diff options
Diffstat (limited to 'drivers/gpu/drm/i915')
22 files changed, 811 insertions, 239 deletions
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 8ba932b22f7c..e4b9eb1f6b60 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -26,6 +26,7 @@ */ #include "i915_drv.h" +#include "intel_ringbuffer.h" /** * DOC: batch buffer command parser @@ -50,13 +51,11 @@ * granting userspace undue privileges. There are three categories of privilege. * * First, commands which are explicitly defined as privileged or which should - * only be used by the kernel driver. The parser generally rejects such - * commands, though it may allow some from the drm master process. + * only be used by the kernel driver. The parser rejects such commands * * Second, commands which access registers. To support correct/enhanced * userspace functionality, particularly certain OpenGL extensions, the parser - * provides a whitelist of registers which userspace may safely access (for both - * normal and drm master processes). + * provides a whitelist of registers which userspace may safely access * * Third, commands which access privileged memory (i.e. GGTT, HWS page, etc). * The parser always rejects such commands. @@ -81,9 +80,9 @@ * in the per-engine command tables. * * Other command table entries map fairly directly to high level categories - * mentioned above: rejected, master-only, register whitelist. The parser - * implements a number of checks, including the privileged memory checks, via a - * general bitmasking mechanism. + * mentioned above: rejected, register whitelist. The parser implements a number + * of checks, including the privileged memory checks, via a general bitmasking + * mechanism. */ /* @@ -101,8 +100,6 @@ struct drm_i915_cmd_descriptor { * CMD_DESC_REJECT: The command is never allowed * CMD_DESC_REGISTER: The command should be checked against the * register whitelist for the appropriate ring - * CMD_DESC_MASTER: The command is allowed if the submitting process - * is the DRM master */ u32 flags; #define CMD_DESC_FIXED (1<<0) @@ -110,7 +107,6 @@ struct drm_i915_cmd_descriptor { #define CMD_DESC_REJECT (1<<2) #define CMD_DESC_REGISTER (1<<3) #define CMD_DESC_BITMASK (1<<4) -#define CMD_DESC_MASTER (1<<5) /* * The command's unique identification bits and the bitmask to get them. @@ -191,7 +187,7 @@ struct drm_i915_cmd_table { #define CMD(op, opm, f, lm, fl, ...) \ { \ .flags = (fl) | ((f) ? CMD_DESC_FIXED : 0), \ - .cmd = { (op), ~0u << (opm) }, \ + .cmd = { (op & ~0u << (opm)), ~0u << (opm) }, \ .length = { (lm) }, \ __VA_ARGS__ \ } @@ -206,14 +202,13 @@ struct drm_i915_cmd_table { #define R CMD_DESC_REJECT #define W CMD_DESC_REGISTER #define B CMD_DESC_BITMASK -#define M CMD_DESC_MASTER /* Command Mask Fixed Len Action ---------------------------------------------------------- */ -static const struct drm_i915_cmd_descriptor common_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_common_cmds[] = { CMD( MI_NOOP, SMI, F, 1, S ), CMD( MI_USER_INTERRUPT, SMI, F, 1, R ), - CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, M ), + CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, R ), CMD( MI_ARB_CHECK, SMI, F, 1, S ), CMD( MI_REPORT_HEAD, SMI, F, 1, S ), CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ), @@ -243,7 +238,7 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = { CMD( MI_BATCH_BUFFER_START, SMI, !F, 0xFF, S ), }; -static const struct drm_i915_cmd_descriptor render_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_render_cmds[] = { CMD( MI_FLUSH, SMI, F, 1, S ), CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), CMD( MI_PREDICATE, SMI, F, 1, S ), @@ -310,7 +305,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = { CMD( MI_URB_ATOMIC_ALLOC, SMI, F, 1, S ), CMD( MI_SET_APPID, SMI, F, 1, S ), CMD( MI_RS_CONTEXT, SMI, F, 1, S ), - CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, M ), + CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, R ), CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ), CMD( MI_LOAD_REGISTER_REG, SMI, !F, 0xFF, W, .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 } ), @@ -327,7 +322,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = { CMD( GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS, S3D, !F, 0x1FF, S ), }; -static const struct drm_i915_cmd_descriptor video_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_video_cmds[] = { CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), CMD( MI_SET_APPID, SMI, F, 1, S ), CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B, @@ -371,7 +366,7 @@ static const struct drm_i915_cmd_descriptor video_cmds[] = { CMD( MFX_WAIT, SMFX, F, 1, S ), }; -static const struct drm_i915_cmd_descriptor vecs_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_vecs_cmds[] = { CMD( MI_ARB_ON_OFF, SMI, F, 1, R ), CMD( MI_SET_APPID, SMI, F, 1, S ), CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B, @@ -409,7 +404,7 @@ static const struct drm_i915_cmd_descriptor vecs_cmds[] = { }}, ), }; -static const struct drm_i915_cmd_descriptor blt_cmds[] = { +static const struct drm_i915_cmd_descriptor gen7_blt_cmds[] = { CMD( MI_DISPLAY_FLIP, SMI, !F, 0xFF, R ), CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, B, .bits = {{ @@ -443,10 +438,64 @@ static const struct drm_i915_cmd_descriptor blt_cmds[] = { }; static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = { - CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, M ), + CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, R ), CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ), }; +/* + * For Gen9 we can still rely on the h/w to enforce cmd security, and only + * need to re-enforce the register access checks. We therefore only need to + * teach the cmdparser how to find the end of each command, and identify + * register accesses. The table doesn't need to reject any commands, and so + * the only commands listed here are: + * 1) Those that touch registers + * 2) Those that do not have the default 8-bit length + * + * Note that the default MI length mask chosen for this table is 0xFF, not + * the 0x3F used on older devices. This is because the vast majority of MI + * cmds on Gen9 use a standard 8-bit Length field. + * All the Gen9 blitter instructions are standard 0xFF length mask, and + * none allow access to non-general registers, so in fact no BLT cmds are + * included in the table at all. + * + */ +static const struct drm_i915_cmd_descriptor gen9_blt_cmds[] = { + CMD( MI_NOOP, SMI, F, 1, S ), + CMD( MI_USER_INTERRUPT, SMI, F, 1, S ), + CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, S ), + CMD( MI_FLUSH, SMI, F, 1, S ), + CMD( MI_ARB_CHECK, SMI, F, 1, S ), + CMD( MI_REPORT_HEAD, SMI, F, 1, S ), + CMD( MI_ARB_ON_OFF, SMI, F, 1, S ), + CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ), + CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, S ), + CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, S ), + CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, S ), + CMD( MI_LOAD_REGISTER_IMM(1), SMI, !F, 0xFF, W, + .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 } ), + CMD( MI_UPDATE_GTT, SMI, !F, 0x3FF, S ), + CMD( MI_STORE_REGISTER_MEM_GEN8, SMI, F, 4, W, + .reg = { .offset = 1, .mask = 0x007FFFFC } ), + CMD( MI_FLUSH_DW, SMI, !F, 0x3F, S ), + CMD( MI_LOAD_REGISTER_MEM_GEN8, SMI, F, 4, W, + .reg = { .offset = 1, .mask = 0x007FFFFC } ), + CMD( MI_LOAD_REGISTER_REG, SMI, !F, 0xFF, W, + .