drm/i915: Engine relative MMIO
PATCH 1/1 drm/i915: Engine relative MMIO
From: John Harrison <[email protected]>
With virtual engines, it is no longer possible to know which specific physical engine a given request will be executed on at the time that request is generated. This means that the request itself must be engine agnostic - any direct register writes must be relative to the engine and not absolute addresses.
The LRI command has support for engine relative addressing. However, the mechanism is not transparent to the driver. The scheme for Gen11 (MI_LRI_ADD_CS_MMIO_START) requires the LRI address to have no absolute engine base component. The hardware then adds on the correct engine offset at execution time.
Due to the non-trivial and differing schemes on different hardware, it is not possible to simply update the code that creates the LRI commands to set a remap flag and let the hardware get on with it. Instead, this patch adds function wrappers for generating the LRI command itself and then for constructing the correct address to use with the LRI.
v2: Fix build break in GVT. Remove flags parameter [review feedback from Chris W].
v3: Fix build break in selftest. Rebase to newer base tree and fix merge conflict.
v4: More rebasing. Rmoved relative addressing support from Gen7-9 only code paths [review feedback from Chris W].
v5: More rebasing (new 'gt' directory). Fix white space issue. Use COPY class rather than BCS0 id for checking against BCS engine.
--- drivers/gpu/drm/i915/gt/intel_engine.h | 4 + drivers/gpu/drm/i915/gt/intel_engine_cs.c | 11 +++ drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 6 +- drivers/gpu/drm/i915/gt/intel_lrc.c | 79 ++++++++++--------- drivers/gpu/drm/i915/gt/intel_lrc_reg.h | 4 +- drivers/gpu/drm/i915/gt/intel_mocs.c | 17 ++-- drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 45 +++++++++-- drivers/gpu/drm/i915/gt/intel_workarounds.c | 4 +- .../gpu/drm/i915/gt/selftest_workarounds.c | 9 ++- drivers/gpu/drm/i915/gvt/mmio_context.c | 16 +++- drivers/gpu/drm/i915/i915_cmd_parser.c | 4 +- drivers/gpu/drm/i915/i915_gem_context.c | 12 +-- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 +- drivers/gpu/drm/i915/i915_perf.c | 19 +++-- 14 files changed, 154 insertions(+), 79 deletions(-)
drivers/gpu/drm/i915/gt/intel_engine.h +4 -0
@@ -546,4 +546,8 @@ static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)#endif +bool i915_engine_has_relative_lri (const struct intel_engine_cs *engine); +u32 i915_get_lri_cmd (const struct intel_engine_cs *engine,u32 word_count); +u32 i915_get_lri_reg (const struct intel_engine_cs *engine,i915_reg_t reg); +#endif /* _INTEL_RINGBUFFER_H_ */
drivers/gpu/drm/i915/gt/intel_engine_cs.c +11 -0
@@ -253,6 +253,17 @@ static u32 __engine_mmio_base(struct drm_i915_private *i915,return bases[i].base; } +bool i915_engine_has_relative_lri (const struct intel_engine_cs *engine) +{ +if (INTEL_GEN (engine->i915) <11 ) +return false; + +if (engine->class ==COPY_ENGINE_CLASS ) +return false; + +return true; +} +static void __sprint_engine_name (char *name,const struct engine_info *info) { WARN_ON(snprintf(name, INTEL_ENGINE_CS_MAX_NAME, "%s%u",
drivers/gpu/drm/i915/gt/intel_gpu_commands.h +5 -1
@@ -123,9 +123,13 @@* simply ignores the register load under certain conditions. * - One can actually load arbitrary many arbitrary registers: Simply issue x * address/value pairs. Don't overdue it, though, x <= 2^4 must hold! +* - Newer hardware supports engine relative addresses but older hardware does +* not. So never call MI_LRI directly, always use the i915_get_lri_cmd() +* and i915_get_lri_reg() helper functions. */ -#define MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1) +#define __MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1)#define MI_LRI_FORCE_POSTED (1<<12) +#define MI_LRI_ADD_CS_MMIO_START_GEN11 (1<<19)#define MI_STORE_REGISTER_MEM MI_INSTR(0x24, 1)#define MI_STORE_REGISTER_MEM_GEN8 MI_INSTR(0x24, 2)#define MI_SRM_LRM_GLOBAL_GTT (1<<22)
drivers/gpu/drm/i915/gt/intel_lrc.c +43 -36
149 lines not on this page · raw message
drivers/gpu/drm/i915/gt/intel_lrc_reg.h +2 -2
@@ -39,10 +39,10 @@#define CTX_R_PWR_CLK_STATE 0x42#define CTX_END 0x44 -#define CTX_REG (reg_state, pos, reg, val) do { \ +#define CTX_REG (engine, reg_state, pos, reg, val) do { \ u32 *reg_state__ = (reg_state); \ const u32 pos__ = (pos); \ - (reg_state__)[(pos__) + 0] = i915_mmio_reg_offset(reg); \ + (reg_state__)[(pos__) + 0] = i915_get_lri_reg((engine), (reg)); \ (reg_state__)[(pos__) + 1] = (val); \ } while (0)
drivers/gpu/drm/i915/gt/intel_mocs.c +10 -7
@@ -324,9 +324,6 @@ static u32 get_entry_control(const struct drm_i915_mocs_table *table,/** * intel_mocs_init_engine() - emit the mocs control table * @engine: The engine for whom to emit the registers. -* -* This function simply emits a MI_LOAD_REGISTER_IMM command for the -* given table starting at the given address. */ void intel_mocs_init_engine (struct intel_engine_cs *engine) {
@@ -380,18 +377,20 @@ static int emit_mocs_control_table(struct i915_request *rq,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (table->n_entries); + *cs++ =i915_get_lri_cmd (rq->engine, table->n_entries);for (index =0 ; index < table->size; index++) {u32 value =get_entry_control (table, index); - *cs++ =i915_mmio_reg_offset (mocs_register (engine, index)); + *cs++ =i915_get_lri_reg (rq->engine, +mocs_register (engine, index)); *cs++ = value; }/* All remaining entries are also unused */ for (; index < table->n_entries; index++) { - *cs++ =i915_mmio_reg_offset (mocs_register (engine, index)); + *cs++ =i915_get_lri_reg (rq->engine, +mocs_register (engine, index)); *cs++ = unused_value; }
@@ -449,7 +448,11 @@ static int emit_mocs_l3cc_table(struct i915_request *rq,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (table->n_entries /2 ); +/* +* GEN9_LNCFCMOCS is not engine relative, therefore there is no +* need for relative addressing? +*/ + *cs++ =__MI_LOAD_REGISTER_IMM (table->n_entries /2 );for (i =0 ; i < table->size /2 ; i++) {u16 low =get_entry_l3cc (table,2 * i);
drivers/gpu/drm/i915/gt/intel_ringbuffer.c +37 -8
75 lines not on this page · raw message
drivers/gpu/drm/i915/gt/intel_workarounds.c +2 -2
@@ -625,9 +625,9 @@ int intel_engine_emit_ctx_wa(struct i915_request *rq)if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (wal->count); + *cs++ =i915_get_lri_cmd (rq->engine, wal->count);for (i =0 , wa = wal->list; i < wal->count; i++, wa++) { - *cs++ =i915_mmio_reg_offset (wa->reg); + *cs++ =i915_get_lri_reg (rq->engine, wa->reg); *cs++ = wa->val; } *cs++ =MI_NOOP ;
drivers/gpu/drm/i915/gt/selftest_workarounds.c +5 -4
@@ -442,6 +442,7 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,for (i =0 ; i < engine->whitelist.count; i++) {u32 reg =i915_mmio_reg_offset (engine->whitelist.list[i].reg); +u32 regLRI =i915_get_lri_reg (engine, engine->whitelist.list[i].reg);u64 addr = scratch->node.start;struct i915_request *rq;u32 srm, lrm, rsvd;
@@ -474,8 +475,8 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx, idx =1 ;for (v =0 ; v <ARRAY_SIZE (values); v++) {/* LRI garbage */ - *cs++ =MI_LOAD_REGISTER_IMM (1 ); - *cs++ = reg; + *cs++ =i915_get_lri_cmd (engine,1 ); + *cs++ = regLRI; *cs++ = values[v];/* SRM result */
@@ -487,8 +488,8 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx, }for (v =0 ; v <ARRAY_SIZE (values); v++) {/* LRI garbage */ - *cs++ =MI_LOAD_REGISTER_IMM (1 ); - *cs++ = reg; + *cs++ =i915_get_lri_cmd (engine,1 ); + *cs++ = regLRI; *cs++ = ~values[v];/* SRM result */
drivers/gpu/drm/i915/gvt/mmio_context.c +12 -4
@@ -200,14 +200,14 @@ restore_context_mmio_for_inhibit(struct intel_vgpu *vgpu,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (count); + *cs++ =i915_get_lri_cmd (req->engine, count);for (mmio = gvt->engine_mmio_list.mmio;i915_mmio_reg_valid (mmio->reg); mmio++) {if (mmio->ring_id != ring_id || !mmio->in_context)continue ; - *cs++ =i915_mmio_reg_offset (mmio->reg); + *cs++ =i915_get_lri_reg (req->engine, mmio->reg); *cs++ =vgpu_vreg_t (vgpu, mmio->reg) | (mmio->mask <<16 ); gvt_dbg_core("add lri reg pair 0x%x:0x%x in inhibit ctx, vgpu:%d, rind_id:%d\n",
@@ -235,7 +235,11 @@ restore_render_mocs_control_for_inhibit(struct intel_vgpu *vgpu,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (GEN9_MOCS_SIZE ); +/* +* GEN9_GFX_MOCS is not engine relative, therefore there is no +* need for relative addressing. +*/ + *cs++ =__MI_LOAD_REGISTER_IMM (GEN9_MOCS_SIZE );for (index =0 ; index <GEN9_MOCS_SIZE ; index++) { *cs++ =i915_mmio_reg_offset (GEN9_GFX_MOCS (index));
@@ -262,7 +266,11 @@ restore_render_mocs_l3cc_for_inhibit(struct intel_vgpu *vgpu,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (GEN9_MOCS_SIZE /2 ); +/* +* GEN9_LNCFCMOCS is not engine relative, therefore there is no +* need for relative addressing. +*/ + *cs++ =__MI_LOAD_REGISTER_IMM (GEN9_MOCS_SIZE /2 );for (index =0 ; index <GEN9_MOCS_SIZE /2 ; index++) { *cs++ =i915_mmio_reg_offset (GEN9_LNCFCMOCS (index));
drivers/gpu/drm/i915/i915_cmd_parser.c +2 -2
@@ -221,7 +221,7 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = {CMD (MI_SUSPEND_FLUSH ,SMI ,F ,1 ,S ),CMD (MI_SEMAPHORE_MBOX ,SMI , !F ,0xFF ,R ),CMD (MI_STORE_DWORD_INDEX ,SMI , !F ,0xFF ,R ), -CMD (MI_LOAD_REGISTER_IMM (1 ),SMI , !F ,0xFF ,W , +CMD (__MI_LOAD_REGISTER_IMM (1 ),SMI , !F ,0xFF ,W , .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 } ), CMD( MI_STORE_REGISTER_MEM, SMI, F, 3, W | B, .reg = { .offset = 1, .mask = 0x007FFFFC },
@@ -1183,7 +1183,7 @@ static bool check_cmd(const struct intel_engine_cs *engine,return false; } -if (desc->cmd.value ==MI_LOAD_REGISTER_IMM (1 ) && +if (desc->cmd.value ==__MI_LOAD_REGISTER_IMM (1 ) && (offset +2 > length || (cmd[offset +1 ] & reg->mask) != reg->value)) { DRM_DEBUG_DRIVER("CMD: Rejected LRI to masked register 0x%08X\n",
drivers/gpu/drm/i915/i915_gem_context.c +6 -6
@@ -1026,11 +1026,11 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (2 ); + *cs++ =i915_get_lri_cmd (engine,2 ); - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_UDW (base,0 )); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_UDW (base,0 )); *cs++ =upper_32_bits (pd_daddr); - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_LDW (base,0 )); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_LDW (base,0 )); *cs++ =lower_32_bits (pd_daddr); *cs++ =MI_NOOP ;
@@ -1040,13 +1040,13 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (2 *GEN8_3LVL_PDPES ); + *cs++ =i915_get_lri_cmd (engine,2 *GEN8_3LVL_PDPES );for (i =GEN8_3LVL_PDPES ; i--; ) {const dma_addr_t pd_daddr =i915_page_dir_dma_addr (ppgtt, i); - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_UDW (base, i)); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_UDW (base, i)); *cs++ =upper_32_bits (pd_daddr); - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_LDW (base, i)); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_LDW (base, i)); *cs++ =lower_32_bits (pd_daddr); } *cs++ =MI_NOOP ;
drivers/gpu/drm/i915/i915_gem_execbuffer.c +2 -1
@@ -1963,7 +1963,8 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq)if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (4 ); +/* Gen7 only so no need to support relative offsets */ + *cs++ =__MI_LOAD_REGISTER_IMM (4 );for (i =0 ; i <4 ; i++) { *cs++ =i915_mmio_reg_offset (GEN7_SO_WRITE_OFFSET (i)); *cs++ =0 ;
drivers/gpu/drm/i915/i915_perf.c +13 -6
@@ -1636,7 +1636,8 @@ static void hsw_disable_metric_set(struct drm_i915_private *dev_priv)* in the case that the OA unit has been disabled. */ static void -gen8_update_reg_state_unlocked (struct intel_context *ce, +gen8_update_reg_state_unlocked (struct intel_engine_cs *engine, +struct intel_context *ce,u32 *reg_state,const struct i915_oa_config *oa_config) {
@@ -1655,7 +1656,12 @@ gen8_update_reg_state_unlocked(struct intel_context *ce, };int i; -CTX_REG (reg_state, ctx_oactxctrl,GEN8_OACTXCONTROL , +/* +* NB: The LRI instruction is generated by the hardware. +* Should we read it in and assert that the offset flag is set? +*/ + +CTX_REG (engine, reg_state, ctx_oactxctrl,GEN8_OACTXCONTROL , (i915->perf.oa.period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | (i915->perf.oa.periodic ?GEN8_OA_TIMER_ENABLE :0 ) |GEN8_OA_COUNTER_RESUME );
@@ -1682,10 +1688,10 @@ gen8_update_reg_state_unlocked(struct intel_context *ce, } } -CTX_REG (reg_state, state_offset, flex_regs[i], value); +CTX_REG (engine, reg_state, state_offset, flex_regs[i], value); } -CTX_REG (reg_state, +CTX_REG (engine, reg_state,CTX_R_PWR_CLK_STATE ,GEN8_R_PWR_CLK_STATE ,intel_sseu_make_rpcs (i915, &ce->sseu)); }
@@ -1770,7 +1776,7 @@ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv, ce->state->obj->mm.dirty = true; regs +=LRC_STATE_PN *PAGE_SIZE /sizeof (*regs); -gen8_update_reg_state_unlocked (ce, regs, oa_config); +gen8_update_reg_state_unlocked (dev_priv->engine[RCS0 ], ce, regs, oa_config);i915_gem_object_unpin_map (ce->state->obj); }
@@ -2166,7 +2172,8 @@ void i915_oa_init_reg_state(struct intel_engine_cs *engine, stream = engine->i915->perf.oa.exclusive_stream;if (stream) -gen8_update_reg_state_unlocked (ce, regs, stream->oa_config); +gen8_update_reg_state_unlocked (engine, ce, regs, + stream->oa_config); }/**
Signature · 6 lines
2.21.0.5.gaeb582a983 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Patchwork
CI✗ Fi.CI.BAT: failure for drm/i915: Engine relative MMIO (rev5)
== Series Details ==
== Series Details ==
Series: drm/i915: Engine relative MMIO (rev5)
URL : https://patchwork.freedesktop.org/series/57117/
State : failure
== Summary ==
CALL scripts/checksyscalls.sh
CALL scripts/atomic/check-atomics.sh
DESCEND objtool
CHK include/generated/compile.h
AR drivers/gpu/drm/i915/built-in.a
CC [M] drivers/gpu/drm/i915/header_test_i915_active_types.o
CC [M] drivers/gpu/drm/i915/header_test_i915_debugfs.o
CC [M] drivers/gpu/drm/i915/header_test_i915_drv.o
CC [M] drivers/gpu/drm/i915/header_test_i915_gem_context_types.o
CC [M] drivers/gpu/drm/i915/header_test_i915_gem_pm.o
CC [M] drivers/gpu/drm/i915/header_test_i915_irq.o
CC [M] drivers/gpu/drm/i915/header_test_i915_params.o
CC [M] drivers/gpu/drm/i915/header_test_i915_priolist_types.o
CC [M] drivers/gpu/drm/i915/header_test_i915_reg.o
CC [M] drivers/gpu/drm/i915/header_test_i915_scheduler_types.o
CC [M] drivers/gpu/drm/i915/header_test_i915_timeline_types.o
CC [M] drivers/gpu/drm/i915/header_test_i915_utils.o
CC [M] drivers/gpu/drm/i915/header_test_intel_acpi.o
CC [M] drivers/gpu/drm/i915/header_test_intel_atomic.o
CC [M] drivers/gpu/drm/i915/header_test_intel_atomic_plane.o
CC [M] drivers/gpu/drm/i915/header_test_intel_audio.o
CC [M] drivers/gpu/drm/i915/header_test_intel_bios.o
CC [M] drivers/gpu/drm/i915/header_test_intel_cdclk.o
CC [M] drivers/gpu/drm/i915/header_test_intel_color.o
CC [M] drivers/gpu/drm/i915/header_test_intel_combo_phy.o
CC [M] drivers/gpu/drm/i915/header_test_intel_connector.o
CC [M] drivers/gpu/drm/i915/header_test_intel_crt.o
CC [M] drivers/gpu/drm/i915/header_test_intel_csr.o
CC [M] drivers/gpu/drm/i915/header_test_intel_ddi.o
CC [M] drivers/gpu/drm/i915/header_test_intel_dp.o
CC [M] drivers/gpu/drm/i915/header_test_intel_dp_aux_backlight.o
CC [M] drivers/gpu/drm/i915/header_test_intel_dp_link_training.o
CC [M] drivers/gpu/drm/i915/header_test_intel_dp_mst.o
CC [M] drivers/gpu/drm/i915/header_test_intel_dpio_phy.o
CC [M] drivers/gpu/drm/i915/header_test_intel_dpll_mgr.o
CC [M] drivers/gpu/drm/i915/header_test_intel_drv.o
CC [M] drivers/gpu/drm/i915/header_test_intel_dsi.o
CC [M] drivers/gpu/drm/i915/header_test_intel_dsi_dcs_backlight.o
CC [M] drivers/gpu/drm/i915/header_test_intel_dvo.o
CC [M] drivers/gpu/drm/i915/header_test_intel_dvo_dev.o
CC [M] drivers/gpu/drm/i915/header_test_intel_fbc.o
CC [M] drivers/gpu/drm/i915/header_test_intel_fbdev.o
CC [M] drivers/gpu/drm/i915/header_test_intel_fifo_underrun.o
CC [M] drivers/gpu/drm/i915/header_test_intel_frontbuffer.o
CC [M] drivers/gpu/drm/i915/header_test_intel_gmbus.o
CC [M] drivers/gpu/drm/i915/header_test_intel_hdcp.o
CC [M] drivers/gpu/drm/i915/header_test_intel_hdmi.o
CC [M] drivers/gpu/drm/i915/header_test_intel_hotplug.o
CC [M] drivers/gpu/drm/i915/header_test_intel_lpe_audio.o
CC [M] drivers/gpu/drm/i915/header_test_intel_lspcon.o
CC [M] drivers/gpu/drm/i915/header_test_intel_lvds.o
CC [M] drivers/gpu/drm/i915/header_test_intel_overlay.o
CC [M] drivers/gpu/drm/i915/header_test_intel_panel.o
CC [M] drivers/gpu/drm/i915/header_test_intel_pipe_crc.o
CC [M] drivers/gpu/drm/i915/header_test_intel_pm.o
CC [M] drivers/gpu/drm/i915/header_test_intel_psr.o
CC [M] drivers/gpu/drm/i915/header_test_intel_quirks.o
CC [M] drivers/gpu/drm/i915/header_test_intel_sdvo.o
CC [M] drivers/gpu/drm/i915/header_test_intel_sideband.o
CC [M] drivers/gpu/drm/i915/header_test_intel_sprite.o
CC [M] drivers/gpu/drm/i915/header_test_intel_tv.o
CC [M] drivers/gpu/drm/i915/header_test_intel_uncore.o
CC [M] drivers/gpu/drm/i915/header_test_intel_vdsc.o
CC [M] drivers/gpu/drm/i915/header_test_intel_wakeref.o
CC [M] drivers/gpu/drm/i915/gt/intel_workarounds.o
In file included from drivers/gpu/drm/i915/gt/intel_workarounds.c:1401:0:
drivers/gpu/drm/i915/gt/selftest_workarounds.c: In function ‘scrub_whitelisted_registers’:
drivers/gpu/drm/i915/gt/selftest_workarounds.c:761:10: error: implicit declaration of function ‘MI_LOAD_REGISTER_IMM’; did you mean ‘__MI_LOAD_REGISTER_IMM’? [-Werror=implicit-function-declaration]
*cs++ = MI_LOAD_REGISTER_IMM(engine->whitelist.count);
^~~~~~~~~~~~~~~~~~~~
__MI_LOAD_REGISTER_IMMcc1: all warnings being treated as errorsscripts/Makefile.build:275: recipe for target 'drivers/gpu/drm/i915/gt/intel_workarounds.o' failed make[4]: *** [drivers/gpu/drm/i915/gt/intel_workarounds.o] Error 1 scripts/Makefile.build:486: recipe for target 'drivers/gpu/drm/i915' failed make[3]: *** [drivers/gpu/drm/i915] Error 2scripts/Makefile.build:486: recipe for target 'drivers/gpu/drm' failed
make[2]: *** [drivers/gpu/drm] Error 2scripts/Makefile.build:486: recipe for target 'drivers/gpu' failed
make[1]: *** [drivers/gpu] Error 2
Makefile:1051: recipe for target 'drivers' failed
make: *** [drivers] Error 2
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: ✗ Fi.CI.BAT: failure for drm/i915: Engine relative MMIO (rev5)
Doh. Ignore this patch. Forgot to actually squash the self-test fix down. Will repost the corrected patch.
