From 609c1e15a44c25f722fb93e18668da30179a172f Mon Sep 17 00:00:00 2001 From: Tom Stellard Date: Tue, 20 Mar 2012 17:17:55 -0400 Subject: drm/radeon/kms: add info query for max pipes The maximum number of pipes is needed by the user space compute driver to calculate the number of wavefronts per thread group. Signed-off-by: Tom Stellard Signed-off-by: Dave Airlie --- include/drm/radeon_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/radeon_drm.h b/include/drm/radeon_drm.h index cb2f0c362a13..6cde931d8e68 100644 --- a/include/drm/radeon_drm.h +++ b/include/drm/radeon_drm.h @@ -962,6 +962,8 @@ struct drm_radeon_cs { #define RADEON_INFO_VA_START 0x0e /* maximum size of ib using the virtual memory cs */ #define RADEON_INFO_IB_VM_MAX_SIZE 0x0f +/* max pipes - needed for compute shaders */ +#define RADEON_INFO_MAX_PIPES 0x10 struct drm_radeon_info { uint32_t request; -- cgit v1.2.3 From dfcf5f36529d69eb35f4fdedfa6f244c5249698c Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 20 Mar 2012 17:18:14 -0400 Subject: drm/radeon/kms: add support for the CONST IB to the CS ioctl This adds a new chunk id to the CS ioctl to support the INDIRECT_BUFFER_CONST packet. On SI, the CP adds a new engine called the CE (Constant Engine) which runs simulatenously with the DE (Drawing Engine, formerly called the ME). This allows the CP to process two related IBs simultaneously. The CE is tasked with loading the constant data (constant buffers, resource descriptors, samplers, etc.) while the DE loads context register state and issues drawing commands. It's up to the userspace application to sychronize the CE and the DE using special synchronization packets. Signed-off-by: Alex Deucher Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/radeon.h | 3 +++ drivers/gpu/drm/radeon/radeon_cs.c | 47 ++++++++++++++++++++++++++++++++++++ drivers/gpu/drm/radeon/radeon_ring.c | 1 + include/drm/radeon_drm.h | 1 + 4 files changed, 52 insertions(+) (limited to 'include') diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 972f1679d1c9..f467fe5edf09 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -632,6 +632,7 @@ struct radeon_ib { uint32_t *ptr; struct radeon_fence *fence; unsigned vm_id; + bool is_const_ib; }; /* @@ -836,7 +837,9 @@ struct radeon_cs_parser { int chunk_ib_idx; int chunk_relocs_idx; int chunk_flags_idx; + int chunk_const_ib_idx; struct radeon_ib *ib; + struct radeon_ib *const_ib; void *track; unsigned family; int parser_error; diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index d9d9f5a59c42..087bd5053774 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -170,6 +170,7 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data) p->chunk_ib_idx = -1; p->chunk_relocs_idx = -1; p->chunk_flags_idx = -1; + p->chunk_const_ib_idx = -1; p->chunks_array = kcalloc(cs->num_chunks, sizeof(uint64_t), GFP_KERNEL); if (p->chunks_array == NULL) { return -ENOMEM; @@ -208,6 +209,12 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data) if (p->chunks[i].length_dw == 0) return -EINVAL; } + if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_CONST_IB) { + p->chunk_const_ib_idx = i; + /* zero length CONST IB isn't useful */ + if (p->chunks[i].length_dw == 0) + return -EINVAL; + } if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS) { p->chunk_flags_idx = i; /* zero length flags aren't useful */ @@ -389,6 +396,32 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev, if ((parser->cs_flags & RADEON_CS_USE_VM) == 0) return 0; + if ((rdev->family >= CHIP_TAHITI) && + (parser->chunk_const_ib_idx != -1)) { + ib_chunk = &parser->chunks[parser->chunk_const_ib_idx]; + if (ib_chunk->length_dw > RADEON_IB_VM_MAX_SIZE) { + DRM_ERROR("cs IB CONST too big: %d\n", ib_chunk->length_dw); + return -EINVAL; + } + r = radeon_ib_get(rdev, parser->ring, &parser->const_ib, + ib_chunk->length_dw * 4); + if (r) { + DRM_ERROR("Failed to get const ib !\n"); + return r; + } + parser->const_ib->is_const_ib = true; + parser->const_ib->length_dw = ib_chunk->length_dw; + /* Copy the packet into the IB */ + if (DRM_COPY_FROM_USER(parser->const_ib->ptr, ib_chunk->user_ptr, + ib_chunk->length_dw * 4)) { + return -EFAULT; + } + r = radeon_ring_ib_parse(rdev, parser->ring, parser->const_ib); + if (r) { + return r; + } + } + ib_chunk = &parser->chunks[parser->chunk_ib_idx]; if (ib_chunk->length_dw > RADEON_IB_VM_MAX_SIZE) { DRM_ERROR("cs IB too big: %d\n", ib_chunk->length_dw); @@ -424,11 +457,25 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev, if (r) { DRM_ERROR("Failed to synchronize rings !\n"); } + + if ((rdev->family >= CHIP_TAHITI) && + (parser->chunk_const_ib_idx != -1)) { + parser->const_ib->vm_id = vm->id; + /* ib pool is bind at 0 in virtual address space to gpu_addr is the + * offset inside the pool bo + */ + parser->const_ib->gpu_addr = parser->const_ib->sa_bo.offset; + r = radeon_ib_schedule(rdev, parser->const_ib); + if (r) + goto out; + } + parser->ib->vm_id = vm->id; /* ib pool is bind at 0 in virtual address space to gpu_addr is the * offset inside the pool bo */ parser->ib->gpu_addr = parser->ib->sa_bo.offset; + parser->ib->is_const_ib = false; r = radeon_ib_schedule(rdev, parser->ib); out: if (!r) { diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c index 30566201dffb..cc33b3d7c33b 100644 --- a/drivers/gpu/drm/radeon/radeon_ring.c +++ b/drivers/gpu/drm/radeon/radeon_ring.c @@ -133,6 +133,7 @@ retry: (*ib)->gpu_addr += (*ib)->sa_bo.offset; (*ib)->fence = fence; (*ib)->vm_id = 0; + (*ib)->is_const_ib = false; /* ib are most likely to be allocated in a ring fashion * thus rdev->ib_pool.head_id should be the id of the * oldest ib diff --git a/include/drm/radeon_drm.h b/include/drm/radeon_drm.h index 6cde931d8e68..7c491b4bcf65 100644 --- a/include/drm/radeon_drm.h +++ b/include/drm/radeon_drm.h @@ -908,6 +908,7 @@ struct drm_radeon_gem_va { #define RADEON_CHUNK_ID_RELOCS 0x01 #define RADEON_CHUNK_ID_IB 0x02 #define RADEON_CHUNK_ID_FLAGS 0x03 +#define RADEON_CHUNK_ID_CONST_IB 0x04 /* The first dword of RADEON_CHUNK_ID_FLAGS is a uint32 of these flags: */ #define RADEON_CS_KEEP_TILING_FLAGS 0x01 -- cgit v1.2.3 From fc7dbcc371c2b35d41f4db71aed7c55bb2a1175e Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 20 Mar 2012 17:18:27 -0400 Subject: drm/radeon/kms: Add SI pci ids Signed-off-by: Alex Deucher Signed-off-by: Dave Airlie --- include/drm/drm_pciids.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include') diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index 14b6cd022284..1ab52700f405 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -202,11 +202,49 @@ {0x1002, 0x6778, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6779, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x677B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6784, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6788, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x678A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6790, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6798, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6799, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x679A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x679E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x679F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6800, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6801, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6802, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6808, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6809, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6810, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6818, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6819, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6820, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6821, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6823, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6824, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6825, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6826, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6827, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6828, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6829, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x682D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x682F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6830, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6831, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6837, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6838, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6839, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x683B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x683D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x683F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6840, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6841, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6842, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6843, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6849, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x684C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6850, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6858, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6859, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ -- cgit v1.2.3 From d09b38d4311d5a1d94407a3f65313a51ce96814f Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 20 Mar 2012 17:18:41 -0400 Subject: drm/radeon/kms: add trinity pci ids Signed-off-by: Alex Deucher Signed-off-by: Dave Airlie --- include/drm/drm_pciids.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index 1ab52700f405..58d0bdab68dd 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -550,6 +550,22 @@ {0x1002, 0x9807, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x9808, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x9809, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9904, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9905, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9906, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9907, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9908, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9909, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x990A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x990F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9990, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9991, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9992, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9993, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9994, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0, 0, 0} #define r128_PCI_IDS \ -- cgit v1.2.3