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 } ), + + /* + * We allow BB_START but apply further checks. We just sanitize the + * basic fields here. + */ +#define MI_BB_START_OPERAND_MASK GENMASK(SMI-1, 0) +#define MI_BB_START_OPERAND_EXPECT (MI_BATCH_PPGTT_HSW | 1) + CMD( MI_BATCH_BUFFER_START_GEN8, SMI, !F, 0xFF, B, + .bits = {{ + .offset = 0, + .mask = MI_BB_START_OPERAND_MASK, + .expected = MI_BB_START_OPERAND_EXPECT, + }}, ), +}; + static const struct drm_i915_cmd_descriptor noop_desc = CMD(MI_NOOP, SMI, F, 1, S); @@ -460,40 +509,44 @@ static const struct drm_i915_cmd_descriptor noop_desc = #undef R #undef W #undef B -#undef M -static const struct drm_i915_cmd_table gen7_render_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { render_cmds, ARRAY_SIZE(render_cmds) }, +static const struct drm_i915_cmd_table gen7_render_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) }, }; -static const struct drm_i915_cmd_table hsw_render_ring_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { render_cmds, ARRAY_SIZE(render_cmds) }, +static const struct drm_i915_cmd_table hsw_render_ring_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) }, { hsw_render_cmds, ARRAY_SIZE(hsw_render_cmds) }, }; -static const struct drm_i915_cmd_table gen7_video_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { video_cmds, ARRAY_SIZE(video_cmds) }, +static const struct drm_i915_cmd_table gen7_video_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_video_cmds, ARRAY_SIZE(gen7_video_cmds) }, }; -static const struct drm_i915_cmd_table hsw_vebox_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { vecs_cmds, ARRAY_SIZE(vecs_cmds) }, +static const struct drm_i915_cmd_table hsw_vebox_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_vecs_cmds, ARRAY_SIZE(gen7_vecs_cmds) }, }; -static const struct drm_i915_cmd_table gen7_blt_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { blt_cmds, ARRAY_SIZE(blt_cmds) }, +static const struct drm_i915_cmd_table gen7_blt_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) }, }; -static const struct drm_i915_cmd_table hsw_blt_ring_cmds[] = { - { common_cmds, ARRAY_SIZE(common_cmds) }, - { blt_cmds, ARRAY_SIZE(blt_cmds) }, +static const struct drm_i915_cmd_table hsw_blt_ring_cmd_table[] = { + { gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) }, + { gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) }, { hsw_blt_cmds, ARRAY_SIZE(hsw_blt_cmds) }, }; +static const struct drm_i915_cmd_table gen9_blt_cmd_table[] = { + { gen9_blt_cmds, ARRAY_SIZE(gen9_blt_cmds) }, +}; + + /* * Register whitelists, sorted by increasing register offset. */ @@ -609,17 +662,27 @@ static const struct drm_i915_reg_descriptor gen7_blt_regs[] = { REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE), }; -static const struct drm_i915_reg_descriptor ivb_master_regs[] = { - REG32(FORCEWAKE_MT), - REG32(DERRMR), - REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_A)), - REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_B)), - REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_C)), -}; - -static const struct drm_i915_reg_descriptor hsw_master_regs[] = { - REG32(FORCEWAKE_MT), - REG32(DERRMR), +static const struct drm_i915_reg_descriptor gen9_blt_regs[] = { + REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE), + REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE), + REG32(BCS_SWCTRL), + REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE), + REG64_IDX(BCS_GPR, 0), + REG64_IDX(BCS_GPR, 1), + REG64_IDX(BCS_GPR, 2), + REG64_IDX(BCS_GPR, 3), + REG64_IDX(BCS_GPR, 4), + REG64_IDX(BCS_GPR, 5), + REG64_IDX(BCS_GPR, 6), + REG64_IDX(BCS_GPR, 7), + REG64_IDX(BCS_GPR, 8), + REG64_IDX(BCS_GPR, 9), + REG64_IDX(BCS_GPR, 10), + REG64_IDX(BCS_GPR, 11), + REG64_IDX(BCS_GPR, 12), + REG64_IDX(BCS_GPR, 13), + REG64_IDX(BCS_GPR, 14), + REG64_IDX(BCS_GPR, 15), }; #undef REG64 @@ -628,28 +691,27 @@ static const struct drm_i915_reg_descriptor hsw_master_regs[] = { struct drm_i915_reg_table { const struct drm_i915_reg_descriptor *regs; int num_regs; - bool master; }; static const struct drm_i915_reg_table ivb_render_reg_tables[] = { - { gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false }, - { ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true }, + { gen7_render_regs, ARRAY_SIZE(gen7_render_regs) }, }; static const struct drm_i915_reg_table ivb_blt_reg_tables[] = { - { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false }, - { ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true }, + { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) }, }; static const struct drm_i915_reg_table hsw_render_reg_tables[] = { - { gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false }, - { hsw_render_regs, ARRAY_SIZE(hsw_render_regs), false }, - { hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true }, + { gen7_render_regs, ARRAY_SIZE(gen7_render_regs) }, + { hsw_render_regs, ARRAY_SIZE(hsw_render_regs) }, }; static const struct drm_i915_reg_table hsw_blt_reg_tables[] = { - { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false }, - { hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true }, + { gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) }, +}; + +static const struct drm_i915_reg_table gen9_blt_reg_tables[] = { + { gen9_blt_regs, ARRAY_SIZE(gen9_blt_regs) }, }; static u32 gen7_render_get_cmd_length_mask(u32 cmd_header) @@ -707,6 +769,17 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header) return 0; } +static u32 gen9_blt_get_cmd_length_mask(u32 cmd_header) +{ + u32 client = cmd_header >> INSTR_CLIENT_SHIFT; + + if (client == INSTR_MI_CLIENT || client == INSTR_BC_CLIENT) + return 0xFF; + + DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header); + return 0; +} + static bool validate_cmds_sorted(const struct intel_engine_cs *engine, const struct drm_i915_cmd_table *cmd_tables, int cmd_table_count) @@ -798,22 +871,15 @@ struct cmd_node { */ static inline u32 cmd_header_key(u32 x) { - u32 shift; - switch (x >> INSTR_CLIENT_SHIFT) { default: case INSTR_MI_CLIENT: - shift = STD_MI_OPCODE_SHIFT; - break; + return x >> STD_MI_OPCODE_SHIFT; case INSTR_RC_CLIENT: - shift = STD_3D_OPCODE_SHIFT; - break; + return x >> STD_3D_OPCODE_SHIFT; case INSTR_BC_CLIENT: - shift = STD_2D_OPCODE_SHIFT; - break; + return x >> STD_2D_OPCODE_SHIFT; } - - return x >> shift; } static int init_hash_table(struct intel_engine_cs *engine, @@ -871,18 +937,19 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) int cmd_table_count; int ret; - if (!IS_GEN7(engine->i915)) + if (!IS_GEN7(engine->i915) && !(IS_GEN9(engine->i915) && + engine->id == BCS)) return; switch (engine->id) { case RCS: if (IS_HASWELL(engine->i915)) { - cmd_tables = hsw_render_ring_cmds; + cmd_tables = hsw_render_ring_cmd_table; cmd_table_count = - ARRAY_SIZE(hsw_render_ring_cmds); + ARRAY_SIZE(hsw_render_ring_cmd_table); } else { - cmd_tables = gen7_render_cmds; - cmd_table_count = ARRAY_SIZE(gen7_render_cmds); + cmd_tables = gen7_render_cmd_table; + cmd_table_count = ARRAY_SIZE(gen7_render_cmd_table); } if (IS_HASWELL(engine->i915)) { @@ -892,36 +959,46 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) engine->reg_tables = ivb_render_reg_tables; engine->reg_table_count = ARRAY_SIZE(ivb_render_reg_tables); } - engine->get_cmd_length_mask = gen7_render_get_cmd_length_mask; break; case VCS: - cmd_tables = gen7_video_cmds; - cmd_table_count = ARRAY_SIZE(gen7_video_cmds); + cmd_tables = gen7_video_cmd_table; + cmd_table_count = ARRAY_SIZE(gen7_video_cmd_table); engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask; break; case BCS: - if (IS_HASWELL(engine->i915)) { - cmd_tables = hsw_blt_ring_cmds; - cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds); + engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask; + if (IS_GEN9(engine->i915)) { + cmd_tables = gen9_blt_cmd_table; + cmd_table_count = ARRAY_SIZE(gen9_blt_cmd_table); + engine->get_cmd_length_mask = + gen9_blt_get_cmd_length_mask; + + /* BCS Engine unsafe without parser */ + engine->flags |= I915_ENGINE_REQUIRES_CMD_PARSER; + } else if (IS_HASWELL(engine->i915)) { + cmd_tables = hsw_blt_ring_cmd_table; + cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmd_table); } else { - cmd_tables = gen7_blt_cmds; - cmd_table_count = ARRAY_SIZE(gen7_blt_cmds); + cmd_tables = gen7_blt_cmd_table; + cmd_table_count = ARRAY_SIZE(gen7_blt_cmd_table); } - if (IS_HASWELL(engine->i915)) { + if (IS_GEN9(engine->i915)) { + engine->reg_tables = gen9_blt_reg_tables; + engine->reg_table_count = + ARRAY_SIZE(gen9_blt_reg_tables); + } else if (IS_HASWELL(engine->i915)) { engine->reg_tables = hsw_blt_reg_tables; engine->reg_table_count = ARRAY_SIZE(hsw_blt_reg_tables); } else { engine->reg_tables = ivb_blt_reg_tables; engine->reg_table_count = ARRAY_SIZE(ivb_blt_reg_tables); } - - engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask; break; case VECS: - cmd_tables = hsw_vebox_cmds; - cmd_table_count = ARRAY_SIZE(hsw_vebox_cmds); + cmd_tables = hsw_vebox_cmd_table; + cmd_table_count = ARRAY_SIZE(hsw_vebox_cmd_table); /* VECS can use the same length_mask function as VCS */ engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask; break; @@ -947,7 +1024,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) return; } - engine->needs_cmd_parser = true; + engine->flags |= I915_ENGINE_USING_CMD_PARSER; } /** @@ -959,7 +1036,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) */ void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine) { - if (!engine->needs_cmd_parser) + if (!intel_engine_using_cmd_parser(engine)) return; fini_hash_table(engine); @@ -1033,22 +1110,16 @@ __find_reg(const struct drm_i915_reg_descriptor *table, int count, u32 addr) } static const struct drm_i915_reg_descriptor * -find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr) +find_reg(const struct intel_engine_cs *engine, u32 addr) { const struct drm_i915_reg_table *table = engine->reg_tables; + const struct drm_i915_reg_descriptor *reg = NULL; int count = engine->reg_table_count; - do { - if (!table->master || is_master) { - const struct drm_i915_reg_descriptor *reg; - - reg = __find_reg(table->regs, table->num_regs, addr); - if (reg != NULL) - return reg; - } - } while (table++, --count); + for (; !reg && (count > 0); ++table, --count) + reg = __find_reg(table->regs, table->num_regs, addr); - return NULL; + return reg; } /* Returns a vmap'd pointer to dst_obj, which the caller must unmap */ @@ -1133,8 +1204,7 @@ unpin_src: static bool check_cmd(const struct intel_engine_cs *engine, const struct drm_i915_cmd_descriptor *desc, - const u32 *cmd, u32 length, - const bool is_master) + const u32 *cmd, u32 length) { if (desc->flags & CMD_DESC_SKIP) return true; @@ -1144,12 +1214,6 @@ static bool check_cmd(const struct intel_engine_cs *engine, return false; } - if ((desc->flags & CMD_DESC_MASTER) && !is_master) { - DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n", - *cmd); - return false; - } - if (desc->flags & CMD_DESC_REGISTER) { /* * Get the distance between individual register offset @@ -1163,7 +1227,7 @@ static bool check_cmd(const struct intel_engine_cs *engine, offset += step) { const u32 reg_addr = cmd[offset] & desc->reg.mask; const struct drm_i915_reg_descriptor *reg = - find_reg(engine, is_master, reg_addr); + find_reg(engine, reg_addr); if (!reg) { DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (%s)\n", @@ -1218,6 +1282,12 @@ static bool check_cmd(const struct intel_engine_cs *engine, continue; } + if (desc->bits[i].offset >= length) { + DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X, too short to check bitmask (%s)\n", + *cmd, engine->name); + return false; + } + dword = cmd[desc->bits[i].offset] & desc->bits[i].mask; @@ -1235,16 +1305,112 @@ static bool check_cmd(const struct intel_engine_cs *engine, return true; } +static int check_bbstart(const struct i915_gem_context *ctx, + u32 *cmd, u32 offset, u32 length, + u32 batch_len, + u64 batch_start, + u64 shadow_batch_start) +{ + u64 jump_offset, jump_target; + u32 target_cmd_offset, target_cmd_index; + + /* For igt compatibility on older platforms */ + if (CMDPARSER_USES_GGTT(ctx->i915)) { + DRM_DEBUG("CMD: Rejecting BB_START for ggtt based submission\n"); + return -EACCES; + } + + if (length != 3) { + DRM_DEBUG("CMD: Recursive BB_START with bad length(%u)\n", + length); + return -EINVAL; + } + + jump_target = *(u64*)(cmd+1); + jump_offset = jump_target - batch_start; + + /* + * Any underflow of jump_target is guaranteed to be outside the range + * of a u32, so >= test catches both too large and too small + */ + if (jump_offset >= batch_len) { + DRM_DEBUG("CMD: BB_START to 0x%llx jumps out of BB\n", + jump_target); + return -EINVAL; + } + + /* + * This cannot overflow a u32 because we already checked jump_offset + * is within the BB, and the batch_len is a u32 + */ + target_cmd_offset = lower_32_bits(jump_offset); + target_cmd_index = target_cmd_offset / sizeof(u32); + + *(u64*)(cmd + 1) = shadow_batch_start + target_cmd_offset; + + if (target_cmd_index == offset) + return 0; + + if (ctx->jump_whitelist_cmds <= target_cmd_index) { + DRM_DEBUG("CMD: Rejecting BB_START - truncated whitelist array\n"); + return -EINVAL; + } else if (!test_bit(target_cmd_index, ctx->jump_whitelist)) { + DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n", + jump_target); + return -EINVAL; + } + + return 0; +} + +static void init_whitelist(struct i915_gem_context *ctx, u32 batch_len) +{ + const u32 batch_cmds = DIV_ROUND_UP(batch_len, sizeof(u32)); + const u32 exact_size = BITS_TO_LONGS(batch_cmds); + u32 next_size = BITS_TO_LONGS(roundup_pow_of_two(batch_cmds)); + unsigned long *next_whitelist; + + if (CMDPARSER_USES_GGTT(ctx->i915)) + return; + + if (batch_cmds <= ctx->jump_whitelist_cmds) { + bitmap_zero(ctx->jump_whitelist, batch_cmds); + return; + } + +again: + next_whitelist = kcalloc(next_size, sizeof(long), GFP_KERNEL); + if (next_whitelist) { + kfree(ctx->jump_whitelist); + ctx->jump_whitelist = next_whitelist; + ctx->jump_whitelist_cmds = + next_size * BITS_PER_BYTE * sizeof(long); + return; + } + + if (next_size > exact_size) { + next_size = exact_size; + goto again; + } + + DRM_DEBUG("CMD: Failed to extend whitelist. BB_START may be disallowed\n"); + bitmap_zero(ctx->jump_whitelist, ctx->jump_whitelist_cmds); + + return; +} + #define LENGTH_BIAS 2 /** * i915_parse_cmds() - parse a submitted batch buffer for privilege violations + * @ctx: the context in which the batch is to execute * @engine: the engine on which the batch is to execute * @batch_obj: the batch buffer in question - * @shadow_batch_obj: copy of the batch buffer in question + * @batch_start: Canonical base address of batch * @batch_start_offset: byte offset in the batch at which execution starts * @batch_len: length of the commands in batch_obj - * @is_master: is the submitting process the drm master? + * @shadow_batch_obj: copy of the batch buffer in question + * @shadow_batch_start: Canonical base address of shadow_batch_obj * * Parses the specified batch buffer looking for privilege violations as * described in the overview. @@ -1252,14 +1418,17 @@ static bool check_cmd(const struct intel_engine_cs *engine, * Return: non-zero if the parser finds violations or otherwise fails; -EACCES * if the batch appears legal but should use hardware parsing */ -int intel_engine_cmd_parser(struct intel_engine_cs *engine, + +int intel_engine_cmd_parser(struct i915_gem_context *ctx, + struct intel_engine_cs *engine, struct drm_i915_gem_object *batch_obj, - struct drm_i915_gem_object *shadow_batch_obj, + u64 batch_start, u32 batch_start_offset, u32 batch_len, - bool is_master) + struct drm_i915_gem_object *shadow_batch_obj, + u64 shadow_batch_start) { - u32 *cmd, *batch_end; + u32 *cmd, *batch_end, offset = 0; struct drm_i915_cmd_descriptor default_desc = noop_desc; const struct drm_i915_cmd_descriptor *desc = &default_desc; bool needs_clflush_after = false; @@ -1273,6 +1442,8 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, return PTR_ERR(cmd); } + init_whitelist(ctx, batch_len); + /* * We use the batch length as size because the shadow object is as * large or larger and copy_batch() will write MI_NOPs to the extra @@ -1282,31 +1453,15 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, do { u32 length; - if (*cmd == MI_BATCH_BUFFER_END) { - if (needs_clflush_after) { - void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping); - drm_clflush_virt_range(ptr, - (void *)(cmd + 1) - ptr); - } + if (*cmd == MI_BATCH_BUFFER_END) break; - } desc = find_cmd(engine, *cmd, desc, &default_desc); if (!desc) { DRM_DEBUG_DRIVER("CMD: Unrecognized command: 0x%08X\n", *cmd); ret = -EINVAL; - break; - } - - /* - * If the batch buffer contains a chained batch, return an - * error that tells the caller to abort and dispatch the - * workload as a non-secure batch. - */ - if (desc->cmd.value == MI_BATCH_BUFFER_START) { - ret = -EACCES; - break; + goto err; } if (desc->flags & CMD_DESC_FIXED) @@ -1320,22 +1475,43 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine, length, batch_end - cmd); ret = -EINVAL; - break; + goto err; } - if (!check_cmd(engine, desc, cmd, length, is_master)) { + if (!check_cmd(engine, desc, cmd, length)) { ret = -EACCES; + goto err; + } + + if (desc->cmd.value == MI_BATCH_BUFFER_START) { + ret = check_bbstart(ctx, cmd, offset, length, + batch_len, batch_start, + shadow_batch_start); + + if (ret) + goto err; break; } + if (ctx->jump_whitelist_cmds > offset) + set_bit(offset, ctx->jump_whitelist); + cmd += length; + offset += length; if (cmd >= batch_end) { DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n"); ret = -EINVAL; - break; + goto err; } } while (1); + if (needs_clflush_after) { + void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping); + + drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr); + } + +err: i915_gem_object_unpin_map(shadow_batch_obj); return ret; } @@ -1357,7 +1533,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv) /* If the command parser is not enabled, report 0 - unsupported */ for_each_engine(engine, dev_priv, id) { - if (engine->needs_cmd_parser) { + if (intel_engine_using_cmd_parser(engine)) { active = true; break; } @@ -1382,6 +1558,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv) * the parser enabled. * 9. Don't whitelist or handle oacontrol specially, as ownership * for oacontrol state is moving to i915-perf. + * 10. Support for Gen9 BCS Parsing */ - return 9; + return 10; } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index c75f4ccbcdef..02a2af7c8166 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -323,7 +323,7 @@ static int i915_getparam(struct drm_device *dev, void *data, value = i915.semaphores; break; case I915_PARAM_HAS_SECURE_BATCHES: - value = capable(CAP_SYS_ADMIN); + value = HAS_SECURE_BATCHES(dev_priv) && capable(CAP_SYS_ADMIN); break; case I915_PARAM_CMD_PARSER_VERSION: value = i915_cmd_parser_get_version(dev_priv); @@ -1564,6 +1564,7 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation) disable_rpm_wakeref_asserts(dev_priv); intel_display_set_init_power(dev_priv, false); + i915_rc6_ctx_wa_suspend(dev_priv); fw_csr = !IS_GEN9_LP(dev_priv) && suspend_to_idle(dev_priv) && dev_priv->csr.dmc_payload; @@ -1800,6 +1801,7 @@ static int i915_drm_resume_early(struct drm_device *dev) intel_display_set_init_power(dev_priv, true); i915_gem_sanitize(dev_priv); + i915_rc6_ctx_wa_resume(dev_priv); enable_rpm_wakeref_asserts(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 41f51509c9e4..a5fb7404b29e 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1320,6 +1320,7 @@ struct intel_gen6_power_mgmt { enum { LOW_POWER, BETWEEN, HIGH_POWER } power; bool enabled; + bool ctx_corrupted; struct delayed_work autoenable_work; atomic_t num_waiters; atomic_t boosts; @@ -2980,6 +2981,12 @@ intel_info(const struct drm_i915_private *dev_priv) #define IS_GEN9_LP(dev_priv) (IS_GEN9(dev_priv) && IS_LP(dev_priv)) #define IS_GEN9_BC(dev_priv) (IS_GEN9(dev_priv) && !IS_LP(dev_priv)) +/* + * The Gen7 cmdparser copies the scanned buffer to the ggtt for execution + * All later gens can run the final buffer from the ppgtt + */ +#define CMDPARSER_USES_GGTT(dev_priv) IS_GEN7(dev_priv) + #define ENGINE_MASK(id) BIT(id) #define RENDER_RING ENGINE_MASK(RCS) #define BSD_RING ENGINE_MASK(VCS) @@ -2996,6 +3003,8 @@ intel_info(const struct drm_i915_private *dev_priv) #define HAS_BLT(dev_priv) HAS_ENGINE(dev_priv, BCS) #define HAS_VEBOX(dev_priv) HAS_ENGINE(dev_priv, VECS) +#define HAS_SECURE_BATCHES(dev_priv) (INTEL_GEN(dev_priv) < 6) + #define HAS_LLC(dev_priv) ((dev_priv)->info.has_llc) #define HAS_SNOOP(dev_priv) ((dev_priv)->info.has_snoop) #define HAS_EDRAM(dev_priv) (!!((dev_priv)->edram_cap & EDRAM_ENABLED)) @@ -3017,9 +3026,12 @@ intel_info(const struct drm_i915_private *dev_priv) /* Early gen2 have a totally busted CS tlb and require pinned batches. */ #define HAS_BROKEN_CS_TLB(dev_priv) (IS_I830(dev_priv) || IS_I845G(dev_priv)) +#define NEEDS_RC6_CTX_CORRUPTION_WA(dev_priv) \ + (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) == 9) + /* WaRsDisableCoarsePowerGating:skl,bxt */ #define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \ - (IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv)) + (INTEL_GEN(dev_priv) == 9) /* * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts @@ -3391,6 +3403,14 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, u64 alignment, u64 flags); +struct i915_vma * __must_check +i915_gem_object_pin(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, + const struct i915_ggtt_view *view, + u64 size, + u64 alignment, + u64 flags); + int i915_gem_object_unbind(struct drm_i915_gem_object *obj); void i915_gem_release_mmap(struct drm_i915_gem_object *obj); @@ -3841,12 +3861,14 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type); int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv); void intel_engine_init_cmd_parser(struct intel_engine_cs *engine); void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine); -int intel_engine_cmd_parser(struct intel_engine_cs *engine, +int intel_engine_cmd_parser(struct i915_gem_context *cxt, + struct intel_engine_cs *engine, struct drm_i915_gem_object *batch_obj, - struct drm_i915_gem_object *shadow_batch_obj, + u64 user_batch_start, u32 batch_start_offset, u32 batch_len, - bool is_master); + struct drm_i915_gem_object *shadow_batch_obj, + u64 shadow_batch_start); /* i915_perf.c */ extern void i915_perf_init(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 727018a16cca..9263b65720bc 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1834,6 +1834,10 @@ int i915_gem_fault(struct vm_fault *vmf) unsigned int flags; int ret; + /* Sanity check that we allow writing into this object */ + if (i915_gem_object_is_readonly(obj) && write) + return VM_FAULT_SIGBUS; + /* We don't use vmf->pgoff since that has the fake offset */ page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT; @@ -3239,6 +3243,12 @@ i915_gem_idle_work_handler(struct work_struct *work) if (INTEL_GEN(dev_priv) >= 6) gen6_rps_idle(dev_priv); + + if (NEEDS_RC6_CTX_CORRUPTION_WA(dev_priv)) { + i915_rc6_ctx_wa_check(dev_priv); + intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); + } + intel_runtime_pm_put(dev_priv); out_unlock: mutex_unlock(&dev->struct_mutex); @@ -3996,6 +4006,20 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, { struct drm_i915_private *dev_priv = to_i915(obj->base.dev); struct i915_address_space *vm = &dev_priv->ggtt.base; + + return i915_gem_object_pin(obj, vm, view, size, alignment, + flags | PIN_GLOBAL); +} + +struct i915_vma * +i915_gem_object_pin(struct drm_i915_gem_object *obj, + struct i915_address_space *vm, + const struct i915_ggtt_view *view, + u64 size, + u64 alignment, + u64 flags) +{ + struct drm_i915_private *dev_priv = to_i915(obj->base.dev); struct i915_vma *vma; int ret; @@ -4053,7 +4077,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, return ERR_PTR(ret); } - ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL); + ret = i915_vma_pin(vma, size, alignment, flags); if (ret) return ERR_PTR(ret); diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 8afd2ce59b8d..3925a63c1661 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -141,6 +141,8 @@ static void i915_gem_context_free(struct i915_gem_context *ctx) __i915_gem_object_release_unless_active(ce->state->obj); } + kfree(ctx->jump_whitelist); + kfree(ctx->name); put_pid(ctx->pid); @@ -321,6 +323,9 @@ __create_hw_context(struct drm_i915_private *dev_priv, else ctx->ggtt_offset_bias = I915_GTT_PAGE_SIZE; + ctx->jump_whitelist = NULL; + ctx->jump_whitelist_cmds = 0; + return ctx; err_pid: diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h index 44688e22a5c2..b651c5f427b9 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.h +++ b/drivers/gpu/drm/i915/i915_gem_context.h @@ -181,6 +181,12 @@ struct i915_gem_context { /** remap_slice: Bitmask of cache lines that need remapping */ u8 remap_slice; + /** jump_whitelist: Bit array for tracking cmds during cmdparsing */ + unsigned long *jump_whitelist; + + /** jump_whitelist_cmds: No of cmd slots available */ + u32 jump_whitelist_cmds; + /** handles_vma: rbtree to look up our context specific obj/vma for * the user handle. (user handles are per fd, but the binding is * per vm, which may be one per context or shared with the global GTT) diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 4cc9ce4b5b16..d99d05a91032 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -268,6 +268,13 @@ static inline u64 gen8_noncanonical_addr(u64 address) return address & GENMASK_ULL(GEN8_HIGH_ADDRESS_BIT, 0); } +static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb) +{ + return intel_engine_requires_cmd_parser(eb->engine) || + (intel_engine_using_cmd_parser(eb->engine) && + eb->args->batch_len); +} + static int eb_create(struct i915_execbuffer *eb) { if (!