John.
Quoted 79 lines · Patchwork
== Series Details ==
Series: drm/i915: Engine relative MMIO (rev5)
URL : https://patchwork.freedesktop.org/series/57117/
State : failure== Summary ==
CALL
scripts/checksyscalls.sh
CALLscripts/atomic/check-atomics.sh
DESCEND objtoolCHK include/generated/compile.h AR drivers/gpu/drm/i915/built-in.a CC [M] drivers/gpu/drm/i915/header_test_i915_active_types.o CC [M] drivers/gpu/drm/i915/header_test_i915_debugfs.o CC [M] drivers/gpu/drm/i915/header_test_i915_drv.o CC [M] drivers/gpu/drm/i915/header_test_i915_gem_context_types.o CC [M] drivers/gpu/drm/i915/header_test_i915_gem_pm.o CC [M] drivers/gpu/drm/i915/header_test_i915_irq.o CC [M] drivers/gpu/drm/i915/header_test_i915_params.o CC [M] drivers/gpu/drm/i915/header_test_i915_priolist_types.o CC [M] drivers/gpu/drm/i915/header_test_i915_reg.o CC [M] drivers/gpu/drm/i915/header_test_i915_scheduler_types.o CC [M] drivers/gpu/drm/i915/header_test_i915_timeline_types.o CC [M] drivers/gpu/drm/i915/header_test_i915_utils.o CC [M] drivers/gpu/drm/i915/header_test_intel_acpi.o CC [M] drivers/gpu/drm/i915/header_test_intel_atomic.o CC [M] drivers/gpu/drm/i915/header_test_intel_atomic_plane.o CC [M] drivers/gpu/drm/i915/header_test_intel_audio.o CC [M] drivers/gpu/drm/i915/header_test_intel_bios.o CC [M] drivers/gpu/drm/i915/header_test_intel_cdclk.o CC [M] drivers/gpu/drm/i915/header_test_intel_color.o CC [M] drivers/gpu/drm/i915/header_test_intel_combo_phy.o CC [M] drivers/gpu/drm/i915/header_test_intel_connector.o CC [M] drivers/gpu/drm/i915/header_test_intel_crt.o CC [M] drivers/gpu/drm/i915/header_test_intel_csr.o CC [M] drivers/gpu/drm/i915/header_test_intel_ddi.o CC [M] drivers/gpu/drm/i915/header_test_intel_dp.o CC [M] drivers/gpu/drm/i915/header_test_intel_dp_aux_backlight.o CC [M] drivers/gpu/drm/i915/header_test_intel_dp_link_training.o CC [M] drivers/gpu/drm/i915/header_test_intel_dp_mst.o CC [M] drivers/gpu/drm/i915/header_test_intel_dpio_phy.o CC [M] drivers/gpu/drm/i915/header_test_intel_dpll_mgr.o CC [M] drivers/gpu/drm/i915/header_test_intel_drv.o CC [M] drivers/gpu/drm/i915/header_test_intel_dsi.o CC [M] drivers/gpu/drm/i915/header_test_intel_dsi_dcs_backlight.o CC [M] drivers/gpu/drm/i915/header_test_intel_dvo.o CC [M] drivers/gpu/drm/i915/header_test_intel_dvo_dev.o CC [M] drivers/gpu/drm/i915/header_test_intel_fbc.o CC [M] drivers/gpu/drm/i915/header_test_intel_fbdev.o CC [M] drivers/gpu/drm/i915/header_test_intel_fifo_underrun.o CC [M] drivers/gpu/drm/i915/header_test_intel_frontbuffer.o CC [M] drivers/gpu/drm/i915/header_test_intel_gmbus.o CC [M] drivers/gpu/drm/i915/header_test_intel_hdcp.o CC [M] drivers/gpu/drm/i915/header_test_intel_hdmi.o CC [M] drivers/gpu/drm/i915/header_test_intel_hotplug.o CC [M] drivers/gpu/drm/i915/header_test_intel_lpe_audio.o CC [M] drivers/gpu/drm/i915/header_test_intel_lspcon.o CC [M] drivers/gpu/drm/i915/header_test_intel_lvds.o CC [M] drivers/gpu/drm/i915/header_test_intel_overlay.o CC [M] drivers/gpu/drm/i915/header_test_intel_panel.o CC [M] drivers/gpu/drm/i915/header_test_intel_pipe_crc.o CC [M] drivers/gpu/drm/i915/header_test_intel_pm.o CC [M] drivers/gpu/drm/i915/header_test_intel_psr.o CC [M] drivers/gpu/drm/i915/header_test_intel_quirks.o CC [M] drivers/gpu/drm/i915/header_test_intel_sdvo.o CC [M] drivers/gpu/drm/i915/header_test_intel_sideband.o CC [M] drivers/gpu/drm/i915/header_test_intel_sprite.o CC [M] drivers/gpu/drm/i915/header_test_intel_tv.o CC [M] drivers/gpu/drm/i915/header_test_intel_uncore.o CC [M] drivers/gpu/drm/i915/header_test_intel_vdsc.o CC [M] drivers/gpu/drm/i915/header_test_intel_wakeref.o CC [M] drivers/gpu/drm/i915/gt/intel_workarounds.o In file included from drivers/gpu/drm/i915/gt/intel_workarounds.c:1401:0: drivers/gpu/drm/i915/gt/selftest_workarounds.c: In function ‘scrub_whitelisted_registers’: drivers/gpu/drm/i915/gt/selftest_workarounds.c:761:10: error: implicit declaration of function ‘MI_LOAD_REGISTER_IMM’; did you mean ‘__MI_LOAD_REGISTER_IMM’? [-Werror=implicit-function-declaration] *cs++ = MI_LOAD_REGISTER_IMM(engine->whitelist.count); ^~~~~~~~~~~~~~~~~~~~ __MI_LOAD_REGISTER_IMM
Quoted 12 lines
cc1: all warnings being treated as errors
scripts/Makefile.build:275: recipe for target 'drivers/gpu/drm/i915/gt/intel_workarounds.o' failed make[4]: *** [drivers/gpu/drm/i915/gt/intel_workarounds.o] Error 1scripts/Makefile.build:486: recipe for target 'drivers/gpu/drm/i915' failed make[3]: *** [drivers/gpu/drm/i915] Error 2scripts/Makefile.build:486: recipe for target 'drivers/gpu/drm' failed
make[2]: *** [drivers/gpu/drm] Error 2scripts/Makefile.build:486: recipe for target 'drivers/gpu' failed
make[1]: *** [drivers/gpu] Error 2
Makefile:1051: recipe for target 'drivers' failed
make: *** [drivers] Error 2
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Quoted 74 lines · On 13/05/2019 20:45, [email protected] wrote:
From: John Harrison <[email protected]>
With virtual engines, it is no longer possible to know which specific physical engine a given request will be executed on at the time that request is generated. This means that the request itself must be engine agnostic - any direct register writes must be relative to the engine and not absolute addresses.
The LRI command has support for engine relative addressing. However, the mechanism is not transparent to the driver. The scheme for Gen11 (
MI_LRI_ADD_CS_MMIO_START) requires the LRI address to have no absolute engine base component. The hardware then adds on the correct engine offset at execution time.Due to the non-trivial and differing schemes on different hardware, it is not possible to simply update the code that creates the LRI commands to set a remap flag and let the hardware get on with it. Instead, this patch adds function wrappers for generating the LRI command itself and then for constructing the correct address to use with the LRI.
v2: Fix build break in GVT. Remove flags parameter [review feedback from Chris W].
v3: Fix build break in selftest. Rebase to newer base tree and fix merge conflict.
v4: More rebasing. Rmoved relative addressing support from Gen7-9 only code paths [review feedback from Chris W].
v5: More rebasing (new 'gt' directory). Fix white space issue. Use COPY class rather than BCS0 id for checking against BCS engine.
Signed-off-by John Harrison <[email protected]>CC Rodrigo Vivi <[email protected]>CC Tvrtko Ursulin <[email protected]>CC Wilson, Chris P <[email protected]>--- drivers/gpu/drm/i915/gt/intel_engine.h | 4 + drivers/gpu/drm/i915/gt/intel_engine_cs.c | 11 +++ drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 6 +- drivers/gpu/drm/i915/gt/intel_lrc.c | 79 ++++++++++--------- drivers/gpu/drm/i915/gt/intel_lrc_reg.h | 4 +- drivers/gpu/drm/i915/gt/intel_mocs.c | 17 ++-- drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 45 +++++++++-- drivers/gpu/drm/i915/gt/intel_workarounds.c | 4 +- .../gpu/drm/i915/gt/selftest_workarounds.c | 9 ++- drivers/gpu/drm/i915/gvt/mmio_context.c | 16 +++- drivers/gpu/drm/i915/i915_cmd_parser.c | 4 +- drivers/gpu/drm/i915/i915_gem_context.c | 12 +-- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 +- drivers/gpu/drm/i915/i915_perf.c | 19 +++-- 14 files changed, 154 insertions(+), 79 deletions(-)drivers/gpu/drm/i915/gt/intel_engine.h +4
-0@@ -546,4 +546,8 @@ static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)#endif +bool i915_engine_has_relative_lri (const struct intel_engine_cs *engine); +u32 i915_get_lri_cmd (const struct intel_engine_cs *engine,u32 word_count); +u32 i915_get_lri_reg (const struct intel_engine_cs *engine,i915_reg_t reg); +#endif /* _INTEL_RINGBUFFER_H_ */ drivers/gpu/drm/i915/gt/intel_engine_cs.c +0
-0@@ -253,6 +253,17 @@ static u32 __engine_mmio_base(struct drm_i915_private *i915,return bases[i].base; }
drivers/gpu/drm/i915/gt/intel_engine_cs.c static u32 __engine_mmio_base(struct drm_i915_private *i915, · line 264
Quoted 10 lines
drivers/gpu/drm/i915/gt/intel_engine_cs.c +9
-0+bool i915_engine_has_relative_lri (const struct intel_engine_cs *engine) +{ +if (INTEL_GEN (engine->i915) <11 ) +return false; + +if (engine->class ==COPY_ENGINE_CLASS ) +return false; + +return true;
I think engine->flags would be better. At least it is one conditional instead of two at runtime, even one too many for something that is invariant.
Quoted 10 lines
drivers/gpu/drm/i915/gt/intel_engine_cs.c +2
-0+} +static void __sprint_engine_name (char *name,const struct engine_info *info) { WARN_ON(snprintf(name, INTEL_ENGINE_CS_MAX_NAME, "%s%u",drivers/gpu/drm/i915/gt/intel_gpu_commands.h +0
-0
drivers/gpu/drm/i915/gt/intel_gpu_commands.h line 130
Quoted 9 lines
drivers/gpu/drm/i915/gt/intel_gpu_commands.h +4
-1@@ -123,9 +123,13 @@* simply ignores the register load under certain conditions. * - One can actually load arbitrary many arbitrary registers: Simply issue x * address/value pairs. Don't overdue it, though, x <= 2^4 must hold! +* - Newer hardware supports engine relative addresses but older hardware does +* not. So never call MI_LRI directly, always use the i915_get_lri_cmd() +* and i915_get_lri_reg() helper functions. */ -#define MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1) +#define __MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1)
So we end up with code using __MI_LOAD_REGISTER_IMM for absolute, and i915_get_lri_cmd for relative addressing. One is a macro, another is a function call, and naming/case is different.
How about we static inline it like:
static inline u32 MI_LOAD_REGISTER_IMM(struct intel_engine_cs *engine,
u32 count,
unsigned int flags)
#define MI_LRI_ABSOLUTE (0)
#define MI_LRI_RELATIVE (1)
{
u32 cmd = __MI_LOAD_REGISTER_IMM(count);
if ((flags & MI_LRI_RELATIVE) &&
(engine->flags & ...HAS_RELATIVE_LRI))
cmd |= ...;
return cmd;
}Then all call sites can use just this single helper and the naming remains familiar.
Register offset can use the same approach - again it is also small enough to be either static inline or a macro. Function calls for both seem excessive, but maybe it is just me.
Quoted 493 lines
drivers/gpu/drm/i915/gt/intel_gpu_commands.h +1
-0#define MI_LRI_FORCE_POSTED (1<<12) +#define MI_LRI_ADD_CS_MMIO_START_GEN11 (1<<19)#define MI_STORE_REGISTER_MEM MI_INSTR(0x24, 1)#define MI_STORE_REGISTER_MEM_GEN8 MI_INSTR(0x24, 2)#define MI_SRM_LRM_GLOBAL_GTT (1<<22)drivers/gpu/drm/i915/gt/intel_lrc.c +43
-36@@ -1388,14 +1388,15 @@ static int emit_pdps(struct i915_request *rq)return PTR_ERR (cs);/* Ensure the LRI have landed before we invalidate & continue */ - *cs++ =MI_LOAD_REGISTER_IMM (2 *GEN8_3LVL_PDPES ) |MI_LRI_FORCE_POSTED ; + *cs++ =i915_get_lri_cmd (engine,2 *GEN8_3LVL_PDPES ) | +MI_LRI_FORCE_POSTED ;for (i =GEN8_3LVL_PDPES ; i--; ) {const dma_addr_t pd_daddr =i915_page_dir_dma_addr (ppgtt, i);u32 base = engine->mmio_base; - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_UDW (base, i)); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_UDW (base, i)); *cs++ =upper_32_bits (pd_daddr); - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_LDW (base, i)); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_LDW (base, i)); *cs++ =lower_32_bits (pd_daddr); } *cs++ =MI_NOOP ;@@ -1469,7 +1470,8 @@ gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch) *batch++ =i915_scratch_offset (engine->i915) +256 ; *batch++ =0 ; - *batch++ =MI_LOAD_REGISTER_IMM (1 ); +/* Gen8/9 only so no need to support relative offsets */ + *batch++ =__MI_LOAD_REGISTER_IMM (1 ); *batch++ =i915_mmio_reg_offset (GEN8_L3SQCREG4 ); *batch++ =0x40400000 |GEN8_LQSC_FLUSH_COHERENT_LINES ;@@ -1540,13 +1542,14 @@ struct lri {u32 value; }; -static u32 *emit_lri (u32 *batch,const struct lri *lri,unsigned int count) +static u32 *emit_lri (struct intel_engine_cs *engine,u32 *batch, +const struct lri *lri,unsigned int count) {GEM_BUG_ON (!count || count >63 ); - *batch++ =MI_LOAD_REGISTER_IMM (count); + *batch++ =i915_get_lri_cmd (engine, count);do { - *batch++ =i915_mmio_reg_offset (lri->reg); + *batch++ =i915_get_lri_reg (engine, lri->reg); *batch++ = lri->value; }while (lri++, --count); *batch++ =MI_NOOP ;@@ -1584,7 +1587,7 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */ batch =gen8_emit_flush_coherentl3_wa (engine, batch); - batch =emit_lri (batch, lri,ARRAY_SIZE (lri)); + batch =emit_lri (engine, batch, lri,ARRAY_SIZE (lri));/* WaMediaPoolStateCmdInWABB:bxt,glk */ if (HAS_POOLED_EU (engine->i915)) {@@ -2537,10 +2540,10 @@ static void execlists_init_reg_state(u32 *regs,* values (including all the missing MI_LOAD_REGISTER_IMM commands that * we are not initializing here). */ - regs[CTX_LRI_HEADER_0 ] =MI_LOAD_REGISTER_IMM (rcs ?14 :11 ) | -MI_LRI_FORCE_POSTED ; + regs[CTX_LRI_HEADER_0 ] =i915_get_lri_cmd (engine, rcs ?14 :11 ) | +MI_LRI_FORCE_POSTED ; -CTX_REG (regs,CTX_CONTEXT_CONTROL ,RING_CONTEXT_CONTROL (base), +CTX_REG (engine, regs,CTX_CONTEXT_CONTROL ,RING_CONTEXT_CONTROL (base),_MASKED_BIT_DISABLE (CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT ) |_MASKED_BIT_ENABLE (CTX_CTRL_INHIBIT_SYN_CTX_SWITCH ));if (INTEL_GEN (engine->i915) <11 ) {@@ -2548,22 +2551,23 @@ static void execlists_init_reg_state(u32 *regs,_MASKED_BIT_DISABLE (CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT |CTX_CTRL_RS_CTX_ENABLE ); } -CTX_REG (regs,CTX_RING_HEAD ,RING_HEAD (base),0 ); -CTX_REG (regs,CTX_RING_TAIL ,RING_TAIL (base),0 ); -CTX_REG (regs,CTX_RING_BUFFER_START ,RING_START (base),0 ); -CTX_REG (regs,CTX_RING_BUFFER_CONTROL ,RING_CTL (base), +CTX_REG (engine, regs,CTX_RING_HEAD ,RING_HEAD (base),0 ); +CTX_REG (engine, regs,CTX_RING_TAIL ,RING_TAIL (base),0 ); +CTX_REG (engine, regs,CTX_RING_BUFFER_START ,RING_START (base),0 ); +CTX_REG (engine, regs,CTX_RING_BUFFER_CONTROL ,RING_CTL (base),RING_CTL_SIZE (ring->size) |RING_VALID ); -CTX_REG (regs,CTX_BB_HEAD_U ,RING_BBADDR_UDW (base),0 ); -CTX_REG (regs,CTX_BB_HEAD_L ,RING_BBADDR (base),0 ); -CTX_REG (regs,CTX_BB_STATE ,RING_BBSTATE (base),RING_BB_PPGTT ); -CTX_REG (regs,CTX_SECOND_BB_HEAD_U ,RING_SBBADDR_UDW (base),0 ); -CTX_REG (regs,CTX_SECOND_BB_HEAD_L ,RING_SBBADDR (base),0 ); -CTX_REG (regs,CTX_SECOND_BB_STATE ,RING_SBBSTATE (base),0 ); +CTX_REG (engine, regs,CTX_BB_HEAD_U ,RING_BBADDR_UDW (base),0 ); +CTX_REG (engine, regs,CTX_BB_HEAD_L ,RING_BBADDR (base),0 ); +CTX_REG (engine, regs,CTX_BB_STATE ,RING_BBSTATE (base),RING_BB_PPGTT ); +CTX_REG (engine, regs,CTX_SECOND_BB_HEAD_U ,RING_SBBADDR_UDW (base),0 ); +CTX_REG (engine, regs,CTX_SECOND_BB_HEAD_L ,RING_SBBADDR (base),0 ); +CTX_REG (engine, regs,CTX_SECOND_BB_STATE ,RING_SBBSTATE (base),0 );if (rcs) {struct i915_ctx_workarounds *wa_ctx = &engine->wa_ctx; -CTX_REG (regs,CTX_RCS_INDIRECT_CTX ,RING_INDIRECT_CTX (base),0 ); -CTX_REG (regs,CTX_RCS_INDIRECT_CTX_OFFSET , +CTX_REG (engine, regs,CTX_RCS_INDIRECT_CTX , +RING_INDIRECT_CTX (base),0 ); +CTX_REG (engine, regs,CTX_RCS_INDIRECT_CTX_OFFSET ,RING_INDIRECT_CTX_OFFSET (base),0 );if (wa_ctx->indirect_ctx.size) {u32 ggtt_offset =i915_ggtt_offset (wa_ctx->vma);@@ -2576,7 +2580,8 @@ static void execlists_init_reg_state(u32 *regs,intel_lr_indirect_ctx_offset (engine) <<6 ; } -CTX_REG (regs,CTX_BB_PER_CTX_PTR ,RING_BB_PER_CTX_PTR (base),0 ); +CTX_REG (engine, regs,CTX_BB_PER_CTX_PTR , +RING_BB_PER_CTX_PTR (base),0 );if (wa_ctx->per_ctx.size) {u32 ggtt_offset =i915_ggtt_offset (wa_ctx->vma);@@ -2585,18 +2590,19 @@ static void execlists_init_reg_state(u32 *regs, } } - regs[CTX_LRI_HEADER_1 ] =MI_LOAD_REGISTER_IMM (9 ) |MI_LRI_FORCE_POSTED ; + regs[CTX_LRI_HEADER_1 ] =i915_get_lri_cmd (engine,9 ) | +MI_LRI_FORCE_POSTED ; -CTX_REG (regs,CTX_CTX_TIMESTAMP ,RING_CTX_TIMESTAMP (base),0 ); +CTX_REG (engine, regs,CTX_CTX_TIMESTAMP ,RING_CTX_TIMESTAMP (base),0 );/* PDP values well be assigned later if needed */ -CTX_REG (regs,CTX_PDP3_UDW ,GEN8_RING_PDP_UDW (base,3 ),0 ); -CTX_REG (regs,CTX_PDP3_LDW ,GEN8_RING_PDP_LDW (base,3 ),0 ); -CTX_REG (regs,CTX_PDP2_UDW ,GEN8_RING_PDP_UDW (base,2 ),0 ); -CTX_REG (regs,CTX_PDP2_LDW ,GEN8_RING_PDP_LDW (base,2 ),0 ); -CTX_REG (regs,CTX_PDP1_UDW ,GEN8_RING_PDP_UDW (base,1 ),0 ); -CTX_REG (regs,CTX_PDP1_LDW ,GEN8_RING_PDP_LDW (base,1 ),0 ); -CTX_REG (regs,CTX_PDP0_UDW ,GEN8_RING_PDP_UDW (base,0 ),0 ); -CTX_REG (regs,CTX_PDP0_LDW ,GEN8_RING_PDP_LDW (base,0 ),0 ); +CTX_REG (engine, regs,CTX_PDP3_UDW ,GEN8_RING_PDP_UDW (base,3 ),0 ); +CTX_REG (engine, regs,CTX_PDP3_LDW ,GEN8_RING_PDP_LDW (base,3 ),0 ); +CTX_REG (engine, regs,CTX_PDP2_UDW ,GEN8_RING_PDP_UDW (base,2 ),0 ); +CTX_REG (engine, regs,CTX_PDP2_LDW ,GEN8_RING_PDP_LDW (base,2 ),0 ); +CTX_REG (engine, regs,CTX_PDP1_UDW ,GEN8_RING_PDP_UDW (base,1 ),0 ); +CTX_REG (engine, regs,CTX_PDP1_LDW ,GEN8_RING_PDP_LDW (base,1 ),0 ); +CTX_REG (engine, regs,CTX_PDP0_UDW ,GEN8_RING_PDP_UDW (base,0 ),0 ); +CTX_REG (engine, regs,CTX_PDP0_LDW ,GEN8_RING_PDP_LDW (base,0 ),0 );if (i915_vm_is_4lvl (&ppgtt->vm)) {/* 64b PPGTT (48bit canonical) @@ -2612,8 +2618,9 @@ static void execlists_init_reg_state(u32 *regs, }if (rcs) { - regs[CTX_LRI_HEADER_2 ] =MI_LOAD_REGISTER_IMM (1 ); -CTX_REG (regs,CTX_R_PWR_CLK_STATE ,GEN8_R_PWR_CLK_STATE ,0 ); + regs[CTX_LRI_HEADER_2 ] =i915_get_lri_cmd (engine,1 ); +CTX_REG (engine, regs,CTX_R_PWR_CLK_STATE , +GEN8_R_PWR_CLK_STATE ,0 );i915_oa_init_reg_state (engine, ce, regs); }drivers/gpu/drm/i915/gt/intel_lrc_reg.h +2
