diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index d0e3fec73d3e..bf4ffd8826ba 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -124,10 +124,20 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = { CMD( MI_STORE_DWORD_INDEX, SMI, !F, 0xFF, R ), CMD( MI_LOAD_REGISTER_IMM(1), SMI, !F, 0xFF, W, .reg = { .offset = 1, .mask = 0x007FFFFC } ), - CMD( MI_STORE_REGISTER_MEM(1), SMI, !F, 0xFF, W, - .reg = { .offset = 1, .mask = 0x007FFFFC } ), - CMD( MI_LOAD_REGISTER_MEM, SMI, !F, 0xFF, W, - .reg = { .offset = 1, .mask = 0x007FFFFC } ), + CMD( MI_STORE_REGISTER_MEM(1), SMI, !F, 0xFF, W | B, + .reg = { .offset = 1, .mask = 0x007FFFFC }, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), + CMD( MI_LOAD_REGISTER_MEM, SMI, !F, 0xFF, W | B, + .reg = { .offset = 1, .mask = 0x007FFFFC }, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), CMD( MI_BATCH_BUFFER_START, SMI, !F, 0xFF, S ), }; @@ -139,9 +149,31 @@ static const struct drm_i915_cmd_descriptor render_cmds[] = { CMD( MI_DISPLAY_FLIP, SMI, !F, 0xFF, R ), CMD( MI_SET_CONTEXT, SMI, !F, 0xFF, R ), CMD( MI_URB_CLEAR, SMI, !F, 0xFF, S ), + CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3F, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), CMD( MI_UPDATE_GTT, SMI, !F, 0xFF, R ), - CMD( MI_CLFLUSH, SMI, !F, 0x3FF, S ), - CMD( MI_CONDITIONAL_BATCH_BUFFER_END, SMI, !F, 0xFF, S ), + CMD( MI_CLFLUSH, SMI, !F, 0x3FF, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), + CMD( MI_REPORT_PERF_COUNT, SMI, !F, 0x3F, B, + .bits = {{ + .offset = 1, + .mask = MI_REPORT_PERF_COUNT_GGTT, + .expected = 0, + }}, ), + CMD( MI_CONDITIONAL_BATCH_BUFFER_END, SMI, !F, 0xFF, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), CMD( GFX_OP_3DSTATE_VF_STATISTICS, S3D, F, 1, S ), CMD( PIPELINE_SELECT, S3D, F, 1, S ), CMD( MEDIA_VFE_STATE, S3D, !F, 0xFFFF, B, @@ -158,6 +190,13 @@ static const struct drm_i915_cmd_descriptor render_cmds[] = { .offset = 1, .mask = (PIPE_CONTROL_MMIO_WRITE | PIPE_CONTROL_NOTIFY), .expected = 0, + }, + { + .offset = 1, + .mask = PIPE_CONTROL_GLOBAL_GTT_IVB, + .expected = 0, + .condition_offset = 1, + .condition_mask = PIPE_CONTROL_POST_SYNC_OP_MASK, }}, ), }; @@ -184,15 +223,32 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = { static const struct drm_i915_cmd_descriptor video_cmds[] = { CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), - CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, S ), + CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), CMD( MI_UPDATE_GTT, SMI, !F, 0x3F, R ), CMD( MI_FLUSH_DW, SMI, !F, 0x3F, B, .bits = {{ .offset = 0, .mask = MI_FLUSH_DW_NOTIFY, .expected = 0, + }, + { + .offset = 1, + .mask = MI_FLUSH_DW_USE_GTT, + .expected = 0, + .condition_offset = 0, + .condition_mask = MI_FLUSH_DW_OP_MASK, + }}, ), + CMD( MI_CONDITIONAL_BATCH_BUFFER_END, SMI, !F, 0xFF, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, }}, ), - CMD( MI_CONDITIONAL_BATCH_BUFFER_END, SMI, !F, 0xFF, S ), /* * MFX_WAIT doesn't fit the way we handle length for most commands. * It has a length field but it uses a non-standard length bias. @@ -203,26 +259,55 @@ static const struct drm_i915_cmd_descriptor video_cmds[] = { static const struct drm_i915_cmd_descriptor vecs_cmds[] = { CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), - CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, S ), + CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), CMD( MI_UPDATE_GTT, SMI, !F, 0x3F, R ), CMD( MI_FLUSH_DW, SMI, !F, 0x3F, B, .bits = {{ .offset = 0, .mask = MI_FLUSH_DW_NOTIFY, .expected = 0, + }, + { + .offset = 1, + .mask = MI_FLUSH_DW_USE_GTT, + .expected = 0, + .condition_offset = 0, + .condition_mask = MI_FLUSH_DW_OP_MASK, + }}, ), + CMD( MI_CONDITIONAL_BATCH_BUFFER_END, SMI, !F, 