From 2b5298b0aa09be3d789052107cb864603b88bc93 Mon Sep 17 00:00:00 2001 From: Caz Yokoyama Date: Wed, 24 Mar 2021 13:04:59 -0700 Subject: drm/i915/gen12: Add recommended hardware tuning value Follow Bspec 31870 to set recommended tuning values for certain GT register. These values aren't workarounds per-se, but it's best to handle them in the same general area of the driver, especially since there may be real workarounds that update other bits of the same registers. At the moment the only value we need to worry about is the TDS_TIMER setting in FF_MODE2. This setting was previously described as "Wa_1604555607" on some platforms, but the spec tells us that we should continue to program this on all current gen12 platforms, even those that do not have that WA. Bspec: 31870 v2: Rephrase some comments to make them clearer (Matt) Cc: Clinton Taylor Signed-off-by: Caz Yokoyama Signed-off-by: Lucas De Marchi Reviewed-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20210324200502.1731265-2-lucas.demarchi@intel.com --- drivers/gpu/drm/i915/gt/intel_workarounds.c | 48 ++++++++++++++++++++++------- 1 file changed, 37 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 2c6f7217469f..25785b46d1e4 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -607,9 +607,38 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU); } +/* + * These settings aren't actually workarounds, but general tuning settings that + * need to be programmed on several platforms. + */ +static void gen12_ctx_gt_tuning_init(struct intel_engine_cs *engine, + struct i915_wa_list *wal) +{ + /* + * Although some platforms refer to it as Wa_1604555607, we need to + * program it even on those that don't explicitly list that + * workaround. + * + * Note that the programming of this register is further modified + * according to the FF_MODE2 guidance given by Wa_1608008084:gen12. + * Wa_1608008084 tells us the FF_MODE2 register will return the wrong + * value when read. The default value for this register is zero for all + * fields and there are no bit masks. So instead of doing a RMW we + * should just write TDS timer value. For the same reason read + * verification is ignored. + */ + wa_add(wal, + FF_MODE2, + FF_MODE2_TDS_TIMER_MASK, + FF_MODE2_TDS_TIMER_128, + 0); +} + static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { + gen12_ctx_gt_tuning_init(engine, wal); + /* * Wa_1409142259:tgl * Wa_1409347922:tgl @@ -636,19 +665,15 @@ static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine, gen12_ctx_workarounds_init(engine, wal); /* - * Wa_1604555607:tgl,rkl + * Wa_16011163337 * - * Note that the implementation of this workaround is further modified - * according to the FF_MODE2 guidance given by Wa_1608008084:gen12. - * FF_MODE2 register will return the wrong value when read. The default - * value for this register is zero for all fields and there are no bit - * masks. So instead of doing a RMW we should just write the GS Timer - * and TDS timer values for Wa_1604555607 and Wa_16011163337. + * Like in gen12_ctx_gt_tuning_init(), read verification is ignored due + * to Wa_1608008084. */ wa_add(wal, FF_MODE2, - FF_MODE2_GS_TIMER_MASK | FF_MODE2_TDS_TIMER_MASK, - FF_MODE2_GS_TIMER_224 | FF_MODE2_TDS_TIMER_128, + FF_MODE2_GS_TIMER_MASK, + FF_MODE2_GS_TIMER_224, 0); } @@ -668,12 +693,13 @@ static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine, /* * Wa_16011163337 * - * Like in tgl_ctx_workarounds_init(), read verification is ignored due + * Like in gen12_ctx_gt_tuning_init(), read verification is ignored due * to Wa_1608008084. */ wa_add(wal, FF_MODE2, - FF_MODE2_GS_TIMER_MASK, FF_MODE2_GS_TIMER_224, 0); + FF_MODE2_GS_TIMER_MASK, + FF_MODE2_GS_TIMER_224, 0); } static void -- cgit 1.4.1 From 503c7ef3b47d7c4274e01d0703ef2d987284716b Mon Sep 17 00:00:00 2001 From: Caz Yokoyama Date: Wed, 24 Mar 2021 13:05:00 -0700 Subject: drm/i915/icl: add Wa_22010271021 for all gen11 Wa_22010271021 does not apply only to EHL, but to all gen11 and other gen12 platforms. Gen12 is already covered in another code path, but we need to stop checking for EHL when handling gen11. Bspec: 33450, 52887 v2: Remove "gen11" suffix as it also applies to gen12 platforms Cc: Clinton Taylor Signed-off-by: Caz Yokoyama Signed-off-by: Lucas De Marchi Reviewed-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20210324200502.1731265-3-lucas.demarchi@intel.com --- drivers/gpu/drm/i915/gt/intel_workarounds.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 25785b46d1e4..30b902fade1d 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -1781,11 +1781,10 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN7_FF_THREAD_MODE, GEN12_FF_TESSELATION_DOP_GATE_DISABLE); - /* Wa_22010271021:ehl */ - if (IS_JSL_EHL(i915)) - wa_masked_en(wal, - GEN9_CS_DEBUG_MODE1, - FF_DOP_CLOCK_GATE_DISABLE); + /* Wa_22010271021 */ + wa_masked_en(wal, + GEN9_CS_DEBUG_MODE1, + FF_DOP_CLOCK_GATE_DISABLE); } if (IS_GEN_RANGE(i915, 9, 12)) { -- cgit 1.4.1 From 0a6b3d35c033b340f0bb1f6d3236ebdb953020ac Mon Sep 17 00:00:00 2001 From: José Roberto de Souza Date: Wed, 24 Mar 2021 13:05:01 -0700 Subject: drm/i915: Move Wa_16011163337 to gen12_ctx_workarounds_init() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This WA is needed in all gen12 platforms, moving it to gen12_ctx_workarounds_init() allow us to remove the duplicated implementation. Also allow us to remove the tgl_ctx_workarounds_init() that after the WA move above was empty. Signed-off-by: José Roberto de Souza Reviewed-by: Lucas De Marchi Signed-off-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20210324200502.1731265-4-lucas.demarchi@intel.com --- drivers/gpu/drm/i915/gt/intel_workarounds.c | 20 -------------------- 1 file changed, 20 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 30b902fade1d..38a2813220b9 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -657,12 +657,6 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine, wa_masked_field_set(wal, GEN8_CS_CHICKEN1, GEN9_PREEMPT_GPGPU_LEVEL_MASK, GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL); -} - -static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine, - struct i915_wa_list *wal) -{ - gen12_ctx_workarounds_init(engine, wal); /* * Wa_16011163337 @@ -689,17 +683,6 @@ static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine, /* Wa_22010493298 */ wa_masked_en(wal, HIZ_CHICKEN, DG1_HZ_READ_SUPPRESSION_OPTIMIZATION_DISABLE); - - /* - * Wa_16011163337 - * - * Like in gen12_ctx_gt_tuning_init(), read verification is ignored due - * to Wa_1608008084. - */ - wa_add(wal, - FF_MODE2, - FF_MODE2_GS_TIMER_MASK, - FF_MODE2_GS_TIMER_224, 0); } static void @@ -716,9 +699,6 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine, if (IS_DG1(i915)) dg1_ctx_workarounds_init(engine, wal); - else if (IS_ALDERLAKE_S(i915) || IS_ROCKETLAKE(i915) || - IS_TIGERLAKE(i915)) - tgl_ctx_workarounds_init(engine, wal); else if (IS_GEN(i915, 12)) gen12_ctx_workarounds_init(engine, wal); else if (IS_GEN(i915, 11)) -- cgit 1.4.1 From cade4696ff8dadf5521eba0d92abad20c20097e1 Mon Sep 17 00:00:00 2001 From: Swathi Dhanavanthri Date: Wed, 24 Mar 2021 13:05:02 -0700 Subject: drm/i915: Add Wa_14011060649 This is a permanent workaround for TGL,RKL,DG1 and ADLS. Signed-off-by: Swathi Dhanavanthri Reviewed-by: Lucas De Marchi Signed-off-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20210324200502.1731265-5-lucas.demarchi@intel.com --- drivers/gpu/drm/i915/gt/intel_workarounds.c | 26 ++++++++++++++++++++++++++ drivers/gpu/drm/i915/i915_reg.h | 3 +++ 2 files changed, 29 insertions(+) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 38a2813220b9..5a03a76bb9e2 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -1084,11 +1084,37 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS); } +/* + * Though there are per-engine instances of these registers, + * they retain their value through engine resets and should + * only be provided on the GT workaround list rather than + * the engine-specific workaround list. + */ +static void +wa_14011060649(struct drm_i915_private *i915, struct i915_wa_list *wal) +{ + struct intel_engine_cs *engine; + struct intel_gt *gt = &i915->gt; + int id; + + for_each_engine(engine, gt, id) { + if (engine->class != VIDEO_DECODE_CLASS || + (engine->instance % 2)) + continue; + + wa_write_or(wal, VDBOX_CGCTL3F10(engine->mmio_base), + IECPUNIT_CLKGATE_DIS); + } +} + static void gen12_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) { wa_init_mcr(i915, wal); + + /* Wa_14011060649:tgl,rkl,dg1,adls */ + wa_14011060649(i915, wal); } static void diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index cbf7a60afe54..e087bcd21911 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2715,6 +2715,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define RING_INDIRECT_CTX_OFFSET(base) _MMIO((base) + 0x1c8) /* gen8+ */ #define RING_CTX_TIMESTAMP(base) _MMIO((base) + 0x3a8) /* gen8+ */ +#define VDBOX_CGCTL3F10(base) _MMIO((base) + 0x3f10) +#define IECPUNIT_CLKGATE_DIS REG_BIT(22) + #define ERROR_GEN6 _MMIO(0x40a0) #define GEN7_ERR_INT _MMIO(0x44040) #define ERR_INT_POISON (1 << 31) -- cgit 1.4.1 From f7c379779161d364eb30338529490eac7dc377b7 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Fri, 26 Mar 2021 10:57:59 +0000 Subject: drm/i915: Take request reference before arming the watchdog timer Reference needs to be taken before arming the timer. Luckily, given the default timer period of 20s, the potential to hit the race is extremely unlikely. Signed-off-by: Tvrtko Ursulin Fixes: 9b4d0598ee94 ("drm/i915: Request watchdog infrastructure") Cc: Daniel Vetter Reviewed-by: Mika Kuoppala Link: https://patchwork.freedesktop.org/patch/msgid/20210326105759.2387104-1-tvrtko.ursulin@linux.intel.com --- drivers/gpu/drm/i915/i915_request.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 9165971c3c47..bec9c3652188 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -350,6 +350,8 @@ static void __rq_arm_watchdog(struct i915_request *rq) if (!ce->watchdog.timeout_us) return; + i915_request_get(rq); + hrtimer_init(&wdg->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); wdg->timer.function = __rq_watchdog_expired; hrtimer_start_range_ns(&wdg->timer, @@ -357,7 +359,6 @@ static void __rq_arm_watchdog(struct i915_request *rq) NSEC_PER_USEC), NSEC_PER_MSEC, HRTIMER_MODE_REL); - i915_request_get(rq); } static void __rq_cancel_watchdog(struct i915_request *rq) -- cgit 1.4.1 From 399cd9797052f5732f7e1db89d15a05bca712be1 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Wed, 31 Mar 2021 11:18:50 +0100 Subject: drm/i915/pmu: Check actual RC6 status RC6 support cannot be simply established by looking at the static device HAS_RC6() flag. There are cases which disable RC6 at driver load time so use the status of those check when deciding whether to enumerate the rc6 counter. Signed-off-by: Tvrtko Ursulin Reported-by: Eero T Tamminen Reviewed-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20210331101850.2582027-1-tvrtko.ursulin@linux.intel.com --- drivers/gpu/drm/i915/i915_pmu.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 41651ac255fa..a75cd1db320b 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -476,6 +476,8 @@ engine_event_status(struct intel_engine_cs *engine, static int config_status(struct drm_i915_private *i915, u64 config) { + struct intel_gt *gt = &i915->gt; + switch (config) { case I915_PMU_ACTUAL_FREQUENCY: if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) @@ -489,7 +491,7 @@ config_status(struct drm_i915_private *i915, u64 config) case I915_PMU_INTERRUPTS: break; case I915_PMU_RC6_RESIDENCY: - if (!HAS_RC6(i915)) + if (!gt->rc6.supported) return -ENODEV; break; case I915_PMU_SOFTWARE_GT_AWAKE_TIME: -- cgit 1.4.1 From 2ef6a01fb636997bfec57b015d4e4b5a745ef38a Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Mon, 19 Apr 2021 11:57:38 +0100 Subject: drm/i915/uapi: fix kernel doc warnings Fix the cases where it is almost already valid kernel doc, for the others just nerf the warnings for now. Signed-off-by: Matthew Auld Cc: Joonas Lahtinen Cc: Jordan Justen Cc: Daniel Vetter Cc: Kenneth Graunke Cc: Jason Ekstrand Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Cc: mesa-dev@lists.freedesktop.org Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210419105741.27844-1-matthew.auld@intel.com --- include/uapi/drm/i915_drm.h | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index ddc47bbf48b6..92da48e935d1 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -1054,12 +1054,12 @@ struct drm_i915_gem_exec_fence { __u32 flags; }; -/** +/* * See drm_i915_gem_execbuffer_ext_timeline_fences. */ #define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0 -/** +/* * This structure describes an array of drm_syncobj and associated points for * timeline variants of drm_syncobj. It is invalid to append this structure to * the execbuf if I915_EXEC_FENCE_ARRAY is set. @@ -1700,7 +1700,7 @@ struct drm_i915_gem_context_param { __u64 value; }; -/** +/* * Context SSEU programming * * It may be necessary for either functional or performance reason to configure @@ -2067,7 +2067,7 @@ struct drm_i915_perf_open_param { __u64 properties_ptr; }; -/** +/* * Enable data capture for a stream that was either opened in a disabled state * via I915_PERF_FLAG_DISABLED or was later disabled via * I915_PERF_IOCTL_DISABLE. @@ -2081,7 +2081,7 @@ struct drm_i915_perf_open_param { */ #define I915_PERF_IOCTL_ENABLE _IO('i', 0x0) -/** +/* * Disable data capture for a stream. * * It is an error to try and read a stream that is disabled. @@ -2090,7 +2090,7 @@ struct drm_i915_perf_open_param { */ #define I915_PERF_IOCTL_DISABLE _IO('i', 0x1) -/** +/* * Change metrics_set captured by a stream. * * If the stream is bound to a specific context, the configuration change @@ -2103,7 +2103,7 @@ struct drm_i915_perf_open_param { */ #define I915_PERF_IOCTL_CONFIG _IO('i', 0x2) -/** +/* * Common to all i915 perf records */ struct drm_i915_perf_record_header { @@ -2151,7 +2151,7 @@ enum drm_i915_perf_record_type { DRM_I915_PERF_RECORD_MAX /* non-ABI */ }; -/** +/* * Structure to upload perf dynamic configuration into the kernel. */ struct drm_i915_perf_oa_config { @@ -2292,21 +2292,21 @@ struct drm_i915_query_topology_info { * Describes one engine and it's capabilities as known to the driver. */ struct drm_i915_engine_info { - /** Engine class and instance. */ + /** @engine: Engine class and instance. */ struct i915_engine_class_instance engine; - /** Reserved field. */ + /** @rsvd0: Reserved field. */ __u32 rsvd0; - /** Engine flags. */ + /** @flags: Engine flags. */ __u64 flags; - /** Capabilities of this engine. */ + /** @capabilities: Capabilities of this engine. */ __u64 capabilities; #define I915_VIDEO_CLASS_CAPABILITY_HEVC (1 << 0) #define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC (1 << 1) - /** Reserved fields. */ + /** @rsvd1: Reserved fields. */ __u64 rsvd1[4]; }; @@ -2317,13 +2317,13 @@ struct drm_i915_engine_info { * an array of struct drm_i915_engine_info structures. */ struct drm_i915_query_engine_info { - /** Number of struct drm_i915_engine_info structs following. */ + /** @num_engines: Number of struct drm_i915_engine_info structs following. */ __u32 num_engines; - /** MBZ */ + /** @rsvd: MBZ */ __u32 rsvd[3]; - /** Marker for drm_i915_engine_info structures. */ + /** @engines: Marker for drm_i915_engine_info structures. */ struct drm_i915_engine_info engines[]; }; -- cgit 1.4.1 From 19d053d477a145069bc2c38b28dcee773690c804 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Mon, 19 Apr 2021 11:57:40 +0100 Subject: drm/i915/uapi: convert i915_user_extension to kernel doc Add some example usage for the extension chaining also, which is quite nifty. v2: (Daniel) - clarify that the name is just some integer, also document that the name space is not global v3: prefer kernel-doc references for structs Suggested-by: Daniel Vetter Signed-off-by: Matthew Auld Cc: Joonas Lahtinen Cc: Jordan Justen Cc: Daniel Vetter Cc: Kenneth Graunke Cc: Jason Ekstrand Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Cc: mesa-dev@lists.freedesktop.org Reviewed-by: Daniel Vetter Reviewed-by: Jason Ekstrand Link: https://patchwork.freedesktop.org/patch/msgid/20210419105741.27844-3-matthew.auld@intel.com --- include/uapi/drm/i915_drm.h | 54 +++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 50 insertions(+), 4 deletions(-) diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 92da48e935d1..e2867d8cd5e3 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -62,8 +62,8 @@ extern "C" { #define I915_ERROR_UEVENT "ERROR" #define I915_RESET_UEVENT "RESET" -/* - * i915_user_extension: Base class for defining a chain of extensions +/** + * struct i915_user_extension - Base class for defining a chain of extensions * * Many interfaces need to grow over time. In most cases we can simply * extend the struct and have userspace pass in more data. Another option, @@ -76,12 +76,58 @@ extern "C" { * increasing complexity, and for large parts of that interface to be * entirely optional. The downside is more pointer chasing; chasing across * the __user boundary with pointers encapsulated inside u64. + * + * Example chaining: + * + * .. code-block:: C + * + * struct i915_user_extension ext3 { + * .next_extension = 0, // end + * .name = ..., + * }; + * struct i915_user_extension ext2 { + * .next_extension = (uintptr_t)&ext3, + * .name = ..., + * }; + * struct i915_user_extension ext1 { + * .next_extension = (uintptr_t)&ext2, + * .name = ..., + * }; + * + * Typically the struct i915_user_extension would be embedded in some uAPI + * struct, and in this case we would feed it the head of the chain(i.e ext1), + * which would then apply all of the above extensions. + * */ struct i915_user_extension { + /** + * @next_extension: + * + * Pointer to the next struct i915_user_extension, or zero if the end. + */ __u64 next_extension; + /** + * @name: Name of the extension. + * + * Note that the name here is just some integer. + * + * Also note that the name space for this is not global for the whole + * driver, but rather its scope/meaning is limited to the specific piece + * of uAPI which has embedded the struct i915_user_extension. + */ __u32 name; - __u32 flags; /* All undefined bits must be zero. */ - __u32 rsvd[4]; /* Reserved for future use; must be zero. */ + /** + * @flags: MBZ + * + * All undefined bits must be zero. + */ + __u32 flags; + /** + * @rsvd: MBZ + * + * Reserved for future use; must be zero. + */ + __u32 rsvd[4]; }; /* -- cgit 1.4.1 From e3bdccafb5bcfab286f4f3d57d35efc4e7368c18 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Mon, 19 Apr 2021 11:57:41 +0100 Subject: drm/i915/uapi: convert i915_query and friend to kernel doc Add a note about the two-step process. v2(Tvrtko): - Also document the other method of just passing in a buffer which is large enough, which avoids two ioctl calls. Can make sense for smaller query items. v3: prefer kernel-doc references for structs and members Suggested-by: Daniel Vetter Signed-off-by: Matthew Auld Cc: Joonas Lahtinen Cc: Tvrtko Ursulin Cc: Jordan Justen Cc: Daniel Vetter Cc: Kenneth Graunke Cc: Jason Ekstrand Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Cc: mesa-dev@lists.freedesktop.org Reviewed-by: Daniel Vetter Reviewed-by: Jason Ekstrand Link: https://patchwork.freedesktop.org/patch/msgid/20210419105741.27844-4-matthew.auld@intel.com --- include/uapi/drm/i915_drm.h | 69 ++++++++++++++++++++++++++++++++++++--------- 1 file changed, 55 insertions(+), 14 deletions(-) diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index e2867d8cd5e3..6a34243a7646 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2218,53 +2218,94 @@ struct drm_i915_perf_oa_config { __u64 flex_regs_ptr; }; +/** + * struct drm_i915_query_item - An individual query for the kernel to process. + * + * The behaviour is determined by the @query_id. Note that exactly what + * @data_ptr is also depends on the specific @query_id. + */ struct drm_i915_query_item { + /** @query_id: The id for this query */ __u64 query_id; #define DRM_I915_QUERY_TOPOLOGY_INFO 1 #define DRM_I915_QUERY_ENGINE_INFO 2 #define DRM_I915_QUERY_PERF_CONFIG 3 /* Must be kept compact -- no holes and well documented */ - /* + /** + * @length: + * * When set to zero by userspace, this is filled with the size of the - * data to be written at the data_ptr pointer. The kernel sets this + * data to be written at the @data_ptr pointer. The kernel sets this * value to a negative value to signal an error on a particular query * item. */ __s32 length; - /* + /** + * @flags: + * * When query_id == DRM_I915_QUERY_TOPOLOGY_INFO, must be 0. * * When query_id == DRM_I915_QUERY_PERF_CONFIG, must be one of the - * following : - * - DRM_I915_QUERY_PERF_CONFIG_LIST - * - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID - * - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID + * following: + * + * - DRM_I915_QUERY_PERF_CONFIG_LIST + * - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID + * - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID */ __u32 flags; #define DRM_I915_QUERY_PERF_CONFIG_LIST 1 #define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID 2 #define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID 3 - /* - * Data will be written at the location pointed by data_ptr when the - * value of length matches the length of the data to be written by the + /** + * @data_ptr: + * + * Data will be written at the location pointed by @data_ptr when the + * value of @length matches the length of the data to be written by the * kernel. */ __u64 data_ptr; }; +/** + * struct drm_i915_query - Supply an array of struct drm_i915_query_item for the + * kernel to fill out. + * + * Note that this is generally a two step process for each struct + * drm_i915_query_item in the array: + * + * 1. Call the DRM_IOCTL_I915_QUERY, giving it our array of struct + * drm_i915_query_item, with &drm_i915_query_item.length set to zero. The + * kernel will then fill in the size, in bytes, which tells userspace how + * memory it needs to allocate for the blob(say for an array of properties). + * + * 2. Next we call DRM_IOCTL_I915_QUERY again, this time with the + * &drm_i915_query_item.data_ptr equal to our newly allocated blob. Note that + * the &drm_i915_query_item.length should still be the same as what the + * kernel previously set. At this point the kernel can fill in the blob. + * + * Note that for some query items it can make sense for userspace to just pass + * in a buffer/blob equal to or larger than the required size. In this case only + * a single ioctl call is needed. For some smaller query items this can work + * quite well. + * + */ struct drm_i915_query { + /** @num_items: The number of elements in the @items_ptr array */ __u32 num_items; - /* - * Unused for now. Must be cleared to zero. + /** + * @flags: Unused for now. Must be cleared to zero. */ __u32 flags; - /* - * This points to an array of num_items drm_i915_query_item structures. + /** + * @items_ptr: + * + * Pointer to an array of struct drm_i915_query_item. The number of + * array elements is @num_items. */ __u64 items_ptr; }; -- cgit 1.4.1 From f44b733e865ae963324e488866a257224e09c85c Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 12 Apr 2021 10:05:08 +0100 Subject: drm/i915/selftests: Skip aperture remapping selftest where there is no aperture If there is no mappable aperture, we cannot remap it for access, and the selftest is void. Signed-off-by: Chris Wilson Reviewed-by: Matthew Auld Reviewed-by: Imre Deak Signed-off-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20210412090526.30547-2-matthew.auld@intel.com --- drivers/gpu/drm/i915/selftests/i915_vma.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c index 5fe7b80ca0bd..dd0607254a95 100644 --- a/drivers/gpu/drm/i915/selftests/i915_vma.c +++ b/drivers/gpu/drm/i915/selftests/i915_vma.c @@ -967,6 +967,9 @@ static int igt_vma_remapped_gtt(void *arg) intel_wakeref_t wakeref; int err = 0; + if (!i915_ggtt_has_aperture(&i915->ggtt)) + return 0; + obj = i915_gem_object_create_internal(i915, 10 * 10 * PAGE_SIZE); if (IS_ERR(obj)) return PTR_ERR(obj); -- cgit 1.4.1 From a36a47490d8e911f0f12521359a8e018bb3fcfb6 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 12 Apr 2021 10:05:09 +0100 Subject: drm/i915/selftests: Only query RAPL for integrated power measurements RAPL provides an on-package power measurements which does not encompass discrete graphics, so let's avoid using the igfx masurements when testing dgfx. Later we will abstract the simple librapl interface over hwmon so that we can verify basic power consumption scenarios. Signed-off-by: Chris Wilson Reviewed-by: Matthew Auld Signed-off-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20210412090526.30547-3-matthew.auld@intel.com --- drivers/gpu/drm/i915/gt/selftest_rc6.c | 32 ++++++++++++++++++++------------ drivers/gpu/drm/i915/gt/selftest_rps.c | 2 +- drivers/gpu/drm/i915/selftests/librapl.c | 10 ++++++++++ drivers/gpu/drm/i915/selftests/librapl.h | 4 ++++ 4 files changed, 35 insertions(+), 13 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c index f097e420ac45..710f825f6e5a 100644 --- a/drivers/gpu/drm/i915/gt/selftest_rc6.c +++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c @@ -34,6 +34,7 @@ int live_rc6_manual(void *arg) struct intel_rc6 *rc6 = >->rc6; u64 rc0_power, rc6_power; intel_wakeref_t wakeref; + bool has_power; ktime_t dt; u64 res[2]; int err = 0; @@ -50,6 +51,7 @@ int live_rc6_manual(void *arg) if (IS_VALLEYVIEW(gt->i915) || IS_CHERRYVIEW(gt->i915)) return 0; + has_power = librapl_supported(gt->i915); wakeref = intel_runtime_pm_get(gt->uncore->rpm); /* Force RC6 off for starters */ @@ -71,11 +73,14 @@ int live_rc6_manual(void *arg) goto out_unlock; } - rc0_power = div64_u64(NSEC_PER_SEC * rc0_power, ktime_to_ns(dt)); - if (!rc0_power) { - pr_err("No power measured while in RC0\n"); - err = -EINVAL; - goto out_unlock; + if (has_power) { + rc0_power = div64_u64(NSEC_PER_SEC * rc0_power, + ktime_to_ns(dt)); + if (!rc0_power) { + pr_err("No power measured while in RC0\n"); + err = -EINVAL; + goto out_unlock; + } } /* Manually enter RC6 */ @@ -97,13 +102,16 @@ int live_rc6_manual(void *arg) err = -EINVAL; } - rc6_power = div64_u64(NSEC_PER_SEC * rc6_power, ktime_to_ns(dt)); - pr_info("GPU consumed %llduW in RC0 and %llduW in RC6\n", - rc0_power, rc6_power); - if (2 * rc6_power > rc0_power) { - pr_err("GPU leaked energy while in RC6!