diff options
| author | Dave Airlie | 2021-06-10 11:03:50 +1000 |
|---|---|---|
| committer | Dave Airlie | 2021-06-10 11:28:09 +1000 |
| commit | 09b020bb05a514f560979438fa40406bc63d5353 (patch) | |
| tree | 2568980e133e47bce3509cab92f7adac99b51cc4 | |
| parent | 5745d647d5563d3e9d32013ad4e5c629acff04d7 (diff) | |
| parent | 5b7a2c92b6102447a973f2f1ef19d660ec329881 (diff) | |
Merge tag 'drm-misc-next-2021-06-09' of git://anongit.freedesktop.org/drm/drm-misc into drm-next
drm-misc-next for 5.14:
UAPI Changes:
* drm/panfrost: Export AFBC_FEATURES register to userspace
Cross-subsystem Changes:
* dma-buf: Fix debug printing; Rename dma_resv_*() functions + changes
in callers; Cleanups
Core Changes:
* Add prefetching memcpy for WC
* Avoid circular dependency on CONFIG_FB
* Cleanups
* Documentation fixes throughout DRM
* ttm: Make struct ttm_resource the base of all managers + changes
in all users of TTM; Add a generic memcpy for page-based iomem; Remove
use of VM_MIXEDMAP; Cleanups
Driver Changes:
* drm/bridge: Add TI SN65DSI83 and SN65DSI84 + DT bindings
* drm/hyperv: Add DRM driver for HyperV graphics output
* drm/msm: Fix module dependencies
* drm/panel: KD53T133: Support rotation
* drm/pl111: Fix module dependencies
* drm/qxl: Fixes
* drm/stm: Cleanups
* drm/sun4i: Be explicit about format modifiers
* drm/vc4: Use struct gpio_desc; Cleanups
* drm/vgem: Cleanups
* drm/vmwgfx: Use ttm_bo_move_null() if there's nothing to copy
* fbdev/mach64: Cleanups
* fbdev/mb862xx: Use DEVICE_ATTR_RO
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/YMBw3DF2b9udByfT@linux-uq9g
154 files changed, 3851 insertions, 1261 deletions
diff --git a/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml b/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml new file mode 100644 index 000000000000..d101233ae17f --- /dev/null +++ b/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml @@ -0,0 +1,159 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/bridge/ti,sn65dsi83.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: SN65DSI83 and SN65DSI84 DSI to LVDS bridge chip + +maintainers: + - Marek Vasut <marex@denx.de> + +description: | + Texas Instruments SN65DSI83 1x Single-link MIPI DSI + to 1x Single-link LVDS + https://www.ti.com/lit/gpn/sn65dsi83 + Texas Instruments SN65DSI84 1x Single-link MIPI DSI + to 1x Dual-link or 2x Single-link LVDS + https://www.ti.com/lit/gpn/sn65dsi84 + +properties: + compatible: + enum: + - ti,sn65dsi83 + - ti,sn65dsi84 + + reg: + enum: + - 0x2c + - 0x2d + + enable-gpios: + maxItems: 1 + description: GPIO specifier for bridge_en pin (active high). + + ports: + $ref: /schemas/graph.yaml#/properties/ports + + properties: + port@0: + $ref: /schemas/graph.yaml#/properties/port + description: Video port for MIPI DSI Channel-A input + + properties: + endpoint: + $ref: /schemas/media/video-interfaces.yaml# + unevaluatedProperties: false + + properties: + data-lanes: + description: array of physical DSI data lane indexes. + minItems: 1 + maxItems: 4 + items: + - const: 1 + - const: 2 + - const: 3 + - const: 4 + + port@1: + $ref: /schemas/graph.yaml#/properties/port + description: Video port for MIPI DSI Channel-B input + + properties: + endpoint: + $ref: /schemas/media/video-interfaces.yaml# + unevaluatedProperties: false + + properties: + data-lanes: + description: array of physical DSI data lane indexes. + minItems: 1 + maxItems: 4 + items: + - const: 1 + - const: 2 + - const: 3 + - const: 4 + + port@2: + $ref: /schemas/graph.yaml#/properties/port + description: Video port for LVDS Channel-A output (panel or bridge). + + port@3: + $ref: /schemas/graph.yaml#/properties/port + description: Video port for LVDS Channel-B output (panel or bridge). + + required: + - port@0 + - port@2 + +required: + - compatible + - reg + - enable-gpios + - ports + +allOf: + - if: + properties: + compatible: + contains: + const: ti,sn65dsi83 + then: + properties: + ports: + properties: + port@1: false + port@3: false + + - if: + properties: + compatible: + contains: + const: ti,sn65dsi84 + then: + properties: + ports: + properties: + port@1: false + +additionalProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + bridge@2d { + compatible = "ti,sn65dsi83"; + reg = <0x2d>; + + enable-gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + endpoint { + remote-endpoint = <&dsi0_out>; + data-lanes = <1 2 3 4>; + }; + }; + + port@2 { + reg = <2>; + + endpoint { + remote-endpoint = <&panel_in_lvds>; + }; + }; + }; + }; + }; diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst index 7f37ec30d9fd..7f21425d9435 100644 --- a/Documentation/driver-api/dma-buf.rst +++ b/Documentation/driver-api/dma-buf.rst @@ -178,6 +178,15 @@ DMA Fence Array .. kernel-doc:: include/linux/dma-fence-array.h :internal: +DMA Fence Chain +~~~~~~~~~~~~~~~ + +.. kernel-doc:: drivers/dma-buf/dma-fence-chain.c + :export: + +.. kernel-doc:: include/linux/dma-fence-chain.h + :internal: + DMA Fence uABI/Sync File ~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst index 21be6deadc12..d5a73fa2c9ef 100644 --- a/Documentation/gpu/drm-mm.rst +++ b/Documentation/gpu/drm-mm.rst @@ -469,8 +469,8 @@ DRM MM Range Allocator Function References .. kernel-doc:: drivers/gpu/drm/drm_mm.c :export: -DRM Cache Handling -================== +DRM Cache Handling and Fast WC memcpy() +======================================= .. kernel-doc:: drivers/gpu/drm/drm_cache.c :export: diff --git a/MAINTAINERS b/MAINTAINERS index 49091fbfa22b..bc336961ed52 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6084,6 +6084,14 @@ T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/hisilicon/ F: drivers/gpu/drm/hisilicon/ +DRM DRIVER FOR HYPERV SYNTHETIC VIDEO DEVICE +M: Deepak Rawat <drawat.floss@gmail.com> +L: linux-hyperv@vger.kernel.org +L: dri-devel@lists.freedesktop.org +S: Maintained +T: git git://anongit.freedesktop.org/drm/drm-misc +F: drivers/gpu/drm/hyperv + DRM DRIVERS FOR LIMA M: Qiang Yu <yuq825@gmail.com> L: dri-devel@lists.freedesktop.org diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index eadd1eaa2fb5..511fe0d217a0 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -234,7 +234,7 @@ retry: shared_count = fobj->shared_count; else shared_count = 0; - fence_excl = rcu_dereference(resv->fence_excl); + fence_excl = dma_resv_excl_fence(resv); if (read_seqcount_retry(&resv->seq, seq)) { rcu_read_unlock(); goto retry; @@ -1147,8 +1147,7 @@ static int __dma_buf_begin_cpu_access(struct dma_buf *dmabuf, long ret; /* Wait on any implicit rendering fences */ - ret = dma_resv_wait_timeout_rcu(resv, write, true, - MAX_SCHEDULE_TIMEOUT); + ret = dma_resv_wait_timeout(resv, write, true, MAX_SCHEDULE_TIMEOUT); if (ret < 0) return ret; @@ -1349,15 +1348,14 @@ EXPORT_SYMBOL_GPL(dma_buf_vunmap); #ifdef CONFIG_DEBUG_FS static int dma_buf_debug_show(struct seq_file *s, void *unused) { - int ret; struct dma_buf *buf_obj; struct dma_buf_attachment *attach_obj; struct dma_resv *robj; struct dma_resv_list *fobj; struct dma_fence *fence; - unsigned seq; int count = 0, attach_count, shared_count, i; size_t size = 0; + int ret; ret = mutex_lock_interruptible(&db_list.lock); @@ -1383,33 +1381,24 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) buf_obj->name ?: ""); robj = buf_obj->resv; - while (true) { - seq = read_seqcount_begin(&robj->seq); - rcu_read_lock(); - fobj = rcu_dereference(robj->fence); - shared_count = fobj ? fobj->shared_count : 0; - fence = rcu_dereference(robj->fence_excl); - if (!read_seqcount_retry(&robj->seq, seq)) - break; - rcu_read_unlock(); - } - + fence = dma_resv_excl_fence(robj); if (fence) seq_printf(s, "\tExclusive fence: %s %s %ssignalled\n", fence->ops->get_driver_name(fence), fence->ops->get_timeline_name(fence), dma_fence_is_signaled(fence) ? "" : "un"); + + fobj = rcu_dereference_protected(robj->fence, + dma_resv_held(robj)); + shared_count = fobj ? fobj->shared_count : 0; for (i = 0; i < shared_count; i++) { - fence = rcu_dereference(fobj->shared[i]); - if (!dma_fence_get_rcu(fence)) - continue; + fence = rcu_dereference_protected(fobj->shared[i], + dma_resv_held(robj)); seq_printf(s, "\tShared fence: %s %s %ssignalled\n", fence->ops->get_driver_name(fence), fence->ops->get_timeline_name(fence), dma_fence_is_signaled(fence) ? "" : "un"); - dma_fence_put(fence); } - rcu_read_unlock(); seq_puts(s, "\tAttached Devices:\n"); attach_count = 0; diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 6ddbeb5dfbf6..f26c71747d43 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: MIT /* * Copyright (C) 2012-2014 Canonical Ltd (Maarten Lankhorst) * @@ -92,49 +93,6 @@ static void dma_resv_list_free(struct dma_resv_list *list) kfree_rcu(list, rcu); } -#if IS_ENABLED(CONFIG_LOCKDEP) -static int __init dma_resv_lockdep(void) -{ - struct mm_struct *mm = mm_alloc(); - struct ww_acquire_ctx ctx; - struct dma_resv obj; - struct address_space mapping; - int ret; - - if (!mm) - return -ENOMEM; - - dma_resv_init(&obj); - address_space_init_once(&mapping); - - mmap_read_lock(mm); - ww_acquire_init(&ctx, &reservation_ww_class); - ret = dma_resv_lock(&obj, &ctx); - if (ret == -EDEADLK) - dma_resv_lock_slow(&obj, &ctx); - fs_reclaim_acquire(GFP_KERNEL); - /* for unmap_mapping_range on trylocked buffer objects in shrinkers */ - i_mmap_lock_write(&mapping); - i_mmap_unlock_write(&mapping); -#ifdef CONFIG_MMU_NOTIFIER - lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); - __dma_fence_might_wait(); - lock_map_release(&__mmu_notifier_invalidate_range_start_map); -#else - __dma_fence_might_wait(); -#endif - fs_reclaim_release(GFP_KERNEL); - ww_mutex_unlock(&obj.lock); - ww_acquire_fini(&ctx); - mmap_read_unlock(mm); - - mmput(mm); - - return 0; -} -subsys_initcall(dma_resv_lockdep); -#endif - /** * dma_resv_init - initialize a reservation object * @obj: the reservation object @@ -191,14 +149,11 @@ int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences) dma_resv_assert_held(obj); - old = dma_resv_get_list(obj); - + old = dma_resv_shared_list(obj); if (old && old->shared_max) { if ((old->shared_count + num_fences) <= old->shared_max) return 0; - else - max = max(old->shared_count + num_fences, - old->shared_max * 2); + max = max(old->shared_count + num_fences, old->shared_max * 2); } else { max = max(4ul, roundup_pow_of_two(num_fences)); } @@ -252,6 +207,28 @@ int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences) } EXPORT_SYMBOL(dma_resv_reserve_shared); +#ifdef CONFIG_DEBUG_MUTEXES +/** + * dma_resv_reset_shared_max - reset shared fences for debugging + * @obj: the dma_resv object to reset + * + * Reset the number of pre-reserved shared slots to test that drivers do + * correct slot allocation using dma_resv_reserve_shared(). See also + * &dma_resv_list.shared_max. + */ +void dma_resv_reset_shared_max(struct dma_resv *obj) +{ + struct dma_resv_list *fences = dma_resv_shared_list(obj); + + dma_resv_assert_held(obj); + + /* Test shared fence slot reservation */ + if (fences) + fences->shared_max = fences->shared_count; +} +EXPORT_SYMBOL(dma_resv_reset_shared_max); +#endif + /** * dma_resv_add_shared_fence - Add a fence to a shared slot * @obj: the reservation object @@ -270,7 +247,7 @@ void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence) dma_resv_assert_held(obj); - fobj = dma_resv_get_list(obj); + fobj = dma_resv_shared_list(obj); count = fobj->shared_count; write_seqcount_begin(&obj->seq); @@ -307,13 +284,13 @@ EXPORT_SYMBOL(dma_resv_add_shared_fence); */ void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence) { - struct dma_fence *old_fence = dma_resv_get_excl(obj); + struct dma_fence *old_fence = dma_resv_excl_fence(obj); struct dma_resv_list *old; u32 i = 0; dma_resv_assert_held(obj); - old = dma_resv_get_list(obj); + old = dma_resv_shared_list(obj); if (old) i = old->shared_count; @@ -337,26 +314,26 @@ void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence) EXPORT_SYMBOL(dma_resv_add_excl_fence); /** -* dma_resv_copy_fences - Copy all fences from src to dst. -* @dst: the destination reservation object -* @src: the source reservation object -* -* Copy all fences from src to dst. dst-lock must be held. -*/ + * dma_resv_copy_fences - Copy all fences from src to dst. + * @dst: the destination reservation object + * @src: the source reservation object + * + * Copy all fences from src to dst. dst-lock must be held. + */ int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src) { struct dma_resv_list *src_list, *dst_list; struct dma_fence *old, *new; - unsigned i; + unsigned int i; dma_resv_assert_held(dst); rcu_read_lock(); - src_list = rcu_dereference(src->fence); + src_list = dma_resv_shared_list(src); retry: if (src_list) { - unsigned shared_count = src_list->shared_count; + unsigned int shared_count = src_list->shared_count; rcu_read_unlock(); @@ -365,7 +342,7 @@ retry: return -ENOMEM; rcu_read_lock(); - src_list = rcu_dereference(src->fence); + src_list = dma_resv_shared_list(src); if (!src_list || src_list->shared_count > shared_count) { kfree(dst_list); goto retry; @@ -373,6 +350,7 @@ retry: dst_list->shared_count = 0; for (i = 0; i < src_list->shared_count; ++i) { + struct dma_fence __rcu **dst; struct dma_fence *fence; fence = rcu_dereference(src_list->shared[i]); @@ -382,7 +360,7 @@ retry: if (!dma_fence_get_rcu(fence)) { dma_resv_list_free(dst_list); - src_list = rcu_dereference(src->fence); + src_list = dma_resv_shared_list(src); goto retry; } @@ -391,7 +369,8 @@ retry: continue; } - rcu_assign_pointer(dst_list->shared[dst_list->shared_count++], fence); + dst = &dst_list->shared[dst_list->shared_count++]; + rcu_assign_pointer(*dst, fence); } } else { dst_list = NULL; @@ -400,8 +379,8 @@ retry: new = dma_fence_get_rcu_safe(&src->fence_excl); rcu_read_unlock(); - src_list = dma_resv_get_list(dst); - old = dma_resv_get_excl(dst); + src_list = dma_resv_shared_list(dst); + old = dma_resv_excl_fence(dst); write_seqcount_begin(&dst->seq); /* write_seqcount_begin provides the necessary memory barrier */ @@ -417,7 +396,7 @@ retry: EXPORT_SYMBOL(dma_resv_copy_fences); /** - * dma_resv_get_fences_rcu - Get an object's shared and exclusive + * dma_resv_get_fences - Get an object's shared and exclusive * fences without update side lock held * @obj: the reservation object * @pfence_excl: the returned exclusive fence (or NULL) @@ -429,10 +408,9 @@ EXPORT_SYMBOL(dma_resv_copy_fences); * exclusive fence is not specified the fence is put into the array of the * shared fences as well. Returns either zero or -ENOMEM. */ -int dma_resv_get_fences_rcu(struct dma_resv *obj, - struct dma_fence **pfence_excl, - unsigned *pshared_count, - struct dma_fence ***pshared) +int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **pfence_excl, + unsigned int *pshared_count, + struct dma_fence ***pshared) { struct dma_fence **shared = NULL; struct dma_fence *fence_excl; @@ -449,11 +427,11 @@ int dma_resv_get_fences_rcu(struct dma_resv *obj, rcu_read_lock(); seq = read_seqcount_begin(&obj->seq); - fence_excl = rcu_dereference(obj->fence_excl); + fence_excl = dma_resv_excl_fence(obj); if (fence_excl && !dma_fence_get_rcu(fence_excl)) goto unlock; - fobj = rcu_dereference(obj->fence); + fobj = dma_resv_shared_list(obj); if (fobj) sz += sizeof(*shared) * fobj->shared_max; @@ -515,27 +493,28 @@ unlock: *pshared = shared; return ret; } -EXPORT_SYMBOL_GPL(dma_resv_get_fences_rcu); +EXPORT_SYMBOL_GPL(dma_resv_get_fences); /** - * dma_resv_wait_timeout_rcu - Wait on reservation's objects + * dma_resv_wait_timeout - Wait on reservation's objects * shared and/or exclusive fences. * @obj: the reservation object * @wait_all: if true, wait on all fences, else wait on just exclusive fence * @intr: if true, do interruptible wait * @timeout: timeout value in jiffies or zero to return immediately * + * Callers are not required to hold specific locks, but maybe hold + * dma_resv_lock() already * RETURNS * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or * greater than zer on success. */ -long dma_resv_wait_timeout_rcu(struct dma_resv *obj, - bool wait_all, bool intr, - unsigned long timeout) +long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, + unsigned long timeout) { - struct dma_fence *fence; - unsigned seq, shared_count; long ret = timeout ? timeout : 1; + unsigned int seq, shared_count; + struct dma_fence *fence; int i; retry: @@ -544,7 +523,7 @@ retry: rcu_read_lock(); i = -1; - fence = rcu_dereference(obj->fence_excl); + fence = dma_resv_excl_fence(obj); if (fence && !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { if (!dma_fence_get_rcu(fence)) goto unlock_retry; @@ -559,14 +538,15 @@ retry: } if (wait_all) { - struct dma_resv_list *fobj = rcu_dereference(obj->fence); + struct dma_resv_list *fobj = dma_resv_shared_list(obj); if (fobj) shared_count = fobj->shared_count; for (i = 0; !fence && i < shared_count; ++i) { - struct dma_fence *lfence = rcu_dereference(fobj->shared[i]); + struct dma_fence *lfence; + lfence = rcu_dereference(fobj->shared[i]); if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &lfence->flags)) continue; @@ -602,7 +582,7 @@ unlock_retry: rcu_read_unlock(); goto retry; } -EXPORT_SYMBOL_GPL(dma_resv_wait_timeout_rcu); +EXPORT_SYMBOL_GPL(dma_resv_wait_timeout); static inline int dma_resv_test_signaled_single(struct dma_fence *passed_fence) @@ -622,18 +602,20 @@ static inline int dma_resv_test_signaled_single(struct dma_fence *passed_fence) } /** - * dma_resv_test_signaled_rcu - Test if a reservation object's - * fences have been signaled. + * dma_resv_test_signaled - Test if a reservation object's fences have been + * signaled. * @obj: the reservation object * @test_all: if true, test all fences, otherwise only test the exclusive * fence * + * Callers are not required to hold specific locks, but maybe hold + * dma_resv_lock() already * RETURNS * true if all fences signaled, else false */ -bool dma_resv_test_signaled_rcu(struct dma_resv *obj, bool test_all) +bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all) { - unsigned seq, shared_count; + unsigned int seq, shared_count; int ret; rcu_read_lock(); @@ -643,16 +625,16 @@ retry: seq = read_seqcount_begin(&obj->seq); if (test_all) { - unsigned i; - - struct dma_resv_list *fobj = rcu_dereference(obj->fence); + struct dma_resv_list *fobj = dma_resv_shared_list(obj); + unsigned int i; if (fobj) shared_count = fobj->shared_count; for (i = 0; i < shared_count; ++i) { - struct dma_fence *fence = rcu_dereference(fobj->shared[i]); + struct dma_fence *fence; + fence = rcu_dereference(fobj->shared[i]); ret = dma_resv_test_signaled_single(fence); if (ret < 0) goto retry; @@ -665,7 +647,7 @@ retry: } if (!shared_count) { - struct dma_fence *fence_excl = rcu_dereference(obj->fence_excl); + struct dma_fence *fence_excl = dma_resv_excl_fence(obj); if (fence_excl) { ret = dma_resv_test_signaled_single(fence_excl); @@ -680,4 +662,47 @@ retry: rcu_read_unlock(); return ret; } -EXPORT_SYMBOL_GPL(dma_resv_test_signaled_rcu); +EXPORT_SYMBOL_GPL(dma_resv_test_signaled); + +#if IS_ENABLED(CONFIG_LOCKDEP) +static int __init dma_resv_lockdep(void) +{ + struct mm_struct *mm = mm_alloc(); + struct ww_acquire_ctx ctx; + struct dma_resv obj; + struct address_space mapping; + int ret; + + if (!mm) + return -ENOMEM; + + dma_resv_init(&obj); + address_space_init_once(&mapping); + + mmap_read_lock(mm); + ww_acquire_init(&ctx, &reservation_ww_class); + ret = dma_resv_lock(&obj, &ctx); + if (ret == -EDEADLK) + dma_resv_lock_slow(&obj, &ctx); + fs_reclaim_acquire(GFP_KERNEL); + /* for unmap_mapping_range on trylocked buffer objects in shrinkers */ + i_mmap_lock_write(&mapping); + i_mmap_unlock_write(&mapping); +#ifdef CONFIG_MMU_NOTIFIER + lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); + __dma_fence_might_wait(); + lock_map_release(&__mmu_notifier_invalidate_range_start_map); +#else + __dma_fence_might_wait(); +#endif + fs_reclaim_release(GFP_KERNEL); + ww_mutex_unlock(&obj.lock); + ww_acquire_fini(&ctx); + mmap_read_unlock(mm); + + mmput(mm); + + return 0; +} +subsys_initcall(dma_resv_lockdep); +#endif diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 594ac6c3a1f4..7ff89690a976 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -98,8 +98,8 @@ config DRM_DEBUG_DP_MST_TOPOLOGY_REFS config DRM_FBDEV_EMULATION bool "Enable legacy fbdev support for your modesetting driver" depends on DRM + depends on FB select DRM_KMS_HELPER - select FB select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT @@ -379,6 +379,19 @@ source "drivers/gpu/drm/xlnx/Kconfig" source "drivers/gpu/drm/gud/Kconfig" +config DRM_HYPERV + tristate "DRM Support for Hyper-V synthetic video device" + depends on DRM && PCI && MMU && HYPERV + select DRM_KMS_HELPER + select DRM_GEM_SHMEM_HELPER + help + This is a KMS driver for Hyper-V synthetic video device. Choose this + option if you would like to enable drm driver for Hyper-V virtual + machine. Unselect Hyper-V framebuffer driver (CONFIG_FB_HYPERV) so + that DRM driver is used by default. + + If M is selected the module will be called hyperv_drm. + # Keep legacy drivers last menuconfig DRM_LEGACY diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index a91cc7684904..a118692a6df7 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -126,3 +126,4 @@ obj-$(CONFIG_DRM_MCDE) += mcde/ obj-$(CONFIG_DRM_TIDSS) += tidss/ obj-y += xlnx/ obj-y += gud/ +obj-$(CONFIG_DRM_HYPERV) += hyperv/ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 141cd297e948..668a28b80a62 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -247,7 +247,7 @@ static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo, if (!ef) return -EINVAL; - old = dma_resv_get_list(resv); + old = dma_resv_shared_list(resv); if (!old) return 0; @@ -1668,7 +1668,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( * the next restore worker */ if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm) && - bo->tbo.mem.mem_type == TTM_PL_SYSTEM) + bo->tbo.resource->mem_type == TTM_PL_SYSTEM) is_invalid_userptr = true; ret = vm_validate_pt_pd_bos(avm); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 0585442b000e..736b8c121979 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4127,9 +4127,9 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) list_for_each_entry(shadow, &adev->shadow_list, shadow_list) { /* No need to recover an evicted BO */ - if (shadow->tbo.mem.mem_type != TTM_PL_TT || - shadow->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET || - shadow->parent->tbo.mem.mem_type != TTM_PL_VRAM) + if (shadow->tbo.resource->mem_type != TTM_PL_TT || + shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET || + shadow->parent->tbo.resource->mem_type != TTM_PL_VRAM) continue; r = amdgpu_bo_restore_shadow(shadow, &next); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 49f73b5b89b0..ac7b37dfff5e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -203,9 +203,8 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc, goto unpin; } - r = dma_resv_get_fences_rcu(new_abo->tbo.base.resv, &work->excl, - &work->shared_count, - &work->shared); + r = dma_resv_get_fences(new_abo->tbo.base.resv, &work->excl, + &work->shared_count, &work->shared); if (unlikely(r != 0)) { DRM_ERROR("failed to get fences for buffer\n"); goto unpin; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 6ec1312b7389..c3053b83b80c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -49,10 +49,10 @@ __dma_resv_make_exclusive(struct dma_resv *obj) unsigned int count; int r; - if (!dma_resv_get_list(obj)) /* no shared fences to convert */ + if (!dma_resv_shared_list(obj)) /* no shared fences to convert */ return 0; - r = dma_resv_get_fences_rcu(obj, NULL, &count, &fences); + r = dma_resv_get_fences(obj, NULL, &count, &fences); if (r) return r; @@ -226,12 +226,12 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach, if (r) return ERR_PTR(r); - } else if (!(amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type) & + } else if (!(amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type) & AMDGPU_GEM_DOMAIN_GTT)) { return ERR_PTR(-EBUSY); } - switch (bo->tbo.mem.mem_type) { + switch (bo->tbo.resource->mem_type) { case TTM_PL_TT: sgt = drm_prime_pages_to_sg(obj->dev, bo->tbo.ttm->pages, @@ -245,8 +245,9 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach, break; case TTM_PL_VRAM: - r = amdgpu_vram_mgr_alloc_sgt(adev, &bo->tbo.mem, 0, - bo->tbo.base.size, attach->dev, dir, &sgt); + r = amdgpu_vram_mgr_alloc_sgt(adev, bo->tbo.resource, 0, + bo->tbo.base.size, attach->dev, + dir, &sgt); if (r) return ERR_PTR(r); break; @@ -436,7 +437,7 @@ amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach) struct amdgpu_vm_bo_base *bo_base; int r; - if (bo->tbo.mem.mem_type == TTM_PL_SYSTEM) + if (bo->tbo.resource->mem_type == TTM_PL_SYSTEM) return; r = ttm_bo_validate(&bo->tbo, &placement, &ctx); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 73c76a3e2b12..1c3e3b608332 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -226,7 +226,7 @@ static void amdgpu_gem_object_close(struct drm_gem_object *obj, if (!amdgpu_vm_ready(vm)) goto out_unlock; - fence = dma_resv_get_excl(bo->tbo.base.resv); + fence = dma_resv_excl_fence(bo->tbo.base.resv); if (fence) { amdgpu_bo_fence(bo, fence, true); fence = NULL; @@ -526,8 +526,7 @@ int amdgpu_gem_wait_idle_ioctl(struct drm_device *dev, void *data, return -ENOENT; } robj = gem_to_amdgpu_bo(gobj); - ret = dma_resv_wait_timeout_rcu(robj->tbo.base.resv, true, true, - timeout); + ret = dma_resv_wait_timeout(robj->tbo.base.resv, true, true, timeout); /* ret == 0 means not signaled, * ret > 0 means signaled diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 7061c4a0e421..85b8bfb8857b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -101,7 +101,7 @@ void amdgpu_gmc_get_pde_for_bo(struct amdgpu_bo *bo, int level, { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); - switch (bo->tbo.mem.mem_type) { + switch (bo->tbo.resource->mem_type) { case TTM_PL_TT: *addr = bo->tbo.ttm->dma_address[0]; break; @@ -112,7 +112,7 @@ void amdgpu_gmc_get_pde_for_bo(struct amdgpu_bo *bo, int level, *addr = 0; break; } - *flags = amdgpu_ttm_tt_pde_flags(bo->tbo.ttm, &bo->tbo.mem); + *flags = amdgpu_ttm_tt_pde_flags(bo->tbo.ttm, bo->tbo.resource); amdgpu_gmc_get_vm_pde(adev, level, addr, flags); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c index 9ab33048923e..ec96e0b26b11 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -22,18 +22,26 @@ * Authors: Christian König */ +#include <drm/ttm/ttm_range_manager.h> + #include "amdgpu.h" +struct amdgpu_gtt_node { + struct ttm_buffer_object *tbo; + struct ttm_range_mgr_node base; +}; + static inline struct amdgpu_gtt_mgr * to_gtt_mgr(struct ttm_resource_manager *man) { return container_of(man, struct amdgpu_gtt_mgr, manager); } -struct amdgpu_gtt_node { - struct drm_mm_node node; - struct ttm_buffer_object *tbo; -}; +static inline struct amdgpu_gtt_node * +to_amdgpu_gtt_node(struct ttm_resource *res) +{ + return container_of(res, struct amdgpu_gtt_node, base.base); +} /** * DOC: mem_info_gtt_total @@ -93,13 +101,15 @@ const struct attribute_group amdgpu_gtt_mgr_attr_group = { /** * amdgpu_gtt_mgr_has_gart_addr - Check if mem has address space * - * @mem: the mem object to check + * @res: the mem object to check * * Check if a mem object has already address space allocated. */ -bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *mem) +bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *res) { - return mem->mm_node != NULL; + struct amdgpu_gtt_node *node = to_amdgpu_gtt_node(res); + + return drm_mm_node_allocated(&node->base.mm_nodes[0]); } /** @@ -115,54 +125,57 @@ bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *mem) static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man, struct ttm_buffer_object *tbo, const struct ttm_place *place, - struct ttm_resource *mem) + struct ttm_resource **res) { struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man); + uint32_t num_pages = PFN_UP(tbo->base.size); struct amdgpu_gtt_node *node; int r; spin_lock(&mgr->lock); - if ((&tbo->mem == mem || tbo->mem.mem_type != TTM_PL_TT) && - atomic64_read(&mgr->available) < mem->num_pages) { + if (tbo->resource && tbo->resource->mem_type != TTM_PL_TT && + atomic64_read(&mgr->available) < num_pages) { spin_unlock(&mgr->lock); return -ENOSPC; } - atomic64_sub(mem->num_pages, &mgr->available); + atomic64_sub(num_pages, &mgr->available); spin_unlock(&mgr->lock); - if (!place->lpfn) { - mem->mm_node = NULL; - mem->start = AMDGPU_BO_INVALID_OFFSET; - return 0; - } - - node = kzalloc(sizeof(*node), GFP_KERNEL); + node = kzalloc(struct_size(node, base.mm_nodes, 1), GFP_KERNEL); if (!node) { r = -ENOMEM; goto err_out; } node->tbo = tbo; + ttm_resource_init(tbo, place, &node->base.base); - spin_lock(&mgr->lock); - r = drm_mm_insert_node_in_range(&mgr->mm, &node->node, mem->num_pages, - tbo->page_alignment, 0, place->fpfn, - place->lpfn, DRM_MM_INSERT_BEST); - spin_unlock(&mgr->lock); - - if (unlikely(r)) - goto err_free; - - mem->mm_node = node; - mem->start = node->node.start; + if (place->lpfn) { + spin_lock(&mgr->lock); + r = drm_mm_insert_node_in_range(&mgr->mm, + &node->base.mm_nodes[0], + num_pages, tbo->page_alignment, + 0, place->fpfn, place->lpfn, + DRM_MM_INSERT_BEST); + spin_unlock(&mgr->lock); + if (unlikely(r)) + goto err_free; + + node->base.base.start = node->base.mm_nodes[0].start; + } else { + node->base.mm_nodes[0].start = 0; + node->base.mm_nodes[0].size = node->base.base.num_pages; + node->base.base.start = AMDGPU_BO_INVALID_OFFSET; + } + *res = &node->base.base; return 0; err_free: kfree(node); err_out: - atomic64_add(mem->num_pages, &mgr->available); + atomic64_add(num_pages, &mgr->available); return r; } @@ -176,19 +189,18 @@ err_out: * Free the allocated GTT again. */ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man, - struct ttm_resource *mem) + struct ttm_resource *res) { + struct amdgpu_gtt_node *node = to_amdgpu_gtt_node(res); struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man); - struct amdgpu_gtt_node *node = mem->mm_node; - if (node) { - spin_lock(&mgr->lock); - drm_mm_remove_node(&node->node); - spin_unlock(&mgr->lock); - kfree(node); - } + spin_lock(&mgr->lock); + if (drm_mm_node_allocated(&node->base.mm_nodes[0])) + drm_mm_remove_node(&node->base.mm_nodes[0]); + spin_unlock(&mgr->lock); + atomic64_add(res->num_pages, &mgr->available); - atomic64_add(mem->num_pages, &mgr->available); + kfree(node); } /** @@ -224,7 +236,7 @@ int amdgpu_gtt_mgr_recover(struct ttm_resource_manager *man) adev = container_of(mgr, typeof(*adev), mman.gtt_mgr); spin_lock(&mgr->lock); drm_mm_for_each_node(mm_node, &mgr->mm) { - node = container_of(mm_node, struct amdgpu_gtt_node, node); + node = container_of(mm_node, typeof(*node), base.mm_nodes[0]); r = amdgpu_ttm_recover_gart(node->tbo); if (r) break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index c7f3aae23c62..b7fb72bff2c1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -112,7 +112,7 @@ void amdgpu_pasid_free_delayed(struct dma_resv *resv, unsigned count; int r; - r = dma_resv_get_fences_rcu(resv, NULL, &count, &fences); + r = dma_resv_get_fences(resv, NULL, &count, &fences); if (r) goto fallback; @@ -156,8 +156,7 @@ fallback: /* Not enough memory for the delayed delete, as last resort * block for all the fences to complete. */ - dma_resv_wait_timeout_rcu(resv, true, false, - MAX_SCHEDULE_TIMEOUT); + dma_resv_wait_timeout(resv, true, false, MAX_SCHEDULE_TIMEOUT); amdgpu_pasid_free(pasid); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index 2741c28ff1b5..d6c54c7f7679 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -75,8 +75,8 @@ static bool amdgpu_mn_invalidate_gfx(struct mmu_interval_notifier *mni, mmu_interval_set_seq(mni, cur_seq); - r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv, true, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(bo->tbo.base.resv, true, false, + MAX_SCHEDULE_TIMEOUT); mutex_unlock(&adev->notifier_lock); if (r <= 0) DRM_ERROR("(%ld) failed to wait for user bo\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index a6fa3968463a..c83f116edde2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -364,14 +364,14 @@ int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev, if (cpu_addr) amdgpu_bo_kunmap(*bo_ptr); - ttm_resource_free(&(*bo_ptr)->tbo, &(*bo_ptr)->tbo.mem); + ttm_resource_free(&(*bo_ptr)->tbo, &(*bo_ptr)->tbo.resource); for (i = 0; i < (*bo_ptr)->placement.num_placement; ++i) { (*bo_ptr)->placements[i].fpfn = offset >> PAGE_SHIFT; (*bo_ptr)->placements[i].lpfn = (offset + size) >> PAGE_SHIFT; } r = ttm_bo_mem_space(&(*bo_ptr)->tbo, &(*bo_ptr)->placement, - &(*bo_ptr)->tbo.mem, &ctx); + &(*bo_ptr)->tbo.resource, &ctx); if (r) goto error; @@ -575,15 +575,15 @@ int amdgpu_bo_create(struct amdgpu_device *adev, return r; if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && - bo->tbo.mem.mem_type == TTM_PL_VRAM && - bo->tbo.mem.start < adev->gmc.visible_vram_size >> PAGE_SHIFT) + bo->tbo.resource->mem_type == TTM_PL_VRAM && + bo->tbo.resource->start < adev->gmc.visible_vram_size >> PAGE_SHIFT) amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, ctx.bytes_moved); else amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, 0); if (bp->flags & AMDGPU_GEM_CREATE_VRAM_CLEARED && - bo->tbo.mem.mem_type == TTM_PL_VRAM) { + bo->tbo.resource->mem_type == TTM_PL_VRAM) { struct dma_fence *fence; r = amdgpu_fill_buffer(bo, 0, bo->tbo.base.resv, &fence); @@ -777,12 +777,12 @@ int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr) return 0; } - r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv, false, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(bo->tbo.base.resv, false, false, + MAX_SCHEDULE_TIMEOUT); if (r < 0) return r; - r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.mem.num_pages, &bo->kmap); + r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.resource->num_pages, &bo->kmap); if (r) return r; @@ -905,8 +905,8 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, domain = amdgpu_bo_get_preferred_pin_domain(adev, domain); if (bo->tbo.pin_count) { - uint32_t mem_type = bo->tbo.mem.mem_type; - uint32_t mem_flags = bo->tbo.mem.placement; + uint32_t mem_type = bo->tbo.resource->mem_type; + uint32_t mem_flags = bo->tbo.resource->placement; if (!(domain & amdgpu_mem_type_to_domain(mem_type))) return -EINVAL; @@ -956,7 +956,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, ttm_bo_pin(&bo->tbo); - domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type); + domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); if (domain == AMDGPU_GEM_DOMAIN_VRAM) { atomic64_add(amdgpu_bo_size(bo), &adev->vram_pin_size); atomic64_add(amdgpu_vram_mgr_bo_visible_size(bo), @@ -1008,11 +1008,11 @@ void amdgpu_bo_unpin(struct amdgpu_bo *bo) if (bo->tbo.base.import_attach) dma_buf_unpin(bo->tbo.base.import_attach); - if (bo->tbo.mem.mem_type == TTM_PL_VRAM) { + if (bo->tbo.resource->mem_type == TTM_PL_VRAM) { atomic64_sub(amdgpu_bo_size(bo), &adev->vram_pin_size); atomic64_sub(amdgpu_vram_mgr_bo_visible_size(bo), &adev->visible_pin_size); - } else if (bo->tbo.mem.mem_type == TTM_PL_TT) { + } else if (bo->tbo.resource->mem_type == TTM_PL_TT) { atomic64_sub(amdgpu_bo_size(bo), &adev->gart_pin_size); } } @@ -1245,7 +1245,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct amdgpu_bo *abo; - struct ttm_resource *old_mem = &bo->mem; + struct ttm_resource *old_mem = bo->resource; if (!amdgpu_bo_is_amdgpu_bo(bo)) return; @@ -1256,7 +1256,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, amdgpu_bo_kunmap(abo); if (abo->tbo.base.dma_buf && !abo->tbo.base.import_attach && - bo->mem.mem_type != TTM_PL_SYSTEM) + bo->resource->mem_type != TTM_PL_SYSTEM) dma_buf_move_notify(abo->tbo.base.dma_buf); /* remember the eviction */ @@ -1276,7 +1276,7 @@ void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem, { unsigned int domain; - domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type); + domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); switch (domain) { case AMDGPU_GEM_DOMAIN_VRAM: *vram_mem += amdgpu_bo_size(bo); @@ -1318,7 +1318,7 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) if (bo->base.resv == &bo->base._resv) amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo); - if (bo->mem.mem_type != TTM_PL_VRAM || !bo->mem.mm_node || + if (bo->resource->mem_type != TTM_PL_VRAM || !