(eb->args->flags & I915_EXEC_HANDLE_LUT)) { @@ -1165,6 +1172,10 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb, if (unlikely(!cache->rq)) { int err; + /* If we need to copy for the cmdparser, we will stall anyway */ + if (eb_use_cmdparser(eb)) + return ERR_PTR(-EWOULDBLOCK); + err = __reloc_gpu_alloc(eb, vma, len); if (unlikely(err)) return ERR_PTR(err); @@ -1902,10 +1913,38 @@ static int i915_reset_gen7_sol_offsets(struct drm_i915_gem_request *req) return 0; } -static struct i915_vma *eb_parse(struct i915_execbuffer *eb, bool is_master) +static struct i915_vma * +shadow_batch_pin(struct i915_execbuffer *eb, struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *dev_priv = eb->i915; + struct i915_address_space *vm; + u64 flags; + + /* + * PPGTT backed shadow buffers must be mapped RO, to prevent + * post-scan tampering + */ + if (CMDPARSER_USES_GGTT(dev_priv)) { + flags = PIN_GLOBAL; + vm = &dev_priv->ggtt.base; + } else if (eb->vm->has_read_only) { + flags = PIN_USER; + vm = eb->vm; + i915_gem_object_set_readonly(obj); + } else { + DRM_DEBUG("Cannot prevent post-scan tampering without RO capable vm\n"); + return ERR_PTR(-EINVAL); + } + + return i915_gem_object_pin(obj, vm, NULL, 0, 0, flags); +} + +static struct i915_vma *eb_parse(struct i915_execbuffer *eb) { struct drm_i915_gem_object *shadow_batch_obj; struct i915_vma *vma; + u64 batch_start; + u64 shadow_batch_start; int err; shadow_batch_obj = i915_gem_batch_pool_get(&eb->engine->batch_pool, @@ -1913,29 +1952,53 @@ static struct i915_vma *eb_parse(struct i915_execbuffer *eb, bool is_master) if (IS_ERR(shadow_batch_obj)) return ERR_CAST(shadow_batch_obj); - err = intel_engine_cmd_parser(eb->engine, + vma = shadow_batch_pin(eb, shadow_batch_obj); + if (IS_ERR(vma)) + goto out; + + batch_start = gen8_canonical_addr(eb->batch->node.start) + + eb->batch_start_offset; + + shadow_batch_start = gen8_canonical_addr(vma->node.start); + + err = intel_engine_cmd_parser(eb->ctx, + eb->engine, eb->batch->obj, - shadow_batch_obj, + batch_start, eb->batch_start_offset, eb->batch_len, - is_master); + shadow_batch_obj, + shadow_batch_start); + if (err) { - if (err == -EACCES) /* unhandled chained batch */ + i915_vma_unpin(vma); + + /* + * Unsafe GGTT-backed buffers can still be submitted safely + * as non-secure. + * For PPGTT backing however, we have no choice but to forcibly + * reject unsafe buffers + */ + if (CMDPARSER_USES_GGTT(eb->i915) && (err == -EACCES)) + /* Execute original buffer non-secure */ vma = NULL; else vma = ERR_PTR(err); - goto out; - } - vma = i915_gem_object_ggtt_pin(shadow_batch_obj, NULL, 0, 0, 0); - if (IS_ERR(vma)) goto out; + } eb->vma[eb->buffer_count] = i915_vma_get(vma); eb->flags[eb->buffer_count] = __EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_REF; vma->exec_flags = &eb->flags[eb->buffer_count]; eb->buffer_count++; + eb->batch_start_offset = 0; + eb->batch = vma; + /* eb->batch_len unchanged */ + + if (CMDPARSER_USES_GGTT(eb->i915)) + eb->batch_flags |= I915_DISPATCH_SECURE; out: i915_gem_object_unpin_pages(shadow_batch_obj); @@ -2186,6 +2249,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, struct drm_i915_gem_exec_object2 *exec, struct drm_syncobj **fences) { + struct drm_i915_private *dev_priv = to_i915(dev); struct i915_execbuffer eb; struct dma_fence *in_fence = NULL; struct sync_file *out_fence = NULL; @@ -2195,7 +2259,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, BUILD_BUG_ON(__EXEC_OBJECT_INTERNAL_FLAGS & ~__EXEC_OBJECT_UNKNOWN_FLAGS); - eb.i915 = to_i915(dev); + eb.i915 = dev_priv; eb.file = file; eb.args = args; if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC)) @@ -2217,8 +2281,15 @@ i915_gem_do_execbuffer(struct drm_device *dev, eb.batch_flags = 0; if (args->flags & I915_EXEC_SECURE) { + if (INTEL_GEN(dev_priv) >= 11) + return -ENODEV; + + /* Return -EPERM to trigger fallback code on old binaries. */ + if (!HAS_SECURE_BATCHES(dev_priv)) + return -EPERM; + if (!drm_is_current_master(file) || !capable(CAP_SYS_ADMIN)) - return -EPERM; + return -EPERM; eb.batch_flags |= I915_DISPATCH_SECURE; } @@ -2305,34 +2376,19 @@ i915_gem_do_execbuffer(struct drm_device *dev, goto err_vma; } - if (eb.engine->needs_cmd_parser && eb.batch_len) { + if (eb.batch_len == 0) + eb.batch_len = eb.batch->size - eb.batch_start_offset; + + if (eb_use_cmdparser(&eb)) { struct i915_vma *vma; - vma = eb_parse(&eb, drm_is_current_master(file)); + vma = eb_parse(&eb); if (IS_ERR(vma)) { err = PTR_ERR(vma); goto err_vma; } - - if (vma) { - /* - * Batch parsed and accepted: - * - * Set the DISPATCH_SECURE bit to remove the NON_SECURE - * bit from MI_BATCH_BUFFER_START commands issued in - * the dispatch_execbuffer implementations. We - * specifically don't want that set on batches the - * command parser has accepted. - */ - eb.batch_flags |= I915_DISPATCH_SECURE; - eb.batch_start_offset = 0; - eb.batch = vma; - } } - if (eb.batch_len == 0) - eb.batch_len = eb.batch->size - eb.batch_start_offset; - /* * snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure * batch" bit. Hence we need to pin secure batches into the global gtt. diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index ad524cb0f6fc..47d178817a29 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -159,7 +159,8 @@ int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv, if (enable_ppgtt == 0 && INTEL_GEN(dev_priv) < 9) return 0; - if (enable_ppgtt == 1) + /* Full PPGTT is required by the Gen9 cmdparser */ + if (enable_ppgtt == 1 && INTEL_GEN(dev_priv) != 9) return 1; if (enable_ppgtt == 2 && has_full_ppgtt) @@ -207,9 +208,9 @@ static int ppgtt_bind_vma(struct i915_vma *vma, vma->pages = vma->obj->mm.pages; - /* Currently applicable only to VLV */ + /* Applicable to VLV, and gen8+ */ pte_flags = 0; - if (vma->obj->gt_ro) + if (i915_gem_object_is_readonly(vma->obj)) pte_flags |= PTE_READ_ONLY; vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags); @@ -223,10 +224,13 @@ static void ppgtt_unbind_vma(struct i915_vma *vma) } static gen8_pte_t gen8_pte_encode(dma_addr_t addr, - enum i915_cache_level level) + enum i915_cache_level level, + u32 flags) { - gen8_pte_t pte = _PAGE_PRESENT | _PAGE_RW; - pte |= addr; + gen8_pte_t pte = addr | _PAGE_PRESENT | _PAGE_RW; + + if (unlikely(flags & PTE_READ_ONLY)) + pte &= ~_PAGE_RW; switch (level) { case I915_CACHE_NONE: @@ -487,7 +491,7 @@ static void gen8_initialize_pt(struct i915_address_space *vm, struct i915_page_table *pt) { fill_px(vm, pt, - gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC)); + gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0)); } static void gen6_initialize_pt(struct i915_address_space *vm, @@ -691,7 +695,7 @@ static bool gen8_ppgtt_clear_pt(struct i915_address_space *vm, unsigned int pte = gen8_pte_index(start); unsigned int pte_end = pte + num_entries; const gen8_pte_t scratch_pte = - gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC); + gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0); gen8_pte_t *vaddr; GEM_BUG_ON(num_entries > pt->used_ptes); @@ -863,10 +867,11 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt, struct i915_page_directory_pointer *pdp, struct sgt_dma *iter, struct gen8_insert_pte *idx, - enum i915_cache_level cache_level) + enum i915_cache_level cache_level, + u32 flags) { struct i915_page_directory *pd; - const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level); + const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags); gen8_pte_t *vaddr; bool ret; @@ -917,20 +922,20 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt, static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm, struct i915_vma *vma, enum i915_cache_level cache_level, - u32 unused) + u32 flags) { struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm); struct sgt_dma iter = sgt_dma(vma); struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start); gen8_ppgtt_insert_pte_entries(ppgtt, &ppgtt->pdp, &iter, &idx, - cache_level); + cache_level, flags); } static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm, struct i915_vma *vma, enum i915_cache_level cache_level, - u32 unused) + u32 flags) { struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm); struct sgt_dma iter = sgt_dma(vma); @@ -938,7 +943,7 @@ static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm, struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start); while (gen8_ppgtt_insert_pte_entries(ppgtt, pdps[idx.pml4e++], &iter, - &idx, cache_level)) + &idx, cache_level, flags)) GEM_BUG_ON(idx.pml4e >= GEN8_PML4ES_PER_PML4); } @@ -1264,7 +1269,7 @@ static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m) { struct i915_address_space *vm = &ppgtt->base; const gen8_pte_t scratch_pte = - gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC); + gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0); u64 