\n"); - err = -EINVAL; - goto out_unlock; + if (has_power) { + rc6_power = div64_u64(NSEC_PER_SEC * rc6_power, + ktime_to_ns(dt)); + pr_info("GPU consumed %llduW in RC0 and %llduW in RC6\n", + rc0_power, rc6_power); + if (2 * rc6_power > rc0_power) { + pr_err("GPU leaked energy while in RC6!\n"); + err = -EINVAL; + goto out_unlock; + } } /* Restore what should have been the original state! */ diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c index 967641fee42a..adf7fdbc00f7 100644 --- a/drivers/gpu/drm/i915/gt/selftest_rps.c +++ b/drivers/gpu/drm/i915/gt/selftest_rps.c @@ -1139,7 +1139,7 @@ int live_rps_power(void *arg) if (!intel_rps_is_enabled(rps) || INTEL_GEN(gt->i915) < 6) return 0; - if (!librapl_energy_uJ()) + if (!librapl_supported(gt->i915)) return 0; if (igt_spinner_init(&spin, gt)) diff --git a/drivers/gpu/drm/i915/selftests/librapl.c b/drivers/gpu/drm/i915/selftests/librapl.c index 58710ac3f979..eb03b5b28bad 100644 --- a/drivers/gpu/drm/i915/selftests/librapl.c +++ b/drivers/gpu/drm/i915/selftests/librapl.c @@ -5,8 +5,18 @@ #include +#include "i915_drv.h" #include "librapl.h" +bool librapl_supported(const struct drm_i915_private *i915) +{ + /* Discrete cards require hwmon integration */ + if (IS_DGFX(i915)) + return false; + + return librapl_energy_uJ(); +} + u64 librapl_energy_uJ(void) { unsigned long long power; diff --git a/drivers/gpu/drm/i915/selftests/librapl.h b/drivers/gpu/drm/i915/selftests/librapl.h index 887f3e91dd05..e3b24fad0a7a 100644 --- a/drivers/gpu/drm/i915/selftests/librapl.h +++ b/drivers/gpu/drm/i915/selftests/librapl.h @@ -8,6 +8,10 @@ #include +struct drm_i915_private; + +bool librapl_supported(const struct drm_i915_private *i915); + u64 librapl_energy_uJ(void); #endif /* SELFTEST_LIBRAPL_H */ -- cgit 1.4.1 From 5b11705608898c31a1cae5340555ee60d5a4fa45 Mon Sep 17 00:00:00 2001 From: Hsin-Yi Wang Date: Tue, 20 Apr 2021 16:08:53 +0300 Subject: drm/i915/selftests: Rename pm_ prefixed functions names pm_resume and pm_suspend might be conflict with the ones defined in include/linux/suspend.h. Rename all pm_* to igt_pm_* in selftests since they are only used here. v2 by Jani: - Use igt_ prefix instead of i915_ to avoid colliding with existing i915_pm_* functions - Rename all pm_ prefixed functions in the file Signed-off-by: Hsin-Yi Wang Reported-by: kernel test robot Reviewed-by: Rodrigo Vivi Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20210420130853.10573-1-jani.nikula@intel.com --- drivers/gpu/drm/i915/selftests/i915_gem.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c index dc394fb7ccfa..152d9ab135b1 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem.c @@ -87,14 +87,14 @@ static void simulate_hibernate(struct drm_i915_private *i915) intel_runtime_pm_put(&i915->runtime_pm, wakeref); } -static int pm_prepare(struct drm_i915_private *i915) +static int igt_pm_prepare(struct drm_i915_private *i915) { i915_gem_suspend(i915); return 0; } -static void pm_suspend(struct drm_i915_private *i915) +static void igt_pm_suspend(struct drm_i915_private *i915) { intel_wakeref_t wakeref; @@ -104,7 +104,7 @@ static void pm_suspend(struct drm_i915_private *i915) } } -static void pm_hibernate(struct drm_i915_private *i915) +static void igt_pm_hibernate(struct drm_i915_private *i915) { intel_wakeref_t wakeref; @@ -116,7 +116,7 @@ static void pm_hibernate(struct drm_i915_private *i915) } } -static void pm_resume(struct drm_i915_private *i915) +static void igt_pm_resume(struct drm_i915_private *i915) { intel_wakeref_t wakeref; @@ -148,16 +148,16 @@ static int igt_gem_suspend(void *arg) if (err) goto out; - err = pm_prepare(i915); + err = igt_pm_prepare(i915); if (err) goto out; - pm_suspend(i915); + igt_pm_suspend(i915); /* Here be dragons! Note that with S3RST any S3 may become S4! */ simulate_hibernate(i915); - pm_resume(i915); + igt_pm_resume(i915); err = switch_to_context(ctx); out: @@ -183,16 +183,16 @@ static int igt_gem_hibernate(void *arg) if (err) goto out; - err = pm_prepare(i915); + err = igt_pm_prepare(i915); if (err) goto out; - pm_hibernate(i915); + igt_pm_hibernate(i915); /* Here be dragons! */ simulate_hibernate(i915); - pm_resume(i915); + igt_pm_resume(i915); err = switch_to_context(ctx); out: -- cgit 1.4.1 From 0c1a77cbdafb0e1874a42284479f3d6023b91f90 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Mon, 19 Apr 2021 11:57:39 +0100 Subject: drm/doc: add section for driver uAPI Add section for drm/i915 uAPI and pull in i915_drm.h. Suggested-by: Daniel Vetter Signed-off-by: Matthew Auld Cc: Joonas Lahtinen Cc: Jordan Justen Cc: Daniel Vetter Cc: Kenneth Graunke Cc: Jason Ekstrand Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Cc: mesa-dev@lists.freedesktop.org Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210419105741.27844-2-matthew.auld@intel.com --- Documentation/gpu/driver-uapi.rst | 8 ++++++++ Documentation/gpu/index.rst | 1 + 2 files changed, 9 insertions(+) create mode 100644 Documentation/gpu/driver-uapi.rst diff --git a/Documentation/gpu/driver-uapi.rst b/Documentation/gpu/driver-uapi.rst new file mode 100644 index 000000000000..4411e6919a3d --- /dev/null +++ b/Documentation/gpu/driver-uapi.rst @@ -0,0 +1,8 @@ +=============== +DRM Driver uAPI +=============== + +drm/i915 uAPI +============= + +.. kernel-doc:: include/uapi/drm/i915_drm.h diff --git a/Documentation/gpu/index.rst b/Documentation/gpu/index.rst index ec4bc72438e4..b9c1214d8f23 100644 --- a/Documentation/gpu/index.rst +++ b/Documentation/gpu/index.rst @@ -10,6 +10,7 @@ Linux GPU Driver Developer's Guide drm-kms drm-kms-helpers drm-uapi + driver-uapi drm-client drivers backlight -- cgit 1.4.1 From c256af0d6c1846db9af357a913b277b566ca3797 Mon Sep 17 00:00:00 2001 From: Matt Roper Date: Tue, 20 Apr 2021 14:18:42 +0100 Subject: drm/i915/lmem: Fail driver init if LMEM training failed Boot firmware performs memory training and health assessment during startup. If the memory training fails, the firmware will consider the GPU unusable and will instruct the punit to keep the GT powered down. If this happens, our driver will be unable to communicate with the GT (all GT registers will read back as 0, forcewake requests will timeout, etc.) so we should abort driver initialization if this happens. We can confirm that LMEM was initialized successfully via sgunit register GU_CNTL. Bspec: 53111 Signed-off-by: Matt Roper Cc: Caz Yokoyama Reviewed-by: Matthew Auld Signed-off-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20210420131842.164163-5-matthew.auld@intel.com --- drivers/gpu/drm/i915/i915_reg.h | 3 +++ drivers/gpu/drm/i915/intel_uncore.c | 12 ++++++++++++ 2 files changed, 15 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index e087bcd21911..f41474913d27 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -487,6 +487,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GAB_CTL _MMIO(0x24000) #define GAB_CTL_CONT_AFTER_PAGEFAULT (1 << 8) +#define GU_CNTL _MMIO(0x101010) +#define LMEM_INIT REG_BIT(7) + #define GEN6_STOLEN_RESERVED _MMIO(0x1082C0) #define GEN6_STOLEN_RESERVED_ADDR_MASK (0xFFF << 20) #define GEN7_STOLEN_RESERVED_ADDR_MASK (0x3FFF << 18) diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index ed5abe7be498..b4aaf8b7109f 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -1917,6 +1917,18 @@ int intel_uncore_init_mmio(struct intel_uncore *uncore) if (ret) return ret; + /* + * The boot firmware initializes local memory and assesses its health. + * If memory training fails, the punit will have been instructed to + * keep the GT powered down; we won't be able to communicate with it + * and we should not continue with driver initialization. + */ + if (IS_DGFX(i915) && + !(__raw_uncore_read32(uncore, GU_CNTL) & LMEM_INIT)) { + drm_err(&i915->drm, "LMEM not initialized by firmware\n"); + return -ENODEV; + } + if (INTEL_GEN(i915) > 5 && !intel_vgpu_active(i915)) uncore->flags |= UNCORE_HAS_FORCEWAKE; -- cgit 1.4.1 From d57d4a1daf5e8393e87244427c9b87dd565bd37c Mon Sep 17 00:00:00 2001 From: CQ Tang Date: Wed, 21 Apr 2021 11:46:55 +0100 Subject: drm/i915: Create stolen memory region from local memory Add "REGION_STOLEN" device info to dg1, create stolen memory region from upper portion of local device memory, starting from DSMBASE. v2: - s/drm_info/drm_dbg; userspace likely doesn't care about stolen. - mem->type is only setup after the region probe, so setting the name as stolen-local or stolen-system based on this value won't work. Split system vs local stolen setup to fix this. - kill all the region->devmem/is_devmem stuff. We already differentiate the different types of stolen so such things shouldn't be needed anymore. v3: - split stolen lmem vs smem ops(Tvrtko) - add shortcut for stolen region in i915(Tvrtko) - sanity check dsm base vs bar size(Xinyun) v4(Tvrtko): - more cleanup - add some TODOs Signed-off-by: CQ Tang Signed-off-by: Matthew Auld Cc: Tvrtko Ursulin Cc: Xinyun Liu Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20210421104658.304142-1-matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_stolen.c | 132 ++++++++++++++++++++++++----- drivers/gpu/drm/i915/gem/i915_gem_stolen.h | 3 +- drivers/gpu/drm/i915/i915_drv.h | 7 ++ drivers/gpu/drm/i915/i915_pci.c | 2 +- drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/intel_memory_region.c | 13 ++- drivers/gpu/drm/i915/intel_memory_region.h | 5 +- 7 files changed, 140 insertions(+), 23 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index b0597de206de..13a7932cfe1a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -10,6 +10,7 @@ #include #include +#include "gem/i915_gem_lmem.h" #include "gem/i915_gem_region.h" #include "i915_drv.h" #include "i915_gem_stolen.h" @@ -121,6 +122,14 @@ static int i915_adjust_stolen(struct drm_i915_private *i915, } } + /* + * With stolen lmem, we don't need to check if the address range + * overlaps with the non-stolen system memory range, since lmem is local + * to the gpu. + */ + if (HAS_LMEM(i915)) + return 0; + /* * Verify that nothing else uses this physical address. Stolen * memory should be reserved by the BIOS and hidden from the @@ -374,8 +383,9 @@ static void icl_get_stolen_reserved(struct drm_i915_private *i915, } } -static int i915_gem_init_stolen(struct drm_i915_private *i915) +static int i915_gem_init_stolen(struct intel_memory_region *mem) { + struct drm_i915_private *i915 = mem->i915; struct intel_uncore *uncore = &i915->uncore; resource_size_t reserved_base, stolen_top; resource_size_t reserved_total, reserved_size; @@ -396,10 +406,10 @@ static int i915_gem_init_stolen(struct drm_i915_private *i915) return 0; } - if (resource_size(&intel_graphics_stolen_res) == 0) + if (resource_size(&mem->region) == 0) return 0; - i915->dsm = intel_graphics_stolen_res; + i915->dsm = mem->region; if (i915_adjust_stolen(i915, &i915->dsm)) return 0; @@ -688,39 +698,123 @@ struct drm_i915_gem_object * i915_gem_object_create_stolen(struct drm_i915_private *i915, resource_size_t size) { - return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_STOLEN_SMEM], + return i915_gem_object_create_region(i915->mm.stolen_region, size, I915_BO_ALLOC_CONTIGUOUS); } -static int init_stolen(struct intel_memory_region *mem) +static int init_stolen_smem(struct intel_memory_region *mem) { - intel_memory_region_set_name(mem, "stolen"); - /* * Initialise stolen early so that we may reserve preallocated * objects for the BIOS to KMS transition. */ - return i915_gem_init_stolen(mem->i915); + return i915_gem_init_stolen(mem); } -static void release_stolen(struct intel_memory_region *mem) +static void release_stolen_smem(struct intel_memory_region *mem) { i915_gem_cleanup_stolen(mem->i915); } -static const struct intel_memory_region_ops i915_region_stolen_ops = { - .init = init_stolen, - .release = release_stolen, +static const struct intel_memory_region_ops i915_region_stolen_smem_ops = { + .init = init_stolen_smem, + .release = release_stolen_smem, .init_object = _i915_gem_object_stolen_init, }; -struct intel_memory_region *i915_gem_stolen_setup(struct drm_i915_private *i915) +static int init_stolen_lmem(struct intel_memory_region *mem) +{ + int err; + + if (GEM_WARN_ON(resource_size(&mem->region) == 0)) + return -ENODEV; + + if (!io_mapping_init_wc(&mem->iomap, + mem->io_start, + resource_size(&mem->region))) + return -EIO; + + /* + * TODO: For stolen lmem we mostly just care about populating the dsm + * related bits and setting up the drm_mm allocator for the range. + * Perhaps split up i915_gem_init_stolen() for this. + */ + err = i915_gem_init_stolen(mem); + if (err) + goto err_fini; + + return 0; + +err_fini: + io_mapping_fini(&mem->iomap); + return err; +} + +static void release_stolen_lmem(struct intel_memory_region *mem) { - return intel_memory_region_create(i915, - intel_graphics_stolen_res.start, - resource_size(&intel_graphics_stolen_res), - PAGE_SIZE, 0, - &i915_region_stolen_ops); + io_mapping_fini(&mem->iomap); + i915_gem_cleanup_stolen(mem->i915); +} + +static const struct intel_memory_region_ops i915_region_stolen_lmem_ops = { + .init = init_stolen_lmem, + .release = release_stolen_lmem, + .init_object = _i915_gem_object_stolen_init, +}; + +struct intel_memory_region * +i915_gem_stolen_lmem_setup(struct drm_i915_private *i915) +{ + struct intel_uncore *uncore = &i915->uncore; + struct pci_dev *pdev = i915->drm.pdev; + struct intel_memory_region *mem; + resource_size_t io_start; + resource_size_t lmem_size; + u64 lmem_base; + + lmem_base = intel_uncore_read64(uncore, GEN12_DSMBASE); + if (GEM_WARN_ON(lmem_base >= pci_resource_len(pdev, 2))) + return ERR_PTR(-ENODEV); + + lmem_size = pci_resource_len(pdev, 2) - lmem_base; + io_start = pci_resource_start(pdev, 2) + lmem_base; + + mem = intel_memory_region_create(i915, lmem_base, lmem_size, + I915_GTT_PAGE_SIZE_4K, io_start, + &i915_region_stolen_lmem_ops); + if (IS_ERR(mem)) + return mem; + + /* + * TODO: consider creating common helper to just print all the + * interesting stuff from intel_memory_region, which we can use for all + * our probed regions. + */ + + drm_dbg(&i915->drm, "Stolen Local memory IO start: %pa\n", + &mem->io_start); + + intel_memory_region_set_name(mem, "stolen-local"); + + return mem; +} + +struct intel_memory_region* +i915_gem_stolen_smem_setup(struct drm_i915_private *i915) +{ + struct intel_memory_region *mem; + + mem = intel_memory_region_create(i915, + intel_graphics_stolen_res.start, + resource_size(&intel_graphics_stolen_res), + PAGE_SIZE, 0, + &i915_region_stolen_smem_ops); + if (IS_ERR(mem)) + return mem; + + intel_memory_region_set_name(mem, "stolen-system"); + + return mem; } struct drm_i915_gem_object * @@ -728,7 +822,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *i915, resource_size_t stolen_offset, resource_size_t size) { - struct intel_memory_region *mem = i915->mm.regions[INTEL_REGION_STOLEN_SMEM]; + struct intel_memory_region *mem = i915->mm.stolen_region; struct drm_i915_gem_object *obj; struct drm_mm_node *stolen; int ret; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.h b/drivers/gpu/drm/i915/gem/i915_gem_stolen.h index b03489706796..2bec6c367b9c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.h @@ -21,7 +21,8 @@ int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv, u64 end); void i915_gem_stolen_remove_node(struct drm_i915_private *dev_priv, struct drm_mm_node *node); -struct intel_memory_region *i915_gem_stolen_setup(struct drm_i915_private *i915); +struct intel_memory_region *i915_gem_stolen_smem_setup(struct drm_i915_private *i915); +struct intel_memory_region *i915_gem_stolen_lmem_setup(struct drm_i915_private *i915); struct drm_i915_gem_object * i915_gem_object_create_stolen(struct drm_i915_private *dev_priv, resource_size_t size); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index e20294e9227a..0b44333eb703 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -514,6 +514,13 @@ struct intel_l3_parity { }; struct i915_gem_mm { + /* + * Shortcut for the stolen region. This points to either + * INTEL_REGION_STOLEN_SMEM for integrated platforms, or + * INTEL_REGION_STOLEN_LMEM for discrete, or NULL if the device doesn't + * support stolen. + */ + struct intel_memory_region *stolen_region; /** Memory allocator for GTT stolen memory */ struct drm_mm stolen; /** Protects the usage of the GTT stolen memory allocator. This is diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 44e7b94db63d..d4673e43a46d 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -908,7 +908,7 @@ static const struct intel_device_info rkl_info = { }; #define DGFX_FEATURES \ - .memory_regions = REGION_SMEM | REGION_LMEM, \ + .memory_regions = REGION_SMEM | REGION_LMEM | REGION_STOLEN_LMEM, \ .has_master_unit_irq = 1, \ .has_llc = 0, \ .has_snoop = 1, \ diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index f41474913d27..da73dc939e58 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -12194,6 +12194,7 @@ enum skl_power_gate { #define GEN12_GLOBAL_MOCS(i) _MMIO(0x4000 + (i) * 4) /* Global MOCS regs */ #define GEN12_GSMBASE _MMIO(0x108100) +#define GEN12_DSMBASE _MMIO(0x1080C0) /* gamt regs */ #define GEN8_L3_LRA_1_GPGPU _MMIO(0x4dd4) diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c index bf837b6bb185..481a487faca6 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.c +++ b/drivers/gpu/drm/i915/intel_memory_region.c @@ -22,6 +22,10 @@ static const struct { .class = INTEL_MEMORY_STOLEN_SYSTEM, .instance = 0, }, + [INTEL_REGION_STOLEN_LMEM] = { + .class = INTEL_MEMORY_STOLEN_LOCAL, + .instance = 0, + }, }; struct intel_memory_region * @@ -278,8 +282,15 @@ int intel_memory_regions_hw_probe(struct drm_i915_private *i915) case INTEL_MEMORY_SYSTEM: mem = i915_gem_shmem_setup(i915); break; + case INTEL_MEMORY_STOLEN_LOCAL: + mem = i915_gem_stolen_lmem_setup(i915); + if (!IS_ERR(mem)) + i915->mm.stolen_region = mem; + break; case INTEL_MEMORY_STOLEN_SYSTEM: - mem = i915_gem_stolen_setup(i915); + mem = i915_gem_stolen_smem_setup(i915); + if (!IS_ERR(mem)) + i915->mm.stolen_region = mem; break; default: continue; diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h index edd49067c8ca..4c8ec15af55f 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.h +++ b/drivers/gpu/drm/i915/intel_memory_region.h @@ -26,18 +26,21 @@ enum intel_memory_type { INTEL_MEMORY_SYSTEM = 0, INTEL_MEMORY_LOCAL, INTEL_MEMORY_STOLEN_SYSTEM, + INTEL_MEMORY_STOLEN_LOCAL, }; enum intel_region_id { INTEL_REGION_SMEM = 0, INTEL_REGION_LMEM, INTEL_REGION_STOLEN_SMEM, + INTEL_REGION_STOLEN_LMEM, INTEL_REGION_UNKNOWN, /* Should be last */ }; #define REGION_SMEM BIT(INTEL_REGION_SMEM) #define REGION_LMEM BIT(INTEL_REGION_LMEM) #define REGION_STOLEN_SMEM BIT(INTEL_REGION_STOLEN_SMEM) +#define REGION_STOLEN_LMEM BIT(INTEL_REGION_STOLEN_LMEM) #define I915_ALLOC_MIN_PAGE_SIZE BIT(0) #define I915_ALLOC_CONTIGUOUS BIT(1) @@ -82,7 +85,7 @@ struct intel_memory_region { u16 type; u16 instance; enum intel_region_id id; - char name[8]; + char name[16]; struct list_head reserved; -- cgit 1.4.1 From b75947e6b29d5b33f79d7b3918747592534e3fb1 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Wed, 21 Apr 2021 11:46:56 +0100 Subject: drm/i915/stolen: treat stolen local as normal local memory Underneath it's the same stuff, so things like the PTE_LM bits for the GTT should just keep working as-is. Signed-off-by: Matthew Auld Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20210421104658.304142-2-matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c index ce1c83c13d05..017db8f71130 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c @@ -19,7 +19,10 @@ const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops = { bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj) { - return obj->ops == &i915_gem_lmem_obj_ops; + struct intel_memory_region *mr = obj->mm.region; + + return mr && (mr->type == INTEL_MEMORY_LOCAL || + mr->type == INTEL_MEMORY_STOLEN_LOCAL); } struct drm_i915_gem_object * -- cgit 1.4.1 From f9a7b01e95d5e6c3f79f0efbbbbb2bbc52a8f3ce Mon Sep 17 00:00:00 2001 From: CQ Tang Date: Wed, 21 Apr 2021 11:46:57 +0100 Subject: drm/i915/stolen: enforce the min_page_size contract Since stolen can now be device local-memory underneath, we should try to enforce any min_page_size restrictions when allocating pages. Signed-off-by: CQ Tang Signed-off-by: Matthew Auld Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20210421104658.304142-3-matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_stolen.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index 13a7932cfe1a..b43929da8de8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -677,7 +677,8 @@ static int _i915_gem_object_stolen_init(struct intel_memory_region *mem, if (!stolen) return -ENOMEM; - ret = i915_gem_stolen_insert_node(i915, stolen, size, 4096); + ret = i915_gem_stolen_insert_node(i915, stolen, size, + mem->min_page_size); if (ret) goto err_free; @@ -836,8 +837,8 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *i915, /* KISS and expect everything to be page-aligned */ if (GEM_WARN_ON(size == 0) || - GEM_WARN_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE)) || - GEM_WARN_ON(!IS_ALIGNED(stolen_offset, I915_GTT_MIN_ALIGNMENT))) + GEM_WARN_ON(!IS_ALIGNED(size, mem->min_page_size)) || + GEM_WARN_ON(!IS_ALIGNED(stolen_offset, mem->min_page_size))) return ERR_PTR(-EINVAL); stolen = kzalloc(sizeof(*stolen), GFP_KERNEL); -- cgit 1.4.1 From ae7f0dc105c4e5248e6e2e2299e52d9a289e1215 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Wed, 21 Apr 2021 11:46:58 +0100 Subject: drm/i915/stolen: actually mark as contiguous Stolen memory is always allocated as physically contiguous pages, so mark the object flags as such. It looks like the flags were previously just ignored so this had no effect. In the future we might to add the proper plumbing for passing the flags all over the way down from the caller, but for now we don't have a use for that. Signed-off-by: Matthew Auld Cc: Tvrtko Ursulin Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20210421104658.304142-4-matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_stolen.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index b43929da8de8..c5b64b2400e8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -637,10 +637,17 @@ static int __i915_gem_object_create_stolen(struct intel_memory_region *mem, { static struct lock_class_key lock_class; unsigned int cache_level; + unsigned int flags; int err; + /* + * Stolen objects are always physically contiguous since we just + * allocate one big block underneath using the drm_mm range allocator. + */ + flags = I915_BO_ALLOC_CONTIGUOUS; + drm_gem_private_object_init(&mem->i915->drm, &obj->base, stolen->size); - i915_gem_object_init(obj, &i915_gem_object_stolen_ops, &lock_class, 0); + i915_gem_object_init(obj, &i915_gem_object_stolen_ops, &lock_class, flags); obj->stolen = stolen; obj->read_domains = I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT; @@ -699,8 +706,7 @@ struct drm_i915_gem_object * i915_gem_object_create_stolen(struct drm_i915_private *i915, resource_size_t size) { - return i915_gem_object_create_region(i915->mm.stolen_region, - size, I915_BO_ALLOC_CONTIGUOUS); + return i915_gem_object_create_region(i915->mm.stolen_region, size, 0); } static int init_stolen_smem(struct intel_memory_region *mem) -- cgit 1.4.1 From 772f7bb75dffd4ec90eaf411f9e09dc2429f5c81 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Wed, 21 Apr 2021 14:09:38 +0200 Subject: drm/i915: Fix docbook descriptions for i915_gem_shrinker Fixes the following htmldocs warning: drivers/gpu/drm/i915/gem/i915_gem_shrinker.c:102: warning: Function parameter or member 'ww' not described in 'i915_gem_shrink' Fixes: cf41a8f1dc1e ("drm/i915: Finally remove obj->mm.lock.") Reported-by: Stephen Rothwell Signed-off-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20210421120938.546076-1-maarten.lankhorst@linux.intel.com Reviewed-by: Daniel Vetter --- drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index 3e248d3bd869..4f9c8d3021ab 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -70,6 +70,7 @@ static void try_to_writeback(struct drm_i915_gem_object *obj, /** * i915_gem_shrink - Shrink buffer object caches + * @ww: i915 gem ww acquire ctx, or NULL * @i915: i915 device * @target: amount of memory to make available, in pages * @nr_scanned: optional output for number of pages scanned (incremental) -- cgit 1.4.1 From f1f7f5538b9f96bb42be5df0349c7e4ef7ff7a64 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Wed, 21 Apr 2021 14:03:53 +0200 Subject: drm/i915: Fix docbook descriptions for i915_cmd_parser Fixes the following htmldocs warnings: drivers/gpu/drm/i915/i915_cmd_parser.c:1420: warning: Excess function parameter 'trampoline' description in 'intel_engine_cmd_parser' drivers/gpu/drm/i915/i915_cmd_parser.c:1420: warning: Function parameter or member 'jump_whitelist' not described in 'intel_engine_cmd_parser' drivers/gpu/drm/i915/i915_cmd_parser.c:1420: warning: Function parameter or member 'shadow_map' not described in 'intel_engine_cmd_parser' drivers/gpu/drm/i915/i915_cmd_parser.c:1420: warning: Function parameter or member 'batch_map' not described in 'intel_engine_cmd_parser' drivers/gpu/drm/i915/i915_cmd_parser.c:1420: warning: Excess function parameter 'trampoline' description in 'intel_engine_cmd_parser' Reported-by: Stephen Rothwell Signed-off-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20210421120353.544518-1-maarten.lankhorst@linux.intel.com Reviewed-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_cmd_parser.