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) return; @@ -1355,10 +1355,10 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) /* Remember that this BO was accessed by the CPU */ abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - if (bo->mem.mem_type != TTM_PL_VRAM) + if (bo->resource->mem_type != TTM_PL_VRAM) return 0; - offset = bo->mem.start << PAGE_SHIFT; + offset = bo->resource->start << PAGE_SHIFT; if ((offset + bo->base.size) <= adev->gmc.visible_vram_size) return 0; @@ -1381,9 +1381,9 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) else if (unlikely(r)) return VM_FAULT_SIGBUS; - offset = bo->mem.start << PAGE_SHIFT; + offset = bo->resource->start << PAGE_SHIFT; /* this should never happen */ - if (bo->mem.mem_type == TTM_PL_VRAM && + if (bo->resource->mem_type == TTM_PL_VRAM && (offset + bo->base.size) > adev->gmc.visible_vram_size) return VM_FAULT_SIGBUS; @@ -1468,11 +1468,11 @@ int amdgpu_bo_sync_wait(struct amdgpu_bo *bo, void *owner, bool intr) */ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo) { - WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_SYSTEM); + WARN_ON_ONCE(bo->tbo.resource->mem_type == TTM_PL_SYSTEM); WARN_ON_ONCE(!dma_resv_is_locked(bo->tbo.base.resv) && !bo->tbo.pin_count && bo->tbo.type != ttm_bo_type_kernel); - WARN_ON_ONCE(bo->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET); - WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_VRAM && + WARN_ON_ONCE(bo->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET); + WARN_ON_ONCE(bo->tbo.resource->mem_type == TTM_PL_VRAM && !(bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)); return amdgpu_bo_gpu_offset_no_check(bo); @@ -1490,8 +1490,8 @@ u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo) struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); uint64_t offset; - offset = (bo->tbo.mem.start << PAGE_SHIFT) + - amdgpu_ttm_domain_start(adev, bo->tbo.mem.mem_type); + offset = (bo->tbo.resource->start << PAGE_SHIFT) + + amdgpu_ttm_domain_start(adev, bo->tbo.resource->mem_type); return amdgpu_gmc_sign_extend(offset); } @@ -1544,7 +1544,7 @@ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) unsigned int pin_count; u64 size; - domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type); + domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); switch (domain) { case AMDGPU_GEM_DOMAIN_VRAM: placement = "VRAM"; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 90eab1c31027..126df03a7066 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -223,10 +223,10 @@ static inline bool amdgpu_bo_in_cpu_visible_vram(struct amdgpu_bo *bo) struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct amdgpu_res_cursor cursor; - if (bo->tbo.mem.mem_type != TTM_PL_VRAM) + if (bo->tbo.resource->mem_type != TTM_PL_VRAM) return false; - amdgpu_res_first(&bo->tbo.mem, 0, amdgpu_bo_size(bo), &cursor); + amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &cursor); while (cursor.remaining) { if (cursor.start < adev->gmc.visible_vram_size) return true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_preempt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_preempt_mgr.c index d607f314cc1b..f6aff7ce5160 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_preempt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_preempt_mgr.c @@ -66,14 +66,18 @@ static DEVICE_ATTR_RO(mem_info_preempt_used); static int amdgpu_preempt_mgr_new(struct ttm_resource_manager *man, struct ttm_buffer_object *tbo, const struct ttm_place *place, - struct ttm_resource *mem) + struct ttm_resource **res) { struct amdgpu_preempt_mgr *mgr = to_preempt_mgr(man); - atomic64_add(mem->num_pages, &mgr->used); + *res = kzalloc(sizeof(**res), GFP_KERNEL); + if (*res) + return -ENOMEM; - mem->mm_node = NULL; - mem->start = AMDGPU_BO_INVALID_OFFSET; + ttm_resource_init(tbo, place, *res); + (*res)->start = AMDGPU_BO_INVALID_OFFSET; + + atomic64_add((*res)->num_pages, &mgr->used); return 0; } @@ -86,11 +90,12 @@ static int amdgpu_preempt_mgr_new(struct ttm_resource_manager *man, * Free the allocated GTT again. */ static void amdgpu_preempt_mgr_del(struct ttm_resource_manager *man, - struct ttm_resource *mem) + struct ttm_resource *res) { struct amdgpu_preempt_mgr *mgr = to_preempt_mgr(man); - atomic64_sub(mem->num_pages, &mgr->used); + atomic64_sub(res->num_pages, &mgr->used); + kfree(res); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h index 40f2adf305bc..59e0fefb15aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h @@ -28,6 +28,7 @@ #include <drm/drm_mm.h> #include <drm/ttm/ttm_resource.h> +#include <drm/ttm/ttm_range_manager.h> /* state back for walking over vram_mgr and gtt_mgr allocations */ struct amdgpu_res_cursor { @@ -53,7 +54,7 @@ static inline void amdgpu_res_first(struct ttm_resource *res, { struct drm_mm_node *node; - if (!res || !res->mm_node) { + if (!res) { cur->start = start; cur->size = size; cur->remaining = size; @@ -63,7 +64,7 @@ static inline void amdgpu_res_first(struct ttm_resource *res, BUG_ON(start + size > res->num_pages << PAGE_SHIFT); - node = res->mm_node; + node = to_ttm_range_mgr_node(res)->mm_nodes; while (start >= node->size << PAGE_SHIFT) start -= node++->size << PAGE_SHIFT; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index 4e558632a5d2..1b2ceccaf5b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -210,10 +210,10 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync, return -EINVAL; /* always sync to the exclusive fence */ - f = dma_resv_get_excl(resv); + f = dma_resv_excl_fence(resv); r = amdgpu_sync_fence(sync, f); - flist = dma_resv_get_list(resv); + flist = dma_resv_shared_list(resv); if (!flist || r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h index 792d20261846..0527772fe1b8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h @@ -127,8 +127,8 @@ TRACE_EVENT(amdgpu_bo_create, TP_fast_assign( __entry->bo = bo; - __entry->pages = bo->tbo.mem.num_pages; - __entry->type = bo->tbo.mem.mem_type; + __entry->pages = bo->tbo.resource->num_pages; + __entry->type = bo->tbo.resource->mem_type; __entry->prefer = bo->preferred_domains; __entry->allow = bo->allowed_domains; __entry->visible = bo->flags; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 832970cff64c..5d0c57b9917f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -45,6 +45,7 @@ #include <drm/ttm/ttm_bo_api.h> #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> +#include <drm/ttm/ttm_range_manager.h> #include <drm/amdgpu_drm.h> @@ -125,7 +126,8 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo, rcu_read_unlock(); return; } - switch (bo->mem.mem_type) { + + switch (bo->resource->mem_type) { case AMDGPU_PL_GDS: case AMDGPU_PL_GWS: case AMDGPU_PL_OA: @@ -460,7 +462,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, { struct amdgpu_device *adev; struct amdgpu_bo *abo; - struct ttm_resource *old_mem = &bo->mem; + struct ttm_resource *old_mem = bo->resource; int r; if (new_mem->mem_type == TTM_PL_TT || @@ -495,7 +497,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, return r; amdgpu_ttm_backend_unbind(bo->bdev, bo->ttm); - ttm_resource_free(bo, &bo->mem); + ttm_resource_free(bo, &bo->resource); ttm_bo_assign_mem(bo, new_mem); goto out; } @@ -605,7 +607,8 @@ static unsigned long amdgpu_ttm_io_mem_pfn(struct ttm_buffer_object *bo, struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct amdgpu_res_cursor cursor; - amdgpu_res_first(&bo->mem, (u64)page_offset << PAGE_SHIFT, 0, &cursor); + amdgpu_res_first(bo->resource, (u64)page_offset << PAGE_SHIFT, 0, + &cursor); return (adev->gmc.aper_base + cursor.start) >> PAGE_SHIFT; } @@ -954,50 +957,50 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo) struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct ttm_operation_ctx ctx = { false, false }; struct amdgpu_ttm_tt *gtt = (void *)bo->ttm; - struct ttm_resource tmp; struct ttm_placement placement; struct ttm_place placements; + struct ttm_resource *tmp; uint64_t addr, flags; int r; - if (bo->mem.start != AMDGPU_BO_INVALID_OFFSET) + if (bo->resource->start != AMDGPU_BO_INVALID_OFFSET) return 0; addr = amdgpu_gmc_agp_addr(bo); if (addr != AMDGPU_BO_INVALID_OFFSET) { - bo->mem.start = addr >> PAGE_SHIFT; - } else { + bo->resource->start = addr >> PAGE_SHIFT; + return 0; + } - /* allocate GART space */ - placement.num_placement = 1; - placement.placement = &placements; - placement.num_busy_placement = 1; - placement.busy_placement = &placements; - placements.fpfn = 0; - placements.lpfn = adev->gmc.gart_size >> PAGE_SHIFT; - placements.mem_type = TTM_PL_TT; - placements.flags = bo->mem.placement; - - r = ttm_bo_mem_space(bo, &placement, &tmp, &ctx); - if (unlikely(r)) - return r; + /* allocate GART space */ + placement.num_placement = 1; + placement.placement = &placements; + placement.num_busy_placement = 1; + placement.busy_placement = &placements; + placements.fpfn = 0; + placements.lpfn = adev->gmc.gart_size >> PAGE_SHIFT; + placements.mem_type = TTM_PL_TT; + placements.flags = bo->resource->placement; - /* compute PTE flags for this buffer object */ - flags = amdgpu_ttm_tt_pte_flags(adev, bo->ttm, &tmp); + r = ttm_bo_mem_space(bo, &placement, &tmp, &ctx); + if (unlikely(r)) + return r; - /* Bind pages */ - gtt->offset = (u64)tmp.start << PAGE_SHIFT; - r = amdgpu_ttm_gart_bind(adev, bo, flags); - if (unlikely(r)) { - ttm_resource_free(bo, &tmp); - return r; - } + /* compute PTE flags for this buffer object */ + flags = amdgpu_ttm_tt_pte_flags(adev, bo->ttm, tmp); - amdgpu_gart_invalidate_tlb(adev); - ttm_resource_free(bo, &bo->mem); - bo->mem = tmp; + /* Bind pages */ + gtt->offset = (u64)tmp->start << PAGE_SHIFT; + r = amdgpu_ttm_gart_bind(adev, bo, flags); + if (unlikely(r)) { + ttm_resource_free(bo, &tmp); + return r; } + amdgpu_gart_invalidate_tlb(adev); + ttm_resource_free(bo, &bo->resource); + ttm_bo_assign_mem(bo, tmp); + return 0; } @@ -1016,7 +1019,7 @@ int amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo) if (!tbo->ttm) return 0; - flags = amdgpu_ttm_tt_pte_flags(adev, tbo->ttm, &tbo->mem); + flags = amdgpu_ttm_tt_pte_flags(adev, tbo->ttm, tbo->resource); r = amdgpu_ttm_gart_bind(adev, tbo, flags); return r; @@ -1330,12 +1333,16 @@ uint64_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm, static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, const struct ttm_place *place) { - unsigned long num_pages = bo->mem.num_pages; + unsigned long num_pages = bo->resource->num_pages; struct amdgpu_res_cursor cursor; struct dma_resv_list *flist; struct dma_fence *f; int i; + /* Swapout? */ + if (bo->resource->mem_type == TTM_PL_SYSTEM) + return true; + if (bo->type == ttm_bo_type_kernel && !amdgpu_vm_evictable(ttm_to_amdgpu_bo(bo))) return false; @@ -1344,7 +1351,7 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, * If true, then return false as any KFD process needs all its BOs to * be resident to run successfully */ - flist = dma_resv_get_list(bo->base.resv); + flist = dma_resv_shared_list(bo->base.resv); if (flist) { for (i = 0; i < flist->shared_count; ++i) { f = rcu_dereference_protected(flist->shared[i], @@ -1354,7 +1361,7 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, } } - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case AMDGPU_PL_PREEMPT: /* Preemptible BOs don't own system resources managed by the * driver (pages, VRAM, GART space). They point to resources @@ -1372,7 +1379,7 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, case TTM_PL_VRAM: /* Check each drm MM node individually */ - amdgpu_res_first(&bo->mem, 0, (u64)num_pages << PAGE_SHIFT, + amdgpu_res_first(bo->resource, 0, (u64)num_pages << PAGE_SHIFT, &cursor); while (cursor.remaining) { if (place->fpfn < PFN_DOWN(cursor.start + cursor.size) @@ -1414,10 +1421,10 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo, uint32_t value = 0; int ret = 0; - if (bo->mem.mem_type != TTM_PL_VRAM) + if (bo->resource->mem_type != TTM_PL_VRAM) return -EIO; - amdgpu_res_first(&bo->mem, offset, len, &cursor); + amdgpu_res_first(bo->resource, offset, len, &cursor); while (cursor.remaining) { uint64_t aligned_pos = cursor.start & ~(uint64_t)3; uint64_t bytes = 4 - (cursor.start & 3); @@ -1942,21 +1949,21 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo, return -EINVAL; } - if (bo->tbo.mem.mem_type == AMDGPU_PL_PREEMPT) { + if (bo->tbo.resource->mem_type == AMDGPU_PL_PREEMPT) { DRM_ERROR("Trying to clear preemptible memory.\n"); return -EINVAL; } - if (bo->tbo.mem.mem_type == TTM_PL_TT) { + if (bo->tbo.resource->mem_type == TTM_PL_TT) { r = amdgpu_ttm_alloc_gart(&bo->tbo); if (r) return r; } - num_bytes = bo->tbo.mem.num_pages << PAGE_SHIFT; + num_bytes = bo->tbo.resource->num_pages << PAGE_SHIFT; num_loops = 0; - amdgpu_res_first(&bo->tbo.mem, 0, num_bytes, &cursor); + amdgpu_res_first(bo->tbo.resource, 0, num_bytes, &cursor); while (cursor.remaining) { num_loops += DIV_ROUND_UP_ULL(cursor.size, max_bytes); amdgpu_res_next(&cursor, cursor.size); @@ -1981,12 +1988,13 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo, } } - amdgpu_res_first(&bo->tbo.mem, 0, num_bytes, &cursor); + amdgpu_res_first(bo->tbo.resource, 0, num_bytes, &cursor); while (cursor.remaining) { uint32_t cur_size = min_t(uint64_t, cursor.size, max_bytes); uint64_t dst_addr = cursor.start; - dst_addr += amdgpu_ttm_domain_start(adev, bo->tbo.mem.mem_type); + dst_addr += amdgpu_ttm_domain_start(adev, + bo->tbo.resource->mem_type); amdgpu_emit_fill_buffer(adev, &job->ibs[0], src_data, dst_addr, cur_size); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index ce8f80a959c6..0f576f294d8a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -1125,9 +1125,8 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo, ib->length_dw = 16; if (direct) { - r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv, - true, false, - msecs_to_jiffies(10)); + r = dma_resv_wait_timeout(bo->tbo.base.resv, true, false, + msecs_to_jiffies(10)); if (r == 0) r = -ETIMEDOUT; if (r < 0) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 8d218c5cfee8..777e8922ecf3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -342,7 +342,7 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base, amdgpu_vm_bo_idle(base); if (bo->preferred_domains & - amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type)) + amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type)) return; /* @@ -658,10 +658,11 @@ void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev, if (!bo->parent) continue; - ttm_bo_move_to_lru_tail(&bo->tbo, &bo->tbo.mem, + ttm_bo_move_to_lru_tail(&bo->tbo, bo->tbo.resource, &vm->lru_bulk_move); if (shadow) - ttm_bo_move_to_lru_tail(&shadow->tbo, &shadow->tbo.mem, + ttm_bo_move_to_lru_tail(&shadow->tbo, + shadow->tbo.resource, &vm->lru_bulk_move); } spin_unlock(&adev->mman.bdev.lru_lock); @@ -1858,10 +1859,10 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, struct drm_gem_object *gobj = dma_buf->priv; struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj); - if (abo->tbo.mem.mem_type == TTM_PL_VRAM) + if (abo->tbo.resource->mem_type == TTM_PL_VRAM) bo = gem_to_amdgpu_bo(gobj); } - mem = &bo->tbo.mem; + mem = bo->tbo.resource; if (mem->mem_type == TTM_PL_TT || mem->mem_type == AMDGPU_PL_PREEMPT) pages_addr = bo->tbo.ttm->dma_address; @@ -1922,7 +1923,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, * next command submission. */ if (bo && bo->tbo.base.resv == vm->root.base.bo->tbo.base.resv) { - uint32_t mem_type = bo->tbo.mem.mem_type; + uint32_t mem_type = bo->tbo.resource->mem_type; if (!(bo->preferred_domains & amdgpu_mem_type_to_domain(mem_type))) @@ -2063,13 +2064,12 @@ static void amdgpu_vm_prt_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) unsigned i, shared_count; int r; - r = dma_resv_get_fences_rcu(resv, &excl, - &shared_count, &shared); + r = dma_resv_get_fences(resv, &excl, &shared_count, &shared); if (r) { /* Not enough memory to grab the fence list, as last resort * block for all the fences to complete. */ - dma_resv_wait_timeout_rcu(resv, true, false, + dma_resv_wait_timeout(resv, true, false, MAX_SCHEDULE_TIMEOUT); return; } @@ -2681,7 +2681,7 @@ bool amdgpu_vm_evictable(struct amdgpu_bo *bo) return true; /* Don't evict VM page tables while they are busy */ - if (!dma_resv_test_signaled_rcu(bo->tbo.base.resv, true)) + if (!dma_resv_test_signaled(bo->tbo.base.resv, true)) return false; /* Try to block ongoing updates */ @@ -2861,8 +2861,8 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size, */ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout) { - timeout = dma_resv_wait_timeout_rcu(vm->root.base.bo->tbo.base.resv, - true, true, timeout); + timeout = dma_resv_wait_timeout(vm->root.base.bo->tbo.base.resv, true, + true, timeout); if (timeout <= 0) return timeout; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 07e007dbff7c..9a6df02477ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -23,6 +23,8 @@ */ #include <linux/dma-mapping.h> +#include <drm/ttm/ttm_range_manager.h> + #include "amdgpu.h" #include "amdgpu_vm.h" #include "amdgpu_res_cursor.h" @@ -217,19 +219,20 @@ static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev, u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); - struct ttm_resource *mem = &bo->tbo.mem; - struct drm_mm_node *nodes = mem->mm_node; - unsigned pages = mem->num_pages; + struct ttm_resource *res = bo->tbo.resource; + unsigned pages = res->num_pages; + struct drm_mm_node *mm; u64 usage; if (amdgpu_gmc_vram_full_visible(&adev->gmc)) return amdgpu_bo_size(bo); - if (mem->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT) + if (res->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT) return 0; - for (usage = 0; nodes && pages; pages -= nodes->size, nodes++) - usage += amdgpu_vram_mgr_vis_size(adev, nodes); + mm = &container_of(res, struct ttm_range_mgr_node, base)->mm_nodes[0]; + for (usage = 0; pages; pages -= mm->size, mm++) + usage += amdgpu_vram_mgr_vis_size(adev, mm); return usage; } @@ -365,15 +368,15 @@ static void amdgpu_vram_mgr_virt_start(struct ttm_resource *mem, static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, struct ttm_buffer_object *tbo, const struct ttm_place *place, - struct ttm_resource *mem) + struct ttm_resource **res) { unsigned long lpfn, num_nodes, pages_per_node, pages_left, pages; struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); struct amdgpu_device *adev = to_amdgpu_device(mgr); uint64_t vis_usage = 0, mem_bytes, max_bytes; + struct ttm_range_mgr_node *node; struct drm_mm *mm = &mgr->mm; enum drm_mm_insert_mode mode; - struct drm_mm_node *nodes; unsigned i; int r; @@ -386,10 +389,10 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, max_bytes -= AMDGPU_VM_RESERVED_VRAM; /* bail out quickly if there's likely not enough VRAM for this BO */ - mem_bytes = (u64)mem->num_pages << PAGE_SHIFT; + mem_bytes = tbo->base.size; if (atomic64_add_return(mem_bytes, &mgr->usage) > max_bytes) { - atomic64_sub(mem_bytes, &mgr->usage); - return -ENOSPC; + r = -ENOSPC; + goto error_sub; } if (place->flags & TTM_PL_FLAG_CONTIGUOUS) { @@ -404,22 +407,23 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, #endif pages_per_node = max_t(uint32_t, pages_per_node, tbo->page_alignment); - num_nodes = DIV_ROUND_UP(mem->num_pages, pages_per_node); + num_nodes = DIV_ROUND_UP(PFN_UP(mem_bytes), pages_per_node); } - nodes = kvmalloc_array((uint32_t)num_nodes, sizeof(*nodes), - GFP_KERNEL | __GFP_ZERO); - if (!nodes) { - atomic64_sub(mem_bytes, &mgr->usage); - return -ENOMEM; + node = kvmalloc(struct_size(node, mm_nodes, num_nodes), + GFP_KERNEL | __GFP_ZERO); + if (!node) { + r = -ENOMEM; + goto error_sub; } + ttm_resource_init(tbo, place, &node->base); + mode = DRM_MM_INSERT_BEST; if (place->flags & TTM_PL_FLAG_TOPDOWN) mode = DRM_MM_INSERT_HIGH; - mem->start = 0; - pages_left = mem->num_pages; + pages_left = node->base.num_pages; /* Limit maximum size to 2GB due to SG table limitations */ pages = min(pages_left, 2UL << (30 - PAGE_SHIFT)); @@ -432,8 +436,9 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, if (pages >= pages_per_node) alignment = pages_per_node; - r = drm_mm_insert_node_in_range(mm, &nodes[i], pages, alignment, - 0, place->fpfn, lpfn, mode); + r = drm_mm_insert_node_in_range(mm, &node->mm_nodes[i], pages, + alignment, 0, place->fpfn, + lpfn, mode); if (unlikely(r)) { if (pages > pages_per_node) { if (is_power_of_2(pages)) @@ -442,11 +447,11 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, pages = rounddown_pow_of_two(pages); continue; } - goto error; + goto error_free; } - vis_usage += amdgpu_vram_mgr_vis_size(adev, &nodes[i]); - amdgpu_vram_mgr_virt_start(mem, &nodes[i]); + vis_usage += amdgpu_vram_mgr_vis_size(adev, &node->mm_nodes[i]); + amdgpu_vram_mgr_virt_start(&node->base, &node->mm_nodes[i]); pages_left -= pages; ++i; @@ -456,19 +461,20 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, spin_unlock(&mgr->lock); if (i == 1) - mem->placement |= TTM_PL_FLAG_CONTIGUOUS; + node->base.placement |= TTM_PL_FLAG_CONTIGUOUS; atomic64_add(vis_usage, &mgr->vis_usage); - mem->mm_node = nodes; + *res = &node->base; return 0; -error: +error_free: while (i--) - drm_mm_remove_node(&nodes[i]); + drm_mm_remove_node(&node->mm_nodes[i]); spin_unlock(&mgr->lock); - atomic64_sub(mem->num_pages << PAGE_SHIFT, &mgr->usage); + kvfree(node); - kvfree(nodes); +error_sub: + atomic64_sub(mem_bytes, &mgr->usage); return r; } @@ -481,24 +487,22 @@ error: * Free the allocated VRAM again. */ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man, - struct ttm_resource *mem) + struct ttm_resource *res) { + struct ttm_range_mgr_node *node = to_ttm_range_mgr_node(res); struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); struct amdgpu_device *adev = to_amdgpu_device(mgr); - struct drm_mm_node *nodes = mem->mm_node; uint64_t usage = 0, vis_usage = 0; - unsigned pages = mem->num_pages; - - if (!mem->mm_node) - return; + unsigned i, pages; spin_lock(&mgr->lock); - while (pages) { - pages -= nodes->size; - drm_mm_remove_node(nodes); - usage += nodes->size << PAGE_SHIFT; - vis_usage += amdgpu_vram_mgr_vis_size(adev, nodes); - ++nodes; + for (i = 0, pages = res->num_pages; pages; + pages -= node->mm_nodes[i].size, ++i) { + struct drm_mm_node *mm = &node->mm_nodes[i]; + + drm_mm_remove_node(mm); + usage += mm->size << PAGE_SHIFT; + vis_usage += amdgpu_vram_mgr_vis_size(adev, mm); } amdgpu_vram_mgr_do_reserve(man); spin_unlock(&mgr->lock); @@ -506,8 +510,7 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man, atomic64_sub(usage, &mgr->usage); atomic64_sub(vis_usage, &mgr->vis_usage); - kvfree(mem->mm_node); - mem->mm_node = NULL; + kvfree(node); } /** @@ -524,7 +527,7 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man, * Allocate and fill a sg table from a VRAM allocation. */ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, - struct ttm_resource *mem, + struct ttm_resource *res, u64 offset, u64 length, struct device *dev, enum dma_data_direction dir, @@ -540,7 +543,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, return -ENOMEM; /* Determine the number of DRM_MM nodes to export */ - amdgpu_res_first(mem, offset, length, &cursor); + amdgpu_res_first(res, offset, length, &cursor); while (cursor.remaining) { num_entries++; amdgpu_res_next(&cursor, cursor.size); @@ -560,7 +563,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, * and the number of bytes from it. Access the following * DRM_MM node(s) if more buffer needs to exported */ - amdgpu_res_first(mem, offset, length, &cursor); + amdgpu_res_first(res, offset, length, &cursor); for_each_sgtable_sg((*sgt), sg, i) { phys_addr_t phys = cursor.start + adev->gmc.aper_base; size_t size = cursor.size; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index fd8f544f0de2..2660f03e63a7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -29,6 +29,7 @@ #include "amdgpu_object.h" #include "amdgpu_vm.h" #include "amdgpu_mn.h" +#include "amdgpu_res_cursor.h" #include "kfd_priv.h" #include "kfd_svm.h" #include "kfd_migrate.h" @@ -205,34 +206,6 @@ svm_migrate_copy_done(struct amdgpu_device *adev, struct dma_fence *mfence) return r; } -static uint64_t -svm_migrate_node_physical_addr(struct amdgpu_device *adev, - struct drm_mm_node **mm_node, uint64_t *offset) -{ - struct drm_mm_node *node = *mm_node; - uint64_t pos = *offset; - - if (node->start == AMDGPU_BO_INVALID_OFFSET) { - pr_debug("drm node is not validated\n"); - return 0; - } - - pr_debug("vram node start 0x%llx npages 0x%llx\n", node->start, - node->size); - - if (pos >= node->size) { - do { - pos -= node->size; - node++; - } while (pos >= node->size); - - *mm_node = node; - *offset = pos; - } - - return (node->start + pos) << PAGE_SHIFT; -} - unsigned long svm_migrate_addr_to_pfn(struct amdgpu_device *adev, unsigned long addr) { @@ -297,11 +270,9 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, { uint64_t npages = migrate->cpages; struct device *dev = adev->dev; - struct drm_mm_node *node; + struct amdgpu_res_cursor cursor; dma_addr_t *src; uint64_t *dst; - uint64_t vram_addr; - uint64_t offset; uint64_t i, j; int r; @@ -317,19 +288,12 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, goto out; } - node = prange->ttm_res->mm_node; - offset = prange->offset; - vram_addr = svm_migrate_node_physical_addr(adev, &node, &offset); - if (!vram_addr) { - WARN_ONCE(1, "vram node address is 0\n"); - r = -ENOMEM; - goto out; - } - + amdgpu_res_first(prange->ttm_res, prange->offset << PAGE_SHIFT, + npages << PAGE_SHIFT, &cursor); for (i = j = 0; i < npages; i++) { struct page *spage; - dst[i] = vram_addr + (j << PAGE_SHIFT); + dst[i] = cursor.start + (j << PAGE_SHIFT); migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]); svm_migrate_get_vram_page(prange, migrate->dst[i]); @@ -354,18 +318,10 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, mfence); if (r) goto out_free_vram_pages; - offset += j; - vram_addr = (node->start + offset) << PAGE_SHIFT; + amdgpu_res_next(&cursor, j << PAGE_SHIFT); j = 0; } else { - offset++; - vram_addr += PAGE_SIZE; - } - if (offset >= node->size) { - node++; - pr_debug("next node size 0x%llx\n", node->size); - vram_addr = node->start << PAGE_SHIFT; - offset = 0; + amdgpu_res_next(&cursor, PAGE_SIZE); } continue; } @@ -373,19 +329,15 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, pr_debug("dma mapping src to 0x%llx, page_to_pfn 0x%lx\n", src[i] >> PAGE_SHIFT, page_to_pfn(spage)); - if (j + offset >= node->size - 1 && i < npages - 1) { + if (j >= (cursor.size >> PAGE_SHIFT) - 1 && i < npages - 1) { r = svm_migrate_copy_memory_gart(adev, src + i - j, dst + i - j, j + 1, FROM_RAM_TO_VRAM, mfence); if (r) goto out_free_vram_pages; - - node++; - pr_debug("next node size 0x%llx\n", node->size); - vram_addr = node->start << PAGE_SHIFT; - offset = 0; - j = 0; + amdgpu_res_next(&cursor, (j + 1) * PAGE_SIZE); + j= 0; } else { j++; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index f2901e7a993e..0d57ef9e73eb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -409,7 +409,7 @@ svm_range_validate_svm_bo(struct amdgpu_device *adev, struct svm_range *prange) pr_debug("reuse old bo svms 0x%p [0x%lx 0x%lx]\n", prange->svms, prange->start, prange->last); - prange->ttm_res = &prange->svm_bo->bo->tbo.mem; + prange->ttm_res = prange->svm_bo->bo->tbo.resource; return true; } @@ -515,7 +515,7 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange, svm_bo->bo = bo; prange->svm_bo = svm_bo; - prange->ttm_res = &bo->tbo.mem; + prange->ttm_res = bo->tbo.resource; prange->offset = 0; spin_lock(&svm_bo->list_lock); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 4f4c6438d245..ae519f929c57 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8447,9 +8447,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, * deadlock during GPU reset when this fence will not signal * but we hold reservation lock for the BO. */ - r = dma_resv_wait_timeout_rcu(abo->tbo.base.resv, true, - false, - msecs_to_jiffies(5000)); + r = dma_resv_wait_timeout(abo->tbo.base.resv, true, false, + msecs_to_jiffies(5000)); if (unlikely(r <= 0)) DRM_ERROR("Waiting for fences timed out!"); diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index c96e4b38d1d3..85b673613687 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -285,6 +285,16 @@ config DRM_TI_TFP410 help Texas Instruments TFP410 DVI/HDMI Transmitter driver +config DRM_TI_SN65DSI83 + tristate "TI SN65DSI83 and SN65DSI84 DSI to LVDS bridge" + depends on OF + select DRM_KMS_HELPER + select REGMAP_I2C + select DRM_PANEL + select DRM_MIPI_DSI + help + Texas Instruments SN65DSI83 and SN65DSI84 DSI to LVDS Bridge driver + config DRM_TI_SN65DSI86 tristate "TI SN65DSI86 DSI to eDP bridge" depends on OF diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile index dff2b2897529..f2c73683cfcb 100644 --- a/drivers/gpu/drm/bridge/Makefile +++ b/drivers/gpu/drm/bridge/Makefile @@ -23,6 +23,7 @@ obj-$(CONFIG_DRM_TOSHIBA_TC358767) += tc358767.o obj-$(CONFIG_DRM_TOSHIBA_TC358768) += tc358768.o obj-$(CONFIG_DRM_TOSHIBA_TC358775) += tc358775.o obj-$(CONFIG_DRM_I2C_ADV7511) += adv7511/ +obj-$(CONFIG_DRM_TI_SN65DSI83) += ti-sn65dsi83.o obj-$(CONFIG_DRM_TI_SN65DSI86) += ti-sn65dsi86.o obj-$(CONFIG_DRM_TI_TFP410) += ti-tfp410.o obj-$(CONFIG_DRM_TI_TPD12S015) += ti-tpd12s015.o diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c new file mode 100644 index 000000000000..750f2172ef08 --- /dev/null +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -0,0 +1,709 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * TI SN65DSI83,84,85 driver + * + * Currently supported: + * - SN65DSI83 + * = 1x Single-link DSI ~ 1x Single-link LVDS + * - Supported + * - Single-link LVDS mode tested + * - SN65DSI84 + * = 1x Single-link DSI ~ 2x Single-link or 1x Dual-link LVDS + * - Supported + * - Dual-link LVDS mode tested + * - 2x Single-link LVDS mode unsupported + * (should be easy to add by someone who has the HW) + * - SN65DSI85 + * = 2x Single-link or 1x Dual-link DSI ~ 2x Single-link or 1x Dual-link LVDS + * - Unsupported + * (should be easy to add by someone who has the HW) + * + * Copyright (C) 2021 Marek Vasut <marex@denx.de> + * + * Based on previous work of: + * Valentin Raevsky <valentin@compulab.co.il> + * Philippe Schenker <philippe.schenker@toradex.com> + */ + +#include <linux/bits.h> +#include <linux/clk.h> +#include <linux/gpio/consumer.h> +#include <linux/i2c.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/of_graph.h> +#include <linux/regmap.h> + +#include <drm/drm_atomic_helper.h> +#include <drm/drm_bridge.h> +#include <drm/drm_mipi_dsi.h> +#include <drm/drm_of.h> +#include <drm/drm_panel.h> +#include <drm/drm_print.h> +#include <drm/drm_probe_helper.h> + +/* ID registers */ +#define REG_ID(n) (0x00 + (n)) +/* Reset and clock registers */ +#define REG_RC_RESET 0x09 +#define REG_RC_RESET_SOFT_RESET BIT(0) +#define REG_RC_LVDS_PLL 0x0a +#define REG_RC_LVDS_PLL_PLL_EN_STAT BIT(7) +#define REG_RC_LVDS_PLL_LVDS_CLK_RANGE(n) (((n) & 0x7) << 1) +#define REG_RC_LVDS_PLL_HS_CLK_SRC_DPHY BIT(0) +#define REG_RC_DSI_CLK 0x0b +#define REG_RC_DSI_CLK_DSI_CLK_DIVIDER(n) (((n) & 0x1f) << 3) +#define REG_RC_DSI_CLK_REFCLK_MULTIPLIER(n) ((n) & 0x3) +#define REG_RC_PLL_EN 0x0d +#define REG_RC_PLL_EN_PLL_EN BIT(0) +/* DSI registers */ +#define REG_DSI_LANE 0x10 +#define REG_DSI_LANE_LEFT_RIGHT_PIXELS BIT(7) /* DSI85-only */ +#define REG_DSI_LANE_DSI_CHANNEL_MODE_DUAL 0 /* DSI85-only */ +#define REG_DSI_LANE_DSI_CHANNEL_MODE_2SINGLE BIT(6) /* DSI85-only */ +#define REG_DSI_LANE_DSI_CHANNEL_MODE_SINGLE BIT(5) +#define REG_DSI_LANE_CHA_DSI_LANES(n) (((n) & 0x3) << 3) +#define REG_DSI_LANE_CHB_DSI_LANES(n) (((n) & 0x3) << 1) +#define REG_DSI_LANE_SOT_ERR_TOL_DIS BIT(0) +#define REG_DSI_EQ 0x11 +#define REG_DSI_EQ_CHA_DSI_DATA_EQ(n) (((n) & 0x3) << 6) +#define REG_DSI_EQ_CHA_DSI_CLK_EQ(n) (((n) & 0x3) << 2) +#define REG_DSI_CLK 0x12 +#define REG_DSI_CLK_CHA_DSI_CLK_RANGE(n) ((n) & 0xff) +/* LVDS registers */ +#define REG_LVDS_FMT 0x18 +#define REG_LVDS_FMT_DE_NEG_POLARITY BIT(7) +#define REG_LVDS_FMT_HS_NEG_POLARITY BIT(6) +#define REG_LVDS_FMT_VS_NEG_POLARITY BIT(5) +#define REG_LVDS_FMT_LVDS_LINK_CFG BIT(4) /* 0:AB 1:A-only */ +#define REG_LVDS_FMT_CHA_24BPP_MODE BIT(3) +#define REG_LVDS_FMT_CHB_24BPP_MODE BIT(2) +#define REG_LVDS_FMT_CHA_24BPP_FORMAT1 BIT(1) +#define REG_LVDS_FMT_CHB_24BPP_FORMAT1 BIT(0) +#define REG_LVDS_VCOM 0x19 +#define REG_LVDS_VCOM_CHA_LVDS_VOCM BIT(6) +#define REG_LVDS_VCOM_CHB_LVDS_VOCM BIT(4) +#define REG_LVDS_VCOM_CHA_LVDS_VOD_SWING(n) (((n) & 0x3) << 2) +#define REG_LVDS_VCOM_CHB_LVDS_VOD_SWING(n) ((n) & 0x3) +#define REG_LVDS_LANE 0x1a +#define REG_LVDS_LANE_EVEN_ODD_SWAP BIT(6) +#define REG_LVDS_LANE_CHA_REVERSE_LVDS BIT(5) +#define REG_LVDS_LANE_CHB_REVERSE_LVDS BIT(4) +#define REG_LVDS_LANE_CHA_LVDS_TERM BIT(1) +#define REG_LVDS_LANE_CHB_LVDS_TERM BIT(0) +#define REG_LVDS_CM 0x1b +#define REG_LVDS_CM_CHA_LVDS_CM_ADJUST(n) (((n) & 0x3) << 4) +#define REG_LVDS_CM_CHB_LVDS_CM_ADJUST(n) ((n) & 0x3) +/* Video registers */ +#define REG_VID_CHA_ACTIVE_LINE_LENGTH_LOW 0x20 +#define REG_VID_CHA_ACTIVE_LINE_LENGTH_HIGH 0x21 +#define REG_VID_CHA_VERTICAL_DISPLAY_SIZE_LOW 0x24 +#define REG_VID_CHA_VERTICAL_DISPLAY_SIZE_HIGH 0x25 +#define REG_VID_CHA_SYNC_DELAY_LOW 0x28 +#define REG_VID_CHA_SYNC_DELAY_HIGH 0x29 +#define REG_VID_CHA_HSYNC_PULSE_WIDTH_LOW 0x2c +#define REG_VID_CHA_HSYNC_PULSE_WIDTH_HIGH 0x2d +#define REG_VID_CHA_VSYNC_PULSE_WIDTH_LOW 0x30 +#define REG_VID_CHA_VSYNC_PULSE_WIDTH_HIGH 0x31 +#define REG_VID_CHA_HORIZONTAL_BACK_PORCH 0x34 +#define REG_VID_CHA_VERTICAL_BACK_PORCH 0x36 +#define REG_VID_CHA_HORIZONTAL_FRONT_PORCH 0x38 +#define REG_VID_CHA_VERTICAL_FRONT_PORCH 0x3a +#define REG_VID_CHA_TEST_PATTERN 0x3c +/* IRQ registers */ +#define REG_IRQ_GLOBAL 0xe0 +#define REG_IRQ_GLOBAL_IRQ_EN BIT(0) +#define REG_IRQ_EN 0xe1 +#define REG_IRQ_EN_CHA_SYNCH_ERR_EN BIT(7) +#define REG_IRQ_EN_CHA_CRC_ERR_EN BIT(6) +#define REG_IRQ_EN_CHA_UNC_ECC_ERR_EN BIT(5) +#define REG_IRQ_EN_CHA_COR_ECC_ERR_EN BIT(4) +#define REG_IRQ_EN_CHA_LLP_ERR_EN BIT(3) +#define REG_IRQ_EN_CHA_SOT_BIT_ERR_EN BIT(2) +#define REG_IRQ_EN_CHA_PLL_UNLOCK_EN BIT(0) +#define REG_IRQ_STAT 0xe5 +#define REG_IRQ_STAT_CHA_SYNCH_ERR BIT(7) +#define REG_IRQ_STAT_CHA_CRC_ERR BIT(6) +#define REG_IRQ_STAT_CHA_UNC_ECC_ERR BIT(5) +#define REG_IRQ_STAT_CHA_COR_ECC_ERR BIT(4) +#define REG_IRQ_STAT_CHA_LLP_ERR BIT(3) +#define REG_IRQ_STAT_CHA_SOT_BIT_ERR BIT(2) +#define REG_IRQ_STAT_CHA_PLL_UNLOCK BIT(0) + +enum sn65dsi83_model { + MODEL_SN65DSI83, + MODEL_SN65DSI84, +}; + +struct sn65dsi83 { + struct drm_bridge bridge; + struct drm_display_mode mode; + struct device *dev; + struct regmap *regmap; + struct device_node *host_node; + struct mipi_dsi_device *dsi; + struct drm_bridge *panel_bridge; + struct gpio_desc *enable_gpio; + int dsi_lanes; + bool lvds_dual_link; + bool lvds_dual_link_even_odd_swap; + bool lvds_format_24bpp; + bool lvds_format_jeida; +}; + +static const struct regmap_range sn65dsi83_readable_ranges[] = { + regmap_reg_range(REG_ID(0), REG_ID(8)), + regmap_reg_range(REG_RC_LVDS_PLL, REG_RC_DSI_CLK), + regmap_reg_range(REG_RC_PLL_EN, REG_RC_PLL_EN), + regmap_reg_range(REG_DSI_LANE, REG_DSI_CLK), + regmap_reg_range(REG_LVDS_FMT, REG_LVDS_CM), + regmap_reg_range(REG_VID_CHA_ACTIVE_LINE_LENGTH_LOW, + REG_VID_CHA_ACTIVE_LINE_LENGTH_HIGH), + regmap_reg_range(REG_VID_CHA_VERTICAL_DISPLAY_SIZE_LOW, + REG_VID_CHA_VERTICAL_DISPLAY_SIZE_HIGH), + regmap_reg_range(REG_VID_CHA_SYNC_DELAY_LOW, + REG_VID_CHA_SYNC_DELAY_HIGH), + regmap_reg_range(REG_VID_CHA_HSYNC_PULSE_WIDTH_LOW, + REG_VID_CHA_HSYNC_PULSE_WIDTH_HIGH), + regmap_reg_range(REG_VID_CHA_VSYNC_PULSE_WIDTH_LOW, + REG_VID_CHA_VSYNC_PULSE_WIDTH_HIGH), + regmap_reg_range(REG_VID_CHA_HORIZONTAL_BACK_PORCH, + REG_VID_CHA_HORIZONTAL_BACK_PORCH), + regmap_reg_range(REG_VID_CHA_VERTICAL_BACK_PORCH, + REG_VID_CHA_VERTICAL_BACK_PORCH), + regmap_reg_range(REG_VID_CHA_HORIZONTAL_FRONT_PORCH, + REG_VID_CHA_HORIZONTAL_FRONT_PORCH), + regmap_reg_range(REG_VID_CHA_VERTICAL_FRONT_PORCH, + REG_VID_CHA_VERTICAL_FRONT_PORCH), + regmap_reg_range(REG_VID_CHA_TEST_PATTERN, REG_VID_CHA_TEST_PATTERN), + regmap_reg_range(REG_IRQ_GLOBAL, REG_IRQ_EN), + regmap_reg_range(REG_IRQ_STAT, REG_IRQ_STAT), +}; + +static const struct regmap_access_table sn65dsi83_readable_table = { + .yes_ranges = sn65dsi83_readable_ranges, + .n_yes_ranges = ARRAY_SIZE(sn65dsi83_readable_ranges), +}; + +static const struct regmap_range