output_notifier(&fbcon_output_nb); +} +#else +static inline void fbcon_register_output_notifier(void) {} +#endif + static void fbcon_start(void) { + if (deferred_takeover) { + fbcon_register_output_notifier(); + return; + } + if (num_registered_fb) { int i; @@ -3594,6 +3659,13 @@ static void fbcon_exit(void) if (fbcon_has_exited) return; +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER + if (deferred_takeover) { + dummycon_unregister_output_notifier(&fbcon_output_nb); + deferred_takeover = false; + } +#endif + kfree((void *)softback_buf); softback_buf = 0UL; diff --git a/include/linux/console.h b/include/linux/console.h index dfd6b0e97855..f59f3dbca65c 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -21,6 +21,7 @@ struct console_font_op; struct console_font; struct module; struct tty_struct; +struct notifier_block; /* * this is what the terminal answers to a ESC-Z or csi0c query. @@ -220,4 +221,8 @@ static inline bool vgacon_text_force(void) { return false; } extern void console_init(void); +/* For deferred console takeover */ +void dummycon_register_output_notifier(struct notifier_block *nb); +void dummycon_unregister_output_notifier(struct notifier_block *nb); + #endif /* _LINUX_CONSOLE_H */ -- cgit v1.2.3-71-gd317 From 1b48b7202c43e41c9f05d39901567dbcad5dc307 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 3 May 2018 16:25:49 +0200 Subject: dma-fence: remove fill_driver_data callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Noticed while I was typing docs. Entirely unused. v2: Remove reference in @timeline_value_str too. While at it clarify why timeline_value_str has a fence parameter - we don't have an explicit timeline structure unfortunately. Cc: Eric Anholt Reviewed-by: Eric Anholt Reviewed-by: Christian König (v1) Cc: Christian König (v1) Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180503142603.28513-2-daniel.vetter@ffwll.ch --- include/linux/dma-fence.h | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index eb9b05aa5aea..111aefe1c956 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -217,17 +217,6 @@ struct dma_fence_ops { */ void (*release)(struct dma_fence *fence); - /** - * @fill_driver_data: - * - * Callback to fill in free-form debug info. - * - * Returns amount of bytes filled, or negative error on failure. - * - * This callback is optional. - */ - int (*fill_driver_data)(struct dma_fence *fence, void *data, int size); - /** * @fence_value_str: * @@ -242,8 +231,9 @@ struct dma_fence_ops { * @timeline_value_str: * * Fills in the current value of the timeline as a string, like the - * sequence number. This should match what @fill_driver_data prints for - * the most recently signalled fence (assuming no delayed signalling). + * sequence number. Note that the specific fence passed to this function + * should not matter, drivers should only use it to look up the + * corresponding timeline structures. */ void (*timeline_value_str)(struct dma_fence *fence, char *str, int size); -- cgit v1.2.3-71-gd317 From c701317a3eb8c012364a8d468f20eabf6df1ad77 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 4 May 2018 16:10:34 +0200 Subject: dma-fence: Make ->enable_signaling optional MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Many drivers have a trivial implementation for ->enable_signaling. Let's make it optional by assuming that signalling is already available when the callback isn't present. v2: Don't do the trick to set the ENABLE_SIGNAL_BIT unconditionally, it results in an expensive spinlock take for everyone. Instead just check if the callback is present. Suggested by Maarten. Also move misplaced kerneldoc hunk to the right patch. Cc: Maarten Lankhorst Reviewed-by: Christian König (v1) Reviewed-by: Maarten Lankhorst Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: Gustavo Padovan Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20180504141034.27727-1-daniel.vetter@ffwll.ch --- drivers/dma-buf/dma-fence.c | 9 +++++---- include/linux/dma-fence.h | 3 ++- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 4edb9fd3cf47..dd01a1720be9 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -200,7 +200,8 @@ void dma_fence_enable_sw_signaling(struct dma_fence *fence) if (!test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags) && - !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { + !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) && + fence->ops->enable_signaling) { trace_dma_fence_enable_signal(fence); spin_lock_irqsave(fence->lock, flags); @@ -260,7 +261,7 @@ int dma_fence_add_callback(struct dma_fence *fence, struct dma_fence_cb *cb, if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) ret = -ENOENT; - else if (!was_set) { + else if (!was_set && fence->ops->enable_signaling) { trace_dma_fence_enable_signal(fence); if (!fence->ops->enable_signaling(fence)) { @@ -388,7 +389,7 @@ dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout) if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) goto out; - if (!was_set) { + if (!was_set && fence->ops->enable_signaling) { trace_dma_fence_enable_signal(fence); if (!fence->ops->enable_signaling(fence)) { @@ -560,7 +561,7 @@ dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops, spinlock_t *lock, u64 context, unsigned seqno) { BUG_ON(!lock); - BUG_ON(!ops || !ops->wait || !ops->enable_signaling || + BUG_ON(!ops || !ops->wait || !ops->get_driver_name || !ops->get_timeline_name); kref_init(&fence->refcount); diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 111aefe1c956..c053d19e1e24 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -166,7 +166,8 @@ struct dma_fence_ops { * released when the fence is signalled (through e.g. the interrupt * handler). * - * This callback is mandatory. + * This callback is optional. If this callback is not present, then the + * driver must always have signaling enabled. */ bool (*enable_signaling)(struct dma_fence *fence); -- cgit v1.2.3-71-gd317 From 55f036ca7e74b85e34958af3d22121c656796413 Mon Sep 17 00:00:00 2001 From: Peter Ziljstra Date: Fri, 15 Jun 2018 10:07:12 +0200 Subject: locking: WW mutex cleanup Make the WW mutex code more readable by adding comments, splitting up functions and pointing out that we're actually using the Wait-Die algorithm. Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Gustavo Padovan Cc: Maarten Lankhorst Cc: Sean Paul Cc: David Airlie Cc: Davidlohr Bueso Cc: "Paul E. McKenney" Cc: Josh Triplett Cc: Thomas Gleixner Cc: Kate Stewart Cc: Philippe Ombredanne Cc: Greg Kroah-Hartman Cc: linux-doc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Co-authored-by: Thomas Hellstrom Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Hellstrom Acked-by: Ingo Molnar --- Documentation/locking/ww-mutex-design.txt | 12 +- include/linux/ww_mutex.h | 28 ++--- kernel/locking/mutex.c | 202 ++++++++++++++++++------------ 3 files changed, 145 insertions(+), 97 deletions(-) (limited to 'include/linux') diff --git a/Documentation/locking/ww-mutex-design.txt b/Documentation/locking/ww-mutex-design.txt index 34c3a1b50b9a..2fd7f2a2af21 100644 --- a/Documentation/locking/ww-mutex-design.txt +++ b/Documentation/locking/ww-mutex-design.txt @@ -32,10 +32,10 @@ the oldest task) wins, and the one with the higher reservation id (i.e. the younger task) unlocks all of the buffers that it has already locked, and then tries again. -In the RDBMS literature this deadlock handling approach is called wait/wound: +In the RDBMS literature this deadlock handling approach is called wait/die: The older tasks waits until it can acquire the contended lock. The younger tasks needs to back off and drop all the locks it is currently holding, i.e. the -younger task is wounded. +younger task dies. Concepts -------- @@ -56,9 +56,9 @@ Furthermore there are three different class of w/w lock acquire functions: * Normal lock acquisition with a context, using ww_mutex_lock. -* Slowpath lock acquisition on the contending lock, used by the wounded task - after having dropped all already acquired locks. These functions have the - _slow postfix. +* Slowpath lock acquisition on the contending lock, used by the task that just + killed its transaction after having dropped all already acquired locks. + These functions have the _slow postfix. From a simple semantics point-of-view the _slow functions are not strictly required, since simply calling the normal ww_mutex_lock functions on the @@ -220,7 +220,7 @@ mutexes are a natural fit for such a case for two reasons: Note that this approach differs in two important ways from the above methods: - Since the list of objects is dynamically constructed (and might very well be - different when retrying due to hitting the -EDEADLK wound condition) there's + different when retrying due to hitting the -EDEADLK die condition) there's no need to keep any object on a persistent list when it's not locked. We can therefore move the list_head into the object itself. - On the other hand the dynamic object list construction also means that the -EALREADY return diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 39fda195bf78..f82fce2229c8 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -6,7 +6,7 @@ * * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar * - * Wound/wait implementation: + * Wait/Die implementation: * Copyright (C) 2013 Canonical Ltd. * * This file contains the main data structure and API definitions. @@ -28,9 +28,9 @@ struct ww_class { struct ww_acquire_ctx { struct task_struct *task; unsigned long stamp; - unsigned acquired; + unsigned int acquired; #ifdef CONFIG_DEBUG_MUTEXES - unsigned done_acquire; + unsigned int done_acquire; struct ww_class *ww_class; struct ww_mutex *contending_lock; #endif @@ -38,8 +38,8 @@ struct ww_acquire_ctx { struct lockdep_map dep_map; #endif #ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH - unsigned deadlock_inject_interval; - unsigned deadlock_inject_countdown; + unsigned int deadlock_inject_interval; + unsigned int deadlock_inject_countdown; #endif }; @@ -102,7 +102,7 @@ static inline void ww_mutex_init(struct ww_mutex *lock, * * Context-based w/w mutex acquiring can be done in any order whatsoever within * a given lock class. Deadlocks will be detected and handled with the - * wait/wound logic. + * wait/die logic. * * Mixing of context-based w/w mutex acquiring and single w/w mutex locking can * result in undetected deadlocks and is so forbidden. Mixing different contexts @@ -195,13 +195,13 @@ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) * Lock the w/w mutex exclusively for this task. * * Deadlocks within a given w/w class of locks are detected and handled with the - * wait/wound algorithm. If the lock isn't immediately avaiable this function + * wait/die algorithm. If the lock isn't immediately available this function * will either sleep until it is (wait case). Or it selects the current context - * for backing off by returning -EDEADLK (wound case). Trying to acquire the + * for backing off by returning -EDEADLK (die case). Trying to acquire the * same lock with the same context twice is also detected and signalled by * returning -EALREADY. Returns 0 if the mutex was successfully acquired. * - * In the wound case the caller must release all currently held w/w mutexes for + * In the die case the caller must release all currently held w/w mutexes for * the given context and then wait for this contending lock to be available by * calling ww_mutex_lock_slow. Alternatively callers can opt to not acquire this * lock and proceed with trying to acquire further w/w mutexes (e.g. when @@ -226,14 +226,14 @@ extern int /* __must_check */ ww_mutex_lock(struct ww_mutex *lock, struct ww_acq * Lock the w/w mutex exclusively for this task. * * Deadlocks within a given w/w class of locks are detected and handled with the - * wait/wound algorithm. If the lock isn't immediately avaiable this function + * wait/die algorithm. If the lock isn't immediately available this function * will either sleep until it is (wait case). Or it selects the current context - * for backing off by returning -EDEADLK (wound case). Trying to acquire the + * for backing off by returning -EDEADLK (die case). Trying to acquire the * same lock with the same context twice is also detected and signalled by * returning -EALREADY. Returns 0 if the mutex was successfully acquired. If a * signal arrives while waiting for the lock then this function returns -EINTR. * - * In the wound case the caller must release all currently held w/w mutexes for + * In the die case the caller must release all currently held w/w mutexes for * the given context and then wait for this contending lock to be available by * calling ww_mutex_lock_slow_interruptible. Alternatively callers can opt to * not acquire this lock and proceed with trying to acquire further w/w mutexes @@ -256,7 +256,7 @@ extern int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock, * @lock: the mutex to be acquired * @ctx: w/w acquire context * - * Acquires