-2@@ -39,10 +39,10 @@#define CTX_R_PWR_CLK_STATE 0x42#define CTX_END 0x44 -#define CTX_REG (reg_state, pos, reg, val) do { \ +#define CTX_REG (engine, reg_state, pos, reg, val) do { \ u32 *reg_state__ = (reg_state); \ const u32 pos__ = (pos); \ - (reg_state__)[(pos__) + 0] = i915_mmio_reg_offset(reg); \ + (reg_state__)[(pos__) + 0] = i915_get_lri_reg((engine), (reg)); \ (reg_state__)[(pos__) + 1] = (val); \ } while (0)drivers/gpu/drm/i915/gt/intel_mocs.c +10
-7@@ -324,9 +324,6 @@ static u32 get_entry_control(const struct drm_i915_mocs_table *table,/** * intel_mocs_init_engine() - emit the mocs control table * @engine: The engine for whom to emit the registers. -* -* This function simply emits a MI_LOAD_REGISTER_IMM command for the -* given table starting at the given address. */ void intel_mocs_init_engine (struct intel_engine_cs *engine) {@@ -380,18 +377,20 @@ static int emit_mocs_control_table(struct i915_request *rq,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (table->n_entries); + *cs++ =i915_get_lri_cmd (rq->engine, table->n_entries);for (index =0 ; index < table->size; index++) {u32 value =get_entry_control (table, index); - *cs++ =i915_mmio_reg_offset (mocs_register (engine, index)); + *cs++ =i915_get_lri_reg (rq->engine, +mocs_register (engine, index)); *cs++ = value; }/* All remaining entries are also unused */ for (; index < table->n_entries; index++) { - *cs++ =i915_mmio_reg_offset (mocs_register (engine, index)); + *cs++ =i915_get_lri_reg (rq->engine, +mocs_register (engine, index)); *cs++ = unused_value; }@@ -449,7 +448,11 @@ static int emit_mocs_l3cc_table(struct i915_request *rq,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (table->n_entries /2 ); +/* +* GEN9_LNCFCMOCS is not engine relative, therefore there is no +* need for relative addressing? +*/ + *cs++ =__MI_LOAD_REGISTER_IMM (table->n_entries /2 );for (i =0 ; i < table->size /2 ; i++) {u16 low =get_entry_l3cc (table,2 * i);drivers/gpu/drm/i915/gt/intel_ringbuffer.c +37
-8@@ -1516,12 +1516,13 @@ static int load_pd_dir(struct i915_request *rq,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (1 ); - *cs++ =i915_mmio_reg_offset (RING_PP_DIR_DCLV (engine->mmio_base)); +/* Can these not be merged into a single LRI??? */ + *cs++ =i915_get_lri_cmd (engine,1 ); + *cs++ =i915_get_lri_reg (engine,RING_PP_DIR_DCLV (engine->mmio_base)); *cs++ =PP_DIR_DCLV_2G ; - *cs++ =MI_LOAD_REGISTER_IMM (1 ); - *cs++ =i915_mmio_reg_offset (RING_PP_DIR_BASE (engine->mmio_base)); + *cs++ =i915_get_lri_cmd (engine,1 ); + *cs++ =i915_get_lri_reg (engine,RING_PP_DIR_BASE (engine->mmio_base)); *cs++ = ppgtt->pd.base.ggtt_offset <<10 ;intel_ring_advance (rq, cs);@@ -1589,7 +1590,11 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)if (num_engines) {struct intel_engine_cs *signaller; - *cs++ =MI_LOAD_REGISTER_IMM (num_engines); +/* +* Must use absolute engine address as the register +* write is targeting a different engine. +*/ + *cs++ =__MI_LOAD_REGISTER_IMM (num_engines);for_each_engine (signaller, i915, id) {if (signaller == engine)continue ;@@ -1643,7 +1648,11 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)struct intel_engine_cs *signaller;i915_reg_t last_reg = {};/* keep gcc quiet */ - *cs++ =MI_LOAD_REGISTER_IMM (num_engines); +/* +* Must use absolute engine address as the register +* write is targeting a different engine. +*/ + *cs++ =__MI_LOAD_REGISTER_IMM (num_engines);for_each_engine (signaller, i915, id) {if (signaller == engine)continue ;@@ -1687,9 +1696,9 @@ static int remap_l3(struct i915_request *rq, int slice)* here because no other code should access these registers other than * at initialization time. */ - *cs++ =MI_LOAD_REGISTER_IMM (GEN7_L3LOG_SIZE /4 ); + *cs++ =i915_get_lri_cmd (rq->engine,GEN7_L3LOG_SIZE /4 );for (i =0 ; i <GEN7_L3LOG_SIZE /4 ; i++) { - *cs++ =i915_mmio_reg_offset (GEN7_L3LOG (slice, i)); + *cs++ =i915_get_lri_reg (rq->engine,GEN7_L3LOG (slice, i)); *cs++ = remap_info[i]; } *cs++ =MI_NOOP ;@@ -2335,3 +2344,23 @@ int intel_ring_submission_init(struct intel_engine_cs *engine)intel_engine_cleanup_common (engine);return err; } + +u32 i915_get_lri_cmd (const struct intel_engine_cs *engine,u32 word_count) +{ +u32 word; + + word =__MI_LOAD_REGISTER_IMM (word_count); + +if (i915_engine_has_relative_lri (engine)) + word |=MI_LRI_ADD_CS_MMIO_START_GEN11 ; + +return word; +} + +u32 i915_get_lri_reg (const struct intel_engine_cs *engine,i915_reg_t reg) +{ +if (!i915_engine_has_relative_lri (engine)) +return i915_mmio_reg_offset (reg); + +return i915_mmio_reg_offset (reg) - engine->mmio_base; +}drivers/gpu/drm/i915/gt/intel_workarounds.c +2
-2@@ -625,9 +625,9 @@ int intel_engine_emit_ctx_wa(struct i915_request *rq)if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (wal->count); + *cs++ =i915_get_lri_cmd (rq->engine, wal->count);for (i =0 , wa = wal->list; i < wal->count; i++, wa++) { - *cs++ =i915_mmio_reg_offset (wa->reg); + *cs++ =i915_get_lri_reg (rq->engine, wa->reg); *cs++ = wa->val; } *cs++ =MI_NOOP ;drivers/gpu/drm/i915/gt/selftest_workarounds.c +5
-4@@ -442,6 +442,7 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,for (i =0 ; i < engine->whitelist.count; i++) {u32 reg =i915_mmio_reg_offset (engine->whitelist.list[i].reg); +u32 regLRI =i915_get_lri_reg (engine, engine->whitelist.list[i].reg);u64 addr = scratch->node.start;struct i915_request *rq;u32 srm, lrm, rsvd;@@ -474,8 +475,8 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx, idx =1 ;for (v =0 ; v <ARRAY_SIZE (values); v++) {/* LRI garbage */ - *cs++ =MI_LOAD_REGISTER_IMM (1 ); - *cs++ = reg; + *cs++ =i915_get_lri_cmd (engine,1 ); + *cs++ = regLRI; *cs++ = values[v];/* SRM result */ @@ -487,8 +488,8 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx, }for (v =0 ; v <ARRAY_SIZE (values); v++) {/* LRI garbage */ - *cs++ =MI_LOAD_REGISTER_IMM (1 ); - *cs++ = reg; + *cs++ =i915_get_lri_cmd (engine,1 ); + *cs++ = regLRI; *cs++ = ~values[v];/* SRM result */ drivers/gpu/drm/i915/gvt/mmio_context.c +12
-4@@ -200,14 +200,14 @@ restore_context_mmio_for_inhibit(struct intel_vgpu *vgpu,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (count); + *cs++ =i915_get_lri_cmd (req->engine, count);for (mmio = gvt->engine_mmio_list.mmio;i915_mmio_reg_valid (mmio->reg); mmio++) {if (mmio->ring_id != ring_id || !mmio->in_context)continue ; - *cs++ =i915_mmio_reg_offset (mmio->reg); + *cs++ =i915_get_lri_reg (req->engine, mmio->reg); *cs++ =vgpu_vreg_t (vgpu, mmio->reg) | (mmio->mask <<16 ); gvt_dbg_core("add lri reg pair 0x%x:0x%x in inhibit ctx, vgpu:%d, rind_id:%d\n",@@ -235,7 +235,11 @@ restore_render_mocs_control_for_inhibit(struct intel_vgpu *vgpu,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (GEN9_MOCS_SIZE ); +/* +* GEN9_GFX_MOCS is not engine relative, therefore there is no +* need for relative addressing. +*/ + *cs++ =__MI_LOAD_REGISTER_IMM (GEN9_MOCS_SIZE );for (index =0 ; index <GEN9_MOCS_SIZE ; index++) { *cs++ =i915_mmio_reg_offset (GEN9_GFX_MOCS (index));@@ -262,7 +266,11 @@ restore_render_mocs_l3cc_for_inhibit(struct intel_vgpu *vgpu,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (GEN9_MOCS_SIZE /2 ); +/* +* GEN9_LNCFCMOCS is not engine relative, therefore there is no +* need for relative addressing. +*/ + *cs++ =__MI_LOAD_REGISTER_IMM (GEN9_MOCS_SIZE /2 );for (index =0 ; index <GEN9_MOCS_SIZE /2 ; index++) { *cs++ =i915_mmio_reg_offset (GEN9_LNCFCMOCS (index));drivers/gpu/drm/i915/i915_cmd_parser.c +2
-2@@ -221,7 +221,7 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = {CMD (MI_SUSPEND_FLUSH ,SMI ,F ,1 ,S ),CMD (MI_SEMAPHORE_MBOX ,SMI , !F ,0xFF ,R ),CMD (MI_STORE_DWORD_INDEX ,SMI , !F ,0xFF ,R ), -CMD (MI_LOAD_REGISTER_IMM (1 ),SMI , !F ,0xFF ,W , +CMD (__MI_LOAD_REGISTER_IMM (1 ),SMI , !F ,0xFF ,W , .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 } ), CMD( MI_STORE_REGISTER_MEM, SMI, F, 3, W | B, .reg = { .offset = 1, .mask = 0x007FFFFC },@@ -1183,7 +1183,7 @@ static bool check_cmd(const struct intel_engine_cs *engine,return false; } -if (desc->cmd.value ==MI_LOAD_REGISTER_IMM (1 ) && +if (desc->cmd.value ==__MI_LOAD_REGISTER_IMM (1 ) && (offset +2 > length || (cmd[offset +1 ] & reg->mask) != reg->value)) { DRM_DEBUG_DRIVER("CMD: Rejected LRI to masked register 0x%08X\n",drivers/gpu/drm/i915/i915_gem_context.c +6
-6@@ -1026,11 +1026,11 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (2 ); + *cs++ =i915_get_lri_cmd (engine,2 ); - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_UDW (base,0 )); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_UDW (base,0 )); *cs++ =upper_32_bits (pd_daddr); - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_LDW (base,0 )); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_LDW (base,0 )); *cs++ =lower_32_bits (pd_daddr); *cs++ =MI_NOOP ;@@ -1040,13 +1040,13 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (2 *GEN8_3LVL_PDPES ); + *cs++ =i915_get_lri_cmd (engine,2 *GEN8_3LVL_PDPES );for (i =GEN8_3LVL_PDPES ; i--; ) {const dma_addr_t pd_daddr =i915_page_dir_dma_addr (ppgtt, i); - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_UDW (base, i)); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_UDW (base, i)); *cs++ =upper_32_bits (pd_daddr); - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_LDW (base, i)); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_LDW (base, i)); *cs++ =lower_32_bits (pd_daddr); } *cs++ =MI_NOOP ;drivers/gpu/drm/i915/i915_gem_execbuffer.c +2
-1@@ -1963,7 +1963,8 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq)if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (4 ); +/* Gen7 only so no need to support relative offsets */ + *cs++ =__MI_LOAD_REGISTER_IMM (4 );for (i =0 ; i <4 ; i++) { *cs++ =i915_mmio_reg_offset (GEN7_SO_WRITE_OFFSET (i)); *cs++ =0 ;drivers/gpu/drm/i915/i915_perf.c +0
-0
drivers/gpu/drm/i915/i915_perf.c static void hsw_disable_metric_set(struct drm_i915_private *dev_priv) · line 1640
Quoted 6 lines
drivers/gpu/drm/i915/i915_perf.c +2
-1@@ -1636,7 +1636,8 @@ static void hsw_disable_metric_set(struct drm_i915_private *dev_priv)* in the case that the OA unit has been disabled. */ static void -gen8_update_reg_state_unlocked(struct intel_context *ce, +gen8_update_reg_state_unlocked(struct intel_engine_cs *engine, + struct intel_context *ce,
ce->engine?
Quoted 41 lines
drivers/gpu/drm/i915/i915_perf.c +9
-4u32 *reg_state, const struct i915_oa_config *oa_config) {@@ -1655,7 +1656,12 @@ gen8_update_reg_state_unlocked(struct intel_context *ce, };int i; -CTX_REG (reg_state, ctx_oactxctrl,GEN8_OACTXCONTROL , +/* +* NB: The LRI instruction is generated by the hardware. +* Should we read it in and assert that the offset flag is set? +*/ + +CTX_REG (engine, reg_state, ctx_oactxctrl,GEN8_OACTXCONTROL , (i915->perf.oa.period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | (i915->perf.oa.periodic ?GEN8_OA_TIMER_ENABLE :0 ) |GEN8_OA_COUNTER_RESUME );@@ -1682,10 +1688,10 @@ gen8_update_reg_state_unlocked(struct intel_context *ce, } } -CTX_REG (reg_state, state_offset, flex_regs[i], value); +CTX_REG (engine, reg_state, state_offset, flex_regs[i], value); } -CTX_REG (reg_state, +CTX_REG (engine, reg_state,CTX_R_PWR_CLK_STATE ,GEN8_R_PWR_CLK_STATE ,intel_sseu_make_rpcs (i915, &ce->sseu)); }@@ -1770,7 +1776,7 @@ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv, ce->state->obj->mm.dirty = true; regs +=LRC_STATE_PN *PAGE_SIZE /sizeof (*regs); -gen8_update_reg_state_unlocked (ce, regs, oa_config); +gen8_update_reg_state_unlocked (dev_priv->engine[RCS0 ], ce, regs, oa_config);i915_gem_object_unpin_map (ce->state->obj); }
drivers/gpu/drm/i915/i915_perf.c void i915_oa_init_reg_state(struct intel_engine_cs *engine, · line 2179
Quoted 9 lines
drivers/gpu/drm/i915/i915_perf.c +2
-1@@ -2166,7 +2172,8 @@ void i915_oa_init_reg_state(struct intel_engine_cs *engine, stream = engine->i915->perf.oa.exclusive_stream;if (stream) -gen8_update_reg_state_unlocked (ce, regs, stream->oa_config); +gen8_update_reg_state_unlocked (engine, ce, regs, + stream->oa_config); }/**
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Quoted 105 lines · Tvrtko Ursulin
Quoted 75 lines · On 13/05/2019 20:45, [email protected] wrote:
From: John Harrison <[email protected]>
With virtual engines, it is no longer possible to know which specific physical engine a given request will be executed on at the time that request is generated. This means that the request itself must be engine agnostic - any direct register writes must be relative to the engine and not absolute addresses.
The LRI command has support for engine relative addressing. However, the mechanism is not transparent to the driver. The scheme for Gen11 (
MI_LRI_ADD_CS_MMIO_START) requires the LRI address to have no absolute engine base component. The hardware then adds on the correct engine offset at execution time.Due to the non-trivial and differing schemes on different hardware, it is not possible to simply update the code that creates the LRI commands to set a remap flag and let the hardware get on with it. Instead, this patch adds function wrappers for generating the LRI command itself and then for constructing the correct address to use with the LRI.
v2: Fix build break in GVT. Remove flags parameter [review feedback from Chris W].
v3: Fix build break in selftest. Rebase to newer base tree and fix merge conflict.
v4: More rebasing. Rmoved relative addressing support from Gen7-9 only code paths [review feedback from Chris W].
v5: More rebasing (new 'gt' directory). Fix white space issue. Use COPY class rather than BCS0 id for checking against BCS engine.
Signed-off-by John Harrison <[email protected]>CC Rodrigo Vivi <[email protected]>CC Tvrtko Ursulin <[email protected]>CC Wilson, Chris P <[email protected]>---
drivers/gpu/drm/i915/gt/intel_engine.h | 4 + drivers/gpu/drm/i915/gt/intel_engine_cs.c | 11 +++ drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 6 +- drivers/gpu/drm/i915/gt/intel_lrc.c | 79 ++++++++++--------- drivers/gpu/drm/i915/gt/intel_lrc_reg.h | 4 +- drivers/gpu/drm/i915/gt/intel_mocs.c | 17 ++-- drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 45 +++++++++-- drivers/gpu/drm/i915/gt/intel_workarounds.c | 4 +- .../gpu/drm/i915/gt/selftest_workarounds.c | 9 ++- drivers/gpu/drm/i915/gvt/mmio_context.c | 16 +++- drivers/gpu/drm/i915/i915_cmd_parser.c | 4 +- drivers/gpu/drm/i915/i915_gem_context.c | 12 +-- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 +- drivers/gpu/drm/i915/i915_perf.c | 19 +++--14 files changed, 154 insertions(+), 79 deletions(-)drivers/gpu/drm/i915/gt/intel_engine.h +2
-0@@ -546,4 +546,8 @@ static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists) #endif +bool i915_engine_has_relative_lri(const struct intel_engine_cs *engine); +u32 i915_get_lri_cmd (const struct intel_engine_cs *engine,u32 word_count); +u32 i915_get_lri_reg(const struct intel_engine_cs *engine,
i915_reg_treg);
+
#endif /* _INTEL_RINGBUFFER_H_ */drivers/gpu/drm/i915/gt/intel_engine_cs.c +0
-0@@ -253,6 +253,17 @@ static u32 __engine_mmio_base(structdrm_i915_private *i915, return bases[i].base;drivers/gpu/drm/i915/gt/intel_engine_cs.c static u32 __engine_mmio_base(struct · line 264
Quoted 10 lines
drivers/gpu/drm/i915/gt/intel_engine_cs.c +8
-0} +bool i915_engine_has_relative_lri(const struct intel_engine_cs *engine) +{ + if (INTEL_GEN(engine->i915) < 11) + return false; + + if (engine->class == COPY_ENGINE_CLASS) + return false; + + return true;I think
engine->flagswould be better. At least it is one conditional instead of two at runtime, even one too many for something that is invariant.Quoted 15 lines
drivers/gpu/drm/i915/gt/intel_engine_cs.c +2
-0+} + static void __sprint_engine_name(char *name, const struct engine_info *info) {WARN_ON(snprintf(name,
INTEL_ENGINE_CS_MAX_NAME, "%s%u",drivers/gpu/drm/i915/gt/intel_gpu_commands.h +1
-0@@ -123,9 +123,13 @@ * simply ignores the register load under certain conditions. * - One can actually load arbitrary many arbitrary registers: Simply issue x * address/value pairs. Don't overdue it, though, x <= 2^4 must hold! + * - Newer hardware supports engine relative addresses but olderhardware does
Quoted 8 lines
drivers/gpu/drm/i915/gt/intel_gpu_commands.h line 130
Quoted 6 lines
+ * not. So never call
MI_LRIdirectly, always use thei915_get_lri_cmd()
+ * andi915_get_lri_reg()helper functions. */drivers/gpu/drm/i915/gt/intel_gpu_commands.h +1
-1-#define MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1) +#define __MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1)So we end up with code using
__MI_LOAD_REGISTER_IMMfor absolute, andi915_get_lri_cmdfor relative addressing. One is a macro, another is a function call, and naming/case is different.