sn65dsi83_writeable_ranges[] = { + regmap_reg_range(REG_RC_RESET, REG_RC_DSI_CLK), + regmap_reg_range(REG_RC_PLL_EN, REG_RC_PLL_EN), + regmap_reg_range(REG_DSI_LANE, REG_DSI_CLK), + regmap_reg_range(REG_LVDS_FMT, REG_LVDS_CM), + regmap_reg_range(REG_VID_CHA_ACTIVE_LINE_LENGTH_LOW, + REG_VID_CHA_ACTIVE_LINE_LENGTH_HIGH), + regmap_reg_range(REG_VID_CHA_VERTICAL_DISPLAY_SIZE_LOW, + REG_VID_CHA_VERTICAL_DISPLAY_SIZE_HIGH), + regmap_reg_range(REG_VID_CHA_SYNC_DELAY_LOW, + REG_VID_CHA_SYNC_DELAY_HIGH), + regmap_reg_range(REG_VID_CHA_HSYNC_PULSE_WIDTH_LOW, + REG_VID_CHA_HSYNC_PULSE_WIDTH_HIGH), + regmap_reg_range(REG_VID_CHA_VSYNC_PULSE_WIDTH_LOW, + REG_VID_CHA_VSYNC_PULSE_WIDTH_HIGH), + regmap_reg_range(REG_VID_CHA_HORIZONTAL_BACK_PORCH, + REG_VID_CHA_HORIZONTAL_BACK_PORCH), + regmap_reg_range(REG_VID_CHA_VERTICAL_BACK_PORCH, + REG_VID_CHA_VERTICAL_BACK_PORCH), + regmap_reg_range(REG_VID_CHA_HORIZONTAL_FRONT_PORCH, + REG_VID_CHA_HORIZONTAL_FRONT_PORCH), + regmap_reg_range(REG_VID_CHA_VERTICAL_FRONT_PORCH, + REG_VID_CHA_VERTICAL_FRONT_PORCH), + regmap_reg_range(REG_VID_CHA_TEST_PATTERN, REG_VID_CHA_TEST_PATTERN), + regmap_reg_range(REG_IRQ_GLOBAL, REG_IRQ_EN), + regmap_reg_range(REG_IRQ_STAT, REG_IRQ_STAT), +}; + +static const struct regmap_access_table sn65dsi83_writeable_table = { + .yes_ranges = sn65dsi83_writeable_ranges, + .n_yes_ranges = ARRAY_SIZE(sn65dsi83_writeable_ranges), +}; + +static const struct regmap_range sn65dsi83_volatile_ranges[] = { + regmap_reg_range(REG_RC_RESET, REG_RC_RESET), + regmap_reg_range(REG_RC_LVDS_PLL, REG_RC_LVDS_PLL), + regmap_reg_range(REG_IRQ_STAT, REG_IRQ_STAT), +}; + +static const struct regmap_access_table sn65dsi83_volatile_table = { + .yes_ranges = sn65dsi83_volatile_ranges, + .n_yes_ranges = ARRAY_SIZE(sn65dsi83_volatile_ranges), +}; + +static const struct regmap_config sn65dsi83_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .rd_table = &sn65dsi83_readable_table, + .wr_table = &sn65dsi83_writeable_table, + .volatile_table = &sn65dsi83_volatile_table, + .cache_type = REGCACHE_RBTREE, + .max_register = REG_IRQ_STAT, +}; + +static struct sn65dsi83 *bridge_to_sn65dsi83(struct drm_bridge *bridge) +{ + return container_of(bridge, struct sn65dsi83, bridge); +} + +static int sn65dsi83_attach(struct drm_bridge *bridge, + enum drm_bridge_attach_flags flags) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + struct device *dev = ctx->dev; + struct mipi_dsi_device *dsi; + struct mipi_dsi_host *host; + int ret = 0; + + const struct mipi_dsi_device_info info = { + .type = "sn65dsi83", + .channel = 0, + .node = NULL, + }; + + host = of_find_mipi_dsi_host_by_node(ctx->host_node); + if (!host) { + dev_err(dev, "failed to find dsi host\n"); + return -EPROBE_DEFER; + } + + dsi = mipi_dsi_device_register_full(host, &info); + if (IS_ERR(dsi)) { + return dev_err_probe(dev, PTR_ERR(dsi), + "failed to create dsi device\n"); + } + + ctx->dsi = dsi; + + dsi->lanes = ctx->dsi_lanes; + dsi->format = MIPI_DSI_FMT_RGB888; + dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST; + + ret = mipi_dsi_attach(dsi); + if (ret < 0) { + dev_err(dev, "failed to attach dsi to host\n"); + goto err_dsi_attach; + } + + return drm_bridge_attach(bridge->encoder, ctx->panel_bridge, + &ctx->bridge, flags); + +err_dsi_attach: + mipi_dsi_device_unregister(dsi); + return ret; +} + +static void sn65dsi83_pre_enable(struct drm_bridge *bridge) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + + /* + * Reset the chip, pull EN line low for t_reset=10ms, + * then high for t_en=1ms. + */ + regcache_mark_dirty(ctx->regmap); + gpiod_set_value(ctx->enable_gpio, 0); + usleep_range(10000, 11000); + gpiod_set_value(ctx->enable_gpio, 1); + usleep_range(1000, 1100); +} + +static u8 sn65dsi83_get_lvds_range(struct sn65dsi83 *ctx) +{ + /* + * The encoding of the LVDS_CLK_RANGE is as follows: + * 000 - 25 MHz <= LVDS_CLK < 37.5 MHz + * 001 - 37.5 MHz <= LVDS_CLK < 62.5 MHz + * 010 - 62.5 MHz <= LVDS_CLK < 87.5 MHz + * 011 - 87.5 MHz <= LVDS_CLK < 112.5 MHz + * 100 - 112.5 MHz <= LVDS_CLK < 137.5 MHz + * 101 - 137.5 MHz <= LVDS_CLK <= 154 MHz + * which is a range of 12.5MHz..162.5MHz in 50MHz steps, except that + * the ends of the ranges are clamped to the supported range. Since + * sn65dsi83_mode_valid() already filters the valid modes and limits + * the clock to 25..154 MHz, the range calculation can be simplified + * as follows: + */ + int mode_clock = ctx->mode.clock; + + if (ctx->lvds_dual_link) + mode_clock /= 2; + + return (mode_clock - 12500) / 25000; +} + +static u8 sn65dsi83_get_dsi_range(struct sn65dsi83 *ctx) +{ + /* + * The encoding of the CHA_DSI_CLK_RANGE is as follows: + * 0x00 through 0x07 - Reserved + * 0x08 - 40 <= DSI_CLK < 45 MHz + * 0x09 - 45 <= DSI_CLK < 50 MHz + * ... + * 0x63 - 495 <= DSI_CLK < 500 MHz + * 0x64 - 500 MHz + * 0x65 through 0xFF - Reserved + * which is DSI clock in 5 MHz steps, clamped to 40..500 MHz. + * The DSI clock are calculated as: + * DSI_CLK = mode clock * bpp / dsi_data_lanes / 2 + * the 2 is there because the bus is DDR. + */ + return DIV_ROUND_UP(clamp((unsigned int)ctx->mode.clock * + mipi_dsi_pixel_format_to_bpp(ctx->dsi->format) / + ctx->dsi_lanes / 2, 40000U, 500000U), 5000U); +} + +static u8 sn65dsi83_get_dsi_div(struct sn65dsi83 *ctx) +{ + /* The divider is (DSI_CLK / LVDS_CLK) - 1, which really is: */ + unsigned int dsi_div = mipi_dsi_pixel_format_to_bpp(ctx->dsi->format); + + dsi_div /= ctx->dsi_lanes; + + if (!ctx->lvds_dual_link) + dsi_div /= 2; + + return dsi_div - 1; +} + +static void sn65dsi83_enable(struct drm_bridge *bridge) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + unsigned int pval; + u16 val; + int ret; + + /* Clear reset, disable PLL */ + regmap_write(ctx->regmap, REG_RC_RESET, 0x00); + regmap_write(ctx->regmap, REG_RC_PLL_EN, 0x00); + + /* Reference clock derived from DSI link clock. */ + regmap_write(ctx->regmap, REG_RC_LVDS_PLL, + REG_RC_LVDS_PLL_LVDS_CLK_RANGE(sn65dsi83_get_lvds_range(ctx)) | + REG_RC_LVDS_PLL_HS_CLK_SRC_DPHY); + regmap_write(ctx->regmap, REG_DSI_CLK, + REG_DSI_CLK_CHA_DSI_CLK_RANGE(sn65dsi83_get_dsi_range(ctx))); + regmap_write(ctx->regmap, REG_RC_DSI_CLK, + REG_RC_DSI_CLK_DSI_CLK_DIVIDER(sn65dsi83_get_dsi_div(ctx))); + + /* Set number of DSI lanes and LVDS link config. */ + regmap_write(ctx->regmap, REG_DSI_LANE, + REG_DSI_LANE_DSI_CHANNEL_MODE_SINGLE | + REG_DSI_LANE_CHA_DSI_LANES(~(ctx->dsi_lanes - 1)) | + /* CHB is DSI85-only, set to default on DSI83/DSI84 */ + REG_DSI_LANE_CHB_DSI_LANES(3)); + /* No equalization. */ + regmap_write(ctx->regmap, REG_DSI_EQ, 0x00); + + /* Set up sync signal polarity. */ + val = (ctx->mode.flags & DRM_MODE_FLAG_NHSYNC ? + REG_LVDS_FMT_HS_NEG_POLARITY : 0) | + (ctx->mode.flags & DRM_MODE_FLAG_NVSYNC ? + REG_LVDS_FMT_VS_NEG_POLARITY : 0); + + /* Set up bits-per-pixel, 18bpp or 24bpp. */ + if (ctx->lvds_format_24bpp) { + val |= REG_LVDS_FMT_CHA_24BPP_MODE; + if (ctx->lvds_dual_link) + val |= REG_LVDS_FMT_CHB_24BPP_MODE; + } + + /* Set up LVDS format, JEIDA/Format 1 or SPWG/Format 2 */ + if (ctx->lvds_format_jeida) { + val |= REG_LVDS_FMT_CHA_24BPP_FORMAT1; + if (ctx->lvds_dual_link) + val |= REG_LVDS_FMT_CHB_24BPP_FORMAT1; + } + + /* Set up LVDS output config (DSI84,DSI85) */ + if (!ctx->lvds_dual_link) + val |= REG_LVDS_FMT_LVDS_LINK_CFG; + + regmap_write(ctx->regmap, REG_LVDS_FMT, val); + regmap_write(ctx->regmap, REG_LVDS_VCOM, 0x05); + regmap_write(ctx->regmap, REG_LVDS_LANE, + (ctx->lvds_dual_link_even_odd_swap ? + REG_LVDS_LANE_EVEN_ODD_SWAP : 0) | + REG_LVDS_LANE_CHA_LVDS_TERM | + REG_LVDS_LANE_CHB_LVDS_TERM); + regmap_write(ctx->regmap, REG_LVDS_CM, 0x00); + + val = cpu_to_le16(ctx->mode.hdisplay); + regmap_bulk_write(ctx->regmap, REG_VID_CHA_ACTIVE_LINE_LENGTH_LOW, + &val, 2); + val = cpu_to_le16(ctx->mode.vdisplay); + regmap_bulk_write(ctx->regmap, REG_VID_CHA_VERTICAL_DISPLAY_SIZE_LOW, + &val, 2); + /* 32 + 1 pixel clock to ensure proper operation */ + val = cpu_to_le16(32 + 1); + regmap_bulk_write(ctx->regmap, REG_VID_CHA_SYNC_DELAY_LOW, &val, 2); + val = cpu_to_le16(ctx->mode.hsync_end - ctx->mode.hsync_start); + regmap_bulk_write(ctx->regmap, REG_VID_CHA_HSYNC_PULSE_WIDTH_LOW, + &val, 2); + val = cpu_to_le16(ctx->mode.vsync_end - ctx->mode.vsync_start); + regmap_bulk_write(ctx->regmap, REG_VID_CHA_VSYNC_PULSE_WIDTH_LOW, + &val, 2); + regmap_write(ctx->regmap, REG_VID_CHA_HORIZONTAL_BACK_PORCH, + ctx->mode.htotal - ctx->mode.hsync_end); + regmap_write(ctx->regmap, REG_VID_CHA_VERTICAL_BACK_PORCH, + ctx->mode.vtotal - ctx->mode.vsync_end); + regmap_write(ctx->regmap, REG_VID_CHA_HORIZONTAL_FRONT_PORCH, + ctx->mode.hsync_start - ctx->mode.hdisplay); + regmap_write(ctx->regmap, REG_VID_CHA_VERTICAL_FRONT_PORCH, + ctx->mode.vsync_start - ctx->mode.vdisplay); + regmap_write(ctx->regmap, REG_VID_CHA_TEST_PATTERN, 0x00); + + /* Enable PLL */ + regmap_write(ctx->regmap, REG_RC_PLL_EN, REG_RC_PLL_EN_PLL_EN); + usleep_range(3000, 4000); + ret = regmap_read_poll_timeout(ctx->regmap, REG_RC_LVDS_PLL, pval, + pval & REG_RC_LVDS_PLL_PLL_EN_STAT, + 1000, 100000); + if (ret) { + dev_err(ctx->dev, "failed to lock PLL, ret=%i\n", ret); + /* On failure, disable PLL again and exit. */ + regmap_write(ctx->regmap, REG_RC_PLL_EN, 0x00); + return; + } + + /* Trigger reset after CSR register update. */ + regmap_write(ctx->regmap, REG_RC_RESET, REG_RC_RESET_SOFT_RESET); + + /* Clear all errors that got asserted during initialization. */ + regmap_read(ctx->regmap, REG_IRQ_STAT, &pval); + regmap_write(ctx->regmap, REG_IRQ_STAT, pval); +} + +static void sn65dsi83_disable(struct drm_bridge *bridge) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + + /* Clear reset, disable PLL */ + regmap_write(ctx->regmap, REG_RC_RESET, 0x00); + regmap_write(ctx->regmap, REG_RC_PLL_EN, 0x00); +} + +static void sn65dsi83_post_disable(struct drm_bridge *bridge) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + + /* Put the chip in reset, pull EN line low. */ + gpiod_set_value(ctx->enable_gpio, 0); +} + +static enum drm_mode_status +sn65dsi83_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + /* LVDS output clock range 25..154 MHz */ + if (mode->clock < 25000) + return MODE_CLOCK_LOW; + if (mode->clock > 154000) + return MODE_CLOCK_HIGH; + + return MODE_OK; +} + +static void sn65dsi83_mode_set(struct drm_bridge *bridge, + const struct drm_display_mode *mode, + const struct drm_display_mode *adj) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + + ctx->mode = *adj; +} + +static bool sn65dsi83_mode_fixup(struct drm_bridge *bridge, + const struct drm_display_mode *mode, + struct drm_display_mode *adj) +{ + struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + u32 input_bus_format = MEDIA_BUS_FMT_RGB888_1X24; + struct drm_encoder *encoder = bridge->encoder; + struct drm_device *ddev = encoder->dev; + struct drm_connector *connector; + + /* The DSI format is always RGB888_1X24 */ + list_for_each_entry(connector, &ddev->mode_config.connector_list, head) { + switch (connector->display_info.bus_formats[0]) { + case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG: + ctx->lvds_format_24bpp = false; + ctx->lvds_format_jeida = true; + break; + case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA: + ctx->lvds_format_24bpp = true; + ctx->lvds_format_jeida = true; + break; + case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG: + ctx->lvds_format_24bpp = true; + ctx->lvds_format_jeida = false; + break; + default: + /* + * Some bridges still don't set the correct + * LVDS bus pixel format, use SPWG24 default + * format until those are fixed. + */ + ctx->lvds_format_24bpp = true; + ctx->lvds_format_jeida = false; + dev_warn(ctx->dev, + "Unsupported LVDS bus format 0x%04x, please check output bridge driver. Falling back to SPWG24.\n", + connector->display_info.bus_formats[0]); + break; + } + + drm_display_info_set_bus_formats(&connector->display_info, + &input_bus_format, 1); + } + + return true; +} + +static const struct drm_bridge_funcs sn65dsi83_funcs = { + .attach = sn65dsi83_attach, + .pre_enable = sn65dsi83_pre_enable, + .enable = sn65dsi83_enable, + .disable = sn65dsi83_disable, + .post_disable = sn65dsi83_post_disable, + .mode_valid = sn65dsi83_mode_valid, + .mode_set = sn65dsi83_mode_set, + .mode_fixup = sn65dsi83_mode_fixup, +}; + +static int sn65dsi83_parse_dt(struct sn65dsi83 *ctx, enum sn65dsi83_model model) +{ + struct drm_bridge *panel_bridge; + struct device *dev = ctx->dev; + struct device_node *endpoint; + struct drm_panel *panel; + int ret; + + endpoint = of_graph_get_endpoint_by_regs(dev->of_node, 0, 0); + ctx->dsi_lanes = of_property_count_u32_elems(endpoint, "data-lanes"); + ctx->host_node = of_graph_get_remote_port_parent(endpoint); + of_node_put(endpoint); + + if (ctx->dsi_lanes < 0 || ctx->dsi_lanes > 4) + return -EINVAL; + if (!ctx->host_node) + return -ENODEV; + + ctx->lvds_dual_link = false; + ctx->lvds_dual_link_even_odd_swap = false; + if (model != MODEL_SN65DSI83) { + struct device_node *port2, *port3; + int dual_link; + + port2 = of_graph_get_port_by_id(dev->of_node, 2); + port3 = of_graph_get_port_by_id(dev->of_node, 3); + dual_link = drm_of_lvds_get_dual_link_pixel_order(port2, port3); + of_node_put(port2); + of_node_put(port3); + + if (dual_link == DRM_LVDS_DUAL_LINK_ODD_EVEN_PIXELS) { + ctx->lvds_dual_link = true; + /* Odd pixels to LVDS Channel A, even pixels to B */ + ctx->lvds_dual_link_even_odd_swap = false; + } else if (dual_link == DRM_LVDS_DUAL_LINK_EVEN_ODD_PIXELS) { + ctx->lvds_dual_link = true; + /* Even pixels to LVDS Channel A, odd pixels to B */ + ctx->lvds_dual_link_even_odd_swap = true; + } + } + + ret = drm_of_find_panel_or_bridge(dev->of_node, 2, 0, &panel, &panel_bridge); + if (ret < 0) + return ret; + if (panel) { + panel_bridge = devm_drm_panel_bridge_add(dev, panel); + if (IS_ERR(panel_bridge)) + return PTR_ERR(panel_bridge); + } + + ctx->panel_bridge = panel_bridge; + + return 0; +} + +static int sn65dsi83_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct device *dev = &client->dev; + enum sn65dsi83_model model; + struct sn65dsi83 *ctx; + int ret; + + ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->dev = dev; + + if (dev->of_node) { + model = (enum sn65dsi83_model)(uintptr_t) + of_device_get_match_data(dev); + } else { + model = id->driver_data; + } + + ctx->enable_gpio = devm_gpiod_get(ctx->dev, "enable", GPIOD_OUT_LOW); + if (IS_ERR(ctx->enable_gpio)) + return PTR_ERR(ctx->enable_gpio); + + ret = sn65dsi83_parse_dt(ctx, model); + if (ret) + return ret; + + ctx->regmap = devm_regmap_init_i2c(client, &sn65dsi83_regmap_config); + if (IS_ERR(ctx->regmap)) + return PTR_ERR(ctx->regmap); + + dev_set_drvdata(dev, ctx); + i2c_set_clientdata(client, ctx); + + ctx->bridge.funcs = &sn65dsi83_funcs; + ctx->bridge.of_node = dev->of_node; + drm_bridge_add(&ctx->bridge); + + return 0; +} + +static int sn65dsi83_remove(struct i2c_client *client) +{ + struct sn65dsi83 *ctx = i2c_get_clientdata(client); + + mipi_dsi_detach(ctx->dsi); + mipi_dsi_device_unregister(ctx->dsi); + drm_bridge_remove(&ctx->bridge); + of_node_put(ctx->host_node); + + return 0; +} + +static struct i2c_device_id sn65dsi83_id[] = { + { "ti,sn65dsi83", MODEL_SN65DSI83 }, + { "ti,sn65dsi84", MODEL_SN65DSI84 }, + {}, +}; +MODULE_DEVICE_TABLE(i2c, sn65dsi83_id); + +static const struct of_device_id sn65dsi83_match_table[] = { + { .compatible = "ti,sn65dsi83", .data = (void *)MODEL_SN65DSI83 }, + { .compatible = "ti,sn65dsi84", .data = (void *)MODEL_SN65DSI84 }, + {}, +}; +MODULE_DEVICE_TABLE(of, sn65dsi83_match_table); + +static struct i2c_driver sn65dsi83_driver = { + .probe = sn65dsi83_probe, + .remove = sn65dsi83_remove, + .id_table = sn65dsi83_id, + .driver = { + .name = "sn65dsi83", + .of_match_table = sn65dsi83_match_table, + }, +}; +module_i2c_driver(sn65dsi83_driver); + +MODULE_AUTHOR("Marek Vasut <marex@denx.de>"); +MODULE_DESCRIPTION("TI SN65DSI83 DSI to LVDS bridge driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c index 79a50ef1250f..546599f19a93 100644 --- a/drivers/gpu/drm/drm_cache.c +++ b/drivers/gpu/drm/drm_cache.c @@ -28,6 +28,7 @@ * Authors: Thomas Hellström <thomas-at-tungstengraphics-dot-com> */ +#include <linux/dma-buf-map.h> #include <linux/export.h> #include <linux/highmem.h> #include <linux/mem_encrypt.h> @@ -35,6 +36,9 @@ #include <drm/drm_cache.h> +/* A small bounce buffer that fits on the stack. */ +#define MEMCPY_BOUNCE_SIZE 128 + #if defined(CONFIG_X86) #include <asm/smp.h> @@ -209,3 +213,147 @@ bool drm_need_swiotlb(int dma_bits) return max_iomem > ((u64)1 << dma_bits); } EXPORT_SYMBOL(drm_need_swiotlb); + +static void memcpy_fallback(struct dma_buf_map *dst, + const struct dma_buf_map *src, + unsigned long len) +{ + if (!dst->is_iomem && !src->is_iomem) { + memcpy(dst->vaddr, src->vaddr, len); + } else if (!src->is_iomem) { + dma_buf_map_memcpy_to(dst, src->vaddr, len); + } else if (!dst->is_iomem) { + memcpy_fromio(dst->vaddr, src->vaddr_iomem, len); + } else { + /* + * Bounce size is not performance tuned, but using a + * bounce buffer like this is significantly faster than + * resorting to ioreadxx() + iowritexx(). + */ + char bounce[MEMCPY_BOUNCE_SIZE]; + void __iomem *_src = src->vaddr_iomem; + void __iomem *_dst = dst->vaddr_iomem; + + while (len >= MEMCPY_BOUNCE_SIZE) { + memcpy_fromio(bounce, _src, MEMCPY_BOUNCE_SIZE); + memcpy_toio(_dst, bounce, MEMCPY_BOUNCE_SIZE); + _src += MEMCPY_BOUNCE_SIZE; + _dst += MEMCPY_BOUNCE_SIZE; + len -= MEMCPY_BOUNCE_SIZE; + } + if (len) { + memcpy_fromio(bounce, _src, MEMCPY_BOUNCE_SIZE); + memcpy_toio(_dst, bounce, MEMCPY_BOUNCE_SIZE); + } + } +} + +#ifdef CONFIG_X86 + +static DEFINE_STATIC_KEY_FALSE(has_movntdqa); + +static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len) +{ + kernel_fpu_begin(); + + while (len >= 4) { + asm("movntdqa (%0), %%xmm0\n" + "movntdqa 16(%0), %%xmm1\n" + "movntdqa 32(%0), %%xmm2\n" + "movntdqa 48(%0), %%xmm3\n" + "movaps %%xmm0, (%1)\n" + "movaps %%xmm1, 16(%1)\n" + "movaps %%xmm2, 32(%1)\n" + "movaps %%xmm3, 48(%1)\n" + :: "r" (src), "r" (dst) : "memory"); + src += 64; + dst += 64; + len -= 4; + } + while (len--) { + asm("movntdqa (%0), %%xmm0\n" + "movaps %%xmm0, (%1)\n" + :: "r" (src), "r" (dst) : "memory"); + src += 16; + dst += 16; + } + + kernel_fpu_end(); +} + +/* + * __drm_memcpy_from_wc copies @len bytes from @src to @dst using + * non-temporal instructions where available. Note that all arguments + * (@src, @dst) must be aligned to 16 bytes and @len must be a multiple + * of 16. + */ +static void __drm_memcpy_from_wc(void *dst, const void *src, unsigned long len) +{ + if (unlikely(((unsigned long)dst | (unsigned long)src | len) & 15)) + memcpy(dst, src, len); + else if (likely(len)) + __memcpy_ntdqa(dst, src, len >> 4); +} + +/** + * drm_memcpy_from_wc - Perform the fastest available memcpy from a source + * that may be WC. + * @dst: The destination pointer + * @src: The source pointer + * @len: The size of the area o transfer in bytes + * + * Tries an arch optimized memcpy for prefetching reading out of a WC region, + * and if no such beast is available, falls back to a normal memcpy. + */ +void drm_memcpy_from_wc(struct dma_buf_map *dst, + const struct dma_buf_map *src, + unsigned long len) +{ + if (WARN_ON(in_interrupt())) { + memcpy_fallback(dst, src, len); + return; + } + + if (static_branch_likely(&has_movntdqa)) { + __drm_memcpy_from_wc(dst->is_iomem ? + (void __force *)dst->vaddr_iomem : + dst->vaddr, + src->is_iomem ? + (void const __force *)src->vaddr_iomem : + src->vaddr, + len); + return; + } + + memcpy_fallback(dst, src, len); +} +EXPORT_SYMBOL(drm_memcpy_from_wc); + +/* + * drm_memcpy_init_early - One time initialization of the WC memcpy code + */ +void drm_memcpy_init_early(void) +{ + /* + * Some hypervisors (e.g. KVM) don't support VEX-prefix instructions + * emulation. So don't enable movntdqa in hypervisor guest. + */ + if (static_cpu_has(X86_FEATURE_XMM4_1) && + !boot_cpu_has(X86_FEATURE_HYPERVISOR)) + static_branch_enable(&has_movntdqa); +} +#else +void drm_memcpy_from_wc(struct dma_buf_map *dst, + const struct dma_buf_map *src, + unsigned long len) +{ + WARN_ON(in_interrupt()); + + memcpy_fallback(dst, src, len); +} +EXPORT_SYMBOL(drm_memcpy_from_wc); + +void drm_memcpy_init_early(void) +{ +} +#endif /* CONFIG_X86 */ diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 3d8d68a98b95..8804ec7d3215 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -35,6 +35,7 @@ #include <linux/slab.h> #include <linux/srcu.h> +#include <drm/drm_cache.h> #include <drm/drm_client.h> #include <drm/drm_color_mgmt.h> #include <drm/drm_drv.h> @@ -1041,6 +1042,7 @@ static int __init drm_core_init(void) drm_connector_ida_init(); idr_init(&drm_minors_idr); + drm_memcpy_init_early(); ret = drm_sysfs_init(); if (ret < 0) { diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 9989425e9875..d62fb1a3c916 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -770,8 +770,7 @@ long drm_gem_dma_resv_wait(struct drm_file *filep, u32 handle, return -EINVAL; } - ret = dma_resv_wait_timeout_rcu(obj->resv, wait_all, - true, timeout); + ret = dma_resv_wait_timeout(obj->resv, wait_all, true, timeout); if (ret == 0) ret = -ETIME; else if (ret > 0) @@ -1375,12 +1374,12 @@ int drm_gem_fence_array_add_implicit(struct xarray *fence_array, if (!write) { struct dma_fence *fence = - dma_resv_get_excl_rcu(obj->resv); + dma_resv_get_excl_unlocked(obj->resv); return drm_gem_fence_array_add(fence_array, fence); } - ret = dma_resv_get_fences_rcu(obj->resv, NULL, + ret = dma_resv_get_fences(obj->resv, NULL, &fence_count, &fences); if (ret || !fence_count) return ret; diff --git a/drivers/gpu/drm/drm_gem_atomic_helper.c b/drivers/gpu/drm/drm_gem_atomic_helper.c index a005c5a0ba46..a27135084ae5 100644 --- a/drivers/gpu/drm/drm_gem_atomic_helper.c +++ b/drivers/gpu/drm/drm_gem_atomic_helper.c @@ -147,7 +147,7 @@ int drm_gem_plane_helper_prepare_fb(struct drm_plane *plane, struct drm_plane_st return 0; obj = drm_gem_fb_get_obj(state->fb, 0); - fence = dma_resv_get_excl_rcu(obj->resv); + fence = dma_resv_get_excl_unlocked(obj->resv); drm_atomic_set_fence_for_plane(state, fence); return 0; diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c index 4a24af2c5c43..d53388199f34 100644 --- a/drivers/gpu/drm/drm_gem_cma_helper.c +++ b/drivers/gpu/drm/drm_gem_cma_helper.c @@ -104,8 +104,7 @@ error: * @size: size of the object to allocate * * This function creates a CMA GEM object and allocates a contiguous chunk of - * memory as backing store. The backing memory has the writecombine attribute - * set. + * memory as backing store. * * Returns: * A struct drm_gem_cma_object * on success or an ERR_PTR()-encoded negative diff --git a/drivers/gpu/drm/drm_gem_ttm_helper.c b/drivers/gpu/drm/drm_gem_ttm_helper.c index b14bed8be771..ecf3d2a54a98 100644 --- a/drivers/gpu/drm/drm_gem_ttm_helper.c +++ b/drivers/gpu/drm/drm_gem_ttm_helper.c @@ -40,12 +40,12 @@ void drm_gem_ttm_print_info(struct drm_printer *p, unsigned int indent, const struct ttm_buffer_object *bo = drm_gem_ttm_of_gem(gem); drm_printf_indent(p, indent, "placement="); - drm_print_bits(p, bo->mem.placement, plname, ARRAY_SIZE(plname)); + drm_print_bits(p, bo->resource->placement, plname, ARRAY_SIZE(plname)); drm_printf(p, "\n"); - if (bo->mem.bus.is_iomem) + if (bo->resource->bus.is_iomem) drm_printf_indent(p, indent, "bus.offset=%lx\n", - (unsigned long)bo->mem.bus.offset); + (unsigned long)bo->resource->bus.offset); } EXPORT_SYMBOL(drm_gem_ttm_print_info); diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 797200315854..2a1229b8364e 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -17,6 +17,8 @@ #include <drm/drm_prime.h> #include <drm/drm_simple_kms_helper.h> +#include <drm/ttm/ttm_range_manager.h> + static const struct drm_gem_object_funcs drm_gem_vram_object_funcs; /** @@ -248,10 +250,11 @@ EXPORT_SYMBOL(drm_gem_vram_put); static u64 drm_gem_vram_pg_offset(struct drm_gem_vram_object *gbo) { /* Keep TTM behavior for now, remove when drivers are audited */ - if (WARN_ON_ONCE(!gbo->bo.mem.mm_node)) + if (WARN_ON_ONCE(!gbo->bo.resource || + gbo->bo.resource->mem_type == TTM_PL_SYSTEM)) return 0; - return gbo->bo.mem.start; + return gbo->bo.resource->start; } /** diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index db69f19ab5bc..b8fa6ed3dd73 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -390,14 +390,12 @@ int etnaviv_gem_cpu_prep(struct drm_gem_object *obj, u32 op, } if (op & ETNA_PREP_NOSYNC) { - if (!dma_resv_test_signaled_rcu(obj->resv, - write)) + if (!dma_resv_test_signaled(obj->resv, write)) return -EBUSY; } else { unsigned long remain = etnaviv_timeout_to_jiffies(timeout); - ret = dma_resv_wait_timeout_rcu(obj->resv, - write, true, remain); + ret = dma_resv_wait_timeout(obj->resv, write, true, remain); if (ret <= 0) return ret == 0 ? -ETIMEDOUT : ret; } @@ -461,7 +459,7 @@ static void etnaviv_gem_describe(struct drm_gem_object *obj, struct seq_file *m) off, etnaviv_obj->vaddr, obj->size); rcu_read_lock(); - fobj = rcu_dereference(robj->fence); + fobj = dma_resv_shared_list(robj); if (fobj) { unsigned int i, shared_count = fobj->shared_count; @@ -471,7 +469,7 @@ static void etnaviv_gem_describe(struct drm_gem_object *obj, struct seq_file *m) } } - fence = rcu_dereference(robj->fence_excl); + fence = dma_resv_excl_fence(robj); if (fence) etnaviv_gem_describe_fence(fence, "Exclusive", m); rcu_read_unlock(); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index d05c35994579..d53856d7a747 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -189,13 +189,13 @@ static int submit_fence_sync(struct etnaviv_gem_submit *submit) continue; if (bo->flags & ETNA_SUBMIT_BO_WRITE) { - ret = dma_resv_get_fences_rcu(robj, &bo->excl, - &bo->nr_shared, - &bo->shared); + ret = dma_resv_get_fences(robj, &bo->excl, + &bo->nr_shared, + &bo->shared); if (ret) return ret; } else { - bo->excl = dma_resv_get_excl_rcu(robj); + bo->excl = dma_resv_get_excl_unlocked(robj); } } diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c index 431c5d32f9a4..9b5e6f94e558 100644 --- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c @@ -344,7 +344,7 @@ static void decon_win_set_colkey(struct decon_context *ctx, unsigned int win) } /** - * shadow_protect_win() - disable updating values from shadow registers at vsync + * decon_shadow_protect_win() - disable updating values from shadow registers at vsync * * @ctx: display and enhancement controller context * @win: window to protect registers for diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c index 4f2b7551b251..9ae868935357 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c +++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c @@ -88,7 +88,7 @@ void exynos_drm_ipp_unregister(struct device *dev, } /** - * exynos_drm_ipp_ioctl_get_res_ioctl - enumerate all ipp modules + * exynos_drm_ipp_get_res_ioctl - enumerate all ipp modules * @dev: DRM device * @data: ioctl data * @file_priv: DRM file info @@ -136,7 +136,7 @@ static inline struct exynos_drm_ipp *__ipp_get(uint32_t id) } /** - * exynos_drm_ipp_ioctl_get_caps - get ipp module capabilities and formats + * exynos_drm_ipp_get_caps_ioctl - get ipp module capabilities and formats * @dev: DRM device * @data: ioctl data * @file_priv: DRM file info diff --git a/drivers/gpu/drm/hyperv/Makefile b/drivers/gpu/drm/hyperv/Makefile new file mode 100644 index 000000000000..265f12f2c660 --- /dev/null +++ b/drivers/gpu/drm/hyperv/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only + +hyperv_drm-y := \ + hyperv_drm_drv.o \ + hyperv_drm_modeset.o \ + hyperv_drm_proto.o + +obj-$(CONFIG_DRM_HYPERV) += hyperv_drm.o diff --git a/drivers/gpu/drm/hyperv/hyperv_drm.h b/drivers/gpu/drm/hyperv/hyperv_drm.h new file mode 100644 index 000000000000..886add4f9cd0 --- /dev/null +++ b/drivers/gpu/drm/hyperv/hyperv_drm.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2021 Microsoft + */ + +#ifndef _HYPERV_DRM_H_ +#define _HYPERV_DRM_H_ + +#define VMBUS_MAX_PACKET_SIZE 0x4000 + +struct hyperv_drm_device { + /* drm */ + struct drm_device dev; + struct drm_simple_display_pipe pipe; + struct drm_connector connector; + + /* mode */ + u32 screen_width_max; + u32 screen_height_max; + u32 preferred_width; + u32 preferred_height; + u32 screen_depth; + + /* hw */ + struct resource *mem; + void __iomem *vram; + unsigned long fb_base; + unsigned long fb_size; + struct completion wait; + u32 synthvid_version; + u32 mmio_megabytes; + bool dirt_needed; + + u8 init_buf[VMBUS_MAX_PACKET_SIZE]; + u8 recv_buf[VMBUS_MAX_PACKET_SIZE]; + + struct hv_device *hdev; +}; + +#define to_hv(_dev) container_of(_dev, struct hyperv_drm_device, dev) + +/* hyperv_drm_modeset */ +int hyperv_mode_config_init(struct hyperv_drm_device *hv); + +/* hyperv_drm_proto */ +int hyperv_update_vram_location(struct hv_device *hdev, phys_addr_t vram_pp); +int hyperv_update_situation(struct hv_device *hdev, u8 active, u32 bpp, + u32 w, u32 h, u32 pitch); +int hyperv_update_dirt(struct hv_device *hdev, struct drm_rect *rect); +int hyperv_connect_vsp(struct hv_device *hdev); + +#endif diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c new file mode 100644 index 000000000000..eb06c92c4bfd --- /dev/null +++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c @@ -0,0 +1,311 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2021 Microsoft + */ + +#include <linux/efi.h> +#include <linux/hyperv.h> +#include <linux/module.h> +#include <linux/pci.h> + +#include <drm/drm_aperture.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_drv.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_simple_kms_helper.h> + +#include "hyperv_drm.h" + +#define DRIVER_NAME "hyperv_drm" +#define DRIVER_DESC "DRM driver for Hyper-V synthetic video device" +#define DRIVER_DATE "2020" +#define DRIVER_MAJOR 1 +#define DRIVER_MINOR 0 + +#define PCI_VENDOR_ID_MICROSOFT 0x1414 +#define PCI_DEVICE_ID_HYPERV_VIDEO 0x5353 + +DEFINE_DRM_GEM_FOPS(hv_fops); + +static struct drm_driver hyperv_driver = { + .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_ATOMIC, + + .name = DRIVER_NAME, + .desc = DRIVER_DESC, + .date = DRIVER_DATE, + .major = DRIVER_MAJOR, + .minor = DRIVER_MINOR, + + .fops = &hv_fops, + DRM_GEM_SHMEM_DRIVER_OPS, +}; + +static int hyperv_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + return 0; +} + +static void hyperv_pci_remove(struct pci_dev *pdev) +{ +} + +static const struct pci_device_id hyperv_pci_tbl[] = { + { + .vendor = PCI_VENDOR_ID_MICROSOFT, + .device = PCI_DEVICE_ID_HYPERV_VIDEO, + }, + { /* end of list */ } +}; + +/* + * PCI stub to support gen1 VM. + */ +static struct pci_driver hyperv_pci_driver = { + .name = KBUILD_MODNAME, + .id_table = hyperv_pci_tbl, + .probe = hyperv_pci_probe, + .remove = hyperv_pci_remove, +}; + +static int hyperv_setup_gen1(struct hyperv_drm_device *hv) +{ + struct drm_device *dev = &hv->dev; + struct pci_dev *pdev; + int ret; + + pdev = pci_get_device(PCI_VENDOR_ID_MICROSOFT, + PCI_DEVICE_ID_HYPERV_VIDEO, NULL); + if (!pdev) { + drm_err(dev, "Unable to find PCI Hyper-V video\n"); + return -ENODEV; + } + + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "hypervdrmfb"); + if (ret) { + drm_err(dev, "Not able to remove boot fb\n"); + return ret; + } + + if (pci_request_region(pdev, 0, DRIVER_NAME) != 0) + drm_warn(dev, "Cannot request framebuffer, boot fb still active?\n"); + + if ((pdev->resource[0].flags & IORESOURCE_MEM) == 0) { + drm_err(dev, "Resource at bar 0 is not IORESOURCE_MEM\n"); + ret = -ENODEV; + goto error; + } + + hv->fb_base = pci_resource_start(pdev, 0); + hv->fb_size = pci_resource_len(pdev, 0); + if (!hv->fb_base) { + drm_err(dev, "Resource not available\n"); + ret = -ENODEV; + goto error; + } + + hv->fb_size = min(hv->fb_size, + (unsigned long)(hv->mmio_megabytes * 1024 * 1024)); + hv->vram = devm_ioremap(&pdev->dev, hv->fb_base, hv->fb_size); + if (!hv->vram) { + drm_err(dev, "Failed to map vram\n"); + ret = -ENOMEM; + } + +error: + pci_dev_put(pdev); + return ret; +} + +static int hyperv_setup_gen2(struct hyperv_drm_device *hv, + struct hv_device *hdev) +{ + struct drm_device *dev = &hv->dev; + int ret; + + drm_aperture_remove_conflicting_framebuffers(screen_info.lfb_base, + screen_info.lfb_size, + false, + "hypervdrmfb"); + + hv->fb_size = (unsigned long)hv->mmio_megabytes * 1024 * 1024; + + ret = vmbus_allocate_mmio(&hv->mem, hdev, 0, -1, hv->fb_size, 0x100000, + true); + if (ret) { + drm_err(dev, "Failed to allocate mmio\n"); + return -ENOMEM; + } + + /* + * Map the VRAM cacheable for performance. This is also required for VM + * connect to display properly for ARM64 Linux VM, as the host also maps + * the VRAM cacheable. + */ + hv->vram = ioremap_cache(hv->mem->start, hv->fb_size); + if (!hv->vram) { + drm_err(dev, "Failed to map vram\n"); + ret = -ENOMEM; + goto error; + } + + hv->fb_base = hv->mem->start; + return 0; + +error: + vmbus_free_mmio(hv->mem->start, hv->fb_size); + return ret; +} + +static int hyperv_vmbus_probe(struct hv_device *hdev, + const struct hv_vmbus_device_id *dev_id) +{ + struct hyperv_drm_device *hv; + struct drm_device *dev; + int ret; + + hv = devm_drm_dev_alloc(&hdev->device, &hyperv_driver, + struct hyperv_drm_device, dev); + if (IS_ERR(hv)) + return PTR_ERR(hv); + + dev = &hv->dev; + init_completion(&hv->wait); + hv_set_drvdata(hdev, hv); + hv->hdev = hdev; + + ret = hyperv_connect_vsp(hdev); + if (ret) { + drm_err(dev, "Failed to connect to vmbus.\n"); + goto err_hv_set_drv_data; + } + + if (efi_enabled(EFI_BOOT)) + ret = hyperv_setup_gen2(hv, hdev); + else + ret = hyperv_setup_gen1(hv); + + if (ret) + goto err_vmbus_close; + + /* + * Should be done only once during init and resume. Failing to update + * vram location is not fatal. Device will update dirty area till + * preferred resolution only. + */ + ret = hyperv_update_vram_location(hdev, hv->fb_base); + if (ret) + drm_warn(dev, "Failed to update vram location.\n"); + + hv->dirt_needed = true; + + ret = hyperv_mode_config_init(hv); + if (ret) + goto err_vmbus_close; + + ret = drm_dev_register(dev, 0); + if (ret) { + drm_err(dev, "Failed to register drm driver.\n"); + goto err_vmbus_close; + } + + drm_fbdev_generic_setup(dev, 0); + + return 0; + +err_vmbus_close: + vmbus_close(hdev->channel); +err_hv_set_drv_data: + hv_set_drvdata(hdev, NULL); + return ret; +} + +static int hyperv_vmbus_remove(struct hv_device *hdev) +{ + struct drm_device *dev = hv_get_drvdata(hdev); + struct hyperv_drm_device *hv = to_hv(dev); + + drm_dev_unplug(dev); + drm_atomic_helper_shutdown(dev); + vmbus_close(hdev->channel); + hv_set_drvdata(hdev, NULL); + vmbus_free_mmio(hv->mem->start, hv->fb_size); + + return 0; +} + +static int hyperv_vmbus_suspend(struct hv_device *hdev) +{ + struct drm_device *dev = hv_get_drvdata(hdev); + int ret; + + ret = drm_mode_config_helper_suspend(dev); + if (ret) + return ret; + + vmbus_close(hdev->channel); + + return 0; +} + +static int hyperv_vmbus_resume(struct hv_device *hdev) +{ + struct drm_device *dev = hv_get_drvdata(hdev); + struct hyperv_drm_device *hv = to_hv(dev); + int ret; + + ret = hyperv_connect_vsp(hdev); + if (ret) + return ret; + + ret = hyperv_update_vram_location(hdev, hv->fb_base); + if (ret) + return ret; + + return drm_mode_config_helper_resume(dev); +} + +static const struct hv_vmbus_device_id hyperv_vmbus_tbl[] = { + /* Synthetic Video Device GUID */ + {HV_SYNTHVID_GUID}, + {} +}; + +static struct hv_driver hyperv_hv_driver = { + .name = KBUILD_MODNAME, + .id_table = hyperv_vmbus_tbl, + .probe = hyperv_vmbus_probe, + .remove = hyperv_vmbus_remove, + .suspend = hyperv_vmbus_suspend, + .resume = hyperv_vmbus_resume, + .driver = { + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, +}; + +static int __init hyperv_init(void) +{ + int ret; + + ret = pci_register_driver(&hyperv_pci_driver); + if (ret != 0) + return ret; + + return vmbus_driver_register(&hyperv_hv_driver); +} + +static void __exit hyperv_exit(void) +{ + vmbus_driver_unregister(&hyperv_hv_driver); + pci_unregister_driver(&hyperv_pci_driver); +} + +module_init(hyperv_init); +module_exit(hyperv_exit); + +MODULE_DEVICE_TABLE(pci, hyperv_pci_tbl); +MODULE_DEVICE_TABLE(vmbus, hyperv_vmbus_tbl); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Deepak Rawat <drawat.floss@gmail.com>"); +MODULE_DESCRIPTION("DRM driver for Hyper-V synthetic video device"); diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c b/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c new file mode 100644 index 000000000000..02718e3e859e --- /dev/null +++ b/drivers/gpu/drm/hyperv/hyperv_drm_modeset.c @@ -0,0 +1,231 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2021 Microsoft + */ + +#include <linux/hyperv.h> + +#include <drm/drm_damage_helper.h> +#include <drm/drm_drv.