a w/w mutex with the given context after a wound case. This function + * Acquires a w/w mutex with the given context after a die case. This function * will sleep until the lock becomes available. * * The caller must have released all w/w mutexes already acquired with the @@ -290,7 +290,7 @@ ww_mutex_lock_slow(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) * @lock: the mutex to be acquired * @ctx: w/w acquire context * - * Acquires a w/w mutex with the given context after a wound case. This function + * Acquires a w/w mutex with the given context after a die case. This function * will sleep until the lock becomes available and returns 0 when the lock has * been acquired. If a signal arrives while waiting for the lock then this * function returns -EINTR. diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index f44f658ae629..cfe48419b7d0 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -244,6 +244,17 @@ void __sched mutex_lock(struct mutex *lock) EXPORT_SYMBOL(mutex_lock); #endif +/* + * Wait-Die: + * The newer transactions are killed when: + * It (the new transaction) makes a request for a lock being held + * by an older transaction. + */ + +/* + * Associate the ww_mutex @ww with the context @ww_ctx under which we acquired + * it. + */ static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) { @@ -282,26 +293,53 @@ ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); #endif ww_ctx->acquired++; + ww->ctx = ww_ctx; } +/* + * Determine if context @a is 'after' context @b. IOW, @a is a younger + * transaction than @b and depending on algorithm either needs to wait for + * @b or die. + */ static inline bool __sched __ww_ctx_stamp_after(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b) { - return a->stamp - b->stamp <= LONG_MAX && - (a->stamp != b->stamp || a > b); + + return (signed long)(a->stamp - b->stamp) > 0; +} + +/* + * Wait-Die; wake a younger waiter context (when locks held) such that it can + * die. + * + * Among waiters with context, only the first one can have other locks acquired + * already (ctx->acquired > 0), because __ww_mutex_add_waiter() and + * __ww_mutex_check_kill() wake any but the earliest context. + */ +static bool __sched +__ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter, + struct ww_acquire_ctx *ww_ctx) +{ + if (waiter->ww_ctx->acquired > 0 && + __ww_ctx_stamp_after(waiter->ww_ctx, ww_ctx)) { + debug_mutex_wake_waiter(lock, waiter); + wake_up_process(waiter->task); + } + + return true; } /* - * Wake up any waiters that may have to back off when the lock is held by the - * given context. + * We just acquired @lock under @ww_ctx, if there are later contexts waiting + * behind us on the wait-list, check if they need to die. * - * Due to the invariants on the wait list, this can only affect the first - * waiter with a context. + * See __ww_mutex_add_waiter() for the list-order construction; basically the + * list is ordered by stamp, smallest (oldest) first. * * The current task must not be on the wait list. */ static void __sched -__ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) +__ww_mutex_check_waiters(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) { struct mutex_waiter *cur; @@ -311,30 +349,23 @@ __ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) if (!cur->ww_ctx) continue; - if (cur->ww_ctx->acquired > 0 && - __ww_ctx_stamp_after(cur->ww_ctx, ww_ctx)) { - debug_mutex_wake_waiter(lock, cur); - wake_up_process(cur->task); - } - - break; + if (__ww_mutex_die(lock, cur, ww_ctx)) + break; } } /* - * After acquiring lock with fastpath or when we lost out in contested - * slowpath, set ctx and wake up any waiters so they can recheck. + * After acquiring lock with fastpath, where we do not hold wait_lock, set ctx + * and wake up any waiters so they can recheck. */ static __always_inline void ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { ww_mutex_lock_acquired(lock, ctx); - lock->ctx = ctx; - /* * The lock->ctx update should be visible on all cores before - * the atomic read is done, otherwise contended waiters might be + * the WAITERS check is done, otherwise contended waiters might be * missed. The contended waiters will either see ww_ctx == NULL * and keep spinning, or it will acquire wait_lock, add itself * to waiter list and sleep. @@ -348,29 +379,14 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) return; /* - * Uh oh, we raced in fastpath, wake up everyone in this case, - * so they can see the new lock->ctx. + * Uh oh, we raced in fastpath, check if any of the waiters need to + * die. */ spin_lock(&lock->base.wait_lock); - __ww_mutex_wakeup_for_backoff(&lock->base, ctx); + __ww_mutex_check_waiters(&lock->base, ctx); spin_unlock(&lock->base.wait_lock); } -/* - * After acquiring lock in the slowpath set ctx. - * - * Unlike for the fast path, the caller ensures that waiters are woken up where - * necessary. - * - * Callers must hold the mutex wait_lock. - */ -static __always_inline void -ww_mutex_set_context_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) -{ - ww_mutex_lock_acquired(lock, ctx); - lock->ctx = ctx; -} - #ifdef CONFIG_MUTEX_SPIN_ON_OWNER static inline @@ -646,37 +662,73 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock) } EXPORT_SYMBOL(ww_mutex_unlock); + +static __always_inline int __sched +__ww_mutex_kill(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) +{ + if (ww_ctx->acquired > 0) { +#ifdef CONFIG_DEBUG_MUTEXES + struct ww_mutex *ww; + + ww = container_of(lock, struct ww_mutex, base); + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock); + ww_ctx->contending_lock = ww; +#endif + return -EDEADLK; + } + + return 0; +} + + +/* + * Check whether we need to kill the transaction for the current lock acquire. + * + * Wait-Die: If we're trying to acquire a lock already held by an older + * context, kill ourselves. + * + * Since __ww_mutex_add_waiter() orders the wait-list on stamp, we only have to + * look at waiters before us in the wait-list. + */ static inline int __sched -__ww_mutex_lock_check_stamp(struct mutex *lock, struct mutex_waiter *waiter, - struct ww_acquire_ctx *ctx) +__ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter, + struct ww_acquire_ctx *ctx) { struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx); struct mutex_waiter *cur; + if (ctx->acquired == 0) + return 0; + if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx)) - goto deadlock; + return __ww_mutex_kill(lock, ctx); /* * If there is