0xFF, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, }}, ), - CMD( MI_CONDITIONAL_BATCH_BUFFER_END, SMI, !F, 0xFF, S ), }; static const struct drm_i915_cmd_descriptor blt_cmds[] = { CMD( MI_DISPLAY_FLIP, SMI, !F, 0xFF, R ), - CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, S ), + CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, B, + .bits = {{ + .offset = 0, + .mask = MI_GLOBAL_GTT, + .expected = 0, + }}, ), CMD( MI_UPDATE_GTT, SMI, !F, 0x3F, R ), CMD( MI_FLUSH_DW, SMI, !F, 0x3F, B, .bits = {{ .offset = 0, .mask = MI_FLUSH_DW_NOTIFY, .expected = 0, + }, + { + .offset = 1, + .mask = MI_FLUSH_DW_USE_GTT, + .expected = 0, + .condition_offset = 0, + .condition_mask = MI_FLUSH_DW_OP_MASK, }}, ), CMD( COLOR_BLT, S2D, !F, 0x3F, S ), CMD( SRC_COPY_BLT, S2D, !F, 0x3F, S ), @@ -617,10 +702,20 @@ finish: */ bool i915_needs_cmd_parser(struct intel_ring_buffer *ring) { + drm_i915_private_t *dev_priv = ring->dev->dev_private; + /* No command tables indicates a platform without parsing */ if (!ring->cmd_tables) return false; + /* + * XXX: VLV is Gen7 and therefore has cmd_tables, but has PPGTT + * disabled. That will cause all of the parser's PPGTT checks to + * fail. For now, disable parsing when PPGTT is off. + */ + if (!dev_priv->mm.aliasing_ppgtt) + return false; + return (i915.enable_cmd_parser == 1); } @@ -737,6 +832,16 @@ int i915_parse_cmds(struct intel_ring_buffer *ring, if (desc->bits[i].mask == 0) break; + if (desc->bits[i].condition_mask != 0) { + u32 offset = + desc->bits[i].condition_offset; + u32 condition = cmd[offset] & + desc->bits[i].condition_mask; + + if (condition == 0) + continue; + } + dword = cmd[desc->bits[i].offset] & desc->bits[i].mask; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index ac764d0fda4b..8e1576cf6d63 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1732,11 +1732,17 @@ struct drm_i915_cmd_descriptor { * the expected value, the parser rejects it. Only valid if flags has * the CMD_DESC_BITMASK bit set. Only entries where mask is non-zero * are valid. + * + * If the check specifies a non-zero condition_mask then the parser + * only performs the check when the bits specified by condition_mask + * are non-zero. */ struct { u32 offset; u32 mask; u32 expected; + u32 condition_offset; + u32 condition_mask; } bits[MAX_CMD_DESC_BITMASKS]; }; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 450a08bad7ae..899bb4434d43 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -190,6 +190,8 @@ * Memory interface instructions used by the kernel */ #define MI_INSTR(opcode, flags) (((opcode) << 23) | (flags)) +/* Many MI commands use bit 22 of the header dword for GGTT vs PPGTT */ +#define MI_GLOBAL_GTT (1<<22) #define MI_NOOP MI_INSTR(0, 0) #define MI_USER_INTERRUPT MI_INSTR(0x02, 0) @@ -270,6 +272,7 @@ #define MI_FLUSH_DW_STORE_INDEX (1<<21) #define MI_INVALIDATE_TLB (1<<18) #define MI_FLUSH_DW_OP_STOREDW (1<<14) +#define MI_FLUSH_DW_OP_MASK (3<<14) #define MI_FLUSH_DW_NOTIFY (1<<8) #define MI_INVALIDATE_BSD (1<<7) #define MI_FLUSH_DW_USE_GTT (1<<2) @@ -336,6 +339,7 @@ #define PIPE_CONTROL_CS_STALL (1<<20) #define PIPE_CONTROL_TLB_INVALIDATE (1<<18) #define PIPE_CONTROL_QW_WRITE (1<<14) +#define PIPE_CONTROL_POST_SYNC_OP_MASK (3<<14) #define PIPE_CONTROL_DEPTH_STALL (1<<13) #define PIPE_CONTROL_WRITE_FLUSH (1<<12) #define PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH (1<<12) /* gen6+ */ @@ -364,6 +368,8 @@ #define MI_URB_CLEAR MI_INSTR(0x19, 0) #define MI_UPDATE_GTT MI_INSTR(0x23, 0) #define MI_CLFLUSH MI_INSTR(0x27, 0) +#define MI_REPORT_PERF_COUNT MI_INSTR(0x28, 0) +#define MI_REPORT_PERF_COUNT_GGTT (1<<0) #define MI_LOAD_REGISTER_MEM MI_INSTR(0x29, 0) #define MI_LOAD_REGISTER_REG MI_INSTR(0x2A, 0) #define MI_RS_STORE_DATA_IMM MI_INSTR(0x2B, 0)