No. The __M_L_R_IMM version is for old code that can only run on pre-Gen11 devices. The helper function is for all other code. The caller does not know (or care) whether it should be using absolute or relative addressing. That is the point of the helper.
See earlier discussion about wanting to make it totally obvious that using the simple macro version is the wrong thing to do in new code.
Quoted 4 lines
...
Then all call sites can use just this single helper and the naming remains familiar.
I originally had a single helper to be used in all call sites. Chris objected violently to the idea of calling a helper in code that is purely pre-Gen11 and thus has no need of the helper.
On the other hand, Rodrigo agreed with you that using the helper everywhere was cleaner. So it is now a 2 vs 1 vote...
John.
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Quoted 120 lines · John Harrison
Quoted 105 lines · Tvrtko Ursulin
Quoted 75 lines · On 13/05/2019 20:45, [email protected] wrote:
From: John Harrison <[email protected]>
With virtual engines, it is no longer possible to know which specific physical engine a given request will be executed on at the time that request is generated. This means that the request itself must be engine agnostic - any direct register writes must be relative to the engine and not absolute addresses.
The LRI command has support for engine relative addressing. However, the mechanism is not transparent to the driver. The scheme for Gen11 (
MI_LRI_ADD_CS_MMIO_START) requires the LRI address to have no absolute engine base component. The hardware then adds on the correct engine offset at execution time.Due to the non-trivial and differing schemes on different hardware, it is not possible to simply update the code that creates the LRI commands to set a remap flag and let the hardware get on with it. Instead, this patch adds function wrappers for generating the LRI command itself and then for constructing the correct address to use with the LRI.
v2: Fix build break in GVT. Remove flags parameter [review feedback from Chris W].
v3: Fix build break in selftest. Rebase to newer base tree and fix merge conflict.
v4: More rebasing. Rmoved relative addressing support from Gen7-9 only code paths [review feedback from Chris W].
v5: More rebasing (new 'gt' directory). Fix white space issue. Use COPY class rather than BCS0 id for checking against BCS engine.
Signed-off-by John Harrison <[email protected]>CC Rodrigo Vivi <[email protected]>CC Tvrtko Ursulin <[email protected]>CC Wilson, Chris P <[email protected]>---
drivers/gpu/drm/i915/gt/intel_engine.h | 4 + drivers/gpu/drm/i915/gt/intel_engine_cs.c | 11 +++ drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 6 +- drivers/gpu/drm/i915/gt/intel_lrc.c | 79 ++++++++++--------- drivers/gpu/drm/i915/gt/intel_lrc_reg.h | 4 +- drivers/gpu/drm/i915/gt/intel_mocs.c | 17 ++-- drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 45 +++++++++-- drivers/gpu/drm/i915/gt/intel_workarounds.c | 4 +- .../gpu/drm/i915/gt/selftest_workarounds.c | 9 ++- drivers/gpu/drm/i915/gvt/mmio_context.c | 16 +++- drivers/gpu/drm/i915/i915_cmd_parser.c | 4 +- drivers/gpu/drm/i915/i915_gem_context.c | 12 +-- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 +- drivers/gpu/drm/i915/i915_perf.c | 19 +++--14 files changed, 154 insertions(+), 79 deletions(-)drivers/gpu/drm/i915/gt/intel_engine.h +2
-0@@ -546,4 +546,8 @@ static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists) #endif +bool i915_engine_has_relative_lri(const struct intel_engine_cs *engine); +u32 i915_get_lri_cmd (const struct intel_engine_cs *engine,u32 word_count); +u32 i915_get_lri_reg(const struct intel_engine_cs *engine,
i915_reg_treg);
+
#endif /* _INTEL_RINGBUFFER_H_ */drivers/gpu/drm/i915/gt/intel_engine_cs.c +0
-0@@ -253,6 +253,17 @@ static u32 __engine_mmio_base(structdrm_i915_private *i915, return bases[i].base;drivers/gpu/drm/i915/gt/intel_engine_cs.c static u32 __engine_mmio_base(struct · line 264
Quoted 10 lines
drivers/gpu/drm/i915/gt/intel_engine_cs.c +8
-0} +bool i915_engine_has_relative_lri(const struct intel_engine_cs *engine) +{ + if (INTEL_GEN(engine->i915) < 11) + return false; + + if (engine->class == COPY_ENGINE_CLASS) + return false; + + return true;I think
engine->flagswould be better. At least it is one conditional instead of two at runtime, even one too many for something that is invariant.Quoted 15 lines
drivers/gpu/drm/i915/gt/intel_engine_cs.c +2
-0+} + static void __sprint_engine_name(char *name, const struct engine_info *info) {WARN_ON(snprintf(name,
INTEL_ENGINE_CS_MAX_NAME, "%s%u",drivers/gpu/drm/i915/gt/intel_gpu_commands.h +1
-0@@ -123,9 +123,13 @@ * simply ignores the register load under certain conditions. * - One can actually load arbitrary many arbitrary registers: Simply issue x * address/value pairs. Don't overdue it, though, x <= 2^4 must hold! + * - Newer hardware supports engine relative addresses but olderhardware does
Quoted 8 lines
drivers/gpu/drm/i915/gt/intel_gpu_commands.h line 130
Quoted 6 lines
+ * not. So never call
MI_LRIdirectly, always use thei915_get_lri_cmd()
+ * andi915_get_lri_reg()helper functions. */drivers/gpu/drm/i915/gt/intel_gpu_commands.h +1
-1-#define MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1) +#define __MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1)So we end up with code using
__MI_LOAD_REGISTER_IMMfor absolute, andi915_get_lri_cmdfor relative addressing. One is a macro, another is a function call, and naming/case is different.No. The
__M_L_R_IMMversion is for old code that can only run on pre-Gen11 devices. The helper function is for all other code. The caller does not know (or care) whether it should be using absolute or relative addressing. That is the point of the helper.See earlier discussion about wanting to make it totally obvious that using the simple macro version is the wrong thing to do in new code.
Quoted 8 lines
Quoted 4 lines
...
Then all call sites can use just this single helper and the naming remains familiar.
I originally had a single helper to be used in all call sites. Chris objected violently to the idea of calling a helper in code that is purely pre-Gen11 and thus has no need of the helper.
On the other hand, Rodrigo agreed with you that using the helper everywhere was cleaner. So it is now a 2 vs 1 vote...
Maybe leaving the legacy code use the existing MI_LOAD_REGISTER_IMM then, and just calling the new one MI_LOAD_REGISTER_IMM_REL would be passable? It would satisfy my complaint that two helpers look so radically different. Would make Chris happy and would make the patch smaller I think.
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Rodrigo Vivi
maintainerQuoted 148 lines · Tvrtko Ursulin
Quoted 146 lines · John Harrison
Quoted 117 lines · Tvrtko Ursulin
Quoted 81 lines · On 13/05/2019 20:45, [email protected] wrote:
From: John Harrison <[email protected]>
With virtual engines, it is no longer possible to know which specific physical engine a given request will be executed on at the time that request is generated. This means that the request itself must be engine agnostic - any direct register writes must be relative to the engine and not absolute addresses.
The LRI command has support for engine relative addressing. However, the mechanism is not transparent to the driver. The scheme for Gen11 (
MI_LRI_ADD_CS_MMIO_START) requires the LRI address to have no absolute engine base component. The hardware then adds on the correct engine offset at execution time.Due to the non-trivial and differing schemes on different hardware, it is not possible to simply update the code that creates the LRI commands to set a remap flag and let the hardware get on with it. Instead, this patch adds function wrappers for generating the LRI command itself and then for constructing the correct address to use with the LRI.
v2: Fix build break in GVT. Remove flags parameter [review feedback from Chris W].
v3: Fix build break in selftest. Rebase to newer base tree and fix merge conflict.
v4: More rebasing. Rmoved relative addressing support from Gen7-9 only code paths [review feedback from Chris W].
v5: More rebasing (new 'gt' directory). Fix white space issue. Use COPY class rather than BCS0 id for checking against BCS engine.
Signed-off-by John Harrison <[email protected]>CC Rodrigo Vivi <[email protected]>CC Tvrtko Ursulin <[email protected]>CC Wilson, Chris P <[email protected]>---
drivers/gpu/drm/i915/gt/intel_engine.h | 4 + drivers/gpu/drm/i915/gt/intel_engine_cs.c | 11 +++ drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 6 +- drivers/gpu/drm/i915/gt/intel_lrc.c | 79 ++++++++++--------- drivers/gpu/drm/i915/gt/intel_lrc_reg.h | 4 +- drivers/gpu/drm/i915/gt/intel_mocs.c | 17 ++-- drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 45 +++++++++-- drivers/gpu/drm/i915/gt/intel_workarounds.c | 4 +- .../gpu/drm/i915/gt/selftest_workarounds.c | 9 ++- drivers/gpu/drm/i915/gvt/mmio_context.c | 16 +++- drivers/gpu/drm/i915/i915_cmd_parser.c | 4 +- drivers/gpu/drm/i915/i915_gem_context.c | 12 +-- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 +- drivers/gpu/drm/i915/i915_perf.c | 19 +++--14 files changed, 154 insertions(+), 79 deletions(-)drivers/gpu/drm/i915/gt/intel_engine.h +0
-0@@ -546,4 +546,8 @@ static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists) #endif+bool
i915_engine_has_relative_lri(const struct intel_engine_cs *engine);
+u32i915_get_lri_cmd(const struct intel_engine_cs *engine, u32 word_count);
+u32i915_get_lri_reg(const struct intel_engine_cs *engine, i915_reg_t reg);
+
#endif /* _INTEL_RINGBUFFER_H_ */drivers/gpu/drm/i915/gt/intel_engine_cs.c +0
-0@@ -253,6 +253,17 @@ static u32 __engine_mmio_base(structdrm_i915_private *i915, return bases[i].base; }+bool i915_engine_has_relative_lri(const struct
intel_engine_cs*engine)drivers/gpu/drm/i915/gt/intel_engine_cs.c static u32 __engine_mmio_base(struct drm_i915_private *i915, · line 264
Quoted 8 lines
drivers/gpu/drm/i915/gt/intel_engine_cs.c +8
-0+{ + if (INTEL_GEN(engine->i915) < 11) + return false; + + if (engine->class == COPY_ENGINE_CLASS) + return false; + + return true;I think
engine->flagswould be better. At least it is one conditional instead of two at runtime, even one too many for something that is invariant.Quoted 21 lines
drivers/gpu/drm/i915/gt/intel_engine_cs.c +2
-0+} +static void
__sprint_engine_name(char *name, const struct engine_info *info)
{
WARN_ON(snprintf(name,INTEL_ENGINE_CS_MAX_NAME, "%s%u",drivers/gpu/drm/i915/gt/intel_gpu_commands.h +0
-0@@ -123,9 +123,13 @@ * simply ignores the register load under certain conditions. * - One can actually load arbitrary many arbitrary registers:Simply issue x
* address/value pairs. Don't overdue it, though, x <= 2^4 must hold!
+ * - Newer hardware supports engine relative addresses but older hardware does
+ * not. So never callMI_LRIdirectly, always use thei915_get_lri_cmd()Quoted 8 lines
drivers/gpu/drm/i915/gt/intel_gpu_commands.h line 130
Quoted 4 lines
+ * and
i915_get_lri_reg()helper functions.
*/drivers/gpu/drm/i915/gt/intel_gpu_commands.h +1
-1-#define MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1) +#define __MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1)So we end up with code using
__MI_LOAD_REGISTER_IMMfor absolute, andi915_get_lri_cmdfor relative addressing. One is a macro, another is a function call, and naming/case is different.No. The
__M_L_R_IMMversion is for old code that can only run on pre-Gen11 devices. The helper function is for all other code. The caller does not know (or care) whether it should be using absolute or relative addressing. That is the point of the helper.See earlier discussion about wanting to make it totally obvious that using the simple macro version is the wrong thing to do in new code.
Quoted 5 lines
...
Then all call sites can use just this single helper and the naming remains familiar.
I originally had a single helper to be used in all call sites. Chris objected violently to the idea of calling a helper in code that is purely pre-Gen11 and thus has no need of the helper.
Quoted 7 lines
Quoted 2 lines
On the other hand, Rodrigo agreed with you that using the helper everywhere was cleaner. So it is now a 2 vs 1 vote...
Maybe leaving the legacy code use the existing
MI_LOAD_REGISTER_IMMthen, and just calling the new oneMI_LOAD_REGISTER_IMM_RELwould be passable? It would satisfy my complaint that two helpers look so radically different. Would make Chris happy and would make the patch smaller I think.
I prefer this approach as well.
Quoted 8 lines
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Quoted 30 lines · On Mon, May 13, 2019 at 12:45:52PM -0700, [email protected] wrote:
From: John Harrison <[email protected]>
With virtual engines, it is no longer possible to know which specific physical engine a given request will be executed on at the time that request is generated. This means that the request itself must be engine agnostic - any direct register writes must be relative to the engine and not absolute addresses.
The LRI command has support for engine relative addressing. However, the mechanism is not transparent to the driver. The scheme for Gen11 (
MI_LRI_ADD_CS_MMIO_START) requires the LRI address to have no absolute engine base component. The hardware then adds on the correct engine offset at execution time.Due to the non-trivial and differing schemes on different hardware, it is not possible to simply update the code that creates the LRI commands to set a remap flag and let the hardware get on with it. Instead, this patch adds function wrappers for generating the LRI command itself and then for constructing the correct address to use with the LRI.
v2: Fix build break in GVT. Remove flags parameter [review feedback from Chris W].
v3: Fix build break in selftest. Rebase to newer base tree and fix merge conflict.
v4: More rebasing. Rmoved relative addressing support from Gen7-9 only code paths [review feedback from Chris W].
Quoted 7 lines
v5: More rebasing (new 'gt' directory). Fix white space issue. Use COPY class rather than BCS0 id for checking against BCS engine.
Signed-off-by John Harrison <[email protected]>CC Rodrigo Vivi <[email protected]>CC Tvrtko Ursulin <[email protected]>CC Wilson, Chris P <[email protected]>
I've reviewed this series and to me it looks like all the concerns have been addressed + CI is passing. Do not feel comfortable give a R-B but this patch is needed for a series I'm working on so I'd like to see it merged. Gentle ping to get this merged.