a waiter in front of us that has a context, then its - * stamp is earlier than ours and we must back off. + * stamp is earlier than ours and we must kill ourself. */ cur = waiter; list_for_each_entry_continue_reverse(cur, &lock->wait_list, list) { - if (cur->ww_ctx) - goto deadlock; + if (!cur->ww_ctx) + continue; + + return __ww_mutex_kill(lock, ctx); } return 0; - -deadlock: -#ifdef CONFIG_DEBUG_MUTEXES - DEBUG_LOCKS_WARN_ON(ctx->contending_lock); - ctx->contending_lock = ww; -#endif - return -EDEADLK; } +/* + * Add @waiter to the wait-list, keep the wait-list ordered by stamp, smallest + * first. Such that older contexts are preferred to acquire the lock over + * younger contexts. + * + * Waiters without context are interspersed in FIFO order. + * + * Furthermore, for Wait-Die kill ourself immediately when possible (there are + * older contexts already waiting) to avoid unnecessary waiting. + */ static inline int __sched __ww_mutex_add_waiter(struct mutex_waiter *waiter, struct mutex *lock, @@ -693,7 +745,7 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, /* * Add the waiter before the first waiter with a higher stamp. * Waiters without a context are skipped to avoid starving - * them. + * them. Wait-Die waiters may die here. */ pos = &lock->wait_list; list_for_each_entry_reverse(cur, &lock->wait_list, list) { @@ -701,34 +753,27 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, continue; if (__ww_ctx_stamp_after(ww_ctx, cur->ww_ctx)) { - /* Back off immediately if necessary. */ - if (ww_ctx->acquired > 0) { -#ifdef CONFIG_DEBUG_MUTEXES - struct ww_mutex *ww; + /* + * Wait-Die: if we find an older context waiting, there + * is no point in queueing behind it, as we'd have to + * die the moment it would acquire the lock. + */ + int ret = __ww_mutex_kill(lock, ww_ctx); - ww = container_of(lock, struct ww_mutex, base); - DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock); - ww_ctx->contending_lock = ww; -#endif - return -EDEADLK; - } + if (ret) + return ret; break; } pos = &cur->list; - /* - * Wake up the waiter so that it gets a chance to back - * off. - */ - if (cur->ww_ctx->acquired > 0) { - debug_mutex_wake_waiter(lock, cur); - wake_up_process(cur->task); - } + /* Wait-Die: ensure younger waiters die. */ + __ww_mutex_die(lock, cur, ww_ctx); } list_add_tail(&waiter->list, pos); + return 0; } @@ -772,7 +817,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, */ if (__mutex_trylock(lock)) { if (use_ww_ctx && ww_ctx) - __ww_mutex_wakeup_for_backoff(lock, ww_ctx); + __ww_mutex_check_waiters(lock, ww_ctx); goto skip_wait; } @@ -790,10 +835,13 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, waiter.ww_ctx = MUTEX_POISON_WW_CTX; #endif } else { - /* Add in stamp order, waking up waiters that must back off. */ + /* + * Add in stamp order, waking up waiters that must kill + * themselves. + */ ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx); if (ret) - goto err_early_backoff; + goto err_early_kill; waiter.ww_ctx = ww_ctx; } @@ -815,7 +863,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, goto acquired; /* - * Check for signals and wound conditions while holding + * Check for signals and kill conditions while holding * wait_lock. This ensures the lock cancellation is ordered * against mutex_unlock() and wake-ups do not go missing. */ @@ -824,8 +872,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, goto err; } - if (use_ww_ctx && ww_ctx && ww_ctx->acquired > 0) { - ret = __ww_mutex_lock_check_stamp(lock, &waiter, ww_ctx); + if (use_ww_ctx && ww_ctx) { + ret = __ww_mutex_check_kill(lock, &waiter, ww_ctx); if (ret) goto err; } @@ -870,7 +918,7 @@ skip_wait: lock_acquired(&lock->dep_map, ip); if (use_ww_ctx && ww_ctx) - ww_mutex_set_context_slowpath(ww, ww_ctx); + ww_mutex_lock_acquired(ww, ww_ctx); spin_unlock(&lock->wait_lock); preempt_enable(); @@ -879,7 +927,7 @@ skip_wait: err: __set_current_state(TASK_RUNNING); mutex_remove_waiter(lock, &waiter, current); -err_early_backoff: +err_early_kill: spin_unlock(&lock->wait_lock); debug_mutex_free_waiter(&waiter); mutex_release(&lock->dep_map, 1, ip); -- cgit v1.2.3-71-gd317 From 08295b3b5beec9aac0f7a9db86f0fc3792039da3 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Fri, 15 Jun 2018 10:17:38 +0200 Subject: locking: Implement an algorithm choice for Wound-Wait mutexes The current Wound-Wait mutex algorithm is actually not Wound-Wait but Wait-Die. Implement also Wound-Wait as a per-ww-class choice. Wound-Wait is, contrary to Wait-Die a preemptive algorithm and is known to generate fewer backoffs. Testing reveals that this is true if the number of simultaneous contending transactions is small. As the number of simultaneous contending threads increases, Wait-Wound becomes inferior to Wait-Die in terms of elapsed time. Possibly due to the larger number of held locks of sleeping transactions. Update documentation and callers. Timings using git://people.freedesktop.org/~thomash/ww_mutex_test tag patch-18-06-15 Each thread runs 100000 batches of lock / unlock 800 ww mutexes randomly chosen out of 100000. Four core Intel x86_64: Algorithm #threads Rollbacks time Wound-Wait 4 ~100 ~17s. Wait-Die 4 ~150000 ~19s. Wound-Wait 16 ~360000 ~109s. Wait-Die 16 ~450000 ~82s. Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Gustavo Padovan Cc: Maarten Lankhorst Cc: Sean Paul Cc: David Airlie Cc: Davidlohr Bueso Cc: "Paul E. McKenney" Cc: Josh Triplett Cc: Thomas Gleixner Cc: Kate Stewart Cc: Philippe Ombredanne Cc: Greg Kroah-Hartman Cc: linux-doc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Co-authored-by: Peter Zijlstra Signed-off-by: Thomas Hellstrom Acked-by: Peter Zijlstra (Intel) Acked-by: Ingo Molnar --- Documentation/locking/ww-mutex-design.txt | 57 +++++++++-- drivers/dma-buf/reservation.c | 2 +- drivers/gpu/drm/drm_modeset_lock.c | 2 +- include/linux/ww_mutex.h | 17 ++- kernel/locking/locktorture.c | 2 +- kernel/locking/mutex.c | 165 +++++++++++++++++++++++++++--- kernel/locking/test-ww_mutex.c | 2 +- lib/locking-selftest.c | 2 +- 8 files changed, 213 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/Documentation/locking/ww-mutex-design.txt b/Documentation/locking/ww-mutex-design.txt index 2fd7f2a2af21..f0ed7c30e695 100644 --- a/Documentation/locking/ww-mutex-design.txt +++ b/Documentation/locking/ww-mutex-design.txt @@ -1,4 +1,4 @@ -Wait/Wound Deadlock-Proof Mutex Design +Wound/Wait Deadlock-Proof Mutex Design ====================================== Please read