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index e6f1e93abbbb..5b4b2bd46e7c 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -1369,6 +1369,20 @@ static int check_bbstart(u32 *cmd, u32 offset, u32 length, return 0; } +/** + * intel_engine_cmd_parser_alloc_jump_whitelist() - preallocate jump whitelist for intel_engine_cmd_parser() + * @batch_length: length of the commands in batch_obj + * @trampoline: Whether jump trampolines are used. + * + * Preallocates a jump whitelist for parsing the cmd buffer in intel_engine_cmd_parser(). + * This has to be preallocated, because the command parser runs in signaling context, + * and may not allocate any memory. + * + * Return: NULL or pointer to a jump whitelist, or ERR_PTR() on failure. Use + * IS_ERR() to check for errors. Must bre freed() with kfree(). + * + * NULL is a valid value, meaning no allocation was required. + */ unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length, bool trampoline) { @@ -1401,7 +1415,9 @@ unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length, * @batch_offset: byte offset in the batch at which execution starts * @batch_length: length of the commands in batch_obj * @shadow: validated copy of the batch buffer in question - * @trampoline: whether to emit a conditional trampoline at the end of the batch + * @jump_whitelist: buffer preallocated with intel_engine_cmd_parser_alloc_jump_whitelist() + * @shadow_map: mapping to @shadow vma + * @batch_map: mapping to @batch vma * * Parses the specified batch buffer looking for privilege violations as * described in the overview. -- cgit 1.4.1 From ed52c62d386f764194e0184fdb905d5f24194cae Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Wed, 21 Apr 2021 18:33:58 +0300 Subject: drm/i915: Avoid div-by-zero on gen2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Gen2 tiles are 2KiB in size so i915_gem_object_get_tile_row_size() can in fact return <4KiB, which leads to div-by-zero here. Avoid that. Not sure i915_gem_object_get_tile_row_size() is entirely sane anyway since it doesn't account for the different tile layouts on i8xx/i915... I'm not able to hit this before commit 6846895fde05 ("drm/i915: Replace PIN_NONFAULT with calls to PIN_NOEVICT") and it looks like I also need to run recent version of Mesa. With those in place xonotic trips on this quite easily on my 85x. Cc: stable@vger.kernel.org Reviewed-by: Chris Wilson Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20210421153401.13847-2-ville.syrjala@linux.intel.com --- drivers/gpu/drm/i915/gem/i915_gem_mman.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 2561a2f1e54f..8598a1c78a4c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -189,7 +189,7 @@ compute_partial_view(const struct drm_i915_gem_object *obj, struct i915_ggtt_view view; if (i915_gem_object_is_tiled(obj)) - chunk = roundup(chunk, tile_row_pages(obj)); + chunk = roundup(chunk, tile_row_pages(obj) ?: 1); view.type = I915_GGTT_VIEW_PARTIAL; view.partial.offset = rounddown(page_offset, chunk); -- cgit 1.4.1 From f765a5b48c667bdada5e49d5e0f23f8c0687b21b Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Wed, 21 Apr 2021 18:33:59 +0300 Subject: drm/i915: Read C0DRB3/C1DRB3 as 16 bits again MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We've defined C0DRB3/C1DRB3 as 16 bit registers, so access them as such. Fixes: 1c8242c3a4b2 ("drm/i915: Use unchecked writes for setting up the fences") Reviewed-by: Chris Wilson Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20210421153401.13847-3-ville.syrjala@linux.intel.com --- drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index e72b7a0dc316..8a322594210c 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -653,8 +653,8 @@ static void detect_bit_6_swizzle(struct i915_ggtt *ggtt) * banks of memory are paired and unswizzled on the * uneven portion, so leave that as unknown. */ - if (intel_uncore_read(uncore, C0DRB3) == - intel_uncore_read(uncore, C1DRB3)) { + if (intel_uncore_read16(uncore, C0DRB3) == + intel_uncore_read16(uncore, C1DRB3)) { swizzle_x = I915_BIT_6_SWIZZLE_9_10; swizzle_y = I915_BIT_6_SWIZZLE_9; } -- cgit 1.4.1 From 924ad0e848b58cc492373d2d5fe9dcc0da0b9c6c Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Wed, 21 Apr 2021 18:34:00 +0300 Subject: drm/i915: Give C0DRB3/C1DRB3 a _BW suffix MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These are the 965g/g45/g33 specific DRB registers. Give them a suitable suffix so we can add their counterparts for other platforms. Reviewed-by: Chris Wilson Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20210421153401.13847-4-ville.syrjala@linux.intel.com --- drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c | 4 ++-- drivers/gpu/drm/i915/i915_debugfs.c | 4 ++-- drivers/gpu/drm/i915/i915_reg.h | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index 8a322594210c..0fa6c38893f7 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -653,8 +653,8 @@ static void detect_bit_6_swizzle(struct i915_ggtt *ggtt) * banks of memory are paired and unswizzled on the * uneven portion, so leave that as unknown. */ - if (intel_uncore_read16(uncore, C0DRB3) == - intel_uncore_read16(uncore, C1DRB3)) { + if (intel_uncore_read16(uncore, C0DRB3_BW) == + intel_uncore_read16(uncore, C1DRB3_BW)) { swizzle_x = I915_BIT_6_SWIZZLE_9_10; swizzle_y = I915_BIT_6_SWIZZLE_9; } diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index b654b7498bcd..8dd374691102 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -622,9 +622,9 @@ static int i915_swizzle_info(struct seq_file *m, void *data) seq_printf(m, "DDC2 = 0x%08x\n", intel_uncore_read(uncore, DCC2)); seq_printf(m, "C0DRB3 = 0x%04x\n", - intel_uncore_read16(uncore, C0DRB3)); + intel_uncore_read16(uncore, C0DRB3_BW)); seq_printf(m, "C1DRB3 = 0x%04x\n", - intel_uncore_read16(uncore, C1DRB3)); + intel_uncore_read16(uncore, C1DRB3_BW)); } else if (INTEL_GEN(dev_priv) >= 6) { seq_printf(m, "MAD_DIMM_C0 = 0x%08x\n", intel_uncore_read(uncore, MAD_DIMM_C0)); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index da73dc939e58..1ed097b8316a 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -3787,8 +3787,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define CSHRDDR3CTL_DDR3 (1 << 2) /* 965 MCH register controlling DRAM channel configuration */ -#define C0DRB3 _MMIO(MCHBAR_MIRROR_BASE + 0x206) -#define C1DRB3 _MMIO(MCHBAR_MIRROR_BASE + 0x606) +#define C0DRB3_BW _MMIO(MCHBAR_MIRROR_BASE + 0x206) +#define C1DRB3_BW _MMIO(MCHBAR_MIRROR_BASE + 0x606) /* snb MCH registers for reading the DRAM channel configuration */ #define MAD_DIMM_C0 _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5004) -- cgit 1.4.1 From ac69496fe65cca0611d5917b7d232730ff605bc7 Mon Sep 17 00:00:00 2001 From: Lv Yunlong Date: Mon, 26 Apr 2021 05:43:40 -0700 Subject: drm/i915/gt: Fix a double free in gen8_preallocate_top_level_pdp Our code analyzer reported a double free bug. In gen8_preallocate_top_level_pdp, pde and pde->pt.base are allocated via alloc_pd(vm) with one reference. If pin_pt_dma() failed, pde->pt.base is freed by i915_gem_object_put() with a reference dropped. Then free_pd calls free_px() defined in intel_ppgtt.c, which calls i915_gem_object_put() to put pde->pt.base again. As pde->pt.base is protected by refcount, so the second put will not free pde->pt.base actually. But, maybe it is better to remove the first put? Fixes: 82adf901138cc ("drm/i915/gt: Shrink i915_page_directory's slab bucket") Signed-off-by: Lv Yunlong Reviewed-by: Matthew Auld Signed-off-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20210426124340.4238-1-lyl2019@mail.ustc.edu.cn --- drivers/gpu/drm/i915/gt/gen8_ppgtt.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index 176c19633412..74bf6fc8461f 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -641,7 +641,6 @@ static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt) err = pin_pt_dma(vm, pde->pt.base); if (err) { - i915_gem_object_put(pde->pt.base); free_pd(vm, pde); return err; } -- cgit 1.4.1 From c27d642b8edbbb112bdc3ca2f219d7c98cc026e1 Mon Sep 17 00:00:00 2001 From: Venkata Ramana Nayana Date: Tue, 27 Apr 2021 09:54:11 +0100 Subject: drm/i915/dg1: Fix mapping type for default state object Use I915_MAP_WC when default state object is allocated in LMEM. Signed-off-by: Venkata Ramana Nayana Reviewed-by: Matthew Auld Signed-off-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20210427085417.120246-1-matthew.auld@intel.com --- drivers/gpu/drm/i915/gt/shmem_utils.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c index f8f02aab842b..0683b27a3890 100644 --- a/drivers/gpu/drm/i915/gt/shmem_utils.c +++ b/drivers/gpu/drm/i915/gt/shmem_utils.c @@ -8,6 +8,7 @@ #include #include "gem/i915_gem_object.h" +#include "gem/i915_gem_lmem.h" #include "shmem_utils.h" struct file *shmem_create_from_data(const char *name, void *data, size_t len) @@ -39,7 +40,8 @@ struct file *shmem_create_from_object(struct drm_i915_gem_object *obj) return file; } - ptr = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB); + ptr = i915_gem_object_pin_map_unlocked(obj, i915_gem_object_is_lmem(obj) ? + I915_MAP_WC : I915_MAP_WB); if (IS_ERR(ptr)) return ERR_CAST(ptr); -- cgit 1.4.1 From fa85bfd19c26739c4cc02afbbab2588332648e9d Mon Sep 17 00:00:00 2001 From: Venkata Sandeep Dhanalakota Date: Tue, 27 Apr 2021 09:54:12 +0100 Subject: drm/i915: Update the helper to set correct mapping Determine the possible coherent map type based on object location, and if target has llc or if user requires an always coherent mapping. Cc: Matthew Auld Cc: CQ Tang Suggested-by: Michal Wajdeczko Signed-off-by: Venkata Sandeep Dhanalakota Signed-off-by: Matthew Auld Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20210427085417.120246-2-matthew.auld@intel.com --- drivers/gpu/drm/i915/gt/intel_engine_pm.c | 2 +- drivers/gpu/drm/i915/gt/intel_lrc.c | 4 +++- drivers/gpu/drm/i915/gt/intel_ring.c | 11 +++++++---- drivers/gpu/drm/i915/gt/selftest_context.c | 3 ++- drivers/gpu/drm/i915/gt/selftest_hangcheck.c | 4 ++-- drivers/gpu/drm/i915/gt/selftest_lrc.c | 4 +++- drivers/gpu/drm/i915/gt/uc/intel_guc.c | 4 +++- drivers/gpu/drm/i915/gt/uc/intel_huc.c | 4 +++- drivers/gpu/drm/i915/i915_drv.h | 11 +++++++++-- drivers/gpu/drm/i915/selftests/igt_spinner.c | 4 ++-- 10 files changed, 35 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index 7c9af86fdb1e..47f4397095e5 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -23,7 +23,7 @@ static void dbg_poison_ce(struct intel_context *ce) if (ce->state) { struct drm_i915_gem_object *obj = ce->state->obj; - int type = i915_coherent_map_type(ce->engine->i915); + int type = i915_coherent_map_type(ce->engine->i915, obj, true); void *map; if (!i915_gem_object_trylock(obj)) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index e86897cde984..aafe2a4df496 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -903,7 +903,9 @@ lrc_pre_pin(struct intel_context *ce, GEM_BUG_ON(!i915_vma_is_pinned(ce->state)); *vaddr = i915_gem_object_pin_map(ce->state->obj, - i915_coherent_map_type(ce->engine->i915) | + i915_coherent_map_type(ce->engine->i915, + ce->state->obj, + false) | I915_MAP_OVERRIDE); return PTR_ERR_OR_ZERO(*vaddr); diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c index aee0a77c77e0..7c4d5158e03b 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring.c +++ b/drivers/gpu/drm/i915/gt/intel_ring.c @@ -51,11 +51,14 @@ int intel_ring_pin(struct intel_ring *ring, struct i915_gem_ww_ctx *ww) if (unlikely(ret)) goto err_unpin; - if (i915_vma_is_map_and_fenceable(vma)) + if (i915_vma_is_map_and_fenceable(vma)) { addr = (void __force *)i915_vma_pin_iomap(vma); - else - addr = i915_gem_object_pin_map(vma->obj, - i915_coherent_map_type(vma->vm->i915)); + } else { + int type = i915_coherent_map_type(vma->vm->i915, vma->obj, false); + + addr = i915_gem_object_pin_map(vma->obj, type); + } + if (IS_ERR(addr)) { ret = PTR_ERR(addr); goto err_ring; diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c index b9bdd1d23243..26685b927169 100644 --- a/drivers/gpu/drm/i915/gt/selftest_context.c +++ b/drivers/gpu/drm/i915/gt/selftest_context.c @@ -88,7 +88,8 @@ static int __live_context_size(struct intel_engine_cs *engine) goto err; vaddr = i915_gem_object_pin_map_unlocked(ce->state->obj, - i915_coherent_map_type(engine->i915)); + i915_coherent_map_type(engine->i915, + ce->state->obj, false)); if (IS_ERR(vaddr)) { err = PTR_ERR(vaddr); intel_context_unpin(ce); diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c index 746985971c3a..5b63d4df8c93 100644 --- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c +++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c @@ -69,7 +69,7 @@ static int hang_init(struct hang *h, struct intel_gt *gt) h->seqno = memset(vaddr, 0xff, PAGE_SIZE); vaddr = i915_gem_object_pin_map_unlocked(h->obj, - i915_coherent_map_type(gt->i915)); + i915_coherent_map_type(gt->i915, h->obj, false)); if (IS_ERR(vaddr)) { err = PTR_ERR(vaddr); goto err_unpin_hws; @@ -130,7 +130,7 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine) return ERR_CAST(obj); } - vaddr = i915_gem_object_pin_map_unlocked(obj, i915_coherent_map_type(gt->i915)); + vaddr = i915_gem_object_pin_map_unlocked(obj, i915_coherent_map_type(gt->i915, obj, false)); if (IS_ERR(vaddr)) { i915_gem_object_put(obj); i915_vm_put(vm); diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c index 85e7df6a5123..d8f6623524e8 100644 --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c @@ -1221,7 +1221,9 @@ static int compare_isolation(struct intel_engine_cs *engine, } lrc = i915_gem_object_pin_map_unlocked(ce->state->obj, - i915_coherent_map_type(engine->i915)); + i915_coherent_map_type(engine->i915, + ce->state->obj, + false)); if (IS_ERR(lrc)) { err = PTR_ERR(lrc); goto err_B1; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c index 78305b2ec89d..adae04c47aab 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c @@ -682,7 +682,9 @@ int intel_guc_allocate_and_map_vma(struct intel_guc *guc, u32 size, if (IS_ERR(vma)) return PTR_ERR(vma); - vaddr = i915_gem_object_pin_map_unlocked(vma->obj, I915_MAP_WB); + vaddr = i915_gem_object_pin_map_unlocked(vma->obj, + i915_coherent_map_type(guc_to_gt(guc)->i915, + vma->obj, true)); if (IS_ERR(vaddr)) { i915_vma_unpin_and_release(&vma, 0); return PTR_ERR(vaddr); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index 2126dd81ac38..56d2144dc6a0 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -82,7 +82,9 @@ static int intel_huc_rsa_data_create(struct intel_huc *huc) if (IS_ERR(vma)) return PTR_ERR(vma); - vaddr = i915_gem_object_pin_map_unlocked(vma->obj, I915_MAP_WB); + vaddr = i915_gem_object_pin_map_unlocked(vma->obj, + i915_coherent_map_type(gt->i915, + vma->obj, true)); if (IS_ERR(vaddr)) { i915_vma_unpin_and_release(&vma, 0); return PTR_ERR(vaddr); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 0b44333eb703..336b09f38aad 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -78,6 +78,7 @@ #include "gem/i915_gem_context_types.h" #include "gem/i915_gem_shrinker.h" #include "gem/i915_gem_stolen.h" +#include "gem/i915_gem_lmem.h" #include "gt/intel_engine.h" #include "gt/intel_gt_types.h" @@ -1936,9 +1937,15 @@ static inline int intel_hws_csb_write_index(struct drm_i915_private *i915) } static inline enum i915_map_type -i915_coherent_map_type(struct drm_i915_private *i915) +i915_coherent_map_type(struct drm_i915_private *i915, + struct drm_i915_gem_object *obj, bool always_coherent) { - return HAS_LLC(i915) ? I915_MAP_WB : I915_MAP_WC; + if (i915_gem_object_is_lmem(obj)) + return I915_MAP_WC; + if (HAS_LLC(i915) || always_coherent) + return I915_MAP_WB; + else + return I915_MAP_WC; } #endif diff --git a/drivers/gpu/drm/i915/selftests/igt_spinner.c b/drivers/gpu/drm/i915/selftests/igt_spinner.c index cfbbe415b57c..5fe397b7d1d9 100644 --- a/drivers/gpu/drm/i915/selftests/igt_spinner.c +++ b/drivers/gpu/drm/i915/selftests/igt_spinner.c @@ -94,9 +94,9 @@ int igt_spinner_pin(struct igt_spinner *spin, } if (!spin->batch) { - unsigned int mode = - i915_coherent_map_type(spin->gt->i915); + unsigned int mode; + mode = i915_coherent_map_type(spin->gt->i915, spin->obj, false); vaddr = igt_spinner_pin_obj(ce, ww, spin->obj, mode, &spin->batch_vma); if (IS_ERR(vaddr)) return PTR_ERR(vaddr); -- cgit 1.4.1 From 529b9ec809a0a073192e5dc757fc383e11926661 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Tue, 27 Apr 2021 09:54:13 +0100 Subject: drm/i915/gtt: map the PD up front We need to generalise our accessor for the page directories and tables from using the simple kmap_atomic to support local memory, and this setup must be done on acquisition of the backing storage prior to entering fence execution contexts. Here we replace the kmap with the object mapping code that for simple single page shmemfs object will return a plain kmap, that is then kept for the lifetime of the page directory. Note that keeping the mapping around is a potential concern here, since while the vma is pinned the mapping remains there for the PDs underneath, or at least until the used_count reaches zero, at which point we can safely destroy the mapping. For 32b this will be even worse since the address space is more limited, but since this change mostly impacts full ppGTT platforms, the justification is that for modern platforms we shouldn't care too much about 32b. Signed-off-by: Matthew Auld Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20210427085417.120246-3-matthew.auld@intel.com --- .../gpu/drm/i915/gem/selftests/i915_gem_context.c | 11 +---- drivers/gpu/drm/i915/gt/gen6_ppgtt.c | 11 ++--- drivers/gpu/drm/i915/gt/gen8_ppgtt.c | 26 +++++------- drivers/gpu/drm/i915/gt/intel_ggtt.c | 2 +- drivers/gpu/drm/i915/gt/intel_gtt.c | 48 ++++++++++------------ drivers/gpu/drm/i915/gt/intel_gtt.h | 11 ++--- drivers/gpu/drm/i915/gt/intel_ppgtt.c | 7 ++-- drivers/gpu/drm/i915/i915_vma.c | 3 +- drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 10 ++--- drivers/gpu/drm/i915/selftests/i915_perf.c | 3 +- 10 files changed, 54 insertions(+), 78 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c index 5fef592390cb..ce70d0a3afb2 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c @@ -1740,7 +1740,6 @@ out: static int check_scratch_page(struct i915_gem_context *ctx, u32 *out) { struct i915_address_space *vm; - struct page *page; u32 *vaddr; int err = 0; @@ -1748,24 +1747,18 @@ static int check_scratch_page(struct i915_gem_context *ctx, u32 *out) if (!vm) return -ENODEV; - page = __px_page(vm->scratch[0]); - if (!page) { + if (!vm->scratch[0]) { pr_err("No scratch page!\n"); return -EINVAL; } - vaddr = kmap(page); - if (!vaddr) { - pr_err("No (mappable) scratch page!\n"); - return -EINVAL; - } + vaddr = __px_vaddr(vm->scratch[0]); memcpy(out, vaddr, sizeof(*out)); if (memchr_inv(vaddr, *out, PAGE_SIZE)) { pr_err("Inconsistent initial state of scratch page!\n"); err = -EINVAL; } - kunmap(page); return err; } diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c index e08dff376339..21b1085769be 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c @@ -96,9 +96,8 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm, * entries back to scratch. */ - vaddr = kmap_atomic_px(pt); + vaddr = px_vaddr(pt); memset32(vaddr + pte, scratch_pte, count); - kunmap_atomic(vaddr); pte = 0; } @@ -120,7 +119,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm, GEM_BUG_ON(!pd->entry[act_pt]); - vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt)); + vaddr = px_vaddr(i915_pt_entry(pd, act_pt)); do { GEM_BUG_ON(sg_dma_len(iter.sg) < I915_GTT_PAGE_SIZE); vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma); @@ -136,12 +135,10 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm, } if (++act_pte == GEN6_PTES) { - kunmap_atomic(vaddr); - vaddr = kmap_atomic_px(i915_pt_entry(pd, ++act_pt)); + vaddr = px_vaddr(i915_pt_entry(pd, ++act_pt)); act_pte = 0; } } while (1); - kunmap_atomic(vaddr); vma->page_sizes.gtt = I915_GTT_PAGE_SIZE; } @@ -235,7 +232,7 @@ static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt) goto err_scratch0; } - ret = pin_pt_dma(vm, vm->scratch[1]); + ret = map_pt_dma(vm, vm->scratch[1]); if (ret) goto err_scratch1; diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index 74bf6fc8461f..90adfee52b41 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -242,11 +242,10 @@ static u64 __gen8_ppgtt_clear(struct i915_address_space * const vm, atomic_read(&pt->used)); GEM_BUG_ON(!count || count >= atomic_read(&pt->used)); - vaddr = kmap_atomic_px(pt); + vaddr = px_vaddr(pt); memset64(vaddr + gen8_pd_index(start, 0), vm->scratch[0]->encode, count); - kunmap_atomic(vaddr); atomic_sub(count, &pt->used); start += count; @@ -375,7 +374,7 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt, gen8_pte_t *vaddr; pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2)); - vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1))); + vaddr = px_vaddr(i915_pt_entry(pd, gen8_pd_index(idx, 1))); do { GEM_BUG_ON(sg_dma_len(iter->sg) < I915_GTT_PAGE_SIZE); vaddr[gen8_pd_index(idx, 0)] = pte_encode | iter->dma; @@ -402,12 +401,10 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt, } clflush_cache_range(vaddr, PAGE_SIZE); - kunmap_atomic(vaddr); - vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1))); + vaddr = px_vaddr(i915_pt_entry(pd, gen8_pd_index(idx, 1))); } } while (1); clflush_cache_range(vaddr, PAGE_SIZE); - kunmap_atomic(vaddr); return idx; } @@ -442,7 +439,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma, encode |= GEN8_PDE_PS_2M; page_size = I915_GTT_PAGE_SIZE_2M; - vaddr = kmap_atomic_px(pd); + vaddr = px_vaddr(pd); } else { struct i915_page_table *pt = i915_pt_entry(pd, __gen8_pte_index(start, 1)); @@ -457,7 +454,7 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma, rem >= (I915_PDES - index) * I915_GTT_PAGE_SIZE)) maybe_64K = __gen8_pte_index(start, 1); - vaddr = kmap_atomic_px(pt); + vaddr = px_vaddr(pt); } do { @@ -491,7 +488,6 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma, } while (rem >= page_size && index < I915_PDES); clflush_cache_range(vaddr, PAGE_SIZE); - kunmap_atomic(vaddr); /* * Is it safe to mark the 2M block as 64K? -- Either we have @@ -505,9 +501,8 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma, !iter->sg && IS_ALIGNED(vma->node.start + vma->node.size, I915_GTT_PAGE_SIZE_2M)))) { - vaddr = kmap_atomic_px(pd); + vaddr = px_vaddr(pd); vaddr[maybe_64K] |= GEN8_PDE_IPS_64K; - kunmap_atomic(vaddr); page_size = I915_GTT_PAGE_SIZE_64K; /* @@ -523,12 +518,11 @@ static void gen8_ppgtt_insert_huge(struct i915_vma *vma, u16 i; encode = vma->vm->scratch[0]->encode; - vaddr = kmap_atomic_px(i915_pt_entry(pd, maybe_64K)); + vaddr = px_vaddr(i915_pt_entry(pd, maybe_64K)); for (i = 1; i < index; i += 16) memset64(vaddr + i, encode, 15); - kunmap_atomic(vaddr); } } @@ -602,7 +596,7 @@ static int gen8_init_scratch(struct i915_address_space *vm) if (IS_ERR(obj)) goto free_scratch; - ret = pin_pt_dma(vm, obj); + ret = map_pt_dma(vm, obj); if (ret) { i915_gem_object_put(obj); goto free_scratch; @@ -639,7 +633,7 @@ static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt) if (IS_ERR(pde)) return PTR_ERR(pde); - err = pin_pt_dma(vm, pde->pt.base); + err = map_pt_dma(vm, pde->pt.base); if (err) { free_pd(vm, pde); return err; @@ -674,7 +668,7 @@ gen8_alloc_top_pd(struct i915_address_space *vm) goto err_pd; } - err = pin_pt_dma(vm, pd->pt.base); + err = map_pt_dma(vm, pd->pt.base); if (err) goto err_pd; diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 670c1271e7d5..d94628b9d89e 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -657,7 +657,7 @@ static int init_aliasing_ppgtt(struct i915_ggtt *ggtt) goto err_ppgtt; i915_gem_object_lock(ppgtt->vm.scratch[0], NULL); - err = i915_vm_pin_pt_stash(&ppgtt->vm, &stash); + err = i915_vm_map_pt_stash(&ppgtt->vm, &stash); i915_gem_object_unlock(ppgtt->vm.scratch[0]); if (err) goto err_stash; diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index 941f8af016d6..d386b89e2758 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -25,27 +25,25 @@ struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz) return obj; } -int pin_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj) +int map_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj) { - int err; + void *vaddr; - i915_gem_object_lock(obj, NULL); - err = i915_gem_object_pin_pages(obj); - i915_gem_object_unlock(obj); - if (err) - return err; + vaddr = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB); + if (IS_ERR(vaddr)) + return PTR_ERR(vaddr); i915_gem_object_make_unshrinkable(obj); return 0; } -int pin_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object *obj) +int map_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object *obj) { - int err; + void *vaddr; - err = i915_gem_object_pin_pages(obj); - if (err) - return err; + vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB); + if (IS_ERR(vaddr)) + return PTR_ERR(vaddr); i915_gem_object_make_unshrinkable(obj); return 0; @@ -155,6 +153,14 @@ void clear_pages(struct i915_vma *vma) memset(&vma->page_sizes, 0, sizeof(vma->page_sizes)); } +void *__px_vaddr(struct drm_i915_gem_object *p) +{ + enum i915_map_type type; + + GEM_BUG_ON(!i915_gem_object_has_pages(p)); + return page_unpack_bits(p->mm.mapping, &type); +} + dma_addr_t __px_dma(struct drm_i915_gem_object *p) { GEM_BUG_ON(!i915_gem_object_has_pages(p)); @@ -170,32 +176,22 @@ struct page *__px_page(struct drm_i915_gem_object *p) void fill_page_dma(struct drm_i915_gem_object *p, const u64 val, unsigned int count) { - struct page *page = __px_page(p); - void *vaddr; + void *vaddr = __px_vaddr(p); - vaddr = kmap(page); memset64(vaddr, val, count); clflush_cache_range(vaddr, PAGE_SIZE); - kunmap(page); } static void poison_scratch_page(struct drm_i915_gem_object *scratch) { - struct sgt_iter sgt; - struct page *page; + void *vaddr = __px_vaddr(scratch); u8 val; val = 0; if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) val = POISON_FREE; - for_each_sgt_page(page, sgt, scratch->mm.pages) { - void *vaddr; - - vaddr = kmap(page); - memset(vaddr, val, PAGE_SIZE); - kunmap(page); - } + memset(vaddr, val, scratch->base.size); } int setup_scratch_page(struct i915_address_space *vm) @@ -225,7 +221,7 @@ int setup_scratch_page(struct i915_address_space *vm) if (IS_ERR(obj)) goto skip; - if (pin_pt_dma(vm, obj)) + if (map_pt_dma(vm, obj)) goto skip_obj; /* We need a single contiguous page for our scratch */ diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index e67e34e17913..40e486704558 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -180,6 +180,9 @@ struct page *__px_page(struct drm_i915_gem_object *p); dma_addr_t __px_dma(struct drm_i915_gem_object *p); #define px_dma(px) (__px_dma(px_base(px))) +void *__px_vaddr(struct drm_i915_gem_object *p); +#define px_vaddr(px) (__px_vaddr(px_base(px))) + #define px_pt(px) \ __px_choose_expr(px, struct i915_page_table *, __x, \ __px_choose_expr(px, struct i915_page_directory *, &__x->pt, \ @@ -511,8 +514,6 @@ struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt); void i915_ggtt_suspend(struct i915_ggtt *gtt); void i915_ggtt_resume(struct i915_ggtt *ggtt); -#define kmap_atomic_px(px) kmap_atomic(__px_page(px_base(px))) - void fill_page_dma(struct drm_i915_gem_object *p, const u64 val, unsigned int count); @@ -530,8 +531,8 @@ struct i915_page_table *alloc_pt(struct i915_address_space *vm); struct i915_page_directory *alloc_pd(struct i915_address_space *vm); struct i915_page_directory *__alloc_pd(int npde); -int pin_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj); -int pin_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object *obj); +int map_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj); +int map_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object *obj); void free_px(struct i915_address_space *vm, struct i915_page_table *pt, int lvl); @@ -578,7 +579,7 @@ void setup_private_pat(struct intel_uncore *uncore); int i915_vm_alloc_pt_stash(struct i915_address_space *vm, struct i915_vm_pt_stash *stash, u64 size); -int i915_vm_pin_pt_stash(struct i915_address_space *vm, +int i915_vm_map_pt_stash(struct i915_address_space *vm, struct i915_vm_pt_stash *stash); void i915_vm_free_pt_stash(struct i915_address_space *vm, struct i915_vm_pt_stash *stash); diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c index 014ae8ac4480..4e3d80c2295c 100644 --- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c @@ -87,11 +87,10 @@ write_dma_entry(struct drm_i915_gem_object * const pdma, const unsigned short idx, const u64 encoded_entry) { - u64 * const vaddr = kmap_atomic(__px_page(pdma)); + u64 * const vaddr = __px_vaddr(pdma); vaddr[idx] = encoded_entry; clflush_cache_range(&vaddr[idx], sizeof(u64)); - kunmap_atomic(vaddr); } void @@ -258,7 +257,7 @@ int i915_vm_alloc_pt_stash(struct i915_address_space *vm, return 0; } -int i915_vm_pin_pt_stash(struct i915_address_space *vm, +int i915_vm_map_pt_stash(struct i915_address_space *vm, struct i915_vm_pt_stash *stash) { struct i915_page_table *pt; @@ -266,7 +265,7 @@ int i915_vm_pin_pt_stash(struct i915_address_space *vm, for (n = 0; n < ARRAY_SIZE(stash->pt); n++) { for (pt = stash->pt[n]; pt; pt = pt->stash) { - err = pin_pt_dma_locked(vm, pt->base); + err = map_pt_dma_locked(vm, pt->base); if (err) return err; } diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 07490db51cdc..eb01899ac6b7 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -905,8 +905,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, if (err) goto err_fence; - err = i915_vm_pin_pt_stash(vma->vm, - &work->stash); + err = i915_vm_map_pt_stash(vma->vm, &work->stash); if (err) goto err_fence; } diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index 2e4f06eaacc1..e060e455e9f6 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -186,7 +186,7 @@ retry: if (err) goto err_ppgtt_cleanup; - err = i915_vm_pin_pt_stash(&ppgtt->vm, &stash); + err = i915_vm_map_pt_stash(&ppgtt->vm, &stash); if (err) { i915_vm_free_pt_stash(&ppgtt->vm, &stash); goto err_ppgtt_cleanup; @@ -208,7 +208,7 @@ retry: if (err) goto err_ppgtt_cleanup; - err = i915_vm_pin_pt_stash(&ppgtt->vm, &stash); + err = i915_vm_map_pt_stash(&ppgtt->vm, &stash); if (err) { i915_vm_free_pt_stash(&ppgtt->vm, &stash); goto err_ppgtt_cleanup; @@ -325,11 +325,10 @@ retry: BIT_ULL(size))) goto alloc_vm_end; - err = i915_vm_pin_pt_stash(vm, &stash); + err = i915_vm_map_pt_stash(vm, &stash); if (!err) vm->allocate_va_range(vm, &stash, addr, BIT_ULL(size)); - i915_vm_free_pt_stash(vm, &stash); alloc_vm_end: if (err == -EDEADLK) { @@ -1967,10 +1966,9 @@ retry: if (err) goto end_ww; - err = i915_vm_pin_pt_stash(vm, &stash); + err = i915_vm_map_pt_stash(vm, &stash); if (!err) vm->allocate_va_range(vm, &stash, offset, chunk_size); - i915_vm_free_pt_stash(vm, &stash); end_ww: if (err == -EDEADLK) { diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c index e9d86dab8677..bfb0290967a1 100644 --- a/drivers/gpu/drm/i915/selftests/i915_perf.c +++ b/drivers/gpu/drm/i915/selftests/i915_perf.c @@ -307,7 +307,7 @@ static int live_noa_gpr(void *arg) } /* Poison the ce->vm so we detect writes not to the GGTT gt->scratch */ - scratch = kmap(__px_page(ce->vm->scratch[0])); + scratch = __px_vaddr(ce->vm->scratch[0]); memset(scratch, POISON_FREE, PAGE_SIZE); rq = intel_context_create_request(ce); @@ -405,7 +405,6 @@ static int live_noa_gpr(void *arg) out_rq: i915_request_put(rq); out_ce: - kunmap(__px_page(ce->vm->scratch[0])); intel_context_put(ce); out: stream_destroy(stream); -- cgit 1.4.1 From 6aed5673f00dcbe86dc40408cab6d85abacd20d4 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Tue, 27 Apr 2021 09:54:14 +0100 Subject: drm/i915/gtt/dgfx: place the PD in LMEM It's a requirement that for dgfx we place all the paging structures in device local-memory. v2: use i915_coherent_map_type() v3: improve the shared dma-resv object comment Signed-off-by: Matthew Auld Cc: Tvrtko Ursulin Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20210427085417.120246-4-matthew.auld@intel.com --- drivers/gpu/drm/i915/gt/gen8_ppgtt.c | 5 ++++- drivers/gpu/drm/i915/gt/intel_gtt.c | 30 +++++++++++++++++++++++++++--- drivers/gpu/drm/i915/gt/intel_gtt.h | 1 + 3 files changed, 32 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index 90adfee52b41..e3a8924d2286 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -711,7 +711,10 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt) */ ppgtt->vm.has_read_only = !IS_GEN_RANGE(gt->i915, 11, 12); - ppgtt->vm.alloc_pt_dma = alloc_pt_dma; + if (HAS_LMEM(gt->i915)) + ppgtt->vm.alloc_pt_dma = alloc_pt_lmem; + else + ppgtt->vm.alloc_pt_dma = alloc_pt_dma; err = gen8_init_scratch(&ppgtt->vm); if (err) diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index d386b89e2758..061c39d2ad51 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -7,10 +7,26 @@ #include +#include "gem/i915_gem_lmem.h" #include "i915_trace.h" #include "intel_gt.h" #include "intel_gtt.h" +struct drm_i915_gem_object *alloc_pt_lmem(struct i915_address_space *vm, int sz) +{ + struct drm_i915_gem_object *obj; + + obj = i915_gem_object_create_lmem(vm->i915, sz, 0); + /* + * Ensure all paging structures for this vm share the same dma-resv + * object underneath, with the idea that one object_lock() will lock + * them all at once. + */ + if (!IS_ERR(obj)) + obj->base.resv = &vm->resv; + return obj; +} + struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz) { struct drm_i915_gem_object *obj; @@ -19,7 +35,11 @@ struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz) i915_gem_shrink_all(vm->i915); obj = i915_gem_object_create_internal(vm->i915, sz); - /* ensure all dma objects have the same reservation class */ + /* + * Ensure all paging structures for this vm share the same dma-resv + * object underneath, with the idea that one object_lock() will lock + * them all at once. + */ if (!IS_ERR(obj)) obj->base.resv = &vm->resv; return obj; @@ -27,9 +47,11 @@ struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz) int map_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj) { + enum i915_map_type type; void *vaddr; - vaddr = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB); + type = i915_coherent_map_type(vm->i915, obj, true); + vaddr = i915_gem_object_pin_map_unlocked(obj, type); if (IS_ERR(vaddr)) return PTR_ERR(vaddr); @@ -39,9 +61,11 @@ int map_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj) int map_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object *obj) { + enum i915_map_type type; void *vaddr; - vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB); + type = i915_coherent_map_type(vm->i915, obj, true); + vaddr = i915_gem_object_pin_map(obj, type); if (IS_ERR(vaddr)) return PTR_ERR(vaddr); diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index 40e486704558..44ce27c51631 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -527,6 +527,7 @@ int setup_scratch_page(struct i915_address_space *vm); void free_scratch(struct i915_address_space *vm); struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz); +struct drm_i915_gem_object *alloc_pt_lmem(struct i915_address_space *vm, int sz); struct i915_page_table *alloc_pt(struct i915_address_space *vm); struct i915_page_directory *alloc_pd(struct i915_address_space *vm); struct i915_page_directory *__alloc_pd(int npde); -- cgit 1.4.1 From a9cf6ab3e7e4fc9e3720efe15cad3f7ae2322141 Mon Sep 17 00:00:00 2001 From: Mohammed Khajapasha Date: Tue, 27 Apr 2021 09:54:15 +0100 Subject: drm/i915/fbdev: Use lmem physical addresses for fb_mmap() on discrete Use local memory io BAR address for fbdev's fb_mmap() operation on discrete, fbdev uses the physical address of our framebuffer for its fb_mmap() fn. Signed-off-by: Mohammed Khajapasha Reviewed-by: Matthew Auld Signed-off-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20210427085417.120246-5-matthew.auld@intel.com --- drivers/gpu/drm/i915/display/intel_fbdev.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index ccd00e65a5fe..2b37959da747 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -41,6 +41,8 @@ #include #include +#include "gem/i915_gem_lmem.h" + #include "i915_drv.h" #include "intel_display_types.h" #include "intel_fbdev.h" @@ -178,6 +180,7 @@ static int intelfb_create(struct drm_fb_helper *helper, unsigned long flags = 0; bool prealloc = false; void __iomem *vaddr; + struct drm_i915_gem_object *obj; int ret; if (intel_fb && @@ -232,13 +235,27 @@ static int intelfb_create(struct drm_fb_helper *helper, info->fbops = &intelfb_ops; /* setup aperture base/size for vesafb takeover */ - info->apertures->ranges[0].base = ggtt->gmadr.start; - info->apertures->ranges[0].size = ggtt->mappable_end; + obj = intel_fb_obj(&intel_fb->base); + if (i915_gem_object_is_lmem(obj)) { + struct intel_memory_region *mem = obj->mm.region; + + info->apertures->ranges[0].base = mem->io_start; + info->apertures->ranges[0].size = mem->total; + + /* Use fbdev's framebuffer from lmem for discrete */ + info->fix.smem_start = + (unsigned long)(mem->io_start + + i915_gem_object_get_dma_address(obj, 0)); + info->fix.smem_len = obj->base.size; + } else { + info->apertures->ranges[0].base = ggtt->gmadr.start; + info->apertures->ranges[0].size = ggtt->mappable_end; - /* Our framebuffer is the entirety of fbdev's system memory */ - info->fix.smem_start = - (unsigned long)(ggtt->gmadr.start + vma->node.start); - info->fix.smem_len = vma->node.size; + /* Our framebuffer is the entirety of fbdev's system memory */ + info->fix.smem_start = + (unsigned long)(ggtt->gmadr.start + vma->node.start); + info->fix.smem_len = vma->node.size; + } vaddr = i915_vma_pin_iomap(vma); if (IS_ERR(vaddr)) { -- cgit 1.4.1 From 4bc91dbde0da2f88b1f3660e8d17dacd2e929a62 Mon Sep 17 00:00:00 2001 From: Anusha Srivatsa Date: Tue, 27 Apr 2021 09:54:16 +0100 Subject: drm/i915/lmem: Bypass aperture when lmem is available MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the scenario where local memory is available, we have rely on CPU access via lmem directly instead of aperture. v2: gmch is only relevant for much older hw, therefore we can drop the has_aperture check since it should always be present on such platforms. (Chris) Cc: Ville Syrjälä Cc: Dhinakaran Pandiyan Cc: Maarten Lankhorst Cc: Chris P Wilson Cc: Daniel Vetter Cc: Joonas Lahtinen Cc: Daniele Ceraolo Spurio Cc: CQ Tang Signed-off-by: Anusha Srivatsa Signed-off-by: Matthew Auld Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20210427085417.120246-6-matthew.auld@intel.com --- drivers/gpu/drm/i915/display/intel_fbdev.c | 22 +++++++++++++++------- drivers/gpu/drm/i915/gem/i915_gem_lmem.c | 15 +++++++++++++++ drivers/gpu/drm/i915/gem/i915_gem_lmem.h | 5 +++++ drivers/gpu/drm/i915/i915_vma.c | 25 +++++++++++++++++++------ 4 files changed, 54 insertions(+), 13 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index 2b37959da747..4af40229f5ec 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -139,14 +139,22 @@ static int intelfb_alloc(struct drm_fb_helper *helper, size = mode_cmd.pitches[0] * mode_cmd.height; size = PAGE_ALIGN(size); - /* If the FB is too big, just don't use it since fbdev is not very - * important and we should probably use that space with FBC or other - * features. */ obj = ERR_PTR(-ENODEV); - if (size * 2 < dev_priv->stolen_usable_size) - obj = i915_gem_object_create_stolen(dev_priv, size); - if (IS_ERR(obj)) - obj = i915_gem_object_create_shmem(dev_priv, size); + if (HAS_LMEM(dev_priv)) { + obj = i915_gem_object_create_lmem(dev_priv, size, + I915_BO_ALLOC_CONTIGUOUS); + } else { + /* + * If the FB is too big, just don't use it since fbdev is not very + * important and we should probably use that space with FBC or other + * features. + */ + if (size * 2 < dev_priv->stolen_usable_size) + obj = i915_gem_object_create_stolen(dev_priv, size); + if (IS_ERR(obj)) + obj = i915_gem_object_create_shmem(dev_priv, size); + } + if (IS_ERR(obj)) { drm_err(&dev_priv->drm, "failed to allocate framebuffer\n"); return PTR_ERR(obj); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c index 017db8f71130..f44bdd08f7cb 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c @@ -17,6 +17,21 @@ const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops = { .release = i915_gem_object_release_memory_region, }; +void __iomem * +i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj, + unsigned long n, + unsigned long size) +{ + resource_size_t offset; + + GEM_BUG_ON(!i915_gem_object_is_contiguous(obj)); + + offset = i915_gem_object_get_dma_address(obj, n); + offset -= obj->mm.region->region.start; + + return io_mapping_map_wc(&obj->mm.region->iomap, offset, size); +} + bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj) { struct intel_memory_region *mr = obj->mm.region; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h index 036d53c01de9..fac6bc5a5ebb 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h @@ -14,6 +14,11 @@ struct intel_memory_region; extern const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops; +void __iomem * +i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj, + unsigned long n, + unsigned long size); + bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj); struct drm_i915_gem_object * diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index eb01899ac6b7..468317e3b477 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -27,6 +27,7 @@ #include "display/intel_frontbuffer.h" +#include "gem/i915_gem_lmem.h" #include "gt/intel_engine.h" #include "gt/intel_engine_heartbeat.h" #include "gt/intel_gt.h" @@ -448,9 +449,11 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma) void __iomem *ptr; int err; - if (GEM_WARN_ON(!i915_vma_is_map_and_fenceable(vma))) { - err = -ENODEV; - goto err; + if (!i915_gem_object_is_lmem(vma->obj)) { + if (GEM_WARN_ON(!i915_vma_is_map_and_fenceable(vma))) { + err = -ENODEV; + goto err; + } } GEM_BUG_ON(!i915_vma_is_ggtt(vma)); @@ -458,9 +461,19 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma) ptr = READ_ONCE(vma->iomap); if (ptr == NULL) { - ptr = io_mapping_map_wc(&i915_vm_to_ggtt(vma->vm)->iomap, - vma->node.start, - vma->node.size); + /* + * TODO: consider just using i915_gem_object_pin_map() for lmem + * instead, which already supports mapping non-contiguous chunks + * of pages, that way we can also drop the + * I915_BO_ALLOC_CONTIGUOUS when allocating the object. + */ + if (i915_gem_object_is_lmem(vma->obj)) + ptr = i915_gem_object_lmem_io_map(vma->obj, 0, + vma->obj->base.size); + else + ptr = io_mapping_map_wc(&i915_vm_to_ggtt(vma->vm)->iomap, + vma->node.start, + vma->node.size); if (ptr == NULL) { err = -ENOMEM; goto err; -- cgit 1.4.1 From 229e22845e81c3d3b4b32bdd69c6a7f345fb0197 Mon Sep 17 00:00:00 2001 From: Mohammed Khajapasha Date: Tue, 27 Apr 2021 09:54:17 +0100 Subject: drm/i915: Return error value when bo not in LMEM for discrete Return EREMOTE value when frame buffer object is not backed by LMEM for discrete. If Local memory is supported by hardware the framebuffer backing gem objects should be from local memory. Signed-off-by: Mohammed Khajapasha Signed-off-by: Matthew Auld Reviewed-by: Tvrtko Ursulin Cc: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210427085417.120246-7-matthew.auld@intel.com --- drivers/gpu/drm/i915/display/intel_display.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 7cd19ff40ed3..fe2624b8f76c 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -63,6 +63,7 @@ #include "display/intel_vdsc.h" #include "display/intel_vrr.h" +#include "gem/i915_gem_lmem.h" #include "gem/i915_gem_object.h" #include "gt/intel_rps.h" @@ -11274,11 +11275,20 @@ intel_user_framebuffer_create(struct drm_device *dev, struct drm_framebuffer *fb; struct drm_i915_gem_object *obj; struct drm_mode_fb_cmd2 mode_cmd = *user_mode_cmd; + struct drm_i915_private *i915; obj = i915_gem_object_lookup(filp, mode_cmd.handles[0]); if (!obj) return ERR_PTR(-ENOENT); + /* object is backed with LMEM for discrete */ + i915 = to_i915(obj->base.dev); + if (HAS_LMEM(i915) && !i915_gem_object_is_lmem(obj)) { + /* object is "remote", not in local memory */ + i915_gem_object_put(obj); + return ERR_PTR(-EREMOTE); + } + fb = intel_framebuffer_create(obj, &mode_cmd); i915_gem_object_put(obj); -- cgit 1.4.1 From ca419f407b43cc89942ebc297c7a63d94abbcae4 Mon Sep 17 00:00:00 2001 From: Stéphane Marchesin Date: Thu, 29 Apr 2021 03:10:21 +0000 Subject: drm/i915: Fix crash in auto_retire MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The retire logic uses the 2 lower bits of the pointer to the retire function to store flags. However, the auto_retire function is not guaranteed to be aligned to a multiple of 4, which causes crashes as we jump to the wrong address, for example like this: 2021-04-24T18:03:53.804300Z WARNING kernel: [ 516.876901] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI 2021-04-24T18:03:53.804310Z WARNING kernel: [ 516.876906] CPU: 7 PID: 146 Comm: kworker/u16:6 Tainted: G U 5.4.105-13595-g3cd84167b2df #1 2021-04-24T18:03:53.804311Z WARNING kernel: [ 516.876907] Hardware name: Google Volteer2/Volteer2, BIOS Google_Volteer2.13672.76.0 02/22/2021 2021-04-24T18:03:53.804312Z WARNING kernel: [ 516.876911] Workqueue: events_unbound active_work 2021-04-24T18:03:53.804313Z WARNING kernel: [ 516.876914] RIP: 0010:auto_retire+0x1/0x20 2021-04-24T18:03:53.804314Z WARNING kernel: [ 516.876916] Code: e8 01 f2 ff ff eb 02 31 db 48 89 d8 5b 5d c3 0f 1f 44 00 00 55 48 89 e5 f0 ff 87 c8 00 00 00 0f 88 ab 47 4a 00 31 c0 5d c3 0f <1f> 44 00 00 55 48 89 e5 f0 ff 8f c8 00 00 00 0f 88 9a 47 4a 00 74 2021-04-24T18:03:53.804319Z WARNING kernel: [ 516.876918] RSP: 0018:ffff9b4d809fbe38 EFLAGS: 00010286 2021-04-24T18:03:53.804320Z WARNING kernel: [ 516.876919] RAX: 0000000000000007 RBX: ffff927915079600 RCX: 0000000000000007 2021-04-24T18:03:53.804320Z WARNING kernel: [ 516.876921] RDX: ffff9b4d809fbe40 RSI: 0000000000000286 RDI: ffff927915079600 2021-04-24T18:03:53.804321Z WARNING kernel: [ 516.876922] RBP: ffff9b4d809fbe68 R08: 8080808080808080 R09: fefefefefefefeff 2021-04-24T18:03:53.804321Z WARNING kernel: [ 516.876924] R10: 0000000000000010 R11: ffffffff92e44bd8 R12: ffff9279150796a0 2021-04-24T18:03:53.804322Z WARNING kernel: [ 516.876925] R13: ffff92791c368180 R14: ffff927915079640 R15: 000000001c867605 2021-04-24T18:03:53.804323Z WARNING kernel: [ 516.876926] FS: 0000000000000000(0000) GS:ffff92791ffc0000(0000) knlGS:0000000000000000 2021-04-24T18:03:53.804323Z WARNING kernel: [ 516.876928] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 2021-04-24T18:03:53.804324Z WARNING kernel: [ 516.876929] CR2: 0000239514955000 CR3: 00000007f82da001 CR4: 0000000000760ee0 2021-04-24T18:03:53.804325Z WARNING kernel: [ 516.876930] PKRU: 55555554 2021-04-24T18:03:53.804325Z WARNING kernel: [ 516.876931] Call Trace: 2021-04-24T18:03:53.804326Z WARNING kernel: [ 516.876935] __active_retire+0x77/0xcf 2021-04-24T18:03:53.804326Z WARNING kernel: [ 516.876939] process_one_work+0x1da/0x394 2021-04-24T18:03:53.804327Z WARNING kernel: [ 516.876941] worker_thread+0x216/0x375 2021-04-24T18:03:53.804327Z WARNING kernel: [ 516.876944] kthread+0x147/0x156 2021-04-24T18:03:53.804335Z WARNING kernel: [ 516.876946] ? pr_cont_work+0x58/0x58 2021-04-24T18:03:53.804335Z WARNING kernel: [ 516.876948] ? kthread_blkcg+0x2e/0x2e 2021-04-24T18:03:53.804336Z WARNING kernel: [ 516.876950] ret_from_fork+0x1f/0x40 2021-04-24T18:03:53.804336Z WARNING kernel: [ 516.876952] Modules linked in: cdc_mbim cdc_ncm cdc_wdm xt_cgroup rfcomm cmac algif_hash algif_skcipher af_alg xt_MASQUERADE uinput snd_soc_rt5682_sdw snd_soc_rt5682 snd_soc_max98373_sdw snd_soc_max98373 snd_soc_rl6231 regmap_sdw snd_soc_sof_sdw snd_soc_hdac_hdmi snd_soc_dmic snd_hda_codec_hdmi snd_sof_pci snd_sof_intel_hda_common intel_ipu6_psys snd_sof_xtensa_dsp soundwire_intel soundwire_generic_allocation soundwire_cadence snd_sof_intel_hda snd_sof snd_soc_hdac_hda snd_soc_acpi_intel_match snd_soc_acpi snd_hda_ext_core soundwire_bus snd_hda_intel snd_intel_dspcfg snd_hda_codec snd_hwdep snd_hda_core intel_ipu6_isys videobuf2_dma_contig videobuf2_v4l2 videobuf2_common videobuf2_memops mei_hdcp intel_ipu6 ov2740 ov8856 at24 sx9310 dw9768 v4l2_fwnode cros_ec_typec intel_pmc_mux roles acpi_als typec fuse iio_trig_sysfs cros_ec_light_prox cros_ec_lid_angle cros_ec_sensors cros_ec_sensors_core industrialio_triggered_buffer cros_ec_sensors_ring kfifo_buf industrialio cros_ec_sensorhub 2021-04-24T18:03:53.804337Z WARNING kernel: [ 516.876972] cdc_ether usbnet iwlmvm lzo_rle lzo_compress iwl7000_mac80211 iwlwifi zram cfg80211 r8152 mii btusb btrtl btintel btbcm bluetooth ecdh_generic ecc joydev 2021-04-24T18:03:53.804337Z EMERG kernel: [ 516.879169] gsmi: Log Shutdown Reason 0x03 This change fixes this by aligning the function. Signed-off-by: Stéphane Marchesin Fixes: 229007e02d69 ("drm/i915: Wrap i915_active in a simple kreffed struct") Signed-off-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20210429031021.1218091-1-marcheu@chromium.org --- drivers/gpu/drm/i915/i915_active.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index cf9a3d384971..aa573b078ae7 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -1156,7 +1156,8 @@ static int auto_active(struct i915_active *ref) return 0; } -static void auto_retire(struct i915_active *ref) +__i915_active_call static void +auto_retire(struct i915_active *ref) { i915_active_put(ref); } -- cgit 1.4.1 From ff2d0ba25ad68b97e3260f16c56113493bc58656 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 27 Apr 2021 19:48:57 +0200 Subject: drm/i915/gem: Remove reference to struct drm_device.pdev MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit References to struct drm_device.pdev should not be used any longer as the field will be moved into the struct's legacy section. Add a fix for the rsp commit. v2: * fix an error in the commit description (Michael) Signed-off-by: Thomas Zimmermann Reviewed-by: Jani Nikula Fixes: d57d4a1daf5e ("drm/i915: Create stolen memory region from local memory") Cc: CQ Tang Cc: Matthew Auld Cc: Tvrtko Ursulin Cc: Xinyun Liu Cc: Tvrtko Ursulin Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Rodrigo Vivi Cc: Chris Wilson Cc: Mika Kuoppala Cc: Daniel Vetter Cc: Maarten Lankhorst Cc: "Thomas Hellström" Cc: "Gustavo A. R. Silva" Cc: Dan Carpenter Cc: intel-gfx@lists.freedesktop.org Reviewed-by: Michael J. Ruhl Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20210427174857.7862-1-tzimmermann@suse.de --- drivers/gpu/drm/i915/gem/i915_gem_stolen.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index c5b64b2400e8..e1a32672bbe8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -773,7 +773,7 @@ struct intel_memory_region * i915_gem_stolen_lmem_setup(struct drm_i915_private *i915) { struct intel_uncore *uncore = &i915->uncore; - struct pci_dev *pdev = i915->drm.pdev; + struct pci_dev *pdev = to_pci_dev(i915->drm.dev); struct intel_memory_region *mem; resource_size_t io_start; resource_size_t lmem_size; -- cgit 1.4.1 From bc6f80cce9ae7c83a4a9082c342fd733a4492928 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Mon, 26 Apr 2021 12:23:51 +0200 Subject: drm/i915: Use trylock in shrinker for ggtt on bsw vt-d and bxt, v2. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The stop_machine() lock may allocate memory, but is called inside vm->mutex, which is taken in the shrinker. This will cause a lockdep splat, as can be seen below: <4>[ 462.585762] ====================================================== <4>[ 462.585768] WARNING: possible circular locking dependency detected <4>[ 462.585773] 5.12.0-rc5-CI-Trybot_7644+ #1 Tainted: G U <4>[ 462.585779] ------------------------------------------------------ <4>[ 462.585783] i915_selftest/5540 is trying to acquire lock: <4>[ 462.585788] ffffffff826440b0 (cpu_hotplug_lock){++++}-{0:0}, at: stop_machine+0x12/0x30 <4>[ 462.585814] but task is already holding lock: <4>[ 462.585818] ffff888125369c70 (&vm->mutex/1){+.+.}-{3:3}, at: i915_vma_pin_ww+0x38e/0xb40 [i915] <4>[ 462.586301] which lock already depends on the new lock. <4>[ 462.586305] the existing dependency chain (in reverse order) is: <4>[ 462.586309] -> #2 (&vm->mutex/1){+.+.}-{3:3}: <4>[ 462.586323] i915_gem_shrinker_taints_mutex+0x2d/0x50 [i915] <4>[ 462.586719] i915_address_space_init+0x12d/0x130 [i915] <4>[ 462.587092] ppgtt_init+0x4e/0x80 [i915] <4>[ 462.587467] gen8_ppgtt_create+0x3e/0x5c0 [i915] <4>[ 462.587828] i915_ppgtt_create+0x28/0xf0 [i915] <4>[ 462.588203] intel_gt_init+0x123/0x370 [i915] <4>[ 462.588572] i915_gem_init+0x129/0x1f0 [i915] <4>[ 462.588971] i915_driver_probe+0x753/0xd80 [i915] <4>[ 462.589320] i915_pci_probe+0x43/0x1d0 [i915] <4>[ 462.589671] pci_device_probe+0x9e/0x110 <4>[ 462.589680] really_probe+0xea/0x410 <4>[ 462.589690] driver_probe_device+0xd9/0x140 <4>[ 462.589697] device_driver_attach+0x4a/0x50 <4>[ 462.589704] __driver_attach+0x83/0x140 <4>[ 462.589711] bus_for_each_dev+0x75/0xc0 <4>[ 462.589718] bus_add_driver+0x14b/0x1f0 <4>[ 462.589724] driver_register+0x66/0xb0 <4>[ 462.589731] i915_init+0x70/0x87 [i915] <4>[ 462.590053] do_one_initcall+0x56/0x2e0 <4>[ 462.590061] do_init_module+0x55/0x200 <4>[ 462.590068] load_module+0x2703/0x2990 <4>[ 462.590074] __do_sys_finit_module+0xad/0x110 <4>[ 462.590080] do_syscall_64+0x33/0x80 <4>[ 462.590089] entry_SYSCALL_64_after_hwframe+0x44/0xae <4>[ 462.590096] -> #1 (fs_reclaim){+.+.