From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ben Widawsky Subject: [PATCH 08/15] [v3] drm/i915/bdw: implement semaphore signal Date: Tue, 17 Dec 2013 15:00:10 -0800 Message-ID: <1387321210-8366-1-git-send-email-benjamin.widawsky@intel.com> References: <20131217191141.GQ22448@nuc-i3427.alporthouse.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mga02.intel.com (mga02.intel.com [134.134.136.20]) by gabe.freedesktop.org (Postfix) with ESMTP id 40EF4FD5D9 for ; Tue, 17 Dec 2013 15:00:17 -0800 (PST) In-Reply-To: <20131217191141.GQ22448@nuc-i3427.alporthouse.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: intel-gfx-bounces@lists.freedesktop.org Errors-To: intel-gfx-bounces@lists.freedesktop.org To: Intel GFX Cc: Ben Widawsky , Ben Widawsky List-Id: intel-gfx@lists.freedesktop.org Semaphore signalling works similarly to previous GENs with the exception that the per ring mailboxes no longer exist. Instead you must define your own space, somewhere in the GTT. The comments in the code define the layout I've opted for, which should be fairly future proof. Ie. I tried to define offsets in abstract terms (NUM_RINGS, seqno size, etc). NOTE: If one wanted to move this to the HWSP they could. I've decided one 4k object would be easier to deal with, and provide potential wins with cache locality, but that's all speculative. v2: Update the macro to not need the other ring's ring->id (Chris) v3: After the num_dwords update in the last patch, size was not properly adjusted on rebase. (Chris) Signed-off-by: Ben Widawsky --- drivers/gpu/drm/i915/i915_drv.h | 1 + drivers/gpu/drm/i915/i915_reg.h | 5 +- drivers/gpu/drm/i915/intel_ringbuffer.c | 198 +++++++++++++++++++++++++------- drivers/gpu/drm/i915/intel_ringbuffer.h | 38 +++++- 4 files changed, 196 insertions(+), 46 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index c638547..4ccb436 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1355,6 +1355,7 @@ typedef struct drm_i915_private { struct pci_dev *bridge_dev; struct intel_ring_buffer ring[I915_NUM_RINGS]; + struct drm_i915_gem_object *semaphore_obj; uint32_t last_seqno, next_seqno; drm_dma_handle_t *status_page_dmah; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index ac87ab8..5c3bf66 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -215,7 +215,7 @@ #define MI_DISPLAY_FLIP_IVB_SPRITE_B (3 << 19) #define MI_DISPLAY_FLIP_IVB_PLANE_C (4 << 19) #define MI_DISPLAY_FLIP_IVB_SPRITE_C (5 << 19) -#define MI_SEMAPHORE_MBOX MI_INSTR(0x16, 1) /* gen6+ */ +#define MI_SEMAPHORE_MBOX MI_INSTR(0x16, 1) /* gen6, gen7 */ #define MI_SEMAPHORE_GLOBAL_GTT (1<<22) #define MI_SEMAPHORE_UPDATE (1<<21) #define MI_SEMAPHORE_COMPARE (1<<20) @@ -240,6 +240,8 @@ #define MI_RESTORE_EXT_STATE_EN (1<<2) #define MI_FORCE_RESTORE (1<<1) #define MI_RESTORE_INHIBIT (1<<0) +#define MI_SEMAPHORE_SIGNAL MI_INSTR(0x1b, 0) /* GEN8+ */ +#define MI_SEMAPHORE_TARGET(engine) ((engine)<<15) #define MI_STORE_DWORD_IMM MI_INSTR(0x20, 1) #define MI_MEM_VIRTUAL (1 << 22) /* 965+ only */ #define MI_STORE_DWORD_INDEX MI_INSTR(0x21, 1) @@ -328,6 +330,7 @@ #define PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE (1<<10) /* GM45+ only */ #define PIPE_CONTROL_INDIRECT_STATE_DISABLE (1<<9) #define PIPE_CONTROL_NOTIFY (1<<8) +#define PIPE_CONTROL_FLUSH_ENABLE (1<<7) /* gen7+ */ #define PIPE_CONTROL_VF_CACHE_INVALIDATE (1<<4) #define PIPE_CONTROL_CONST_CACHE_INVALIDATE (1<<3) #define PIPE_CONTROL_STATE_CACHE_INVALIDATE (1<<2) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index db63a5c..d6e664d 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -619,6 +619,13 @@ static int init_render_ring(struct intel_ring_buffer *ring) static void render_ring_cleanup(struct intel_ring_buffer *ring) { struct drm_device *dev = ring->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + if (dev_priv->semaphore_obj) { + i915_gem_object_unpin(dev_priv->semaphore_obj); + drm_gem_object_unreference(&dev_priv->semaphore_obj->base); + dev_priv->semaphore_obj = NULL; + } if (ring->scratch.obj == NULL) return; @@ -632,6 +639,85 @@ static void render_ring_cleanup(struct intel_ring_buffer *ring) ring->scratch.obj = NULL; } +static int gen8_rcs_signal(struct intel_ring_buffer *signaller, + unsigned int num_dwords) +{ +#define MBOX_UPDATE_DWORDS 8 + struct drm_device *dev = signaller->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_ring_buffer *waiter; + int i, ret, num_rings; + + num_rings = hweight_long(INTEL_INFO(dev)->ring_mask); + num_dwords += (num_rings-1) * MBOX_UPDATE_DWORDS; +#undef MBOX_UPDATE_DWORDS + + ret = intel_ring_begin(signaller, num_dwords); + if (ret) + return ret; + + for_each_ring(waiter, dev_priv, i) { + u64 gtt_offset = signaller->semaphore.signal_ggtt[i]; + if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID) + continue; + + intel_ring_emit(signaller, GFX_OP_PIPE_CONTROL(6)); + intel_ring_emit(signaller, PIPE_CONTROL_GLOBAL_GTT_IVB | + PIPE_CONTROL_QW_WRITE | + PIPE_CONTROL_FLUSH_ENABLE); + intel_ring_emit(signaller, lower_32_bits(gtt_offset)); + intel_ring_emit(signaller, upper_32_bits(gtt_offset)); + intel_ring_emit(signaller, signaller->outstanding_lazy_seqno); + intel_ring_emit(signaller, 0); + intel_ring_emit(signaller, MI_SEMAPHORE_SIGNAL | + MI_SEMAPHORE_TARGET(waiter->id)); + intel_ring_emit(signaller, 0); + } + + WARN_ON(i != num_rings); + + return 0; +} + +static int gen8_xcs_signal(struct intel_ring_buffer *signaller, + unsigned int num_dwords) +{ +#define MBOX_UPDATE_DWORDS 6 + struct drm_device *dev = signaller->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_ring_buffer *waiter; + int i, ret, num_rings; + + num_rings = hweight_long(INTEL_INFO(dev)->ring_mask); + num_dwords = (num_rings-1) * MBOX_UPDATE_DWORDS; +#undef MBOX_UPDATE_DWORDS + + /* XXX: + 4 for the caller */ + ret = intel_ring_begin(signaller, num_dwords + 4); + if (ret) + return ret; + + for_each_ring(waiter, dev_priv, i) { + u64 gtt_offset = signaller->semaphore.signal_ggtt[i]; + if (gtt_offset == MI_SEMAPHORE_SYNC_INVALID) + continue; + + intel_ring_emit(signaller, (MI_FLUSH_DW + 1) | + MI_FLUSH_DW_OP_STOREDW); + intel_ring_emit(signaller, lower_32_bits(gtt_offset) | + MI_FLUSH_DW_USE_GTT); + intel_ring_emit(signaller, upper_32_bits(gtt_offset)); + intel_ring_emit(signaller, signaller->outstanding_lazy_seqno); + intel_ring_emit(signaller, MI_SEMAPHORE_SIGNAL | + MI_SEMAPHORE_TARGET(waiter->id)); + intel_ring_emit(signaller, 0); + } + + WARN_ON(i != num_rings); + + return 0; +} + static int gen6_signal(struct intel_ring_buffer *signaller, unsigned int num_dwords) { @@ -1848,16 +1934,67 @@ static int gen6_ring_flush(struct intel_ring_buffer *ring, return 0; } +/* seqno size is actually only a uint32, but since we plan to use MI_FLUSH_DW to + * do the writes, and that must have qw aligned offsets, simply pretend it's 8b. + */ +#define SEQNO_SIZE sizeof(uint64_t) +#define GEN8_SIGNAL_OFFSET(to) \ + (i915_gem_obj_ggtt_offset(dev_priv->semaphore_obj) + \ + (ring->id * I915_NUM_RINGS * SEQNO_SIZE) + \ + (SEQNO_SIZE * (to))) + +#define GEN8_WAIT_OFFSET(from) \ + (i915_gem_obj_ggtt_offset(dev_priv->semaphore_obj) + \ + ((from) * I915_NUM_RINGS * SEQNO_SIZE) + \ + (SEQNO_SIZE * ring->id)) + +#define GEN8_RING_SEMAPHORE_INIT do { \ + if (!dev_priv->semaphore_obj) { \ + break; \ + } \ + ring->semaphore.signal_ggtt[RCS] = GEN8_SIGNAL_OFFSET(RCS); \ + ring->semaphore.signal_ggtt[VCS] = GEN8_SIGNAL_OFFSET(VCS); \ + ring->semaphore.signal_ggtt[BCS] = GEN8_SIGNAL_OFFSET(BCS); \ + ring->semaphore.signal_ggtt[VECS] = GEN8_SIGNAL_OFFSET(VECS); \ + ring->semaphore.mbox[RCS] = GEN8_WAIT_OFFSET(RCS); \ + ring->semaphore.mbox[VCS] = GEN8_WAIT_OFFSET(VCS); \ + ring->semaphore.mbox[BCS] = GEN8_WAIT_OFFSET(BCS); \ + ring->semaphore.mbox[VECS] = GEN8_WAIT_OFFSET(VECS); \ + ring->semaphore.signal_ggtt[ring->id] = MI_SEMAPHORE_SYNC_INVALID; \ + ring->semaphore.mbox[ring->id] = GEN6_NOSYNC; \ + } while(0) +#undef seqno_size + + + int intel_init_render_ring_buffer(struct drm_device *dev) { drm_i915_private_t *dev_priv = dev->dev_private; struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct drm_i915_gem_object *obj; + int ret; ring->name = "render ring"; ring->id = RCS; ring->mmio_base = RENDER_RING_BASE; if (INTEL_INFO(dev)->gen >= 8) { + if (i915_semaphore_is_enabled(dev)) { + obj = i915_gem_alloc_object(dev, 4096); + if (obj == NULL) { + DRM_ERROR("Failed to allocate semaphore bo. Disabling semaphores\n"); + i915_semaphores = 0; + } else { + i915_gem_object_set_cache_level(obj, I915_CACHE_LLC); + ret = i915_gem_obj_ggtt_pin(obj, 0, false, true); + if (ret != 0) { + drm_gem_object_unreference(&obj->base); + DRM_ERROR("Failed to pin semaphore bo. Disabling semaphores\n"); + i915_semaphores = 0; + } else + dev_priv->semaphore_obj = obj; + } + } ring->add_request = gen6_add_request; ring->flush = gen8_render_ring_flush; ring->irq_get = gen8_ring_get_irq; @@ -1866,17 +2003,11 @@ int intel_init_render_ring_buffer(struct drm_device *dev) ring->get_seqno = gen6_ring_get_seqno; ring->set_seqno = ring_set_seqno; ring->semaphore.sync_to = gen6_ring_sync; - if (i915_semaphore_is_enabled(dev)) - ring->semaphore.signal = gen6_signal; - ring->semaphore.signal = gen6_signal; - ring->semaphore.mbox[RCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.mbox[VCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.mbox[BCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.mbox[VECS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.signal_mbox[RCS] = GEN6_NOSYNC; - ring->semaphore.signal_mbox[VCS] = GEN6_NOSYNC; - ring->semaphore.signal_mbox[BCS] = GEN6_NOSYNC; - ring->semaphore.signal_mbox[VECS] = GEN6_NOSYNC; + if (i915_semaphore_is_enabled(dev)) { + BUG_ON(!dev_priv->semaphore_obj); + ring->semaphore.signal = gen8_rcs_signal; + GEN8_RING_SEMAPHORE_INIT; + } } else if (INTEL_INFO(dev)->gen >= 6) { ring->add_request = gen6_add_request; ring->flush = gen7_render_ring_flush; @@ -1943,9 +2074,6 @@ int intel_init_render_ring_buffer(struct drm_device *dev) /* Workaround batchbuffer to combat CS tlb bug. */ if (HAS_BROKEN_CS_TLB(dev)) { - struct drm_i915_gem_object *obj; - int ret; - obj = i915_gem_alloc_object(dev, I830_BATCH_LIMIT); if (obj == NULL) { DRM_ERROR("Failed to allocate batch bo\n"); @@ -2060,16 +2188,10 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev) ring->dispatch_execbuffer = gen8_ring_dispatch_execbuffer; ring->semaphore.sync_to = gen6_ring_sync; - if (i915_semaphore_is_enabled(dev)) - ring->semaphore.signal = gen6_signal; - ring->semaphore.mbox[RCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.mbox[VCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.mbox[BCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.mbox[VECS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.signal_mbox[RCS] = GEN6_NOSYNC; - ring->semaphore.signal_mbox[VCS] = GEN6_NOSYNC; - ring->semaphore.signal_mbox[BCS] = GEN6_NOSYNC; - ring->semaphore.signal_mbox[VECS] = GEN6_NOSYNC; + if (i915_semaphore_is_enabled(dev)) { + ring->semaphore.signal = gen8_xcs_signal; + GEN8_RING_SEMAPHORE_INIT; + } } else { ring->irq_enable_mask = GT_BSD_USER_INTERRUPT; ring->irq_get = gen6_ring_get_irq; @@ -2131,16 +2253,10 @@ int intel_init_blt_ring_buffer(struct drm_device *dev) ring->irq_put = gen8_ring_put_irq; ring->dispatch_execbuffer = gen8_ring_dispatch_execbuffer; ring->semaphore.sync_to = gen6_ring_sync; - if (i915_semaphore_is_enabled(dev)) - ring->semaphore.signal = gen6_signal; - ring->semaphore.mbox[RCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.mbox[VCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.mbox[BCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.mbox[VECS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.signal_mbox[RCS] = GEN6_NOSYNC; - ring->semaphore.signal_mbox[VCS] = GEN6_NOSYNC; - ring->semaphore.signal_mbox[BCS] = GEN6_NOSYNC; - ring->semaphore.signal_mbox[VECS] = GEN6_NOSYNC; + if (i915_semaphore_is_enabled(dev)) { + ring->semaphore.signal = gen8_xcs_signal; + GEN8_RING_SEMAPHORE_INIT; + } } else { ring->irq_enable_mask = GT_BLT_USER_INTERRUPT; ring->irq_get = gen6_ring_get_irq; @@ -2186,16 +2302,10 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev) ring->irq_put = gen8_ring_put_irq; ring->dispatch_execbuffer = gen8_ring_dispatch_execbuffer; ring->semaphore.sync_to = gen6_ring_sync; - if (i915_semaphore_is_enabled(dev)) - ring->semaphore.signal = gen6_signal; - ring->semaphore.mbox[RCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.mbox[VCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.mbox[BCS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.mbox[VECS] = MI_SEMAPHORE_SYNC_INVALID; - ring->semaphore.signal_mbox[RCS] = GEN6_NOSYNC; - ring->semaphore.signal_mbox[VCS] = GEN6_NOSYNC; - ring->semaphore.signal_mbox[BCS] = GEN6_NOSYNC; - ring->semaphore.signal_mbox[VECS] = GEN6_NOSYNC; + if (i915_semaphore_is_enabled(dev)) { + ring->semaphore.signal = gen8_xcs_signal; + GEN8_RING_SEMAPHORE_INIT; + } } else { ring->irq_enable_mask = PM_VEBOX_USER_INTERRUPT; ring->irq_get = hsw_vebox_get_irq; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index c69ae10..cbaa346 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -111,6 +111,39 @@ struct intel_ring_buffer { #define I915_DISPATCH_PINNED 0x2 void (*cleanup)(struct intel_ring_buffer *ring); + /* GEN8 signal/wait table + * signal to signal to signal to signal to + * RCS VCS BCS VECS + * ------------------------------------------------------ + * RCS | NOP (0x00) | BCS (0x08) | VCS (0x10) | VECS (0x18) | + * |----------------------------------------------------- + * VCS | RCS (0x20) | NOP (0x28) | BCS (0x30) | VECS (0x38) | + * |----------------------------------------------------- + * BCS | RCS (0x40) | VCS (0x48) | NOP (0x50) | VECS (0x58) | + * |----------------------------------------------------- + * VECS | RCS (0x60) | VCS (0x68) | BCS (0x70) | NOP (0x78) | + * |----------------------------------------------------- + * + * Generalization: + * f(x, y) := (x->id * NUM_RINGS) + (seqno_size * y->id) + * ie. transpose of g(x, y) + * + * sync from sync from sync from sync from + * RCS VCS BCS VECS + * ------------------------------------------------------ + * RCS | NOP (0x00) | BCS (0x20) | VCS (0x40) | VECS (0x60) | + * |----------------------------------------------------- + * VCS | RCS (0x08) | NOP (0x28) | BCS (0x48) | VECS (0x68) | + * |----------------------------------------------------- + * BCS | RCS (0x10) | VCS (0x30) | NOP (0x50) | VECS (0x60) | + * |----------------------------------------------------- + * VECS | RCS (0x18) | VCS (0x38) | BCS (0x58) | NOP (0x78) | + * |----------------------------------------------------- + * + * Generalization: + * g(x, y) := (y->id * NUM_RINGS * NUM_RINGS) + (seqno_size * x->id) + * ie. transpose of f(x, y) + */ struct { u32 sync_seqno[I915_NUM_RINGS-1]; /* AKA wait() */ @@ -120,7 +153,10 @@ struct intel_ring_buffer { /* our mbox written by others */ u32 mbox[I915_NUM_RINGS]; /* mboxes this ring signals to */ - u32 signal_mbox[I915_NUM_RINGS]; + union { + u32 signal_mbox[I915_NUM_RINGS]; + u64 signal_ggtt[I915_NUM_RINGS]; + }; /* num_dwords is space the caller will need for atomic update */ int (*signal)(struct intel_ring_buffer *signaller, -- 1.8.5.1