Thanks,
Matt
Quoted 621 lines
---
drivers/gpu/drm/i915/gt/intel_engine.h | 4 + drivers/gpu/drm/i915/gt/intel_engine_cs.c | 11 +++ drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 6 +- drivers/gpu/drm/i915/gt/intel_lrc.c | 79 ++++++++++--------- drivers/gpu/drm/i915/gt/intel_lrc_reg.h | 4 +- drivers/gpu/drm/i915/gt/intel_mocs.c | 17 ++-- drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 45 +++++++++-- drivers/gpu/drm/i915/gt/intel_workarounds.c | 4 +- .../gpu/drm/i915/gt/selftest_workarounds.c | 9 ++- drivers/gpu/drm/i915/gvt/mmio_context.c | 16 +++- drivers/gpu/drm/i915/i915_cmd_parser.c | 4 +- drivers/gpu/drm/i915/i915_gem_context.c | 12 +-- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 +- drivers/gpu/drm/i915/i915_perf.c | 19 +++-- 14 files changed, 154 insertions(+), 79 deletions(-)drivers/gpu/drm/i915/gt/intel_engine.h +4
-0@@ -546,4 +546,8 @@ static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)#endif +bool i915_engine_has_relative_lri (const struct intel_engine_cs *engine); +u32 i915_get_lri_cmd (const struct intel_engine_cs *engine,u32 word_count); +u32 i915_get_lri_reg (const struct intel_engine_cs *engine,i915_reg_t reg); +#endif /* _INTEL_RINGBUFFER_H_ */ drivers/gpu/drm/i915/gt/intel_engine_cs.c +11
-0@@ -253,6 +253,17 @@ static u32 __engine_mmio_base(struct drm_i915_private *i915,return bases[i].base; } +bool i915_engine_has_relative_lri (const struct intel_engine_cs *engine) +{ +if (INTEL_GEN (engine->i915) <11 ) +return false; + +if (engine->class ==COPY_ENGINE_CLASS ) +return false; + +return true; +} +static void __sprint_engine_name (char *name,const struct engine_info *info) { WARN_ON(snprintf(name, INTEL_ENGINE_CS_MAX_NAME, "%s%u",drivers/gpu/drm/i915/gt/intel_gpu_commands.h +5
-1@@ -123,9 +123,13 @@* simply ignores the register load under certain conditions. * - One can actually load arbitrary many arbitrary registers: Simply issue x * address/value pairs. Don't overdue it, though, x <= 2^4 must hold! +* - Newer hardware supports engine relative addresses but older hardware does +* not. So never call MI_LRI directly, always use the i915_get_lri_cmd() +* and i915_get_lri_reg() helper functions. */ -#define MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1) +#define __MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1)#define MI_LRI_FORCE_POSTED (1<<12) +#define MI_LRI_ADD_CS_MMIO_START_GEN11 (1<<19)#define MI_STORE_REGISTER_MEM MI_INSTR(0x24, 1)#define MI_STORE_REGISTER_MEM_GEN8 MI_INSTR(0x24, 2)#define MI_SRM_LRM_GLOBAL_GTT (1<<22)drivers/gpu/drm/i915/gt/intel_lrc.c +43
-36@@ -1388,14 +1388,15 @@ static int emit_pdps(struct i915_request *rq)return PTR_ERR (cs);/* Ensure the LRI have landed before we invalidate & continue */ - *cs++ =MI_LOAD_REGISTER_IMM (2 *GEN8_3LVL_PDPES ) |MI_LRI_FORCE_POSTED ; + *cs++ =i915_get_lri_cmd (engine,2 *GEN8_3LVL_PDPES ) | +MI_LRI_FORCE_POSTED ;for (i =GEN8_3LVL_PDPES ; i--; ) {const dma_addr_t pd_daddr =i915_page_dir_dma_addr (ppgtt, i);u32 base = engine->mmio_base; - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_UDW (base, i)); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_UDW (base, i)); *cs++ =upper_32_bits (pd_daddr); - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_LDW (base, i)); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_LDW (base, i)); *cs++ =lower_32_bits (pd_daddr); } *cs++ =MI_NOOP ;@@ -1469,7 +1470,8 @@ gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch) *batch++ =i915_scratch_offset (engine->i915) +256 ; *batch++ =0 ; - *batch++ =MI_LOAD_REGISTER_IMM (1 ); +/* Gen8/9 only so no need to support relative offsets */ + *batch++ =__MI_LOAD_REGISTER_IMM (1 ); *batch++ =i915_mmio_reg_offset (GEN8_L3SQCREG4 ); *batch++ =0x40400000 |GEN8_LQSC_FLUSH_COHERENT_LINES ;@@ -1540,13 +1542,14 @@ struct lri {u32 value; }; -static u32 *emit_lri (u32 *batch,const struct lri *lri,unsigned int count) +static u32 *emit_lri (struct intel_engine_cs *engine,u32 *batch, +const struct lri *lri,unsigned int count) {GEM_BUG_ON (!count || count >63 ); - *batch++ =MI_LOAD_REGISTER_IMM (count); + *batch++ =i915_get_lri_cmd (engine, count);do { - *batch++ =i915_mmio_reg_offset (lri->reg); + *batch++ =i915_get_lri_reg (engine, lri->reg); *batch++ = lri->value; }while (lri++, --count); *batch++ =MI_NOOP ;@@ -1584,7 +1587,7 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */ batch =gen8_emit_flush_coherentl3_wa (engine, batch); - batch =emit_lri (batch, lri,ARRAY_SIZE (lri)); + batch =emit_lri (engine, batch, lri,ARRAY_SIZE (lri));/* WaMediaPoolStateCmdInWABB:bxt,glk */ if (HAS_POOLED_EU (engine->i915)) {@@ -2537,10 +2540,10 @@ static void execlists_init_reg_state(u32 *regs,* values (including all the missing MI_LOAD_REGISTER_IMM commands that * we are not initializing here). */ - regs[CTX_LRI_HEADER_0 ] =MI_LOAD_REGISTER_IMM (rcs ?14 :11 ) | -MI_LRI_FORCE_POSTED ; + regs[CTX_LRI_HEADER_0 ] =i915_get_lri_cmd (engine, rcs ?14 :11 ) | +MI_LRI_FORCE_POSTED ; -CTX_REG (regs,CTX_CONTEXT_CONTROL ,RING_CONTEXT_CONTROL (base), +CTX_REG (engine, regs,CTX_CONTEXT_CONTROL ,RING_CONTEXT_CONTROL (base),_MASKED_BIT_DISABLE (CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT ) |_MASKED_BIT_ENABLE (CTX_CTRL_INHIBIT_SYN_CTX_SWITCH ));if (INTEL_GEN (engine->i915) <11 ) {@@ -2548,22 +2551,23 @@ static void execlists_init_reg_state(u32 *regs,_MASKED_BIT_DISABLE (CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT |CTX_CTRL_RS_CTX_ENABLE ); } -CTX_REG (regs,CTX_RING_HEAD ,RING_HEAD (base),0 ); -CTX_REG (regs,CTX_RING_TAIL ,RING_TAIL (base),0 ); -CTX_REG (regs,CTX_RING_BUFFER_START ,RING_START (base),0 ); -CTX_REG (regs,CTX_RING_BUFFER_CONTROL ,RING_CTL (base), +CTX_REG (engine, regs,CTX_RING_HEAD ,RING_HEAD (base),0 ); +CTX_REG (engine, regs,CTX_RING_TAIL ,RING_TAIL (base),0 ); +CTX_REG (engine, regs,CTX_RING_BUFFER_START ,RING_START (base),0 ); +CTX_REG (engine, regs,CTX_RING_BUFFER_CONTROL ,RING_CTL (base),RING_CTL_SIZE (ring->size) |RING_VALID ); -CTX_REG (regs,CTX_BB_HEAD_U ,RING_BBADDR_UDW (base),0 ); -CTX_REG (regs,CTX_BB_HEAD_L ,RING_BBADDR (base),0 ); -CTX_REG (regs,CTX_BB_STATE ,RING_BBSTATE (base),RING_BB_PPGTT ); -CTX_REG (regs,CTX_SECOND_BB_HEAD_U ,RING_SBBADDR_UDW (base),0 ); -CTX_REG (regs,CTX_SECOND_BB_HEAD_L ,RING_SBBADDR (base),0 ); -CTX_REG (regs,CTX_SECOND_BB_STATE ,RING_SBBSTATE (base),0 ); +CTX_REG (engine, regs,CTX_BB_HEAD_U ,RING_BBADDR_UDW (base),0 ); +CTX_REG (engine, regs,CTX_BB_HEAD_L ,RING_BBADDR (base),0 ); +CTX_REG (engine, regs,CTX_BB_STATE ,RING_BBSTATE (base),RING_BB_PPGTT ); +CTX_REG (engine, regs,CTX_SECOND_BB_HEAD_U ,RING_SBBADDR_UDW (base),0 ); +CTX_REG (engine, regs,CTX_SECOND_BB_HEAD_L ,RING_SBBADDR (base),0 ); +CTX_REG (engine, regs,CTX_SECOND_BB_STATE ,RING_SBBSTATE (base),0 );if (rcs) {struct i915_ctx_workarounds *wa_ctx = &engine->wa_ctx; -CTX_REG (regs,CTX_RCS_INDIRECT_CTX ,RING_INDIRECT_CTX (base),0 ); -CTX_REG (regs,CTX_RCS_INDIRECT_CTX_OFFSET , +CTX_REG (engine, regs,CTX_RCS_INDIRECT_CTX , +RING_INDIRECT_CTX (base),0 ); +CTX_REG (engine, regs,CTX_RCS_INDIRECT_CTX_OFFSET ,RING_INDIRECT_CTX_OFFSET (base),0 );if (wa_ctx->indirect_ctx.size) {u32 ggtt_offset =i915_ggtt_offset (wa_ctx->vma);@@ -2576,7 +2580,8 @@ static void execlists_init_reg_state(u32 *regs,intel_lr_indirect_ctx_offset (engine) <<6 ; } -CTX_REG (regs,CTX_BB_PER_CTX_PTR ,RING_BB_PER_CTX_PTR (base),0 ); +CTX_REG (engine, regs,CTX_BB_PER_CTX_PTR , +RING_BB_PER_CTX_PTR (base),0 );if (wa_ctx->per_ctx.size) {u32 ggtt_offset =i915_ggtt_offset (wa_ctx->vma);@@ -2585,18 +2590,19 @@ static void execlists_init_reg_state(u32 *regs, } } - regs[CTX_LRI_HEADER_1 ] =MI_LOAD_REGISTER_IMM (9 ) |MI_LRI_FORCE_POSTED ; + regs[CTX_LRI_HEADER_1 ] =i915_get_lri_cmd (engine,9 ) | +MI_LRI_FORCE_POSTED ; -CTX_REG (regs,CTX_CTX_TIMESTAMP ,RING_CTX_TIMESTAMP (base),0 ); +CTX_REG (engine, regs,CTX_CTX_TIMESTAMP ,RING_CTX_TIMESTAMP (base),0 );/* PDP values well be assigned later if needed */ -CTX_REG (regs,CTX_PDP3_UDW ,GEN8_RING_PDP_UDW (base,3 ),0 ); -CTX_REG (regs,CTX_PDP3_LDW ,GEN8_RING_PDP_LDW (base,3 ),0 ); -CTX_REG (regs,CTX_PDP2_UDW ,GEN8_RING_PDP_UDW (base,2 ),0 ); -CTX_REG (regs,CTX_PDP2_LDW ,GEN8_RING_PDP_LDW (base,2 ),0 ); -CTX_REG (regs,CTX_PDP1_UDW ,GEN8_RING_PDP_UDW (base,1 ),0 ); -CTX_REG (regs,CTX_PDP1_LDW ,GEN8_RING_PDP_LDW (base,1 ),0 ); -CTX_REG (regs,CTX_PDP0_UDW ,GEN8_RING_PDP_UDW (base,0 ),0 ); -CTX_REG (regs,CTX_PDP0_LDW ,GEN8_RING_PDP_LDW (base,0 ),0 ); +CTX_REG (engine, regs,CTX_PDP3_UDW ,GEN8_RING_PDP_UDW (base,3 ),0 ); +CTX_REG (engine, regs,CTX_PDP3_LDW ,GEN8_RING_PDP_LDW (base,3 ),0 ); +CTX_REG (engine, regs,CTX_PDP2_UDW ,GEN8_RING_PDP_UDW (base,2 ),0 ); +CTX_REG (engine, regs,CTX_PDP2_LDW ,GEN8_RING_PDP_LDW (base,2 ),0 ); +CTX_REG (engine, regs,CTX_PDP1_UDW ,GEN8_RING_PDP_UDW (base,1 ),0 ); +CTX_REG (engine, regs,CTX_PDP1_LDW ,GEN8_RING_PDP_LDW (base,1 ),0 ); +CTX_REG (engine, regs,CTX_PDP0_UDW ,GEN8_RING_PDP_UDW (base,0 ),0 ); +CTX_REG (engine, regs,CTX_PDP0_LDW ,GEN8_RING_PDP_LDW (base,0 ),0 );if (i915_vm_is_4lvl (&ppgtt->vm)) {/* 64b PPGTT (48bit canonical) @@ -2612,8 +2618,9 @@ static void execlists_init_reg_state(u32 *regs, }if (rcs) { - regs[CTX_LRI_HEADER_2 ] =MI_LOAD_REGISTER_IMM (1 ); -CTX_REG (regs,CTX_R_PWR_CLK_STATE ,GEN8_R_PWR_CLK_STATE ,0 ); + regs[CTX_LRI_HEADER_2 ] =i915_get_lri_cmd (engine,1 ); +CTX_REG (engine, regs,CTX_R_PWR_CLK_STATE , +GEN8_R_PWR_CLK_STATE ,0 );i915_oa_init_reg_state (engine, ce, regs); }drivers/gpu/drm/i915/gt/intel_lrc_reg.h +2
-2@@ -39,10 +39,10 @@#define CTX_R_PWR_CLK_STATE 0x42#define CTX_END 0x44 -#define CTX_REG (reg_state, pos, reg, val) do { \ +#define CTX_REG (engine, reg_state, pos, reg, val) do { \ u32 *reg_state__ = (reg_state); \ const u32 pos__ = (pos); \ - (reg_state__)[(pos__) + 0] = i915_mmio_reg_offset(reg); \ + (reg_state__)[(pos__) + 0] = i915_get_lri_reg((engine), (reg)); \ (reg_state__)[(pos__) + 1] = (val); \ } while (0)drivers/gpu/drm/i915/gt/intel_mocs.c +10
-7@@ -324,9 +324,6 @@ static u32 get_entry_control(const struct drm_i915_mocs_table *table,/** * intel_mocs_init_engine() - emit the mocs control table * @engine: The engine for whom to emit the registers. -* -* This function simply emits a MI_LOAD_REGISTER_IMM command for the -* given table starting at the given address. */ void intel_mocs_init_engine (struct intel_engine_cs *engine) {@@ -380,18 +377,20 @@ static int emit_mocs_control_table(struct i915_request *rq,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (table->n_entries); + *cs++ =i915_get_lri_cmd (rq->engine, table->n_entries);for (index =0 ; index < table->size; index++) {u32 value =get_entry_control (table, index); - *cs++ =i915_mmio_reg_offset (mocs_register (engine, index)); + *cs++ =i915_get_lri_reg (rq->engine, +mocs_register (engine, index)); *cs++ = value; }/* All remaining entries are also unused */ for (; index < table->n_entries; index++) { - *cs++ =i915_mmio_reg_offset (mocs_register (engine, index)); + *cs++ =i915_get_lri_reg (rq->engine, +mocs_register (engine, index)); *cs++ = unused_value; }@@ -449,7 +448,11 @@ static int emit_mocs_l3cc_table(struct i915_request *rq,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (table->n_entries /2 ); +/* +* GEN9_LNCFCMOCS is not engine relative, therefore there is no +* need for relative addressing? +*/ + *cs++ =__MI_LOAD_REGISTER_IMM (table->n_entries /2 );for (i =0 ; i < table->size /2 ; i++) {u16 low =get_entry_l3cc (table,2 * i);drivers/gpu/drm/i915/gt/intel_ringbuffer.c +37
-8@@ -1516,12 +1516,13 @@ static int load_pd_dir(struct i915_request *rq,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (1 ); - *cs++ =i915_mmio_reg_offset (RING_PP_DIR_DCLV (engine->mmio_base)); +/* Can these not be merged into a single LRI??? */ + *cs++ =i915_get_lri_cmd (engine,1 ); + *cs++ =i915_get_lri_reg (engine,RING_PP_DIR_DCLV (engine->mmio_base)); *cs++ =PP_DIR_DCLV_2G ; - *cs++ =MI_LOAD_REGISTER_IMM (1 ); - *cs++ =i915_mmio_reg_offset (RING_PP_DIR_BASE (engine->mmio_base)); + *cs++ =i915_get_lri_cmd (engine,1 ); + *cs++ =i915_get_lri_reg (engine,RING_PP_DIR_BASE (engine->mmio_base)); *cs++ = ppgtt->pd.base.ggtt_offset <<10 ;intel_ring_advance (rq, cs);@@ -1589,7 +1590,11 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)if (num_engines) {struct intel_engine_cs *signaller; - *cs++ =MI_LOAD_REGISTER_IMM (num_engines); +/* +* Must use absolute engine address as the register +* write is targeting a different engine. +*/ + *cs++ =__MI_LOAD_REGISTER_IMM (num_engines);for_each_engine (signaller, i915, id) {if (signaller == engine)continue ;@@ -1643,7 +1648,11 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)struct intel_engine_cs *signaller;i915_reg_t last_reg = {};/* keep gcc quiet */ - *cs++ =MI_LOAD_REGISTER_IMM (num_engines); +/* +* Must use absolute engine address as the register +* write is targeting a different engine. +*/ + *cs++ =__MI_LOAD_REGISTER_IMM (num_engines);for_each_engine (signaller, i915, id) {if (signaller == engine)continue ;@@ -1687,9 +1696,9 @@ static int remap_l3(struct i915_request *rq, int slice)* here because no other code should access these registers other than * at initialization time. */ - *cs++ =MI_LOAD_REGISTER_IMM (GEN7_L3LOG_SIZE /4 ); + *cs++ =i915_get_lri_cmd (rq->engine,GEN7_L3LOG_SIZE /4 );for (i =0 ; i <GEN7_L3LOG_SIZE /4 ; i++) { - *cs++ =i915_mmio_reg_offset (GEN7_L3LOG (slice, i)); + *cs++ =i915_get_lri_reg (rq->engine,GEN7_L3LOG (slice, i)); *cs++ = remap_info[i]; } *cs++ =MI_NOOP ;@@ -2335,3 +2344,23 @@ int intel_ring_submission_init(struct intel_engine_cs *engine)intel_engine_cleanup_common (engine);return err; } + +u32 i915_get_lri_cmd (const struct intel_engine_cs *engine,u32 word_count) +{ +u32 word; + + word =__MI_LOAD_REGISTER_IMM (word_count); + +if (i915_engine_has_relative_lri (engine)) + word |=MI_LRI_ADD_CS_MMIO_START_GEN11 ; + +return word; +} + +u32 i915_get_lri_reg (const struct intel_engine_cs *engine,i915_reg_t reg) +{ +if (!i915_engine_has_relative_lri (engine)) +return i915_mmio_reg_offset (reg); + +return i915_mmio_reg_offset (reg) - engine->mmio_base; +}drivers/gpu/drm/i915/gt/intel_workarounds.c +2
-2@@ -625,9 +625,9 @@ int intel_engine_emit_ctx_wa(struct i915_request *rq)if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (wal->count); + *cs++ =i915_get_lri_cmd (rq->engine, wal->count);for (i =0 , wa = wal->list; i < wal->count; i++, wa++) { - *cs++ =i915_mmio_reg_offset (wa->reg); + *cs++ =i915_get_lri_reg (rq->engine, wa->reg); *cs++ = wa->val; } *cs++ =MI_NOOP ;drivers/gpu/drm/i915/gt/selftest_workarounds.c +5
-4@@ -442,6 +442,7 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,for (i =0 ; i < engine->whitelist.count; i++) {u32 reg =i915_mmio_reg_offset (engine->whitelist.list[i].reg); +u32 regLRI =i915_get_lri_reg (engine, engine->whitelist.list[i].reg);u64 addr = scratch->node.start;struct i915_request *rq;u32 srm, lrm, rsvd;@@ -474,8 +475,8 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx, idx =1 ;for (v =0 ; v <ARRAY_SIZE (values); v++) {/* LRI garbage */ - *cs++ =MI_LOAD_REGISTER_IMM (1 ); - *cs++ = reg; + *cs++ =i915_get_lri_cmd (engine,1 ); + *cs++ = regLRI; *cs++ = values[v];/* SRM result */ @@ -487,8 +488,8 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx, }for (v =0 ; v <ARRAY_SIZE (values); v++) {/* LRI garbage */ - *cs++ =MI_LOAD_REGISTER_IMM (1 ); - *cs++ = reg; + *cs++ =i915_get_lri_cmd (engine,1 ); + *cs++ = regLRI; *cs++ = ~values[v];/* SRM result */ drivers/gpu/drm/i915/gvt/mmio_context.c +12
-4@@ -200,14 +200,14 @@ restore_context_mmio_for_inhibit(struct intel_vgpu *vgpu,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (count); + *cs++ =i915_get_lri_cmd (req->engine, count);for (mmio = gvt->engine_mmio_list.mmio;i915_mmio_reg_valid (mmio->reg); mmio++) {if (mmio->ring_id != ring_id || !mmio->in_context)continue ; - *cs++ =i915_mmio_reg_offset (mmio->reg); + *cs++ =i915_get_lri_reg (req->engine, mmio->reg); *cs++ =vgpu_vreg_t (vgpu, mmio->reg) | (mmio->mask <<16 ); gvt_dbg_core("add lri reg pair 0x%x:0x%x in inhibit ctx, vgpu:%d, rind_id:%d\n",@@ -235,7 +235,11 @@ restore_render_mocs_control_for_inhibit(struct intel_vgpu *vgpu,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (GEN9_MOCS_SIZE ); +/* +* GEN9_GFX_MOCS is not engine relative, therefore there is no +* need for relative addressing. +*/ + *cs++ =__MI_LOAD_REGISTER_IMM (GEN9_MOCS_SIZE );for (index =0 ; index <GEN9_MOCS_SIZE ; index++) { *cs++ =i915_mmio_reg_offset (GEN9_GFX_MOCS (index));@@ -262,7 +266,11 @@ restore_render_mocs_l3cc_for_inhibit(struct intel_vgpu *vgpu,if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (GEN9_MOCS_SIZE /2 ); +/* +* GEN9_LNCFCMOCS is not engine relative, therefore there is no +* need for relative addressing. +*/ + *cs++ =__MI_LOAD_REGISTER_IMM (GEN9_MOCS_SIZE /2 );for (index =0 ; index <GEN9_MOCS_SIZE /2 ; index++) { *cs++ =i915_mmio_reg_offset (GEN9_LNCFCMOCS (index));drivers/gpu/drm/i915/i915_cmd_parser.c +2
-2@@ -221,7 +221,7 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = {CMD (MI_SUSPEND_FLUSH ,SMI ,F ,1 ,S ),CMD (MI_SEMAPHORE_MBOX ,SMI , !F ,0xFF ,R ),CMD (MI_STORE_DWORD_INDEX ,SMI , !F ,0xFF ,R ), -CMD (MI_LOAD_REGISTER_IMM (1 ),SMI , !F ,0xFF ,W , +CMD (__MI_LOAD_REGISTER_IMM (1 ),SMI , !F ,0xFF ,W , .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 } ), CMD( MI_STORE_REGISTER_MEM, SMI, F, 3, W | B, .reg = { .offset = 1, .mask = 0x007FFFFC },@@ -1183,7 +1183,7 @@ static bool check_cmd(const struct intel_engine_cs *engine,return false; } -if (desc->cmd.value ==MI_LOAD_REGISTER_IMM (1 ) && +if (desc->cmd.value ==__MI_LOAD_REGISTER_IMM (1 ) && (offset +2 > length || (cmd[offset +1 ] & reg->mask) != reg->value)) { DRM_DEBUG_DRIVER("CMD: Rejected LRI to masked register 0x%08X\n",drivers/gpu/drm/i915/i915_gem_context.c +6
-6@@ -1026,11 +1026,11 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (2 ); + *cs++ =i915_get_lri_cmd (engine,2 ); - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_UDW (base,0 )); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_UDW (base,0 )); *cs++ =upper_32_bits (pd_daddr); - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_LDW (base,0 )); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_LDW (base,0 )); *cs++ =lower_32_bits (pd_daddr); *cs++ =MI_NOOP ;@@ -1040,13 +1040,13 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (2 *GEN8_3LVL_PDPES ); + *cs++ =i915_get_lri_cmd (engine,2 *GEN8_3LVL_PDPES );for (i =GEN8_3LVL_PDPES ; i--; ) {const dma_addr_t pd_daddr =i915_page_dir_dma_addr (ppgtt, i); - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_UDW (base, i)); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_UDW (base, i)); *cs++ =upper_32_bits (pd_daddr); - *cs++ =i915_mmio_reg_offset (GEN8_RING_PDP_LDW (base, i)); + *cs++ =i915_get_lri_reg (engine,GEN8_RING_PDP_LDW (base, i)); *cs++ =lower_32_bits (pd_daddr); } *cs++ =MI_NOOP ;drivers/gpu/drm/i915/i915_gem_execbuffer.c +2
-1@@ -1963,7 +1963,8 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq)if (IS_ERR (cs))return PTR_ERR (cs); - *cs++ =MI_LOAD_REGISTER_IMM (4 ); +/* Gen7 only so no need to support relative offsets */ + *cs++ =__MI_LOAD_REGISTER_IMM (4 );for (i =0 ; i <4 ; i++) { *cs++ =i915_mmio_reg_offset (GEN7_SO_WRITE_OFFSET (i)); *cs++ =0 ;drivers/gpu/drm/i915/i915_perf.c +0
-0@@ -1636,7 +1636,8 @@ static void hsw_disable_metric_set(struct drm_i915_private *dev_priv)* in the case that the OA unit has been disabled. */ static void
drivers/gpu/drm/i915/i915_perf.c +2
-1-gen8_update_reg_state_unlocked(struct intel_context *ce, +gen8_update_reg_state_unlocked(struct intel_engine_cs *engine, + struct intel_context *ce,u32 *reg_state, const struct i915_oa_config *oa_config){
drivers/gpu/drm/i915/i915_perf.c +11
-5@@ -1655,7 +1656,12 @@ gen8_update_reg_state_unlocked(struct intel_context *ce, };int i; -CTX_REG (reg_state, ctx_oactxctrl,GEN8_OACTXCONTROL , +/* +* NB: The LRI instruction is generated by the hardware. +* Should we read it in and assert that the offset flag is set? +*/ + +CTX_REG (engine, reg_state, ctx_oactxctrl,GEN8_OACTXCONTROL , (i915->perf.oa.period_exponent <<GEN8_OA_TIMER_PERIOD_SHIFT ) | (i915->perf.oa.periodic ?GEN8_OA_TIMER_ENABLE :0 ) |GEN8_OA_COUNTER_RESUME );@@ -1682,10 +1688,10 @@ gen8_update_reg_state_unlocked(struct intel_context *ce, } } -CTX_REG (reg_state, state_offset, flex_regs[i], value); +CTX_REG (engine, reg_state, state_offset, flex_regs[i], value); } -CTX_REG (reg_state, +CTX_REG (engine, reg_state,CTX_R_PWR_CLK_STATE ,GEN8_R_PWR_CLK_STATE ,intel_sseu_make_rpcs (i915, &ce->sseu)); }@@ -1770,7 +1776,7 @@ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv, ce->state->obj->mm.dirty = true; regs +=LRC_STATE_PN *PAGE_SIZE /sizeof (*regs); -gen8_update_reg_state_unlocked (ce, regs, oa_config); +gen8_update_reg_state_unlocked (dev_priv->engine[RCS0 ], ce, regs, oa_config);i915_gem_object_unpin_map (ce->state->obj); }@@ -2166,7 +2172,8 @@ void i915_oa_init_reg_state(struct intel_engine_cs *engine, stream = engine->i915->perf.oa.exclusive_stream;if (stream) -gen8_update_reg_state_unlocked (ce, regs, stream->oa_config); +gen8_update_reg_state_unlocked (engine, ce, regs, + stream->oa_config); }/** Signature · 6 lines
2.21.0.5.gaeb582a983 _______________________________________________ Intel-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
[fixed Chris' email]
Quoted 39 lines · Matthew Brost
Quoted 30 lines · On Mon, May 13, 2019 at 12:45:52PM -0700, [email protected] wrote:
From: John Harrison <[email protected]>
With virtual engines, it is no longer possible to know which specific physical engine a given request will be executed on at the time that request is generated. This means that the request itself must be engine agnostic - any direct register writes must be relative to the engine and not absolute addresses.