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_format_helper.h> +#include <drm/drm_fourcc.h> +#include <drm/drm_gem_atomic_helper.h> +#include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_probe_helper.h> +#include <drm/drm_simple_kms_helper.h> + +#include "hyperv_drm.h" + +static int hyperv_blit_to_vram_rect(struct drm_framebuffer *fb, + const struct dma_buf_map *map, + struct drm_rect *rect) +{ + struct hyperv_drm_device *hv = to_hv(fb->dev); + void *vmap = map->vaddr; /* TODO: Use mapping abstraction properly */ + int idx; + + if (!drm_dev_enter(&hv->dev, &idx)) + return -ENODEV; + + drm_fb_memcpy_dstclip(hv->vram, fb->pitches[0], vmap, fb, rect); + drm_dev_exit(idx); + + return 0; +} + +static int hyperv_blit_to_vram_fullscreen(struct drm_framebuffer *fb, const struct dma_buf_map *map) +{ + struct drm_rect fullscreen = { + .x1 = 0, + .x2 = fb->width, + .y1 = 0, + .y2 = fb->height, + }; + return hyperv_blit_to_vram_rect(fb, map, &fullscreen); +} + +static int hyperv_connector_get_modes(struct drm_connector *connector) +{ + struct hyperv_drm_device *hv = to_hv(connector->dev); + int count; + + count = drm_add_modes_noedid(connector, + connector->dev->mode_config.max_width, + connector->dev->mode_config.max_height); + drm_set_preferred_mode(connector, hv->preferred_width, + hv->preferred_height); + + return count; +} + +static const struct drm_connector_helper_funcs hyperv_connector_helper_funcs = { + .get_modes = hyperv_connector_get_modes, +}; + +static const struct drm_connector_funcs hyperv_connector_funcs = { + .fill_modes = drm_helper_probe_single_connector_modes, + .destroy = drm_connector_cleanup, + .reset = drm_atomic_helper_connector_reset, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, +}; + +static inline int hyperv_conn_init(struct hyperv_drm_device *hv) +{ + drm_connector_helper_add(&hv->connector, &hyperv_connector_helper_funcs); + return drm_connector_init(&hv->dev, &hv->connector, + &hyperv_connector_funcs, + DRM_MODE_CONNECTOR_VIRTUAL); +} + +static int hyperv_check_size(struct hyperv_drm_device *hv, int w, int h, + struct drm_framebuffer *fb) +{ + u32 pitch = w * (hv->screen_depth / 8); + + if (fb) + pitch = fb->pitches[0]; + + if (pitch * h > hv->fb_size) + return -EINVAL; + + return 0; +} + +static void hyperv_pipe_enable(struct drm_simple_display_pipe *pipe, + struct drm_crtc_state *crtc_state, + struct drm_plane_state *plane_state) +{ + struct hyperv_drm_device *hv = to_hv(pipe->crtc.dev); + struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(plane_state); + + hyperv_update_situation(hv->hdev, 1, hv->screen_depth, + crtc_state->mode.hdisplay, + crtc_state->mode.vdisplay, + plane_state->fb->pitches[0]); + hyperv_blit_to_vram_fullscreen(plane_state->fb, &shadow_plane_state->map[0]); +} + +static int hyperv_pipe_check(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *plane_state, + struct drm_crtc_state *crtc_state) +{ + struct hyperv_drm_device *hv = to_hv(pipe->crtc.dev); + struct drm_framebuffer *fb = plane_state->fb; + + if (fb->format->format != DRM_FORMAT_XRGB8888) + return -EINVAL; + + if (fb->pitches[0] * fb->height > hv->fb_size) + return -EINVAL; + + return 0; +} + +static void hyperv_pipe_update(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *old_state) +{ + struct hyperv_drm_device *hv = to_hv(pipe->crtc.dev); + struct drm_plane_state *state = pipe->plane.state; + struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(state); + struct drm_rect rect; + + if (drm_atomic_helper_damage_merged(old_state, state, &rect)) { + hyperv_blit_to_vram_rect(state->fb, &shadow_plane_state->map[0], &rect); + hyperv_update_dirt(hv->hdev, &rect); + } +} + +static const struct drm_simple_display_pipe_funcs hyperv_pipe_funcs = { + .enable = hyperv_pipe_enable, + .check = hyperv_pipe_check, + .update = hyperv_pipe_update, + DRM_GEM_SIMPLE_DISPLAY_PIPE_SHADOW_PLANE_FUNCS, +}; + +static const uint32_t hyperv_formats[] = { + DRM_FORMAT_XRGB8888, +}; + +static const uint64_t hyperv_modifiers[] = { + DRM_FORMAT_MOD_LINEAR, + DRM_FORMAT_MOD_INVALID +}; + +static inline int hyperv_pipe_init(struct hyperv_drm_device *hv) +{ + int ret; + + ret = drm_simple_display_pipe_init(&hv->dev, + &hv->pipe, + &hyperv_pipe_funcs, + hyperv_formats, + ARRAY_SIZE(hyperv_formats), + NULL, + &hv->connector); + if (ret) + return ret; + + drm_plane_enable_fb_damage_clips(&hv->pipe.plane); + + return 0; +} + +static enum drm_mode_status +hyperv_mode_valid(struct drm_device *dev, + const struct drm_display_mode *mode) +{ + struct hyperv_drm_device *hv = to_hv(dev); + + if (hyperv_check_size(hv, mode->hdisplay, mode->vdisplay, NULL)) + return MODE_BAD; + + return MODE_OK; +} + +static const struct drm_mode_config_funcs hyperv_mode_config_funcs = { + .fb_create = drm_gem_fb_create_with_dirty, + .mode_valid = hyperv_mode_valid, + .atomic_check = drm_atomic_helper_check, + .atomic_commit = drm_atomic_helper_commit, +}; + +int hyperv_mode_config_init(struct hyperv_drm_device *hv) +{ + struct drm_device *dev = &hv->dev; + int ret; + + ret = drmm_mode_config_init(dev); + if (ret) { + drm_err(dev, "Failed to initialized mode setting.\n"); + return ret; + } + + dev->mode_config.min_width = 0; + dev->mode_config.min_height = 0; + dev->mode_config.max_width = hv->screen_width_max; + dev->mode_config.max_height = hv->screen_height_max; + + dev->mode_config.preferred_depth = hv->screen_depth; + dev->mode_config.prefer_shadow = 0; + + dev->mode_config.funcs = &hyperv_mode_config_funcs; + + ret = hyperv_conn_init(hv); + if (ret) { + drm_err(dev, "Failed to initialized connector.\n"); + return ret; + } + + ret = hyperv_pipe_init(hv); + if (ret) { + drm_err(dev, "Failed to initialized pipe.\n"); + return ret; + } + + drm_mode_config_reset(dev); + + return 0; +} diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_proto.c b/drivers/gpu/drm/hyperv/hyperv_drm_proto.c new file mode 100644 index 000000000000..6d4bdccfbd1a --- /dev/null +++ b/drivers/gpu/drm/hyperv/hyperv_drm_proto.c @@ -0,0 +1,485 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2021 Microsoft + * + * Portions of this code is derived from hyperv_fb.c + */ + +#include <linux/hyperv.h> + +#include <drm/drm_print.h> +#include <drm/drm_simple_kms_helper.h> + +#include "hyperv_drm.h" + +#define VMBUS_RING_BUFSIZE (256 * 1024) +#define VMBUS_VSP_TIMEOUT (10 * HZ) + +#define SYNTHVID_VERSION(major, minor) ((minor) << 16 | (major)) +#define SYNTHVID_VER_GET_MAJOR(ver) (ver & 0x0000ffff) +#define SYNTHVID_VER_GET_MINOR(ver) ((ver & 0xffff0000) >> 16) +#define SYNTHVID_VERSION_WIN7 SYNTHVID_VERSION(3, 0) +#define SYNTHVID_VERSION_WIN8 SYNTHVID_VERSION(3, 2) +#define SYNTHVID_VERSION_WIN10 SYNTHVID_VERSION(3, 5) + +#define SYNTHVID_DEPTH_WIN7 16 +#define SYNTHVID_DEPTH_WIN8 32 +#define SYNTHVID_FB_SIZE_WIN7 (4 * 1024 * 1024) +#define SYNTHVID_FB_SIZE_WIN8 (8 * 1024 * 1024) +#define SYNTHVID_WIDTH_MAX_WIN7 1600 +#define SYNTHVID_HEIGHT_MAX_WIN7 1200 + +enum pipe_msg_type { + PIPE_MSG_INVALID, + PIPE_MSG_DATA, + PIPE_MSG_MAX +}; + +enum synthvid_msg_type { + SYNTHVID_ERROR = 0, + SYNTHVID_VERSION_REQUEST = 1, + SYNTHVID_VERSION_RESPONSE = 2, + SYNTHVID_VRAM_LOCATION = 3, + SYNTHVID_VRAM_LOCATION_ACK = 4, + SYNTHVID_SITUATION_UPDATE = 5, + SYNTHVID_SITUATION_UPDATE_ACK = 6, + SYNTHVID_POINTER_POSITION = 7, + SYNTHVID_POINTER_SHAPE = 8, + SYNTHVID_FEATURE_CHANGE = 9, + SYNTHVID_DIRT = 10, + SYNTHVID_RESOLUTION_REQUEST = 13, + SYNTHVID_RESOLUTION_RESPONSE = 14, + + SYNTHVID_MAX = 15 +}; + +struct pipe_msg_hdr { + u32 type; + u32 size; /* size of message after this field */ +} __packed; + +struct hvd_screen_info { + u16 width; + u16 height; +} __packed; + +struct synthvid_msg_hdr { + u32 type; + u32 size; /* size of this header + payload after this field */ +} __packed; + +struct synthvid_version_req { + u32 version; +} __packed; + +struct synthvid_version_resp { + u32 version; + u8 is_accepted; + u8 max_video_outputs; +} __packed; + +struct synthvid_vram_location { + u64 user_ctx; + u8 is_vram_gpa_specified; + u64 vram_gpa; +} __packed; + +struct synthvid_vram_location_ack { + u64 user_ctx; +} __packed; + +struct video_output_situation { + u8 active; + u32 vram_offset; + u8 depth_bits; + u32 width_pixels; + u32 height_pixels; + u32 pitch_bytes; +} __packed; + +struct synthvid_situation_update { + u64 user_ctx; + u8 video_output_count; + struct video_output_situation video_output[1]; +} __packed; + +struct synthvid_situation_update_ack { + u64 user_ctx; +} __packed; + +struct synthvid_pointer_position { + u8 is_visible; + u8 video_output; + s32 image_x; + s32 image_y; +} __packed; + +#define SYNTHVID_CURSOR_MAX_X 96 +#define SYNTHVID_CURSOR_MAX_Y 96 +#define SYNTHVID_CURSOR_ARGB_PIXEL_SIZE 4 +#define SYNTHVID_CURSOR_MAX_SIZE (SYNTHVID_CURSOR_MAX_X * \ + SYNTHVID_CURSOR_MAX_Y * SYNTHVID_CURSOR_ARGB_PIXEL_SIZE) +#define SYNTHVID_CURSOR_COMPLETE (-1) + +struct synthvid_pointer_shape { + u8 part_idx; + u8 is_argb; + u32 width; /* SYNTHVID_CURSOR_MAX_X at most */ + u32 height; /* SYNTHVID_CURSOR_MAX_Y at most */ + u32 hot_x; /* hotspot relative to upper-left of pointer image */ + u32 hot_y; + u8 data[4]; +} __packed; + +struct synthvid_feature_change { + u8 is_dirt_needed; + u8 is_ptr_pos_needed; + u8 is_ptr_shape_needed; + u8 is_situ_needed; +} __packed; + +struct rect { + s32 x1, y1; /* top left corner */ + s32 x2, y2; /* bottom right corner, exclusive */ +} __packed; + +struct synthvid_dirt { + u8 video_output; + u8 dirt_count; + struct rect rect[1]; +} __packed; + +#define SYNTHVID_EDID_BLOCK_SIZE 128 +#define SYNTHVID_MAX_RESOLUTION_COUNT 64 + +struct synthvid_supported_resolution_req { + u8 maximum_resolution_count; +} __packed; + +struct synthvid_supported_resolution_resp { + u8 edid_block[SYNTHVID_EDID_BLOCK_SIZE]; + u8 resolution_count; + u8 default_resolution_index; + u8 is_standard; + struct hvd_screen_info supported_resolution[SYNTHVID_MAX_RESOLUTION_COUNT]; +} __packed; + +struct synthvid_msg { + struct pipe_msg_hdr pipe_hdr; + struct synthvid_msg_hdr vid_hdr; + union { + struct synthvid_version_req ver_req; + struct synthvid_version_resp ver_resp; + struct synthvid_vram_location vram; + struct synthvid_vram_location_ack vram_ack; + struct synthvid_situation_update situ; + struct synthvid_situation_update_ack situ_ack; + struct synthvid_pointer_position ptr_pos; + struct synthvid_pointer_shape ptr_shape; + struct synthvid_feature_change feature_chg; + struct synthvid_dirt dirt; + struct synthvid_supported_resolution_req resolution_req; + struct synthvid_supported_resolution_resp resolution_resp; + }; +} __packed; + +static inline bool hyperv_version_ge(u32 ver1, u32 ver2) +{ + if (SYNTHVID_VER_GET_MAJOR(ver1) > SYNTHVID_VER_GET_MAJOR(ver2) || + (SYNTHVID_VER_GET_MAJOR(ver1) == SYNTHVID_VER_GET_MAJOR(ver2) && + SYNTHVID_VER_GET_MINOR(ver1) >= SYNTHVID_VER_GET_MINOR(ver2))) + return true; + + return false; +} + +static inline int hyperv_sendpacket(struct hv_device *hdev, struct synthvid_msg *msg) +{ + static atomic64_t request_id = ATOMIC64_INIT(0); + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + int ret; + + msg->pipe_hdr.type = PIPE_MSG_DATA; + msg->pipe_hdr.size = msg->vid_hdr.size; + + ret = vmbus_sendpacket(hdev->channel, msg, + msg->vid_hdr.size + sizeof(struct pipe_msg_hdr), + atomic64_inc_return(&request_id), + VM_PKT_DATA_INBAND, 0); + + if (ret) + drm_err(&hv->dev, "Unable to send packet via vmbus\n"); + + return ret; +} + +static int hyperv_negotiate_version(struct hv_device *hdev, u32 ver) +{ + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + struct synthvid_msg *msg = (struct synthvid_msg *)hv->init_buf; + struct drm_device *dev = &hv->dev; + unsigned long t; + + memset(msg, 0, sizeof(struct synthvid_msg)); + msg->vid_hdr.type = SYNTHVID_VERSION_REQUEST; + msg->vid_hdr.size = sizeof(struct synthvid_msg_hdr) + + sizeof(struct synthvid_version_req); + msg->ver_req.version = ver; + hyperv_sendpacket(hdev, msg); + + t = wait_for_completion_timeout(&hv->wait, VMBUS_VSP_TIMEOUT); + if (!t) { + drm_err(dev, "Time out on waiting version response\n"); + return -ETIMEDOUT; + } + + if (!msg->ver_resp.is_accepted) { + drm_err(dev, "Version request not accepted\n"); + return -ENODEV; + } + + hv->synthvid_version = ver; + drm_info(dev, "Synthvid Version major %d, minor %d\n", + SYNTHVID_VER_GET_MAJOR(ver), SYNTHVID_VER_GET_MINOR(ver)); + + return 0; +} + +int hyperv_update_vram_location(struct hv_device *hdev, phys_addr_t vram_pp) +{ + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + struct synthvid_msg *msg = (struct synthvid_msg *)hv->init_buf; + struct drm_device *dev = &hv->dev; + unsigned long t; + + memset(msg, 0, sizeof(struct synthvid_msg)); + msg->vid_hdr.type = SYNTHVID_VRAM_LOCATION; + msg->vid_hdr.size = sizeof(struct synthvid_msg_hdr) + + sizeof(struct synthvid_vram_location); + msg->vram.user_ctx = vram_pp; + msg->vram.vram_gpa = vram_pp; + msg->vram.is_vram_gpa_specified = 1; + hyperv_sendpacket(hdev, msg); + + t = wait_for_completion_timeout(&hv->wait, VMBUS_VSP_TIMEOUT); + if (!t) { + drm_err(dev, "Time out on waiting vram location ack\n"); + return -ETIMEDOUT; + } + if (msg->vram_ack.user_ctx != vram_pp) { + drm_err(dev, "Unable to set VRAM location\n"); + return -ENODEV; + } + + return 0; +} + +int hyperv_update_situation(struct hv_device *hdev, u8 active, u32 bpp, + u32 w, u32 h, u32 pitch) +{ + struct synthvid_msg msg; + + memset(&msg, 0, sizeof(struct synthvid_msg)); + + msg.vid_hdr.type = SYNTHVID_SITUATION_UPDATE; + msg.vid_hdr.size = sizeof(struct synthvid_msg_hdr) + + sizeof(struct synthvid_situation_update); + msg.situ.user_ctx = 0; + msg.situ.video_output_count = 1; + msg.situ.video_output[0].active = active; + /* vram_offset should always be 0 */ + msg.situ.video_output[0].vram_offset = 0; + msg.situ.video_output[0].depth_bits = bpp; + msg.situ.video_output[0].width_pixels = w; + msg.situ.video_output[0].height_pixels = h; + msg.situ.video_output[0].pitch_bytes = pitch; + + hyperv_sendpacket(hdev, &msg); + + return 0; +} + +int hyperv_update_dirt(struct hv_device *hdev, struct drm_rect *rect) +{ + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + struct synthvid_msg msg; + + if (!hv->dirt_needed) + return 0; + + memset(&msg, 0, sizeof(struct synthvid_msg)); + + msg.vid_hdr.type = SYNTHVID_DIRT; + msg.vid_hdr.size = sizeof(struct synthvid_msg_hdr) + + sizeof(struct synthvid_dirt); + msg.dirt.video_output = 0; + msg.dirt.dirt_count = 1; + msg.dirt.rect[0].x1 = rect->x1; + msg.dirt.rect[0].y1 = rect->y1; + msg.dirt.rect[0].x2 = rect->x2; + msg.dirt.rect[0].y2 = rect->y2; + + hyperv_sendpacket(hdev, &msg); + + return 0; +} + +static int hyperv_get_supported_resolution(struct hv_device *hdev) +{ + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + struct synthvid_msg *msg = (struct synthvid_msg *)hv->init_buf; + struct drm_device *dev = &hv->dev; + unsigned long t; + u8 index; + int i; + + memset(msg, 0, sizeof(struct synthvid_msg)); + msg->vid_hdr.type = SYNTHVID_RESOLUTION_REQUEST; + msg->vid_hdr.size = sizeof(struct synthvid_msg_hdr) + + sizeof(struct synthvid_supported_resolution_req); + msg->resolution_req.maximum_resolution_count = + SYNTHVID_MAX_RESOLUTION_COUNT; + hyperv_sendpacket(hdev, msg); + + t = wait_for_completion_timeout(&hv->wait, VMBUS_VSP_TIMEOUT); + if (!t) { + drm_err(dev, "Time out on waiting resolution response\n"); + return -ETIMEDOUT; + } + + if (msg->resolution_resp.resolution_count == 0) { + drm_err(dev, "No supported resolutions\n"); + return -ENODEV; + } + + index = msg->resolution_resp.default_resolution_index; + if (index >= msg->resolution_resp.resolution_count) { + drm_err(dev, "Invalid resolution index: %d\n", index); + return -ENODEV; + } + + for (i = 0; i < msg->resolution_resp.resolution_count; i++) { + hv->screen_width_max = max_t(u32, hv->screen_width_max, + msg->resolution_resp.supported_resolution[i].width); + hv->screen_height_max = max_t(u32, hv->screen_height_max, + msg->resolution_resp.supported_resolution[i].height); + } + + hv->preferred_width = + msg->resolution_resp.supported_resolution[index].width; + hv->preferred_height = + msg->resolution_resp.supported_resolution[index].height; + + return 0; +} + +static void hyperv_receive_sub(struct hv_device *hdev) +{ + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + struct synthvid_msg *msg; + + if (!hv) + return; + + msg = (struct synthvid_msg *)hv->recv_buf; + + /* Complete the wait event */ + if (msg->vid_hdr.type == SYNTHVID_VERSION_RESPONSE || + msg->vid_hdr.type == SYNTHVID_RESOLUTION_RESPONSE || + msg->vid_hdr.type == SYNTHVID_VRAM_LOCATION_ACK) { + memcpy(hv->init_buf, msg, VMBUS_MAX_PACKET_SIZE); + complete(&hv->wait); + return; + } + + if (msg->vid_hdr.type == SYNTHVID_FEATURE_CHANGE) + hv->dirt_needed = msg->feature_chg.is_dirt_needed; +} + +static void hyperv_receive(void *ctx) +{ + struct hv_device *hdev = ctx; + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + struct synthvid_msg *recv_buf; + u32 bytes_recvd; + u64 req_id; + int ret; + + if (!hv) + return; + + recv_buf = (struct synthvid_msg *)hv->recv_buf; + + do { + ret = vmbus_recvpacket(hdev->channel, recv_buf, + VMBUS_MAX_PACKET_SIZE, + &bytes_recvd, &req_id); + if (bytes_recvd > 0 && + recv_buf->pipe_hdr.type == PIPE_MSG_DATA) + hyperv_receive_sub(hdev); + } while (bytes_recvd > 0 && ret == 0); +} + +int hyperv_connect_vsp(struct hv_device *hdev) +{ + struct hyperv_drm_device *hv = hv_get_drvdata(hdev); + struct drm_device *dev = &hv->dev; + int ret; + + ret = vmbus_open(hdev->channel, VMBUS_RING_BUFSIZE, VMBUS_RING_BUFSIZE, + NULL, 0, hyperv_receive, hdev); + if (ret) { + drm_err(dev, "Unable to open vmbus channel\n"); + return ret; + } + + /* Negotiate the protocol version with host */ + switch (vmbus_proto_version) { + case VERSION_WIN10: + case VERSION_WIN10_V5: + ret = hyperv_negotiate_version(hdev, SYNTHVID_VERSION_WIN10); + if (!ret) + break; + fallthrough; + case VERSION_WIN8: + case VERSION_WIN8_1: + ret = hyperv_negotiate_version(hdev, SYNTHVID_VERSION_WIN8); + if (!ret) + break; + fallthrough; + case VERSION_WS2008: + case VERSION_WIN7: + ret = hyperv_negotiate_version(hdev, SYNTHVID_VERSION_WIN7); + break; + default: + ret = hyperv_negotiate_version(hdev, SYNTHVID_VERSION_WIN10); + break; + } + + if (ret) { + drm_err(dev, "Synthetic video device version not accepted %d\n", ret); + goto error; + } + + if (hv->synthvid_version == SYNTHVID_VERSION_WIN7) + hv->screen_depth = SYNTHVID_DEPTH_WIN7; + else + hv->screen_depth = SYNTHVID_DEPTH_WIN8; + + if (hyperv_version_ge(hv->synthvid_version, SYNTHVID_VERSION_WIN10)) { + ret = hyperv_get_supported_resolution(hdev); + if (ret) + drm_err(dev, "Failed to get supported resolution from host, use default\n"); + } else { + hv->screen_width_max = SYNTHVID_WIDTH_MAX_WIN7; + hv->screen_height_max = SYNTHVID_HEIGHT_MAX_WIN7; + } + + hv->mmio_megabytes = hdev->channel->offermsg.offer.mmio_megabytes; + + return 0; + +error: + vmbus_close(hdev->channel); + return ret; +} diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 422b59ebf6dc..5f0b85a10215 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -11040,7 +11040,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane, if (ret < 0) goto unpin_fb; - fence = dma_resv_get_excl_rcu(obj->base.resv); + fence = dma_resv_get_excl_unlocked(obj->base.resv); if (fence) { add_rps_boost_after_vblank(new_plane_state->hw.crtc, fence); diff --git a/drivers/gpu/drm/i915/dma_resv_utils.c b/drivers/gpu/drm/i915/dma_resv_utils.c index 9e508e7d4629..7df91b7e4ca8 100644 --- a/drivers/gpu/drm/i915/dma_resv_utils.c +++ b/drivers/gpu/drm/i915/dma_resv_utils.c @@ -10,7 +10,7 @@ void dma_resv_prune(struct dma_resv *resv) { if (dma_resv_trylock(resv)) { - if (dma_resv_test_signaled_rcu(resv, true)) + if (dma_resv_test_signaled(resv, true)) dma_resv_add_excl_fence(resv, NULL); dma_resv_unlock(resv); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_busy.c b/drivers/gpu/drm/i915/gem/i915_gem_busy.c index 25235ef630c1..6234e17259c1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_busy.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_busy.c @@ -105,7 +105,7 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data, * Alternatively, we can trade that extra information on read/write * activity with * args->busy = - * !dma_resv_test_signaled_rcu(obj->resv, true); + * !dma_resv_test_signaled(obj->resv, true); * to report the overall busyness. This is what the wait-ioctl does. * */ @@ -113,11 +113,10 @@ retry: seq = raw_read_seqcount(&obj->base.resv->seq); /* Translate the exclusive fence to the READ *and* WRITE engine */ - args->busy = - busy_check_writer(rcu_dereference(obj->base.resv->fence_excl)); + args->busy = busy_check_writer(dma_resv_excl_fence(obj->base.resv)); /* Translate shared fences to READ set of engines */ - list = rcu_dereference(obj->base.resv->fence); + list = dma_resv_shared_list(obj->base.resv); if (list) { unsigned int shared_count = list->shared_count, i; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 297143511f99..66789111a24b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -1481,7 +1481,7 @@ static inline bool use_reloc_gpu(struct i915_vma *vma) if (DBG_FORCE_RELOC) return false; - return !dma_resv_test_signaled_rcu(vma->resv, true); + return !dma_resv_test_signaled(vma->resv, true); } static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 2ebd79537aea..7c0eb425cb3b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -500,7 +500,7 @@ i915_gem_object_last_write_engine(struct drm_i915_gem_object *obj) struct dma_fence *fence; rcu_read_lock(); - fence = dma_resv_get_excl_rcu(obj->base.resv); + fence = dma_resv_get_excl_unlocked(obj->base.resv); rcu_read_unlock(); if (fence && dma_fence_is_i915(fence) && !dma_fence_is_signaled(fence)) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index a657b99ec760..b5cbbe659a77 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -85,8 +85,8 @@ static bool i915_gem_userptr_invalidate(struct mmu_interval_notifier *mni, return true; /* we will unbind on next submission, still have userptr pins */ - r = dma_resv_wait_timeout_rcu(obj->base.resv, true, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(obj->base.resv, true, false, + MAX_SCHEDULE_TIMEOUT); if (r <= 0) drm_err(&i915->drm, "(%ld) failed to wait for idle\n", r); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c index 4b9856d5ba14..1e97520c62b2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c @@ -45,7 +45,7 @@ i915_gem_object_wait_reservation(struct dma_resv *resv, unsigned int count, i; int ret; - ret = dma_resv_get_fences_rcu(resv, &excl, &count, &shared); + ret = dma_resv_get_fences(resv, &excl, &count, &shared); if (ret) return ret; @@ -73,7 +73,7 @@ i915_gem_object_wait_reservation(struct dma_resv *resv, */ prune_fences = count && timeout >= 0; } else { - excl = dma_resv_get_excl_rcu(resv); + excl = dma_resv_get_excl_unlocked(resv); } if (excl && timeout >= 0) @@ -158,8 +158,8 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj, unsigned int count, i; int ret; - ret = dma_resv_get_fences_rcu(obj->base.resv, - &excl, &count, &shared); + ret = dma_resv_get_fences(obj->base.resv, &excl, &count, + &shared); if (ret) return ret; @@ -170,7 +170,7 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj, kfree(shared); } else { - excl = dma_resv_get_excl_rcu(obj->base.resv); + excl = dma_resv_get_excl_unlocked(obj->base.resv); } if (excl) { diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 970d8f4986bb..90185ca1b763 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1594,8 +1594,8 @@ i915_request_await_object(struct i915_request *to, struct dma_fence **shared; unsigned int count, i; - ret = dma_resv_get_fences_rcu(obj->base.resv, - &excl, &count, &shared); + ret = dma_resv_get_fences(obj->base.resv, &excl, &count, + &shared); if (ret) return ret; @@ -1611,7 +1611,7 @@ i915_request_await_object(struct i915_request *to, dma_fence_put(shared[i]); kfree(shared); } else { - excl = dma_resv_get_excl_rcu(obj->base.resv); + excl = dma_resv_get_excl_unlocked(obj->base.resv); } if (excl) { diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index 2744558f3050..c589a681da77 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -582,7 +582,7 @@ int i915_sw_fence_await_reservation(struct i915_sw_fence *fence, struct dma_fence **shared; unsigned int count, i; - ret = dma_resv_get_fences_rcu(resv, &excl, &count, &shared); + ret = dma_resv_get_fences(resv, &excl, &count, &shared); if (ret) return ret; @@ -606,7 +606,7 @@ int i915_sw_fence_await_reservation(struct i915_sw_fence *fence, dma_fence_put(shared[i]); kfree(shared); } else { - excl = dma_resv_get_excl_rcu(resv); + excl = dma_resv_get_excl_unlocked(resv); } if (ret >= 0 && excl && excl->ops != exclude) { diff --git a/drivers/gpu/drm/mediatek/mtk_disp_color.c b/drivers/gpu/drm/mediatek/mtk_disp_color.c index 63f411ab393b..6f4c80bbc0eb 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_color.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_color.c @@ -30,9 +30,8 @@ struct mtk_disp_color_data { unsigned int color_offset; }; -/** +/* * struct mtk_disp_color - DISP_COLOR driver structure - * @ddp_comp: structure containing type enum and hardware resources * @crtc: associated crtc to report irq events to * @data: platform colour driver data */ diff --git a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c index 3ebf91e0ab41..3a5815ab4079 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c @@ -29,10 +29,8 @@ struct mtk_disp_gamma_data { bool has_dither; }; -/** +/* * struct mtk_disp_gamma - DISP_GAMMA driver structure - * @ddp_comp - structure containing type enum and hardware resources - * @crtc - associated crtc to report irq events to */ struct mtk_disp_gamma { struct clk *clk; diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index 961f87f8d4d1..fa9d79963cd3 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -66,9 +66,8 @@ struct mtk_disp_ovl_data { bool smi_id_en; }; -/** +/* * struct mtk_disp_ovl - DISP_OVL driver structure - * @ddp_comp: structure containing type enum and hardware resources * @crtc: associated crtc to report vblank events to * @data: platform data */ diff --git a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c index 728aaadfea8c..705f28ceb4dd 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c @@ -55,10 +55,8 @@ struct mtk_disp_rdma_data { unsigned int fifo_size; }; -/** +/* * struct mtk_disp_rdma - DISP_RDMA driver structure - * @ddp_comp: structure containing type enum and hardware resources - * @crtc: associated crtc to report irq events to * @data: local driver data */ struct mtk_disp_rdma { diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index 10f693ea89d3..52536e7adb95 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -7,6 +7,8 @@ config DRM_MSM depends on IOMMU_SUPPORT depends on OF && COMMON_CLK depends on QCOM_OCMEM || QCOM_OCMEM=n + depends on QCOM_LLCC || QCOM_LLCC=n + depends on QCOM_COMMAND_DB || QCOM_COMMAND_DB=n select IOMMU_IO_PGTABLE select QCOM_MDT_LOADER if ARCH_QCOM select REGULATOR @@ -15,7 +17,6 @@ config DRM_MSM select SHMEM select TMPFS select QCOM_SCM if ARCH_QCOM - select QCOM_COMMAND_DB if ARCH_QCOM select WANT_DEV_COREDUMP select SND_SOC_HDMI_CODEC if SND_SOC select SYNC_FILE diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 56df86e5f740..a94a43de95ef 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -817,9 +817,9 @@ int msm_gem_sync_object(struct drm_gem_object *obj, struct dma_fence *fence; int i, ret; - fobj = dma_resv_get_list(obj->resv); + fobj = dma_resv_shared_list(obj->resv); if (!fobj || (fobj->shared_count == 0)) { - fence = dma_resv_get_excl(obj->resv); + fence = dma_resv_excl_fence(obj->resv); /* don't need to wait on our own fences, since ring is fifo */ if (fence && (fence->context != fctx->context)) { ret = dma_fence_wait(fence, true); @@ -915,8 +915,7 @@ int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout) op & MSM_PREP_NOSYNC ? 0 : timeout_to_jiffies(timeout); long ret; - ret = dma_resv_wait_timeout_rcu(obj->resv, write, - true, remain); + ret = dma_resv_wait_timeout(obj->resv, write, true, remain); if (ret == 0) return remain == 0 ? -EBUSY : -ETIMEDOUT; else if (ret < 0) @@ -1025,7 +1024,7 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m, } rcu_read_lock(); - fobj = rcu_dereference(robj->fence); + fobj = dma_resv_shared_list(robj); if (fobj) { unsigned int i, shared_count = fobj->shared_count; @@ -1035,7 +1034,7 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m, } } - fence = rcu_dereference(robj->fence_excl); + fence = dma_resv_excl_fence(robj); if (fence) describe_fence(fence, "Exclusive", m); rcu_read_unlock(); diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 0cb1f9d848d3..8d048bacd6f0 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -561,7 +561,7 @@ nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) asyw->image.handle[0] = ctxdma->object.handle; } - asyw->state.fence = dma_resv_get_excl_rcu(nvbo->bo.base.resv); + asyw->state.fence = dma_resv_get_excl_unlocked(nvbo->bo.base.resv); asyw->image.offset[0] = nvbo->offset; if (wndw->func->prepare) { diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index 0a9334deffe2..b45ec3086285 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -312,7 +312,7 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS) init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_VRAM | NOUVEAU_GEM_DOMAIN_GART; else - if (chan->chan->push.buffer->bo.mem.mem_type == TTM_PL_VRAM) + if (chan->chan->push.buffer->bo.resource->mem_type == TTM_PL_VRAM) init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_VRAM; else init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_GART; diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index c390f24f25f3..520b1ea9d16c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -433,7 +433,7 @@ nouveau_bo_pin(struct nouveau_bo *nvbo, uint32_t domain, bool contig) if (nvbo->bo.pin_count) { bool error = evict; - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_VRAM: error |= !(domain & NOUVEAU_GEM_DOMAIN_VRAM); break; @@ -446,7 +446,7 @@ nouveau_bo_pin(struct nouveau_bo *nvbo, uint32_t domain, bool contig) if (error) { NV_ERROR(drm, "bo %p pinned elsewhere: " "0x%08x vs 0x%08x\n", bo, - bo->mem.mem_type, domain); + bo->resource->mem_type, domain); ret = -EBUSY; } ttm_bo_pin(&nvbo->bo); @@ -467,7 +467,7 @@ nouveau_bo_pin(struct nouveau_bo *nvbo, uint32_t domain, bool contig) ttm_bo_pin(&nvbo->bo); - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_VRAM: drm->gem.vram_available -= bo->base.size; break; @@ -498,7 +498,7 @@ nouveau_bo_unpin(struct nouveau_bo *nvbo) ttm_bo_unpin(&nvbo->bo); if (!nvbo->bo.pin_count) { - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_VRAM: drm->gem.vram_available += bo->base.size; break; @@ -523,7 +523,7 @@ nouveau_bo_map(struct nouveau_bo *nvbo) if (ret) return ret; - ret = ttm_bo_kmap(&nvbo->bo, 0, nvbo->bo.mem.num_pages, &nvbo->kmap); + ret = ttm_bo_kmap(&nvbo->bo, 0, nvbo->bo.resource->num_pages, &nvbo->kmap); ttm_bo_unreserve(&nvbo->bo); return ret; @@ -737,7 +737,7 @@ nouveau_bo_evict_flags(struct ttm_buffer_object *bo, struct ttm_placement *pl) { struct nouveau_bo *nvbo = nouveau_bo(bo); - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_VRAM: nouveau_bo_placement_set(nvbo, NOUVEAU_GEM_DOMAIN_GART, NOUVEAU_GEM_DOMAIN_CPU); @@ -754,7 +754,7 @@ static int nouveau_bo_move_prep(struct nouveau_drm *drm, struct ttm_buffer_object *bo, struct ttm_resource *reg) { - struct nouveau_mem *old_mem = nouveau_mem(&bo->mem); + struct nouveau_mem *old_mem = nouveau_mem(bo->resource); struct nouveau_mem *new_mem = nouveau_mem(reg); struct nvif_vmm *vmm = &drm->client.vmm.vmm; int ret; @@ -809,7 +809,7 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, mutex_lock_nested(&cli->mutex, SINGLE_DEPTH_NESTING); ret = nouveau_fence_sync(nouveau_bo(bo), chan, true, ctx->interruptible); if (ret == 0) { - ret = drm->ttm.move(chan, bo, &bo->mem, new_reg); + ret = drm->ttm.move(chan, bo, bo->resource, new_reg); if (ret == 0) { ret = nouveau_fence_new(chan, false, &fence); if (ret == 0) { @@ -918,12 +918,8 @@ static void nouveau_bo_move_ntfy(struct ttm_buffer_object *bo, } } - if (new_reg) { - if (new_reg->mm_node) - nvbo->offset = (new_reg->start << PAGE_SHIFT); - else - nvbo->offset = 0; - } + if (new_reg) + nvbo->offset = (new_reg->start << PAGE_SHIFT); } @@ -955,7 +951,7 @@ nouveau_bo_vm_cleanup(struct ttm_buffer_object *bo, { struct nouveau_drm *drm = nouveau_bdev(bo->bdev); struct drm_device *dev = drm->dev; - struct dma_fence *fence = dma_resv_get_excl(bo->base.resv); + struct dma_fence *fence = dma_resv_excl_fence(bo->base.resv); nv10_bo_put_tile_region(dev, *old_tile, fence); *old_tile = new_tile; @@ -969,7 +965,7 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, { struct nouveau_drm *drm = nouveau_bdev(bo->bdev); struct nouveau_bo *nvbo = nouveau_bo(bo); - struct ttm_resource *old_reg = &bo->mem; + struct ttm_resource *old_reg = bo->resource; struct nouveau_drm_tile *new_tile = NULL; int ret = 0; @@ -1009,7 +1005,7 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict, if (old_reg->mem_type == TTM_PL_TT && new_reg->mem_type == TTM_PL_SYSTEM) { nouveau_ttm_tt_unbind(bo->bdev, bo->ttm); - ttm_resource_free(bo, &bo->mem); + ttm_resource_free(bo, &bo->resource); ttm_bo_assign_mem(bo, new_reg); goto out; } @@ -1045,7 +1041,7 @@ out: } out_ntfy: if (ret) { - nouveau_bo_move_ntfy(bo, &bo->mem); + nouveau_bo_move_ntfy(bo, bo->resource); } return ret; } @@ -1170,7 +1166,7 @@ out: list_del_init(&nvbo->io_reserve_lru); drm_vma_node_unmap(&nvbo->bo.base.vma_node, bdev->dev_mapping); - nouveau_ttm_io_mem_free_locked(drm, &nvbo->bo.mem); + nouveau_ttm_io_mem_free_locked(drm, nvbo->bo.resource); goto retry; } @@ -1200,12 +1196,12 @@ vm_fault_t nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo) /* as long as the bo isn't in vram, and isn't tiled, we've got * nothing to do here. */ - if (bo->mem.mem_type != TTM_PL_VRAM) { + if (bo->resource->mem_type != TTM_PL_VRAM) { if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA || !nvbo->kind) return 0; - if (bo->mem.mem_type != TTM_PL_SYSTEM) + if (bo->resource->mem_type != TTM_PL_SYSTEM) return 0; nouveau_bo_placement_set(nvbo, NOUVEAU_GEM_DOMAIN_GART, 0); @@ -1213,7 +1209,7 @@ vm_fault_t nouveau_ttm_fault_reserve_notify(struct ttm_buffer_object *bo) } else { /* make sure bo is in mappable vram */ if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA || - bo->mem.start + bo->mem.num_pages < mappable) + bo->resource->start + bo->resource->num_pages < mappable) return 0; for (i = 0; i < nvbo->placement.num_placement; ++i) { diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index 7cfac265fd45..40362600eed2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -212,7 +212,7 @@ nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device, args.start = 0; args.limit = chan->vmm->vmm.limit - 1; } else - if (chan->push.buffer->bo.mem.mem_type == TTM_PL_VRAM) { + if (chan->push.buffer->bo.resource->mem_type == TTM_PL_VRAM) { if (device->info.family == NV_DEVICE_INFO_V0_TNT) { /* nv04 vram pushbuf hack, retarget to its location in * the framebuffer bar rather than direct vram access.. diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 93ac78bda750..4f9b3aa5deda 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -378,7 +378,7 @@ nouveau_fbcon_create(struct drm_fb_helper *helper, FBINFO_HWACCEL_FILLRECT | FBINFO_HWACCEL_IMAGEBLIT; info->fbops = &nouveau_fbcon_sw_ops; - info->fix.smem_start = nvbo->bo.mem.bus.offset; + info->fix.smem_start = nvbo->bo.resource->bus.offset; info->fix.smem_len = nvbo->bo.base.size; info->screen_base = nvbo_kmap_obj_iovirtual(nvbo); diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index e5dcbf67de7e..6b43918035df 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -355,8 +355,8 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, bool e return ret; } - fobj = dma_resv_get_list(resv); - fence = dma_resv_get_excl(resv); + fobj = dma_resv_shared_list(resv); + fence = dma_resv_excl_fence(resv); if (fence && (!exclusive || !fobj || !fobj->shared_count)) { struct nouveau_channel *prev = NULL; diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 722e1decc202..5b27845075a1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -276,7 +276,7 @@ nouveau_gem_info(struct drm_file *file_priv, struct drm_gem_object *gem, if (is_power_of_2(nvbo->valid_domains)) rep->domain = nvbo->valid_domains; - else if (nvbo->bo.mem.mem_type == TTM_PL_TT) + else if (nvbo->bo.resource->mem_type == TTM_PL_TT) rep->domain = NOUVEAU_GEM_DOMAIN_GART; else rep->domain = NOUVEAU_GEM_DOMAIN_VRAM; @@ -347,11 +347,11 @@ nouveau_gem_set_domain(struct drm_gem_object *gem, uint32_t read_domains, valid_domains &= ~(NOUVEAU_GEM_DOMAIN_VRAM | NOUVEAU_GEM_DOMAIN_GART); if ((domains & NOUVEAU_GEM_DOMAIN_VRAM) && - bo->mem.mem_type == TTM_PL_VRAM) + bo->resource->mem_type == TTM_PL_VRAM) pref_domains |= NOUVEAU_GEM_DOMAIN_VRAM; else if ((domains & NOUVEAU_GEM_DOMAIN_GART) && - bo->mem.mem_type == TTM_PL_TT) + bo->resource->mem_type == TTM_PL_TT) pref_domains |= NOUVEAU_GEM_DOMAIN_GART; else if (domains & NOUVEAU_GEM_DOMAIN_VRAM) @@ -561,13 +561,13 @@ validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli, if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA) { if (nvbo->offset == b->presumed.offset && - ((nvbo->bo.mem.mem_type == TTM_PL_VRAM && + ((nvbo->bo.resource->mem_type == TTM_PL_VRAM && b->presumed.domain & NOUVEAU_GEM_DOMAIN_VRAM) || - (nvbo->bo.mem.mem_type == TTM_PL_TT && + (nvbo->bo.resource->mem_type == TTM_PL_TT && b->presumed.domain & NOUVEAU_GEM_DOMAIN_GART))) continue; - if (nvbo->bo.mem.mem_type == TTM_PL_TT) + if (nvbo->bo.resource->mem_type == TTM_PL_TT) b->presumed.domain = NOUVEAU_GEM_DOMAIN_GART; else b->presumed.domain = NOUVEAU_GEM_DOMAIN_VRAM; @@ -681,7 +681,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli, } if (!nvbo->kmap.virtual) { - ret = ttm_bo_kmap(&nvbo->bo, 0, nvbo->bo.mem.num_pages, + ret = ttm_bo_kmap(&nvbo->bo, 0, nvbo->bo.resource->num_pages, &nvbo->kmap); if (ret) { NV_PRINTK(err, cli, "failed kmap for reloc\n"); @@ -870,7 +870,7 @@ revalidate: if (unlikely(cmd != req->suffix0)) { if (!nvbo->kmap.virtual) { ret = ttm_bo_kmap(&nvbo->bo, 0, - nvbo->bo.mem. + nvbo->bo.resource-> num_pages, &nvbo->kmap); if (ret) { @@ -964,8 +964,8 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data, return -ENOENT; nvbo = nouveau_gem_object(gem); - lret = dma_resv_wait_timeout_rcu(nvbo->bo.base.resv, write, true, - no_wait ? 