start = 0, length = ppgtt->base.total; if (use_4lvl(vm)) { @@ -1339,6 +1344,13 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt) return ret; } + /* + * From bdw, there is support for read-only pages in the PPGTT. + * + * XXX GVT is not honouring the lack of RW in the PTE bits. + */ + ppgtt->base.has_read_only = !intel_vgpu_active(dev_priv); + /* There are only few exceptions for gen >=6. chv and bxt. * And we are not sure about the latter so play safe for now. */ @@ -2078,7 +2090,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm, gen8_pte_t __iomem *pte = (gen8_pte_t __iomem *)ggtt->gsm + (offset >> PAGE_SHIFT); - gen8_set_pte(pte, gen8_pte_encode(addr, level)); + gen8_set_pte(pte, gen8_pte_encode(addr, level, 0)); ggtt->invalidate(vm->i915); } @@ -2086,14 +2098,19 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm, static void gen8_ggtt_insert_entries(struct i915_address_space *vm, struct i915_vma *vma, enum i915_cache_level level, - u32 unused) + u32 flags) { struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm); struct sgt_iter sgt_iter; gen8_pte_t __iomem *gtt_entries; - const gen8_pte_t pte_encode = gen8_pte_encode(0, level); + const gen8_pte_t pte_encode = gen8_pte_encode(0, level, 0); dma_addr_t addr; + /* + * Note that we ignore PTE_READ_ONLY here. The caller must be careful + * not to allow the user to override access to a read only page. + */ + gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm; gtt_entries += vma->node.start >> PAGE_SHIFT; for_each_sgt_dma(addr, sgt_iter, vma->pages) @@ -2162,7 +2179,7 @@ static void gen8_ggtt_clear_range(struct i915_address_space *vm, unsigned first_entry = start >> PAGE_SHIFT; unsigned num_entries = length >> PAGE_SHIFT; const gen8_pte_t scratch_pte = - gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC); + gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0); gen8_pte_t __iomem *gtt_base = (gen8_pte_t __iomem *)ggtt->gsm + first_entry; const int max_entries = ggtt_total_entries(ggtt) - first_entry; @@ -2223,13 +2240,14 @@ struct insert_entries { struct i915_address_space *vm; struct i915_vma *vma; enum i915_cache_level level; + u32 flags; }; static int bxt_vtd_ggtt_insert_entries__cb(void *_arg) { struct insert_entries *arg = _arg; - gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, 0); + gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, arg->flags); bxt_vtd_ggtt_wa(arg->vm); return 0; @@ -2238,9 +2256,9 @@ static int bxt_vtd_ggtt_insert_entries__cb(void *_arg) static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm, struct i915_vma *vma, enum i915_cache_level level, - u32 unused) + u32 flags) { - struct insert_entries arg = { vm, vma, level }; + struct insert_entries arg = { vm, vma, level, flags }; stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL); } @@ -2337,9 +2355,9 @@ static int ggtt_bind_vma(struct i915_vma *vma, return ret; } - /* Currently applicable only to VLV */ + /* Applicable to VLV (gen8+ do not support RO in the GGTT) */ pte_flags = 0; - if (obj->gt_ro) + if (i915_gem_object_is_readonly(obj)) pte_flags |= PTE_READ_ONLY; intel_runtime_pm_get(i915); @@ -2381,7 +2399,7 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma, /* Currently applicable only to VLV */ pte_flags = 0; - if (vma->obj->gt_ro) + if (i915_gem_object_is_readonly(vma->obj)) pte_flags |= PTE_READ_ONLY; if (flags & I915_VMA_LOCAL_BIND) { @@ -3063,6 +3081,10 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv) */ mutex_lock(&dev_priv->drm.struct_mutex); i915_address_space_init(&ggtt->base, dev_priv, "[global]"); + + /* Only VLV supports read-only GGTT mappings */ + ggtt->base.has_read_only = IS_VALLEYVIEW(dev_priv); + if (!HAS_LLC(dev_priv) && !USES_PPGTT(dev_priv)) ggtt->base.mm.color_adjust = i915_gtt_color_adjust; mutex_unlock(&dev_priv->drm.struct_mutex); @@ -3095,7 +3117,6 @@ int i915_ggtt_enable_hw(struct drm_i915_private *dev_priv) { if (INTEL_GEN(dev_priv) < 6 && !intel_enable_gtt()) return -EIO; - return 0; } diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index 0dbbe840f5f0..4b63d6cbd81e 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -295,7 +295,12 @@ struct i915_address_space { struct list_head unbound_list; struct pagevec free_pages; - bool pt_kmap_wc; + + /* Some systems require uncached updates of the page directories */ + bool pt_kmap_wc:1; + + /* Some systems support read-only mappings for GGTT and/or PPGTT */ + bool has_read_only:1; /* FIXME: Need a more generic return type */ gen6_pte_t (*pte_encode)(dma_addr_t addr, diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h index c30d8f808185..39cfe04dcdb8 100644 --- a/drivers/gpu/drm/i915/i915_gem_object.h +++ b/drivers/gpu/drm/i915/i915_gem_object.h @@ -140,7 +140,6 @@ struct drm_i915_gem_object { * Is the object to be mapped as read-only to the GPU * Only honoured if hardware has relevant pte bit */ - unsigned long gt_ro:1; unsigned int cache_level:3; unsigned int cache_coherent:2; #define I915_BO_CACHE_COHERENT_FOR_READ BIT(0) @@ -313,6 +312,18 @@ static inline void i915_gem_object_unlock(struct drm_i915_gem_object *obj) reservation_object_unlock(obj->resv); } +static inline void +i915_gem_object_set_readonly(struct drm_i915_gem_object *obj) +{ + obj->base.vma_node.readonly = true; +} + +static inline bool +i915_gem_object_is_readonly(const struct drm_i915_gem_object *obj) +{ + return obj->base.vma_node.readonly; +} + static inline bool i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj) { diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c index 813a3b546d6e..1d556dcbd656 100644 --- a/drivers/gpu/drm/i915/i915_gem_request.c +++ b/drivers/gpu/drm/i915/i915_gem_request.c @@ -252,6 +252,10 @@ static void mark_busy(struct drm_i915_private *i915) GEM_BUG_ON(!i915->gt.active_requests); intel_runtime_pm_get_noresume(i915); + + if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) + intel_uncore_forcewake_get(i915, FORCEWAKE_ALL); + i915->gt.awake = true; intel_enable_gt_powersave(i915); diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c index 05ae8c4a8a1b..480d20758324 100644 --- a/drivers/gpu/drm/i915/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -690,8 +690,28 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj, i915_gem_gtt_finish_pages(obj, pages); for_each_sgt_page(page, sgt_iter, pages) { - if (obj->mm.dirty) + if (obj->mm.dirty && trylock_page(page)) { + /* + * As this may not be anonymous memory (e.g. shmem) + * but exist on a real mapping, we have to lock + * the page in order to dirty it -- holding + * the page reference is not sufficient to + * prevent the inode from being truncated. + * Play safe and take the lock. + * + * However...! + * + * The mmu-notifier can be invalidated for a + * migrate_page, that is alreadying holding the lock + * on the page. Such a try_to_unmap() will result + * in us calling put_pages() and so recursively try + * to lock the page. We avoid that deadlock with + * a trylock_page() and in exchange we risk missing + * some page dirtying. + */ set_page_dirty(page); + unlock_page(page); + } mark_page_accessed(page); put_page(page); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 2e706f1abe64..1db70350af0b 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -358,6 +358,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN8_CONFIG0 _MMIO(0xD00) #define GEN9_DEFAULT_FIXES (1 << 3 | 1 << 2 | 1 << 1) +#define GEN8_RC6_CTX_INFO _MMIO(0x8504) + #define GAC_ECO_BITS _MMIO(0x14090) #define ECOBITS_SNB_BIT (1<<13) #define ECOBITS_PPGTT_CACHE64B (3<<8) @@ -703,6 +705,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) */ #define BCS_SWCTRL _MMIO(0x22200) +/* There are 16 GPR registers */ +#define BCS_GPR(n) _MMIO(0x22600 + (n) * 8) +#define BCS_GPR_UDW(n) _MMIO(0x22600 + (n) * 8 + 4) + #define GPGPU_THREADS_DISPATCHED _MMIO(0x2290) #define GPGPU_THREADS_DISPATCHED_UDW _MMIO(0x2290 + 4) #define HS_INVOCATION_COUNT _MMIO(0x2300) @@ -6722,6 +6728,10 @@ enum { #define SKL_CSR_DC5_DC6_COUNT _MMIO(0x8002C) #define BXT_CSR_DC3_DC5_COUNT _MMIO(0x80038) +/* Display Internal Timeout Register */ +#define RM_TIMEOUT _MMIO(0x42060) +#define MMIO_TIMEOUT_US(us) ((us) << 0) + /* interrupts */ #define DE_MASTER_IRQ_CONTROL (1 << 31) #define DE_SPRITEB_FLIP_DONE (1 << 29) diff --git a/drivers/gpu/drm/i915/i915_vgpu.c b/drivers/gpu/drm/i915/i915_vgpu.c index 5fe9f3f39467..e13ddd559f79 100644 --- a/drivers/gpu/drm/i915/i915_vgpu.c +++ b/drivers/gpu/drm/i915/i915_vgpu.c @@ -100,6 +100,9 @@ static struct _balloon_info_ bl_info; static void vgt_deballoon_space(struct i915_ggtt *ggtt, struct drm_mm_node *node) { + if (!drm_mm_node_allocated(node)) + return; + DRM_DEBUG_DRIVER("deballoon space: range [0x%llx - 0x%llx] %llu KiB.