The LRI command has support for engine relative addressing. However, the mechanism is not transparent to the driver. The scheme for Gen11 (
MI_LRI_ADD_CS_MMIO_START) requires the LRI address to have no absolute engine base component. The hardware then adds on the correct engine offset at execution time.Due to the non-trivial and differing schemes on different hardware, it is not possible to simply update the code that creates the LRI commands to set a remap flag and let the hardware get on with it. Instead, this patch adds function wrappers for generating the LRI command itself and then for constructing the correct address to use with the LRI.
v2: Fix build break in GVT. Remove flags parameter [review feedback from Chris W].
v3: Fix build break in selftest. Rebase to newer base tree and fix merge conflict.
v4: More rebasing. Rmoved relative addressing support from Gen7-9 only code paths [review feedback from Chris W].
Quoted 7 lines
v5: More rebasing (new 'gt' directory). Fix white space issue. Use COPY class rather than BCS0 id for checking against BCS engine.
Signed-off-by John Harrison <[email protected]>CC Rodrigo Vivi <[email protected]>CC Tvrtko Ursulin <[email protected]>CC Wilson, Chris P <[email protected]>
Quoted 4 lines
I've reviewed this series and to me it looks like all the concerns have been addressed + CI is passing. Do not feel comfortable give a R-B but this patch is needed for a series I'm working on so I'd like to see it merged. Gentle ping to get this merged.
AFAIR the conclusion between Rodrigo and me was to leave the existing macro as is and leave a new one (in uppercase) for relative addressing.
So leave MI_LOAD_REGISTER_IMM as is, add MI_LOAD_REGISTER_IMM_REL for usage on relevant (new) paths.
Chris did not say anything but I expect this would also satisfy his wish to keep the patch as small as possible eg not touch legacy code paths.
Regards,
Tvrtko
Quoted 667 lines
Thanks,
MattQuoted 663 lines
---
drivers/gpu/drm/i915/gt/intel_engine.h | 4 + drivers/gpu/drm/i915/gt/intel_engine_cs.c | 11 +++ drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 6 +- drivers/gpu/drm/i915/gt/intel_lrc.c | 79 ++++++++++--------- drivers/gpu/drm/i915/gt/intel_lrc_reg.h | 4 +- drivers/gpu/drm/i915/gt/intel_mocs.c | 17 ++-- drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 45 +++++++++-- drivers/gpu/drm/i915/gt/intel_workarounds.c | 4 +- .../gpu/drm/i915/gt/selftest_workarounds.c | 9 ++- drivers/gpu/drm/i915/gvt/mmio_context.c | 16 +++- drivers/gpu/drm/i915/i915_cmd_parser.c | 4 +- drivers/gpu/drm/i915/i915_gem_context.c | 12 +-- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 +- drivers/gpu/drm/i915/i915_perf.c | 19 +++--14 files changed, 154 insertions(+), 79 deletions(-)drivers/gpu/drm/i915/gt/intel_engine.h +2
-0@@ -546,4 +546,8 @@ static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)#endif +bool i915_engine_has_relative_lri (const struct intel_engine_cs *engine); +u32 i915_get_lri_cmd(const struct intel_engine_cs *engine, u32
word_count);
+u32i915_get_lri_reg(const struct intel_engine_cs *engine, i915_reg_t reg);
+
#endif /* _INTEL_RINGBUFFER_H_ */drivers/gpu/drm/i915/gt/intel_engine_cs.c +11
-0@@ -253,6 +253,17 @@ static u32 __engine_mmio_base(structdrm_i915_private *i915, return bases[i].base; } +bool i915_engine_has_relative_lri (const struct intel_engine_cs *engine) +{ + if (INTEL_GEN(engine->i915) < 11) + return false; + + if (engine->class == COPY_ENGINE_CLASS) + return false; + + return true; +} +static void __sprint_engine_name (char *name,const struct engine_info *info) {WARN_ON(snprintf(name,
INTEL_ENGINE_CS_MAX_NAME, "%s%u",drivers/gpu/drm/i915/gt/intel_gpu_commands.h +1
-0@@ -123,9 +123,13 @@ * simply ignores the register load under certain conditions. * - One can actually load arbitrary many arbitrary registers: Simply issue x * address/value pairs. Don't overdue it, though, x <= 2^4 must hold! + * - Newer hardware supports engine relative addresses but olderhardware does
+ * not. So never callMI_LRIdirectly, always use thei915_get_lri_cmd()
+ * andi915_get_lri_reg()helper functions. */drivers/gpu/drm/i915/gt/intel_gpu_commands.h +1
-1-#define MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1) +#define __MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1)#define MI_LRI_FORCE_POSTED (1<<12) +#define MI_LRI_ADD_CS_MMIO_START_GEN11 (1<<19) #define MI_STORE_REGISTER_MEM
MI_INSTR(0x24, 1)#define MI_STORE_REGISTER_MEM_GEN8MI_INSTR(0x24, 2)#define MI_SRM_LRM_GLOBAL_GTT (1<<22)drivers/gpu/drm/i915/gt/intel_lrc.c +4
-3@@ -1388,14 +1388,15 @@ static int emit_pdps(struct i915_request *rq) return PTR_ERR(cs); /* Ensure the LRI have landed before we invalidate & continue */ - *cs++ = MI_LOAD_REGISTER_IMM(2 * GEN8_3LVL_PDPES) |MI_LRI_FORCE_POSTED ; + *cs++ = i915_get_lri_cmd(engine, 2 * GEN8_3LVL_PDPES) | + MI_LRI_FORCE_POSTED; for (i = GEN8_3LVL_PDPES; i--; ) { const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i); u32 base = engine->mmio_base; - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, i)); + *cs++ = i915_get_lri_reg(engine, GEN8_RING_PDP_UDW(base, i)); *cs++ = upper_32_bits(pd_daddr); - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, i)); + *cs++ = i915_get_lri_reg(engine, GEN8_RING_PDP_LDW(base, i)); *cs++ = lower_32_bits(pd_daddr); }*cs++ =
MI_NOOP;drivers/gpu/drm/i915/gt/intel_lrc.c +6
-4@@ -1469,7 +1470,8 @@ gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch) *batch++ = i915_scratch_offset(engine->i915) + 256; *batch++ = 0; - *batch++ = MI_LOAD_REGISTER_IMM(1); + /* Gen8/9 only so no need to support relative offsets */ + *batch++ = __MI_LOAD_REGISTER_IMM(1); *batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4); *batch++ = 0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES;@@ -1540,13 +1542,14 @@ struct lri { u32 value; }; -static u32 *emit_lri (u32 *batch,const struct lri *lri,unsigned int count) +static u32 *emit_lri(struct intel_engine_cs *engine, u32 *batch, + const struct lri *lri, unsigned int count) { GEM_BUG_ON(!count || count > 63); - *batch++ = MI_LOAD_REGISTER_IMM(count); + *batch++ = i915_get_lri_cmd(engine, count); do { - *batch++ = i915_mmio_reg_offset(lri->reg); + *batch++ = i915_get_lri_reg(engine, lri->reg); *batch++ = lri->value; } while (lri++, --count);*batch++ =
MI_NOOP;drivers/gpu/drm/i915/gt/intel_lrc.c +1
-1@@ -1584,7 +1587,7 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) /* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */ batch = gen8_emit_flush_coherentl3_wa(engine, batch); - batch = emit_lri(batch, lri, ARRAY_SIZE(lri)); + batch = emit_lri(engine, batch, lri, ARRAY_SIZE(lri)); /* WaMediaPoolStateCmdInWABB:bxt,glk */if (
HAS_POOLED_EU(engine->i915)) {drivers/gpu/drm/i915/gt/intel_lrc.c +3
-3@@ -2537,10 +2540,10 @@ static void execlists_init_reg_state(u32 *regs,* values (including all the missing MI_LOAD_REGISTER_IMM commands that * we are not initializing here). */ - regs[CTX_LRI_HEADER_0] = MI_LOAD_REGISTER_IMM(rcs ? 14 : 11) | - MI_LRI_FORCE_POSTED; + regs[CTX_LRI_HEADER_0] = i915_get_lri_cmd(engine, rcs ? 14 : 11) | + MI_LRI_FORCE_POSTED; - CTX_REG(regs, CTX_CONTEXT_CONTROL, RING_CONTEXT_CONTROL(base), + CTX_REG(engine, regs, CTX_CONTEXT_CONTROL, RING_CONTEXT_CONTROL(base),
_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT)|_MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH)); if (INTEL_GEN(engine->i915)< 11) {drivers/gpu/drm/i915/gt/intel_lrc.c +0
-0@@ -2548,22 +2551,23 @@ static void execlists_init_reg_state(u32 *regs,
_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT | CTX_CTRL_RS_CTX_ENABLE);
}
-CTX_REG(regs, CTX_RING_HEAD, RING_HEAD(base), 0);
-CTX_REG(regs, CTX_RING_TAIL, RING_TAIL(base), 0);
-CTX_REG(regs, CTX_RING_BUFFER_START, RING_START(base), 0); - CTX_REG(regs,CTX_RING_BUFFER_CONTROL,RING_CTL(base), +CTX_REG(engine, regs, CTX_RING_HEAD, RING_HEAD(base), 0); +CTX_REG(engine, regs, CTX_RING_TAIL, RING_TAIL(base), 0); +CTX_REG(engine, regs, CTX_RING_BUFFER_START, RING_START(base), 0); +CTX_REG(engine, regs, CTX_RING_BUFFER_CONTROL, RING_CTL(base), RING_CTL_SIZE(ring->size) | RING_VALID);
-CTX_REG(regs, CTX_BB_HEAD_U, RING_BBADDR_UDW(base), 0); -CTX_REG(regs, CTX_BB_HEAD_L, RING_BBADDR(base), 0);
-CTX_REG(regs, CTX_BB_STATE, RING_BBSTATE(base), RING_BB_PPGTT); -CTX_REG(regs, CTX_SECOND_BB_HEAD_U, RING_SBBADDR_UDW(base), 0); -CTX_REG(regs, CTX_SECOND_BB_HEAD_L, RING_SBBADDR(base), 0); -CTX_REG(regs, CTX_SECOND_BB_STATE, RING_SBBSTATE(base), 0); +CTX_REG(engine, regs, CTX_BB_HEAD_U, RING_BBADDR_UDW(base), 0); +CTX_REG(engine, regs, CTX_BB_HEAD_L, RING_BBADDR(base), 0); +CTX_REG(engine, regs, CTX_BB_STATE, RING_BBSTATE(base), RING_BB_PPGTT);
+CTX_REG(engine, regs, CTX_SECOND_BB_HEAD_U, RING_SBBADDR_UDW(base), 0);
+CTX_REG(engine, regs, CTX_SECOND_BB_HEAD_L, RING_SBBADDR(base), 0); +CTX_REG(engine, regs, CTX_SECOND_BB_STATE, RING_SBBSTATE(base), 0); if (rcs) {
structi915_ctx_workarounds*wa_ctx=&engine->wa_ctx;-
CTX_REG(regs, CTX_RCS_INDIRECT_CTX, RING_INDIRECT_CTX(base), 0); - CTX_REG(regs,CTX_RCS_INDIRECT_CTX_OFFSET,
+ CTX_REG(engine, regs,CTX_RCS_INDIRECT_CTX,
+RING_INDIRECT_CTX(base), 0);
+CTX_REG(engine, regs, CTX_RCS_INDIRECT_CTX_OFFSET, RING_INDIRECT_CTX_OFFSET(base), 0);
if (wa_ctx->indirect_ctx.size) {
u32ggtt_offset=i915_ggtt_offset(wa_ctx->vma);drivers/gpu/drm/i915/gt/intel_lrc.c +13
-11@@ -2576,7 +2580,8 @@ static void execlists_init_reg_state(u32 *regs, intel_lr_indirect_ctx_offset(engine) << 6; } - CTX_REG(regs, CTX_BB_PER_CTX_PTR, RING_BB_PER_CTX_PTR(base), 0); + CTX_REG(engine, regs, CTX_BB_PER_CTX_PTR, + RING_BB_PER_CTX_PTR(base), 0); if (wa_ctx->per_ctx.size) { u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);@@ -2585,18 +2590,19 @@ static void execlists_init_reg_state(u32 *regs, } } - regs[CTX_LRI_HEADER_1] = MI_LOAD_REGISTER_IMM(9) |MI_LRI_FORCE_POSTED ; + regs[CTX_LRI_HEADER_1] = i915_get_lri_cmd(engine, 9) | + MI_LRI_FORCE_POSTED; - CTX_REG(regs, CTX_CTX_TIMESTAMP, RING_CTX_TIMESTAMP(base), 0); + CTX_REG(engine, regs, CTX_CTX_TIMESTAMP,RING_CTX_TIMESTAMP (base),0 ); /* PDP values well be assigned later if needed */ - CTX_REG(regs, CTX_PDP3_UDW, GEN8_RING_PDP_UDW(base, 3), 0); - CTX_REG(regs, CTX_PDP3_LDW, GEN8_RING_PDP_LDW(base, 3), 0); - CTX_REG(regs, CTX_PDP2_UDW, GEN8_RING_PDP_UDW(base, 2), 0); - CTX_REG(regs, CTX_PDP2_LDW, GEN8_RING_PDP_LDW(base, 2), 0); - CTX_REG(regs, CTX_PDP1_UDW, GEN8_RING_PDP_UDW(base, 1), 0); - CTX_REG(regs, CTX_PDP1_LDW, GEN8_RING_PDP_LDW(base, 1), 0); - CTX_REG(regs, CTX_PDP0_UDW, GEN8_RING_PDP_UDW(base, 0), 0); - CTX_REG(regs, CTX_PDP0_LDW, GEN8_RING_PDP_LDW(base, 0), 0); + CTX_REG(engine, regs, CTX_PDP3_UDW, GEN8_RING_PDP_UDW(base, 3), 0); + CTX_REG(engine, regs, CTX_PDP3_LDW, GEN8_RING_PDP_LDW(base, 3), 0); + CTX_REG(engine, regs, CTX_PDP2_UDW, GEN8_RING_PDP_UDW(base, 2), 0); + CTX_REG(engine, regs, CTX_PDP2_LDW, GEN8_RING_PDP_LDW(base, 2), 0); + CTX_REG(engine, regs, CTX_PDP1_UDW, GEN8_RING_PDP_UDW(base, 1), 0); + CTX_REG(engine, regs, CTX_PDP1_LDW, GEN8_RING_PDP_LDW(base, 1), 0); + CTX_REG(engine, regs, CTX_PDP0_UDW, GEN8_RING_PDP_UDW(base, 0), 0); + CTX_REG(engine, regs, CTX_PDP0_LDW, GEN8_RING_PDP_LDW(base, 0), 0);if (
i915_vm_is_4lvl(&ppgtt->vm)) {
/* 64b PPGTT (48bit canonical)drivers/gpu/drm/i915/gt/intel_lrc.c +3
-2@@ -2612,8 +2618,9 @@ static void execlists_init_reg_state(u32 *regs, } if (rcs) { - regs[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1); - CTX_REG(regs, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE, 0); + regs[CTX_LRI_HEADER_2] = i915_get_lri_cmd(engine, 1); + CTX_REG(engine, regs, CTX_R_PWR_CLK_STATE, + GEN8_R_PWR_CLK_STATE, 0); i915_oa_init_reg_state(engine, ce, regs); }drivers/gpu/drm/i915/gt/intel_lrc_reg.h +2
-2@@ -39,10 +39,10 @@#define CTX_R_PWR_CLK_STATE 0x42#define CTX_END 0x44 -#define CTX_REG (reg_state, pos, reg, val) do { \ +#define CTX_REG (engine, reg_state, pos, reg, val) do { \ u32 *reg_state__ = (reg_state); \ const u32 pos__ = (pos); \ - (reg_state__)[(pos__) + 0] = i915_mmio_reg_offset(reg); \ + (reg_state__)[(pos__) + 0] = i915_get_lri_reg((engine), (reg)); \ (reg_state__)[(pos__) + 1] = (val); \ } while (0)drivers/gpu/drm/i915/gt/intel_mocs.c +0
-3@@ -324,9 +324,6 @@ static u32 get_entry_control(const structdrm_i915_mocs_table *table,/** * intel_mocs_init_engine() - emit the mocs control table * @engine: The engine for whom to emit the registers. -* -* This function simply emits a MI_LOAD_REGISTER_IMM command for the -* given table starting at the given address. */ void intel_mocs_init_engine(struct intel_engine_cs *engine){
drivers/gpu/drm/i915/gt/intel_mocs.c +10
-4@@ -380,18 +377,20 @@ static int emit_mocs_control_table(structi915_request *rq, if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(table->n_entries); + *cs++ = i915_get_lri_cmd(rq->engine, table->n_entries); for (index = 0; index < table->size; index++) { u32 value = get_entry_control(table, index); - *cs++ = i915_mmio_reg_offset(mocs_register(engine, index)); + *cs++ = i915_get_lri_reg(rq->engine, + mocs_register(engine, index)); *cs++ = value; } /* All remaining entries are also unused */ for (; index < table->n_entries; index++) { - *cs++ = i915_mmio_reg_offset(mocs_register(engine, index)); + *cs++ = i915_get_lri_reg(rq->engine, + mocs_register(engine, index)); *cs++ = unused_value; }@@ -449,7 +448,11 @@ static int emit_mocs_l3cc_table(structi915_request *rq, if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(table->n_entries / 2); + /* + * GEN9_LNCFCMOCS is not engine relative, therefore there is no + * need for relative addressing? + */ + *cs++ = __MI_LOAD_REGISTER_IMM(table->n_entries / 2); for (i = 0; i < table->size / 2; i++) {u16 low =
get_entry_l3cc(table, 2 * i);drivers/gpu/drm/i915/gt/intel_ringbuffer.c +5
-4@@ -1516,12 +1516,13 @@ static int load_pd_dir(struct i915_request *rq, if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = i915_mmio_reg_offset(RING_PP_DIR_DCLV(engine->mmio_base)); + /* Can these not be merged into a single LRI??? */ + *cs++ = i915_get_lri_cmd(engine, 1); + *cs++ = i915_get_lri_reg(engine,RING_PP_DIR_DCLV (engine->mmio_base)); *cs++ = PP_DIR_DCLV_2G; - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine->mmio_base)); + *cs++ = i915_get_lri_cmd(engine, 1); + *cs++ = i915_get_lri_reg(engine,RING_PP_DIR_BASE (engine->mmio_base)); *cs++ = ppgtt->pd.base.ggtt_offset << 10;intel_ring_advance(rq, cs);
drivers/gpu/drm/i915/gt/intel_ringbuffer.c +5
-1@@ -1589,7 +1590,11 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) if (num_engines) { struct intel_engine_cs *signaller; - *cs++ = MI_LOAD_REGISTER_IMM(num_engines); + /* + * Must use absolute engine address as the register + * write is targeting a different engine. + */ + *cs++ = __MI_LOAD_REGISTER_IMM(num_engines); for_each_engine(signaller, i915, id) { if (signaller == engine)continue;
drivers/gpu/drm/i915/gt/intel_ringbuffer.c +0
-0@@ -1643,7 +1648,11 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) struct intel_engine_cs *signaller;
i915_reg_tlast_reg= {}; /* keep gcc quiet */- *cs++ =
MI_LOAD_REGISTER_IMM(num_engines); + /*
+ * Must use absolute engine address as the register + * write is targeting a different engine. + */
+ *cs++ =__MI_LOAD_REGISTER_IMM(num_engines);for_each_engine(signaller, i915, id){
if (signaller == engine)
continue;drivers/gpu/drm/i915/gt/intel_ringbuffer.c +2
-2@@ -1687,9 +1696,9 @@ static int remap_l3(struct i915_request *rq, intslice) * here because no other code should access these registers other than * at initialization time. */ - *cs++ = MI_LOAD_REGISTER_IMM(GEN7_L3LOG_SIZE/4); + *cs++ = i915_get_lri_cmd(rq->engine, GEN7_L3LOG_SIZE/4); for (i = 0; i < GEN7_L3LOG_SIZE/4; i++) { - *cs++ = i915_mmio_reg_offset(GEN7_L3LOG(slice, i)); + *cs++ = i915_get_lri_reg(rq->engine, GEN7_L3LOG(slice, i)); *cs++ = remap_info[i]; }*cs++ =
MI_NOOP;drivers/gpu/drm/i915/gt/intel_ringbuffer.c +0
-0@@ -2335,3 +2344,23 @@ int intel_ring_submission_init(struct intel_engine_cs *engine) intel_engine_cleanup_common(engine); return err;}