mutex-design.txt first, as it applies to wait/wound mutexes too. @@ -32,10 +32,26 @@ the oldest task) wins, and the one with the higher reservation id (i.e. the younger task) unlocks all of the buffers that it has already locked, and then tries again. -In the RDBMS literature this deadlock handling approach is called wait/die: -The older tasks waits until it can acquire the contended lock. The younger tasks -needs to back off and drop all the locks it is currently holding, i.e. the -younger task dies. +In the RDBMS literature, a reservation ticket is associated with a transaction. +and the deadlock handling approach is called Wait-Die. The name is based on +the actions of a locking thread when it encounters an already locked mutex. +If the transaction holding the lock is younger, the locking transaction waits. +If the transaction holding the lock is older, the locking transaction backs off +and dies. Hence Wait-Die. +There is also another algorithm called Wound-Wait: +If the transaction holding the lock is younger, the locking transaction +wounds the transaction holding the lock, requesting it to die. +If the transaction holding the lock is older, it waits for the other +transaction. Hence Wound-Wait. +The two algorithms are both fair in that a transaction will eventually succeed. +However, the Wound-Wait algorithm is typically stated to generate fewer backoffs +compared to Wait-Die, but is, on the other hand, associated with more work than +Wait-Die when recovering from a backoff. Wound-Wait is also a preemptive +algorithm in that transactions are wounded by other transactions, and that +requires a reliable way to pick up up the wounded condition and preempt the +running transaction. Note that this is not the same as process preemption. A +Wound-Wait transaction is considered preempted when it dies (returning +-EDEADLK) following a wound. Concepts -------- @@ -47,10 +63,12 @@ Acquire context: To ensure eventual forward progress it is important the a task trying to acquire locks doesn't grab a new reservation id, but keeps the one it acquired when starting the lock acquisition. This ticket is stored in the acquire context. Furthermore the acquire context keeps track of debugging state -to catch w/w mutex interface abuse. +to catch w/w mutex interface abuse. An acquire context is representing a +transaction. W/w class: In contrast to normal mutexes the lock class needs to be explicit for -w/w mutexes, since it is required to initialize the acquire context. +w/w mutexes, since it is required to initialize the acquire context. The lock +class also specifies what algorithm to use, Wound-Wait or Wait-Die. Furthermore there are three different class of w/w lock acquire functions: @@ -90,6 +108,12 @@ provided. Usage ----- +The algorithm (Wait-Die vs Wound-Wait) is chosen by using either +DEFINE_WW_CLASS() (Wound-Wait) or DEFINE_WD_CLASS() (Wait-Die) +As a rough rule of thumb, use Wound-Wait iff you +expect the number of simultaneous competing transactions to be typically small, +and you want to reduce the number of rollbacks. + Three different ways to acquire locks within the same w/w class. Common definitions for methods #1 and #2: @@ -312,12 +336,23 @@ Design: We maintain the following invariants for the wait list: (1) Waiters with an acquire context are sorted by stamp order; waiters without an acquire context are interspersed in FIFO order. - (2) Among waiters with contexts, only the first one can have other locks - acquired already (ctx->acquired > 0). Note that this waiter may come - after other waiters without contexts in the list. + (2) For Wait-Die, among waiters with contexts, only the first one can have + other locks acquired already (ctx->acquired > 0). Note that this waiter + may come after other waiters without contexts in the list. + + The Wound-Wait preemption is implemented with a lazy-preemption scheme: + The wounded status of the transaction is checked only when there is + contention for a new lock and hence a true chance of deadlock. In that + situation, if the transaction is wounded, it backs off, clears the + wounded status and retries. A great benefit of implementing preemption in + this way is that the wounded transaction can identify a contending lock to + wait for before restarting the transaction. Just blindly restarting the + transaction would likely make the transaction end up in a situation where + it would have to back off again. In general, not much contention is expected. The locks are typically used to - serialize access to resources for devices. + serialize access to resources for devices, and optimization focus should + therefore be directed towards the uncontended cases. Lockdep: Special care has been taken to warn for as many cases of api abuse diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c index 314eb1071cce..20bf90f4ee63 100644 --- a/drivers/dma-buf/reservation.c +++ b/drivers/dma-buf/reservation.c @@ -46,7 +46,7 @@ * write-side updates. */ -DEFINE_WW_CLASS(reservation_ww_class); +DEFINE_WD_CLASS(reservation_ww_class); EXPORT_SYMBOL(reservation_ww_class); struct lock_class_key reservation_seqcount_class; diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c index 8a5100685875..638be2eb67b4 100644 --- a/drivers/gpu/drm/drm_modeset_lock.c +++ b/drivers/gpu/drm/drm_modeset_lock.c @@ -70,7 +70,7 @@ * lists and lookup data structures. */ -static DEFINE_WW_CLASS(crtc_ww_class); +static DEFINE_WD_CLASS(crtc_ww_class); /** * drm_modeset_lock_all - take all modeset locks diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index f82fce2229c8..3af7c0e03be5 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -8,6 +8,8 @@ * * Wait/Die implementation: * Copyright (C) 2013 Canonical Ltd. + * Choice of algorithm: + * Copyright (C) 2018 WMWare Inc. * * This file contains the main data structure and API definitions. */ @@ -23,12 +25,15 @@ struct ww_class { struct lock_class_key mutex_key; const char *acquire_name; const char *mutex_name; + unsigned int is_wait_die; }; struct ww_acquire_ctx { struct task_struct *task; unsigned long stamp; unsigned int acquired; + unsigned short wounded; + unsigned short is_wait_die; #ifdef CONFIG_DEBUG_MUTEXES unsigned int done_acquire; struct ww_class *ww_class; @@ -58,17 +63,21 @@ struct ww_mutex { # define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) #endif -#define __WW_CLASS_INITIALIZER(ww_class) \ +#define __WW_CLASS_INITIALIZER(ww_class, _is_wait_die) \ { .stamp = ATOMIC_LONG_INIT(0) \ , .acquire_name = #ww_class "_acquire" \ - , .mutex_name = #ww_class "_mutex" } + , .mutex_name = #ww_class "_mutex" \ + , .is_wait_die = _is_wait_die } #define __WW_MUTEX_INITIALIZER(lockname, class) \ { .base = __MUTEX_INITIALIZER(lockname.base) \ __WW_CLASS_MUTEX_INITIALIZER(lockname, class) } +#define DEFINE_WD_CLASS(classname) \ + struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 1) + #define DEFINE_WW_CLASS(classname) \ - struct ww_class classname = __WW_CLASS_INITIALIZER(classname) + struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 0) #define DEFINE_WW_MUTEX(mutexname, ww_class) \ struct ww_mutex mutexname = __WW_MUTEX_INITIALIZER(mutexname, ww_class) @@ -123,6 +132,8 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx, ctx->task = current; ctx->stamp = atomic_long_inc_return_relaxed(&ww_class->stamp); ctx->acquired = 0; + ctx->wounded = false; + ctx->is_wait_die = ww_class->is_wait_die; #ifdef CONFIG_DEBUG_MUTEXES ctx->ww_class = ww_class; ctx->done_acquire = 0; diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 8402b3349dca..c28224347d69 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -365,7 +365,7 @@ static struct lock_torture_ops mutex_lock_ops = { }; #include -static DEFINE_WW_CLASS(torture_ww_class); +static DEFINE_WD_CLASS(torture_ww_class); static DEFINE_WW_MUTEX(torture_ww_mutex_0, &torture_ww_class); static DEFINE_WW_MUTEX(torture_ww_mutex_1, &torture_ww_class); static DEFINE_WW_MUTEX(torture_ww_mutex_2, &torture_ww_class); diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index cfe48419b7d0..1a81a1257b3f 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -173,6 +173,21 @@ static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_wait return list_first_entry(&lock->wait_list, struct mutex_waiter, list) == waiter; } +/* + * Add @waiter to a given location in the lock wait_list and set the + * FLAG_WAITERS flag if it's the first waiter. + */ +static void __sched +__mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, + struct list_head *list) +{ + debug_mutex_add_waiter(lock, waiter, current); + + list_add_tail(&waiter->list, list); + if (__mutex_waiter_is_first(lock, waiter)) + __mutex_set_flag(lock, MUTEX_FLAG_WAITERS); +} + /* * Give up ownership to a specific task, when @task = NULL, this is equivalent * to a regular unlock. Sets PICKUP on a handoff, clears HANDOF, preserves @@ -249,6 +264,11 @@ EXPORT_SYMBOL(mutex_lock); * The newer transactions are killed when: * It (the new transaction) makes a request for a lock being held * by an older transaction. + * + * Wound-Wait: + * The newer transactions are wounded when: + * An older transaction makes a request for a lock being held by + * the newer transaction. */ /* @@ -320,6 +340,9 @@ static bool __sched __ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter, struct ww_acquire_ctx *ww_ctx) { + if (!ww_ctx->is_wait_die) + return false; + if (waiter->ww_ctx->acquired > 0 && __ww_ctx_stamp_after(waiter->ww_ctx, ww_ctx)) { debug_mutex_wake_waiter(lock, waiter); @@ -329,13 +352,65 @@ __ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter, return true; } +/* + * Wound-Wait; wound a younger @hold_ctx if it holds the lock. + * + * Wound the lock holder if there are waiters with older transactions than + * the lock holders. Even if multiple waiters may wound the lock holder, + * it's sufficient that only one does. + */ +static bool __ww_mutex_wound(struct mutex *lock, + struct ww_acquire_ctx *ww_ctx, + struct ww_acquire_ctx *hold_ctx) +{ + struct task_struct *owner = __mutex_owner(lock); + + lockdep_assert_held(&lock->wait_lock); + + /* + * Possible through __ww_mutex_add_waiter() when we race with + * ww_mutex_set_context_fastpath(). In that case we'll get here again + * through __ww_mutex_check_waiters(). + */ + if (!hold_ctx) + return false; + + /* + * Can have !owner because of __mutex_unlock_slowpath(), but if owner, + * it cannot go away because we'll have FLAG_WAITERS set and hold + * wait_lock. + */ + if (!owner) + return false; + + if (ww_ctx->acquired > 0 && __ww_ctx_stamp_after(hold_ctx, ww_ctx)) { + hold_ctx->wounded = 1; + + /* + * wake_up_process() paired with set_current_state() + * inserts sufficient barriers to make sure @owner either sees + * it's wounded in __ww_mutex_lock_check_stamp() or has a + * wakeup pending to re-read the wounded state. + */ + if (owner != current) + wake_up_process(owner); + + return true; + } + + return false; +} + /* * We just acquired @lock under @ww_ctx, if there are later contexts waiting - * behind us on the wait-list, check if they need to die. + * behind us on the wait-list, check if they need to die, or wound us. * * See __ww_mutex_add_waiter() for the list-order construction; basically the * list is ordered by stamp, smallest (oldest) first. * + * This relies on never mixing wait-die/wound-wait on the same wait-list; + * which is currently ensured by that being a ww_class property. + * * The current task must not be on the wait list. */ static void __sched @@ -349,7 +424,8 @@ __ww_mutex_check_waiters(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) if (!cur->ww_ctx) continue; - if (__ww_mutex_die(lock, cur, ww_ctx)) + if (__ww_mutex_die(lock, cur, ww_ctx) || + __ww_mutex_wound(lock, cur->ww_ctx, ww_ctx)) break; } } @@ -370,17 +446,23 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) * and keep spinning, or it will acquire wait_lock, add itself * to waiter list and sleep. */ - smp_mb(); /* ^^^ */ + smp_mb(); /* See comments above and below. */ /* - * Check if lock is contended, if not there is nobody to wake up + * [W] ww->ctx = ctx [W] MUTEX_FLAG_WAITERS + * MB MB + * [R] MUTEX_FLAG_WAITERS [R] ww->ctx + * + * The memory barrier above pairs with the memory barrier in + * __ww_mutex_add_waiter() and makes sure we either observe ww->ctx + * and/or !empty list. */ if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS))) return; /* * Uh oh, we raced in fastpath, check if any of the waiters need to - * die. + * die or wound us. */ spin_lock(&lock->base.wait_lock); __ww_mutex_check_waiters(&lock->base, ctx); @@ -682,7 +764,9 @@ __ww_mutex_kill(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) /* - * Check whether we need to kill the transaction for the current lock acquire. + * Check the wound condition for the current lock acquire. + * + * Wound-Wait: If we're wounded, kill ourself. * * Wait-Die: If we're trying to acquire a lock already held by an older * context, kill ourselves. @@ -701,6 +785,13 @@ __ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter, if (ctx->acquired == 0) return 0; + if (!ctx->is_wait_die) { + if (ctx->wounded) + return __ww_mutex_kill(lock, ctx); + + return 0; + } + if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx)) return __ww_mutex_kill(lock, ctx); @@ -727,7 +818,8 @@ __ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter, * Waiters without context are interspersed in FIFO order. * * Furthermore, for Wait-Die kill ourself immediately when possible (there are - * older contexts already waiting) to avoid unnecessary waiting. + * older contexts already waiting) to avoid unnecessary waiting and for + * Wound-Wait ensure we wound the owning context when it is younger. */ static inline int __sched __ww_mutex_add_waiter(struct mutex_waiter *waiter, @@ -736,16 +828,21 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, { struct mutex_waiter *cur; struct list_head *pos; + bool is_wait_die; if (!ww_ctx) { - list_add_tail(&waiter->list, &lock->wait_list); + __mutex_add_waiter(lock, waiter, &lock->wait_list); return 0; } + is_wait_die = ww_ctx->is_wait_die; + /* * Add the waiter before the first waiter with a higher stamp. * Waiters without a context are skipped to avoid starving - * them. Wait-Die waiters may die here. + * them. Wait-Die waiters may die here. Wound-Wait waiters + * never die here, but they are sorted in stamp order and + * may wound the lock holder. */ pos = &lock->wait_list; list_for_each_entry_reverse(cur, &lock->wait_list, list) { @@ -758,10 +855,12 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, * is no point in queueing behind it, as we'd have to * die the moment it would acquire the lock. */ - int ret = __ww_mutex_kill(lock, ww_ctx); + if (is_wait_die) { + int ret = __ww_mutex_kill(lock, ww_ctx); - if (ret) - return ret; + if (ret) + return ret; + } break; } @@ -772,7 +871,23 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, __ww_mutex_die(lock, cur, ww_ctx); } - list_add_tail(&waiter->list, pos); + __mutex_add_waiter(lock, waiter, pos); + + /* + * Wound-Wait: if we're blocking on a mutex owned by a younger context, + * wound that such that we might proceed. + */ + if (!is_wait_die) { + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); + + /* + * See ww_mutex_set_context_fastpath(). Orders setting + * MUTEX_FLAG_WAITERS vs the ww->ctx load, + * such that either we or the fastpath will wound @ww->ctx. + */ + smp_mb(); + __ww_mutex_wound(lock, ww_ctx, ww->ctx); + } return 0; } @@ -796,6 +911,14 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, if (use_ww_ctx && ww_ctx) { if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) return -EALREADY; + + /* + * Reset the wounded flag after a kill. No other process can + * race and wound us here since they can't have a valid owner + * pointer if we don't have any locks held. + */ + if (ww_ctx->acquired == 0) + ww_ctx->wounded = 0; } preempt_disable(); @@ -829,7 +952,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, if (!use_ww_ctx) { /* add waiting tasks to the end of the waitqueue (FIFO): */ - list_add_tail(&waiter.list, &lock->wait_list); + __mutex_add_waiter(lock, &waiter, &lock->wait_list); + #ifdef CONFIG_DEBUG_MUTEXES waiter.ww_ctx = MUTEX_POISON_WW_CTX; @@ -848,9 +972,6 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, waiter.task = current; - if (__mutex_waiter_is_first(lock, &waiter)) - __mutex_set_flag(lock, MUTEX_FLAG_WAITERS); - set_current_state(state); for (;;) { /* @@ -907,6 +1028,16 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, acquired: __set_current_state(TASK_RUNNING); + if (use_ww_ctx && ww_ctx) { + /* + * Wound-Wait; we stole the lock (!first_waiter), check the + * waiters as anyone might want to wound us. + */ + if (!ww_ctx->is_wait_die && + !__mutex_waiter_is_first(lock, &waiter)) + __ww_mutex_check_waiters(lock, ww_ctx); + } + mutex_remove_waiter(lock, &waiter, current); if (likely(list_empty(&lock->wait_list))) __mutex_clear_flag(lock, MUTEX_FLAGS); diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 0e4cd64ad2c0..5b915b370d5a 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -26,7 +26,7 @@ #include #include -static DEFINE_WW_CLASS(ww_class); +static DEFINE_WD_CLASS(ww_class); struct workqueue_struct *wq; struct test_mutex { diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index b5c1293ce147..1e1bbf171eca 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -29,7 +29,7 @@ */ static unsigned int debug_locks_verbose; -static DEFINE_WW_CLASS(ww_lockdep); +static DEFINE_WD_CLASS(ww_lockdep); static int __init setup_debug_locks_verbose(char *str) { -- cgit v1.2.3-71-gd317 From 418cc6ca06071e7b7d75c0d525d80a6f49a763d6 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 3 May 2018 16:25:52 +0200 Subject: dma-fence: Make ->wait callback optional MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Almost everyone uses dma_fence_default_wait. v2: Also remove the BUG_ON(!ops->wait) (Chris). Reviewed-by: Christian König (v1) Signed-off-by: Daniel Vetter Cc: Chris Wilson Cc: Sumit Semwal Cc: Gustavo Padovan Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20180503142603.28513-5-daniel.vetter@ffwll.ch --- drivers/dma-buf/dma-fence-array.c | 1 - drivers/dma-buf/dma-fence.c | 8 +++++--- drivers/dma-buf/sw_sync.c | 1 - include/linux/dma-fence.h | 13 ++++++++----- 4 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c index dd1edfb27b61..a8c254497251 100644 --- a/drivers/dma-buf/dma-fence-array.c +++ b/drivers/dma-buf/dma-fence-array.c @@ -104,7 +104,6 @@ const struct dma_fence_ops dma_fence_array_ops = { .get_timeline_name = dma_fence_array_get_timeline_name, .enable_signaling = dma_fence_array_enable_signaling, .signaled = dma_fence_array_signaled, - .wait = dma_fence_default_wait, .release = dma_fence_array_release, }; EXPORT_SYMBOL(dma_fence_array_ops); diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index ea343f992112..7a92f85a4cec 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -158,7 +158,10 @@ dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout) return -EINVAL; trace_dma_fence_wait_start(fence); - ret = fence->ops->wait(fence, intr, timeout); + if (fence->ops->wait) + ret = fence->ops->wait(fence, intr, timeout); + else + ret = dma_fence_default_wait(fence, intr, timeout); trace_dma_fence_wait_end(fence); return ret; } @@ -556,8 +559,7 @@ dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops, spinlock_t *lock, u64 context, unsigned