0 : 30 * HZ); + lret = dma_resv_wait_timeout(nvbo->bo.base.resv, write, true, + no_wait ? 0 : 30 * HZ); if (!lret) ret = -EBUSY; else if (lret > 0) diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c index a1049e9feee1..0de6549fb875 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.c +++ b/drivers/gpu/drm/nouveau/nouveau_mem.c @@ -178,25 +178,24 @@ void nouveau_mem_del(struct ttm_resource *reg) { struct nouveau_mem *mem = nouveau_mem(reg); - if (!mem) - return; + nouveau_mem_fini(mem); - kfree(reg->mm_node); - reg->mm_node = NULL; + kfree(mem); } int nouveau_mem_new(struct nouveau_cli *cli, u8 kind, u8 comp, - struct ttm_resource *reg) + struct ttm_resource **res) { struct nouveau_mem *mem; if (!(mem = kzalloc(sizeof(*mem), GFP_KERNEL))) return -ENOMEM; + mem->cli = cli; mem->kind = kind; mem->comp = comp; - reg->mm_node = mem; + *res = &mem->base; return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.h b/drivers/gpu/drm/nouveau/nouveau_mem.h index 7df3848e85aa..2c01166a90f2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.h +++ b/drivers/gpu/drm/nouveau/nouveau_mem.h @@ -6,13 +6,8 @@ struct ttm_tt; #include <nvif/mem.h> #include <nvif/vmm.h> -static inline struct nouveau_mem * -nouveau_mem(struct ttm_resource *reg) -{ - return reg->mm_node; -} - struct nouveau_mem { + struct ttm_resource base; struct nouveau_cli *cli; u8 kind; u8 comp; @@ -20,8 +15,14 @@ struct nouveau_mem { struct nvif_vma vma[2]; }; +static inline struct nouveau_mem * +nouveau_mem(struct ttm_resource *reg) +{ + return container_of(reg, struct nouveau_mem, base); +} + int nouveau_mem_new(struct nouveau_cli *, u8 kind, u8 comp, - struct ttm_resource *); + struct ttm_resource **); void nouveau_mem_del(struct ttm_resource *); int nouveau_mem_vram(struct ttm_resource *, bool contig, u8 page); int nouveau_mem_host(struct ttm_resource *, struct ttm_tt *); diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c index 65430912ff72..f4c2e46b6fe1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_ttm.c +++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c @@ -26,6 +26,8 @@ #include <linux/limits.h> #include <linux/swiotlb.h> +#include <drm/ttm/ttm_range_manager.h> + #include "nouveau_drv.h" #include "nouveau_gem.h" #include "nouveau_mem.h" @@ -43,7 +45,7 @@ static int nouveau_vram_manager_new(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *reg) + struct ttm_resource **res) { struct nouveau_bo *nvbo = nouveau_bo(bo); struct nouveau_drm *drm = nouveau_bdev(bo->bdev); @@ -52,13 +54,15 @@ nouveau_vram_manager_new(struct ttm_resource_manager *man, if (drm->client.device.info.ram_size == 0) return -ENOMEM; - ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, reg); + ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, res); if (ret) return ret; - ret = nouveau_mem_vram(reg, nvbo->contig, nvbo->page); + ttm_resource_init(bo, place, *res); + + ret = nouveau_mem_vram(*res, nvbo->contig, nvbo->page); if (ret) { - nouveau_mem_del(reg); + nouveau_mem_del(*res); return ret; } @@ -74,17 +78,18 @@ static int nouveau_gart_manager_new(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *reg) + struct ttm_resource **res) { struct nouveau_bo *nvbo = nouveau_bo(bo); struct nouveau_drm *drm = nouveau_bdev(bo->bdev); int ret; - ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, reg); + ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, res); if (ret) return ret; - reg->start = 0; + ttm_resource_init(bo, place, *res); + (*res)->start = 0; return 0; } @@ -97,26 +102,27 @@ static int nv04_gart_manager_new(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *reg) + struct ttm_resource **res) { struct nouveau_bo *nvbo = nouveau_bo(bo); struct nouveau_drm *drm = nouveau_bdev(bo->bdev); struct nouveau_mem *mem; int ret; - ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, reg); - mem = nouveau_mem(reg); + ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, res); if (ret) return ret; + mem = nouveau_mem(*res); + ttm_resource_init(bo, place, *res); ret = nvif_vmm_get(&mem->cli->vmm.vmm, PTES, false, 12, 0, - (long)reg->num_pages << PAGE_SHIFT, &mem->vma[0]); + (long)(*res)->num_pages << PAGE_SHIFT, &mem->vma[0]); if (ret) { - nouveau_mem_del(reg); + nouveau_mem_del(*res); return ret; } - reg->start = mem->vma[0].addr >> PAGE_SHIFT; + (*res)->start = mem->vma[0].addr >> PAGE_SHIFT; return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c index a49e88129c92..67d6619fcd5e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c @@ -77,7 +77,7 @@ int nouveau_vma_new(struct nouveau_bo *nvbo, struct nouveau_vmm *vmm, struct nouveau_vma **pvma) { - struct nouveau_mem *mem = nouveau_mem(&nvbo->bo.mem); + struct nouveau_mem *mem = nouveau_mem(nvbo->bo.resource); struct nouveau_vma *vma; struct nvif_vma tmp; int ret; @@ -96,7 +96,7 @@ nouveau_vma_new(struct nouveau_bo *nvbo, struct nouveau_vmm *vmm, vma->fence = NULL; list_add_tail(&vma->head, &nvbo->vma_list); - if (nvbo->bo.mem.mem_type != TTM_PL_SYSTEM && + if (nvbo->bo.resource->mem_type != TTM_PL_SYSTEM && mem->mem.page == nvbo->page) { ret = nvif_vmm_get(&vmm->vmm, LAZY, false, mem->mem.page, 0, mem->mem.size, &tmp); diff --git a/drivers/gpu/drm/nouveau/nv17_fence.c b/drivers/gpu/drm/nouveau/nv17_fence.c index b1cd8d7dd87d..07c2e0878c24 100644 --- a/drivers/gpu/drm/nouveau/nv17_fence.c +++ b/drivers/gpu/drm/nouveau/nv17_fence.c @@ -77,8 +77,8 @@ static int nv17_fence_context_new(struct nouveau_channel *chan) { struct nv10_fence_priv *priv = chan->drm->fence; + struct ttm_resource *reg = priv->bo->bo.resource; struct nv10_fence_chan *fctx; - struct ttm_resource *reg = &priv->bo->bo.mem; u32 start = reg->start * PAGE_SIZE; u32 limit = start + priv->bo->bo.base.size - 1; int ret = 0; diff --git a/drivers/gpu/drm/nouveau/nv50_fence.c b/drivers/gpu/drm/nouveau/nv50_fence.c index 1625826505f6..ea1e1f480bfe 100644 --- a/drivers/gpu/drm/nouveau/nv50_fence.c +++ b/drivers/gpu/drm/nouveau/nv50_fence.c @@ -37,7 +37,7 @@ nv50_fence_context_new(struct nouveau_channel *chan) { struct nv10_fence_priv *priv = chan->drm->fence; struct nv10_fence_chan *fctx; - struct ttm_resource *reg = &priv->bo->bo.mem; + struct ttm_resource *reg = priv->bo->bo.resource; u32 start = reg->start * PAGE_SIZE; u32 limit = start + priv->bo->bo.base.size - 1; int ret; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/tu102.c index 58db83ebadc5..a96084b34a78 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/tu102.c @@ -46,7 +46,7 @@ tu102_mc_intr_update(struct tu102_mc *mc) nvkm_wr32(device, 0xb81610, 0x6); } -void +static void tu102_mc_intr_unarm(struct nvkm_mc *base) { struct tu102_mc *mc = tu102_mc(base); @@ -58,7 +58,7 @@ tu102_mc_intr_unarm(struct nvkm_mc *base) spin_unlock_irqrestore(&mc->lock, flags); } -void +static void tu102_mc_intr_rearm(struct nvkm_mc *base) { struct tu102_mc *mc = tu102_mc(base); @@ -70,7 +70,7 @@ tu102_mc_intr_rearm(struct nvkm_mc *base) spin_unlock_irqrestore(&mc->lock, flags); } -void +static void tu102_mc_intr_mask(struct nvkm_mc *base, u32 mask, u32 intr) { struct tu102_mc *mc = tu102_mc(base); diff --git a/drivers/gpu/drm/panel/panel-elida-kd35t133.c b/drivers/gpu/drm/panel/panel-elida-kd35t133.c index fe5ac3ef9018..4787f0833264 100644 --- a/drivers/gpu/drm/panel/panel-elida-kd35t133.c +++ b/drivers/gpu/drm/panel/panel-elida-kd35t133.c @@ -42,6 +42,7 @@ struct kd35t133 { struct gpio_desc *reset_gpio; struct regulator *vdd; struct regulator *iovcc; + enum drm_panel_orientation orientation; bool prepared; }; @@ -216,6 +217,7 @@ static int kd35t133_get_modes(struct drm_panel *panel, connector->display_info.width_mm = mode->width_mm; connector->display_info.height_mm = mode->height_mm; drm_mode_probed_add(connector, mode); + drm_connector_set_panel_orientation(connector, ctx->orientation); return 1; } @@ -258,6 +260,12 @@ static int kd35t133_probe(struct mipi_dsi_device *dsi) return ret; } + ret = of_drm_get_panel_orientation(dev->of_node, &ctx->orientation); + if (ret < 0) { + dev_err(dev, "%pOF: failed to get orientation %d\n", dev->of_node, ret); + return ret; + } + mipi_dsi_set_drvdata(dsi, ctx); ctx->dev = dev; diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c index 5e9ccefb88f6..2229f1af2ca8 100644 --- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c +++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c @@ -29,7 +29,7 @@ * DEALINGS IN THE SOFTWARE. */ -/** +/* * Raspberry Pi 7" touchscreen panel driver. * * The 7" touchscreen consists of a DPI LCD panel, a Toshiba diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7701.c b/drivers/gpu/drm/panel/panel-sitronix-st7701.c index 4d2a149b202c..320a2a8fd459 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7701.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7701.c @@ -38,7 +38,7 @@ #define DSI_CMD2_BK1_SPD2 0xC2 /* Source EQ2 Setting */ #define DSI_CMD2_BK1_MIPISET1 0xD0 /* MIPI Setting 1 */ -/** +/* * Command2 with BK function selection. * * BIT[4, 0]: [CN2, BKXSEL] diff --git a/drivers/gpu/drm/panfrost/panfrost_device.h b/drivers/gpu/drm/panfrost/panfrost_device.h index 597cf1459b0a..f614e98771e4 100644 --- a/drivers/gpu/drm/panfrost/panfrost_device.h +++ b/drivers/gpu/drm/panfrost/panfrost_device.h @@ -45,6 +45,7 @@ struct panfrost_features { u32 thread_max_workgroup_sz; u32 thread_max_barrier_sz; u32 coherency_features; + u32 afbc_features; u32 texture_features[4]; u32 js_features[16]; diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index ca07098a6141..075ec0ef746c 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -63,6 +63,7 @@ static int panfrost_ioctl_get_param(struct drm_device *ddev, void *data, struct PANFROST_FEATURE(THREAD_MAX_BARRIER_SZ, thread_max_barrier_sz); PANFROST_FEATURE(COHERENCY_FEATURES, coherency_features); + PANFROST_FEATURE(AFBC_FEATURES, afbc_features); PANFROST_FEATURE_ARRAY(TEXTURE_FEATURES, texture_features, 3); PANFROST_FEATURE_ARRAY(JS_FEATURES, js_features, 15); PANFROST_FEATURE(NR_CORE_GROUPS, nr_core_groups); @@ -311,8 +312,7 @@ panfrost_ioctl_wait_bo(struct drm_device *dev, void *data, if (!gem_obj) return -ENOENT; - ret = dma_resv_wait_timeout_rcu(gem_obj->resv, true, - true, timeout); + ret = dma_resv_wait_timeout(gem_obj->resv, true, true, timeout); if (!ret) ret = timeout ? -ETIMEDOUT : -EBUSY; @@ -547,6 +547,7 @@ DEFINE_DRM_GEM_FOPS(panfrost_drm_driver_fops); * Panfrost driver version: * - 1.0 - initial interface * - 1.1 - adds HEAP and NOEXEC flags for CREATE_BO + * - 1.2 - adds AFBC_FEATURES query */ static const struct drm_driver panfrost_drm_driver = { .driver_features = DRIVER_RENDER | DRIVER_GEM | DRIVER_SYNCOBJ, @@ -559,7 +560,7 @@ static const struct drm_driver panfrost_drm_driver = { .desc = "panfrost DRM", .date = "20180908", .major = 1, - .minor = 1, + .minor = 2, .gem_create_object = panfrost_gem_create_object, .prime_handle_to_fd = drm_gem_prime_handle_to_fd, diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c index 2aae636f1cf5..0e70e27fd8c3 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gpu.c +++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c @@ -228,6 +228,7 @@ static void panfrost_gpu_init_features(struct panfrost_device *pfdev) pfdev->features.thread_max_workgroup_sz = gpu_read(pfdev, GPU_THREAD_MAX_WORKGROUP_SIZE); pfdev->features.thread_max_barrier_sz = gpu_read(pfdev, GPU_THREAD_MAX_BARRIER_SIZE); pfdev->features.coherency_features = gpu_read(pfdev, GPU_COHERENCY_FEATURES); + pfdev->features.afbc_features = gpu_read(pfdev, GPU_AFBC_FEATURES); for (i = 0; i < 4; i++) pfdev->features.texture_features[i] = gpu_read(pfdev, GPU_TEXTURE_FEATURES(i)); diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 6003cfeb1322..2df3e999a38d 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -203,7 +203,7 @@ static void panfrost_acquire_object_fences(struct drm_gem_object **bos, int i; for (i = 0; i < bo_count; i++) - implicit_fences[i] = dma_resv_get_excl_rcu(bos[i]->resv); + implicit_fences[i] = dma_resv_get_excl_unlocked(bos[i]->resv); } static void panfrost_attach_object_fences(struct drm_gem_object **bos, diff --git a/drivers/gpu/drm/panfrost/panfrost_regs.h b/drivers/gpu/drm/panfrost/panfrost_regs.h index eddaa62ad8b0..dc9df5457f1c 100644 --- a/drivers/gpu/drm/panfrost/panfrost_regs.h +++ b/drivers/gpu/drm/panfrost/panfrost_regs.h @@ -82,6 +82,7 @@ #define GPU_TEXTURE_FEATURES(n) (0x0B0 + ((n) * 4)) #define GPU_JS_FEATURES(n) (0x0C0 + ((n) * 4)) +#define GPU_AFBC_FEATURES (0x4C) /* (RO) AFBC support on Bifrost */ #define GPU_SHADER_PRESENT_LO 0x100 /* (RO) Shader core present bitmap, low word */ #define GPU_SHADER_PRESENT_HI 0x104 /* (RO) Shader core present bitmap, high word */ diff --git a/drivers/gpu/drm/pl111/Kconfig b/drivers/gpu/drm/pl111/Kconfig index 80f6748055e3..3aae387a96af 100644 --- a/drivers/gpu/drm/pl111/Kconfig +++ b/drivers/gpu/drm/pl111/Kconfig @@ -3,6 +3,7 @@ config DRM_PL111 tristate "DRM Support for PL111 CLCD Controller" depends on DRM depends on ARM || ARM64 || COMPILE_TEST + depends on VEXPRESS_CONFIG || VEXPRESS_CONFIG=n depends on COMMON_CLK select DRM_KMS_HELPER select DRM_KMS_CMA_HELPER diff --git a/drivers/gpu/drm/qxl/qxl_debugfs.c b/drivers/gpu/drm/qxl/qxl_debugfs.c index 183d15e2cf58..1f9a59601bb1 100644 --- a/drivers/gpu/drm/qxl/qxl_debugfs.c +++ b/drivers/gpu/drm/qxl/qxl_debugfs.c @@ -61,7 +61,7 @@ qxl_debugfs_buffers_info(struct seq_file *m, void *data) int rel; rcu_read_lock(); - fobj = rcu_dereference(bo->tbo.base.resv->fence); + fobj = dma_resv_shared_list(bo->tbo.base.resv); rel = fobj ? fobj->shared_count : 0; rcu_read_unlock(); diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index 20a0f3ab84ad..dd6abee55f56 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/gpu/drm/qxl/qxl_drv.h @@ -292,12 +292,12 @@ qxl_bo_physical_address(struct qxl_device *qdev, struct qxl_bo *bo, unsigned long offset) { struct qxl_memslot *slot = - (bo->tbo.mem.mem_type == TTM_PL_VRAM) + (bo->tbo.resource->mem_type == TTM_PL_VRAM) ? &qdev->main_slot : &qdev->surfaces_slot; - /* TODO - need to hold one of the locks to read bo->tbo.mem.start */ + /* TODO - need to hold one of the locks to read bo->tbo.resource->start */ - return slot->high_bits | ((bo->tbo.mem.start << PAGE_SHIFT) + offset); + return slot->high_bits | ((bo->tbo.resource->start << PAGE_SHIFT) + offset); } /* qxl_display.c */ diff --git a/drivers/gpu/drm/qxl/qxl_dumb.c b/drivers/gpu/drm/qxl/qxl_dumb.c index a635d9fdf8ac..d636ba685451 100644 --- a/drivers/gpu/drm/qxl/qxl_dumb.c +++ b/drivers/gpu/drm/qxl/qxl_dumb.c @@ -58,6 +58,8 @@ int qxl_mode_dumb_create(struct drm_file *file_priv, surf.height = args->height; surf.stride = pitch; surf.format = format; + surf.data = 0; + r = qxl_gem_object_create_with_handle(qdev, file_priv, QXL_GEM_DOMAIN_CPU, args->size, &surf, &qobj, diff --git a/drivers/gpu/drm/qxl/qxl_object.c b/drivers/gpu/drm/qxl/qxl_object.c index 6e26d70f2f07..fbb36e3e8564 100644 --- a/drivers/gpu/drm/qxl/qxl_object.c +++ b/drivers/gpu/drm/qxl/qxl_object.c @@ -212,14 +212,14 @@ void *qxl_bo_kmap_atomic_page(struct qxl_device *qdev, struct io_mapping *map; struct dma_buf_map bo_map; - if (bo->tbo.mem.mem_type == TTM_PL_VRAM) + if (bo->tbo.resource->mem_type == TTM_PL_VRAM) map = qdev->vram_mapping; - else if (bo->tbo.mem.mem_type == TTM_PL_PRIV) + else if (bo->tbo.resource->mem_type == TTM_PL_PRIV) map = qdev->surface_mapping; else goto fallback; - offset = bo->tbo.mem.start << PAGE_SHIFT; + offset = bo->tbo.resource->start << PAGE_SHIFT; return io_mapping_map_atomic_wc(map, offset + page_offset); fallback: if (bo->kptr) { @@ -266,8 +266,8 @@ int qxl_bo_vunmap(struct qxl_bo *bo) void qxl_bo_kunmap_atomic_page(struct qxl_device *qdev, struct qxl_bo *bo, void *pmap) { - if ((bo->tbo.mem.mem_type != TTM_PL_VRAM) && - (bo->tbo.mem.mem_type != TTM_PL_PRIV)) + if ((bo->tbo.resource->mem_type != TTM_PL_VRAM) && + (bo->tbo.resource->mem_type != TTM_PL_PRIV)) goto fallback; io_mapping_unmap_atomic(pmap); diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c index 47afe95d04a1..19fd39d9a00c 100644 --- a/drivers/gpu/drm/qxl/qxl_ttm.c +++ b/drivers/gpu/drm/qxl/qxl_ttm.c @@ -32,6 +32,7 @@ #include <drm/ttm/ttm_bo_api.h> #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> +#include <drm/ttm/ttm_range_manager.h> #include "qxl_drv.h" #include "qxl_object.h" @@ -131,7 +132,7 @@ static void qxl_bo_move_notify(struct ttm_buffer_object *bo, qbo = to_qxl_bo(bo); qdev = to_qxl(qbo->tbo.base.dev); - if (bo->mem.mem_type == TTM_PL_PRIV && qbo->surface_id) + if (bo->resource->mem_type == TTM_PL_PRIV && qbo->surface_id) qxl_surface_evict(qdev, qbo, new_mem ? true : false); } @@ -140,7 +141,7 @@ static int qxl_bo_move(struct ttm_buffer_object *bo, bool evict, struct ttm_resource *new_mem, struct ttm_place *hop) { - struct ttm_resource *old_mem = &bo->mem; + struct ttm_resource *old_mem = bo->resource; int ret; qxl_bo_move_notify(bo, new_mem); diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index 80a3bee933d6..9ed2b2700e0a 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -400,8 +400,8 @@ static int cmp_size_smaller_first(void *priv, const struct list_head *a, struct radeon_bo_list *lb = list_entry(b, struct radeon_bo_list, tv.head); /* Sort A before B if A is smaller. */ - return (int)la->robj->tbo.mem.num_pages - - (int)lb->robj->tbo.mem.num_pages; + return (int)la->robj->tbo.resource->num_pages - + (int)lb->robj->tbo.resource->num_pages; } /** @@ -516,7 +516,7 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *p, } r = radeon_vm_bo_update(rdev, vm->ib_bo_va, - &rdev->ring_tmp_bo.bo->tbo.mem); + rdev->ring_tmp_bo.bo->tbo.resource); if (r) return r; @@ -530,7 +530,7 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *p, return -EINVAL; } - r = radeon_vm_bo_update(rdev, bo_va, &bo->tbo.mem); + r = radeon_vm_bo_update(rdev, bo_va, bo->tbo.resource); if (r) return r; diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 652af7a134bd..406681317419 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -533,7 +533,7 @@ static int radeon_crtc_page_flip_target(struct drm_crtc *crtc, DRM_ERROR("failed to pin new rbo buffer before flip\n"); goto cleanup; } - work->fence = dma_fence_get(dma_resv_get_excl(new_rbo->tbo.base.resv)); + work->fence = dma_fence_get(dma_resv_excl_fence(new_rbo->tbo.base.resv)); radeon_bo_get_tiling_flags(new_rbo, &tiling_flags, NULL); radeon_bo_unreserve(new_rbo); diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index ff8849827d61..458f92a70887 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -161,7 +161,7 @@ static int radeon_gem_set_domain(struct drm_gem_object *gobj, } if (domain == RADEON_GEM_DOMAIN_CPU) { /* Asking for cpu access wait for object idle */ - r = dma_resv_wait_timeout_rcu(robj->tbo.base.resv, true, true, 30 * HZ); + r = dma_resv_wait_timeout(robj->tbo.base.resv, true, true, 30 * HZ); if (!r) r = -EBUSY; @@ -523,13 +523,13 @@ int radeon_gem_busy_ioctl(struct drm_device *dev, void *data, } robj = gem_to_radeon_bo(gobj); - r = dma_resv_test_signaled_rcu(robj->tbo.base.resv, true); + r = dma_resv_test_signaled(robj->tbo.base.resv, true); if (r == 0) r = -EBUSY; else r = 0; - cur_placement = READ_ONCE(robj->tbo.mem.mem_type); + cur_placement = READ_ONCE(robj->tbo.resource->mem_type); args->domain = radeon_mem_type_to_domain(cur_placement); drm_gem_object_put(gobj); return r; @@ -552,14 +552,14 @@ int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data, } robj = gem_to_radeon_bo(gobj); - ret = dma_resv_wait_timeout_rcu(robj->tbo.base.resv, true, true, 30 * HZ); + ret = dma_resv_wait_timeout(robj->tbo.base.resv, true, true, 30 * HZ); if (ret == 0) r = -EBUSY; else if (ret < 0) r = ret; /* Flush HDP cache via MMIO if necessary */ - cur_placement = READ_ONCE(robj->tbo.mem.mem_type); + cur_placement = READ_ONCE(robj->tbo.resource->mem_type); if (rdev->asic->mmio_hdp_flush && radeon_mem_type_to_domain(cur_placement) == RADEON_GEM_DOMAIN_VRAM) robj->rdev->asic->mmio_hdp_flush(rdev); @@ -643,7 +643,7 @@ static void radeon_gem_va_update_vm(struct radeon_device *rdev, goto error_free; list_for_each_entry(entry, &list, head) { - domain = radeon_mem_type_to_domain(entry->bo->mem.mem_type); + domain = radeon_mem_type_to_domain(entry->bo->resource->mem_type); /* if anything is swapped out don't swap it in here, just abort and wait for the next CS */ if (domain == RADEON_GEM_DOMAIN_CPU) @@ -656,7 +656,7 @@ static void radeon_gem_va_update_vm(struct radeon_device *rdev, goto error_unlock; if (bo_va->it.start) - r = radeon_vm_bo_update(rdev, bo_va, &bo_va->bo->tbo.mem); + r = radeon_vm_bo_update(rdev, bo_va, bo_va->bo->tbo.resource); error_unlock: mutex_unlock(&bo_va->vm->mutex); @@ -860,7 +860,7 @@ static int radeon_debugfs_gem_info_show(struct seq_file *m, void *unused) unsigned domain; const char *placement; - domain = radeon_mem_type_to_domain(rbo->tbo.mem.mem_type); + domain = radeon_mem_type_to_domain(rbo->tbo.resource->mem_type); switch (domain) { case RADEON_GEM_DOMAIN_VRAM: placement = "VRAM"; diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c index e37c9a57a7c3..9fa88549c89e 100644 --- a/drivers/gpu/drm/radeon/radeon_mn.c +++ b/drivers/gpu/drm/radeon/radeon_mn.c @@ -66,8 +66,8 @@ static bool radeon_mn_invalidate(struct mmu_interval_notifier *mn, return true; } - r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv, true, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(bo->tbo.base.resv, true, false, + MAX_SCHEDULE_TIMEOUT); if (r <= 0) DRM_ERROR("(%ld) failed to wait for user bo\n", r); diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index cee11c55fd15..bfaaa3c969a3 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -76,7 +76,7 @@ static void radeon_ttm_bo_destroy(struct ttm_buffer_object *tbo) bo = container_of(tbo, struct radeon_bo, tbo); - radeon_update_memory_usage(bo, bo->tbo.mem.mem_type, -1); + radeon_update_memory_usage(bo, bo->tbo.resource->mem_type, -1); mutex_lock(&bo->rdev->gem.mutex); list_del_init(&bo->list); @@ -250,7 +250,7 @@ int radeon_bo_kmap(struct radeon_bo *bo, void **ptr) } return 0; } - r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.mem.num_pages, &bo->kmap); + r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.resource->num_pages, &bo->kmap); if (r) { return r; } @@ -359,7 +359,7 @@ void radeon_bo_unpin(struct radeon_bo *bo) { ttm_bo_unpin(&bo->tbo); if (!bo->tbo.pin_count) { - if (bo->tbo.mem.mem_type == TTM_PL_VRAM) + if (bo->tbo.resource->mem_type == TTM_PL_VRAM) bo->rdev->vram_pin_size -= radeon_bo_size(bo); else bo->rdev->gart_pin_size -= radeon_bo_size(bo); @@ -506,7 +506,7 @@ int radeon_bo_list_validate(struct radeon_device *rdev, u32 domain = lobj->preferred_domains; u32 allowed = lobj->allowed_domains; u32 current_domain = - radeon_mem_type_to_domain(bo->tbo.mem.mem_type); + radeon_mem_type_to_domain(bo->tbo.resource->mem_type); /* Check if this buffer will be moved and don't move it * if we have moved too many buffers for this IB already. @@ -605,7 +605,7 @@ int radeon_bo_get_surface_reg(struct radeon_bo *bo) out: radeon_set_surface_reg(rdev, i, bo->tiling_flags, bo->pitch, - bo->tbo.mem.start << PAGE_SHIFT, + bo->tbo.resource->start << PAGE_SHIFT, bo->tbo.base.size); return 0; } @@ -711,7 +711,7 @@ int radeon_bo_check_tiling(struct radeon_bo *bo, bool has_moved, return 0; } - if (bo->tbo.mem.mem_type != TTM_PL_VRAM) { + if (bo->tbo.resource->mem_type != TTM_PL_VRAM) { if (!has_moved) return 0; @@ -743,7 +743,7 @@ void radeon_bo_move_notify(struct ttm_buffer_object *bo, if (!new_mem) return; - radeon_update_memory_usage(rbo, bo->mem.mem_type, -1); + radeon_update_memory_usage(rbo, bo->resource->mem_type, -1); radeon_update_memory_usage(rbo, new_mem->mem_type, 1); } @@ -760,11 +760,11 @@ vm_fault_t radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo) rbo = container_of(bo, struct radeon_bo, tbo); radeon_bo_check_tiling(rbo, 0, 0); rdev = rbo->rdev; - if (bo->mem.mem_type != TTM_PL_VRAM) + if (bo->resource->mem_type != TTM_PL_VRAM) return 0; - size = bo->mem.num_pages << PAGE_SHIFT; - offset = bo->mem.start << PAGE_SHIFT; + size = bo->resource->num_pages << PAGE_SHIFT; + offset = bo->resource->start << PAGE_SHIFT; if ((offset + size) <= rdev->mc.visible_vram_size) return 0; @@ -786,7 +786,7 @@ vm_fault_t radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo) radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT); r = ttm_bo_validate(bo, &rbo->placement, &ctx); } else if (likely(!r)) { - offset = bo->mem.start << PAGE_SHIFT; + offset = bo->resource->start << PAGE_SHIFT; /* this should never happen */ if ((offset + size) > rdev->mc.visible_vram_size) return VM_FAULT_SIGBUS; diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h index fd4116bdde0f..1739c6a142cd 100644 --- a/drivers/gpu/drm/radeon/radeon_object.h +++ b/drivers/gpu/drm/radeon/radeon_object.h @@ -95,7 +95,7 @@ static inline u64 radeon_bo_gpu_offset(struct radeon_bo *bo) rdev = radeon_get_rdev(bo->tbo.bdev); - switch (bo->tbo.mem.mem_type) { + switch (bo->tbo.resource->mem_type) { case TTM_PL_TT: start = rdev->mc.gtt_start; break; @@ -104,7 +104,7 @@ static inline u64 radeon_bo_gpu_offset(struct radeon_bo *bo) break; } - return (bo->tbo.mem.start << PAGE_SHIFT) + start; + return (bo->tbo.resource->start << PAGE_SHIFT) + start; } static inline unsigned long radeon_bo_size(struct radeon_bo *bo) diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 3861c0b98fcf..c67b6ddb29a4 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -154,7 +154,7 @@ static void radeon_unmap_vram_bos(struct radeon_device *rdev) return; list_for_each_entry_safe(bo, n, &rdev->gem.objects, list) { - if (bo->tbo.mem.mem_type == TTM_PL_VRAM) + if (bo->tbo.resource->mem_type == TTM_PL_VRAM) ttm_bo_unmap_virtual(&bo->tbo); } } diff --git a/drivers/gpu/drm/radeon/radeon_sync.c b/drivers/gpu/drm/radeon/radeon_sync.c index 5d3302945076..9257b60144c4 100644 --- a/drivers/gpu/drm/radeon/radeon_sync.c +++ b/drivers/gpu/drm/radeon/radeon_sync.c @@ -98,14 +98,14 @@ int radeon_sync_resv(struct radeon_device *rdev, int r = 0; /* always sync to the exclusive fence */ - f = dma_resv_get_excl(resv); + f = dma_resv_excl_fence(resv); fence = f ? to_radeon_fence(f) : NULL; if (fence && fence->rdev == rdev) radeon_sync_fence(sync, fence); else if (f) r = dma_fence_wait(f, true); - flist = dma_resv_get_list(resv); + flist = dma_resv_shared_list(resv); if (shared || !flist || r) return r; diff --git a/drivers/gpu/drm/radeon/radeon_trace.h b/drivers/gpu/drm/radeon/radeon_trace.h index 1729cb9a95c5..c9fed5f2b870 100644 --- a/drivers/gpu/drm/radeon/radeon_trace.h +++ b/drivers/gpu/drm/radeon/radeon_trace.h @@ -22,7 +22,7 @@ TRACE_EVENT(radeon_bo_create, TP_fast_assign( __entry->bo = bo; - __entry->pages = bo->tbo.mem.num_pages; + __entry->pages = bo->tbo.resource->num_pages; ), TP_printk("bo=%p, pages=%u", __entry->bo, __entry->pages) ); diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index a71d94f7067b..ad2a5a791bba 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -45,6 +45,7 @@ #include <drm/ttm/ttm_bo_api.h> #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> +#include <drm/ttm/ttm_range_manager.h> #include "radeon_reg.h" #include "radeon.h" @@ -98,12 +99,12 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo, return; } rbo = container_of(bo, struct radeon_bo, tbo); - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_VRAM: if (rbo->rdev->ring[radeon_copy_ring_index(rbo->rdev)].ready == false) radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_CPU); else if (rbo->rdev->mc.visible_vram_size < rbo->rdev->mc.real_vram_size && - bo->mem.start < (rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT)) { + bo->resource->start < (rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT)) { unsigned fpfn = rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT; int i; @@ -195,9 +196,9 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, bool evict, struct ttm_resource *new_mem, struct ttm_place *hop) { + struct ttm_resource *old_mem = bo->resource; struct radeon_device *rdev; struct radeon_bo *rbo; - struct ttm_resource *old_mem = &bo->mem; int r; if (new_mem->mem_type == TTM_PL_TT) { @@ -229,7 +230,7 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, bool evict, if (old_mem->mem_type == TTM_PL_TT && new_mem->mem_type == TTM_PL_SYSTEM) { radeon_ttm_tt_unbind(bo->bdev, bo->ttm); - ttm_resource_free(bo, &bo->mem); + ttm_resource_free(bo, &bo->resource); ttm_bo_assign_mem(bo, new_mem); goto out; } diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index dfa9fdbe98da..1f5b1a5c0a09 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -477,7 +477,7 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, return -EINVAL; } - f = dma_resv_get_excl(bo->tbo.base.resv); + f = dma_resv_excl_fence(bo->tbo.base.resv); if (f) { r = radeon_fence_wait((struct radeon_fence *)f, false); if (r) { diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c index 5c2b650b561d..03f3377f918c 100644 --- a/drivers/gpu/drm/sti/sti_hda.c +++ b/drivers/gpu/drm/sti/sti_hda.c @@ -272,7 +272,7 @@ static void hda_write(struct sti_hda *hda, u32 val, int offset) } /** - * Search for a video mode in the supported modes table + * hda_get_mode_idx - Search for a video mode in the supported modes table * * @mode: mode being searched * @idx: index of the found mode @@ -292,7 +292,7 @@ static bool hda_get_mode_idx(struct drm_display_mode mode, int *idx) } /** - * Enable the HD DACS + * hda_enable_hd_dacs - Enable the HD DACS * * @hda: pointer to HD analog structure * @enable: true if HD DACS need to be enabled, else false @@ -380,7 +380,7 @@ static void hda_debugfs_init(struct sti_hda *hda, struct drm_minor *minor) } /** - * Configure AWG, writing instructions + * sti_hda_configure_awg - Configure AWG, writing instructions * * @hda: pointer to HD analog structure * @awg_instr: pointer to AWG instructions table diff --git a/drivers/gpu/drm/sti/sti_hdmi_tx3g4c28phy.c b/drivers/gpu/drm/sti/sti_hdmi_tx3g4c28phy.c index d5f94dca0d32..d25ecd4f4b67 100644 --- a/drivers/gpu/drm/sti/sti_hdmi_tx3g4c28phy.c +++ b/drivers/gpu/drm/sti/sti_hdmi_tx3g4c28phy.c @@ -67,7 +67,7 @@ static struct hdmi_phy_config hdmiphy_config[NB_HDMI_PHY_CONFIG] = { }; /** - * Start hdmi phy macro cell tx3g4c28 + * sti_hdmi_tx3g4c28phy_start - Start hdmi phy macro cell tx3g4c28 * * @hdmi: pointer on the hdmi internal structure * @@ -179,7 +179,7 @@ err: } /** - * Stop hdmi phy macro cell tx3g4c28 + * sti_hdmi_tx3g4c28phy_stop - Stop hdmi phy macro cell tx3g4c28 * * @hdmi: pointer on the hdmi internal structure */ diff --git a/drivers/gpu/drm/sti/sti_hqvdp.c b/drivers/gpu/drm/sti/sti_hqvdp.c index edbb99f53de1..d09b08995b12 100644 --- a/drivers/gpu/drm/sti/sti_hqvdp.c +++ b/drivers/gpu/drm/sti/sti_hqvdp.c @@ -782,7 +782,7 @@ static void sti_hqvdp_disable(struct sti_hqvdp *hqvdp) } /** - * sti_vdp_vtg_cb + * sti_hqvdp_vtg_cb * @nb: notifier block * @evt: event message * @data: private data diff --git a/drivers/gpu/drm/sti/sti_tvout.c b/drivers/gpu/drm/sti/sti_tvout.c index df3817f0fd30..2499715a69b7 100644 --- a/drivers/gpu/drm/sti/sti_tvout.c +++ b/drivers/gpu/drm/sti/sti_tvout.c @@ -153,7 +153,7 @@ static void tvout_write(struct sti_tvout *tvout, u32 val, int offset) } /** - * Set the clipping mode of a VIP + * tvout_vip_set_color_order - Set the clipping mode of a VIP * * @tvout: tvout structure * @reg: register to set @@ -177,7 +177,7 @@ static void tvout_vip_set_color_order(struct sti_tvout *tvout, int reg, } /** - * Set the clipping mode of a VIP + * tvout_vip_set_clip_mode - Set the clipping mode of a VIP * * @tvout: tvout structure * @reg: register to set @@ -193,7 +193,7 @@ static void tvout_vip_set_clip_mode(struct sti_tvout *tvout, int reg, u32 range) } /** - * Set the rounded value of a VIP + * tvout_vip_set_rnd - Set the rounded value of a VIP * * @tvout: tvout structure * @reg: register to set @@ -209,7 +209,7 @@ static void tvout_vip_set_rnd(struct sti_tvout *tvout, int reg, u32 rnd) } /** - * Select the VIP input + * tvout_vip_set_sel_input - Select the VIP input * * @tvout: tvout structure * @reg: register to set @@ -247,7 +247,7 @@ static void tvout_vip_set_sel_input(struct sti_tvout *tvout, } /** - * Select the input video signed or unsigned + * tvout_vip_set_in_vid_fmt - Select the input video signed or unsigned * * @tvout: tvout structure * @reg: register to set @@ -264,7 +264,7 @@ static void tvout_vip_set_in_vid_fmt(struct sti_tvout *tvout, } /** - * Set preformatter matrix + * tvout_preformatter_set_matrix - Set preformatter matrix * * @tvout: tvout structure * @mode: display mode structure @@ -289,7 +289,7 @@ static void tvout_preformatter_set_matrix(struct sti_tvout *tvout, } /** - * Start VIP block for DVO output + * tvout_dvo_start - Start VIP block for DVO output * * @tvout: pointer on tvout structure * @main_path: true if main path has to be used in the vip configuration @@ -343,7 +343,7 @@ static void tvout_dvo_start(struct sti_tvout *tvout, bool main_path) } /** - * Start VIP block for HDMI output + * tvout_hdmi_start - Start VIP block for HDMI output * * @tvout: pointer on tvout structure * @main_path: true if main path has to be used in the vip configuration @@ -392,7 +392,7 @@ static void tvout_hdmi_start(struct sti_tvout *tvout, bool main_path) } /** - * Start HDF VIP and HD DAC + * tvout_hda_start - Start HDF VIP and HD DAC * * @tvout: pointer on tvout structure * @main_path: true if main path has to be used in the vip configuration diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c index e99771b947b6..08b71248044d 100644 --- a/drivers/gpu/drm/stm/ltdc.c +++ b/drivers/gpu/drm/stm/ltdc.c @@ -531,7 +531,6 @@ static void ltdc_crtc_mode_set_nofb(struct drm_crtc *crtc) struct drm_encoder *encoder = NULL; struct drm_bridge *bridge = NULL; struct drm_display_mode *mode = &crtc->state->adjusted_mode; - struct videomode vm; u32 hsync, vsync, accum_hbp, accum_vbp, accum_act_w, accum_act_h; u32 total_width, total_height; u32 bus_flags = 0; @@ -570,31 +569,33 @@ static void ltdc_crtc_mode_set_nofb(struct drm_crtc *crtc) } } - drm_display_mode_to_videomode(mode, &vm); - DRM_DEBUG_DRIVER("CRTC:%d mode:%s\n", crtc->base.id, mode->name); - DRM_DEBUG_DRIVER("Video mode: %dx%d", vm.hactive, vm.vactive); + DRM_DEBUG_DRIVER("Video mode: %dx%d", mode->hdisplay, mode->vdisplay); DRM_DEBUG_DRIVER(" hfp %d hbp %d hsl %d vfp %d vbp %d vsl %d\n", - vm.hfront_porch, vm.hback_porch, vm.hsync_len, - vm.vfront_porch, vm.vback_porch, vm.vsync_len); + mode->hsync_start - mode->hdisplay, + mode->htotal - mode->hsync_end, + mode->hsync_end - mode->hsync_start, + mode->vsync_start - mode->vdisplay, + mode->vtotal - mode->vsync_end, + mode->vsync_end - mode->vsync_start); /* Convert video timings to ltdc timings */ - hsync = vm.hsync_len - 1; - vsync = vm.vsync_len - 1; - accum_hbp = hsync + vm.hback_porch; - accum_vbp = vsync + vm.vback_porch; - accum_act_w = accum_hbp + vm.hactive; - accum_act_h = accum_vbp + vm.vactive; - total_width = accum_act_w + vm.hfront_porch; - total_height = accum_act_h + vm.vfront_porch; + hsync = mode->hsync_end - mode->hsync_start - 1; + vsync = mode->vsync_end - mode->vsync_start - 1; + accum_hbp = mode->htotal - mode->hsync_start - 1; + accum_vbp = mode->vtotal - mode->vsync_start - 1; + accum_act_w = accum_hbp + mode->hdisplay; + accum_act_h = accum_vbp + mode->vdisplay; + total_width = mode->htotal - 1; + total_height = mode->vtotal - 1; /* Configures the HS, VS, DE and PC polarities. Default Active Low */ val = 0; - if (vm.flags & DISPLAY_FLAGS_HSYNC_HIGH) + if (mode->flags & DRM_MODE_FLAG_PHSYNC) val |= GCR_HSPOL; - if (vm.flags & DISPLAY_FLAGS_VSYNC_HIGH) + if (mode->flags & DRM_MODE_FLAG_PVSYNC) val |= GCR_VSPOL; if (bus_flags & DRM_BUS_FLAG_DE_LOW) diff --git a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c index 0db164a774a1..e779855bcd6e 100644 --- a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c +++ b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c @@ -370,6 +370,11 @@ static const u32 sun8i_ui_layer_formats[] = { DRM_FORMAT_XRGB8888, }; +static const uint64_t sun8i_layer_modifiers[] = { + DRM_FORMAT_MOD_LINEAR, + DRM_FORMAT_MOD_INVALID +}; + struct sun8i_ui_layer *sun8i_ui_layer_init_one(struct drm_device *drm, struct sun8i_mixer *mixer, int index) @@ -392,7 +397,7 @@ struct sun8i_ui_layer *sun8i_ui_layer_init_one(struct drm_device *drm, &sun8i_ui_layer_funcs, sun8i_ui_layer_formats, ARRAY_SIZE(sun8i_ui_layer_formats), - NULL, type, NULL); + sun8i_layer_modifiers, type, NULL); if (ret) { dev_err(drm->dev, "Couldn't initialize layer\n"); return ERR_PTR(ret); diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c index 46420780db59..1c86c2dd0bbf 100644 --- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c +++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c @@ -534,6 +534,11 @@ static const u32 sun8i_vi_layer_de3_formats[] = { DRM_FORMAT_YVU422, }; +static const uint64_t sun8i_layer_modifiers[] = { + DRM_FORMAT_MOD_LINEAR, + DRM_FORMAT_MOD_INVALID +}; + struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm, struct sun8i_mixer *mixer, int index) @@ -560,7 +565,8 @@ struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm, ret = drm_universal_plane_init(drm, &layer->plane, 0, &sun8i_vi_layer_funcs, formats, format_count, - NULL, DRM_PLANE_TYPE_OVERLAY, NULL); + sun8i_layer_modifiers, + DRM_PLANE_TYPE_OVERLAY, NULL); if (ret) { dev_err(drm->dev, "Couldn't initialize layer\n"); return ERR_PTR(ret); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 51a94fd63bd7..db53fecca696 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -58,7 +58,7 @@ static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo, int i, mem_type; drm_printf(&p, "No space for %p (%lu pages, %zuK, %zuM)\n", - bo, bo->mem.num_pages, bo->base.size >> 10, + bo, bo->resource->num_pages, bo->base.size >> 10, bo->base.size >> 20); for (i = 0; i < placement->num_placement; i++) { mem_type = placement->placement[i].mem_type; @@ -109,7 +109,7 @@ void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo, bdev->funcs->del_from_lru_notify(bo); if (bulk && !bo->pin_count) { - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_TT: ttm_bo_bulk_move_set_pos(&bulk->tt[bo->priority], bo); break; @@ -163,11 +163,13 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, struct ttm_place *hop) { + struct ttm_resource_manager *old_man, *new_man; struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *old_man = ttm_manager_type(bdev, bo->mem.mem_type); - struct ttm_resource_manager *new_man = ttm_manager_type(bdev, mem->mem_type); int ret; + old_man = ttm_manager_type(bdev, bo->resource->mem_type); + new_man = ttm_manager_type(bdev, mem->mem_type); + ttm_bo_unmap_virtual(bo); /* @@ -200,7 +202,7 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, return 0; out_err: - new_man = ttm_manager_type(bdev, bo->mem.mem_type); + new_man = ttm_manager_type(bdev, bo->resource->mem_type); if (!new_man->use_tt) ttm_bo_tt_destroy(bo); @@ -221,7 +223,7 @@ static void ttm_bo_cleanup_memtype_use(struct ttm_buffer_object *bo) bo->bdev->funcs->delete_mem_notify(bo); ttm_bo_tt_destroy(bo); - ttm_resource_free(bo, &bo->mem); + ttm_resource_free(bo, &bo->resource); } static int ttm_bo_individualize_resv(struct ttm_buffer_object *bo) @@ -259,8 +261,8 @@ static void ttm_bo_flush_all_fences(struct ttm_buffer_object *bo) int i; rcu_read_lock(); - fobj = rcu_dereference(resv->fence); - fence = rcu_dereference(resv->fence_excl); + fobj = dma_resv_shared_list(resv); + fence = dma_resv_excl_fence(resv); if (fence && !fence->ops->signaled) dma_fence_enable_sw_signaling(fence); @@ -294,7 +296,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, struct dma_resv *resv = &bo->base._resv; int ret; - if (dma_resv_test_signaled_rcu(resv, true)) + if (dma_resv_test_signaled(resv, true)) ret = 0; else ret = -EBUSY; @@ -306,8 +308,8 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, dma_resv_unlock(bo->base.resv); spin_unlock(&bo->bdev->lru_lock); - lret = dma_resv_wait_timeout_rcu(resv, true, interruptible, - 30 * HZ); + lret = dma_resv_wait_timeout(resv, true, interruptible, + 30 * HZ); if (lret < 0) return lret; @@ -409,18 +411,18 @@ static void ttm_bo_release(struct kref *kref) /* Last resort, if we fail to allocate memory for the * fences block for the BO to become idle */ - dma_resv_wait_timeout_rcu(bo->base.resv, true, false, - 30 * HZ); + dma_resv_wait_timeout(bo->base.resv, true, false, + 30 * HZ); } if (bo->bdev->funcs->release_notify) bo->bdev->funcs->release_notify(bo); drm_vma_offset_remove(bdev->vma_manager, &bo->base.vma_node); - ttm_mem_io_free(bdev, &bo->mem); + ttm_mem_io_free(bdev, bo->resource); } - if (!dma_resv_test_signaled_rcu(bo->base.resv, true) || + if (!dma_resv_test_signaled(bo->base.resv, true) || !dma_resv_trylock(bo->base.resv)) { /* The BO is not idle, resurrect it for delayed destroy */ ttm_bo_flush_all_fences(bo); @@ -438,7 +440,7 @@ static void ttm_bo_release(struct kref *kref) */ if (bo->pin_count) { bo->pin_count = 0; - ttm_bo_move_to_lru_tail(bo, &bo->mem, NULL); + ttm_bo_move_to_lru_tail(bo, bo->resource, NULL); } kref_init(&bo->kref); @@ -487,7 +489,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx) { struct ttm_device *bdev = bo->bdev; - struct ttm_resource evict_mem; + struct ttm_resource *evict_mem; struct ttm_placement placement; struct ttm_place hop; int ret = 0; @@ -501,10 +503,15 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bdev->funcs->evict_flags(bo, &placement); if (!placement.num_placement && !placement.num_busy_placement) { - ttm_bo_wait(bo, false, false); + ret = ttm_bo_wait(bo, true, false); + if (ret) + return ret; - ttm_bo_cleanup_memtype_use(bo); - return ttm_tt_create(bo, false); + /* + * Since we've already synced, this frees backing store + * immediately. + */ + return ttm_bo_pipeline_gutting(bo); } ret = ttm_bo_mem_space(bo, &placement, &evict_mem, ctx); @@ -517,7 +524,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, goto out; } - ret = ttm_bo_handle_move_mem(bo, &evict_mem, true, ctx, &hop); + ret = ttm_bo_handle_move_mem(bo, evict_mem, true, ctx, &hop); if (unlikely(ret)) { WARN(ret == -EMULTIHOP, "Unexpected multihop in eviction - likely driver bug\n"); if (ret != -ERESTARTSYS) @@ -531,11 +538,15 @@ out: bool ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, const struct ttm_place *place) { + dma_resv_assert_held(bo->base.resv); + if (bo->resource->mem_type == TTM_PL_SYSTEM) + return true; + /* Don't evict this BO if it's outside of the * requested placement range */ - if (place->fpfn >= (bo->mem.start + bo->mem.num_pages) || - (place->lpfn && place->lpfn <= bo->mem.start)) + if (place->fpfn >= (bo->resource->start + bo->resource->num_pages) || + (place->lpfn && place->lpfn <= bo->resource->start)) return false; return true; @@ -553,7 +564,9 @@ EXPORT_SYMBOL(ttm_bo_eviction_valuable); * b. Otherwise, trylock it. */ static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo, - struct ttm_operation_ctx *ctx, bool *locked, bool *busy) + struct ttm_operation_ctx *ctx, + const struct ttm_place *place, + bool *locked, bool *busy) { bool ret = false; @@ -571,6 +584,14 @@ static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo, *busy = !ret; } + if (ret && place && !bo->bdev->funcs->eviction_valuable(bo, place)) { + ret = false; + if (*locked) { + dma_resv_unlock(bo->base.resv); + *locked = false; + } + } + return ret; } @@ -625,20 +646,14 @@ int ttm_mem_evict_first(struct ttm_device *bdev, list_for_each_entry(bo, &man->lru[i], lru) { bool busy; - if (!ttm_bo_evict_swapout_allowable(bo, ctx, &locked, - &busy)) { + if (!ttm_bo_evict_swapout_allowable(bo, ctx, place, + &locked, &busy)) { if (busy && !busy_bo && ticket != dma_resv_locking_ctx(bo->base.resv)) busy_bo = bo; continue; } - if (place && !bdev->funcs->eviction_valuable(bo, - place)) { - if (locked) - dma_resv_unlock(bo->base.resv); - continue; - } if (!ttm_bo_get_unless_zero(bo)) { if (locked) dma_resv_unlock(bo->base.resv); @@ -726,14 +741,15 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, */ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *mem, + struct ttm_resource **mem, struct ttm_operation_ctx *ctx) { struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *man = ttm_manager_type(bdev, mem->mem_type); + struct ttm_resource_manager *man; struct ww_acquire_ctx *ticket; int ret; + man = ttm_manager_type(bdev, place->mem_type); ticket = dma_resv_locking_ctx(bo->base.resv); do { ret = ttm_resource_alloc(bo, place, mem); @@ -747,37 +763,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, return ret; } while (1); - return ttm_bo_add_move_fence(bo, man, mem, ctx->no_wait_gpu); -} - -/** - * ttm_bo_mem_placement - check if placement is compatible - * @bo: BO to find memory for - * @place: where to search - * @mem: the memory object to fill in - * - * Check if placement is compatible and fill in mem structure. - * Returns -EBUSY if placement won't work or negative error code. - * 0 when placement can be used. - */ -static int ttm_bo_mem_placement(struct ttm_buffer_object *bo, - const struct ttm_place *place, - struct ttm_resource *mem) -{ - struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *man; - - man = ttm_manager_type(bdev, place->mem_type); - if (!man || !ttm_resource_manager_used(man)) - return -EBUSY; - - mem->mem_type = place->mem_type; - mem->placement = place->flags; - - spin_lock(&bo->bdev->lru_lock); - ttm_bo_move_to_lru_tail(bo, mem, NULL); - spin_unlock(&bo->bdev->lru_lock); - return 0; + return ttm_bo_add_move_fence(bo, man, *mem, ctx->no_wait_gpu); } /* @@ -790,7 +776,7 @@ static int ttm_bo_mem_placement(struct ttm_buffer_object *bo, */ int ttm_bo_mem_space(struct ttm_buffer_object *bo, struct ttm_placement *placement, - struct ttm_resource *mem, + struct ttm_resource **mem, struct ttm_operation_ctx *ctx) { struct ttm_device *bdev = bo->bdev; @@ -805,8 +791,8 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, const struct ttm_place *place = &placement->placement[i]; struct ttm_resource_manager *man; - ret = ttm_bo_mem_placement(bo, place, mem); - if (ret) + man = ttm_manager_type(bdev, place->mem_type); + if (!man || !ttm_resource_manager_used(man)) continue; type_found = true; @@ -816,8 +802,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, if (unlikely(ret)) goto error; - man = ttm_manager_type(bdev, mem->mem_type); - ret = ttm_bo_add_move_fence(bo, man, mem, ctx->no_wait_gpu); + ret = ttm_bo_add_move_fence(bo, man, *mem, ctx->no_wait_gpu); if (unlikely(ret)) { ttm_resource_free(bo, mem); if (ret == -EBUSY) @@ -830,9 +815,10 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, for (i = 0; i < placement->num_busy_placement; ++i) { const struct ttm_place *place = &placement->busy_placement[i]; + struct ttm_resource_manager *man; - ret = ttm_bo_mem_placement(bo, place, mem); - if (ret) + man = ttm_manager_type(bdev, place->mem_type); + if (!man || !ttm_resource_manager_used(man)) continue; type_found = true; @@ -851,7 +837,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, } error: - if (bo->mem.mem_type == TTM_PL_SYSTEM && !bo->pin_count) + if (bo->resource->mem_type == TTM_PL_SYSTEM && !bo->pin_count) ttm_bo_move_to_lru_tail_unlocked(bo); return ret; @@ -859,12 +845,12 @@ error: EXPORT_SYMBOL(ttm_bo_mem_space); static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo, - struct ttm_resource *mem, + struct ttm_resource **mem, struct ttm_operation_ctx *ctx, struct ttm_place *hop) { struct ttm_placement hop_placement; - struct ttm_resource hop_mem; + struct ttm_resource *hop_mem; int ret; hop_placement.num_placement = hop_placement.num_busy_placement = 1; @@ -875,7 +861,7 @@ static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo, if (ret) return ret; /* move to the bounce domain */ - ret = ttm_bo_handle_move_mem(bo, &hop_mem, false, ctx, NULL); + ret = ttm_bo_handle_move_mem(bo, hop_mem, false, ctx, NULL); if (ret) { ttm_resource_free(bo, &hop_mem); return ret; @@ -887,14 +873,12 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo, struct ttm_placement *placement, struct ttm_operation_ctx *ctx) { + struct ttm_resource *mem; struct ttm_place hop; - struct ttm_resource mem; int ret; dma_resv_assert_held(bo->base.resv); - memset(&hop, 0, sizeof(hop)); - /* * Determine where to move the buffer. * @@ -908,7 +892,7 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo, if (ret) return ret; bounce: - ret = ttm_bo_handle_move_mem(bo, &mem, false, ctx, &hop); + ret = ttm_bo_handle_move_mem(bo, mem, false, ctx, &hop); if (ret == -EMULTIHOP) { ret = ttm_bo_bounce_temp_buffer(bo, &mem, ctx, &hop); if (ret) @@ -976,18 +960,13 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, /* * Remove the backing store if no placement is given. */ - if (!placement->num_placement && !placement->num_busy_placement) { - ret = ttm_bo_pipeline_gutting(bo); - if (ret) - return ret; - - return ttm_tt_create(bo, false); - } + if (!placement->num_placement && !placement->num_busy_placement) + return ttm_bo_pipeline_gutting(bo); /* * Check whether we need to move buffer. */ - if (!ttm_bo_mem_compat(placement, &bo->mem, &new_flags)) { + if (!ttm_bo_mem_compat(placement, bo->resource, &new_flags)) { ret = ttm_bo_move_buffer(bo, placement, ctx); if (ret) return ret; @@ -995,7 +974,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, /* * We might need to add a TTM. */ - if (bo->mem.mem_type == TTM_PL_SYSTEM) { + if (bo->resource->mem_type == TTM_PL_SYSTEM) { ret = ttm_tt_create(bo, true); if (ret) return ret; @@ -1017,7 +996,7 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, { static const struct ttm_place sys_mem = { .mem_type = TTM_PL_SYSTEM }; bool locked; - int ret = 0; + int ret; bo->destroy = destroy ? destroy : ttm_bo_default_destroy; @@ -1027,7 +1006,6 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, bo->bdev = bdev; bo->type = type; bo->page_alignment = page_alignment; - ttm_resource_alloc(bo, &sys_mem, &bo->mem); bo->moving = NULL; bo->pin_count = 0; bo->sg = sg; @@ -1039,6 +1017,12 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, } atomic_inc(&ttm_glob.bo_count); + ret = ttm_resource_alloc(bo, &sys_mem, &bo->resource); + if (unlikely(ret)) { + ttm_bo_put(bo); + return ret; + } + /* * For ttm_bo_type_device buffers, allocate * address space from the device. @@ -1046,7 +1030,7 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, if (bo->type == ttm_bo_type_device || bo->type == ttm_bo_type_sg) ret = drm_vma_offset_add(bdev->vma_manager, &bo->base.vma_node, - bo->mem.num_pages); + bo->resource->num_pages); /* passed reservation objects should already be locked, * since otherwise lockdep will be angered in radeon. @@ -1108,7 +1092,7 @@ void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo) struct ttm_device *bdev = bo->bdev; drm_vma_node_unmap(&bo->base.vma_node, bdev->dev_mapping); - ttm_mem_io_free(bdev, &bo->mem); + ttm_mem_io_free(bdev, bo->resource); } EXPORT_SYMBOL(ttm_bo_unmap_virtual); @@ -1118,14 +1102,14 @@ int ttm_bo_wait(struct ttm_buffer_object *bo, long timeout = 15 * HZ; if (no_wait) { - if (dma_resv_test_signaled_rcu(bo->base.resv, true)) + if (dma_resv_test_signaled(bo->base.resv, true)) return 0; else return -EBUSY; } - timeout = dma_resv_wait_timeout_rcu(bo->base.resv, true, - interruptible, timeout); + timeout = dma_resv_wait_timeout(bo->base.resv, true, interruptible, + timeout); if (timeout < 0) return timeout; @@ -1140,10 +1124,19 @@ EXPORT_SYMBOL(ttm_bo_wait); int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, gfp_t gfp_flags) { + struct ttm_place place; bool locked; int ret; - if (!ttm_bo_evict_swapout_allowable(bo, ctx, &locked, NULL)) + /* + * While the bo may already reside in SYSTEM placement, set + * SYSTEM as new placement to cover also the move further below. + * The driver may use the fact that we're moving from SYSTEM + * as an indication that we're about to swap out. + */ + memset(&place, 0, sizeof(place)); + place.mem_type = TTM_PL_SYSTEM; + if (!ttm_bo_evict_swapout_allowable(bo, ctx, &place, &locked, NULL)) return -EBUSY; if (!ttm_bo_get_unless_zero(bo)) { @@ -1165,21 +1158,17 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, /* * Move to system cached */ - if (bo->mem.mem_type != TTM_PL_SYSTEM) { + if (bo->resource->mem_type != TTM_PL_SYSTEM) { struct ttm_operation_ctx ctx = { false, false }; - struct ttm_resource evict_mem; - struct ttm_place place, hop; + struct ttm_resource *evict_mem; + struct ttm_place hop; - memset(&place, 0, sizeof(place)); memset(&hop, 0, sizeof(hop)); - - place.mem_type = TTM_PL_SYSTEM; - ret = ttm_resource_alloc(bo, &place, &evict_mem); if (unlikely(ret)) goto out; - ret = ttm_bo_handle_move_mem(bo, &evict_mem, true, &ctx, &hop); + ret = ttm_bo_handle_move_mem(bo, evict_mem, true, &ctx, &hop); if (unlikely(ret != 0)) { WARN(ret == -EMULTIHOP, "Unexpected multihop in swaput - likely driver bug.\n"); goto out; @@ -1202,7 +1191,8 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, if (bo->bdev->funcs->swap_notify) bo->bdev->funcs->swap_notify(bo); - ret = ttm_tt_swapout(bo->bdev, bo->ttm, gfp_flags); + if (ttm_tt_is_populated(bo->ttm)) + ret = ttm_tt_swapout(bo->bdev, bo->ttm, gfp_flags); out: /* diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index ae8b61460724..2f57f824e6db 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -31,6 +31,7 @@ #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> +#include <drm/drm_cache.h> #include <drm/drm_vma_manager.h> #include <linux/dma-buf-map.h> #include <linux/io.h> @@ -72,190 +73,112 @@ void ttm_mem_io_free(struct ttm_device *bdev, mem->bus.addr = NULL; } -static int ttm_resource_ioremap(struct ttm_device *bdev, - struct ttm_resource *mem, - void **virtual) +/** + * ttm_move_memcpy - Helper to perform a memcpy ttm move operation. + * @bo: The struct ttm_buffer_object. + * @new_mem: The struct ttm_resource we're moving to (copy destination). + * @new_iter: A struct ttm_kmap_iter representing the destination resource. + * @src_iter: A struct ttm_kmap_iter representing the source resource. + * + * This function is intended to be able to move out async under a + * dma-fence if desired. + */ +void ttm_move_memcpy(struct ttm_buffer_object *bo, + u32 num_pages, + struct ttm_kmap_iter *dst_iter, + struct ttm_kmap_iter *src_iter) { - int ret; - void *addr; - - *virtual = NULL; - ret = ttm_mem_io_reserve(bdev, mem); - if (ret || !mem->bus.is_iomem) - return ret; + const struct ttm_kmap_iter_ops *dst_ops = dst_iter->ops; + const struct ttm_kmap_iter_ops *src_ops = src_iter->ops; + struct ttm_tt *ttm = bo->ttm; + struct dma_buf_map src_map, dst_map; + pgoff_t i; - if (mem->bus.addr) { - addr = mem->bus.addr; - } else { - size_t bus_size = (size_t)mem->num_pages << PAGE_SHIFT; + /* Single TTM move. NOP */ + if (dst_ops->maps_tt && src_ops->maps_tt) + return; - if (mem->bus.caching == ttm_write_combined) - addr = ioremap_wc(mem->bus.offset, bus_size); -#ifdef CONFIG_X86 - else if (mem->bus.caching == ttm_cached) - addr = ioremap_cache(mem->bus.offset, bus_size); -#endif - else - addr = ioremap(mem->bus.offset, bus_size); - if (!addr) { - ttm_mem_io_free(bdev, mem); - return -ENOMEM; + /* Don't move nonexistent data. Clear destination instead. */ + if (src_ops->maps_tt && (!ttm || !ttm_tt_is_populated(ttm))) { + if (ttm && !(ttm->page_flags & TTM_PAGE_FLAG_ZERO_ALLOC)) + return; + + for (i = 0; i < num_pages; ++i) { + dst_ops->map_local(dst_iter, &dst_map, i); + if (dst_map.is_iomem) + memset_io(dst_map.vaddr_iomem, 0, PAGE_SIZE); + else + memset(dst_map.vaddr, 0, PAGE_SIZE); + if (dst_ops->unmap_local) + dst_ops->unmap_local(dst_iter, &dst_map); } + return; } - *virtual = addr; - return 0; -} - -static void ttm_resource_iounmap(struct ttm_device *bdev, - struct ttm_resource *mem, - void *virtual) -{ - if (virtual && mem->bus.addr == NULL) - iounmap(virtual); - ttm_mem_io_free(bdev, mem); -} - -static int ttm_copy_io_page(void *dst, void *src, unsigned long page) -{ - uint32_t *dstP = - (uint32_t *) ((unsigned long)dst + (page << PAGE_SHIFT)); - uint32_t *srcP = - (uint32_t *) ((unsigned long)src + (page << PAGE_SHIFT)); - - int i; - for (i = 0; i < PAGE_SIZE / sizeof(uint32_t); ++i) - iowrite32(ioread32(srcP++), dstP++); - return 0; -} - -static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void *src, - unsigned long page, - pgprot_t prot) -{ - struct page *d = ttm->pages[page]; - void *dst; - - if (!d) - return -ENOMEM; - - src = (void *)((unsigned long)src + (page << PAGE_SHIFT)); - dst = kmap_atomic_prot(d, prot); - if (!dst) - return -ENOMEM; - - memcpy_fromio(dst, src, PAGE_SIZE); - - kunmap_atomic(dst); - - return 0; -} - -static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst, - unsigned long page, - pgprot_t prot) -{ - struct page *s = ttm->pages[page]; - void *src; - - if (!s) - return -ENOMEM; - - dst = (void *)((unsigned long)dst + (page << PAGE_SHIFT)); - src = kmap_atomic_prot(s, prot); - if (!src) - return -ENOMEM; - memcpy_toio(dst, src, PAGE_SIZE); + for (i = 0; i < num_pages; ++i) { + dst_ops->map_local(dst_iter, &dst_map, i); + src_ops->map_local(src_iter, &src_map, i); - kunmap_atomic(src); + drm_memcpy_from_wc(&dst_map, &src_map, PAGE_SIZE); - return 0; + if (src_ops->unmap_local) + src_ops->unmap_local(src_iter, &src_map); + if (dst_ops->unmap_local) + dst_ops->unmap_local(dst_iter, &dst_map); + } } +EXPORT_SYMBOL(ttm_move_memcpy); int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, - struct ttm_resource *new_mem) + struct ttm_resource *dst_mem) { struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type); + struct ttm_resource_manager *dst_man = + ttm_manager_type(bo->bdev, dst_mem->mem_type); struct ttm_tt *ttm = bo->ttm; - struct ttm_resource *old_mem = &bo->mem; - struct ttm_resource old_copy = *old_mem; - void *old_iomap; - void *new_iomap; - int ret; - unsigned long i; - - ret = ttm_bo_wait_ctx(bo, ctx); - if (ret) - return ret; - - ret = ttm_resource_ioremap(bdev, old_mem, &old_iomap); - if (ret) - return ret; - ret = ttm_resource_ioremap(bdev, new_mem, &new_iomap); - if (ret) - goto out; - - /* - * Single TTM move. NOP. - */ - if (old_iomap == NULL && new_iomap == NULL) - goto out2; - - /* - * Don't move nonexistent data. Clear destination instead. - */ - if (old_iomap == NULL && - (ttm == NULL || (!ttm_tt_is_populated(ttm) && - !(ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)))) { - memset_io(new_iomap, 0, new_mem->num_pages*PAGE_SIZE); - goto out2; - } + struct ttm_resource *src_mem = bo->resource; + struct ttm_resource_manager *src_man = + ttm_manager_type(bdev, src_mem->mem_type); + struct ttm_resource src_copy = *src_mem; + union { + struct ttm_kmap_iter_tt tt; + struct ttm_kmap_iter_linear_io io; + } _dst_iter, _src_iter; + struct ttm_kmap_iter *dst_iter, *src_iter; + int ret = 0; - /* - * TTM might be null for moves within the same region. - */ - if (ttm) { + if (ttm && ((ttm->page_flags & TTM_PAGE_FLAG_SWAPPED) || + dst_man->use_tt)) { ret = ttm_tt_populate(bdev, ttm, ctx); if (ret) - goto out1; + return ret; } - for (i = 0; i < new_mem->num_pages; ++i) { - if (old_iomap == NULL) { - pgprot_t prot = ttm_io_prot(bo, old_mem, PAGE_KERNEL); - ret = ttm_copy_ttm_io_page(ttm, new_iomap, i, - prot); - } else if (new_iomap == NULL) { - pgprot_t prot = ttm_io_prot(bo, new_mem, PAGE_KERNEL); - ret = ttm_copy_io_ttm_page(ttm, old_iomap, i, - prot); - } else { - ret = ttm_copy_io_page(new_iomap, old_iomap, i); - } - if (ret) - goto out1; + dst_iter = ttm_kmap_iter_linear_io_init(&_dst_iter.io, bdev, dst_mem); + if (PTR_ERR(dst_iter) == -EINVAL && dst_man->use_tt) + dst_iter = ttm_kmap_iter_tt_init(&_dst_iter.tt, bo->ttm); + if (IS_ERR(dst_iter)) + return PTR_ERR(dst_iter); + + src_iter = ttm_kmap_iter_linear_io_init(&_src_iter.io, bdev, src_mem); + if (PTR_ERR(src_iter) == -EINVAL && src_man->use_tt) + src_iter = ttm_kmap_iter_tt_init(&_src_iter.tt, bo->ttm); + if (IS_ERR(src_iter)) { + ret = PTR_ERR(src_iter); + goto out_src_iter; } - mb(); -out2: - old_copy = *old_mem; - ttm_bo_assign_mem(bo, new_mem); + ttm_move_memcpy(bo, dst_mem->num_pages, dst_iter, src_iter); + src_copy = *src_mem; + ttm_bo_move_sync_cleanup(bo, dst_mem); - if (!man->use_tt) - ttm_bo_tt_destroy(bo); + if (!src_iter->ops->maps_tt) + ttm_kmap_iter_linear_io_fini(&_src_iter.io, bdev, &src_copy); +out_src_iter: + if (!dst_iter->ops->maps_tt) + ttm_kmap_iter_linear_io_fini(&_dst_iter.io, bdev, dst_mem); -out1: - ttm_resource_iounmap(bdev, old_mem, new_iomap); -out: - ttm_resource_iounmap(bdev, &old_copy, old_iomap); - - /* - * On error, keep the mm node! - */ - if (!ret) - ttm_resource_free(bo, &old_copy); return ret; } EXPORT_SYMBOL(ttm_bo_move_memcpy); @@ -336,27 +259,7 @@ pgprot_t ttm_io_prot(struct ttm_buffer_object *bo, struct ttm_resource *res, man = ttm_manager_type(bo->bdev, res->mem_type); caching = man->use_tt ? bo->ttm->caching : res->bus.caching; - /* Cached mappings need no adjustment */ - if (caching == ttm_cached) - return tmp; - -#if defined(__i386__) || defined(__x86_64__) - if (caching == ttm_write_combined) - tmp = pgprot_writecombine(tmp); - else if (boot_cpu_data.x86 > 3) - tmp = pgprot_noncached(tmp); -#endif -#if defined(__ia64__) || defined(__arm__) || defined(__aarch64__) || \ - defined(__powerpc__) || defined(__mips__) - if (caching == ttm_write_combined) - tmp = pgprot_writecombine(tmp); - else - tmp = pgprot_noncached(tmp); -#endif -#if defined(__sparc__) - tmp = pgprot_noncached(tmp); -#endif - return tmp; + return ttm_prot_from_caching(caching, tmp); } EXPORT_SYMBOL(ttm_io_prot); @@ -365,24 +268,23 @@ static int ttm_bo_ioremap(struct ttm_buffer_object *bo, unsigned long size, struct ttm_bo_kmap_obj *map) { - struct ttm_resource *mem = &bo->mem; + struct ttm_resource *mem = bo->resource; - if (bo->mem.bus.addr) { + if (bo->resource->bus.addr) { map->bo_kmap_type = ttm_bo_map_premapped; - map->virtual = (void *)(((u8 *)bo->mem.bus.addr) + offset); + map->virtual = ((u8 *)bo->resource->bus.addr) + offset; } else { + resource_size_t res = bo->resource->bus.offset + offset; + map->bo_kmap_type = ttm_bo_map_iomap; if (mem->bus.caching == ttm_write_combined) - map->virtual = ioremap_wc(bo->mem.bus.offset + offset, - size); + map->virtual = ioremap_wc(res, size); #ifdef CONFIG_X86 else if (mem->bus.caching == ttm_cached) - map->virtual = ioremap_cache(bo->mem.bus.offset + offset, - size); + map->virtual = ioremap_cache(res, size); #endif else - map->virtual = ioremap(bo->mem.bus.offset + offset, - size); + map->virtual = ioremap(res, size); } return (!map->virtual) ? -ENOMEM : 0; } @@ -392,7 +294,7 @@ static int ttm_bo_kmap_ttm(struct ttm_buffer_object *bo, unsigned long num_pages, struct ttm_bo_kmap_obj *map) { - struct ttm_resource *mem = &bo->mem; + struct ttm_resource *mem = bo->resource; struct ttm_operation_ctx ctx = { .interruptible = false, .no_wait_gpu = false @@ -438,15 +340,15 @@ int ttm_bo_kmap(struct ttm_buffer_object *bo, map->virtual = NULL; map->bo = bo; - if (num_pages > bo->mem.num_pages) + if (num_pages > bo->resource->num_pages) return -EINVAL; - if ((start_page + num_pages) > bo->mem.num_pages) + if ((start_page + num_pages) > bo->resource->num_pages) return -EINVAL; - ret = ttm_mem_io_reserve(bo->bdev, &bo->mem); + ret = ttm_mem_io_reserve(bo->bdev, bo->resource); if (ret) return ret; - if (!bo->mem.bus.is_iomem) { + if (!bo->resource->bus.is_iomem) { return ttm_bo_kmap_ttm(bo, start_page, num_pages, map); } else { offset = start_page << PAGE_SHIFT; @@ -475,7 +377,7 @@ void ttm_bo_kunmap(struct ttm_bo_kmap_obj *map) default: BUG(); } - ttm_mem_io_free(map->bo->bdev, &map->bo->mem); + ttm_mem_io_free(map->bo->bdev, map->bo->resource); map->virtual = NULL; map->page = NULL; } @@ -483,7 +385,7 @@ EXPORT_SYMBOL(ttm_bo_kunmap); int ttm_bo_vmap(struct ttm_buffer_object *bo, struct dma_buf_map *map) { - struct ttm_resource *mem = &bo->mem; + struct ttm_resource *mem = bo->resource; int ret; ret = ttm_mem_io_reserve(bo->bdev, mem); @@ -542,7 +444,7 @@ EXPORT_SYMBOL(ttm_bo_vmap); void ttm_bo_vunmap(struct ttm_buffer_object *bo, struct dma_buf_map *map) { - struct ttm_resource *mem = &bo->mem; + struct ttm_resource *mem = bo->resource; if (dma_buf_map_is_null(map)) return; @@ -553,7 +455,7 @@ void ttm_bo_vunmap(struct ttm_buffer_object *bo, struct dma_buf_map *map) iounmap(map->vaddr_iomem); dma_buf_map_clear(map); - ttm_mem_io_free(bo->bdev, &bo->mem); + ttm_mem_io_free(bo->bdev, bo->resource); } EXPORT_SYMBOL(ttm_bo_vunmap); @@ -567,7 +469,7 @@ static int ttm_bo_wait_free_node(struct ttm_buffer_object *bo, if (!dst_use_tt) ttm_bo_tt_destroy(bo); - ttm_resource_free(bo, &bo->mem); + ttm_resource_free(bo, &bo->resource); return 0; } @@ -605,6 +507,7 @@ static int ttm_bo_move_to_ghost(struct ttm_buffer_object *bo, ghost_obj->ttm = NULL; else bo->ttm = NULL; + bo->resource = NULL; dma_resv_unlock(&ghost_obj->base._resv); ttm_bo_put(ghost_obj); @@ -615,7 +518,9 @@ static void ttm_bo_move_pipeline_evict(struct ttm_buffer_object *bo, struct dma_fence *fence) { struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *from = ttm_manager_type(bdev, bo->mem.mem_type); + struct ttm_resource_manager *from; + + from = ttm_manager_type(bdev, bo->resource->mem_type); /** * BO doesn't have a TTM we need to bind/unbind. Just remember @@ -628,7 +533,7 @@ static void ttm_bo_move_pipeline_evict(struct ttm_buffer_object *bo, } spin_unlock(&from->move_lock); - ttm_resource_free(bo, &bo->mem); + ttm_resource_free(bo, &bo->resource); dma_fence_put(bo->moving); bo->moving = dma_fence_get(fence); @@ -641,7 +546,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, struct ttm_resource *new_mem) { struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *from = ttm_manager_type(bdev, bo->mem.mem_type); + struct ttm_resource_manager *from = ttm_manager_type(bdev, bo->resource->mem_type); struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type); int ret = 0; @@ -662,26 +567,82 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, } EXPORT_SYMBOL(ttm_bo_move_accel_cleanup); +/** + * ttm_bo_pipeline_gutting - purge the contents of a bo + * @bo: The buffer object + * + * Purge the contents of a bo, async if the bo is not idle. + * After a successful call, the bo is left unpopulated in + * system placement. The function may wait uninterruptible + * for idle on OOM. + * + * Return: 0 if successful, negative error code on failure. + */ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo) { static const struct ttm_place sys_mem = { .mem_type = TTM_PL_SYSTEM }; struct ttm_buffer_object *ghost; + struct ttm_resource *sys_res; + struct ttm_tt *ttm; int ret; - ret = ttm_buffer_object_transfer(bo, &ghost); + ret = ttm_resource_alloc(bo, &sys_mem, &sys_res); if (ret) return ret; + /* If already idle, no need for ghost object dance. */ + ret = ttm_bo_wait(bo, false, true); + if (ret != -EBUSY) { + if (!bo->ttm) { + /* See comment below about clearing. */ + ret = ttm_tt_create(bo, true); + if (ret) + goto error_free_sys_mem; + } else { + ttm_tt_unpopulate(bo->bdev, bo->ttm); + if (bo->type == ttm_bo_type_device) + ttm_tt_mark_for_clear(bo->ttm); + } + ttm_resource_free(bo, &bo->resource); + ttm_bo_assign_mem(bo, sys_res); + return 0; + } + + /* + * We need an unpopulated ttm_tt after giving our current one, + * if any, to the ghost object. And we can't afford to fail + * creating one *after* the operation. If the bo subsequently gets + * resurrected, make sure it's cleared (if ttm_bo_type_device) + * to avoid leaking sensitive information to user-space. + */ + + ttm = bo->ttm; + bo->ttm = NULL; + ret = ttm_tt_create(bo, true); + swap(bo->ttm, ttm); + if (ret) + goto error_free_sys_mem; + + ret = ttm_buffer_object_transfer(bo, &ghost); + if (ret) + goto error_destroy_tt; + ret = dma_resv_copy_fences(&ghost->base._resv, bo->base.resv); /* Last resort, wait for the BO to be idle when we are OOM */ if (ret) ttm_bo_wait(bo, false, false); - ttm_resource_alloc(bo, &sys_mem, &bo->mem); - bo->ttm = NULL; - dma_resv_unlock(&ghost->base._resv); ttm_bo_put(ghost); - + bo->ttm = ttm; + bo->resource = NULL; + ttm_bo_assign_mem(bo, sys_res); return 0; + +error_destroy_tt: + ttm_tt_destroy(bo->bdev, ttm); + +error_free_sys_mem: + ttm_resource_free(bo, &sys_res); + return ret; } diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 9bd15cb39145..f56be5bc0861 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -102,7 +102,7 @@ static unsigned long ttm_bo_io_mem_pfn(struct ttm_buffer_object *bo, if (bdev->funcs->io_mem_pfn) return bdev->funcs->io_mem_pfn(bo, page_offset); - return (bo->mem.bus.offset >> PAGE_SHIFT) + page_offset; + return (bo->resource->bus.offset >> PAGE_SHIFT) + page_offset; } /** @@ -200,10 +200,10 @@ static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf, /* Fault should not cross bo boundary. */ page_offset &= ~(fault_page_size - 1); - if (page_offset + fault_page_size > bo->mem.num_pages) + if (page_offset + fault_page_size > bo->resource->num_pages) goto out_fallback; - if (bo->mem.bus.is_iomem) + if (bo->resource->bus.is_iomem) pfn = ttm_bo_io_mem_pfn(bo, page_offset); else pfn = page_to_pfn(ttm->pages[page_offset]); @@ -213,7 +213,7 @@ static vm_fault_t ttm_bo_vm_insert_huge(struct vm_fault *vmf, goto out_fallback; /* Check that memory is contiguous. */ - if (!bo->mem.bus.is_iomem) { + if (!bo->resource->bus.is_iomem) { for (i = 1; i < fault_page_size; ++i) { if (page_to_pfn(ttm->pages[page_offset + i]) != pfn + i) goto out_fallback; @@ -299,7 +299,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, if (unlikely(ret != 0)) return ret; - err = ttm_mem_io_reserve(bdev, &bo->mem); + err = ttm_mem_io_reserve(bdev, bo->resource); if (unlikely(err != 0)) return VM_FAULT_SIGBUS; @@ -308,11 +308,11 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, page_last = vma_pages(vma) + vma->vm_pgoff - drm_vma_node_start(&bo->base.vma_node); - if (unlikely(page_offset >= bo->mem.num_pages)) + if (unlikely(page_offset >= bo->resource->num_pages)) return VM_FAULT_SIGBUS; - prot = ttm_io_prot(bo, &bo->mem, prot); - if (!bo->mem.bus.is_iomem) { + prot = ttm_io_prot(bo, bo->resource, prot); + if (!bo->resource->bus.is_iomem) { struct ttm_operation_ctx ctx = { .interruptible = false, .no_wait_gpu = false, @@ -337,7 +337,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, * first page. */ for (i = 0; i < num_prefault; ++i) { - if (bo->mem.bus.is_iomem) { + if (bo->resource->bus.is_iomem) { pfn = ttm_bo_io_mem_pfn(bo, page_offset); } else { page = ttm->pages[page_offset]; @@ -359,12 +359,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, * at arbitrary times while the data is mmap'ed. * See vmf_insert_mixed_prot() for a discussion. */ - if (vma->vm_flags & VM_MIXEDMAP) - ret = vmf_insert_mixed_prot(vma, address, - __pfn_to_pfn_t(pfn, PFN_DEV), - prot); - else - ret = vmf_insert_pfn_prot(vma, address, pfn, prot); + ret = vmf_insert_pfn_prot(vma, address, pfn, prot); /* Never