drivers/gpu/drm/i915/gt/intel_ringbuffer.c +2
-0+ +u32 i915_get_lri_cmd(const struct intel_engine_cs *engine, u32
word_count)drivers/gpu/drm/i915/gt/intel_ringbuffer.c +12
-0+{ + u32 word; + + word = __MI_LOAD_REGISTER_IMM(word_count); + + if (i915_engine_has_relative_lri(engine)) + word |= MI_LRI_ADD_CS_MMIO_START_GEN11; + + return word; +} + +u32 i915_get_lri_reg(const struct intel_engine_cs *engine, i915_reg_treg)
drivers/gpu/drm/i915/gt/intel_ringbuffer.c +6
-0+{ + if (!i915_engine_has_relative_lri(engine)) + return i915_mmio_reg_offset(reg); + + return i915_mmio_reg_offset(reg) - engine->mmio_base; +}drivers/gpu/drm/i915/gt/intel_workarounds.c +2
-2@@ -625,9 +625,9 @@ int intel_engine_emit_ctx_wa(struct i915_request *rq) if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(wal->count); + *cs++ = i915_get_lri_cmd(rq->engine, wal->count); for (i = 0, wa = wal->list; i < wal->count; i++, wa++) { - *cs++ = i915_mmio_reg_offset(wa->reg); + *cs++ = i915_get_lri_reg(rq->engine, wa->reg); *cs++ = wa->val; } *cs++ = MI_NOOP;drivers/gpu/drm/i915/gt/selftest_workarounds.c +1
-0@@ -442,6 +442,7 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx, for (i = 0; i < engine->whitelist.count; i++) { u32 reg = i915_mmio_reg_offset(engine->whitelist.list[i].reg); + u32 regLRI = i915_get_lri_reg(engine, engine->whitelist.list[i].reg); u64 addr = scratch->node.start;struct
i915_request*rq;
u32 srm, lrm, rsvd;drivers/gpu/drm/i915/gt/selftest_workarounds.c +2
-2@@ -474,8 +475,8 @@ static int check_dirty_whitelist(structi915_gem_context *ctx, idx = 1; for (v = 0; v < ARRAY_SIZE(values); v++) { /* LRI garbage */ - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = reg; + *cs++ = i915_get_lri_cmd(engine, 1); + *cs++ = regLRI; *cs++ = values[v];/* SRM result */
drivers/gpu/drm/i915/gt/selftest_workarounds.c +2
-2@@ -487,8 +488,8 @@ static int check_dirty_whitelist(structi915_gem_context *ctx, } for (v = 0; v < ARRAY_SIZE(values); v++) { /* LRI garbage */ - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = reg; + *cs++ = i915_get_lri_cmd(engine, 1); + *cs++ = regLRI; *cs++ = ~values[v];/* SRM result */
drivers/gpu/drm/i915/gvt/mmio_context.c +1
-1@@ -200,14 +200,14 @@ restore_context_mmio_for_inhibit(structintel_vgpu *vgpu, if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(count); + *cs++ = i915_get_lri_cmd(req->engine, count); for (mmio = gvt->engine_mmio_list.mmio; i915_mmio_reg_valid(mmio->reg); mmio++) {if (
mmio->ring_id!=ring_id||
!mmio->in_context)
continue;- *cs++ =
i915_mmio_reg_offset(mmio->reg);
+ *cs++ =i915_get_lri_reg(req->engine, mmio->reg);
*cs++ =vgpu_vreg_t(vgpu, mmio->reg)|
(mmio->mask<< 16);
gvt_dbg_core("add lri reg pair 0x%x:0x%x in inhibit ctx, vgpu:%d, rind_id:%d\n",drivers/gpu/drm/i915/gvt/mmio_context.c +5
-1@@ -235,7 +235,11 @@ restore_render_mocs_control_for_inhibit(structintel_vgpu *vgpu, if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(GEN9_MOCS_SIZE); + /* + * GEN9_GFX_MOCS is not engine relative, therefore there is no + * need for relative addressing. + */ + *cs++ = __MI_LOAD_REGISTER_IMM(GEN9_MOCS_SIZE); for (index = 0; index < GEN9_MOCS_SIZE; index++) {*cs++ = i915_mmio_reg_offset(GEN9_GFX_MOCS(index));
drivers/gpu/drm/i915/gvt/mmio_context.c +5
-1@@ -262,7 +266,11 @@ restore_render_mocs_l3cc_for_inhibit(structintel_vgpu *vgpu, if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(GEN9_MOCS_SIZE / 2); + /* + * GEN9_LNCFCMOCS is not engine relative, therefore there is no + * need for relative addressing. + */ + *cs++ = __MI_LOAD_REGISTER_IMM(GEN9_MOCS_SIZE / 2); for (index = 0; index < GEN9_MOCS_SIZE / 2; index++) {*cs++ = i915_mmio_reg_offset(GEN9_LNCFCMOCS(index));
drivers/gpu/drm/i915/i915_cmd_parser.c +1
-1@@ -221,7 +221,7 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = { CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ), CMD( MI_SEMAPHORE_MBOX, SMI, !F, 0xFF, R ), CMD( MI_STORE_DWORD_INDEX, SMI, !F, 0xFF, R ), - CMD( MI_LOAD_REGISTER_IMM(1), SMI, !F, 0xFF, W, + CMD( __MI_LOAD_REGISTER_IMM(1), SMI, !F, 0xFF, W, .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 } ), CMD( MI_STORE_REGISTER_MEM, SMI, F, 3, W | B,.reg = { .offset = 1, .mask =
0x007FFFFC},drivers/gpu/drm/i915/i915_cmd_parser.c +1
-1@@ -1183,7 +1183,7 @@ static bool check_cmd(const struct intel_engine_cs *engine, return false; } - if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1) && + if (desc->cmd.value == __MI_LOAD_REGISTER_IMM(1) &&(offset + 2 > length ||
(cmd[offset + 1] ®->mask) !=reg->value)) { DRM_DEBUG_DRIVER("CMD: Rejected LRI to masked register 0x%08X\n",drivers/gpu/drm/i915/i915_gem_context.c +3
-3@@ -1026,11 +1026,11 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data) if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(2); + *cs++ = i915_get_lri_cmd(engine, 2); - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, 0)); + *cs++ = i915_get_lri_reg(engine, GEN8_RING_PDP_UDW(base, 0)); *cs++ = upper_32_bits(pd_daddr); - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, 0)); + *cs++ = i915_get_lri_reg(engine, GEN8_RING_PDP_LDW(base, 0)); *cs++ = lower_32_bits(pd_daddr);*cs++ =
MI_NOOP;drivers/gpu/drm/i915/i915_gem_context.c +3
-3@@ -1040,13 +1040,13 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data) if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(2 * GEN8_3LVL_PDPES); + *cs++ = i915_get_lri_cmd(engine, 2 * GEN8_3LVL_PDPES); for (i = GEN8_3LVL_PDPES; i--; ) { const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i); - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, i)); + *cs++ = i915_get_lri_reg(engine, GEN8_RING_PDP_UDW(base, i)); *cs++ = upper_32_bits(pd_daddr); - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, i)); + *cs++ = i915_get_lri_reg(engine, GEN8_RING_PDP_LDW(base, i));*cs++ =
lower_32_bits(pd_daddr);
}
*cs++ =MI_NOOP;drivers/gpu/drm/i915/i915_gem_execbuffer.c +2
-1@@ -1963,7 +1963,8 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq) if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(4); + /* Gen7 only so no need to support relative offsets */ + *cs++ = __MI_LOAD_REGISTER_IMM(4); for (i = 0; i < 4; i++) { *cs++ = i915_mmio_reg_offset(GEN7_SO_WRITE_OFFSET(i));*cs++ = 0;
drivers/gpu/drm/i915/i915_perf.c +0
-0@@ -1636,7 +1636,8 @@ static void hsw_disable_metric_set(structdrm_i915_private *dev_priv) * in the case that the OA unit has been disabled. */ static void
drivers/gpu/drm/i915/i915_perf.c +2
-1-gen8_update_reg_state_unlocked(struct intel_context *ce, +gen8_update_reg_state_unlocked(struct intel_engine_cs *engine, + struct intel_context *ce,u32
*reg_state,
const structi915_oa_config*oa_config) {drivers/gpu/drm/i915/i915_perf.c +6
-1@@ -1655,7 +1656,12 @@ gen8_update_reg_state_unlocked(structintel_context *ce, }; int i; - CTX_REG(reg_state, ctx_oactxctrl, GEN8_OACTXCONTROL, + /* + * NB: The LRI instruction is generated by the hardware. + * Should we read it in and assert that the offset flag is set? + */ + + CTX_REG(engine, reg_state, ctx_oactxctrl, GEN8_OACTXCONTROL,(
i915->perf.oa.period_exponent<<GEN8_OA_TIMER_PERIOD_SHIFT) | (i915->perf.oa.periodic?GEN8_OA_TIMER_ENABLE: 0) |GEN8_OA_COUNTER_RESUME);drivers/gpu/drm/i915/i915_perf.c +2
-2@@ -1682,10 +1688,10 @@ gen8_update_reg_state_unlocked(structintel_context *ce, } } - CTX_REG(reg_state, state_offset, flex_regs[i], value); + CTX_REG(engine, reg_state, state_offset, flex_regs[i], value); } - CTX_REG(reg_state, + CTX_REG(engine, reg_state, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE, intel_sseu_make_rpcs(i915, &ce->sseu));}
drivers/gpu/drm/i915/i915_perf.c +1
-1@@ -1770,7 +1776,7 @@ static int gen8_configure_all_contexts(structdrm_i915_private *dev_priv, ce->state->obj->mm.dirty = true; regs += LRC_STATE_PN * PAGE_SIZE / sizeof(*regs); - gen8_update_reg_state_unlocked(ce, regs, oa_config); + gen8_update_reg_state_unlocked(dev_priv->engine[RCS0], ce, regs, oa_config);
i915_gem_object_unpin_map(ce->state->obj); }drivers/gpu/drm/i915/i915_perf.c +2
-1@@ -2166,7 +2172,8 @@ void i915_oa_init_reg_state(structintel_engine_cs *engine, stream = engine->i915->perf.oa.exclusive_stream; if (stream) - gen8_update_reg_state_unlocked(ce, regs, stream->oa_config); + gen8_update_reg_state_unlocked(engine, ce, regs, + stream->oa_config); }/**
Signature · 1 line
2.21.0.5.gaeb582a983
Quoted 8 lines
Quoted 4 lines
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Rodrigo Vivi
maintainerQuoted 51 lines · Tvrtko Ursulin
[fixed Chris' email]
Quoted 39 lines · Matthew Brost
Quoted 30 lines · On Mon, May 13, 2019 at 12:45:52PM -0700, [email protected] wrote:
From: John Harrison <[email protected]>
With virtual engines, it is no longer possible to know which specific physical engine a given request will be executed on at the time that request is generated. This means that the request itself must be engine agnostic - any direct register writes must be relative to the engine and not absolute addresses.
The LRI command has support for engine relative addressing. However, the mechanism is not transparent to the driver. The scheme for Gen11 (
MI_LRI_ADD_CS_MMIO_START) requires the LRI address to have no absolute engine base component. The hardware then adds on the correct engine offset at execution time.Due to the non-trivial and differing schemes on different hardware, it is not possible to simply update the code that creates the LRI commands to set a remap flag and let the hardware get on with it. Instead, this patch adds function wrappers for generating the LRI command itself and then for constructing the correct address to use with the LRI.
v2: Fix build break in GVT. Remove flags parameter [review feedback from Chris W].
v3: Fix build break in selftest. Rebase to newer base tree and fix merge conflict.
v4: More rebasing. Rmoved relative addressing support from Gen7-9 only code paths [review feedback from Chris W].
Quoted 7 lines
v5: More rebasing (new 'gt' directory). Fix white space issue. Use COPY class rather than BCS0 id for checking against BCS engine.
Signed-off-by John Harrison <[email protected]>CC Rodrigo Vivi <[email protected]>CC Tvrtko Ursulin <[email protected]>CC Wilson, Chris P <[email protected]>Quoted 7 lines
I've reviewed this series and to me it looks like all the concerns have been
addressed + CI is passing. Do not feel comfortable give a R-B but this patch is
needed for a series I'm working on so I'd like to see it merged. Gentle ping to
get this merged.
Quoted 5 lines
AFAIR the conclusion between Rodrigo and me was to leave the existing macro as is and leave a new one (in uppercase) for relative addressing.
So leave
MI_LOAD_REGISTER_IMMas is, addMI_LOAD_REGISTER_IMM_RELfor usage on relevant (new) paths.
yeap, that's my view as well.
We should be able to do this as simple as possible.
Quoted 703 lines
Chris did not say anything but I expect this would also satisfy his wish to keep the patch as small as possible eg not touch legacy code paths.
Regards,
Tvrtko
Quoted 687 lines
Thanks,
MattQuoted 683 lines
---
drivers/gpu/drm/i915/gt/intel_engine.h | 4 + drivers/gpu/drm/i915/gt/intel_engine_cs.c | 11 +++ drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 6 +- drivers/gpu/drm/i915/gt/intel_lrc.c | 79 ++++++++++--------- drivers/gpu/drm/i915/gt/intel_lrc_reg.h | 4 +- drivers/gpu/drm/i915/gt/intel_mocs.c | 17 ++-- drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 45 +++++++++-- drivers/gpu/drm/i915/gt/intel_workarounds.c | 4 +- .../gpu/drm/i915/gt/selftest_workarounds.c | 9 ++- drivers/gpu/drm/i915/gvt/mmio_context.c | 16 +++- drivers/gpu/drm/i915/i915_cmd_parser.c | 4 +- drivers/gpu/drm/i915/i915_gem_context.c | 12 +-- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 +- drivers/gpu/drm/i915/i915_perf.c | 19 +++--14 files changed, 154 insertions(+), 79 deletions(-)drivers/gpu/drm/i915/gt/intel_engine.h +2
-0@@ -546,4 +546,8 @@ static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)#endif +bool i915_engine_has_relative_lri (const struct intel_engine_cs *engine); +u32 i915_get_lri_cmd(const struct intel_engine_cs *engine, u32
word_count);
+u32i915_get_lri_reg(const struct intel_engine_cs *engine, i915_reg_t reg);
+
#endif /* _INTEL_RINGBUFFER_H_ */drivers/gpu/drm/i915/gt/intel_engine_cs.c +11
-0@@ -253,6 +253,17 @@ static u32 __engine_mmio_base(structdrm_i915_private *i915, return bases[i].base; } +bool i915_engine_has_relative_lri (const struct intel_engine_cs *engine) +{ + if (INTEL_GEN(engine->i915) < 11) + return false; + + if (engine->class == COPY_ENGINE_CLASS) + return false; + + return true; +} +static void
__sprint_engine_name(char *name, const struct engine_info *info)
{
WARN_ON(snprintf(name,INTEL_ENGINE_CS_MAX_NAME, "%s%u",drivers/gpu/drm/i915/gt/intel_gpu_commands.h +0
-0@@ -123,9 +123,13 @@ * simply ignores the register load under certain conditions. * - One can actually load arbitrary many arbitrary registers:Simply issue x
* address/value pairs. Don't overdue it, though, x <= 2^4 must hold!
+ * - Newer hardware supports engine relative addresses but older hardware does
+ * not. So never callMI_LRIdirectly, always use thei915_get_lri_cmd()
+ * andi915_get_lri_reg()helper functions.
*/drivers/gpu/drm/i915/gt/intel_gpu_commands.h +1
-1-#define MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1) +#define __MI_LOAD_REGISTER_IMM (x) MI_INSTR(0x22, 2*(x)-1)#define MI_LRI_FORCE_POSTED (1<<12) +#define MI_LRI_ADD_CS_MMIO_START_GEN11 (1<<19) #define MI_STORE_REGISTER_MEM
MI_INSTR(0x24, 1)#define MI_STORE_REGISTER_MEM_GEN8MI_INSTR(0x24, 2)#define MI_SRM_LRM_GLOBAL_GTT (1<<22)drivers/gpu/drm/i915/gt/intel_lrc.c +4
-3@@ -1388,14 +1388,15 @@ static int emit_pdps(struct i915_request *rq) return PTR_ERR(cs); /* Ensure the LRI have landed before we invalidate & continue */ - *cs++ = MI_LOAD_REGISTER_IMM(2 * GEN8_3LVL_PDPES) |MI_LRI_FORCE_POSTED ; + *cs++ = i915_get_lri_cmd(engine, 2 * GEN8_3LVL_PDPES) | + MI_LRI_FORCE_POSTED; for (i = GEN8_3LVL_PDPES; i--; ) { const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i); u32 base = engine->mmio_base; - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, i)); + *cs++ = i915_get_lri_reg(engine, GEN8_RING_PDP_UDW(base, i)); *cs++ = upper_32_bits(pd_daddr); - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, i)); + *cs++ = i915_get_lri_reg(engine, GEN8_RING_PDP_LDW(base, i)); *cs++ = lower_32_bits(pd_daddr); }*cs++ =
MI_NOOP;drivers/gpu/drm/i915/gt/intel_lrc.c +6
-4@@ -1469,7 +1470,8 @@ gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch) *batch++ = i915_scratch_offset(engine->i915) + 256; *batch++ = 0; - *batch++ = MI_LOAD_REGISTER_IMM(1); + /* Gen8/9 only so no need to support relative offsets */ + *batch++ = __MI_LOAD_REGISTER_IMM(1); *batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4); *batch++ = 0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES;@@ -1540,13 +1542,14 @@ struct lri { u32 value; }; -static u32 *emit_lri (u32 *batch,const struct lri *lri,unsigned int count) +static u32 *emit_lri (struct intel_engine_cs *engine,u32 *batch, + const struct lri *lri, unsigned int count) { GEM_BUG_ON(!count || count > 63); - *batch++ = MI_LOAD_REGISTER_IMM(count); + *batch++ = i915_get_lri_cmd(engine, count); do { - *batch++ = i915_mmio_reg_offset(lri->reg); + *batch++ = i915_get_lri_reg(engine, lri->reg); *batch++ = lri->value; } while (lri++, --count);*batch++ =
MI_NOOP;drivers/gpu/drm/i915/gt/intel_lrc.c +1
-1@@ -1584,7 +1587,7 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) /* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */ batch = gen8_emit_flush_coherentl3_wa(engine, batch); - batch = emit_lri(batch, lri, ARRAY_SIZE(lri)); + batch = emit_lri(engine, batch, lri, ARRAY_SIZE(lri)); /* WaMediaPoolStateCmdInWABB:bxt,glk */if (
HAS_POOLED_EU(engine->i915)) {drivers/gpu/drm/i915/gt/intel_lrc.c +0
-0@@ -2537,10 +2540,10 @@ static void execlists_init_reg_state(u32 *regs, * values (including all the missing MI_LOAD_REGISTER_IMMcommands that
* we are not initializing here).