seqno) { BUG_ON(!lock); - BUG_ON(!ops || !ops->wait || - !ops->get_driver_name || !ops->get_timeline_name); + BUG_ON(!ops || !ops->get_driver_name || !ops->get_timeline_name); kref_init(&fence->refcount); fence->ops = ops; diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c index 3d78ca89a605..53c1d6d36a64 100644 --- a/drivers/dma-buf/sw_sync.c +++ b/drivers/dma-buf/sw_sync.c @@ -188,7 +188,6 @@ static const struct dma_fence_ops timeline_fence_ops = { .get_timeline_name = timeline_fence_get_timeline_name, .enable_signaling = timeline_fence_enable_signaling, .signaled = timeline_fence_signaled, - .wait = dma_fence_default_wait, .release = timeline_fence_release, .fence_value_str = timeline_fence_value_str, .timeline_value_str = timeline_fence_timeline_value_str, diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index c053d19e1e24..02dba8cd033d 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -191,11 +191,14 @@ struct dma_fence_ops { /** * @wait: * - * Custom wait implementation, or dma_fence_default_wait. + * Custom wait implementation, defaults to dma_fence_default_wait() if + * not set. * - * Must not be NULL, set to dma_fence_default_wait for default implementation. - * the dma_fence_default_wait implementation should work for any fence, as long - * as enable_signaling works correctly. + * The dma_fence_default_wait implementation should work for any fence, as long + * as @enable_signaling works correctly. This hook allows drivers to + * have an optimized version for the case where a process context is + * already available, e.g. if @enable_signaling for the general case + * needs to set up a worker thread. * * Must return -ERESTARTSYS if the wait is intr = true and the wait was * interrupted, and remaining jiffies if fence has signaled, or 0 if wait @@ -203,7 +206,7 @@ struct dma_fence_ops { * which should be treated as if the fence is signaled. For example a hardware * lockup could be reported like that. * - * This callback is mandatory. + * This callback is optional. */ signed long (*wait)(struct dma_fence *fence, bool intr, signed long timeout); -- cgit v1.2.3-71-gd317 From 576c7218a1546e0153480b208b125509cec71470 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 25 Jun 2018 13:17:41 -0500 Subject: PCI: Export pcie_get_speed_cap and pcie_get_width_cap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So drivers can use them. This can be used to replace duplicate code in the drm subsystem. Acked-by: Christian König Acked-by: Bjorn Helgaas Signed-off-by: Alex Deucher --- drivers/pci/pci.c | 2 ++ include/linux/pci.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 97acba712e4e..22adaf35b136 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5222,6 +5222,7 @@ enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev) return PCI_SPEED_UNKNOWN; } +EXPORT_SYMBOL(pcie_get_speed_cap); /** * pcie_get_width_cap - query for the PCI device's link width capability @@ -5240,6 +5241,7 @@ enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev) return PCIE_LNK_WIDTH_UNKNOWN; } +EXPORT_SYMBOL(pcie_get_width_cap); /** * pcie_bandwidth_capable - calculate a PCI device's link bandwidth capability diff --git a/include/linux/pci.h b/include/linux/pci.h index 340029b2fb38..6e0c0803b241 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -261,6 +261,9 @@ enum pci_bus_speed { PCI_SPEED_UNKNOWN = 0xff, }; +enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev); +enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev); + struct pci_cap_saved_data { u16 cap_nr; bool cap_extended; -- cgit v1.2.3-71-gd317 From 489cae632fc04927e8ef36ac8d8847193a41df3b Mon Sep 17 00:00:00 2001 From: Jordan Crouse Date: Tue, 24 Jul 2018 10:33:19 -0600 Subject: include: Move ascii85 functions from i915 to linux/ascii85.h The i915 DRM driver very cleverly used ascii85 encoding for their GPU state file. Move the encode functions to a general header file to support other drivers that might be interested in the same functionality. v4: Make the return value const char * as suggested by Chris Wilson v3: Fix error_puts -> err_puts pointed out by the 01.org bot v2: Update API to be cleaner for the caller as suggested by Chris Wilson Reviewed-by: Chris Wilson Signed-off-by: Jordan Crouse Signed-off-by: Rob Clark --- drivers/gpu/drm/i915/i915_gpu_error.c | 34 ++++--------------------------- include/linux/ascii85.h | 38 +++++++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+), 30 deletions(-) create mode 100644 include/linux/ascii85.h (limited to 'include/linux') diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 8c81cf3aa182..f7f2aa71d8d9 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -31,6 +31,7 @@ #include #include #include +#include #include "i915_gpu_error.h" #include "i915_drv.h" @@ -517,35 +518,12 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...) va_end(args); } -static int -ascii85_encode_len(int len) -{ - return DIV_ROUND_UP(len, 4); -} - -static bool -ascii85_encode(u32 in, char *out) -{ - int i; - - if (in == 0) - return false; - - out[5] = '\0'; - for (i = 5; i--; ) { - out[i] = '!' + in % 85; - in /= 85; - } - - return true; -} - static void print_error_obj(struct drm_i915_error_state_buf *m, struct intel_engine_cs *engine, const char *name, struct drm_i915_error_object *obj) { - char out[6]; + char out[ASCII85_BUFSZ]; int page; if (!obj) @@ -567,12 +545,8 @@ static void print_error_obj(struct drm_i915_error_state_buf *m, len -= obj->unused; len = ascii85_encode_len(len); - for (i = 0; i < len; i++) { - if (ascii85_encode(obj->pages[page][i], out)) - err_puts(m, out); - else - err_puts(m, "z"); - } + for (i = 0; i < len; i++) + err_puts(m, ascii85_encode(obj->pages[page][i], out)); } err_puts(m, "\n"); } diff --git a/include/linux/ascii85.h b/include/linux/ascii85.h new file mode 100644 index 000000000000..4cc40201273e --- /dev/null +++ b/include/linux/ascii85.h @@ -0,0 +1,38 @@ +/* + * SPDX-License-Identifier: GPL-2.0 + * + * Copyright (c) 2008 Intel Corporation + * Copyright (c) 2018 The Linux Foundation. All rights reserved. + */ + +#ifndef _ASCII85_H_ +#define _ASCII85_H_ + +#include + +#define ASCII85_BUFSZ 6 + +static inline long +ascii85_encode_len(long len) +{ + return DIV_ROUND_UP(len, 4); +} + +static inline const char * +ascii85_encode(u32 in, char *out) +{ + int i; + + if (in == 0) + return "z"; + + out[5] = '\0'; + for (i = 5; i--; ) { + out[i] = '!' + in % 85; + in /= 85; + } + + return out; +} + +#endif -- cgit v1.2.3-71-gd317