error on prefaulted PTEs */ if (unlikely((ret & VM_FAULT_ERROR))) { @@ -411,15 +406,9 @@ vm_fault_t ttm_bo_vm_dummy_page(struct vm_fault *vmf, pgprot_t prot) pfn = page_to_pfn(page); /* Prefault the entire VMA range right away to avoid further faults */ - for (address = vma->vm_start; address < vma->vm_end; address += PAGE_SIZE) { - - if (vma->vm_flags & VM_MIXEDMAP) - ret = vmf_insert_mixed_prot(vma, address, - __pfn_to_pfn_t(pfn, PFN_DEV), - prot); - else - ret = vmf_insert_pfn_prot(vma, address, pfn, prot); - } + for (address = vma->vm_start; address < vma->vm_end; + address += PAGE_SIZE) + ret = vmf_insert_pfn_prot(vma, address, pfn, prot); return ret; } @@ -521,14 +510,14 @@ int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr, << PAGE_SHIFT); int ret; - if (len < 1 || (offset + len) >> PAGE_SHIFT > bo->mem.num_pages) + if (len < 1 || (offset + len) >> PAGE_SHIFT > bo->resource->num_pages) return -EIO; ret = ttm_bo_reserve(bo, true, false, NULL); if (ret) return ret; - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_SYSTEM: if (unlikely(bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)) { ret = ttm_tt_swapin(bo->ttm); @@ -560,8 +549,14 @@ static const struct vm_operations_struct ttm_bo_vm_ops = { .access = ttm_bo_vm_access, }; -static void ttm_bo_mmap_vma_setup(struct ttm_buffer_object *bo, struct vm_area_struct *vma) +int ttm_bo_mmap_obj(struct vm_area_struct *vma, struct ttm_buffer_object *bo) { + /* Enforce no COW since would have really strange behavior with it. */ + if (is_cow_mapping(vma->vm_flags)) + return -EINVAL; + + ttm_bo_get(bo); + /* * Drivers may want to override the vm_ops field. Otherwise we * use TTM's default callbacks. @@ -576,21 +571,8 @@ static void ttm_bo_mmap_vma_setup(struct ttm_buffer_object *bo, struct vm_area_s vma->vm_private_data = bo; - /* - * We'd like to use VM_PFNMAP on shared mappings, where - * (vma->vm_flags & VM_SHARED) != 0, for performance reasons, - * but for some reason VM_PFNMAP + x86 PAT + write-combine is very - * bad for performance. Until that has been sorted out, use - * VM_MIXEDMAP on all mappings. See freedesktop.org bug #75719 - */ - vma->vm_flags |= VM_MIXEDMAP; + vma->vm_flags |= VM_PFNMAP; vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; -} - -int ttm_bo_mmap_obj(struct vm_area_struct *vma, struct ttm_buffer_object *bo) -{ - ttm_bo_get(bo); - ttm_bo_mmap_vma_setup(bo, vma); return 0; } EXPORT_SYMBOL(ttm_bo_mmap_obj); diff --git a/drivers/gpu/drm/ttm/ttm_module.c b/drivers/gpu/drm/ttm/ttm_module.c index 56b0efdba1a9..997c458f68a9 100644 --- a/drivers/gpu/drm/ttm/ttm_module.c +++ b/drivers/gpu/drm/ttm/ttm_module.c @@ -31,12 +31,47 @@ */ #include <linux/module.h> #include <linux/device.h> +#include <linux/pgtable.h> #include <linux/sched.h> #include <linux/debugfs.h> #include <drm/drm_sysfs.h> +#include <drm/ttm/ttm_caching.h> #include "ttm_module.h" +/** + * ttm_prot_from_caching - Modify the page protection according to the + * ttm cacing mode + * @caching: The ttm caching mode + * @tmp: The original page protection + * + * Return: The modified page protection + */ +pgprot_t ttm_prot_from_caching(enum ttm_caching caching, pgprot_t tmp) +{ + /* Cached mappings need no adjustment */ + if (caching == ttm_cached) + return tmp; + +#if defined(__i386__) || defined(__x86_64__) + if (caching == ttm_write_combined) + tmp = pgprot_writecombine(tmp); + else if (boot_cpu_data.x86 > 3) + tmp = pgprot_noncached(tmp); +#endif +#if defined(__ia64__) || defined(__arm__) || defined(__aarch64__) || \ + defined(__powerpc__) || defined(__mips__) + if (caching == ttm_write_combined) + tmp = pgprot_writecombine(tmp); + else + tmp = pgprot_noncached(tmp); +#endif +#if defined(__sparc__) + tmp = pgprot_noncached(tmp); +#endif + return tmp; +} + struct dentry *ttm_debugfs_root; static int __init ttm_init(void) diff --git a/drivers/gpu/drm/ttm/ttm_range_manager.c b/drivers/gpu/drm/ttm/ttm_range_manager.c index b9d5da6e6a81..03395386e8a7 100644 --- a/drivers/gpu/drm/ttm/ttm_range_manager.c +++ b/drivers/gpu/drm/ttm/ttm_range_manager.c @@ -29,12 +29,13 @@ * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com> */ -#include <drm/ttm/ttm_bo_driver.h> +#include <drm/ttm/ttm_device.h> #include <drm/ttm/ttm_placement.h> +#include <drm/ttm/ttm_range_manager.h> +#include <drm/ttm/ttm_bo_api.h> #include <drm/drm_mm.h> #include <linux/slab.h> #include <linux/spinlock.h> -#include <linux/module.h> /* * Currently we use a spinlock for the lock, but a mutex *may* be @@ -57,11 +58,11 @@ to_range_manager(struct ttm_resource_manager *man) static int ttm_range_man_alloc(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *mem) + struct ttm_resource **res) { struct ttm_range_manager *rman = to_range_manager(man); + struct ttm_range_mgr_node *node; struct drm_mm *mm = &rman->mm; - struct drm_mm_node *node; enum drm_mm_insert_mode mode; unsigned long lpfn; int ret; @@ -70,7 +71,7 @@ static int ttm_range_man_alloc(struct ttm_resource_manager *man, if (!lpfn) lpfn = man->size; - node = kzalloc(sizeof(*node), GFP_KERNEL); + node = kzalloc(struct_size(node, mm_nodes, 1), GFP_KERNEL); if (!node) return -ENOMEM; @@ -78,35 +79,36 @@ static int ttm_range_man_alloc(struct ttm_resource_manager *man, if (place->flags & TTM_PL_FLAG_TOPDOWN) mode = DRM_MM_INSERT_HIGH; + ttm_resource_init(bo, place, &node->base); + spin_lock(&rman->lock); - ret = drm_mm_insert_node_in_range(mm, node, mem->num_pages, + ret = drm_mm_insert_node_in_range(mm, &node->mm_nodes[0], + node->base.num_pages, bo->page_alignment, 0, place->fpfn, lpfn, mode); spin_unlock(&rman->lock); if (unlikely(ret)) { kfree(node); - } else { - mem->mm_node = node; - mem->start = node->start; + return ret; } - return ret; + node->base.start = node->mm_nodes[0].start; + *res = &node->base; + return 0; } static void ttm_range_man_free(struct ttm_resource_manager *man, - struct ttm_resource *mem) + struct ttm_resource *res) { + struct ttm_range_mgr_node *node = to_ttm_range_mgr_node(res); struct ttm_range_manager *rman = to_range_manager(man); - if (mem->mm_node) { - spin_lock(&rman->lock); - drm_mm_remove_node(mem->mm_node); - spin_unlock(&rman->lock); + spin_lock(&rman->lock); + drm_mm_remove_node(&node->mm_nodes[0]); + spin_unlock(&rman->lock); - kfree(mem->mm_node); - mem->mm_node = NULL; - } + kfree(node); } static void ttm_range_man_debug(struct ttm_resource_manager *man, @@ -125,6 +127,17 @@ static const struct ttm_resource_manager_func ttm_range_manager_func = { .debug = ttm_range_man_debug }; +/** + * ttm_range_man_init + * + * @bdev: ttm device + * @type: memory manager type + * @use_tt: if the memory manager uses tt + * @p_size: size of area to be managed in pages. + * + * Initialise a generic range manager for the selected memory type. + * The range manager is installed for this device in the type slot. + */ int ttm_range_man_init(struct ttm_device *bdev, unsigned type, bool use_tt, unsigned long p_size) @@ -152,6 +165,14 @@ int ttm_range_man_init(struct ttm_device *bdev, } EXPORT_SYMBOL(ttm_range_man_init); +/** + * ttm_range_man_fini + * + * @bdev: ttm device + * @type: memory manager type + * + * Remove the generic range manager from a slot and tear it down. + */ int ttm_range_man_fini(struct ttm_device *bdev, unsigned type) { diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c index 59e2b7157e41..2431717376e7 100644 --- a/drivers/gpu/drm/ttm/ttm_resource.c +++ b/drivers/gpu/drm/ttm/ttm_resource.c @@ -22,17 +22,17 @@ * Authors: Christian König */ +#include <linux/dma-buf-map.h> +#include <linux/io-mapping.h> +#include <linux/scatterlist.h> + #include <drm/ttm/ttm_resource.h> #include <drm/ttm/ttm_bo_driver.h> -int ttm_resource_alloc(struct ttm_buffer_object *bo, - const struct ttm_place *place, - struct ttm_resource *res) +void ttm_resource_init(struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource *res) { - struct ttm_resource_manager *man = - ttm_manager_type(bo->bdev, place->mem_type); - - res->mm_node = NULL; res->start = 0; res->num_pages = PFN_UP(bo->base.size); res->mem_type = place->mem_type; @@ -41,18 +41,29 @@ int ttm_resource_alloc(struct ttm_buffer_object *bo, res->bus.offset = 0; res->bus.is_iomem = false; res->bus.caching = ttm_cached; - - return man->func->alloc(man, bo, place, res); } +EXPORT_SYMBOL(ttm_resource_init); -void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource *res) +int ttm_resource_alloc(struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource **res_ptr) { struct ttm_resource_manager *man = - ttm_manager_type(bo->bdev, res->mem_type); + ttm_manager_type(bo->bdev, place->mem_type); - man->func->free(man, res); - res->mm_node = NULL; - res->mem_type = TTM_PL_SYSTEM; + return man->func->alloc(man, bo, place, res_ptr); +} + +void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res) +{ + struct ttm_resource_manager *man; + + if (!*res) + return; + + man = ttm_manager_type(bo->bdev, (*res)->mem_type); + man->func->free(man, *res); + *res = NULL; } EXPORT_SYMBOL(ttm_resource_free); @@ -147,3 +158,192 @@ void ttm_resource_manager_debug(struct ttm_resource_manager *man, man->func->debug(man, p); } EXPORT_SYMBOL(ttm_resource_manager_debug); + +static void ttm_kmap_iter_iomap_map_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *dmap, + pgoff_t i) +{ + struct ttm_kmap_iter_iomap *iter_io = + container_of(iter, typeof(*iter_io), base); + void __iomem *addr; + +retry: + while (i >= iter_io->cache.end) { + iter_io->cache.sg = iter_io->cache.sg ? + sg_next(iter_io->cache.sg) : iter_io->st->sgl; + iter_io->cache.i = iter_io->cache.end; + iter_io->cache.end += sg_dma_len(iter_io->cache.sg) >> + PAGE_SHIFT; + iter_io->cache.offs = sg_dma_address(iter_io->cache.sg) - + iter_io->start; + } + + if (i < iter_io->cache.i) { + iter_io->cache.end = 0; + iter_io->cache.sg = NULL; + goto retry; + } + + addr = io_mapping_map_local_wc(iter_io->iomap, iter_io->cache.offs + + (((resource_size_t)i - iter_io->cache.i) + << PAGE_SHIFT)); + dma_buf_map_set_vaddr_iomem(dmap, addr); +} + +static void ttm_kmap_iter_iomap_unmap_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *map) +{ + io_mapping_unmap_local(map->vaddr_iomem); +} + +static const struct ttm_kmap_iter_ops ttm_kmap_iter_io_ops = { + .map_local = ttm_kmap_iter_iomap_map_local, + .unmap_local = ttm_kmap_iter_iomap_unmap_local, + .maps_tt = false, +}; + +/** + * ttm_kmap_iter_iomap_init - Initialize a struct ttm_kmap_iter_iomap + * @iter_io: The struct ttm_kmap_iter_iomap to initialize. + * @iomap: The struct io_mapping representing the underlying linear io_memory. + * @st: sg_table into @iomap, representing the memory of the struct + * ttm_resource. + * @start: Offset that needs to be subtracted from @st to make + * sg_dma_address(st->sgl) - @start == 0 for @iomap start. + * + * Return: Pointer to the embedded struct ttm_kmap_iter. + */ +struct ttm_kmap_iter * +ttm_kmap_iter_iomap_init(struct ttm_kmap_iter_iomap *iter_io, + struct io_mapping *iomap, + struct sg_table *st, + resource_size_t start) +{ + iter_io->base.ops = &ttm_kmap_iter_io_ops; + iter_io->iomap = iomap; + iter_io->st = st; + iter_io->start = start; + memset(&iter_io->cache, 0, sizeof(iter_io->cache)); + + return &iter_io->base; +} +EXPORT_SYMBOL(ttm_kmap_iter_iomap_init); + +/** + * DOC: Linear io iterator + * + * This code should die in the not too near future. Best would be if we could + * make io-mapping use memremap for all io memory, and have memremap + * implement a kmap_local functionality. We could then strip a huge amount of + * code. These linear io iterators are implemented to mimic old functionality, + * and they don't use kmap_local semantics at all internally. Rather ioremap or + * friends, and at least on 32-bit they add global TLB flushes and points + * of failure. + */ + +static void ttm_kmap_iter_linear_io_map_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *dmap, + pgoff_t i) +{ + struct ttm_kmap_iter_linear_io *iter_io = + container_of(iter, typeof(*iter_io), base); + + *dmap = iter_io->dmap; + dma_buf_map_incr(dmap, i * PAGE_SIZE); +} + +static const struct ttm_kmap_iter_ops ttm_kmap_iter_linear_io_ops = { + .map_local = ttm_kmap_iter_linear_io_map_local, + .maps_tt = false, +}; + +/** + * ttm_kmap_iter_linear_io_init - Initialize an iterator for linear io memory + * @iter_io: The iterator to initialize + * @bdev: The TTM device + * @mem: The ttm resource representing the iomap. + * + * This function is for internal TTM use only. It sets up a memcpy kmap iterator + * pointing at a linear chunk of io memory. + * + * Return: A pointer to the embedded struct ttm_kmap_iter or error pointer on + * failure. + */ +struct ttm_kmap_iter * +ttm_kmap_iter_linear_io_init(struct ttm_kmap_iter_linear_io *iter_io, + struct ttm_device *bdev, + struct ttm_resource *mem) +{ + int ret; + + ret = ttm_mem_io_reserve(bdev, mem); + if (ret) + goto out_err; + if (!mem->bus.is_iomem) { + ret = -EINVAL; + goto out_io_free; + } + + if (mem->bus.addr) { + dma_buf_map_set_vaddr(&iter_io->dmap, mem->bus.addr); + iter_io->needs_unmap = false; + } else { + size_t bus_size = (size_t)mem->num_pages << PAGE_SHIFT; + + iter_io->needs_unmap = true; + memset(&iter_io->dmap, 0, sizeof(iter_io->dmap)); + if (mem->bus.caching == ttm_write_combined) + dma_buf_map_set_vaddr_iomem(&iter_io->dmap, + ioremap_wc(mem->bus.offset, + bus_size)); + else if (mem->bus.caching == ttm_cached) + dma_buf_map_set_vaddr(&iter_io->dmap, + memremap(mem->bus.offset, bus_size, + MEMREMAP_WB | + MEMREMAP_WT | + MEMREMAP_WC)); + + /* If uncached requested or if mapping cached or wc failed */ + if (dma_buf_map_is_null(&iter_io->dmap)) + dma_buf_map_set_vaddr_iomem(&iter_io->dmap, + ioremap(mem->bus.offset, + bus_size)); + + if (dma_buf_map_is_null(&iter_io->dmap)) { + ret = -ENOMEM; + goto out_io_free; + } + } + + iter_io->base.ops = &ttm_kmap_iter_linear_io_ops; + return &iter_io->base; + +out_io_free: + ttm_mem_io_free(bdev, mem); +out_err: + return ERR_PTR(ret); +} + +/** + * ttm_kmap_iter_linear_io_fini - Clean up an iterator for linear io memory + * @iter_io: The iterator to initialize + * @bdev: The TTM device + * @mem: The ttm resource representing the iomap. + * + * This function is for internal TTM use only. It cleans up a memcpy kmap + * iterator initialized by ttm_kmap_iter_linear_io_init. + */ +void +ttm_kmap_iter_linear_io_fini(struct ttm_kmap_iter_linear_io *iter_io, + struct ttm_device *bdev, + struct ttm_resource *mem) +{ + if (iter_io->needs_unmap && dma_buf_map_is_set(&iter_io->dmap)) { + if (iter_io->dmap.is_iomem) + iounmap(iter_io->dmap.vaddr_iomem); + else + memunmap(iter_io->dmap.vaddr); + } + + ttm_mem_io_free(bdev, mem); +} diff --git a/drivers/gpu/drm/ttm/ttm_sys_manager.c b/drivers/gpu/drm/ttm/ttm_sys_manager.c index 474221e863d0..63aca52f75e1 100644 --- a/drivers/gpu/drm/ttm/ttm_sys_manager.c +++ b/drivers/gpu/drm/ttm/ttm_sys_manager.c @@ -3,20 +3,27 @@ #include <drm/ttm/ttm_resource.h> #include <drm/ttm/ttm_device.h> #include <drm/ttm/ttm_placement.h> +#include <linux/slab.h> #include "ttm_module.h" static int ttm_sys_man_alloc(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *mem) + struct ttm_resource **res) { + *res = kzalloc(sizeof(**res), GFP_KERNEL); + if (!*res) + return -ENOMEM; + + ttm_resource_init(bo, place, *res); return 0; } static void ttm_sys_man_free(struct ttm_resource_manager *man, - struct ttm_resource *mem) + struct ttm_resource *res) { + kfree(res); } static const struct ttm_resource_manager_func ttm_sys_manager_func = { diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 539e0232cb3b..24031a8acd2d 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -415,7 +415,7 @@ DEFINE_SHOW_ATTRIBUTE(ttm_tt_debugfs_shrink); #endif -/** +/* * ttm_tt_mgr_init - register with the MM shrinker * * Register with the MM shrinker for swapping out BOs. @@ -433,3 +433,48 @@ void ttm_tt_mgr_init(unsigned long num_pages, unsigned long num_dma32_pages) if (!ttm_dma32_pages_limit) ttm_dma32_pages_limit = num_dma32_pages; } + +static void ttm_kmap_iter_tt_map_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *dmap, + pgoff_t i) +{ + struct ttm_kmap_iter_tt *iter_tt = + container_of(iter, typeof(*iter_tt), base); + + dma_buf_map_set_vaddr(dmap, kmap_local_page_prot(iter_tt->tt->pages[i], + iter_tt->prot)); +} + +static void ttm_kmap_iter_tt_unmap_local(struct ttm_kmap_iter *iter, + struct dma_buf_map *map) +{ + kunmap_local(map->vaddr); +} + +static const struct ttm_kmap_iter_ops ttm_kmap_iter_tt_ops = { + .map_local = ttm_kmap_iter_tt_map_local, + .unmap_local = ttm_kmap_iter_tt_unmap_local, + .maps_tt = true, +}; + +/** + * ttm_kmap_iter_tt_init - Initialize a struct ttm_kmap_iter_tt + * @iter_tt: The struct ttm_kmap_iter_tt to initialize. + * @tt: Struct ttm_tt holding page pointers of the struct ttm_resource. + * + * Return: Pointer to the embedded struct ttm_kmap_iter. + */ +struct ttm_kmap_iter * +ttm_kmap_iter_tt_init(struct ttm_kmap_iter_tt *iter_tt, + struct ttm_tt *tt) +{ + iter_tt->base.ops = &ttm_kmap_iter_tt_ops; + iter_tt->tt = tt; + if (tt) + iter_tt->prot = ttm_prot_from_caching(tt->caching, PAGE_KERNEL); + else + iter_tt->prot = PAGE_KERNEL; + + return &iter_tt->base; +} +EXPORT_SYMBOL(ttm_kmap_iter_tt_init); diff --git a/drivers/gpu/drm/vboxvideo/hgsmi_base.c b/drivers/gpu/drm/vboxvideo/hgsmi_base.c index 361d3193258e..8c041d7ce4f1 100644 --- a/drivers/gpu/drm/vboxvideo/hgsmi_base.c +++ b/drivers/gpu/drm/vboxvideo/hgsmi_base.c @@ -9,7 +9,8 @@ #include "hgsmi_ch_setup.h" /** - * Inform the host of the location of the host flags in VRAM via an HGSMI cmd. + * hgsmi_report_flags_location - Inform the host of the location of + * the host flags in VRAM via an HGSMI cmd. * Return: 0 or negative errno value. * @ctx: The context of the guest heap to use. * @location: The offset chosen for the flags within guest VRAM. @@ -33,7 +34,8 @@ int hgsmi_report_flags_location(struct gen_pool *ctx, u32 location) } /** - * Notify the host of HGSMI-related guest capabilities via an HGSMI command. + * hgsmi_send_caps_info - Notify the host of HGSMI-related guest capabilities + * via an HGSMI command. * Return: 0 or negative errno value. * @ctx: The context of the guest heap to use. * @caps: The capabilities to report, see vbva_caps. @@ -71,7 +73,8 @@ int hgsmi_test_query_conf(struct gen_pool *ctx) } /** - * Query the host for an HGSMI configuration parameter via an HGSMI command. + * hgsmi_query_conf - Query the host for an HGSMI configuration + * parameter via an HGSMI command. * Return: 0 or negative errno value. * @ctx: The context containing the heap used. * @index: The index of the parameter to query. @@ -99,7 +102,8 @@ int hgsmi_query_conf(struct gen_pool *ctx, u32 index, u32 *value_ret) } /** - * Pass the host a new mouse pointer shape via an HGSMI command. + * hgsmi_update_pointer_shape - Pass the host a new mouse pointer shape + * via an HGSMI command. * Return: 0 or negative errno value. * @ctx: The context containing the heap to be used. * @flags: Cursor flags. @@ -171,9 +175,10 @@ int hgsmi_update_pointer_shape(struct gen_pool *ctx, u32 flags, } /** - * Report the guest cursor position. The host may wish to use this information - * to re-position its own cursor (though this is currently unlikely). The - * current host cursor position is returned. + * hgsmi_cursor_position - Report the guest cursor position. The host may + * wish to use this information to re-position its + * own cursor (though this is currently unlikely). + * The current host cursor position is returned. * Return: 0 or negative errno value. * @ctx: The context containing the heap used. * @report_position: Are we reporting a position? diff --git a/drivers/gpu/drm/vboxvideo/modesetting.c b/drivers/gpu/drm/vboxvideo/modesetting.c index 7580b9002379..10b32d986b95 100644 --- a/drivers/gpu/drm/vboxvideo/modesetting.c +++ b/drivers/gpu/drm/vboxvideo/modesetting.c @@ -8,9 +8,11 @@ #include "hgsmi_channels.h" /** - * Set a video mode via an HGSMI request. The views must have been - * initialised first using @a VBoxHGSMISendViewInfo and if the mode is being - * set on the first display then it must be set first using registers. + * hgsmi_process_display_info - Set a video mode via an HGSMI request. + * The views must have been initialised first + * using @a VBoxHGSMISendViewInfo and if the mode + * is being set on the first display then it must + * be set first using registers. * @ctx: The context containing the heap to use. * @display: The screen number. * @origin_x: The horizontal displacement relative to the first scrn. @@ -51,10 +53,12 @@ void hgsmi_process_display_info(struct gen_pool *ctx, u32 display, } /** - * Report the rectangle relative to which absolute pointer events should be - * expressed. This information remains valid until the next VBVA resize event - * for any screen, at which time it is reset to the bounding rectangle of all - * virtual screens. + * hgsmi_update_input_mapping - Report the rectangle relative to which absolute + * pointer events should be expressed. This + * information remains valid until the next VBVA + * resize event for any screen, at which time it is + * reset to the bounding rectangle of all virtual + * screens. * Return: 0 or negative errno value. * @ctx: The context containing the heap to use. * @origin_x: Upper left X co-ordinate relative to the first screen. @@ -84,7 +88,7 @@ int hgsmi_update_input_mapping(struct gen_pool *ctx, s32 origin_x, s32 origin_y, } /** - * Get most recent video mode hints. + * hgsmi_get_mode_hints - Get most recent video mode hints. * Return: 0 or negative errno value. * @ctx: The context containing the heap to use. * @screens: The number of screens to query hints for, starting at 0. diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index f9de8632a28b..3c4cc133e3df 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -166,10 +166,9 @@ vc4_hdmi_connector_detect(struct drm_connector *connector, bool force) struct vc4_hdmi *vc4_hdmi = connector_to_vc4_hdmi(connector); bool connected = false; - if (vc4_hdmi->hpd_gpio) { - if (gpio_get_value_cansleep(vc4_hdmi->hpd_gpio) ^ - vc4_hdmi->hpd_active_low) - connected = true; + if (vc4_hdmi->hpd_gpio && + gpiod_get_value_cansleep(vc4_hdmi->hpd_gpio)) { + connected = true; } else if (drm_probe_ddc(vc4_hdmi->ddc)) { connected = true; } else if (HDMI_READ(HDMI_HOTPLUG) & VC4_HDMI_HOTPLUG_CONNECTED) { @@ -2105,7 +2104,6 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) struct vc4_hdmi *vc4_hdmi; struct drm_encoder *encoder; struct device_node *ddc_node; - u32 value; int ret; vc4_hdmi = devm_kzalloc(dev, sizeof(*vc4_hdmi), GFP_KERNEL); @@ -2144,18 +2142,10 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) /* Only use the GPIO HPD pin if present in the DT, otherwise * we'll use the HDMI core's register. */ - if (of_find_property(dev->of_node, "hpd-gpios", &value)) { - enum of_gpio_flags hpd_gpio_flags; - - vc4_hdmi->hpd_gpio = of_get_named_gpio_flags(dev->of_node, - "hpd-gpios", 0, - &hpd_gpio_flags); - if (vc4_hdmi->hpd_gpio < 0) { - ret = vc4_hdmi->hpd_gpio; - goto err_unprepare_hsm; - } - - vc4_hdmi->hpd_active_low = hpd_gpio_flags & OF_GPIO_ACTIVE_LOW; + vc4_hdmi->hpd_gpio = devm_gpiod_get_optional(dev, "hpd", GPIOD_IN); + if (IS_ERR(vc4_hdmi->hpd_gpio)) { + ret = PTR_ERR(vc4_hdmi->hpd_gpio); + goto err_put_ddc; } vc4_hdmi->disable_wifi_frequencies = @@ -2209,8 +2199,8 @@ err_destroy_conn: vc4_hdmi_connector_destroy(&vc4_hdmi->connector); err_destroy_encoder: drm_encoder_cleanup(encoder); -err_unprepare_hsm: pm_runtime_disable(dev); +err_put_ddc: put_device(&vc4_hdmi->ddc->dev); return ret; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h index 39bd2c413ec0..884d245507a9 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.h +++ b/drivers/gpu/drm/vc4/vc4_hdmi.h @@ -148,8 +148,7 @@ struct vc4_hdmi { /* VC5 Only */ void __iomem *rm_regs; - int hpd_gpio; - bool hpd_active_low; + struct gpio_desc *hpd_gpio; /* * On some systems (like the RPi4), some modes are in the same diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c index a0e75f1d5d01..bf38a7e319d1 100644 --- a/drivers/gpu/drm/vgem/vgem_drv.c +++ b/drivers/gpu/drm/vgem/vgem_drv.c @@ -25,7 +25,7 @@ * Ben Widawsky <ben@bwidawsk.net> */ -/** +/* * This is vgem, a (non-hardware-backed) GEM service. This is used by Mesa's * software renderer and the X server for efficient buffer sharing. */ diff --git a/drivers/gpu/drm/vgem/vgem_fence.c b/drivers/gpu/drm/vgem/vgem_fence.c index 2902dc6e64fa..bd6f75285fd9 100644 --- a/drivers/gpu/drm/vgem/vgem_fence.c +++ b/drivers/gpu/drm/vgem/vgem_fence.c @@ -151,8 +151,7 @@ int vgem_fence_attach_ioctl(struct drm_device *dev, /* Check for a conflicting fence */ resv = obj->resv; - if (!dma_resv_test_signaled_rcu(resv, - arg->flags & VGEM_FENCE_WRITE)) { + if (!dma_resv_test_signaled(resv, arg->flags & VGEM_FENCE_WRITE)) { ret = -EBUSY; goto err_fence; } diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 669f2ee39515..5c1ad1596889 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -451,10 +451,9 @@ static int virtio_gpu_wait_ioctl(struct drm_device *dev, void *data, return -ENOENT; if (args->flags & VIRTGPU_WAIT_NOWAIT) { - ret = dma_resv_test_signaled_rcu(obj->resv, true); + ret = dma_resv_test_signaled(obj->resv, true); } else { - ret = dma_resv_wait_timeout_rcu(obj->resv, true, true, - timeout); + ret = dma_resv_wait_timeout(obj->resv, true, true, timeout); } if (ret == 0) ret = -EBUSY; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c index cdbd5a870711..09fe20e918f9 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c @@ -483,10 +483,10 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst, d.src_addr = NULL; d.dst_pages = dst->ttm->pages; d.src_pages = src->ttm->pages; - d.dst_num_pages = dst->mem.num_pages; - d.src_num_pages = src->mem.num_pages; - d.dst_prot = ttm_io_prot(dst, &dst->mem, PAGE_KERNEL); - d.src_prot = ttm_io_prot(src, &src->mem, PAGE_KERNEL); + d.dst_num_pages = dst->resource->num_pages; + d.src_num_pages = src->resource->num_pages; + d.dst_prot = ttm_io_prot(dst, dst->resource, PAGE_KERNEL); + d.src_prot = ttm_io_prot(src, src->resource, PAGE_KERNEL); d.diff = diff; for (j = 0; j < h; ++j) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 04dd49c4c257..362f56d5b12b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -103,7 +103,7 @@ int vmw_bo_pin_in_placement(struct vmw_private *dev_priv, goto err; if (buf->base.pin_count > 0) - ret = ttm_bo_mem_compat(placement, &bo->mem, + ret = ttm_bo_mem_compat(placement, bo->resource, &new_flags) == true ? 0 : -EINVAL; else ret = ttm_bo_validate(bo, placement, &ctx); @@ -145,7 +145,7 @@ int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv, goto err; if (buf->base.pin_count > 0) { - ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem, + ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, bo->resource, &new_flags) == true ? 0 : -EINVAL; goto out_unreserve; } @@ -211,7 +211,7 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, uint32_t new_flags; place = vmw_vram_placement.placement[0]; - place.lpfn = bo->mem.num_pages; + place.lpfn = bo->resource->num_pages; placement.num_placement = 1; placement.placement = &place; placement.num_busy_placement = 1; @@ -227,22 +227,22 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, * In that case, evict it first because TTM isn't good at handling * that situation. */ - if (bo->mem.mem_type == TTM_PL_VRAM && - bo->mem.start < bo->mem.num_pages && - bo->mem.start > 0 && + if (bo->resource->mem_type == TTM_PL_VRAM && + bo->resource->start < bo->resource->num_pages && + bo->resource->start > 0 && buf->base.pin_count == 0) { ctx.interruptible = false; (void) ttm_bo_validate(bo, &vmw_sys_placement, &ctx); } if (buf->base.pin_count > 0) - ret = ttm_bo_mem_compat(&placement, &bo->mem, + ret = ttm_bo_mem_compat(&placement, bo->resource, &new_flags) == true ? 0 : -EINVAL; else ret = ttm_bo_validate(bo, &placement, &ctx); /* For some reason we didn't end up at the start of vram */ - WARN_ON(ret == 0 && bo->mem.start != 0); + WARN_ON(ret == 0 && bo->resource->start != 0); if (!ret) vmw_bo_pin_reserved(buf, true); @@ -293,11 +293,11 @@ err: void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *bo, SVGAGuestPtr *ptr) { - if (bo->mem.mem_type == TTM_PL_VRAM) { + if (bo->resource->mem_type == TTM_PL_VRAM) { ptr->gmrId = SVGA_GMR_FRAMEBUFFER; - ptr->offset = bo->mem.start << PAGE_SHIFT; + ptr->offset = bo->resource->start << PAGE_SHIFT; } else { - ptr->gmrId = bo->mem.start; + ptr->gmrId = bo->resource->start; ptr->offset = 0; } } @@ -316,7 +316,7 @@ void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin) struct ttm_place pl; struct ttm_placement placement; struct ttm_buffer_object *bo = &vbo->base; - uint32_t old_mem_type = bo->mem.mem_type; + uint32_t old_mem_type = bo->resource->mem_type; int ret; dma_resv_assert_held(bo->base.resv); @@ -326,8 +326,8 @@ void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin) pl.fpfn = 0; pl.lpfn = 0; - pl.mem_type = bo->mem.mem_type; - pl.flags = bo->mem.placement; + pl.mem_type = bo->resource->mem_type; + pl.flags = bo->resource->placement; memset(&placement, 0, sizeof(placement)); placement.num_placement = 1; @@ -335,7 +335,7 @@ void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin) ret = ttm_bo_validate(bo, &placement, &ctx); - BUG_ON(ret != 0 || bo->mem.mem_type != old_mem_type); + BUG_ON(ret != 0 || bo->resource->mem_type != old_mem_type); if (pin) ttm_bo_pin(bo); @@ -369,7 +369,7 @@ void *vmw_bo_map_and_cache(struct vmw_buffer_object *vbo) if (virtual) return virtual; - ret = ttm_bo_kmap(bo, 0, bo->mem.num_pages, &vbo->map); + ret = ttm_bo_kmap(bo, 0, bo->resource->num_pages, &vbo->map); if (ret) DRM_ERROR("Buffer object map failed: %d.\n", ret); @@ -743,9 +743,9 @@ static int vmw_user_bo_synccpu_grab(struct vmw_user_buffer_object *user_bo, if (flags & drm_vmw_synccpu_allow_cs) { long lret; - lret = dma_resv_wait_timeout_rcu - (bo->base.resv, true, true, - nonblock ? 0 : MAX_SCHEDULE_TIMEOUT); + lret = dma_resv_wait_timeout(bo->base.resv, true, true, + nonblock ? 0 : + MAX_SCHEDULE_TIMEOUT); if (!lret) return -EBUSY; else if (lret < 0) @@ -1197,7 +1197,7 @@ void vmw_bo_move_notify(struct ttm_buffer_object *bo, * With other types of moves, the underlying pages stay the same, * and the map can be kept. */ - if (mem->mem_type == TTM_PL_VRAM || bo->mem.mem_type == TTM_PL_VRAM) + if (mem->mem_type == TTM_PL_VRAM || bo->resource->mem_type == TTM_PL_VRAM) vmw_bo_unmap(vbo); /* @@ -1205,6 +1205,6 @@ void vmw_bo_move_notify(struct ttm_buffer_object *bo, * read back all resource content first, and unbind the MOB from * the resource. */ - if (mem->mem_type != VMW_PL_MOB && bo->mem.mem_type == VMW_PL_MOB) + if (mem->mem_type != VMW_PL_MOB && bo->resource->mem_type == VMW_PL_MOB) vmw_resource_unbind_list(vbo); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c index 9c89189a226d..956b85e35cef 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c @@ -576,11 +576,11 @@ static int vmw_cmd_emit_dummy_legacy_query(struct vmw_private *dev_priv, cmd->body.cid = cid; cmd->body.type = SVGA3D_QUERYTYPE_OCCLUSION; - if (bo->mem.mem_type == TTM_PL_VRAM) { + if (bo->resource->mem_type == TTM_PL_VRAM) { cmd->body.guestResult.gmrId = SVGA_GMR_FRAMEBUFFER; - cmd->body.guestResult.offset = bo->mem.start << PAGE_SHIFT; + cmd->body.guestResult.offset = bo->resource->start << PAGE_SHIFT; } else { - cmd->body.guestResult.gmrId = bo->mem.start; + cmd->body.guestResult.gmrId = bo->resource->start; cmd->body.guestResult.offset = 0; } @@ -621,8 +621,8 @@ static int vmw_cmd_emit_dummy_gb_query(struct vmw_private *dev_priv, cmd->header.size = sizeof(cmd->body); cmd->body.cid = cid; cmd->body.type = SVGA3D_QUERYTYPE_OCCLUSION; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); - cmd->body.mobid = bo->mem.start; + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); + cmd->body.mobid = bo->resource->start; cmd->body.offset = 0; vmw_cmd_commit(dev_priv, sizeof(*cmd)); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c index 05ca310ed61a..6bb4961e64a5 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c @@ -889,7 +889,7 @@ static int vmw_cmdbuf_space_pool(struct vmw_cmdbuf_man *man, header->cmd = man->map + offset; if (man->using_mob) { cb_hdr->flags = SVGA_CB_FLAG_MOB; - cb_hdr->ptr.mob.mobid = man->cmd_space->mem.start; + cb_hdr->ptr.mob.mobid = man->cmd_space->resource->start; cb_hdr->ptr.mob.mobOffset = offset; } else { cb_hdr->ptr.pa = (u64)man->handle + (u64)offset; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c index 3ed9914cb994..dffe3804ad3e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c @@ -346,7 +346,7 @@ static int vmw_gb_context_bind(struct vmw_resource *res, } *cmd; struct ttm_buffer_object *bo = val_buf->bo; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd)); if (unlikely(cmd == NULL)) @@ -355,7 +355,7 @@ static int vmw_gb_context_bind(struct vmw_resource *res, cmd->header.id = SVGA_3D_CMD_BIND_GB_CONTEXT; cmd->header.size = sizeof(cmd->body); cmd->body.cid = res->id; - cmd->body.mobid = bo->mem.start; + cmd->body.mobid = bo->resource->start; cmd->body.validContents = res->backup_dirty; res->backup_dirty = false; vmw_cmd_commit(dev_priv, sizeof(*cmd)); @@ -385,7 +385,7 @@ static int vmw_gb_context_unbind(struct vmw_resource *res, uint8_t *cmd; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); mutex_lock(&dev_priv->binding_mutex); vmw_binding_state_scrub(uctx->cbs); @@ -513,7 +513,7 @@ static int vmw_dx_context_bind(struct vmw_resource *res, } *cmd; struct ttm_buffer_object *bo = val_buf->bo; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd)); if (unlikely(cmd == NULL)) @@ -522,7 +522,7 @@ static int vmw_dx_context_bind(struct vmw_resource *res, cmd->header.id = SVGA_3D_CMD_DX_BIND_CONTEXT; cmd->header.size = sizeof(cmd->body); cmd->body.cid = res->id; - cmd->body.mobid = bo->mem.start; + cmd->body.mobid = bo->resource->start; cmd->body.validContents = res->backup_dirty; res->backup_dirty = false; vmw_cmd_commit(dev_priv, sizeof(*cmd)); @@ -594,7 +594,7 @@ static int vmw_dx_context_unbind(struct vmw_resource *res, uint8_t *cmd; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); mutex_lock(&dev_priv->binding_mutex); vmw_dx_context_scrub_cotables(res, readback); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c index b40aa002bf2b..c84a16c1def0 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c @@ -173,7 +173,7 @@ static int vmw_cotable_unscrub(struct vmw_resource *res) SVGA3dCmdDXSetCOTable body; } *cmd; - WARN_ON_ONCE(bo->mem.mem_type != VMW_PL_MOB); + WARN_ON_ONCE(bo->resource->mem_type != VMW_PL_MOB); dma_resv_assert_held(bo->base.resv); cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd)); @@ -181,12 +181,12 @@ static int vmw_cotable_unscrub(struct vmw_resource *res) return -ENOMEM; WARN_ON(vcotbl->ctx->id == SVGA3D_INVALID_ID); - WARN_ON(bo->mem.mem_type != VMW_PL_MOB); + WARN_ON(bo->resource->mem_type != VMW_PL_MOB); cmd->header.id = SVGA_3D_CMD_DX_SET_COTABLE; cmd->header.size = sizeof(cmd->body); cmd->body.cid = vcotbl->ctx->id; cmd->body.type = vcotbl->type; - cmd->body.mobid = bo->mem.start; + cmd->body.mobid = bo->resource->start; cmd->body.validSizeInBytes = vcotbl->size_read_back; vmw_cmd_commit_flush(dev_priv, sizeof(*cmd)); @@ -315,7 +315,7 @@ static int vmw_cotable_unbind(struct vmw_resource *res, if (!vmw_resource_mob_attached(res)) return 0; - WARN_ON_ONCE(bo->mem.mem_type != VMW_PL_MOB); + WARN_ON_ONCE(bo->resource->mem_type != VMW_PL_MOB); dma_resv_assert_held(bo->base.resv); mutex_lock(&dev_priv->binding_mutex); @@ -431,7 +431,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) * Do a page by page copy of COTables. This eliminates slow vmap()s. * This should really be a TTM utility. */ - for (i = 0; i < old_bo->mem.num_pages; ++i) { + for (i = 0; i < old_bo->resource->num_pages; ++i) { bool dummy; ret = ttm_bo_kmap(old_bo, i, 1, &old_map); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 32a84dff3fbf..a2b8464b3f56 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -735,7 +735,7 @@ static int vmw_rebind_all_dx_query(struct vmw_resource *ctx_res) cmd->header.id = SVGA_3D_CMD_DX_BIND_ALL_QUERY; cmd->header.size = sizeof(cmd->body); cmd->body.cid = ctx_res->id; - cmd->body.mobid = dx_query_mob->base.mem.start; + cmd->body.mobid = dx_query_mob->base.resource->start; vmw_cmd_commit(dev_priv, sizeof(*cmd)); vmw_context_bind_dx_query(ctx_res, dx_query_mob); @@ -1046,7 +1046,7 @@ static int vmw_query_bo_switch_prepare(struct vmw_private *dev_priv, if (unlikely(new_query_bo != sw_context->cur_query_bo)) { - if (unlikely(new_query_bo->base.mem.num_pages > 4)) { + if (unlikely(new_query_bo->base.resource->num_pages > 4)) { VMW_DEBUG_USER("Query buffer too large.\n"); return -EINVAL; } @@ -3710,16 +3710,16 @@ static void vmw_apply_relocations(struct vmw_sw_context *sw_context) list_for_each_entry(reloc, &sw_context->bo_relocations, head) { bo = &reloc->vbo->base; - switch (bo->mem.mem_type) { + switch (bo->resource->mem_type) { case TTM_PL_VRAM: - reloc->location->offset += bo->mem.start << PAGE_SHIFT; + reloc->location->offset += bo->resource->start << PAGE_SHIFT; reloc->location->gmrId = SVGA_GMR_FRAMEBUFFER; break; case VMW_PL_GMR: - reloc->location->gmrId = bo->mem.start; + reloc->location->gmrId = bo->resource->start; break; case VMW_PL_MOB: - *reloc->mob_loc = bo->mem.start; + *reloc->mob_loc = bo->resource->start; break; default: BUG(); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c index 1774960d1b89..28ceb749a733 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c @@ -52,11 +52,17 @@ static struct vmwgfx_gmrid_man *to_gmrid_manager(struct ttm_resource_manager *ma static int vmw_gmrid_man_get_node(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *mem) + struct ttm_resource **res) { struct vmwgfx_gmrid_man *gman = to_gmrid_manager(man); int id; + *res = kmalloc(sizeof(**res), GFP_KERNEL); + if (!*res) + return -ENOMEM; + + ttm_resource_init(bo, place, *res); + id = ida_alloc_max(&gman->gmr_ida, gman->max_gmr_ids - 1, GFP_KERNEL); if (id < 0) return id; @@ -64,36 +70,34 @@ static int vmw_gmrid_man_get_node(struct ttm_resource_manager *man, spin_lock(&gman->lock); if (gman->max_gmr_pages > 0) { - gman->used_gmr_pages += mem->num_pages; + gman->used_gmr_pages += (*res)->num_pages; if (unlikely(gman->used_gmr_pages > gman->max_gmr_pages)) goto nospace; } - mem->mm_node = gman; - mem->start = id; + (*res)->start = id; spin_unlock(&gman->lock); return 0; nospace: - gman->used_gmr_pages -= mem->num_pages; + gman->used_gmr_pages -= (*res)->num_pages; spin_unlock(&gman->lock); ida_free(&gman->gmr_ida, id); + kfree(*res); return -ENOSPC; } static void vmw_gmrid_man_put_node(struct ttm_resource_manager *man, - struct ttm_resource *mem) + struct ttm_resource *res) { struct vmwgfx_gmrid_man *gman = to_gmrid_manager(man); - if (mem->mm_node) { - ida_free(&gman->gmr_ida, mem->start); - spin_lock(&gman->lock); - gman->used_gmr_pages -= mem->num_pages; - spin_unlock(&gman->lock); - mem->mm_node = NULL; - } + ida_free(&gman->gmr_ida, res->start); + spin_lock(&gman->lock); + gman->used_gmr_pages -= res->num_pages; + spin_unlock(&gman->lock); + kfree(res); } static const struct ttm_resource_manager_func vmw_gmrid_manager_func; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c index 45c9c6a7f1d6..e5a9a5cbd01a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c @@ -232,7 +232,7 @@ void vmw_bo_dirty_unmap(struct vmw_buffer_object *vbo, int vmw_bo_dirty_add(struct vmw_buffer_object *vbo) { struct vmw_bo_dirty *dirty = vbo->dirty; - pgoff_t num_pages = vbo->base.mem.num_pages; + pgoff_t num_pages = vbo->base.resource->num_pages; size_t size, acc_size; int ret; static struct ttm_operation_ctx ctx = { @@ -413,7 +413,7 @@ vm_fault_t vmw_bo_vm_mkwrite(struct vm_fault *vmf) return ret; page_offset = vmf->pgoff - drm_vma_node_start(&bo->base.vma_node); - if (unlikely(page_offset >= bo->mem.num_pages)) { + if (unlikely(page_offset >= bo->resource->num_pages)) { ret = VM_FAULT_SIGBUS; goto out_unlock; } @@ -456,7 +456,7 @@ vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf) page_offset = vmf->pgoff - drm_vma_node_start(&bo->base.vma_node); - if (page_offset >= bo->mem.num_pages || + if (page_offset >= bo->resource->num_pages || vmw_resources_clean(vbo, page_offset, page_offset + PAGE_SIZE, &allowed_prefault)) { @@ -529,7 +529,7 @@ vm_fault_t vmw_bo_vm_huge_fault(struct vm_fault *vmf, page_offset = vmf->pgoff - drm_vma_node_start(&bo->base.vma_node); - if (page_offset >= bo->mem.num_pages || + if (page_offset >= bo->resource->num_pages || vmw_resources_clean(vbo, page_offset, page_offset + PAGE_SIZE, &allowed_prefault)) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 62ea920addc3..7b45393ad98e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -1166,7 +1166,7 @@ int vmw_resources_clean(struct vmw_buffer_object *vbo, pgoff_t start, if (bo->moving) dma_fence_put(bo->moving); bo->moving = dma_fence_get - (dma_resv_get_excl(bo->base.resv)); + (dma_resv_excl_fence(bo->base.resv)); } return 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index b391975871a5..b3c8d2da6f1a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -254,7 +254,7 @@ static int vmw_gb_shader_bind(struct vmw_resource *res, } *cmd; struct ttm_buffer_object *bo = val_buf->bo; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd)); if (unlikely(cmd == NULL)) @@ -263,7 +263,7 @@ static int vmw_gb_shader_bind(struct vmw_resource *res, cmd->header.id = SVGA_3D_CMD_BIND_GB_SHADER; cmd->header.size = sizeof(cmd->body); cmd->body.shid = res->id; - cmd->body.mobid = bo->mem.start; + cmd->body.mobid = bo->resource->start; cmd->body.offsetInBytes = res->backup_offset; res->backup_dirty = false; vmw_cmd_commit(dev_priv, sizeof(*cmd)); @@ -282,7 +282,7 @@ static int vmw_gb_shader_unbind(struct vmw_resource *res, } *cmd; struct vmw_fence_obj *fence; - BUG_ON(res->backup->base.mem.mem_type != VMW_PL_MOB); + BUG_ON(res->backup->base.resource->mem_type != VMW_PL_MOB); cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd)); if (unlikely(cmd == NULL)) @@ -402,7 +402,7 @@ static int vmw_dx_shader_unscrub(struct vmw_resource *res) cmd->header.size = sizeof(cmd->body); cmd->body.cid = shader->ctx->id; cmd->body.shid = shader->id; - cmd->body.mobid = res->backup->base.mem.start; + cmd->body.mobid = res->backup->base.resource->start; cmd->body.offsetInBytes = res->backup_offset; vmw_cmd_commit(dev_priv, sizeof(*cmd)); @@ -450,7 +450,7 @@ static int vmw_dx_shader_bind(struct vmw_resource *res, struct vmw_private *dev_priv = res->dev_priv; struct ttm_buffer_object *bo = val_buf->bo; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); mutex_lock(&dev_priv->binding_mutex); vmw_dx_shader_unscrub(res); mutex_unlock(&dev_priv->binding_mutex); @@ -513,7 +513,7 @@ static int vmw_dx_shader_unbind(struct vmw_resource *res, struct vmw_fence_obj *fence; int ret; - BUG_ON(res->backup->base.mem.mem_type != VMW_PL_MOB); + BUG_ON(res->backup->base.resource->mem_type != VMW_PL_MOB); mutex_lock(&dev_priv->binding_mutex); ret = vmw_dx_shader_scrub(res); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_streamoutput.c b/drivers/gpu/drm/vmwgfx/vmwgfx_streamoutput.c index 1dd042a20a66..c8efa4a6c995 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_streamoutput.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_streamoutput.c @@ -106,7 +106,7 @@ static int vmw_dx_streamoutput_unscrub(struct vmw_resource *res) cmd->header.id = SVGA_3D_CMD_DX_BIND_STREAMOUTPUT; cmd->header.size = sizeof(cmd->body); cmd->body.soid = so->id; - cmd->body.mobid = res->backup->base.mem.start; + cmd->body.mobid = res->backup->base.resource->start; cmd->body.offsetInBytes = res->backup_offset; cmd->body.sizeInBytes = so->size; vmw_cmd_commit(dev_priv, sizeof(*cmd)); @@ -142,7 +142,7 @@ static int vmw_dx_streamoutput_bind(struct vmw_resource *res, struct ttm_buffer_object *bo = val_buf->bo; int ret; - if (WARN_ON(bo->mem.mem_type != VMW_PL_MOB)) + if (WARN_ON(bo->resource->mem_type != VMW_PL_MOB)) return -EINVAL; mutex_lock(&dev_priv->binding_mutex); @@ -197,7 +197,7 @@ static int vmw_dx_streamoutput_unbind(struct vmw_resource *res, bool readback, struct vmw_fence_obj *fence; int ret; - if (WARN_ON(res->backup->base.mem.mem_type != VMW_PL_MOB)) + if (WARN_ON(res->backup->base.resource->mem_type != VMW_PL_MOB)) return -EINVAL; mutex_lock(&dev_priv->binding_mutex); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 8ead06574850..0835468bb2ee 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -1212,7 +1212,7 @@ static int vmw_gb_surface_bind(struct vmw_resource *res, uint32_t submit_size; struct ttm_buffer_object *bo = val_buf->bo; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); submit_size = sizeof(*cmd1) + (res->backup_dirty ? sizeof(*cmd2) : 0); @@ -1223,7 +1223,7 @@ static int vmw_gb_surface_bind(struct vmw_resource *res, cmd1->header.id = SVGA_3D_CMD_BIND_GB_SURFACE; cmd1->header.size = sizeof(cmd1->body); cmd1->body.sid = res->id; - cmd1->body.mobid = bo->mem.start; + cmd1->body.mobid = bo->resource->start; if (res->backup_dirty) { cmd2 = (void *) &cmd1[1]; cmd2->header.id = SVGA_3D_CMD_UPDATE_GB_SURFACE; @@ -1266,7 +1266,7 @@ static int vmw_gb_surface_unbind(struct vmw_resource *res, uint8_t *cmd; - BUG_ON(bo->mem.mem_type != VMW_PL_MOB); + BUG_ON(bo->resource->mem_type != VMW_PL_MOB); submit_size = sizeof(*cmd3) + (readback ? sizeof(*cmd1) : sizeof(*cmd2)); cmd = VMW_CMD_RESERVE(dev_priv, submit_size); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c index 5ccc35b3194c..2a3d3468e4e0 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c @@ -7,6 +7,7 @@ #include "vmwgfx_drv.h" #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_placement.h> +#include <drm/ttm/ttm_range_manager.h> /** * struct vmw_thp_manager - Range manager implementing huge page alignment @@ -50,20 +51,22 @@ static int vmw_thp_insert_aligned(struct ttm_buffer_object *bo, static int vmw_thp_get_node(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *mem) + struct ttm_resource **res) { struct vmw_thp_manager *rman = to_thp_manager(man); struct drm_mm *mm = &rman->mm; - struct drm_mm_node *node; + struct ttm_range_mgr_node *node; unsigned long align_pages; unsigned long lpfn; enum drm_mm_insert_mode mode = DRM_MM_INSERT_BEST; int ret; - node = kzalloc(sizeof(*node), GFP_KERNEL); + node = kzalloc(struct_size(node, mm_nodes, 1), GFP_KERNEL); if (!node) return -ENOMEM; + ttm_resource_init(bo, place, &node->base); + lpfn = place->lpfn; if (!lpfn) lpfn = man->size; @@ -75,23 +78,26 @@ static int vmw_thp_get_node(struct ttm_resource_manager *man, spin_lock(&rman->lock); if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)) { align_pages = (HPAGE_PUD_SIZE >> PAGE_SHIFT); - if (mem->num_pages >= align_pages) { - ret = vmw_thp_insert_aligned(bo, mm, node, align_pages, - place, mem, lpfn, mode); + if (node->base.num_pages >= align_pages) { + ret = vmw_thp_insert_aligned(bo, mm, &node->mm_nodes[0], + align_pages, place, + &node->base, lpfn, mode); if (!ret) goto found_unlock; } } align_pages = (HPAGE_PMD_SIZE >> PAGE_SHIFT); - if (mem->num_pages >= align_pages) { - ret = vmw_thp_insert_aligned(bo, mm, node, align_pages, place, - mem, lpfn, mode); + if (node->base.num_pages >= align_pages) { + ret = vmw_thp_insert_aligned(bo, mm, &node->mm_nodes[0], + align_pages, place, &node->base, + lpfn, mode); if (!ret) goto found_unlock; } - ret = drm_mm_insert_node_in_range(mm, node, mem->num_pages, + ret = drm_mm_insert_node_in_range(mm, &node->mm_nodes[0], + node->base.num_pages, bo->page_alignment, 0, place->fpfn, lpfn, mode); found_unlock: @@ -100,28 +106,24 @@ found_unlock: if (unlikely(ret)) { kfree(node); } else { - mem->mm_node = node; - mem->start = node->start; + node->base.start = node->mm_nodes[0].start; + *res = &node->base; } return ret; } - - static void vmw_thp_put_node(struct ttm_resource_manager *man, - struct ttm_resource *mem) + struct ttm_resource *res) { + struct ttm_range_mgr_node *node = to_ttm_range_mgr_node(res); struct vmw_thp_manager *rman = to_thp_manager(man); - if (mem->mm_node) { - spin_lock(&rman->lock); - drm_mm_remove_node(mem->mm_node); - spin_unlock(&rman->lock); + spin_lock(&rman->lock); + drm_mm_remove_node(&node->mm_nodes[0]); + spin_unlock(&rman->lock); - kfree(mem->mm_node); - mem->mm_node = NULL; - } + kfree(node); } int vmw_thp_init(struct vmw_private *dev_priv) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index 35b03fe21161..0488042fb287 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -719,7 +719,7 @@ static int vmw_move(struct ttm_buffer_object *bo, struct ttm_resource *new_mem, struct ttm_place *hop) { - struct ttm_resource_manager *old_man = ttm_manager_type(bo->bdev, bo->mem.mem_type); + struct ttm_resource_manager *old_man = ttm_manager_type(bo->bdev, bo->resource->mem_type); struct ttm_resource_manager *new_man = ttm_manager_type(bo->bdev, new_mem->mem_type); int ret; @@ -729,11 +729,11 @@ static int vmw_move(struct ttm_buffer_object *bo, return ret; } - vmw_move_notify(bo, &bo->mem, new_mem); + vmw_move_notify(bo, bo->resource, new_mem); if (old_man->use_tt && new_man->use_tt) { - if (bo->mem.mem_type == TTM_PL_SYSTEM) { - ttm_bo_assign_mem(bo, new_mem); + if (bo->resource->mem_type == TTM_PL_SYSTEM) { + ttm_bo_move_null(bo, new_mem); return 0; } ret = ttm_bo_wait_ctx(bo, ctx); @@ -741,7 +741,7 @@ static int vmw_move(struct ttm_buffer_object *bo, goto fail; vmw_ttm_unbind(bo->bdev, bo->ttm); - ttm_resource_free(bo, &bo->mem); + ttm_resource_free(bo, &bo->resource); ttm_bo_assign_mem(bo, new_mem); return 0; } else { @@ -751,7 +751,7 @@ static int vmw_move(struct ttm_buffer_object *bo, } return 0; fail: - vmw_move_notify(bo, new_mem, &bo->mem); + vmw_move_notify(bo, new_mem, bo->resource); return ret; } diff --git a/drivers/infiniband/core/umem_dmabuf.c b/drivers/infiniband/core/umem_dmabuf.c index 0d65ce146fc4..c6e875619fac 100644 --- a/drivers/infiniband/core/umem_dmabuf.c +++ b/drivers/infiniband/core/umem_dmabuf.c @@ -66,7 +66,7 @@ wait_fence: * may be not up-to-date. Wait for the exporter to finish * the migration. */ - fence = dma_resv_get_excl(umem_dmabuf->attach->dmabuf->resv); + fence = dma_resv_excl_fence(umem_dmabuf->attach->dmabuf->resv); if (fence) return dma_fence_wait(fence, false); diff --git a/drivers/video/fbdev/aty/mach64_cursor.c b/drivers/video/fbdev/aty/mach64_cursor.c index b06fa6e42e6e..4ad0331a8c57 100644 --- a/drivers/video/fbdev/aty/mach64_cursor.c +++ b/drivers/video/fbdev/aty/mach64_cursor.c @@ -46,7 +46,7 @@ * The Screen position of the top left corner of the displayed * cursor is specificed by CURS_HORZ_VERT_POSN. Care must be taken * when the cursor hot spot is not the top left corner and the - * physical cursor position becomes negative. It will be be displayed + * physical cursor position becomes negative. It will be displayed * if either the horizontal or vertical cursor position is negative * * If x becomes negative the cursor manager must adjust the CURS_HORZ_OFFSET diff --git a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c index 52755b591c14..63721337a377 100644 --- a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c +++ b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c @@ -542,8 +542,8 @@ static int mb862xxfb_init_fbinfo(struct fb_info *fbi) /* * show some display controller and cursor registers */ -static ssize_t mb862xxfb_show_dispregs(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t dispregs_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct fb_info *fbi = dev_get_drvdata(dev); struct mb862xxfb_par *par = fbi->par; @@ -577,7 +577,7 @@ static ssize_t mb862xxfb_show_dispregs(struct device *dev, return ptr - buf; } -static DEVICE_ATTR(dispregs, 0444, mb862xxfb_show_dispregs, NULL); +static DEVICE_ATTR_RO(dispregs); static irqreturn_t mb862xx_intr(int irq, void *dev_id) { diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h index e9ad4863d915..cc9de1632dd3 100644 --- a/include/drm/drm_cache.h +++ b/include/drm/drm_cache.h @@ -35,6 +35,8 @@ #include <linux/scatterlist.h> +struct dma_buf_map; + void drm_clflush_pages(struct page *pages[], unsigned long num_pages); void drm_clflush_sg(struct sg_table *st); void drm_clflush_virt_range(void *addr, unsigned long length); @@ -70,4 +72,9 @@ static inline bool drm_arch_can_wc_memory(void) #endif } +void drm_memcpy_init_early(void); + +void drm_memcpy_from_wc(struct dma_buf_map *dst, + const struct dma_buf_map *src, + unsigned long len); #endif diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 10225a0a35d0..d18af49fd009 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -275,7 +275,7 @@ struct drm_sched_backend_ops { * @pending_list: the list of jobs which are currently in the job queue. * @job_list_lock: lock to protect the pending_list. * @hang_limit: once the hangs by a job crosses this limit then it is marked - * guilty and it will be considered for scheduling further. + * guilty and it will no longer be considered for scheduling. * @score: score to help loadbalancer pick a idle sched * @_score: score used when the driver doesn't provide one * @ready: marks if the underlying HW is ready to work diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index f2a5f37c61b7..f681bbdbc698 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -136,7 +136,7 @@ struct ttm_buffer_object { * Members protected by the bo::resv::reserved lock. */ - struct ttm_resource mem; + struct ttm_resource *resource; struct ttm_tt *ttm; bool deleted; diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index dbccac957f8f..68d6069572aa 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -40,6 +40,7 @@ #include <drm/ttm/ttm_device.h> #include "ttm_bo_api.h" +#include "ttm_kmap_iter.h" #include "ttm_placement.h" #include "ttm_tt.h" #include "ttm_pool.h" @@ -96,7 +97,7 @@ struct ttm_lru_bulk_move { */ int ttm_bo_mem_space(struct ttm_buffer_object *bo, struct ttm_placement *placement, - struct ttm_resource *mem, + struct ttm_resource **mem, struct ttm_operation_ctx *ctx); /** @@ -181,15 +182,15 @@ static inline void ttm_bo_move_to_lru_tail_unlocked(struct ttm_buffer_object *bo) { spin_lock(&bo->bdev->lru_lock); - ttm_bo_move_to_lru_tail(bo, &bo->mem, NULL); + ttm_bo_move_to_lru_tail(bo, bo->resource, NULL); spin_unlock(&bo->bdev->lru_lock); } static inline void ttm_bo_assign_mem(struct ttm_buffer_object *bo, struct ttm_resource *new_mem) { - bo->mem = *new_mem; - new_mem->mm_node = NULL; + WARN_ON(bo->resource); + bo->resource = new_mem; } /** @@ -202,9 +203,7 @@ static inline void ttm_bo_assign_mem(struct ttm_buffer_object *bo, static inline void ttm_bo_move_null(struct ttm_buffer_object *bo, struct ttm_resource *new_mem) { - struct ttm_resource *old_mem = &bo->mem; - - WARN_ON(old_mem->mm_node != NULL); + ttm_resource_free(bo, &bo->resource); ttm_bo_assign_mem(bo, new_mem); } @@ -273,6 +272,23 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, struct ttm_resource *new_mem); /** + * ttm_bo_move_accel_cleanup. + * + * @bo: A pointer to a struct ttm_buffer_object. + * @new_mem: struct ttm_resource indicating where to move. + * + * Special case of ttm_bo_move_accel_cleanup where the bo is guaranteed + * by the caller to be idle. Typically used after memcpy buffer moves. + */ +static inline void ttm_bo_move_sync_cleanup(struct ttm_buffer_object *bo, + struct ttm_resource *new_mem) +{ + int ret = ttm_bo_move_accel_cleanup(bo, NULL, true, false, new_mem); + + WARN_ON(ret); +} + +/** * ttm_bo_pipeline_gutting. * * @bo: A pointer to a struct ttm_buffer_object. @@ -306,30 +322,14 @@ int ttm_bo_tt_bind(struct ttm_buffer_object *bo, struct ttm_resource *mem); */ void ttm_bo_tt_destroy(struct ttm_buffer_object *bo); -/** - * ttm_range_man_init - * - * @bdev: ttm device - * @type: memory manager type - * @use_tt: if the memory manager uses tt - * @p_size: size of area to be managed in pages. - * - * Initialise a generic range manager for the selected memory type. - * The range manager is installed for this device in the type slot. - */ -int ttm_range_man_init(struct ttm_device *bdev, - unsigned type, bool use_tt, - unsigned long p_size); - -/** - * ttm_range_man_fini - * - * @bdev: ttm device - * @type: memory manager type - * - * Remove the generic range manager from a slot and tear it down. - */ -int ttm_range_man_fini(struct ttm_device *bdev, - unsigned type); +void ttm_move_memcpy(struct ttm_buffer_object *bo, + u32 num_pages, + struct ttm_kmap_iter *dst_iter, + struct ttm_kmap_iter *src_iter); +struct ttm_kmap_iter * +ttm_kmap_iter_iomap_init(struct ttm_kmap_iter_iomap *iter_io, + struct io_mapping *iomap, + struct sg_table *st, + resource_size_t start); #endif diff --git a/include/drm/ttm/ttm_caching.h b/include/drm/ttm/ttm_caching.h index a0b4a49fa432..3c9dd65f5aaf 100644 --- a/include/drm/ttm/ttm_caching.h +++ b/include/drm/ttm/ttm_caching.h @@ -33,4 +33,6 @@ enum ttm_caching { ttm_cached }; +pgprot_t ttm_prot_from_caching(enum ttm_caching caching, pgprot_t tmp); + #endif diff --git a/include/drm/ttm/ttm_kmap_iter.h b/include/drm/ttm/ttm_kmap_iter.h new file mode 100644 index 000000000000..8bb00fd39d6c --- /dev/null +++ b/include/drm/ttm/ttm_kmap_iter.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ +#ifndef __TTM_KMAP_ITER_H__ +#define __TTM_KMAP_ITER_H__ + +#include <linux/types.h> + +struct ttm_kmap_iter; +struct dma_buf_map; + +/** + * struct ttm_kmap_iter_ops - Ops structure for a struct + * ttm_kmap_iter. + * @maps_tt: Whether the iterator maps TT memory directly, as opposed + * mapping a TT through an aperture. Both these modes have + * struct ttm_resource_manager::use_tt set, but the latter typically + * returns is_iomem == true from ttm_mem_io_reserve. + */ +struct ttm_kmap_iter_ops { + /** + * kmap_local() - Map a PAGE_SIZE part of the resource using + * kmap_local semantics. + * @res_iter: Pointer to the struct ttm_kmap_iter representing + * the resource. + * @dmap: The struct dma_buf_map holding the virtual address after + * the operation. + * @i: The location within the resource to map. PAGE_SIZE granularity. + */ + void (*map_local)(struct ttm_kmap_iter *res_iter, + struct dma_buf_map *dmap, pgoff_t i); + /** + * unmap_local() - Unmap a PAGE_SIZE part of the resource previously + * mapped using kmap_local. + * @res_iter: Pointer to the struct ttm_kmap_iter representing + * the resource. + * @dmap: The struct dma_buf_map holding the virtual address after + * the operation. + */ + void (*unmap_local)(struct ttm_kmap_iter *res_iter, + struct dma_buf_map *dmap); + bool maps_tt; +}; + +/** + * struct ttm_kmap_iter - Iterator for kmap_local type operations on a + * resource. + * @ops: Pointer to the operations struct. + * + * This struct is intended to be embedded in a resource-specific specialization + * implementing operations for the resource. + * + * Nothing stops us from extending the operations to vmap, vmap_pfn etc, + * replacing some or parts of the ttm_bo_util. cpu-map functionality. + */ +struct ttm_kmap_iter { + const struct ttm_kmap_iter_ops *ops; +}; + +#endif /* __TTM_KMAP_ITER_H__ */ diff --git a/include/drm/ttm/ttm_range_manager.h b/include/drm/ttm/ttm_range_manager.h new file mode 100644 index 000000000000..22b6fa42ac20 --- /dev/null +++ b/include/drm/ttm/ttm_range_manager.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ + +#ifndef _TTM_RANGE_MANAGER_H_ +#define _TTM_RANGE_MANAGER_H_ + +#include <drm/ttm/ttm_resource.h> +#include <drm/drm_mm.h> + +/** + * struct ttm_range_mgr_node + * + * @base: base clase we extend + * @mm_nodes: MM nodes, usually 1 + * + * Extending the ttm_resource object to manage an address space allocation with + * one or more drm_mm_nodes. + */ +struct ttm_range_mgr_node { + struct ttm_resource base; + struct drm_mm_node mm_nodes[]; +}; + +/** + * to_ttm_range_mgr_node + * + * @res: the resource to upcast + * + * Upcast the ttm_resource object into a ttm_range_mgr_node object. + */ +static inline struct ttm_range_mgr_node * +to_ttm_range_mgr_node(struct ttm_resource *res) +{ + return container_of(res, struct ttm_range_mgr_node, base); +} + +int ttm_range_man_init(struct ttm_device *bdev, + unsigned type, bool use_tt, + unsigned long p_size); +int ttm_range_man_fini(struct ttm_device *bdev, + unsigned type); + +#endif diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 890b9d369519..140b6b9a8bbe 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -27,9 +27,11 @@ #include <linux/types.h> #include <linux/mutex.h> +#include <linux/dma-buf-map.h> #include <linux/dma-fence.h> #include <drm/drm_print.h> #include <drm/ttm/ttm_caching.h> +#include <drm/ttm/ttm_kmap_iter.h> #define TTM_MAX_BO_PRIORITY 4U @@ -38,6 +40,10 @@ struct ttm_resource_manager; struct ttm_resource; struct ttm_place; struct ttm_buffer_object; +struct dma_buf_map; +struct io_mapping; +struct sg_table; +struct scatterlist; struct ttm_resource_manager_func { /** @@ -45,46 +51,38 @@ struct ttm_resource_manager_func { * * @man: Pointer to a memory type manager. * @bo: Pointer to the buffer object we're allocating space for. - * @placement: Placement details. - * @flags: Additional placement flags. - * @mem: Pointer to a struct ttm_resource to be filled in. + * @place: Placement details. + * @res: Resulting pointer to the ttm_resource. * * This function should allocate space in the memory type managed - * by @man. Placement details if - * applicable are given by @placement. If successful, - * @mem::mm_node should be set to a non-null value, and - * @mem::start should be set to a value identifying the beginning + * by @man. Placement details if applicable are given by @place. If + * successful, a filled in ttm_resource object should be returned in + * @res. @res::start should be set to a value identifying the beginning * of the range allocated, and the function should return zero. - * If the memory region accommodate the buffer object, @mem::mm_node - * should be set to NULL, and the function should return 0. + * If the manager can't fulfill the request -ENOSPC should be returned. * If a system error occurred, preventing the request to be fulfilled, * the function should return a negative error code. * - * Note that @mem::mm_node will only be dereferenced by - * struct ttm_resource_manager functions and optionally by the driver, - * which has knowledge of the underlying type. - * - * This function may not be called from within atomic context, so - * an implementation can and must use either a mutex or a spinlock to - * protect any data structures managing the space. + * This function may not be called from within atomic context and needs + * to take care of its own locking to protect any data structures + * managing the space. */ int (*alloc)(struct ttm_resource_manager *man, struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *mem); + struct ttm_resource **res); /** * struct ttm_resource_manager_func member free * * @man: Pointer to a memory type manager. - * @mem: Pointer to a struct ttm_resource to be filled in. + * @res: Pointer to a struct ttm_resource to be freed. * - * This function frees memory type resources previously allocated - * and that are identified by @mem::mm_node and @mem::start. May not - * be called from within atomic context. + * This function frees memory type resources previously allocated. + * May not be called from within atomic context. */ void (*free)(struct ttm_resource_manager *man, - struct ttm_resource *mem); + struct ttm_resource *res); /** * struct ttm_resource_manager_func member debug @@ -158,9 +156,9 @@ struct ttm_bus_placement { /** * struct ttm_resource * - * @mm_node: Memory manager node. - * @size: Requested size of memory region. - * @num_pages: Actual size of memory region in pages. + * @start: Start of the allocation. + * @num_pages: Actual size of resource in pages. + * @mem_type: Resource type of the allocation. * @placement: Placement flags. * @bus: Placement on io bus accessible to the CPU * @@ -168,7 +166,6 @@ struct ttm_bus_placement { * buffer object. */ struct ttm_resource { - void *mm_node; unsigned long start; unsigned long num_pages; uint32_t mem_type; @@ -177,6 +174,45 @@ struct ttm_resource { }; /** + * struct ttm_kmap_iter_iomap - Specialization for a struct io_mapping + + * struct sg_table backed struct ttm_resource. + * @base: Embedded struct ttm_kmap_iter providing the usage interface. + * @iomap: struct io_mapping representing the underlying linear io_memory. + * @st: sg_table into @iomap, representing the memory of the struct ttm_resource. + * @start: Offset that needs to be subtracted from @st to make + * sg_dma_address(st->sgl) - @start == 0 for @iomap start. + * @cache: Scatterlist traversal cache for fast lookups. + * @cache.sg: Pointer to the currently cached scatterlist segment. + * @cache.i: First index of @sg. PAGE_SIZE granularity. + * @cache.end: Last index + 1 of @sg. PAGE_SIZE granularity. + * @cache.offs: First offset into @iomap of @sg. PAGE_SIZE granularity. + */ +struct ttm_kmap_iter_iomap { + struct ttm_kmap_iter base; + struct io_mapping *iomap; + struct sg_table *st; + resource_size_t start; + struct { + struct scatterlist *sg; + pgoff_t i; + pgoff_t end; + pgoff_t offs; + } cache; +}; + +/** + * struct ttm_kmap_iter_linear_io - Iterator specialization for linear io + * @base: The base iterator + * @dmap: Points to the starting address of the region + * @needs_unmap: Whether we need to unmap on fini + */ +struct ttm_kmap_iter_linear_io { + struct ttm_kmap_iter base; + struct dma_buf_map dmap; + bool needs_unmap; +}; + +/** * ttm_resource_manager_set_used * * @man: A memory manager object. @@ -223,10 +259,13 @@ ttm_resource_manager_cleanup(struct ttm_resource_manager *man) man->move = NULL; } +void ttm_resource_init(struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource *res); int ttm_resource_alloc(struct ttm_buffer_object *bo, const struct ttm_place *place, - struct ttm_resource *res); -void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource *res); + struct ttm_resource **res); +void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res); void ttm_resource_manager_init(struct ttm_resource_manager *man, unsigned long p_size); @@ -237,4 +276,20 @@ int ttm_resource_manager_evict_all(struct ttm_device *bdev, void ttm_resource_manager_debug(struct ttm_resource_manager *man, struct drm_printer *p); +struct ttm_kmap_iter * +ttm_kmap_iter_iomap_init(struct ttm_kmap_iter_iomap *iter_io, + struct io_mapping *iomap, + struct sg_table *st, + resource_size_t start); + +struct ttm_kmap_iter_linear_io; + +struct ttm_kmap_iter * +ttm_kmap_iter_linear_io_init(struct ttm_kmap_iter_linear_io *iter_io, + struct ttm_device *bdev, + struct ttm_resource *mem); + +void ttm_kmap_iter_linear_io_fini(struct ttm_kmap_iter_linear_io *iter_io, + struct ttm_device *bdev, + struct ttm_resource *mem); #endif diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index 134d09ef7766..818680c6a8ed 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -29,6 +29,7 @@ #include <linux/types.h> #include <drm/ttm/ttm_caching.h> +#include <drm/ttm/ttm_kmap_iter.h> struct ttm_bo_device; struct ttm_tt; @@ -69,6 +70,18 @@ struct ttm_tt { enum ttm_caching caching; }; +/** + * struct ttm_kmap_iter_tt - Specialization of a mappig iterator for a tt. + * @base: Embedded struct ttm_kmap_iter providing the usage interface + * @tt: Cached struct ttm_tt. + * @prot: Cached page protection for mapping. + */ +struct ttm_kmap_iter_tt { + struct ttm_kmap_iter base; + struct ttm_tt *tt; + pgprot_t prot; +}; + static inline bool ttm_tt_is_populated(struct ttm_tt *tt) { return tt->page_flags & TTM_PAGE_FLAG_PRIV_POPULATED; @@ -157,8 +170,24 @@ int ttm_tt_populate(struct ttm_device *bdev, struct ttm_tt *ttm, struct ttm_oper */ void ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm); +/** + * ttm_tt_mark_for_clear - Mark pages for clearing on populate. + * + * @ttm: Pointer to the ttm_tt structure + * + * Marks pages for clearing so that the next time the page vector is + * populated, the pages will be cleared. + */ +static inline void ttm_tt_mark_for_clear(struct ttm_tt *ttm) +{ + ttm->page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC; +} + void ttm_tt_mgr_init(unsigned long num_pages, unsigned long num_dma32_pages); +struct ttm_kmap_iter *ttm_kmap_iter_tt_init(struct ttm_kmap_iter_tt *iter_tt, + struct ttm_tt *tt); + #if IS_ENABLED(CONFIG_AGP) #include <linux/agp_backend.h> diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index d44a77e8a7e3..562b885cf9c3 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -78,19 +78,11 @@ struct dma_resv { #define dma_resv_held(obj) lockdep_is_held(&(obj)->lock.base) #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base) -/** - * dma_resv_get_list - get the reservation object's - * shared fence list, with update-side lock held - * @obj: the reservation object - * - * Returns the shared fence list. Does NOT take references to - * the fence. The obj->lock must be held. - */ -static inline struct dma_resv_list *dma_resv_get_list(struct dma_resv *obj) -{ - return rcu_dereference_protected(obj->fence, - dma_resv_held(obj)); -} +#ifdef CONFIG_DEBUG_MUTEXES +void dma_resv_reset_shared_max(struct dma_resv *obj); +#else +static inline void dma_resv_reset_shared_max(struct dma_resv *obj) {} +#endif /** * dma_resv_lock - lock the reservation object @@ -215,38 +207,29 @@ static inline struct ww_acquire_ctx *dma_resv_locking_ctx(struct dma_resv *obj) */ static inline void dma_resv_unlock(struct dma_resv *obj) { -#ifdef CONFIG_DEBUG_MUTEXES - /* Test shared fence slot reservation */ - if (rcu_access_pointer(obj->fence)) { - struct dma_resv_list *fence = dma_resv_get_list(obj); - - fence->shared_max = fence->shared_count; - } -#endif + dma_resv_reset_shared_max(obj); ww_mutex_unlock(&obj->lock); } /** - * dma_resv_get_excl - get the reservation object's - * exclusive fence, with update-side lock held + * dma_resv_exclusive - return the object's exclusive fence * @obj: the reservation object * - * Returns the exclusive fence (if any). Does NOT take a - * reference. Writers must hold obj->lock, readers may only - * hold a RCU read side lock. + * Returns the exclusive fence (if any). Caller must either hold the objects + * through dma_resv_lock() or the RCU read side lock through rcu_read_lock(), + * or one of the variants of each * * RETURNS * The exclusive fence or NULL */ static inline struct dma_fence * -dma_resv_get_excl(struct dma_resv *obj) +dma_resv_excl_fence(struct dma_resv *obj) { - return rcu_dereference_protected(obj->fence_excl, - dma_resv_held(obj)); + return rcu_dereference_check(obj->fence_excl, dma_resv_held(obj)); } /** - * dma_resv_get_excl_rcu - get the reservation object's + * dma_resv_get_excl_unlocked - get the reservation object's * exclusive fence, without lock held. * @obj: the reservation object * @@ -257,7 +240,7 @@ dma_resv_get_excl(struct dma_resv *obj) * The exclusive fence or NULL if none */ static inline struct dma_fence * -dma_resv_get_excl_rcu(struct dma_resv *obj) +dma_resv_get_excl_unlocked(struct dma_resv *obj) { struct dma_fence *fence; @@ -271,23 +254,29 @@ dma_resv_get_excl_rcu(struct dma_resv *obj) return fence; } +/** + * dma_resv_shared_list - get the reservation object's shared fence list + * @obj: the reservation object + * + * Returns the shared fence list. Caller must either hold the objects + * through dma_resv_lock() or the RCU read side lock through rcu_read_lock(), + * or one of the variants of each + */ +static inline struct dma_resv_list *dma_resv_shared_list(struct dma_resv *obj) +{ + return rcu_dereference_check(obj->fence, dma_resv_held(obj)); +} + void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences); void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence); - void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); - -int dma_resv_get_fences_rcu(struct dma_resv *obj, - struct dma_fence **pfence_excl, - unsigned *pshared_count, - struct dma_fence ***pshared); - +int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **pfence_excl, + unsigned *pshared_count, struct dma_fence ***pshared); int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src); - -long dma_resv_wait_timeout_rcu(struct dma_resv *obj, bool wait_all, bool intr, - unsigned long timeout); - -bool dma_resv_test_signaled_rcu(struct dma_resv *obj, bool test_all); +long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, + unsigned long timeout); +bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all); #endif /* _LINUX_RESERVATION_H */ diff --git a/include/uapi/drm/panfrost_drm.h b/include/uapi/drm/panfrost_drm.h index ec19db1eead8..061e700dd06c 100644 --- a/include/uapi/drm/panfrost_drm.h +++ b/include/uapi/drm/panfrost_drm.h @@ -171,6 +171,7 @@ enum drm_panfrost_param { DRM_PANFROST_PARAM_JS_FEATURES15, DRM_PANFROST_PARAM_NR_CORE_GROUPS, DRM_PANFROST_PARAM_THREAD_TLS_ALLOC, + DRM_PANFROST_PARAM_AFBC_FEATURES, }; struct drm_panfrost_get_param { |