\n", node->start, node->start + node->size, diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 92c1f8e166dc..0bdbbd4027fe 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -277,10 +277,17 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv, uint32_t i; uint32_t *dmc_payload; uint32_t required_version; + size_t fsize; if (!fw) return NULL; + fsize = sizeof(struct intel_css_header) + + sizeof(struct intel_package_header) + + sizeof(struct intel_dmc_header); + if (fsize > fw->size) + goto error_truncated; + /* Extract CSS Header information*/ css_header = (struct intel_css_header *)fw->data; if (sizeof(struct intel_css_header) != @@ -350,6 +357,9 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv, return NULL; } readcount += dmc_offset; + fsize += dmc_offset; + if (fsize > fw->size) + goto error_truncated; /* Extract dmc_header information. */ dmc_header = (struct intel_dmc_header *)&fw->data[readcount]; @@ -380,6 +390,10 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv, /* fw_size is in dwords, so multiplied by 4 to convert into bytes. */ nbytes = dmc_header->fw_size * 4; + fsize += nbytes; + if (fsize > fw->size) + goto error_truncated; + if (nbytes > CSR_MAX_FW_SIZE) { DRM_ERROR("CSR firmware too big (%u) bytes\n", nbytes); return NULL; @@ -393,6 +407,10 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv, } return memcpy(dmc_payload, &fw->data[readcount], nbytes); + +error_truncated: + DRM_ERROR("Truncated DMC firmware, rejecting.\n"); + return NULL; } static void csr_load_work_fn(struct work_struct *work) diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 3adb9c3b412e..cba10cdab2a9 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1838,6 +1838,9 @@ void intel_enable_gt_powersave(struct drm_i915_private *dev_priv); void intel_autoenable_gt_powersave(struct drm_i915_private *dev_priv); void intel_disable_gt_powersave(struct drm_i915_private *dev_priv); void intel_suspend_gt_powersave(struct drm_i915_private *dev_priv); +bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915); +void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915); +void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915); void gen6_rps_busy(struct drm_i915_private *dev_priv); void gen6_rps_reset_ei(struct drm_i915_private *dev_priv); void gen6_rps_idle(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_dsi_pll.c b/drivers/gpu/drm/i915/intel_dsi_pll.c index 2ff2ee7f3b78..03c592753fc3 100644 --- a/drivers/gpu/drm/i915/intel_dsi_pll.c +++ b/drivers/gpu/drm/i915/intel_dsi_pll.c @@ -422,8 +422,8 @@ static void glk_dsi_program_esc_clock(struct drm_device *dev, else txesc2_div = 10; - I915_WRITE(MIPIO_TXESC_CLK_DIV1, txesc1_div & GLK_TX_ESC_CLK_DIV1_MASK); - I915_WRITE(MIPIO_TXESC_CLK_DIV2, txesc2_div & GLK_TX_ESC_CLK_DIV2_MASK); + I915_WRITE(MIPIO_TXESC_CLK_DIV1, (1 << (txesc1_div - 1)) & GLK_TX_ESC_CLK_DIV1_MASK); + I915_WRITE(MIPIO_TXESC_CLK_DIV2, (1 << (txesc2_div - 1)) & GLK_TX_ESC_CLK_DIV2_MASK); } /* Program BXT Mipi clocks and dividers */ diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index cb377b003321..674410682ccc 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -121,6 +121,14 @@ static void bxt_init_clock_gating(struct drm_i915_private *dev_priv) */ I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) | PWM1_GATING_DIS | PWM2_GATING_DIS); + + /* + * Lower the display internal timeout. + * This is needed to avoid any hard hangs when DSI port PLL + * is off and a MMIO access is attempted by any privilege + * application, using batch buffers or any other means. + */ + I915_WRITE(RM_TIMEOUT, MMIO_TIMEOUT_US(950)); } static void glk_init_clock_gating(struct drm_i915_private *dev_priv) @@ -6274,19 +6282,23 @@ static void gen9_disable_rps(struct drm_i915_private *dev_priv) I915_WRITE(GEN6_RP_CONTROL, 0); } -static void gen6_disable_rps(struct drm_i915_private *dev_priv) +static void gen6_disable_rc6(struct drm_i915_private *dev_priv) { I915_WRITE(GEN6_RC_CONTROL, 0); +} + +static void gen6_disable_rps(struct drm_i915_private *dev_priv) +{ I915_WRITE(GEN6_RPNSWREQ, 1 << 31); I915_WRITE(GEN6_RP_CONTROL, 0); } -static void cherryview_disable_rps(struct drm_i915_private *dev_priv) +static void cherryview_disable_rc6(struct drm_i915_private *dev_priv) { I915_WRITE(GEN6_RC_CONTROL, 0); } -static void valleyview_disable_rps(struct drm_i915_private *dev_priv) +static void valleyview_disable_rc6(struct drm_i915_private *dev_priv) { /* we're doing forcewake before Disabling RC6, * This what the BIOS expects when going into suspend */ @@ -6537,7 +6549,8 @@ static void gen9_enable_rc6(struct drm_i915_private *dev_priv) I915_WRITE(GEN9_RENDER_PG_IDLE_HYSTERESIS, 25); /* 3a: Enable RC6 */ - if (intel_enable_rc6() & INTEL_RC6_ENABLE) + if (!dev_priv->rps.ctx_corrupted && + intel_enable_rc6() & INTEL_RC6_ENABLE) rc6_mask = GEN6_RC_CTL_RC6_ENABLE; DRM_INFO("RC6 %s\n", onoff(rc6_mask & GEN6_RC_CTL_RC6_ENABLE)); I915_WRITE(GEN6_RC6_THRESHOLD, 37500); /* 37.5/125ms per EI */ @@ -6586,7 +6599,8 @@ static void gen8_enable_rps(struct drm_i915_private *dev_priv) I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */ /* 3: Enable RC6 */ - if (intel_enable_rc6() & INTEL_RC6_ENABLE) + if (!dev_priv->rps.ctx_corrupted && + intel_enable_rc6() & INTEL_RC6_ENABLE) rc6_mask = GEN6_RC_CTL_RC6_ENABLE; intel_print_rc6_info(dev_priv, rc6_mask); if (IS_BROADWELL(dev_priv)) @@ -7767,6 +7781,95 @@ static void intel_init_emon(struct drm_i915_private *dev_priv) dev_priv->ips.corr = (lcfuse & LCFUSE_HIV_MASK); } +static bool i915_rc6_ctx_corrupted(struct drm_i915_private *dev_priv) +{ + return !I915_READ(GEN8_RC6_CTX_INFO); +} + +static void i915_rc6_ctx_wa_init(struct drm_i915_private *i915) +{ + if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915)) + return; + + if (i915_rc6_ctx_corrupted(i915)) { + DRM_INFO("RC6 context corrupted, disabling runtime power management\n"); + i915->rps.ctx_corrupted = true; + intel_runtime_pm_get(i915); + } +} + +static void i915_rc6_ctx_wa_cleanup(struct drm_i915_private *i915) +{ + if (i915->rps.ctx_corrupted) { + intel_runtime_pm_put(i915); + i915->rps.ctx_corrupted = false; + } +} + +/** + * i915_rc6_ctx_wa_suspend - system suspend sequence for the RC6 CTX WA + * @i915: i915 device + * + * Perform any steps needed to clean up the RC6 CTX WA before system suspend. + */ +void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915) +{ + if (i915->rps.ctx_corrupted) + intel_runtime_pm_put(i915); +} + +/** + * i915_rc6_ctx_wa_resume - system resume sequence for the RC6 CTX WA + * @i915: i915 device + * + * Perform any steps needed to re-init the RC6 CTX WA after system resume. + */ +void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915) +{ + if (!i915->rps.ctx_corrupted) + return; + + if (i915_rc6_ctx_corrupted(i915)) { + intel_runtime_pm_get(i915); + return; + } + + DRM_INFO("RC6 context restored, re-enabling runtime power management\n"); + i915->rps.ctx_corrupted = false; +} + +static void intel_disable_rc6(struct drm_i915_private *dev_priv); + +/** + * i915_rc6_ctx_wa_check - check for a new RC6 CTX corruption + * @i915: i915 device + * + * Check if an RC6 CTX corruption has happened since the last check and if so + * disable RC6 and runtime power management. + * + * Return false if no context corruption has happened since the last call of + * this function, true otherwise. +*/ +bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915) +{ + if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915)) + return false; + + if (i915->rps.ctx_corrupted) + return false; + + if (!i915_rc6_ctx_corrupted(i915)) + return false; + + DRM_NOTE("RC6 context corruption, disabling runtime power management\n"); + + intel_disable_rc6(i915); + i915->rps.ctx_corrupted = true; + intel_runtime_pm_get_noresume(i915); + + return true; +} + void intel_init_gt_powersave(struct drm_i915_private *dev_priv) { /* @@ -7781,6 +7884,8 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv) mutex_lock(&dev_priv->drm.struct_mutex); mutex_lock(&dev_priv->rps.hw_lock); + i915_rc6_ctx_wa_init(dev_priv); + /* Initialize RPS limits (for userspace) */ if (IS_CHERRYVIEW(dev_priv)) cherryview_init_gt_powersave(dev_priv); @@ -7830,6 +7935,8 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv) if (IS_VALLEYVIEW(dev_priv)) valleyview_cleanup_gt_powersave(dev_priv); + i915_rc6_ctx_wa_cleanup(dev_priv); + if (!i915.enable_rc6) intel_runtime_pm_put(dev_priv); } @@ -7861,27 +7968,47 @@ void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv) gen6_reset_rps_interrupts(dev_priv); } -void intel_disable_gt_powersave(struct drm_i915_private *dev_priv) +static void __intel_disable_rc6(struct drm_i915_private *dev_priv) { - if (!READ_ONCE(dev_priv->rps.enabled)) - return; + if (INTEL_GEN(dev_priv) >= 9) + gen9_disable_rc6(dev_priv); + else if (IS_CHERRYVIEW(dev_priv)) + cherryview_disable_rc6(dev_priv); + else if (IS_VALLEYVIEW(dev_priv)) + valleyview_disable_rc6(dev_priv); + else if (INTEL_GEN(dev_priv) >= 6) + gen6_disable_rc6(dev_priv); +} +static void intel_disable_rc6(struct drm_i915_private *dev_priv) +{ mutex_lock(&dev_priv->rps.hw_lock); + __intel_disable_rc6(dev_priv); + mutex_unlock(&dev_priv->rps.hw_lock); +} - if (INTEL_GEN(dev_priv) >= 9) { - gen9_disable_rc6(dev_priv); +static void intel_disable_rps(struct drm_i915_private *dev_priv) +{ + if (INTEL_GEN(dev_priv) >= 9) gen9_disable_rps(dev_priv); - } else if (IS_CHERRYVIEW(dev_priv)) { - cherryview_disable_rps(dev_priv); - } else if (IS_VALLEYVIEW(dev_priv)) { - valleyview_disable_rps(dev_priv); - } else if (INTEL_GEN(dev_priv) >= 6) { + else if (INTEL_GEN(dev_priv) >= 6) gen6_disable_rps(dev_priv); - } else if (IS_IRONLAKE_M(dev_priv)) { + else if (IS_IRONLAKE_M(dev_priv)) ironlake_disable_drps(dev_priv); - } +} + +void intel_disable_gt_powersave(struct drm_i915_private *dev_priv) +{ + if (!READ_ONCE(dev_priv->rps.enabled)) + return; + + mutex_lock(&dev_priv->rps.hw_lock); + + __intel_disable_rc6(dev_priv); + intel_disable_rps(dev_priv); dev_priv->rps.enabled = false; + mutex_unlock(&dev_priv->rps.hw_lock); } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index cdf084ef5aae..63667a5c2c87 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -1358,6 +1358,7 @@ void intel_ring_unpin(struct intel_ring *ring) static struct i915_vma * intel_ring_create_vma(struct drm_i915_private *dev_priv, int size) { + struct i915_address_space *vm = &dev_priv->ggtt.base; struct drm_i915_gem_object *obj; struct i915_vma *vma; @@ -1367,10 +1368,14 @@ intel_ring_create_vma(struct drm_i915_private *dev_priv, int size) if (IS_ERR(obj)) return ERR_CAST(obj); - /* mark ring buffers as read-only from GPU side by default */ - obj->gt_ro = 1; + /* + * Mark ring buffers as read-only from GPU side (so no stray overwrites) + * if supported by the platform's GGTT. + */ + if (vm->has_read_only) + i915_gem_object_set_readonly(obj); - vma = i915_vma_instance(obj, &dev_priv->ggtt.base, NULL); + vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(vma)) goto err; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 6b2067f10824..774e3772d0ed 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -417,7 +417,9 @@ struct intel_engine_cs { struct intel_engine_hangcheck hangcheck; - bool needs_cmd_parser; +#define I915_ENGINE_USING_CMD_PARSER BIT(0) +#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(3) + unsigned int flags; /* * Table of commands the command parser needs to know about @@ -444,6 +446,18 @@ struct intel_engine_cs { u32 (*get_cmd_length_mask)(u32 cmd_header); }; +static inline bool +intel_engine_using_cmd_parser(const struct intel_engine_cs *engine) +{ + return engine->flags & I915_ENGINE_USING_CMD_PARSER; +} + +static inline bool +intel_engine_requires_cmd_parser(const struct intel_engine_cs *engine) +{ + return engine->flags & I915_ENGINE_REQUIRES_CMD_PARSER; +} + static inline unsigned int intel_engine_flag(const struct intel_engine_cs *engine) { diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 29a3b0f5bec7..6d1bd11226c6 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -928,6 +928,13 @@ static bool intel_sdvo_set_colorimetry(struct intel_sdvo *intel_sdvo, return intel_sdvo_set_value(intel_sdvo, SDVO_CMD_SET_COLORIMETRY, &mode, 1); } +static bool intel_sdvo_set_audio_state(struct intel_sdvo *intel_sdvo, + u8 audio_state) +{ + return intel_sdvo_set_value(intel_sdvo, SDVO_CMD_SET_AUDIO_STAT, + &audio_state, 1); +} + #if 0 static void intel_sdvo_dump_hdmi_buf(struct intel_sdvo *intel_sdvo) { @@ -1359,11 +1366,6 @@ static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder, else sdvox |= SDVO_PIPE_SEL(crtc->pipe); - if (crtc_state->has_audio) { - WARN_ON_ONCE(INTEL_GEN(dev_priv) < 4); - sdvox |= SDVO_AUDIO_ENABLE; - } - if (INTEL_GEN(dev_priv) >= 4) { /* done in crtc_mode_set as the dpll_md reg must be written early */ } else if (IS_I945G(dev_priv) || IS_I945GM(dev_priv) || @@ -1492,8 +1494,13 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder, if (sdvox & HDMI_COLOR_RANGE_16_235) pipe_config->limited_color_range = true; - if (sdvox & SDVO_AUDIO_ENABLE) - pipe_config->has_audio = true; + if (intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_AUDIO_STAT, + &val, 1)) { + u8 mask = SDVO_AUDIO_ELD_VALID | SDVO_AUDIO_PRESENCE_DETECT; + + if ((val & mask) == mask) + pipe_config->has_audio = true; + } if (intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_ENCODE, &val, 1)) { @@ -1506,6 +1513,32 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder, pipe_config->pixel_multiplier, encoder_pixel_multiplier); } +static void intel_sdvo_disable_audio(struct intel_sdvo *intel_sdvo) +{ + intel_sdvo_set_audio_state(intel_sdvo, 0); +} + +static void intel_sdvo_enable_audio(struct intel_sdvo *intel_sdvo, + const struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state) +{ + const struct drm_display_mode *adjusted_mode = + &crtc_state->base.adjusted_mode; + struct drm_connector *connector = conn_state->connector; + u8 *eld = connector->eld; + + eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2; + + intel_sdvo_set_audio_state(intel_sdvo, 0); + + intel_sdvo_write_infoframe(intel_sdvo, SDVO_HBUF_INDEX_ELD, + SDVO_HBUF_TX_DISABLED, + eld, drm_eld_size(eld)); + + intel_sdvo_set_audio_state(intel_sdvo, SDVO_AUDIO_ELD_VALID | + SDVO_AUDIO_PRESENCE_DETECT); +} + static void intel_disable_sdvo(struct intel_encoder *encoder, struct intel_crtc_state *old_crtc_state, struct drm_connector_state *conn_state) @@ -1515,6 +1548,9 @@ static void intel_disable_sdvo(struct intel_encoder *encoder, struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); u32 temp; + if (old_crtc_state->has_audio) + intel_sdvo_disable_audio(intel_sdvo); + intel_sdvo_set_active_outputs(intel_sdvo, 0); if (0) intel_sdvo_set_encoder_power_state(intel_sdvo, @@ -1598,6 +1634,9 @@ static void intel_enable_sdvo(struct intel_encoder *encoder, intel_sdvo_set_encoder_power_state(intel_sdvo, DRM_MODE_DPMS_ON); intel_sdvo_set_active_outputs(intel_sdvo, intel_sdvo->attached_output); + + if (pipe_config->has_audio) + intel_sdvo_enable_audio(intel_sdvo, pipe_config, conn_state); } static enum drm_mode_status @@ -2468,7 +2507,6 @@ static bool intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device) { struct drm_encoder *encoder = &intel_sdvo->base.base; - struct drm_i915_private *dev_priv = to_i915(encoder->dev); struct drm_connector *connector; struct intel_encoder *intel_encoder = to_intel_encoder(encoder); struct intel_connector *intel_connector; @@ -2504,9 +2542,7 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device) encoder->encoder_type = DRM_MODE_ENCODER_TMDS; connector->connector_type = DRM_MODE_CONNECTOR_DVID; - /* gen3 doesn't do the hdmi bits in the SDVO register */ - if (INTEL_GEN(dev_priv) >= 4 && - intel_sdvo_is_hdmi_connector(intel_sdvo, device)) { + if (intel_sdvo_is_hdmi_connector(intel_sdvo, device)) { connector->connector_type = DRM_MODE_CONNECTOR_HDMIA; intel_sdvo->is_hdmi = true; } diff --git a/drivers/gpu/drm/i915/intel_sdvo_regs.h b/drivers/gpu/drm/i915/intel_sdvo_regs.h index db0ed499268a..e9ba3b047f93 100644 --- a/drivers/gpu/drm/i915/intel_sdvo_regs.h +++ b/drivers/gpu/drm/i915/intel_sdvo_regs.h @@ -707,6 +707,9 @@ struct intel_sdvo_enhancements_arg { #define SDVO_CMD_GET_AUDIO_ENCRYPT_PREFER 0x90 #define SDVO_CMD_SET_AUDIO_STAT 0x91 #define SDVO_CMD_GET_AUDIO_STAT 0x92 + #define SDVO_AUDIO_ELD_VALID (1 << 0) + #define SDVO_AUDIO_PRESENCE_DETECT (1 << 1) + #define SDVO_AUDIO_CP_READY (1 << 2) #define SDVO_CMD_SET_HBUF_INDEX 0x93 #define SDVO_HBUF_INDEX_ELD 0 #define SDVO_HBUF_INDEX_AVI_IF 1 |