*/
- regs[CTX_LRI_HEADER_0] =MI_LOAD_REGISTER_IMM(rcs ? 14 : 11)| -MI_LRI_FORCE_POSTED;
+ regs[CTX_LRI_HEADER_0] =i915_get_lri_cmd(engine, rcs ? 14 : 11)| +MI_LRI_FORCE_POSTED;- CTX_REG(regs,
CTX_CONTEXT_CONTROL,RING_CONTEXT_CONTROL(base), + CTX_REG(engine, regs,CTX_CONTEXT_CONTROL,RING_CONTEXT_CONTROL(base),_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT)|_MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH)); if (INTEL_GEN(engine->i915)< 11) {drivers/gpu/drm/i915/gt/intel_lrc.c +0
-0@@ -2548,22 +2551,23 @@ static void execlists_init_reg_state(u32 *regs,
_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT | CTX_CTRL_RS_CTX_ENABLE);
}
-CTX_REG(regs, CTX_RING_HEAD, RING_HEAD(base), 0);
-CTX_REG(regs, CTX_RING_TAIL, RING_TAIL(base), 0);
-CTX_REG(regs, CTX_RING_BUFFER_START, RING_START(base), 0); - CTX_REG(regs,CTX_RING_BUFFER_CONTROL,RING_CTL(base), +CTX_REG(engine, regs, CTX_RING_HEAD, RING_HEAD(base), 0); +CTX_REG(engine, regs, CTX_RING_TAIL, RING_TAIL(base), 0); +CTX_REG(engine, regs, CTX_RING_BUFFER_START, RING_START(base), 0); +CTX_REG(engine, regs, CTX_RING_BUFFER_CONTROL, RING_CTL(base), RING_CTL_SIZE(ring->size) | RING_VALID);
-CTX_REG(regs, CTX_BB_HEAD_U, RING_BBADDR_UDW(base), 0); -CTX_REG(regs, CTX_BB_HEAD_L, RING_BBADDR(base), 0);
-CTX_REG(regs, CTX_BB_STATE, RING_BBSTATE(base), RING_BB_PPGTT); -CTX_REG(regs, CTX_SECOND_BB_HEAD_U, RING_SBBADDR_UDW(base), 0); -CTX_REG(regs, CTX_SECOND_BB_HEAD_L, RING_SBBADDR(base), 0); -CTX_REG(regs, CTX_SECOND_BB_STATE, RING_SBBSTATE(base), 0); +CTX_REG(engine, regs, CTX_BB_HEAD_U, RING_BBADDR_UDW(base), 0); +CTX_REG(engine, regs, CTX_BB_HEAD_L, RING_BBADDR(base), 0); +CTX_REG(engine, regs, CTX_BB_STATE, RING_BBSTATE(base), RING_BB_PPGTT);
+CTX_REG(engine, regs, CTX_SECOND_BB_HEAD_U, RING_SBBADDR_UDW(base), 0);
+CTX_REG(engine, regs, CTX_SECOND_BB_HEAD_L, RING_SBBADDR(base), 0); +CTX_REG(engine, regs, CTX_SECOND_BB_STATE, RING_SBBSTATE(base), 0); if (rcs) {
structi915_ctx_workarounds*wa_ctx=&engine->wa_ctx;-
CTX_REG(regs, CTX_RCS_INDIRECT_CTX, RING_INDIRECT_CTX(base), 0); - CTX_REG(regs,CTX_RCS_INDIRECT_CTX_OFFSET,
+ CTX_REG(engine, regs,CTX_RCS_INDIRECT_CTX,
+RING_INDIRECT_CTX(base), 0);
+CTX_REG(engine, regs, CTX_RCS_INDIRECT_CTX_OFFSET, RING_INDIRECT_CTX_OFFSET(base), 0);
if (wa_ctx->indirect_ctx.size) {
u32ggtt_offset=i915_ggtt_offset(wa_ctx->vma);drivers/gpu/drm/i915/gt/intel_lrc.c +13
-11@@ -2576,7 +2580,8 @@ static void execlists_init_reg_state(u32 *regs, intel_lr_indirect_ctx_offset(engine) << 6; } - CTX_REG(regs, CTX_BB_PER_CTX_PTR, RING_BB_PER_CTX_PTR(base), 0); + CTX_REG(engine, regs, CTX_BB_PER_CTX_PTR, + RING_BB_PER_CTX_PTR(base), 0); if (wa_ctx->per_ctx.size) { u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);@@ -2585,18 +2590,19 @@ static void execlists_init_reg_state(u32 *regs, } } - regs[CTX_LRI_HEADER_1] = MI_LOAD_REGISTER_IMM(9) |MI_LRI_FORCE_POSTED ; + regs[CTX_LRI_HEADER_1] = i915_get_lri_cmd(engine, 9) | + MI_LRI_FORCE_POSTED; - CTX_REG(regs, CTX_CTX_TIMESTAMP, RING_CTX_TIMESTAMP(base), 0); + CTX_REG(engine, regs, CTX_CTX_TIMESTAMP,RING_CTX_TIMESTAMP (base),0 ); /* PDP values well be assigned later if needed */ - CTX_REG(regs, CTX_PDP3_UDW, GEN8_RING_PDP_UDW(base, 3), 0); - CTX_REG(regs, CTX_PDP3_LDW, GEN8_RING_PDP_LDW(base, 3), 0); - CTX_REG(regs, CTX_PDP2_UDW, GEN8_RING_PDP_UDW(base, 2), 0); - CTX_REG(regs, CTX_PDP2_LDW, GEN8_RING_PDP_LDW(base, 2), 0); - CTX_REG(regs, CTX_PDP1_UDW, GEN8_RING_PDP_UDW(base, 1), 0); - CTX_REG(regs, CTX_PDP1_LDW, GEN8_RING_PDP_LDW(base, 1), 0); - CTX_REG(regs, CTX_PDP0_UDW, GEN8_RING_PDP_UDW(base, 0), 0); - CTX_REG(regs, CTX_PDP0_LDW, GEN8_RING_PDP_LDW(base, 0), 0); + CTX_REG(engine, regs, CTX_PDP3_UDW, GEN8_RING_PDP_UDW(base, 3), 0); + CTX_REG(engine, regs, CTX_PDP3_LDW, GEN8_RING_PDP_LDW(base, 3), 0); + CTX_REG(engine, regs, CTX_PDP2_UDW, GEN8_RING_PDP_UDW(base, 2), 0); + CTX_REG(engine, regs, CTX_PDP2_LDW, GEN8_RING_PDP_LDW(base, 2), 0); + CTX_REG(engine, regs, CTX_PDP1_UDW, GEN8_RING_PDP_UDW(base, 1), 0); + CTX_REG(engine, regs, CTX_PDP1_LDW, GEN8_RING_PDP_LDW(base, 1), 0); + CTX_REG(engine, regs, CTX_PDP0_UDW, GEN8_RING_PDP_UDW(base, 0), 0); + CTX_REG(engine, regs, CTX_PDP0_LDW, GEN8_RING_PDP_LDW(base, 0), 0);if (
i915_vm_is_4lvl(&ppgtt->vm)) {
/* 64b PPGTT (48bit canonical)drivers/gpu/drm/i915/gt/intel_lrc.c +3
-2@@ -2612,8 +2618,9 @@ static void execlists_init_reg_state(u32 *regs, } if (rcs) { - regs[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1); - CTX_REG(regs, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE, 0); + regs[CTX_LRI_HEADER_2] = i915_get_lri_cmd(engine, 1); + CTX_REG(engine, regs, CTX_R_PWR_CLK_STATE, + GEN8_R_PWR_CLK_STATE, 0); i915_oa_init_reg_state(engine, ce, regs); }drivers/gpu/drm/i915/gt/intel_lrc_reg.h +2
-2@@ -39,10 +39,10 @@#define CTX_R_PWR_CLK_STATE 0x42#define CTX_END 0x44 -#define CTX_REG (reg_state, pos, reg, val) do { \ +#define CTX_REG (engine, reg_state, pos, reg, val) do { \ u32 *reg_state__ = (reg_state); \ const u32 pos__ = (pos); \ - (reg_state__)[(pos__) + 0] = i915_mmio_reg_offset(reg); \ + (reg_state__)[(pos__) + 0] = i915_get_lri_reg((engine), (reg)); \ (reg_state__)[(pos__) + 1] = (val); \ } while (0)drivers/gpu/drm/i915/gt/intel_mocs.c +0
-3@@ -324,9 +324,6 @@ static u32 get_entry_control(const structdrm_i915_mocs_table *table,/** * intel_mocs_init_engine() - emit the mocs control table * @engine: The engine for whom to emit the registers. -* -* This function simply emits a MI_LOAD_REGISTER_IMM command for the -* given table starting at the given address. */ void intel_mocs_init_engine(struct intel_engine_cs *engine){
drivers/gpu/drm/i915/gt/intel_mocs.c +10
-4@@ -380,18 +377,20 @@ static int emit_mocs_control_table(structi915_request *rq, if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(table->n_entries); + *cs++ = i915_get_lri_cmd(rq->engine, table->n_entries); for (index = 0; index < table->size; index++) { u32 value = get_entry_control(table, index); - *cs++ = i915_mmio_reg_offset(mocs_register(engine, index)); + *cs++ = i915_get_lri_reg(rq->engine, + mocs_register(engine, index)); *cs++ = value; } /* All remaining entries are also unused */ for (; index < table->n_entries; index++) { - *cs++ = i915_mmio_reg_offset(mocs_register(engine, index)); + *cs++ = i915_get_lri_reg(rq->engine, + mocs_register(engine, index)); *cs++ = unused_value; }@@ -449,7 +448,11 @@ static int emit_mocs_l3cc_table(structi915_request *rq, if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(table->n_entries / 2); + /* + * GEN9_LNCFCMOCS is not engine relative, therefore there is no + * need for relative addressing? + */ + *cs++ = __MI_LOAD_REGISTER_IMM(table->n_entries / 2); for (i = 0; i < table->size / 2; i++) {u16 low =
get_entry_l3cc(table, 2 * i);drivers/gpu/drm/i915/gt/intel_ringbuffer.c +5
-4@@ -1516,12 +1516,13 @@ static int load_pd_dir(struct i915_request *rq, if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = i915_mmio_reg_offset(RING_PP_DIR_DCLV(engine->mmio_base)); + /* Can these not be merged into a single LRI??? */ + *cs++ = i915_get_lri_cmd(engine, 1); + *cs++ = i915_get_lri_reg(engine,RING_PP_DIR_DCLV (engine->mmio_base)); *cs++ = PP_DIR_DCLV_2G; - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine->mmio_base)); + *cs++ = i915_get_lri_cmd(engine, 1); + *cs++ = i915_get_lri_reg(engine,RING_PP_DIR_BASE (engine->mmio_base)); *cs++ = ppgtt->pd.base.ggtt_offset << 10;intel_ring_advance(rq, cs);
drivers/gpu/drm/i915/gt/intel_ringbuffer.c +5
-1@@ -1589,7 +1590,11 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) if (num_engines) { struct intel_engine_cs *signaller; - *cs++ = MI_LOAD_REGISTER_IMM(num_engines); + /* + * Must use absolute engine address as the register + * write is targeting a different engine. + */ + *cs++ = __MI_LOAD_REGISTER_IMM(num_engines); for_each_engine(signaller, i915, id) { if (signaller == engine)continue;
drivers/gpu/drm/i915/gt/intel_ringbuffer.c +0
-0@@ -1643,7 +1648,11 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) struct intel_engine_cs *signaller;
i915_reg_tlast_reg= {}; /* keep gcc quiet */- *cs++ =
MI_LOAD_REGISTER_IMM(num_engines); + /*
+ * Must use absolute engine address as the register + * write is targeting a different engine. + */
+ *cs++ =__MI_LOAD_REGISTER_IMM(num_engines);for_each_engine(signaller, i915, id){
if (signaller == engine)
continue;drivers/gpu/drm/i915/gt/intel_ringbuffer.c +0
-0@@ -1687,9 +1696,9 @@ static int remap_l3(struct i915_request *rq, int slice) * here because no other code should access these registersother than
* at initialization time.
*/
- *cs++ =MI_LOAD_REGISTER_IMM(GEN7_L3LOG_SIZE/4);
+ *cs++ =i915_get_lri_cmd(rq->engine, GEN7_L3LOG_SIZE/4); for (i = 0; i < GEN7_L3LOG_SIZE/4; i++) {
- *cs++ =i915_mmio_reg_offset(GEN7_L3LOG(slice, i)); + *cs++ =i915_get_lri_reg(rq->engine, GEN7_L3LOG(slice, i)); *cs++ = remap_info[i];
}
*cs++ =MI_NOOP;drivers/gpu/drm/i915/gt/intel_ringbuffer.c +0
-0@@ -2335,3 +2344,23 @@ int intel_ring_submission_init(struct intel_engine_cs *engine) intel_engine_cleanup_common(engine); return err;}
drivers/gpu/drm/i915/gt/intel_ringbuffer.c +2
-0+ +u32 i915_get_lri_cmd(const struct intel_engine_cs *engine, u32
word_count)drivers/gpu/drm/i915/gt/intel_ringbuffer.c +12
-0+{ + u32 word; + + word = __MI_LOAD_REGISTER_IMM(word_count); + + if (i915_engine_has_relative_lri(engine)) + word |= MI_LRI_ADD_CS_MMIO_START_GEN11; + + return word; +} + +u32 i915_get_lri_reg(const struct intel_engine_cs *engine,
i915_reg_treg)drivers/gpu/drm/i915/gt/intel_ringbuffer.c +6
-0+{ + if (!i915_engine_has_relative_lri(engine)) + return i915_mmio_reg_offset(reg); + + return i915_mmio_reg_offset(reg) - engine->mmio_base; +}drivers/gpu/drm/i915/gt/intel_workarounds.c +2
-2@@ -625,9 +625,9 @@ int intel_engine_emit_ctx_wa(struct i915_request *rq) if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(wal->count); + *cs++ = i915_get_lri_cmd(rq->engine, wal->count); for (i = 0, wa = wal->list; i < wal->count; i++, wa++) { - *cs++ = i915_mmio_reg_offset(wa->reg); + *cs++ = i915_get_lri_reg(rq->engine, wa->reg); *cs++ = wa->val; } *cs++ = MI_NOOP;drivers/gpu/drm/i915/gt/selftest_workarounds.c +1
-0@@ -442,6 +442,7 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx, for (i = 0; i < engine->whitelist.count; i++) { u32 reg = i915_mmio_reg_offset(engine->whitelist.list[i].reg); + u32 regLRI = i915_get_lri_reg(engine, engine->whitelist.list[i].reg); u64 addr = scratch->node.start;struct
i915_request*rq;
u32 srm, lrm, rsvd;drivers/gpu/drm/i915/gt/selftest_workarounds.c +2
-2@@ -474,8 +475,8 @@ static int check_dirty_whitelist(structi915_gem_context *ctx, idx = 1; for (v = 0; v < ARRAY_SIZE(values); v++) { /* LRI garbage */ - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = reg; + *cs++ = i915_get_lri_cmd(engine, 1); + *cs++ = regLRI; *cs++ = values[v];/* SRM result */
drivers/gpu/drm/i915/gt/selftest_workarounds.c +2
-2@@ -487,8 +488,8 @@ static int check_dirty_whitelist(structi915_gem_context *ctx, } for (v = 0; v < ARRAY_SIZE(values); v++) { /* LRI garbage */ - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = reg; + *cs++ = i915_get_lri_cmd(engine, 1); + *cs++ = regLRI; *cs++ = ~values[v];/* SRM result */
drivers/gpu/drm/i915/gvt/mmio_context.c +1
-1@@ -200,14 +200,14 @@ restore_context_mmio_for_inhibit(structintel_vgpu *vgpu, if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(count); + *cs++ = i915_get_lri_cmd(req->engine, count); for (mmio = gvt->engine_mmio_list.mmio; i915_mmio_reg_valid(mmio->reg); mmio++) {if (
mmio->ring_id!=ring_id||
!mmio->in_context)
continue;- *cs++ =
i915_mmio_reg_offset(mmio->reg);
+ *cs++ =i915_get_lri_reg(req->engine, mmio->reg); *cs++ =vgpu_vreg_t(vgpu, mmio->reg)| (mmio->mask<< 16);
gvt_dbg_core("add lri reg pair 0x%x:0x%x in inhibit ctx, vgpu:%d, rind_id:%d\n",drivers/gpu/drm/i915/gvt/mmio_context.c +5
-1@@ -235,7 +235,11 @@ restore_render_mocs_control_for_inhibit(structintel_vgpu *vgpu, if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(GEN9_MOCS_SIZE); + /* + * GEN9_GFX_MOCS is not engine relative, therefore there is no + * need for relative addressing. + */ + *cs++ = __MI_LOAD_REGISTER_IMM(GEN9_MOCS_SIZE); for (index = 0; index < GEN9_MOCS_SIZE; index++) {*cs++ = i915_mmio_reg_offset(GEN9_GFX_MOCS(index));
drivers/gpu/drm/i915/gvt/mmio_context.c +5
-1@@ -262,7 +266,11 @@ restore_render_mocs_l3cc_for_inhibit(structintel_vgpu *vgpu, if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(GEN9_MOCS_SIZE / 2); + /* + * GEN9_LNCFCMOCS is not engine relative, therefore there is no + * need for relative addressing. + */ + *cs++ = __MI_LOAD_REGISTER_IMM(GEN9_MOCS_SIZE / 2); for (index = 0; index < GEN9_MOCS_SIZE / 2; index++) {*cs++ = i915_mmio_reg_offset(GEN9_LNCFCMOCS(index));
drivers/gpu/drm/i915/i915_cmd_parser.c +1
-1@@ -221,7 +221,7 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = { CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ), CMD( MI_SEMAPHORE_MBOX, SMI, !F, 0xFF, R ), CMD( MI_STORE_DWORD_INDEX, SMI, !F, 0xFF, R ), - CMD( MI_LOAD_REGISTER_IMM(1), SMI, !F, 0xFF, W, + CMD( __MI_LOAD_REGISTER_IMM(1), SMI, !F, 0xFF, W, .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 } ), CMD( MI_STORE_REGISTER_MEM, SMI, F, 3, W | B,.reg = { .offset = 1, .mask =
0x007FFFFC},drivers/gpu/drm/i915/i915_cmd_parser.c +1
-1@@ -1183,7 +1183,7 @@ static bool check_cmd(const struct intel_engine_cs *engine, return false; } - if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1) && + if (desc->cmd.value == __MI_LOAD_REGISTER_IMM(1) &&(offset + 2 > length ||
(cmd[offset + 1] ®->mask) !=reg->value)) { DRM_DEBUG_DRIVER("CMD: Rejected LRI to masked register 0x%08X\n",drivers/gpu/drm/i915/i915_gem_context.c +3
-3@@ -1026,11 +1026,11 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data) if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(2); + *cs++ = i915_get_lri_cmd(engine, 2); - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, 0)); + *cs++ = i915_get_lri_reg(engine, GEN8_RING_PDP_UDW(base, 0)); *cs++ = upper_32_bits(pd_daddr); - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, 0)); + *cs++ = i915_get_lri_reg(engine, GEN8_RING_PDP_LDW(base, 0)); *cs++ = lower_32_bits(pd_daddr);*cs++ =
MI_NOOP;drivers/gpu/drm/i915/i915_gem_context.c +3
-3@@ -1040,13 +1040,13 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data) if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(2 * GEN8_3LVL_PDPES); + *cs++ = i915_get_lri_cmd(engine, 2 * GEN8_3LVL_PDPES); for (i = GEN8_3LVL_PDPES; i--; ) { const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i); - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, i)); + *cs++ = i915_get_lri_reg(engine,GEN8_RING_PDP_UDW (base, i)); *cs++ = upper_32_bits(pd_daddr); - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, i)); + *cs++ = i915_get_lri_reg(engine,GEN8_RING_PDP_LDW (base, i));*cs++ =
lower_32_bits(pd_daddr);
}
*cs++ =MI_NOOP;drivers/gpu/drm/i915/i915_gem_execbuffer.c +2
-1@@ -1963,7 +1963,8 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq) if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(4); + /* Gen7 only so no need to support relative offsets */ + *cs++ = __MI_LOAD_REGISTER_IMM(4); for (i = 0; i < 4; i++) { *cs++ = i915_mmio_reg_offset(GEN7_SO_WRITE_OFFSET(i));*cs++ = 0;
drivers/gpu/drm/i915/i915_perf.c +0
-0@@ -1636,7 +1636,8 @@ static void hsw_disable_metric_set(structdrm_i915_private *dev_priv) * in the case that the OA unit has been disabled. */ static void
drivers/gpu/drm/i915/i915_perf.c +2
-1-gen8_update_reg_state_unlocked(struct intel_context *ce, +gen8_update_reg_state_unlocked(struct intel_engine_cs *engine, + struct intel_context *ce,u32
*reg_state,
const structi915_oa_config*oa_config) {drivers/gpu/drm/i915/i915_perf.c +6
-1@@ -1655,7 +1656,12 @@ gen8_update_reg_state_unlocked(structintel_context *ce, }; int i; - CTX_REG(reg_state, ctx_oactxctrl, GEN8_OACTXCONTROL, + /* + * NB: The LRI instruction is generated by the hardware. + * Should we read it in and assert that the offset flag is set? + */ + + CTX_REG(engine, reg_state, ctx_oactxctrl, GEN8_OACTXCONTROL,(
i915->perf.oa.period_exponent<<GEN8_OA_TIMER_PERIOD_SHIFT) | (i915->perf.oa.periodic?GEN8_OA_TIMER_ENABLE: 0) |GEN8_OA_COUNTER_RESUME);drivers/gpu/drm/i915/i915_perf.c +2
-2@@ -1682,10 +1688,10 @@ gen8_update_reg_state_unlocked(structintel_context *ce, } } - CTX_REG(reg_state, state_offset, flex_regs[i], value); + CTX_REG(engine, reg_state, state_offset, flex_regs[i], value); } - CTX_REG(reg_state, + CTX_REG(engine, reg_state, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE, intel_sseu_make_rpcs(i915, &ce->sseu));}
drivers/gpu/drm/i915/i915_perf.c +1
-1@@ -1770,7 +1776,7 @@ static int gen8_configure_all_contexts(structdrm_i915_private *dev_priv, ce->state->obj->mm.dirty = true; regs += LRC_STATE_PN * PAGE_SIZE / sizeof(*regs); - gen8_update_reg_state_unlocked(ce, regs, oa_config); + gen8_update_reg_state_unlocked(dev_priv->engine[RCS0], ce, regs, oa_config);
i915_gem_object_unpin_map(ce->state->obj); }drivers/gpu/drm/i915/i915_perf.c +2
-1@@ -2166,7 +2172,8 @@ void i915_oa_init_reg_state(structintel_engine_cs *engine, stream = engine->i915->perf.oa.exclusive_stream; if (stream) - gen8_update_reg_state_unlocked(ce, regs, stream->oa_config); + gen8_update_reg_state_unlocked(engine, ce, regs, + stream->oa_config); }/**
Signature · 1 line
2.21.0.5.gaeb582a983Quoted 8 lines
Quoted 4 lines
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
Quoted 4 lines
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx