untrusted comment: verify with openbsd-66-base.pub RWSvK/c+cFe24AwHGsot6zZZCHIO+QLeZX4ZBpO7LUH9YYXYz1xdklMNqZ9gpKzNLtmu86rDGqY3U8tWyuZx+fk3EsBB3PYnWwk= OpenBSD 6.6 errata 007, November 22, 2019: A local user could cause the system to hang by reading specific registers when Intel Gen8/Gen9 graphics hardware is in a low power state. A local user could perform writes to memory that should be blocked with Intel Gen9 graphics hardware. Apply by doing: signify -Vep /etc/signify/openbsd-66-base.pub -x 007_inteldrm.patch.sig \ -m - | (cd /usr/src && patch -p0) And then rebuild and install a new kernel: KK=`sysctl -n kern.osversion | cut -d# -f1` cd /usr/src/sys/arch/`machine`/compile/$KK make obj make config make make install Index: sys/dev/pci/drm/i915/i915_cmd_parser.c =================================================================== RCS file: /cvs/src/sys/dev/pci/drm/i915/i915_cmd_parser.c,v retrieving revision 1.2 diff -u -p -r1.2 i915_cmd_parser.c --- sys/dev/pci/drm/i915/i915_cmd_parser.c 14 Apr 2019 10:14:51 -0000 1.2 +++ sys/dev/pci/drm/i915/i915_cmd_parser.c 20 Nov 2019 07:02:22 -0000 @@ -51,13 +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. @@ -82,9 +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. */ /* @@ -102,8 +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) @@ -111,7 +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. @@ -192,7 +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__ \ } @@ -207,14 +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 ), @@ -244,7 +238,7 @@ static const struct drm_i915_cmd_descrip 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 ), @@ -311,7 +305,7 @@ static const struct drm_i915_cmd_descrip 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 } ), @@ -328,7 +322,7 @@ static const struct drm_i915_cmd_descrip 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, @@ -372,7 +366,7 @@ static const struct drm_i915_cmd_descrip 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, @@ -410,7 +404,7 @@ static const struct drm_i915_cmd_descrip }}, ), }; -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 = {{ @@ -444,10 +438,64 @@ static const struct drm_i915_cmd_descrip }; 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); @@ -461,40 +509,44 @@ static const struct drm_i915_cmd_descrip #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. */ @@ -610,17 +662,27 @@ static const struct drm_i915_reg_descrip 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 @@ -629,28 +691,27 @@ static const struct drm_i915_reg_descrip 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) @@ -708,6 +769,17 @@ static u32 gen7_blt_get_cmd_length_mask( 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) @@ -865,18 +937,19 @@ void intel_engine_init_cmd_parser(struct 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)) { @@ -886,36 +959,46 @@ void intel_engine_init_cmd_parser(struct 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; @@ -941,7 +1024,7 @@ void intel_engine_init_cmd_parser(struct return; } - engine->flags |= I915_ENGINE_NEEDS_CMD_PARSER; + engine->flags |= I915_ENGINE_USING_CMD_PARSER; } /** @@ -953,7 +1036,7 @@ void intel_engine_init_cmd_parser(struct */ void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine) { - if (!intel_engine_needs_cmd_parser(engine)) + if (!intel_engine_using_cmd_parser(engine)) return; fini_hash_table(engine); @@ -1027,22 +1110,16 @@ __find_reg(const struct drm_i915_reg_des } 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; - for (; count > 0; ++table, --count) { - 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; - } - } + 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 */ @@ -1127,8 +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; @@ -1138,12 +1214,6 @@ static bool check_cmd(const struct intel 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 @@ -1157,7 +1227,7 @@ static bool check_cmd(const struct intel 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", @@ -1235,16 +1305,112 @@ static bool check_cmd(const struct intel 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 * 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 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 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 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 d /* If the command parser is not enabled, report 0 - unsupported */ for_each_engine(engine, dev_priv, id) { - if (intel_engine_needs_cmd_parser(engine)) { + if (intel_engine_using_cmd_parser(engine)) { active = true; break; } @@ -1382,6 +1558,7 @@ int i915_cmd_parser_get_version(struct d * 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; } Index: sys/dev/pci/drm/i915/i915_drv.c =================================================================== RCS file: /cvs/src/sys/dev/pci/drm/i915/i915_drv.c,v retrieving revision 1.122 diff -u -p -r1.122 i915_drv.c --- sys/dev/pci/drm/i915/i915_drv.c 7 Sep 2019 00:51:40 -0000 1.122 +++ sys/dev/pci/drm/i915/i915_drv.c 20 Nov 2019 07:02:22 -0000 @@ -369,7 +369,7 @@ static int i915_getparam_ioctl(struct dr value = HAS_LEGACY_SEMAPHORES(dev_priv); 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); @@ -1821,6 +1821,7 @@ static int i915_drm_suspend_late(struct i915_gem_suspend_late(dev_priv); intel_display_set_init_power(dev_priv, false); + i915_rc6_ctx_wa_suspend(dev_priv); intel_uncore_suspend(dev_priv); /* @@ -2048,6 +2049,8 @@ static int i915_drm_resume_early(struct intel_power_domains_init_hw(dev_priv, true); else intel_display_set_init_power(dev_priv, true); + + i915_rc6_ctx_wa_resume(dev_priv); intel_engines_sanitize(dev_priv); Index: sys/dev/pci/drm/i915/i915_drv.h =================================================================== RCS file: /cvs/src/sys/dev/pci/drm/i915/i915_drv.h,v retrieving revision 1.84 diff -u -p -r1.84 i915_drv.h --- sys/dev/pci/drm/i915/i915_drv.h 24 Aug 2019 01:43:12 -0000 1.84 +++ sys/dev/pci/drm/i915/i915_drv.h 20 Nov 2019 07:02:22 -0000 @@ -902,6 +902,7 @@ struct intel_rps { struct intel_rc6 { bool enabled; + bool ctx_corrupted; u64 prev_hw_residency[4]; u64 cur_residency[4]; }; @@ -2657,6 +2658,12 @@ intel_info(const struct drm_i915_private #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) @@ -2678,6 +2685,8 @@ intel_info(const struct drm_i915_private #define HAS_LEGACY_SEMAPHORES(dev_priv) IS_GEN7(dev_priv) +#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)) @@ -2710,10 +2719,12 @@ intel_info(const struct drm_i915_private /* 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,cnl */ #define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \ - (IS_CANNONLAKE(dev_priv) || \ - IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv)) + (IS_CANNONLAKE(dev_priv) || INTEL_GEN(dev_priv) == 9) #define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4) #define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \ @@ -3108,6 +3119,14 @@ i915_gem_object_ggtt_pin(struct drm_i915 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); @@ -3507,12 +3526,14 @@ const char *i915_cache_level_str(struct 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); Index: sys/dev/pci/drm/i915/i915_gem.c =================================================================== RCS file: /cvs/src/sys/dev/pci/drm/i915/i915_gem.c,v retrieving revision 1.122 diff -u -p -r1.122 i915_gem.c --- sys/dev/pci/drm/i915/i915_gem.c 16 Sep 2019 15:22:46 -0000 1.122 +++ sys/dev/pci/drm/i915/i915_gem.c 20 Nov 2019 07:02:22 -0000 @@ -174,6 +174,11 @@ static u32 __i915_gem_park(struct drm_i9 if (INTEL_GEN(i915) >= 6) gen6_rps_idle(i915); + if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) { + i915_rc6_ctx_wa_check(i915); + intel_uncore_forcewake_put(i915, FORCEWAKE_ALL); + } + intel_display_power_put(i915, POWER_DOMAIN_GT_IRQ); intel_runtime_pm_put(i915); @@ -220,6 +225,9 @@ void i915_gem_unpark(struct drm_i915_pri */ intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ); + if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) + intel_uncore_forcewake_get(i915, FORCEWAKE_ALL); + i915->gt.awake = true; if (unlikely(++i915->gt.epoch == 0)) /* keep 0 as invalid */ i915->gt.epoch = 1; @@ -4844,6 +4852,20 @@ i915_gem_object_ggtt_pin(struct drm_i915 { struct drm_i915_private *dev_priv = to_i915(obj->base.dev); struct i915_address_space *vm = &dev_priv->ggtt.vm; + + 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; @@ -4907,7 +4929,7 @@ i915_gem_object_ggtt_pin(struct drm_i915 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); Index: sys/dev/pci/drm/i915/i915_gem_context.c =================================================================== RCS file: /cvs/src/sys/dev/pci/drm/i915/i915_gem_context.c,v retrieving revision 1.16 diff -u -p -r1.16 i915_gem_context.c --- sys/dev/pci/drm/i915/i915_gem_context.c 14 Apr 2019 10:14:51 -0000 1.16 +++ sys/dev/pci/drm/i915/i915_gem_context.c 20 Nov 2019 07:02:22 -0000 @@ -128,6 +128,8 @@ static void i915_gem_context_free(struct i915_ppgtt_put(ctx->ppgtt); + kfree(ctx->jump_whitelist); + for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) { struct intel_context *ce = &ctx->__engine[n]; @@ -350,6 +352,9 @@ __create_hw_context(struct drm_i915_priv ctx->ggtt_offset_bias = dev_priv->guc.ggtt_pin_bias; else ctx->ggtt_offset_bias = I915_GTT_PAGE_SIZE; + + ctx->jump_whitelist = NULL; + ctx->jump_whitelist_cmds = 0; return ctx; Index: sys/dev/pci/drm/i915/i915_gem_context.h =================================================================== RCS file: /cvs/src/sys/dev/pci/drm/i915/i915_gem_context.h,v retrieving revision 1.1 diff -u -p -r1.1 i915_gem_context.h --- sys/dev/pci/drm/i915/i915_gem_context.h 14 Apr 2019 10:14:51 -0000 1.1 +++ sys/dev/pci/drm/i915/i915_gem_context.h 20 Nov 2019 07:02:22 -0000 @@ -187,6 +187,12 @@ 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) Index: sys/dev/pci/drm/i915/i915_gem_execbuffer.c =================================================================== RCS file: /cvs/src/sys/dev/pci/drm/i915/i915_gem_execbuffer.c,v retrieving revision 1.45 diff -u -p -r1.45 i915_gem_execbuffer.c --- sys/dev/pci/drm/i915/i915_gem_execbuffer.c 14 Apr 2019 10:14:51 -0000 1.45 +++ sys/dev/pci/drm/i915/i915_gem_execbuffer.c 20 Nov 2019 07:02:22 -0000 @@ -315,7 +315,9 @@ static inline u64 gen8_noncanonical_addr static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb) { - return intel_engine_needs_cmd_parser(eb->engine) && eb->batch_len; + 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) @@ -1923,10 +1925,38 @@ static int i915_reset_gen7_sol_offsets(s 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.vm; + } 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, @@ -1934,29 +1964,54 @@ static struct i915_vma *eb_parse(struct 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); @@ -2209,6 +2264,7 @@ i915_gem_do_execbuffer(struct drm_device struct drm_i915_gem_exec_object2 *exec, struct drm_syncobj **fences) { + struct drm_i915_private *i915 = to_i915(dev); struct i915_execbuffer eb; struct dma_fence *in_fence = NULL; struct sync_file *out_fence = NULL; @@ -2219,7 +2275,7 @@ i915_gem_do_execbuffer(struct drm_device BUILD_BUG_ON(__EXEC_OBJECT_INTERNAL_FLAGS & ~__EXEC_OBJECT_UNKNOWN_FLAGS); - eb.i915 = to_i915(dev); + eb.i915 = i915; eb.file = file; eb.args = args; if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC)) @@ -2241,8 +2297,15 @@ i915_gem_do_execbuffer(struct drm_device eb.batch_flags = 0; if (args->flags & I915_EXEC_SECURE) { + if (INTEL_GEN(i915) >= 11) + return -ENODEV; + + /* Return -EPERM to trigger fallback code on old binaries. */ + if (!HAS_SECURE_BATCHES(i915)) + return -EPERM; + if (!drm_is_current_master(file) || !capable(CAP_SYS_ADMIN)) - return -EPERM; + return -EPERM; eb.batch_flags |= I915_DISPATCH_SECURE; } @@ -2329,33 +2392,18 @@ i915_gem_do_execbuffer(struct drm_device goto err_vma; } + 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 Index: sys/dev/pci/drm/i915/i915_gem_gtt.c =================================================================== RCS file: /cvs/src/sys/dev/pci/drm/i915/i915_gem_gtt.c,v retrieving revision 1.17 diff -u -p -r1.17 i915_gem_gtt.c --- sys/dev/pci/drm/i915/i915_gem_gtt.c 14 Apr 2019 10:14:51 -0000 1.17 +++ sys/dev/pci/drm/i915/i915_gem_gtt.c 20 Nov 2019 07:02:22 -0000 @@ -158,7 +158,8 @@ int intel_sanitize_enable_ppgtt(struct d 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) Index: sys/dev/pci/drm/i915/i915_reg.h =================================================================== RCS file: /cvs/src/sys/dev/pci/drm/i915/i915_reg.h,v retrieving revision 1.17 diff -u -p -r1.17 i915_reg.h --- sys/dev/pci/drm/i915/i915_reg.h 16 Sep 2019 15:07:03 -0000 1.17 +++ sys/dev/pci/drm/i915/i915_reg.h 20 Nov 2019 07:02:22 -0000 @@ -387,6 +387,8 @@ static inline bool i915_mmio_reg_valid(i #define ECOCHK_PPGTT_WT_HSW (0x2 << 3) #define ECOCHK_PPGTT_WB_HSW (0x3 << 3) +#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) @@ -471,6 +473,10 @@ static inline bool i915_mmio_reg_valid(i */ #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) @@ -7004,6 +7010,10 @@ enum { #define SKL_CSR_DC3_DC5_COUNT _MMIO(0x80030) #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) Index: sys/dev/pci/drm/i915/intel_drv.h =================================================================== RCS file: /cvs/src/sys/dev/pci/drm/i915/intel_drv.h,v retrieving revision 1.12 diff -u -p -r1.12 intel_drv.h --- sys/dev/pci/drm/i915/intel_drv.h 14 Apr 2019 10:14:52 -0000 1.12 +++ sys/dev/pci/drm/i915/intel_drv.h 20 Nov 2019 07:02:22 -0000 @@ -2064,6 +2064,9 @@ void intel_sanitize_gt_powersave(struct void intel_enable_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); Index: sys/dev/pci/drm/i915/intel_pm.c =================================================================== RCS file: /cvs/src/sys/dev/pci/drm/i915/intel_pm.c,v retrieving revision 1.43 diff -u -p -r1.43 intel_pm.c --- sys/dev/pci/drm/i915/intel_pm.c 14 Apr 2019 10:14:52 -0000 1.43 +++ sys/dev/pci/drm/i915/intel_pm.c 20 Nov 2019 07:02:22 -0000 @@ -116,6 +116,14 @@ static void bxt_init_clock_gating(struct */ 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) @@ -8201,6 +8209,95 @@ static void intel_init_emon(struct drm_i 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->gt_pm.rc6.ctx_corrupted = true; + intel_runtime_pm_get(i915); + } +} + +static void i915_rc6_ctx_wa_cleanup(struct drm_i915_private *i915) +{ + if (i915->gt_pm.rc6.ctx_corrupted) { + intel_runtime_pm_put(i915); + i915->gt_pm.rc6.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->gt_pm.rc6.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->gt_pm.rc6.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->gt_pm.rc6.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->gt_pm.rc6.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->gt_pm.rc6.ctx_corrupted = true; + intel_runtime_pm_get_noresume(i915); + + return true; +} + void intel_init_gt_powersave(struct drm_i915_private *dev_priv) { struct intel_rps *rps = &dev_priv->gt_pm.rps; @@ -8216,6 +8313,8 @@ void intel_init_gt_powersave(struct drm_ mutex_lock(&dev_priv->pcu_lock); + i915_rc6_ctx_wa_init(dev_priv); + /* Initialize RPS limits (for userspace) */ if (IS_CHERRYVIEW(dev_priv)) cherryview_init_gt_powersave(dev_priv); @@ -8262,6 +8361,8 @@ void intel_cleanup_gt_powersave(struct d if (IS_VALLEYVIEW(dev_priv)) valleyview_cleanup_gt_powersave(dev_priv); + i915_rc6_ctx_wa_cleanup(dev_priv); + if (!HAS_RC6(dev_priv)) intel_runtime_pm_put(dev_priv); } @@ -8306,7 +8407,7 @@ static inline void intel_disable_llc_pst i915->gt_pm.llc_pstate.enabled = false; } -static void intel_disable_rc6(struct drm_i915_private *dev_priv) +static void __intel_disable_rc6(struct drm_i915_private *dev_priv) { lockdep_assert_held(&dev_priv->pcu_lock); @@ -8325,6 +8426,13 @@ static void intel_disable_rc6(struct drm dev_priv->gt_pm.rc6.enabled = false; } +static void intel_disable_rc6(struct drm_i915_private *dev_priv) +{ + mutex_lock(&dev_priv->pcu_lock); + __intel_disable_rc6(dev_priv); + mutex_unlock(&dev_priv->pcu_lock); +} + static void intel_disable_rps(struct drm_i915_private *dev_priv) { lockdep_assert_held(&dev_priv->pcu_lock); @@ -8350,7 +8458,7 @@ void intel_disable_gt_powersave(struct d { mutex_lock(&dev_priv->pcu_lock); - intel_disable_rc6(dev_priv); + __intel_disable_rc6(dev_priv); intel_disable_rps(dev_priv); if (HAS_LLC(dev_priv)) intel_disable_llc_pstate(dev_priv); @@ -8375,6 +8483,9 @@ static void intel_enable_rc6(struct drm_ lockdep_assert_held(&dev_priv->pcu_lock); if (dev_priv->gt_pm.rc6.enabled) + return; + + if (dev_priv->gt_pm.rc6.ctx_corrupted) return; if (IS_CHERRYVIEW(dev_priv)) Index: sys/dev/pci/drm/i915/intel_ringbuffer.h =================================================================== RCS file: /cvs/src/sys/dev/pci/drm/i915/intel_ringbuffer.h,v retrieving revision 1.9 diff -u -p -r1.9 intel_ringbuffer.h --- sys/dev/pci/drm/i915/intel_ringbuffer.h 14 Apr 2019 10:14:52 -0000 1.9 +++ sys/dev/pci/drm/i915/intel_ringbuffer.h 20 Nov 2019 07:02:22 -0000 @@ -590,9 +590,10 @@ struct intel_engine_cs { struct intel_engine_hangcheck hangcheck; -#define I915_ENGINE_NEEDS_CMD_PARSER BIT(0) -#define I915_ENGINE_SUPPORTS_STATS BIT(1) -#define I915_ENGINE_HAS_PREEMPTION BIT(2) +#define I915_ENGINE_USING_CMD_PARSER BIT(0) +#define I915_ENGINE_SUPPORTS_STATS BIT(1) +#define I915_ENGINE_HAS_PREEMPTION BIT(2) +#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(3) unsigned int flags; /* @@ -653,9 +654,15 @@ struct intel_engine_cs { }; static inline bool -intel_engine_needs_cmd_parser(const struct intel_engine_cs *engine) +intel_engine_using_cmd_parser(const struct intel_engine_cs *engine) { - return engine->flags & I915_ENGINE_NEEDS_CMD_PARSER; + 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 bool