}-{0:0}: <4>[ 462.590109] fs_reclaim_acquire+0x9f/0xd0 <4>[ 462.590118] kmem_cache_alloc_trace+0x3d/0x430 <4>[ 462.590126] intel_cpuc_prepare+0x3b/0x1b0 <4>[ 462.590133] cpuhp_invoke_callback+0x9e/0x890 <4>[ 462.590141] _cpu_up+0xa4/0x130 <4>[ 462.590147] cpu_up+0x82/0x90 <4>[ 462.590153] bringup_nonboot_cpus+0x4a/0x60 <4>[ 462.590159] smp_init+0x21/0x5c <4>[ 462.590167] kernel_init_freeable+0x8a/0x1b7 <4>[ 462.590175] kernel_init+0x5/0xff <4>[ 462.590181] ret_from_fork+0x22/0x30 <4>[ 462.590187] -> #0 (cpu_hotplug_lock){++++}-{0:0}: <4>[ 462.590199] __lock_acquire+0x1520/0x2590 <4>[ 462.590207] lock_acquire+0xd1/0x3d0 <4>[ 462.590213] cpus_read_lock+0x39/0xc0 <4>[ 462.590219] stop_machine+0x12/0x30 <4>[ 462.590226] bxt_vtd_ggtt_insert_entries__BKL+0x36/0x50 [i915] <4>[ 462.590601] ggtt_bind_vma+0x5d/0x80 [i915] <4>[ 462.590970] i915_vma_bind+0xdc/0x1c0 [i915] <4>[ 462.591374] i915_vma_pin_ww+0x435/0xb40 [i915] <4>[ 462.591779] make_obj_busy+0xcb/0x330 [i915] <4>[ 462.592170] igt_mmap_offset_exhaustion+0x45f/0x4c0 [i915] <4>[ 462.592562] __i915_subtests.cold.7+0x42/0x92 [i915] <4>[ 462.592995] __run_selftests.part.3+0x10d/0x172 [i915] <4>[ 462.593428] i915_live_selftests.cold.5+0x1f/0x47 [i915] <4>[ 462.593860] i915_pci_probe+0x93/0x1d0 [i915] <4>[ 462.594210] pci_device_probe+0x9e/0x110 <4>[ 462.594217] really_probe+0xea/0x410 <4>[ 462.594226] driver_probe_device+0xd9/0x140 <4>[ 462.594233] device_driver_attach+0x4a/0x50 <4>[ 462.594240] __driver_attach+0x83/0x140 <4>[ 462.594247] bus_for_each_dev+0x75/0xc0 <4>[ 462.594254] bus_add_driver+0x14b/0x1f0 <4>[ 462.594260] driver_register+0x66/0xb0 <4>[ 462.594267] i915_init+0x70/0x87 [i915] <4>[ 462.594586] do_one_initcall+0x56/0x2e0 <4>[ 462.594592] do_init_module+0x55/0x200 <4>[ 462.594599] load_module+0x2703/0x2990 <4>[ 462.594605] __do_sys_finit_module+0xad/0x110 <4>[ 462.594612] do_syscall_64+0x33/0x80 <4>[ 462.594618] entry_SYSCALL_64_after_hwframe+0x44/0xae <4>[ 462.594625] other info that might help us debug this: <4>[ 462.594629] Chain exists of: cpu_hotplug_lock --> fs_reclaim --> &vm->mutex/1 <4>[ 462.594645] Possible unsafe locking scenario: <4>[ 462.594648] CPU0 CPU1 <4>[ 462.594652] ---- ---- <4>[ 462.594655] lock(&vm->mutex/1); <4>[ 462.594664] lock(fs_reclaim); <4>[ 462.594671] lock(&vm->mutex/1); <4>[ 462.594679] lock(cpu_hotplug_lock); <4>[ 462.594686] *** DEADLOCK *** <4>[ 462.594690] 4 locks held by i915_selftest/5540: <4>[ 462.594696] #0: ffff888100fbc240 (&dev->mutex){....}-{3:3}, at: device_driver_attach+0x18/0x50 <4>[ 462.594715] #1: ffffc900006cb9a0 (reservation_ww_class_acquire){+.+.}-{0:0}, at: make_obj_busy+0x81/0x330 [i915] <4>[ 462.595118] #2: ffff88812a6081e8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: make_obj_busy+0x21f/0x330 [i915] <4>[ 462.595519] #3: ffff888125369c70 (&vm->mutex/1){+.+.}-{3:3}, at: i915_vma_pin_ww+0x38e/0xb40 [i915] <4>[ 462.595934] stack backtrace: <4>[ 462.595939] CPU: 0 PID: 5540 Comm: i915_selftest Tainted: G U 5.12.0-rc5-CI-Trybot_7644+ #1 <4>[ 462.595947] Hardware name: GOOGLE Kefka/Kefka, BIOS MrChromebox 02/04/2018 <4>[ 462.595952] Call Trace: <4>[ 462.595961] dump_stack+0x7f/0xad <4>[ 462.595974] check_noncircular+0x12e/0x150 <4>[ 462.595982] ? save_stack.isra.17+0x3f/0x70 <4>[ 462.595991] ? drm_mm_insert_node_in_range+0x34a/0x5b0 <4>[ 462.596000] ? i915_vma_pin_ww+0x9ec/0xb40 [i915] <4>[ 462.596410] __lock_acquire+0x1520/0x2590 <4>[ 462.596419] ? do_init_module+0x55/0x200 <4>[ 462.596429] lock_acquire+0xd1/0x3d0 <4>[ 462.596435] ? stop_machine+0x12/0x30 <4>[ 462.596445] ? gen8_ggtt_insert_entries+0xf0/0xf0 [i915] <4>[ 462.596816] cpus_read_lock+0x39/0xc0 <4>[ 462.596824] ? stop_machine+0x12/0x30 <4>[ 462.596831] stop_machine+0x12/0x30 <4>[ 462.596839] bxt_vtd_ggtt_insert_entries__BKL+0x36/0x50 [i915] <4>[ 462.597210] ggtt_bind_vma+0x5d/0x80 [i915] <4>[ 462.597580] i915_vma_bind+0xdc/0x1c0 [i915] <4>[ 462.597986] i915_vma_pin_ww+0x435/0xb40 [i915] <4>[ 462.598395] ? make_obj_busy+0xcb/0x330 [i915] <4>[ 462.598786] make_obj_busy+0xcb/0x330 [i915] <4>[ 462.599180] ? 0xffffffff81000000 <4>[ 462.599187] ? debug_mutex_unlock+0x50/0xa0 <4>[ 462.599198] igt_mmap_offset_exhaustion+0x45f/0x4c0 [i915] <4>[ 462.599592] __i915_subtests.cold.7+0x42/0x92 [i915] <4>[ 462.600026] ? i915_perf_selftests+0x20/0x20 [i915] <4>[ 462.600422] ? __i915_nop_setup+0x10/0x10 [i915] <4>[ 462.600820] __run_selftests.part.3+0x10d/0x172 [i915] <4>[ 462.601253] i915_live_selftests.cold.5+0x1f/0x47 [i915] <4>[ 462.601686] i915_pci_probe+0x93/0x1d0 [i915] <4>[ 462.602037] ? _raw_spin_unlock_irqrestore+0x3d/0x60 <4>[ 462.602047] pci_device_probe+0x9e/0x110 <4>[ 462.602057] really_probe+0xea/0x410 <4>[ 462.602067] driver_probe_device+0xd9/0x140 <4>[ 462.602075] device_driver_attach+0x4a/0x50 <4>[ 462.602084] __driver_attach+0x83/0x140 <4>[ 462.602091] ? device_driver_attach+0x50/0x50 <4>[ 462.602099] ? device_driver_attach+0x50/0x50 <4>[ 462.602107] bus_for_each_dev+0x75/0xc0 <4>[ 462.602116] bus_add_driver+0x14b/0x1f0 <4>[ 462.602124] driver_register+0x66/0xb0 <4>[ 462.602133] i915_init+0x70/0x87 [i915] <4>[ 462.602453] ? 0xffffffffa0606000 <4>[ 462.602458] do_one_initcall+0x56/0x2e0 <4>[ 462.602466] ? kmem_cache_alloc_trace+0x374/0x430 <4>[ 462.602476] do_init_module+0x55/0x200 <4>[ 462.602484] load_module+0x2703/0x2990 <4>[ 462.602500] ? __do_sys_finit_module+0xad/0x110 <4>[ 462.602507] __do_sys_finit_module+0xad/0x110 <4>[ 462.602519] do_syscall_64+0x33/0x80 <4>[ 462.602527] entry_SYSCALL_64_after_hwframe+0x44/0xae <4>[ 462.602535] RIP: 0033:0x7fab69d8d89d Changes since v1: - Add lockdep annotations during init, to ensure that lockdep is primed. This also fixes a false positive when reading /proc/lockdep_stats during module reload. Signed-off-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20210426102351.921874-1-maarten.lankhorst@linux.intel.com Reviewed-by: Thomas Hellström --- drivers/gpu/drm/i915/gem/i915_gem_shrinker.c | 13 +++++++++---- drivers/gpu/drm/i915/gt/intel_ggtt.c | 8 +++++--- drivers/gpu/drm/i915/gt/intel_gtt.c | 17 ++++++++++++++++- drivers/gpu/drm/i915/i915_drv.h | 11 +++++++++-- drivers/gpu/drm/i915/i915_gem.c | 15 +++++++++++++-- 5 files changed, 52 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index 4f9c8d3021ab..f4fb68e8955a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -38,15 +38,17 @@ static bool can_release_pages(struct drm_i915_gem_object *obj) } static bool unsafe_drop_pages(struct drm_i915_gem_object *obj, - unsigned long shrink) + unsigned long shrink, bool trylock_vm) { unsigned long flags; flags = 0; if (shrink & I915_SHRINK_ACTIVE) - flags = I915_GEM_OBJECT_UNBIND_ACTIVE; + flags |= I915_GEM_OBJECT_UNBIND_ACTIVE; if (!(shrink & I915_SHRINK_BOUND)) - flags = I915_GEM_OBJECT_UNBIND_TEST; + flags |= I915_GEM_OBJECT_UNBIND_TEST; + if (trylock_vm) + flags |= I915_GEM_OBJECT_UNBIND_VM_TRYLOCK; if (i915_gem_object_unbind(obj, flags) == 0) return true; @@ -117,6 +119,9 @@ i915_gem_shrink(struct i915_gem_ww_ctx *ww, unsigned long scanned = 0; int err; + /* CHV + VTD workaround use stop_machine(); need to trylock vm->mutex */ + bool trylock_vm = !ww && intel_vm_no_concurrent_access_wa(i915); + trace_i915_gem_shrink(i915, target, shrink); /* @@ -204,7 +209,7 @@ i915_gem_shrink(struct i915_gem_ww_ctx *ww, spin_unlock_irqrestore(&i915->mm.obj_lock, flags); err = 0; - if (unsafe_drop_pages(obj, shrink)) { + if (unsafe_drop_pages(obj, shrink, trylock_vm)) { /* May arrive from get_pages on another bo */ if (!ww) { if (!i915_gem_object_trylock(obj)) diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index d94628b9d89e..dcb3b299cf4a 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -906,9 +906,11 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) ggtt->vm.insert_entries = gen8_ggtt_insert_entries; - /* Serialize GTT updates with aperture access on BXT if VT-d is on. */ - if (intel_ggtt_update_needs_vtd_wa(i915) || - IS_CHERRYVIEW(i915) /* fails with concurrent use/update */) { + /* + * Serialize GTT updates with aperture access on BXT if VT-d is on, + * and always on CHV. + */ + if (intel_vm_no_concurrent_access_wa(i915)) { ggtt->vm.insert_entries = bxt_vtd_ggtt_insert_entries__BKL; ggtt->vm.insert_page = bxt_vtd_ggtt_insert_page__BKL; ggtt->vm.bind_async_flags = diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index 061c39d2ad51..9b98f9d9faa3 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -154,7 +154,22 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass) */ mutex_init(&vm->mutex); lockdep_set_subclass(&vm->mutex, subclass); - i915_gem_shrinker_taints_mutex(vm->i915, &vm->mutex); + + if (!intel_vm_no_concurrent_access_wa(vm->i915)) { + i915_gem_shrinker_taints_mutex(vm->i915, &vm->mutex); + } else { + /* + * CHV + BXT VTD workaround use stop_machine(), + * which is allowed to allocate memory. This means &vm->mutex + * is the outer lock, and in theory we can allocate memory inside + * it through stop_machine(). + * + * Add the annotation for this, we use trylock in shrinker. + */ + mutex_acquire(&vm->mutex.dep_map, 0, 0, _THIS_IP_); + might_alloc(GFP_KERNEL); + mutex_release(&vm->mutex.dep_map, _THIS_IP_); + } dma_resv_init(&vm->resv); GEM_BUG_ON(!vm->total); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 336b09f38aad..3cfa6effbb5f 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1720,9 +1720,15 @@ static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv) } static inline bool -intel_ggtt_update_needs_vtd_wa(struct drm_i915_private *dev_priv) +intel_ggtt_update_needs_vtd_wa(struct drm_i915_private *i915) { - return IS_BROXTON(dev_priv) && intel_vtd_active(); + return IS_BROXTON(i915) && intel_vtd_active(); +} + +static inline bool +intel_vm_no_concurrent_access_wa(struct drm_i915_private *i915) +{ + return IS_CHERRYVIEW(i915) || intel_ggtt_update_needs_vtd_wa(i915); } /* i915_drv.c */ @@ -1802,6 +1808,7 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj, #define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0) #define I915_GEM_OBJECT_UNBIND_BARRIER BIT(1) #define I915_GEM_OBJECT_UNBIND_TEST BIT(2) +#define I915_GEM_OBJECT_UNBIND_VM_TRYLOCK BIT(3) void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index b23f58e94cfb..07da6a9342e3 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -157,8 +157,19 @@ try_again: if (vma) { ret = -EBUSY; if (flags & I915_GEM_OBJECT_UNBIND_ACTIVE || - !i915_vma_is_active(vma)) - ret = i915_vma_unbind(vma); + !i915_vma_is_active(vma)) { + if (i915_is_ggtt(vma->vm) && + flags & I915_GEM_OBJECT_UNBIND_VM_TRYLOCK) { + if (mutex_trylock(&vma->vm->mutex)) { + ret = __i915_vma_unbind(vma); + mutex_unlock(&vma->vm->mutex); + } else { + ret = -EBUSY; + } + } else { + ret = i915_vma_unbind(vma); + } + } __i915_vma_put(vma); } -- cgit 1.4.1 From d8e44e4dd221ee283ea60a6fb87bca08807aa0ab Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Thu, 29 Apr 2021 09:35:29 +0100 Subject: drm/i915/overlay: Fix active retire callback alignment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit __i915_active_call annotation is required on the retire callback to ensure correct function alignment. Signed-off-by: Tvrtko Ursulin Fixes: a21ce8ad12d2 ("drm/i915/overlay: Switch to using i915_active tracking") Cc: Chris Wilson Cc: Matthew Auld Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20210429083530.849546-1-tvrtko.ursulin@linux.intel.com --- drivers/gpu/drm/i915/display/intel_overlay.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c index d1255911a327..8fa4313569a9 100644 --- a/drivers/gpu/drm/i915/display/intel_overlay.c +++ b/drivers/gpu/drm/i915/display/intel_overlay.c @@ -383,7 +383,7 @@ static void intel_overlay_off_tail(struct intel_overlay *overlay) i830_overlay_clock_gating(dev_priv, true); } -static void +__i915_active_call static void intel_overlay_last_flip_retire(struct i915_active *active) { struct intel_overlay *overlay = -- cgit 1.4.1 From fd5f262db118355590eb123cd5287c461f3ba89c Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Thu, 29 Apr 2021 09:35:30 +0100 Subject: drm/i915/selftests: Fix active retire callback alignment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit __i915_active_call annotation is required on the retire callback to ensure correct function alignment. Signed-off-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20210429083530.849546-2-tvrtko.ursulin@linux.intel.com Reviewed-by: Ville Syrjälä --- drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c | 2 +- drivers/gpu/drm/i915/selftests/i915_active.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c index b2c369317bf1..fcde223e26ff 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c +++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c @@ -63,7 +63,7 @@ static void pulse_put(struct pulse *p) kref_put(&p->kref, pulse_free); } -static void pulse_retire(struct i915_active *active) +__i915_active_call static void pulse_retire(struct i915_active *active) { pulse_put(container_of(active, struct pulse, active)); } diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c index 4002c984c2e0..1aa52b5cc488 100644 --- a/drivers/gpu/drm/i915/selftests/i915_active.c +++ b/drivers/gpu/drm/i915/selftests/i915_active.c @@ -51,7 +51,7 @@ static int __live_active(struct i915_active *base) return 0; } -static void __live_retire(struct i915_active *base) +__i915_active_call static void __live_retire(struct i915_active *base) { struct live_active *active = container_of(base, typeof(*active), base); -- cgit 1.4.1 From 73552e008a853f38f02bfb151ae7f8298debe5f8 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Thu, 29 Apr 2021 14:01:58 +0200 Subject: drm/i915: Remove erroneous i915_is_ggtt check for I915_GEM_OBJECT_UNBIND_VM_TRYLOCK MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We changed the locking hierarchy for both ppgtt and ggtt, so both locks should be trylocked inside i915_gem_object_unbind(). Signed-off-by: Maarten Lankhorst Fixes: bc6f80cce9ae ("drm/i915: Use trylock in shrinker for ggtt on bsw vt-d and bxt, v2.") Cc: Thomas Hellström Link: https://patchwork.freedesktop.org/patch/msgid/20210429120158.1105318-1-maarten.lankhorst@linux.intel.com Reviewed-by: Thomas Hellström #irc --- drivers/gpu/drm/i915/i915_gem.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 07da6a9342e3..d0018c5f88bd 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -158,8 +158,7 @@ try_again: ret = -EBUSY; if (flags & I915_GEM_OBJECT_UNBIND_ACTIVE || !i915_vma_is_active(vma)) { - if (i915_is_ggtt(vma->vm) && - flags & I915_GEM_OBJECT_UNBIND_VM_TRYLOCK) { + if (flags & I915_GEM_OBJECT_UNBIND_VM_TRYLOCK) { if (mutex_trylock(&vma->vm->mutex)) { ret = __i915_vma_unbind(vma); mutex_unlock(&vma->vm->mutex); -- cgit 1.4.1 From 0333ec8806dfe7b8766ad025821bf58dc49dc970 Mon Sep 17 00:00:00 2001 From: Bernard Zhao Date: Wed, 28 Apr 2021 19:13:27 -0700 Subject: drm/i915: Use might_alloc() This maybe uses lockdep through the fs_reclaim annotations. Signed-off-by: Bernard Zhao Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210429021327.57944-1-bernard@vivo.com --- drivers/gpu/drm/i915/i915_request.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index bec9c3652188..970d8f4986bb 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -929,7 +929,7 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) u32 seqno; int ret; - might_sleep_if(gfpflags_allow_blocking(gfp)); + might_alloc(gfp); /* Check that the caller provided an already pinned context */ __intel_context_pin(ce); -- cgit 1.4.1 From 2bc9c04ea7020df3a98682f12c50e38870d3104a Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Thu, 29 Apr 2021 11:30:48 +0100 Subject: drm/doc/rfc: i915 DG1 uAPI MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add an entry for the new uAPI needed for DG1. Also add the overall upstream plan, including some notes for the TTM conversion. v2(Daniel): - include the overall upstreaming plan - add a note for mmap, there are differences here for TTM vs i915 - bunch of other suggestions from Daniel v3: (Daniel) - add a note for set/get caching stuff - add some more docs for existing query and extensions stuff - add an actual code example for regions query - bunch of other stuff (Jason) - uAPI change(!): - try a simpler design with the placements extension - rather than have a generic setparam which can cover multiple use cases, have each extension be responsible for one thing only v4: (Daniel) - add some more notes for ttm conversion - bunch of other stuff (Jason) - uAPI change(!): - drop all the extra rsvd members for the region_query and region_info, just keep the bare minimum needed for padding v5: (Jason) - for the upstream plan, add a requirement that we send the uAPI bits again for final sign off before turning it on for real - document how we intend to extend the rsvd bits for the region query (Kenneth) - improve the comment for the smem+lmem mmap mode and caching Signed-off-by: Matthew Auld Cc: Joonas Lahtinen Cc: Thomas Hellström Cc: Daniele Ceraolo Spurio Cc: Lionel Landwerlin Cc: Jon Bloomfield Cc: Jordan Justen Cc: Daniel Vetter Cc: Kenneth Graunke Cc: Jason Ekstrand Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Cc: mesa-dev@lists.freedesktop.org Acked-by: Daniel Vetter Acked-by: Dave Airlie Acked-by: Kenneth Graunke Acked-by: Jon Bloomfield Link: https://patchwork.freedesktop.org/patch/msgid/20210429103056.407067-1-matthew.auld@intel.com --- Documentation/gpu/rfc/i915_gem_lmem.h | 237 ++++++++++++++++++++++++++++++++ Documentation/gpu/rfc/i915_gem_lmem.rst | 131 ++++++++++++++++++ Documentation/gpu/rfc/index.rst | 4 + 3 files changed, 372 insertions(+) create mode 100644 Documentation/gpu/rfc/i915_gem_lmem.h create mode 100644 Documentation/gpu/rfc/i915_gem_lmem.rst diff --git a/Documentation/gpu/rfc/i915_gem_lmem.h b/Documentation/gpu/rfc/i915_gem_lmem.h new file mode 100644 index 000000000000..d9c61bea0556 --- /dev/null +++ b/Documentation/gpu/rfc/i915_gem_lmem.h @@ -0,0 +1,237 @@ +/** + * enum drm_i915_gem_memory_class - Supported memory classes + */ +enum drm_i915_gem_memory_class { + /** @I915_MEMORY_CLASS_SYSTEM: System memory */ + I915_MEMORY_CLASS_SYSTEM = 0, + /** @I915_MEMORY_CLASS_DEVICE: Device local-memory */ + I915_MEMORY_CLASS_DEVICE, +}; + +/** + * struct drm_i915_gem_memory_class_instance - Identify particular memory region + */ +struct drm_i915_gem_memory_class_instance { + /** @memory_class: See enum drm_i915_gem_memory_class */ + __u16 memory_class; + + /** @memory_instance: Which instance */ + __u16 memory_instance; +}; + +/** + * struct drm_i915_memory_region_info - Describes one region as known to the + * driver. + * + * Note that we reserve some stuff here for potential future work. As an example + * we might want expose the capabilities for a given region, which could include + * things like if the region is CPU mappable/accessible, what are the supported + * mapping types etc. + * + * Note that to extend struct drm_i915_memory_region_info and struct + * drm_i915_query_memory_regions in the future the plan is to do the following: + * + * .. code-block:: C + * + * struct drm_i915_memory_region_info { + * struct drm_i915_gem_memory_class_instance region; + * union { + * __u32 rsvd0; + * __u32 new_thing1; + * }; + * ... + * union { + * __u64 rsvd1[8]; + * struct { + * __u64 new_thing2; + * __u64 new_thing3; + * ... + * }; + * }; + * }; + * + * With this things should remain source compatible between versions for + * userspace, even as we add new fields. + * + * Note this is using both struct drm_i915_query_item and struct drm_i915_query. + * For this new query we are adding the new query id DRM_I915_QUERY_MEMORY_REGIONS + * at &drm_i915_query_item.query_id. + */ +struct drm_i915_memory_region_info { + /** @region: The class:instance pair encoding */ + struct drm_i915_gem_memory_class_instance region; + + /** @rsvd0: MBZ */ + __u32 rsvd0; + + /** @probed_size: Memory probed by the driver (-1 = unknown) */ + __u64 probed_size; + + /** @unallocated_size: Estimate of memory remaining (-1 = unknown) */ + __u64 unallocated_size; + + /** @rsvd1: MBZ */ + __u64 rsvd1[8]; +}; + +/** + * struct drm_i915_query_memory_regions + * + * The region info query enumerates all regions known to the driver by filling + * in an array of struct drm_i915_memory_region_info structures. + * + * Example for getting the list of supported regions: + * + * .. code-block:: C + * + * struct drm_i915_query_memory_regions *info; + * struct drm_i915_query_item item = { + * .query_id = DRM_I915_QUERY_MEMORY_REGIONS; + * }; + * struct drm_i915_query query = { + * .num_items = 1, + * .items_ptr = (uintptr_t)&item, + * }; + * int err, i; + * + * // First query the size of the blob we need, this needs to be large + * // enough to hold our array of regions. The kernel will fill out the + * // item.length for us, which is the number of bytes we need. + * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); + * if (err) ... + * + * info = calloc(1, item.length); + * // Now that we allocated the required number of bytes, we call the ioctl + * // again, this time with the data_ptr pointing to our newly allocated + * // blob, which the kernel can then populate with the all the region info. + * item.data_ptr = (uintptr_t)&info, + * + * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); + * if (err) ... + * + * // We can now access each region in the array + * for (i = 0; i < info->num_regions; i++) { + * struct drm_i915_memory_region_info mr = info->regions[i]; + * u16 class = mr.region.class; + * u16 instance = mr.region.instance; + * + * .... + * } + * + * free(info); + */ +struct drm_i915_query_memory_regions { + /** @num_regions: Number of supported regions */ + __u32 num_regions; + + /** @rsvd: MBZ */ + __u32 rsvd[3]; + + /** @regions: Info about each supported region */ + struct drm_i915_memory_region_info regions[]; +}; + +#define DRM_I915_GEM_CREATE_EXT 0xdeadbeaf +#define DRM_IOCTL_I915_GEM_CREATE_EXT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE_EXT, struct drm_i915_gem_create_ext) + +/** + * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added + * extension support using struct i915_user_extension. + * + * Note that in the future we want to have our buffer flags here, at least for + * the stuff that is immutable. Previously we would have two ioctls, one to + * create the object with gem_create, and another to apply various parameters, + * however this creates some ambiguity for the params which are considered + * immutable. Also in general we're phasing out the various SET/GET ioctls. + */ +struct drm_i915_gem_create_ext { + /** + * @size: Requested size for the object. + * + * The (page-aligned) allocated size for the object will be returned. + * + * Note that for some devices we have might have further minimum + * page-size restrictions(larger than 4K), like for device local-memory. + * However in general the final size here should always reflect any + * rounding up, if for example using the I915_GEM_CREATE_EXT_MEMORY_REGIONS + * extension to place the object in device local-memory. + */ + __u64 size; + /** + * @handle: Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; + /** @flags: MBZ */ + __u32 flags; + /** + * @extensions: The chain of extensions to apply to this object. + * + * This will be useful in the future when we need to support several + * different extensions, and we need to apply more than one when + * creating the object. See struct i915_user_extension. + * + * If we don't supply any extensions then we get the same old gem_create + * behaviour. + * + * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see + * struct drm_i915_gem_create_ext_memory_regions. + */ +#define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0 + __u64 extensions; +}; + +/** + * struct drm_i915_gem_create_ext_memory_regions - The + * I915_GEM_CREATE_EXT_MEMORY_REGIONS extension. + * + * Set the object with the desired set of placements/regions in priority + * order. Each entry must be unique and supported by the device. + * + * This is provided as an array of struct drm_i915_gem_memory_class_instance, or + * an equivalent layout of class:instance pair encodings. See struct + * drm_i915_query_memory_regions and DRM_I915_QUERY_MEMORY_REGIONS for how to + * query the supported regions for a device. + * + * As an example, on discrete devices, if we wish to set the placement as + * device local-memory we can do something like: + * + * .. code-block:: C + * + * struct drm_i915_gem_memory_class_instance region_lmem = { + * .memory_class = I915_MEMORY_CLASS_DEVICE, + * .memory_instance = 0, + * }; + * struct drm_i915_gem_create_ext_memory_regions regions = { + * .base = { .name = I915_GEM_CREATE_EXT_MEMORY_REGIONS }, + * .regions = (uintptr_t)®ion_lmem, + * .num_regions = 1, + * }; + * struct drm_i915_gem_create_ext create_ext = { + * .size = 16 * PAGE_SIZE, + * .extensions = (uintptr_t)®ions, + * }; + * + * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); + * if (err) ... + * + * At which point we get the object handle in &drm_i915_gem_create_ext.handle, + * along with the final object size in &drm_i915_gem_create_ext.size, which + * should account for any rounding up, if required. + */ +struct drm_i915_gem_create_ext_memory_regions { + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + + /** @pad: MBZ */ + __u32 pad; + /** @num_regions: Number of elements in the @regions array. */ + __u32 num_regions; + /** + * @regions: The regions/placements array. + * + * An array of struct drm_i915_gem_memory_class_instance. + */ + __u64 regions; +}; diff --git a/Documentation/gpu/rfc/i915_gem_lmem.rst b/Documentation/gpu/rfc/i915_gem_lmem.rst new file mode 100644 index 000000000000..1d344c593018 --- /dev/null +++ b/Documentation/gpu/rfc/i915_gem_lmem.rst @@ -0,0 +1,131 @@ +========================= +I915 DG1/LMEM RFC Section +========================= + +Upstream plan +============= +For upstream the overall plan for landing all the DG1 stuff and turning it for +real, with all the uAPI bits is: + +* Merge basic HW enabling of DG1(still without pciid) +* Merge the uAPI bits behind special CONFIG_BROKEN(or so) flag + * At this point we can still make changes, but importantly this lets us + start running IGTs which can utilize local-memory in CI +* Convert over to TTM, make sure it all keeps working. Some of the work items: + * TTM shrinker for discrete + * dma_resv_lockitem for full dma_resv_lock, i.e not just trylock + * Use TTM CPU pagefault handler + * Route shmem backend over to TTM SYSTEM for discrete + * TTM purgeable object support + * Move i915 buddy allocator over to TTM + * MMAP ioctl mode(see `I915 MMAP`_) + * SET/GET ioctl caching(see `I915 SET/GET CACHING`_) +* Send RFC(with mesa-dev on cc) for final sign off on the uAPI +* Add pciid for DG1 and turn on uAPI for real + +New object placement and region query uAPI +========================================== +Starting from DG1 we need to give userspace the ability to allocate buffers from +device local-memory. Currently the driver supports gem_create, which can place +buffers in system memory via shmem, and the usual assortment of other +interfaces, like dumb buffers and userptr. + +To support this new capability, while also providing a uAPI which will work +beyond just DG1, we propose to offer three new bits of uAPI: + +DRM_I915_QUERY_MEMORY_REGIONS +----------------------------- +New query ID which allows userspace to discover the list of supported memory +regions(like system-memory and local-memory) for a given device. We identify +each region with a class and instance pair, which should be unique. The class +here would be DEVICE or SYSTEM, and the instance would be zero, on platforms +like DG1. + +Side note: The class/instance design is borrowed from our existing engine uAPI, +where we describe every physical engine in terms of its class, and the +particular instance, since we can have more than one per class. + +In the future we also want to expose more information which can further +describe the capabilities of a region. + +.. kernel-doc:: Documentation/gpu/rfc/i915_gem_lmem.h + :functions: drm_i915_gem_memory_class drm_i915_gem_memory_class_instance drm_i915_memory_region_info drm_i915_query_memory_regions + +GEM_CREATE_EXT +-------------- +New ioctl which is basically just gem_create but now allows userspace to provide +a chain of possible extensions. Note that if we don't provide any extensions and +set flags=0 then we get the exact same behaviour as gem_create. + +Side note: We also need to support PXP[1] in the near future, which is also +applicable to integrated platforms, and adds its own gem_create_ext extension, +which basically lets userspace mark a buffer as "protected". + +.. kernel-doc:: Documentation/gpu/rfc/i915_gem_lmem.h + :functions: drm_i915_gem_create_ext + +I915_GEM_CREATE_EXT_MEMORY_REGIONS +---------------------------------- +Implemented as an extension for gem_create_ext, we would now allow userspace to +optionally provide an immutable list of preferred placements at creation time, +in priority order, for a given buffer object. For the placements we expect +them each to use the class/instance encoding, as per the output of the regions +query. Having the list in priority order will be useful in the future when +placing an object, say during eviction. + +.. kernel-doc:: Documentation/gpu/rfc/i915_gem_lmem.h + :functions: drm_i915_gem_create_ext_memory_regions + +One fair criticism here is that this seems a little over-engineered[2]. If we +just consider DG1 then yes, a simple gem_create.flags or something is totally +all that's needed to tell the kernel to allocate the buffer in local-memory or +whatever. However looking to the future we need uAPI which can also support +upcoming Xe HP multi-tile architecture in a sane way, where there can be +multiple local-memory instances for a given device, and so using both class and +instance in our uAPI to describe regions is desirable, although specifically +for DG1 it's uninteresting, since we only have a single local-memory instance. + +Existing uAPI issues +==================== +Some potential issues we still need to resolve. + +I915 MMAP +--------- +In i915 there are multiple ways to MMAP GEM object, including mapping the same +object using different mapping types(WC vs WB), i.e multiple active mmaps per +object. TTM expects one MMAP at most for the lifetime of the object. If it +turns out that we have to backpedal here, there might be some potential +userspace fallout. + +I915 SET/GET CACHING +-------------------- +In i915 we have set/get_caching ioctl. TTM doesn't let us to change this, but +DG1 doesn't support non-snooped pcie transactions, so we can just always +allocate as WB for smem-only buffers. If/when our hw gains support for +non-snooped pcie transactions then we must fix this mode at allocation time as +a new GEM extension. + +This is related to the mmap problem, because in general (meaning, when we're +not running on intel cpus) the cpu mmap must not, ever, be inconsistent with +allocation mode. + +Possible idea is to let the kernel picks the mmap mode for userspace from the +following table: + +smem-only: WB. Userspace does not need to call clflush. + +smem+lmem: We only ever allow a single mode, so simply allocate this as uncached +memory, and always give userspace a WC mapping. GPU still does snooped access +here(assuming we can't turn it off like on DG1), which is a bit inefficient. + +lmem only: always WC + +This means on discrete you only get a single mmap mode, all others must be +rejected. That's probably going to be a new default mode or something like +that. + +Links +===== +[1] https://patchwork.freedesktop.org/series/86798/ + +[2] https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5599#note_553791 diff --git a/Documentation/gpu/rfc/index.rst b/Documentation/gpu/rfc/index.rst index a8621f7dab8b..05670442ca1b 100644 --- a/Documentation/gpu/rfc/index.rst +++ b/Documentation/gpu/rfc/index.rst @@ -15,3 +15,7 @@ host such documentation: * Once the code has landed move all the documentation to the right places in the main core, helper or driver sections. + +.. toctree:: + + i915_gem_lmem.rst -- cgit 1.4.1 From 36150bba44329d7a96e58498bfc91fee9a2de08c Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Thu, 29 Apr 2021 11:30:49 +0100 Subject: drm/i915: mark stolen as private MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the next patch we want to expose the supported regions to userspace, which can then be fed into the gem_create_ext placement extensions. For now treat stolen memory as private from userspace pov. Signed-off-by: Matthew Auld Cc: Joonas Lahtinen Cc: Thomas Hellström Cc: Daniele Ceraolo Spurio Cc: Lionel Landwerlin Cc: Jon Bloomfield Cc: Jordan Justen Cc: Daniel Vetter Cc: Kenneth Graunke Cc: Jason Ekstrand Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Cc: mesa-dev@lists.freedesktop.org Reviewed-by: Kenneth Graunke Link: https://patchwork.freedesktop.org/patch/msgid/20210429103056.407067-2-matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_stolen.c | 4 ++++ drivers/gpu/drm/i915/intel_memory_region.h | 1 + 2 files changed, 5 insertions(+) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index e1a32672bbe8..293f640faa0a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -803,6 +803,8 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915) intel_memory_region_set_name(mem, "stolen-local"); + mem->private = true; + return mem; } @@ -821,6 +823,8 @@ i915_gem_stolen_smem_setup(struct drm_i915_private *i915) intel_memory_region_set_name(mem, "stolen-system"); + mem->private = true; + return mem; } diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h index 4c8ec15af55f..942fc4f68764 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.h +++ b/drivers/gpu/drm/i915/intel_memory_region.h @@ -86,6 +86,7 @@ struct intel_memory_region { u16 instance; enum intel_region_id id; char name[16]; + bool private; /* not for userspace */ struct list_head reserved; -- cgit 1.4.1 From 710217292a61110a8ccf010cf6886d25e34bf024 Mon Sep 17 00:00:00 2001 From: Abdiel Janulgue Date: Thu, 29 Apr 2021 11:30:50 +0100 Subject: drm/i915/query: Expose memory regions through the query uAPI MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Returns the available memory region areas supported by the HW. v2(Daniel & Jason): - Add some kernel-doc, including example usage. - Drop all the extra rsvd v3(Jason & Tvrtko) - add back rsvd Signed-off-by: Abdiel Janulgue Signed-off-by: Matthew Auld Cc: Joonas Lahtinen Cc: Thomas Hellström Cc: Daniele Ceraolo Spurio Cc: Lionel Landwerlin Cc: Jon Bloomfield Cc: Jordan Justen Cc: Daniel Vetter Cc: Kenneth Graunke Cc: Jason Ekstrand Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Cc: mesa-dev@lists.freedesktop.org Reviewed-by: Kenneth Graunke Link: https://patchwork.freedesktop.org/patch/msgid/20210429103056.407067-3-matthew.auld@intel.com --- drivers/gpu/drm/i915/i915_query.c | 59 +++++++++++++ drivers/gpu/drm/i915/intel_memory_region.h | 8 +- include/uapi/drm/i915_drm.h | 134 +++++++++++++++++++++++++++++ 3 files changed, 196 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c index fed337ad7b68..5e2b909827f4 100644 --- a/drivers/gpu/drm/i915/i915_query.c +++ b/drivers/gpu/drm/i915/i915_query.c @@ -419,11 +419,70 @@ static int query_perf_config(struct drm_i915_private *i915, } } +static int query_memregion_info(struct drm_i915_private *i915, + struct drm_i915_query_item *query_item) +{ + struct drm_i915_query_memory_regions __user *query_ptr = + u64_to_user_ptr(query_item->data_ptr); + struct drm_i915_memory_region_info __user *info_ptr = + &query_ptr->regions[0]; + struct drm_i915_memory_region_info info = { }; + struct drm_i915_query_memory_regions query; + struct intel_memory_region *mr; + u32 total_length; + int ret, id, i; + + if (query_item->flags != 0) + return -EINVAL; + + total_length = sizeof(query); + for_each_memory_region(mr, i915, id) { + if (mr->private) + continue; + + total_length += sizeof(info); + } + + ret = copy_query_item(&query, sizeof(query), total_length, query_item); + if (ret != 0) + return ret; + + if (query.num_regions) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(query.rsvd); i++) { + if (query.rsvd[i]) + return -EINVAL; + } + + for_each_memory_region(mr, i915, id) { + if (mr->private) + continue; + + info.region.memory_class = mr->type; + info.region.memory_instance = mr->instance; + info.probed_size = mr->total; + info.unallocated_size = mr->avail; + + if (__copy_to_user(info_ptr, &info, sizeof(info))) + return -EFAULT; + + query.num_regions++; + info_ptr++; + } + + if (__copy_to_user(query_ptr, &query, sizeof(query))) + return -EFAULT; + + return total_length; +} + static int (* const i915_query_funcs[])(struct drm_i915_private *dev_priv, struct drm_i915_query_item *query_item) = { query_topology_info, query_engine_info, query_perf_config, + query_memregion_info, }; int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file) diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h index 942fc4f68764..7cd8e3d66a7f 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.h +++ b/drivers/gpu/drm/i915/intel_memory_region.h @@ -11,6 +11,7 @@ #include #include #include +#include #include "i915_buddy.h" @@ -19,12 +20,9 @@ struct drm_i915_gem_object; struct intel_memory_region; struct sg_table; -/** - * Base memory type - */ enum intel_memory_type { - INTEL_MEMORY_SYSTEM = 0, - INTEL_MEMORY_LOCAL, + INTEL_MEMORY_SYSTEM = I915_MEMORY_CLASS_SYSTEM, + INTEL_MEMORY_LOCAL = I915_MEMORY_CLASS_DEVICE, INTEL_MEMORY_STOLEN_SYSTEM, INTEL_MEMORY_STOLEN_LOCAL, }; diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 6a34243a7646..582ee6f7d595 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2230,6 +2230,7 @@ struct drm_i915_query_item { #define DRM_I915_QUERY_TOPOLOGY_INFO 1 #define DRM_I915_QUERY_ENGINE_INFO 2 #define DRM_I915_QUERY_PERF_CONFIG 3 +#define DRM_I915_QUERY_MEMORY_REGIONS 4 /* Must be kept compact -- no holes and well documented */ /** @@ -2464,6 +2465,139 @@ struct drm_i915_query_perf_config { __u8 data[]; }; +/** + * enum drm_i915_gem_memory_class - Supported memory classes + */ +enum drm_i915_gem_memory_class { + /** @I915_MEMORY_CLASS_SYSTEM: System memory */ + I915_MEMORY_CLASS_SYSTEM = 0, + /** @I915_MEMORY_CLASS_DEVICE: Device local-memory */ + I915_MEMORY_CLASS_DEVICE, +}; + +/** + * struct drm_i915_gem_memory_class_instance - Identify particular memory region + */ +struct drm_i915_gem_memory_class_instance { + /** @memory_class: See enum drm_i915_gem_memory_class */ + __u16 memory_class; + + /** @memory_instance: Which instance */ + __u16 memory_instance; +}; + +/** + * struct drm_i915_memory_region_info - Describes one region as known to the + * driver. + * + * Note that we reserve some stuff here for potential future work. As an example + * we might want expose the capabilities for a given region, which could include + * things like if the region is CPU mappable/accessible, what are the supported + * mapping types etc. + * + * Note that to extend struct drm_i915_memory_region_info and struct + * drm_i915_query_memory_regions in the future the plan is to do the following: + * + * .. code-block:: C + * + * struct drm_i915_memory_region_info { + * struct drm_i915_gem_memory_class_instance region; + * union { + * __u32 rsvd0; + * __u32 new_thing1; + * }; + * ... + * union { + * __u64 rsvd1[8]; + * struct { + * __u64 new_thing2; + * __u64 new_thing3; + * ... + * }; + * }; + * }; + * + * With this things should remain source compatible between versions for + * userspace, even as we add new fields. + * + * Note this is using both struct drm_i915_query_item and struct drm_i915_query. + * For this new query we are adding the new query id DRM_I915_QUERY_MEMORY_REGIONS + * at &drm_i915_query_item.query_id. + */ +struct drm_i915_memory_region_info { + /** @region: The class:instance pair encoding */ + struct drm_i915_gem_memory_class_instance region; + + /** @rsvd0: MBZ */ + __u32 rsvd0; + + /** @probed_size: Memory probed by the driver (-1 = unknown) */ + __u64 probed_size; + + /** @unallocated_size: Estimate of memory remaining (-1 = unknown) */ + __u64 unallocated_size; + + /** @rsvd1: MBZ */ + __u64 rsvd1[8]; +}; + +/** + * struct drm_i915_query_memory_regions + * + * The region info query enumerates all regions known to the driver by filling + * in an array of struct drm_i915_memory_region_info structures. + * + * Example for getting the list of supported regions: + * + * .. code-block:: C + * + * struct drm_i915_query_memory_regions *info; + * struct drm_i915_query_item item = { + * .query_id = DRM_I915_QUERY_MEMORY_REGIONS; + * }; + * struct drm_i915_query query = { + * .num_items = 1, + * .items_ptr = (uintptr_t)&item, + * }; + * int err, i; + * + * // First query the size of the blob we need, this needs to be large + * // enough to hold our array of regions. The kernel will fill out the + * // item.length for us, which is the number of bytes we need. + * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); + * if (err) ... + * + * info = calloc(1, item.length); + * // Now that we allocated the required number of bytes, we call the ioctl + * // again, this time with the data_ptr pointing to our newly allocated + * // blob, which the kernel can then populate with the all the region info. + * item.data_ptr = (uintptr_t)&info, + * + * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); + * if (err) ... + * + * // We can now access each region in the array + * for (i = 0; i < info->num_regions; i++) { + * struct drm_i915_memory_region_info mr = info->regions[i]; + * u16 class = mr.region.class; + * u16 instance = mr.region.instance; + * + * .... + * } + * + * free(info); + */ +struct drm_i915_query_memory_regions { + /** @num_regions: Number of supported regions */ + __u32 num_regions; + + /** @rsvd: MBZ */ + __u32 rsvd[3]; + + /** @regions: Info about each supported region */ + struct drm_i915_memory_region_info regions[]; +}; + #if defined(__cplusplus) } #endif -- cgit 1.4.1 From 357814f878f97a82fd7b4146e1a50822847c4ed7 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Thu, 29 Apr 2021 11:30:51 +0100 Subject: drm/i915: rework gem_create flow for upcoming extensions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With the upcoming gem_create_ext we want to be able create a "vanilla" object upfront and pass that directly to the extensions, before actually initialising the object. Functionally this should be the same expect we now feed the object into the lower-level region specific init_object. Signed-off-by: Matthew Auld Cc: Joonas Lahtinen Cc: Thomas Hellström Cc: Daniele Ceraolo Spurio Cc: Lionel Landwerlin Cc: Jon Bloomfield Cc: Jordan Justen Cc: Daniel Vetter Cc: Kenneth Graunke Cc: Jason Ekstrand Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Cc: mesa-dev@lists.freedesktop.org Reviewed-by: Kenneth Graunke Link: https://patchwork.freedesktop.org/patch/msgid/20210429103056.407067-4-matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_create.c | 92 +++++++++++++++++++++--------- 1 file changed, 65 insertions(+), 27 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c index 45d60e3d98e3..409226df0dd2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_create.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c @@ -7,41 +7,51 @@ #include "gem/i915_gem_region.h" #include "i915_drv.h" +#include "i915_trace.h" + +static int i915_gem_publish(struct drm_i915_gem_object *obj, + struct drm_file *file, + u64 *size_p, + u32 *handle_p) +{ + u64 size = obj->base.size; + int ret; + + ret = drm_gem_handle_create(file, &obj->base, handle_p); + /* drop reference from allocate - handle holds it now */ + i915_gem_object_put(obj); + if (ret) + return ret; + + *size_p = size; + return 0; +} static int -i915_gem_create(struct drm_file *file, - struct intel_memory_region *mr, - u64 *size_p, - u32 *handle_p) +i915_gem_setup(struct drm_i915_gem_object *obj, + struct intel_memory_region *mr, + u64 size) { - struct drm_i915_gem_object *obj; - u32 handle; - u64 size; int ret; GEM_BUG_ON(!is_power_of_2(mr->min_page_size)); - size = round_up(*size_p, mr->min_page_size); + size = round_up(size, mr->min_page_size); if (size == 0) return -EINVAL; /* For most of the ABI (e.g. mmap) we think in system pages */ GEM_BUG_ON(!IS_ALIGNED(size, PAGE_SIZE)); - /* Allocate the new object */ - obj = i915_gem_object_create_region(mr, size, 0); - if (IS_ERR(obj)) - return PTR_ERR(obj); - - GEM_BUG_ON(size != obj->base.size); + if (i915_gem_object_size_2big(size)) + return -E2BIG; - ret = drm_gem_handle_create(file, &obj->base, &handle); - /* drop reference from allocate - handle holds it now */ - i915_gem_object_put(obj); + ret = mr->ops->init_object(mr, obj, size, 0); if (ret) return ret; - *handle_p = handle; - *size_p = size; + GEM_BUG_ON(size != obj->base.size); + + trace_i915_gem_object_create(obj); return 0; } @@ -50,9 +60,11 @@ i915_gem_dumb_create(struct drm_file *file, struct drm_device *dev, struct drm_mode_create_dumb *args) { + struct drm_i915_gem_object *obj; enum intel_memory_type mem_type; int cpp = DIV_ROUND_UP(args->bpp, 8); u32 format; + int ret; switch (cpp) { case 1: @@ -85,10 +97,22 @@ i915_gem_dumb_create(struct drm_file *file, if (HAS_LMEM(to_i915(dev))) mem_type = INTEL_MEMORY_LOCAL; - return i915_gem_create(file, - intel_memory_region_by_type(to_i915(dev), - mem_type), - &args->size, &args->handle); + obj = i915_gem_object_alloc(); + if (!obj) + return -ENOMEM; + + ret = i915_gem_setup(obj, + intel_memory_region_by_type(to_i915(dev), + mem_type), + args->size); + if (ret) + goto object_free; + + return i915_gem_publish(obj, file, &args->size, &args->handle); + +object_free: + i915_gem_object_free(obj); + return ret; } /** @@ -103,11 +127,25 @@ i915_gem_create_ioctl(struct drm_device *dev, void *data, { struct drm_i915_private *i915 = to_i915(dev); struct drm_i915_gem_create *args = data; + struct drm_i915_gem_object *obj; + int ret; i915_gem_flush_free_objects(i915); - return i915_gem_create(file, - intel_memory_region_by_type(i915, - INTEL_MEMORY_SYSTEM), - &args->size, &args->handle); + obj = i915_gem_object_alloc(); + if (!obj) + return -ENOMEM; + + ret = i915_gem_setup(obj, + intel_memory_region_by_type(i915, + INTEL_MEMORY_SYSTEM), + args->size); + if (ret) + goto object_free; + + return i915_gem_publish(obj, file, &args->size, &args->handle); + +object_free: + i915_gem_object_free(obj); + return ret; } -- cgit 1.4.1 From ebcb40298947bdb0622e53c69734e6b4fb64b348 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Thu, 29 Apr 2021 11:30:52 +0100 Subject: drm/i915/uapi: introduce drm_i915_gem_create_ext Same old gem_create but with now with extensions support. This is needed to support various upcoming usecases. v2:(Chris) - Use separate ioctl number for gem_create_ext, instead of hijacking the existing gem_create ioctl, otherwise we run into the issue with being unable to detect if the kernel supports the new extension behaviour. - We now have gem_create_ext.flags, which should be zeroed. - I915_GEM_CREATE_EXT_SETPARAM value is now zero, since this is the index into our array of extensions. - Setup a "vanilla" object which we can directly apply our extensions to. v3:(Daniel & Jason) - drop I915_GEM_CREATE_EXT_SETPARAM. Instead just have each extension do one thing only, instead of generic setparam which can cover various use cases. - add some kernel-doc. Signed-off-by: Matthew Auld Signed-off-by: CQ Tang Cc: Joonas Lahtinen Cc: Daniele Ceraolo Spurio Cc: Lionel Landwerlin Cc: Jordan Justen Cc: Daniel Vetter Cc: Kenneth Graunke Cc: Jason Ekstrand Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Cc: mesa-dev@lists.freedesktop.org Reviewed-by: Kenneth Graunke Link: https://patchwork.freedesktop.org/patch/msgid/20210429103056.407067-5-matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_create.c | 56 ++++++++++++++++++++++++++++++ drivers/gpu/drm/i915/gem/i915_gem_ioctls.h | 2 ++ drivers/gpu/drm/i915/i915_drv.c | 1 + include/uapi/drm/i915_drm.h | 42 ++++++++++++++++++++++ 4 files changed, 101 insertions(+) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c index 409226df0dd2..1e82633a3898 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_create.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c @@ -8,6 +8,7 @@ #include "i915_drv.h" #include "i915_trace.h" +#include "i915_user_extensions.h" static int i915_gem_publish(struct drm_i915_gem_object *obj, struct drm_file *file, @@ -149,3 +150,58 @@ object_free: i915_gem_object_free(obj); return ret; } + +struct create_ext { + struct drm_i915_private *i915; + struct drm_i915_gem_object *vanilla_object; +}; + +static const i915_user_extension_fn create_extensions[] = { +}; + +/** + * Creates a new mm object and returns a handle to it. + * @dev: drm device pointer + * @data: ioctl data blob + * @file: drm file pointer + */ +int +i915_gem_create_ext_ioctl(struct drm_device *dev, void *data, + struct drm_file *file) +{ + struct drm_i915_private *i915 = to_i915(dev); + struct drm_i915_gem_create_ext *args = data; + struct create_ext ext_data = { .i915 = i915 }; + struct drm_i915_gem_object *obj; + int ret; + + if (args->flags) + return -EINVAL; + + i915_gem_flush_free_objects(i915); + + obj = i915_gem_object_alloc(); + if (!obj) + return -ENOMEM; + + ext_data.vanilla_object = obj; + ret = i915_user_extensions(u64_to_user_ptr(args->extensions), + create_extensions, + ARRAY_SIZE(create_extensions), + &ext_data); + if (ret) + goto object_free; + + ret = i915_gem_setup(obj, + intel_memory_region_by_type(i915, + INTEL_MEMORY_SYSTEM), + args->size); + if (ret) + goto object_free; + + return i915_gem_publish(obj, file, &args->size, &args->handle); + +object_free: + i915_gem_object_free(obj); + return ret; +} diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h b/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h index 7fd22f3efbef..28d6526e32ab 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h @@ -14,6 +14,8 @@ int i915_gem_busy_ioctl(struct drm_device *dev, void *data, struct drm_file *file); int i915_gem_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file); +int i915_gem_create_ext_ioctl(struct drm_device *dev, void *data, + struct drm_file *file); int i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data, struct drm_file *file); int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data, diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 3286bcd0a6d5..f50f7b4ff541 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1705,6 +1705,7 @@ static const struct drm_ioctl_desc i915_ioctls[] = { DRM_IOCTL_DEF_DRV(I915_GEM_ENTERVT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), DRM_IOCTL_DEF_DRV(I915_GEM_LEAVEVT, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), DRM_IOCTL_DEF_DRV(I915_GEM_CREATE, i915_gem_create_ioctl, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_CREATE_EXT, i915_gem_create_ext_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_GEM_PREAD, i915_gem_pread_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_GEM_PWRITE, i915_gem_pwrite_ioctl, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_GEM_MMAP, i915_gem_mmap_ioctl, DRM_RENDER_ALLOW), diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 582ee6f7d595..9ab609e0cabb 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -406,6 +406,7 @@ typedef struct _drm_i915_sarea { #define DRM_I915_QUERY 0x39 #define DRM_I915_GEM_VM_CREATE 0x3a #define DRM_I915_GEM_VM_DESTROY 0x3b +#define DRM_I915_GEM_CREATE_EXT 0x3c /* Must be kept compact -- no holes */ #define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) @@ -438,6 +439,7 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_GEM_ENTERVT DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_ENTERVT) #define DRM_IOCTL_I915_GEM_LEAVEVT DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_LEAVEVT) #define DRM_IOCTL_I915_GEM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE, struct drm_i915_gem_create) +#define DRM_IOCTL_I915_GEM_CREATE_EXT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE_EXT, struct drm_i915_gem_create_ext) #define DRM_IOCTL_I915_GEM_PREAD DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PREAD, struct drm_i915_gem_pread) #define DRM_IOCTL_I915_GEM_PWRITE DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite) #define DRM_IOCTL_I915_GEM_MMAP DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap) @@ -2598,6 +2600,46 @@ struct drm_i915_query_memory_regions { struct drm_i915_memory_region_info regions[]; }; +/** + * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added + * extension support using struct i915_user_extension. + * + * Note that in the future we want to have our buffer flags here, at least for + * the stuff that is immutable. Previously we would have two ioctls, one to + * create the object with gem_create, and another to apply various parameters, + * however this creates some ambiguity for the params which are considered + * immutable. Also in general we're phasing out the various SET/GET ioctls. + */ +struct drm_i915_gem_create_ext { + /** + * @size: Requested size for the object. + * + * The (page-aligned) allocated size for the object will be returned. + * + */ + __u64 size; + /** + * @handle: Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; + /** @flags: MBZ */ + __u32 flags; + /** + * @extensions: The chain of extensions to apply to this object. + * + * This will be useful in the future when we need to support several + * different extensions, and we need to apply more than one when + * creating the object. See struct i915_user_extension. + * + * If we don't supply any extensions then we get the same old gem_create + * behaviour. + * + */ + __u64 extensions; +}; + #if defined(__cplusplus) } #endif -- cgit 1.4.1 From 2459e56fd8af0b47fcbfbdff2fdc02e4077680ec Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Thu, 29 Apr 2021 11:30:53 +0100 Subject: drm/i915/uapi: implement object placement extension Add new extension to support setting an immutable-priority-list of potential placements, at creation time. If we use the normal gem_create or gem_create_ext without the extensions/placements then we still get the old behaviour with only placing the object in system memory. v2(Daniel & Jason): - Add a bunch of kernel-doc - Simplify design for placements extension Testcase: igt/gem_create/create-ext-placement-sanity-check Testcase: igt/gem_create/create-ext-placement-each Testcase: igt/gem_create/create-ext-placement-all Signed-off-by: Matthew Auld Signed-off-by: CQ Tang Cc: Joonas Lahtinen Cc: Daniele Ceraolo Spurio Cc: Lionel Landwerlin Cc: Jordan Justen Cc: Daniel Vetter Cc: Kenneth Graunke Cc: Jason Ekstrand Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Cc: mesa-dev@lists.freedesktop.org Reviewed-by: Kenneth Graunke Link: https://patchwork.freedesktop.org/patch/msgid/20210429103056.407067-6-matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_create.c | 218 +++++++++++++++++++-- drivers/gpu/drm/i915/gem/i915_gem_object.c | 3 + drivers/gpu/drm/i915/gem/i915_gem_object_types.h | 6 + drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c | 26 +++ drivers/gpu/drm/i915/intel_memory_region.c | 16 ++ drivers/gpu/drm/i915/intel_memory_region.h | 4 + include/uapi/drm/i915_drm.h | 62 ++++++ 7 files changed, 318 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c index 1e82633a3898..957f790c644b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_create.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c @@ -4,12 +4,51 @@ */ #include "gem/i915_gem_ioctls.h" +#include "gem/i915_gem_lmem.h" #include "gem/i915_gem_region.h" #include "i915_drv.h" #include "i915_trace.h" #include "i915_user_extensions.h" +static u32 object_max_page_size(struct drm_i915_gem_object *obj) +{ + u32 max_page_size = 0; + int i; + + for (i = 0; i < obj->mm.n_placements; i++) { + struct intel_memory_region *mr = obj->mm.placements[i]; + + GEM_BUG_ON(!is_power_of_2(mr->min_page_size)); + max_page_size = max_t(u32, max_page_size, mr->min_page_size); + } + + GEM_BUG_ON(!max_page_size); + return max_page_size; +} + +static void object_set_placements(struct drm_i915_gem_object *obj, + struct intel_memory_region **placements, + unsigned int n_placements) +{ + GEM_BUG_ON(!n_placements); + + /* + * For the common case of one memory region, skip storing an + * allocated array and just point at the region directly. + */ + if (n_placements == 1) { + struct intel_memory_region *mr = placements[0]; + struct drm_i915_private *i915 = mr->i915; + + obj->mm.placements = &i915->mm.regions[mr->id]; + obj->mm.n_placements = 1; + } else { + obj->mm.placements = placements; + obj->mm.n_placements = n_placements; + } +} + static int i915_gem_publish(struct drm_i915_gem_object *obj, struct drm_file *file, u64 *size_p, @@ -29,14 +68,12 @@ static int i915_gem_publish(struct drm_i915_gem_object *obj, } static int -i915_gem_setup(struct drm_i915_gem_object *obj, - struct intel_memory_region *mr, - u64 size) +i915_gem_setup(struct drm_i915_gem_object *obj, u64 size) { + struct intel_memory_region *mr = obj->mm.placements[0]; int ret; - GEM_BUG_ON(!is_power_of_2(mr->min_page_size)); - size = round_up(size, mr->min_page_size); + size = round_up(size, object_max_page_size(obj)); if (size == 0) return -EINVAL; @@ -62,6 +99,7 @@ i915_gem_dumb_create(struct drm_file *file, struct drm_mode_create_dumb *args) { struct drm_i915_gem_object *obj; + struct intel_memory_region *mr; enum intel_memory_type mem_type; int cpp = DIV_ROUND_UP(args->bpp, 8); u32 format; @@ -102,10 +140,10 @@ i915_gem_dumb_create(struct drm_file *file, if (!obj) return -ENOMEM; - ret = i915_gem_setup(obj, - intel_memory_region_by_type(to_i915(dev), - mem_type), - args->size); + mr = intel_memory_region_by_type(to_i915(dev), mem_type); + object_set_placements(obj, &mr, 1); + + ret = i915_gem_setup(obj, args->size); if (ret) goto object_free; @@ -129,6 +167,7 @@ i915_gem_create_ioctl(struct drm_device *dev, void *data, struct drm_i915_private *i915 = to_i915(dev); struct drm_i915_gem_create *args = data; struct drm_i915_gem_object *obj; + struct intel_memory_region *mr; int ret; i915_gem_flush_free_objects(i915); @@ -137,10 +176,10 @@ i915_gem_create_ioctl(struct drm_device *dev, void *data, if (!obj) return -ENOMEM; - ret = i915_gem_setup(obj, - intel_memory_region_by_type(i915, - INTEL_MEMORY_SYSTEM), - args->size); + mr = intel_memory_region_by_type(i915, INTEL_MEMORY_SYSTEM); + object_set_placements(obj, &mr, 1); + + ret = i915_gem_setup(obj, args->size); if (ret) goto object_free; @@ -156,7 +195,144 @@ struct create_ext { struct drm_i915_gem_object *vanilla_object; }; +static void repr_placements(char *buf, size_t size, + struct intel_memory_region **placements, + int n_placements) +{ + int i; + + buf[0] = '\0'; + + for (i = 0; i < n_placements; i++) { + struct intel_memory_region *mr = placements[i]; + int r; + + r = snprintf(buf, size, "\n %s -> { class: %d, inst: %d }", + mr->name, mr->type, mr->instance); + if (r >= size) + return; + + buf += r; + size -= r; + } +} + +static int set_placements(struct drm_i915_gem_create_ext_memory_regions *args, + struct create_ext *ext_data) +{ + struct drm_i915_private *i915 = ext_data->i915; + struct drm_i915_gem_memory_class_instance __user *uregions = + u64_to_user_ptr(args->regions); + struct drm_i915_gem_object *obj = ext_data->vanilla_object; + struct intel_memory_region **placements; + u32 mask; + int i, ret = 0; + + if (args->pad) { + drm_dbg(&i915->drm, "pad should be zero\n"); + ret = -EINVAL; + } + + if (!args->num_regions) { + drm_dbg(&i915->drm, "num_regions is zero\n"); + ret = -EINVAL; + } + + if (args->num_regions > ARRAY_SIZE(i915->mm.regions)) { + drm_dbg(&i915->drm, "num_regions is too large\n"); + ret = -EINVAL; + } + + if (ret) + return ret; + + placements = kmalloc_array(args->num_regions, + sizeof(struct intel_memory_region *), + GFP_KERNEL); + if (!placements) + return -ENOMEM; + + mask = 0; + for (i = 0; i < args->num_regions; i++) { + struct drm_i915_gem_memory_class_instance region; + struct intel_memory_region *mr; + + if (copy_from_user(®ion, uregions, sizeof(region))) { + ret = -EFAULT; + goto out_free; + } + + mr = intel_memory_region_lookup(i915, + region.memory_class, + region.memory_instance); + if (!mr || mr->private) { + drm_dbg(&i915->drm, "Device is missing region { class: %d, inst: %d } at index = %d\n", + region.memory_class, region.memory_instance, i); + ret = -EINVAL; + goto out_dump; + } + + if (mask & BIT(mr->id)) { + drm_dbg(&i915->drm, "Found duplicate placement %s -> { class: %d, inst: %d } at index = %d\n", + mr->name, region.memory_class, + region.memory_instance, i); + ret = -EINVAL; + goto out_dump; + } + + placements[i] = mr; + mask |= BIT(mr->id); + + ++uregions; + } + + if (obj->mm.placements) { + ret = -EINVAL; + goto out_dump; + } + + object_set_placements(obj, placements, args->num_regions); + if (args->num_regions == 1) + kfree(placements); + + return 0; + +out_dump: + if (1) { + char buf[256]; + + if (obj->mm.placements) { + repr_placements(buf, + sizeof(buf), + obj->mm.placements, + obj->mm.n_placements); + drm_dbg(&i915->drm, + "Placements were already set in previous EXT. Existing placements: %s\n", + buf); + } + + repr_placements(buf, sizeof(buf), placements, i); + drm_dbg(&i915->drm, "New placements(so far validated): %s\n", buf); + } + +out_free: + kfree(placements); + return ret; +} + +static int ext_set_placements(struct i915_user_extension __user *base, + void *data) +{ + struct drm_i915_gem_create_ext_memory_regions ext; + + if (copy_from_user(&ext, base, sizeof(ext))) + return -EFAULT; + + return set_placements(&ext, data); +} + static const i915_user_extension_fn create_extensions[] = { + [I915_GEM_CREATE_EXT_MEMORY_REGIONS] = ext_set_placements, }; /** @@ -172,6 +348,7 @@ i915_gem_create_ext_ioctl(struct drm_device *dev, void *data, struct drm_i915_private *i915 = to_i915(dev); struct drm_i915_gem_create_ext *args = data; struct create_ext ext_data = { .i915 = i915 }; + struct intel_memory_region **placements_ext; struct drm_i915_gem_object *obj; int ret; @@ -189,19 +366,26 @@ i915_gem_create_ext_ioctl(struct drm_device *dev, void *data, create_extensions, ARRAY_SIZE(create_extensions), &ext_data); + placements_ext = obj->mm.placements; if (ret) goto object_free; - ret = i915_gem_setup(obj, - intel_memory_region_by_type(i915, - INTEL_MEMORY_SYSTEM), - args->size); + if (!placements_ext) { + struct intel_memory_region *mr = + intel_memory_region_by_type(i915, INTEL_MEMORY_SYSTEM); + + object_set_placements(obj, &mr, 1); + } + + ret = i915_gem_setup(obj, args->size); if (ret) goto object_free; return i915_gem_publish(obj, file, &args->size, &args->handle); object_free: + if (obj->mm.n_placements > 1) + kfree(placements_ext); i915_gem_object_free(obj); return ret; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index ea74cbca95be..28144410df86 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -249,6 +249,9 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915, if (obj->ops->release) obj->ops->release(obj); + if (obj->mm.n_placements > 1) + kfree(obj->mm.placements); + /* But keep the pointer alive for RCU-protected lookups */ call_rcu(&obj->rcu, __i915_gem_free_object_rcu); cond_resched(); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 8e485cb3343c..69d6e54bc569 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -219,6 +219,12 @@ struct drm_i915_gem_object { atomic_t pages_pin_count; atomic_t shrink_pin; + /** + * Priority list of potential placements for this object. + */ + struct intel_memory_region **placements; + int n_placements; + /** * Memory region for this object. */ diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index 5cf6df49c333..05a3b29f545e 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -842,6 +842,24 @@ static bool can_mmap(struct drm_i915_gem_object *obj, enum i915_mmap_type type) return true; } +static void object_set_placements(struct drm_i915_gem_object *obj, + struct intel_memory_region **placements, + unsigned int n_placements) +{ + GEM_BUG_ON(!n_placements); + + if (n_placements == 1) { + struct drm_i915_private *i915 = to_i915(obj->base.dev); + struct intel_memory_region *mr = placements[0]; + + obj->mm.placements = &i915->mm.regions[mr->id]; + obj->mm.n_placements = 1; + } else { + obj->mm.placements = placements; + obj->mm.n_placements = n_placements; + } +} + #define expand32(x) (((x) << 0) | ((x) << 8) | ((x) << 16) | ((x) << 24)) static int __igt_mmap(struct drm_i915_private *i915, struct drm_i915_gem_object *obj, @@ -950,6 +968,8 @@ static int igt_mmap(void *arg) if (IS_ERR(obj)) return PTR_ERR(obj); + object_set_placements(obj, &mr, 1); + err = __igt_mmap(i915, obj, I915_MMAP_TYPE_GTT); if (err == 0) err = __igt_mmap(i915, obj, I915_MMAP_TYPE_WC); @@ -1068,6 +1088,8 @@ static int igt_mmap_access(void *arg) if (IS_ERR(obj)) return PTR_ERR(obj); + object_set_placements(obj, &mr, 1); + err = __igt_mmap_access(i915, obj, I915_MMAP_TYPE_GTT); if (err == 0) err = __igt_mmap_access(i915, obj, I915_MMAP_TYPE_WB); @@ -1211,6 +1233,8 @@ static int igt_mmap_gpu(void *arg) if (IS_ERR(obj)) return PTR_ERR(obj); + object_set_placements(obj, &mr, 1); + err = __igt_mmap_gpu(i915, obj, I915_MMAP_TYPE_GTT); if (err == 0) err = __igt_mmap_gpu(i915, obj, I915_MMAP_TYPE_WC); @@ -1354,6 +1378,8 @@ static int igt_mmap_revoke(void *arg) if (IS_ERR(obj)) return PTR_ERR(obj); + object_set_placements(obj, &mr, 1); + err = __igt_mmap_revoke(i915, obj, I915_MMAP_TYPE_GTT); if (err == 0) err = __igt_mmap_revoke(i915, obj, I915_MMAP_TYPE_WC); diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c index 481a487faca6..d98e8b81d322 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.c +++ b/drivers/gpu/drm/i915/intel_memory_region.c @@ -28,6 +28,22 @@ static const struct { }, }; +struct intel_memory_region * +intel_memory_region_lookup(struct drm_i915_private *i915, + u16 class, u16 instance) +{ + struct intel_memory_region *mr; + int id; + + /* XXX: consider maybe converting to an rb tree at some point */ + for_each_memory_region(mr, i915, id) { + if (mr->type == class && mr->instance == instance) + return mr; + } + + return NULL; +} + struct intel_memory_region * intel_memory_region_by_type(struct drm_i915_private *i915, enum intel_memory_type mem_type) diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h index 7cd8e3d66a7f..d24ce5a0b30b 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.h +++ b/drivers/gpu/drm/i915/intel_memory_region.h @@ -97,6 +97,10 @@ struct intel_memory_region { } objects; }; +struct intel_memory_region * +intel_memory_region_lookup(struct drm_i915_private *i915, + u16 class, u16 instance); + int intel_memory_region_init_buddy(struct intel_memory_region *mem); void intel_memory_region_release_buddy(struct intel_memory_region *mem); diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 9ab609e0cabb..c2c7759b7d2e 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -2616,6 +2616,11 @@ struct drm_i915_gem_create_ext { * * The (page-aligned) allocated size for the object will be returned. * + * Note that for some devices we have might have further minimum + * page-size restrictions(larger than 4K), like for device local-memory. + * However in general the final size here should always reflect any + * rounding up, if for example using the I915_GEM_CREATE_EXT_MEMORY_REGIONS + * extension to place the object in device local-memory. */ __u64 size; /** @@ -2636,10 +2641,67 @@ struct drm_i915_gem_create_ext { * If we don't supply any extensions then we get the same old gem_create * behaviour. * + * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see + * struct drm_i915_gem_create_ext_memory_regions. */ +#define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0 __u64 extensions; }; +/** + * struct drm_i915_gem_create_ext_memory_regions - The + * I915_GEM_CREATE_EXT_MEMORY_REGIONS extension. + * + * Set the object with the desired set of placements/regions in priority + * order. Each entry must be unique and supported by the device. + * + * This is provided as an array of struct drm_i915_gem_memory_class_instance, or + * an equivalent layout of class:instance pair encodings. See struct + * drm_i915_query_memory_regions and DRM_I915_QUERY_MEMORY_REGIONS for how to + * query the supported regions for a device. + * + * As an example, on discrete devices, if we wish to set the placement as + * device local-memory we can do something like: + * + * .. code-block:: C + * + * struct drm_i915_gem_memory_class_instance region_lmem = { + * .memory_class = I915_MEMORY_CLASS_DEVICE, + * .memory_instance = 0, + * }; + * struct drm_i915_gem_create_ext_memory_regions regions = { + * .base = { .name = I915_GEM_CREATE_EXT_MEMORY_REGIONS }, + * .regions = (uintptr_t)®ion_lmem, + * .num_regions = 1, + * }; + * struct drm_i915_gem_create_ext create_ext = { + * .size = 16 * PAGE_SIZE, + * .extensions = (uintptr_t)®ions, + * }; + * + * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); + * if (err) ... + * + * At which point we get the object handle in &drm_i915_gem_create_ext.handle, + * along with the final object size in &drm_i915_gem_create_ext.size, which + * should account for any rounding up, if required. + */ +struct drm_i915_gem_create_ext_memory_regions { + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + + /** @pad: MBZ */ + __u32 pad; + /** @num_regions: Number of elements in the @regions array. */ + __u32 num_regions; + /** + * @regions: The regions/placements array. + * + * An array of struct drm_i915_gem_memory_class_instance. + */ + __u64 regions; +}; + #if defined(__cplusplus) } #endif -- cgit 1.4.1 From 4f869f1dbd7eac42f3d4b129b8c941de54de77bf Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Thu, 29 Apr 2021 11:30:54 +0100 Subject: drm/i915/lmem: support optional CPU clearing for special internal use MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For some internal device local-memory objects it would be useful to have an option to CPU clear the pages upon gathering the backing store. Note that this might be before the blitter is useable, which is the case for some internal GuC objects. Signed-off-by: Matthew Auld Cc: Joonas Lahtinen Cc: Thomas Hellström Cc: Daniele Ceraolo Spurio Cc: Lionel Landwerlin Cc: Jon Bloomfield Cc: Jordan Justen Cc: Daniel Vetter Cc: Kenneth Graunke Cc: Jason Ekstrand Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Cc: mesa-dev@lists.freedesktop.org Acked-by: Kenneth Graunke Link: https://patchwork.freedesktop.org/patch/msgid/20210429103056.407067-7-matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_object_types.h | 8 +- drivers/gpu/drm/i915/gem/i915_gem_region.c | 22 ++++++ .../gpu/drm/i915/selftests/intel_memory_region.c | 87 +++++++++++++++++++++- 3 files changed, 113 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 69d6e54bc569..0727d0c76aa0 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -172,11 +172,13 @@ struct drm_i915_gem_object { #define I915_BO_ALLOC_CONTIGUOUS BIT(0) #define I915_BO_ALLOC_VOLATILE BIT(1) #define I915_BO_ALLOC_STRUCT_PAGE BIT(2) +#define I915_BO_ALLOC_CPU_CLEAR BIT(3) #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | \ I915_BO_ALLOC_VOLATILE | \ - I915_BO_ALLOC_STRUCT_PAGE) -#define I915_BO_READONLY BIT(3) -#define I915_TILING_QUIRK_BIT 4 /* unknown swizzling; do not release! */ + I915_BO_ALLOC_STRUCT_PAGE | \ + I915_BO_ALLOC_CPU_CLEAR) +#define I915_BO_READONLY BIT(4) +#define I915_TILING_QUIRK_BIT 5 /* unknown swizzling; do not release! */ /* * Is the object to be mapped as read-only to the GPU diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c index 6a84fb6dde24..ce8fcfc54079 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_region.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c @@ -95,6 +95,28 @@ i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj) sg_mark_end(sg); i915_sg_trim(st); + /* Intended for kernel internal use only */ + if (obj->flags & I915_BO_ALLOC_CPU_CLEAR) { + struct scatterlist *sg; + unsigned long i; + + for_each_sg(st->sgl, sg, st->nents, i) { + unsigned int length; + void __iomem *vaddr; + dma_addr_t daddr; + + daddr = sg_dma_address(sg); + daddr -= mem->region.start; + length = sg_dma_len(sg); + + vaddr = io_mapping_map_wc(&mem->iomap, daddr, length); + memset64((void __force *)vaddr, 0, length / sizeof(u64)); + io_mapping_unmap(vaddr); + } + + wmb(); + } + __i915_gem_object_set_pages(obj, st, sg_page_sizes); return 0; diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c index a5fc0bf3feb9..f85fd8cbfbf5 100644 --- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c +++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c @@ -513,7 +513,7 @@ static int igt_cpu_check(struct drm_i915_gem_object *obj, u32 dword, u32 val) if (err) return err; - ptr = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC); + ptr = i915_gem_object_pin_map(obj, I915_MAP_WC); if (IS_ERR(ptr)) return PTR_ERR(ptr); @@ -593,7 +593,9 @@ static int igt_gpu_write(struct i915_gem_context *ctx, if (err) break; + i915_gem_object_lock(obj, NULL); err = igt_cpu_check(obj, dword, rng); + i915_gem_object_unlock(obj); if (err) break; } while (!__igt_timeout(end_time, NULL)); @@ -629,6 +631,88 @@ out_put: return err; } +static int igt_lmem_create_cleared_cpu(void *arg) +{ + struct drm_i915_private *i915 = arg; + I915_RND_STATE(prng); + IGT_TIMEOUT(end_time); + u32 size, i; + int err; + + i915_gem_drain_freed_objects(i915); + + size = max_t(u32, PAGE_SIZE, i915_prandom_u32_max_state(SZ_32M, &prng)); + size = round_up(size, PAGE_SIZE); + i = 0; + + do { + struct drm_i915_gem_object *obj; + unsigned int flags; + u32 dword, val; + void *vaddr; + + /* + * Alternate between cleared and uncleared allocations, while + * also dirtying the pages each time to check that the pages are + * always cleared if requested, since we should get some overlap + * of the underlying pages, if not all, since we are the only + * user. + */ + + flags = I915_BO_ALLOC_CPU_CLEAR; + if (i & 1) + flags = 0; + + obj = i915_gem_object_create_lmem(i915, size, flags); + if (IS_ERR(obj)) + return PTR_ERR(obj); + + i915_gem_object_lock(obj, NULL); + err = i915_gem_object_pin_pages(obj); + if (err) + goto out_put; + + dword = i915_prandom_u32_max_state(PAGE_SIZE / sizeof(u32), + &prng); + + if (flags & I915_BO_ALLOC_CPU_CLEAR) { + err = igt_cpu_check(obj, dword, 0); + if (err) { + pr_err("%s failed with size=%u, flags=%u\n", + __func__, size, flags); + goto out_unpin; + } + } + + vaddr = i915_gem_object_pin_map(obj, I915_MAP_WC); + if (IS_ERR(vaddr)) { + err = PTR_ERR(vaddr); + goto out_unpin; + } + + val = prandom_u32_state(&prng); + + memset32(vaddr, val, obj->base.size / sizeof(u32)); + + i915_gem_object_flush_map(obj); + i915_gem_object_unpin_map(obj); +out_unpin: + i915_gem_object_unpin_pages(obj); + __i915_gem_object_put_pages(obj); +out_put: + i915_gem_object_unlock(obj); + i915_gem_object_put(obj); + + if (err) + break; + ++i; + } while (!__igt_timeout(end_time, NULL)); + + pr_info("%s completed (%u) iterations\n", __func__, i); + + return err; +} + static int igt_lmem_write_gpu(void *arg) { struct drm_i915_private *i915 = arg; @@ -1043,6 +1127,7 @@ int intel_memory_region_live_selftests(struct drm_i915_private *i915) { static const struct i915_subtest tests[] = { SUBTEST(igt_lmem_create), + SUBTEST(igt_lmem_create_cleared_cpu), SUBTEST(igt_lmem_write_cpu), SUBTEST(igt_lmem_write_gpu), }; -- cgit 1.4.1 From 0e997a36ecb61b161a22980ec9240ee7537f3f62 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Thu, 29 Apr 2021 11:30:55 +0100 Subject: drm/i915/gem: clear userspace buffers for LMEM MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All userspace objects must be cleared when allocating the backing store, before they are potentially visible to userspace. For now use simple CPU based clearing to do this for device local-memory objects, note that in the near future this will instead use the blitter engine. Signed-off-by: Matthew Auld Cc: Joonas Lahtinen Cc: Thomas Hellström Cc: Daniele Ceraolo Spurio Cc: Lionel Landwerlin Cc: Jon Bloomfield Cc: Jordan Justen Cc: Daniel Vetter Cc: Kenneth Graunke Cc: Jason Ekstrand Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Cc: mesa-dev@lists.freedesktop.org Reviewed-by: Kenneth Graunke Link: https://patchwork.freedesktop.org/patch/msgid/20210429103056.407067-8-matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_create.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c index 957f790c644b..f6729feae582 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_create.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c @@ -71,6 +71,7 @@ static int i915_gem_setup(struct drm_i915_gem_object *obj, u64 size) { struct intel_memory_region *mr = obj->mm.placements[0]; + unsigned int flags; int ret; size = round_up(size, object_max_page_size(obj)); @@ -83,7 +84,16 @@ i915_gem_setup(struct drm_i915_gem_object *obj, u64 size) if (i915_gem_object_size_2big(size)) return -E2BIG; - ret = mr->ops->init_object(mr, obj, size, 0); + /* + * For now resort to CPU based clearing for device local-memory, in the + * near future this will use the blitter engine for accelerated, GPU + * based clearing. + */ + flags = 0; + if (mr->type == INTEL_MEMORY_LOCAL) + flags = I915_BO_ALLOC_CPU_CLEAR; + + ret = mr->ops->init_object(mr, obj, size, flags); if (ret) return ret; -- cgit 1.4.1 From 0a46be95c282956a9d3229a46e33ba701c26594c Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Thu, 29 Apr 2021 11:30:56 +0100 Subject: drm/i915/gem: hide new uAPI behind CONFIG_BROKEN MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Treat it the same as the fake local-memory stuff, where it is disabled for normal kernels, in case some random UMD is tempted to use this. Once we have all the other bits and pieces in place, like the TTM conversion, we can turn this on for real. Signed-off-by: Matthew Auld Cc: Joonas Lahtinen Cc: Thomas Hellström Cc: Daniele Ceraolo Spurio Cc: Lionel Landwerlin Cc: Jon Bloomfield Cc: Jordan Justen Cc: Daniel Vetter Cc: Kenneth Graunke Cc: Jason Ekstrand Cc: Dave Airlie Cc: dri-devel@lists.freedesktop.org Cc: mesa-dev@lists.freedesktop.org Reviewed-by: Kenneth Graunke Link: https://patchwork.freedesktop.org/patch/msgid/20210429103056.407067-9-matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_create.c | 3 +++ drivers/gpu/drm/i915/i915_query.c | 3 +++ 2 files changed, 6 insertions(+) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c index f6729feae582..548ddf39d853 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_create.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c @@ -335,6 +335,9 @@ static int ext_set_placements(struct i915_user_extension __user *base, { struct drm_i915_gem_create_ext_memory_regions ext; + if (!IS_ENABLED(CONFIG_DRM_I915_UNSTABLE_FAKE_LMEM)) + return -ENODEV; + if (copy_from_user(&ext, base, sizeof(ext))) return -EFAULT; diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c index 5e2b909827f4..e49da36c62fb 100644 --- a/drivers/gpu/drm/i915/i915_query.c +++ b/drivers/gpu/drm/i915/i915_query.c @@ -432,6 +432,9 @@ static int query_memregion_info(struct drm_i915_private *i915, u32 total_length; int ret, id, i; + if (!IS_ENABLED(CONFIG_DRM_I915_UNSTABLE_FAKE_LMEM)) + return -ENODEV; + if (query_item->flags != 0) return -EINVAL; -- cgit 1.4.1 From c3b147604f279051865ebef59d971fde1d2cd457 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Tue, 4 May 2021 17:41:36 +0100 Subject: drm/i915: drop the __i915_active_call pointer packing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We use some of the lower bits of the retire function pointer for potential flags, which is quite thorny, since the caller needs to remember to give the function the correct alignment with __i915_active_call, otherwise we might incorrectly unpack the pointer and jump to some garbage address later. Instead of all this let's just pass the flags along as a separate parameter. Suggested-by: Ville Syrjälä Suggested-by: Daniel Vetter References: ca419f407b43 ("drm/i915: Fix crash in auto_retire") References: d8e44e4dd221 ("drm/i915/overlay: Fix active retire callback alignment") References: fd5f262db118 ("drm/i915/selftests: Fix active retire callback alignment") Signed-off-by: Matthew Auld Reviewed-by: Matthew Brost Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210504164136.96456-1-matthew.auld@intel.com --- drivers/gpu/drm/i915/display/intel_frontbuffer.c | 4 ++-- drivers/gpu/drm/i915/display/intel_overlay.c | 5 ++--- drivers/gpu/drm/i915/gem/i915_gem_context.c | 3 +-- drivers/gpu/drm/i915/gt/gen6_ppgtt.c | 2 +- drivers/gpu/drm/i915/gt/intel_context.c | 3 +-- drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c | 2 +- drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c | 3 +-- drivers/gpu/drm/i915/gt/intel_timeline.c | 4 ++-- drivers/gpu/drm/i915/gt/mock_engine.c | 2 +- drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c | 4 ++-- drivers/gpu/drm/i915/i915_active.c | 14 +++++--------- drivers/gpu/drm/i915/i915_active.h | 11 ++++++----- drivers/gpu/drm/i915/i915_active_types.h | 5 ----- drivers/gpu/drm/i915/i915_vma.c | 3 +-- drivers/gpu/drm/i915/selftests/i915_active.c | 4 ++-- 15 files changed, 28 insertions(+), 41 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.c b/drivers/gpu/drm/i915/display/intel_frontbuffer.c index 6fc6965b6133..2a25f7bf7e5c 100644 --- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c +++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c @@ -206,7 +206,6 @@ static int frontbuffer_active(struct i915_active *ref) return 0; } -__i915_active_call static void frontbuffer_retire(struct i915_active *ref) { struct intel_frontbuffer *front = @@ -261,7 +260,8 @@ intel_frontbuffer_get(struct drm_i915_gem_object *obj) atomic_set(&front->bits, 0); i915_active_init(&front->write, frontbuffer_active, - i915_active_may_sleep(frontbuffer_retire)); + frontbuffer_retire, + I915_ACTIVE_RETIRE_SLEEPS); spin_lock(&i915->fb_tracking.lock); if (rcu_access_pointer(obj->frontbuffer)) { diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c index 8fa4313569a9..addc83a92315 100644 --- a/drivers/gpu/drm/i915/display/intel_overlay.c +++ b/drivers/gpu/drm/i915/display/intel_overlay.c @@ -383,8 +383,7 @@ static void intel_overlay_off_tail(struct intel_overlay *overlay) i830_overlay_clock_gating(dev_priv, true); } -__i915_active_call static void -intel_overlay_last_flip_retire(struct i915_active *active) +static void intel_overlay_last_flip_retire(struct i915_active *active) { struct intel_overlay *overlay = container_of(active, typeof(*overlay), last_flip); @@ -1399,7 +1398,7 @@ void intel_overlay_setup(struct drm_i915_private *dev_priv) overlay->saturation = 146; i915_active_init(&overlay->last_flip, - NULL, intel_overlay_last_flip_retire); + NULL, intel_overlay_last_flip_retire, 0); ret = get_registers(overlay, OVERLAY_NEEDS_PHYSICAL(dev_priv)); if (ret) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index fd8ee52e17a4..188dee13e017 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -1046,7 +1046,6 @@ struct context_barrier_task { void *data; }; -__i915_active_call static void cb_retire(struct i915_active *base) { struct context_barrier_task *cb = container_of(base, typeof(*cb), base); @@ -1080,7 +1079,7 @@ static int context_barrier_task(struct i915_gem_context *ctx, if (!cb) return -ENOMEM; - i915_active_init(&cb->base, NULL, cb_retire); + i915_active_init(&cb->base, NULL, cb_retire, 0); err = i915_active_acquire(&cb->base); if (err) { kfree(cb); diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c index 21b1085769be..1aee5e6b1b23 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c @@ -343,7 +343,7 @@ static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size) if (!vma) return ERR_PTR(-ENOMEM); - i915_active_init(&vma->active, NULL, NULL); + i915_active_init(&vma->active, NULL, NULL, 0); kref_init(&vma->ref); mutex_init(&vma->pages_mutex); diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 17cf2640b082..4033184f13b9 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -326,7 +326,6 @@ void intel_context_unpin(struct intel_context *ce) intel_context_put(ce); } -__i915_active_call static void __intel_context_retire(struct i915_active *active) { struct intel_context *ce = container_of(active, typeof(*ce), active); @@ -385,7 +384,7 @@ intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine) mutex_init(&ce->pin_mutex); i915_active_init(&ce->active, - __intel_context_active, __intel_context_retire); + __intel_context_active, __intel_context_retire, 0); } void intel_context_fini(struct intel_context *ce) diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index 0fa6c38893f7..7bf84cd21543 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -867,7 +867,7 @@ void intel_ggtt_init_fences(struct i915_ggtt *ggtt) for (i = 0; i < num_fences; i++) { struct i915_fence_reg *fence = &ggtt->fence_regs[i]; - i915_active_init(&fence->active, NULL, NULL); + i915_active_init(&fence->active, NULL, NULL, 0); fence->ggtt = ggtt; fence->id = i; list_add_tail(&fence->link, &ggtt->fence_list); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c index c59468107598..aa0a59c5b614 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c @@ -98,7 +98,6 @@ static void pool_free_work(struct work_struct *wrk) round_jiffies_up_relative(HZ)); } -__i915_active_call static void pool_retire(struct i915_active *ref) { struct intel_gt_buffer_pool_node *node = @@ -154,7 +153,7 @@ node_create(struct intel_gt_buffer_pool *pool, size_t sz, node->age = 0; node->pool = pool; node->pinned = false; - i915_active_init(&node->active, NULL, pool_retire); + i915_active_init(&node->active, NULL, pool_retire, 0); obj = i915_gem_object_create_internal(gt->i915, sz); if (IS_ERR(obj)) { diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c index f19cf6d2fa85..c4a126c8caef 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline.c +++ b/drivers/gpu/drm/i915/gt/intel_timeline.c @@ -32,7 +32,6 @@ static struct i915_vma *hwsp_alloc(struct intel_gt *gt) return vma; } -__i915_active_call static void __timeline_retire(struct i915_active *active) { struct intel_timeline *tl = @@ -104,7 +103,8 @@ static int intel_timeline_init(struct intel_timeline *timeline, INIT_LIST_HEAD(&timeline->requests); i915_syncmap_init(&timeline->sync); - i915_active_init(&timeline->active, __timeline_active, __timeline_retire); + i915_active_init(&timeline->active, __timeline_active, + __timeline_retire, 0); return 0; } diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c index e1ba03b93ffa..32589c6625e1 100644 --- a/drivers/gpu/drm/i915/gt/mock_engine.c +++ b/drivers/gpu/drm/i915/gt/mock_engine.c @@ -55,7 +55,7 @@ static struct intel_ring *mock_ring(struct intel_engine_cs *engine) kfree(ring); return NULL; } - i915_active_init(&ring->vma->active, NULL, NULL); + i915_active_init(&ring->vma->active, NULL, NULL, 0); __set_bit(I915_VMA_GGTT_BIT, __i915_vma_flags(ring->vma)); __set_bit(DRM_MM_NODE_ALLOCATED_BIT, &ring->vma->node.flags); ring->vma->node.size = sz; diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c index fcde223e26ff..4896e4ccad50 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c +++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c @@ -63,7 +63,7 @@ static void pulse_put(struct pulse *p) kref_put(&p->kref, pulse_free); } -__i915_active_call static void pulse_retire(struct i915_active *active) +static void pulse_retire(struct i915_active *active) { pulse_put(container_of(active, struct pulse, active)); } @@ -77,7 +77,7 @@ static struct pulse *pulse_create(void) return p; kref_init(&p->kref); - i915_active_init(&p->active, pulse_active, pulse_retire); + i915_active_init(&p->active, pulse_active, pulse_retire, 0); return p; } diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index aa573b078ae7..b1aa1c482c32 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -343,18 +343,15 @@ out: void __i915_active_init(struct i915_active *ref, int (*active)(struct i915_active *ref), void (*retire)(struct i915_active *ref), + unsigned long flags, struct lock_class_key *mkey, struct lock_class_key *wkey) { - unsigned long bits; - debug_active_init(ref); - ref->flags = 0; + ref->flags = flags; ref->active = active; - ref->retire = ptr_unpack_bits(retire, &bits, 2); - if (bits & I915_ACTIVE_MAY_SLEEP) - ref->flags |= I915_ACTIVE_RETIRE_SLEEPS; + ref->retire = retire; spin_lock_init(&ref->tree_lock); ref->tree = RB_ROOT; @@ -1156,8 +1153,7 @@ static int auto_active(struct i915_active *ref) return 0; } -__i915_active_call static void -auto_retire(struct i915_active *ref) +static void auto_retire(struct i915_active *ref) { i915_active_put(ref); } @@ -1171,7 +1167,7 @@ struct i915_active *i915_active_create(void) return NULL; kref_init(&aa->ref); - i915_active_init(&aa->base, auto_active, auto_retire); + i915_active_init(&aa->base, auto_active, auto_retire, 0); return &aa->base; } diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h index fb165d3f01cf..d0feda68b874 100644 --- a/drivers/gpu/drm/i915/i915_active.h +++ b/drivers/gpu/drm/i915/i915_active.h @@ -152,15 +152,16 @@ i915_active_fence_isset(const struct i915_active_fence *active) void __i915_active_init(struct i915_active *ref, int (*active)(struct i915_active *ref), void (*retire)(struct i915_active *ref), + unsigned long flags, struct lock_class_key *mkey, struct lock_class_key *wkey); /* Specialise each class of i915_active to avoid impossible lockdep cycles. */ -#define i915_active_init(ref, active, retire) do { \ - static struct lock_class_key __mkey; \ - static struct lock_class_key __wkey; \ - \ - __i915_active_init(ref, active, retire, &__mkey, &__wkey); \ +#define i915_active_init(ref, active, retire, flags) do { \ + static struct lock_class_key __mkey; \ + static struct lock_class_key __wkey; \ + \ + __i915_active_init(ref, active, retire, flags, &__mkey, &__wkey); \ } while (0) struct dma_fence * diff --git a/drivers/gpu/drm/i915/i915_active_types.h b/drivers/gpu/drm/i915/i915_active_types.h index 6360c3e4b765..c149f348a972 100644 --- a/drivers/gpu/drm/i915/i915_active_types.h +++ b/drivers/gpu/drm/i915/i915_active_types.h @@ -24,11 +24,6 @@ struct i915_active_fence { struct active_node; -#define I915_ACTIVE_MAY_SLEEP BIT(0) - -#define __i915_active_call __aligned(4) -#define i915_active_may_sleep(fn) ptr_pack_bits(&(fn), I915_ACTIVE_MAY_SLEEP, 2) - struct i915_active { atomic_t count; struct mutex mutex; diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 468317e3b477..a6cd0fa62847 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -94,7 +94,6 @@ static int __i915_vma_active(struct i915_active *ref) return i915_vma_tryget(active_to_vma(ref)) ? 0 : -ENOENT; } -__i915_active_call static void __i915_vma_retire(struct i915_active *ref) { i915_vma_put(active_to_vma(ref)); @@ -125,7 +124,7 @@ vma_create(struct drm_i915_gem_object *obj, vma->size = obj->base.size; vma->display_alignment = I915_GTT_MIN_ALIGNMENT; - i915_active_init(&vma->active, __i915_vma_active, __i915_vma_retire); + i915_active_init(&vma->active, __i915_vma_active, __i915_vma_retire, 0); /* Declare ourselves safe for use inside shrinkers */ if (IS_ENABLED(CONFIG_LOCKDEP)) { diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c index 1aa52b5cc488..61bf4560d8af 100644 --- a/drivers/gpu/drm/i915/selftests/i915_active.c +++ b/drivers/gpu/drm/i915/selftests/i915_active.c @@ -51,7 +51,7 @@ static int __live_active(struct i915_active *base) return 0; } -__i915_active_call static void __live_retire(struct i915_active *base) +static void __live_retire(struct i915_active *base) { struct live_active *active = container_of(base, typeof(*active), base); @@ -68,7 +68,7 @@ static struct live_active *__live_alloc(struct drm_i915_private *i915) return NULL; kref_init(&active->ref); - i915_active_init(&active->base, __live_active, __live_retire); + i915_active_init(&active->base, __live_active, __live_retire, 0); return active; } -- cgit 1.4.1 From ae9faeb9a2c9019953590dcf71312f70ce53c7d0 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Fri, 7 May 2021 09:49:26 +0100 Subject: drm/i915: Drop duplicate WaDisable4x2SubspanOptimization:hsw Same workaround was listed two times - once under the Gen7 block and once under the Haswell section. Signed-off-by: Tvrtko Ursulin Reviewed-by: Lucas De Marchi Link: https://patchwork.freedesktop.org/patch/msgid/20210507084926.2423003-1-tvrtko.ursulin@linux.intel.com --- drivers/gpu/drm/i915/gt/intel_workarounds.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 5a03a76bb9e2..62cb9ee5bfc3 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -1859,9 +1859,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) CACHE_MODE_0_GEN7, /* enable HiZ Raw Stall Optimization */ HIZ_RAW_STALL_OPT_DISABLE); - - /* WaDisable4x2SubspanOptimization:hsw */ - wa_masked_en(wal, CACHE_MODE_1, PIXEL_SUBSPAN_COLLECT_OPT_DISABLE); } if (IS_VALLEYVIEW(i915)) { -- cgit 1.4.1 From e49a8b2cc8522a836ec2ade3d8e4dc02de6f4d67 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Fri, 7 May 2021 16:42:51 +0200 Subject: drm/i915/gt: Do release kernel context if breadcrumb measure fails Commit fb5970da1b42 ("drm/i915/gt: Use the kernel_context to measure the breadcrumb size") reordered some operations inside engine_init_common() and added an error unwind path to that function. In that path, a reference to a kernel context candidate supposed to be released on error was put, but the context, pinned when created, was not unpinned first. Fix it by replacing intel_context_put() with destroy_pinned_context() introduced later by commit b436a5f8b6c8 ("drm/i915/gt: Track all timelines created using the HWSP"). Signed-off-by: Janusz Krzysztofik Cc: Chris Wilson Reviewed-by: Tvrtko Ursulin Signed-off-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20210507144251.376538-1-janusz.krzysztofik@linux.intel.com --- drivers/gpu/drm/i915/gt/intel_engine_cs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 6dbdbde00f14..eba2da9679a5 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -898,7 +898,7 @@ static int engine_init_common(struct intel_engine_cs *engine) return 0; err_context: - intel_context_put(ce); + destroy_pinned_context(ce); return ret; } -- cgit 1.4.1 From 00d6dc3da1d76bdd735cd47d026b5a0d673559f7 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Fri, 7 May 2021 10:59:48 +0100 Subject: drm/i915/stolen: shuffle around init_memory_region MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We generally want to first call i915_gem_object_init_memory_region() before calling into get_pages(), since this sets up various bits of state which might be needed there. Currently for stolen this doesn't matter much, but it might in the future, and at the very least this makes things consistent with the other backends. Signed-off-by: Matthew Auld Cc: Thomas Hellström Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20210507095948.384230-1-matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_stolen.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index 293f640faa0a..b5553fc3ac4d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -657,9 +657,11 @@ static int __i915_gem_object_create_stolen(struct intel_memory_region *mem, if (WARN_ON(!i915_gem_object_trylock(obj))) return -EBUSY; + i915_gem_object_init_memory_region(obj, mem); + err = i915_gem_object_pin_pages(obj); - if (!err) - i915_gem_object_init_memory_region(obj, mem); + if (err) + i915_gem_object_release_memory_region(obj); i915_gem_object_unlock(obj); return err; -- cgit 1.4.1 From 727ecd99a4c91cd08cea7301d0e97d81d2d11d20 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Tue, 11 May 2021 18:03:56 +0100 Subject: drm/doc/rfc: drop the i915_gem_lmem.h header The proper headers have now landed in include/uapi/drm/i915_drm.h, so we can drop i915_gem_lmem.h and instead just reference the real headers for pulling in the kernel doc. Suggested-by: Daniel Vetter Signed-off-by: Matthew Auld Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210511170356.430284-1-matthew.auld@intel.com --- Documentation/gpu/rfc/i915_gem_lmem.h | 237 -------------------------------- Documentation/gpu/rfc/i915_gem_lmem.rst | 6 +- 2 files changed, 3 insertions(+), 240 deletions(-) delete mode 100644 Documentation/gpu/rfc/i915_gem_lmem.h diff --git a/Documentation/gpu/rfc/i915_gem_lmem.h b/Documentation/gpu/rfc/i915_gem_lmem.h deleted file mode 100644 index d9c61bea0556..000000000000 --- a/Documentation/gpu/rfc/i915_gem_lmem.h +++ /dev/null @@ -1,237 +0,0 @@ -/** - * enum drm_i915_gem_memory_class - Supported memory classes - */ -enum drm_i915_gem_memory_class { - /** @I915_MEMORY_CLASS_SYSTEM: System memory */ - I915_MEMORY_CLASS_SYSTEM = 0, - /** @I915_MEMORY_CLASS_DEVICE: Device local-memory */ - I915_MEMORY_CLASS_DEVICE, -}; - -/** - * struct drm_i915_gem_memory_class_instance - Identify particular memory region - */ -struct drm_i915_gem_memory_class_instance { - /** @memory_class: See enum drm_i915_gem_memory_class */ - __u16 memory_class; - - /** @memory_instance: Which instance */ - __u16 memory_instance; -}; - -/** - * struct drm_i915_memory_region_info - Describes one region as known to the - * driver. - * - * Note that we reserve some stuff here for potential future work. As an example - * we might want expose the capabilities for a given region, which could include - * things like if the region is CPU mappable/accessible, what are the supported - * mapping types etc. - * - * Note that to extend struct drm_i915_memory_region_info and struct - * drm_i915_query_memory_regions in the future the plan is to do the following: - * - * .. code-block:: C - * - * struct drm_i915_memory_region_info { - * struct drm_i915_gem_memory_class_instance region; - * union { - * __u32 rsvd0; - * __u32 new_thing1; - * }; - * ... - * union { - * __u64 rsvd1[8]; - * struct { - * __u64 new_thing2; - * __u64 new_thing3; - * ... - * }; - * }; - * }; - * - * With this things should remain source compatible between versions for - * userspace, even as we add new fields. - * - * Note this is using both struct drm_i915_query_item and struct drm_i915_query. - * For this new query we are adding the new query id DRM_I915_QUERY_MEMORY_REGIONS - * at &drm_i915_query_item.query_id. - */ -struct drm_i915_memory_region_info { - /** @region: The class:instance pair encoding */ - struct drm_i915_gem_memory_class_instance region; - - /** @rsvd0: MBZ */ - __u32 rsvd0; - - /** @probed_size: Memory probed by the driver (-1 = unknown) */ - __u64 probed_size; - - /** @unallocated_size: Estimate of memory remaining (-1 = unknown) */ - __u64 unallocated_size; - - /** @rsvd1: MBZ */ - __u64 rsvd1[8]; -}; - -/** - * struct drm_i915_query_memory_regions - * - * The region info query enumerates all regions known to the driver by filling - * in an array of struct drm_i915_memory_region_info structures. - * - * Example for getting the list of supported regions: - * - * .. code-block:: C - * - * struct drm_i915_query_memory_regions *info; - * struct drm_i915_query_item item = { - * .query_id = DRM_I915_QUERY_MEMORY_REGIONS; - * }; - * struct drm_i915_query query = { - * .num_items = 1, - * .items_ptr = (uintptr_t)&item, - * }; - * int err, i; - * - * // First query the size of the blob we need, this needs to be large - * // enough to hold our array of regions. The kernel will fill out the - * // item.length for us, which is the number of bytes we need. - * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); - * if (err) ... - * - * info = calloc(1, item.length); - * // Now that we allocated the required number of bytes, we call the ioctl - * // again, this time with the data_ptr pointing to our newly allocated - * // blob, which the kernel can then populate with the all the region info. - * item.data_ptr = (uintptr_t)&info, - * - * err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query); - * if (err) ... - * - * // We can now access each region in the array - * for (i = 0; i < info->num_regions; i++) { - * struct drm_i915_memory_region_info mr = info->regions[i]; - * u16 class = mr.region.class; - * u16 instance = mr.region.instance; - * - * .... - * } - * - * free(info); - */ -struct drm_i915_query_memory_regions { - /** @num_regions: Number of supported regions */ - __u32 num_regions; - - /** @rsvd: MBZ */ - __u32 rsvd[3]; - - /** @regions: Info about each supported region */ - struct drm_i915_memory_region_info regions[]; -}; - -#define DRM_I915_GEM_CREATE_EXT 0xdeadbeaf -#define DRM_IOCTL_I915_GEM_CREATE_EXT DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE_EXT, struct drm_i915_gem_create_ext) - -/** - * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added - * extension support using struct i915_user_extension. - * - * Note that in the future we want to have our buffer flags here, at least for - * the stuff that is immutable. Previously we would have two ioctls, one to - * create the object with gem_create, and another to apply various parameters, - * however this creates some ambiguity for the params which are considered - * immutable. Also in general we're phasing out the various SET/GET ioctls. - */ -struct drm_i915_gem_create_ext { - /** - * @size: Requested size for the object. - * - * The (page-aligned) allocated size for the object will be returned. - * - * Note that for some devices we have might have further minimum - * page-size restrictions(larger than 4K), like for device local-memory. - * However in general the final size here should always reflect any - * rounding up, if for example using the I915_GEM_CREATE_EXT_MEMORY_REGIONS - * extension to place the object in device local-memory. - */ - __u64 size; - /** - * @handle: Returned handle for the object. - * - * Object handles are nonzero. - */ - __u32 handle; - /** @flags: MBZ */ - __u32 flags; - /** - * @extensions: The chain of extensions to apply to this object. - * - * This will be useful in the future when we need to support several - * different extensions, and we need to apply more than one when - * creating the object. See struct i915_user_extension. - * - * If we don't supply any extensions then we get the same old gem_create - * behaviour. - * - * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see - * struct drm_i915_gem_create_ext_memory_regions. - */ -#define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0 - __u64 extensions; -}; - -/** - * struct drm_i915_gem_create_ext_memory_regions - The - * I915_GEM_CREATE_EXT_MEMORY_REGIONS extension. - * - * Set the object with the desired set of placements/regions in priority - * order. Each entry must be unique and supported by the device. - * - * This is provided as an array of struct drm_i915_gem_memory_class_instance, or - * an equivalent layout of class:instance pair encodings. See struct - * drm_i915_query_memory_regions and DRM_I915_QUERY_MEMORY_REGIONS for how to - * query the supported regions for a device. - * - * As an example, on discrete devices, if we wish to set the placement as - * device local-memory we can do something like: - * - * .. code-block:: C - * - * struct drm_i915_gem_memory_class_instance region_lmem = { - * .memory_class = I915_MEMORY_CLASS_DEVICE, - * .memory_instance = 0, - * }; - * struct drm_i915_gem_create_ext_memory_regions regions = { - * .base = { .name = I915_GEM_CREATE_EXT_MEMORY_REGIONS }, - * .regions = (uintptr_t)®ion_lmem, - * .num_regions = 1, - * }; - * struct drm_i915_gem_create_ext create_ext = { - * .size = 16 * PAGE_SIZE, - * .extensions = (uintptr_t)®ions, - * }; - * - * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); - * if (err) ... - * - * At which point we get the object handle in &drm_i915_gem_create_ext.handle, - * along with the final object size in &drm_i915_gem_create_ext.size, which - * should account for any rounding up, if required. - */ -struct drm_i915_gem_create_ext_memory_regions { - /** @base: Extension link. See struct i915_user_extension. */ - struct i915_user_extension base; - - /** @pad: MBZ */ - __u32 pad; - /** @num_regions: Number of elements in the @regions array. */ - __u32 num_regions; - /** - * @regions: The regions/placements array. - * - * An array of struct drm_i915_gem_memory_class_instance. - */ - __u64 regions; -}; diff --git a/Documentation/gpu/rfc/i915_gem_lmem.rst b/Documentation/gpu/rfc/i915_gem_lmem.rst index 1d344c593018..675ba8620d66 100644 --- a/Documentation/gpu/rfc/i915_gem_lmem.rst +++ b/Documentation/gpu/rfc/i915_gem_lmem.rst @@ -48,7 +48,7 @@ particular instance, since we can have more than one per class. In the future we also want to expose more information which can further describe the capabilities of a region. -.. kernel-doc:: Documentation/gpu/rfc/i915_gem_lmem.h +.. kernel-doc:: include/uapi/drm/i915_drm.h :functions: drm_i915_gem_memory_class drm_i915_gem_memory_class_instance drm_i915_memory_region_info drm_i915_query_memory_regions GEM_CREATE_EXT @@ -61,7 +61,7 @@ Side note: We also need to support PXP[1] in the near future, which is also applicable to integrated platforms, and adds its own gem_create_ext extension, which basically lets userspace mark a buffer as "protected". -.. kernel-doc:: Documentation/gpu/rfc/i915_gem_lmem.h +.. kernel-doc:: include/uapi/drm/i915_drm.h :functions: drm_i915_gem_create_ext I915_GEM_CREATE_EXT_MEMORY_REGIONS @@ -73,7 +73,7 @@ them each to use the class/instance encoding, as per the output of the regions query. Having the list in priority order will be useful in the future when placing an object, say during eviction. -.. kernel-doc:: Documentation/gpu/rfc/i915_gem_lmem.h +.. kernel-doc:: include/uapi/drm/i915_drm.h :functions: drm_i915_gem_create_ext_memory_regions One fair criticism here is that this seems a little over-engineered[2]. If we -- cgit 1.4.1 From 8777d17b68dcfbfbd4d524f444adefae56f41225 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 17 May 2021 09:46:40 +0100 Subject: drm/i915/gem: Pin the L-shape quirked object as unshrinkable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When instantiating a tiled object on an L-shaped memory machine, we mark the object as unshrinkable to prevent the shrinker from trying to swap out the pages. We have to do this as we do not know the swizzling on the individual pages, and so the data will be scrambled across swap out/in. Not only do we need to move the object off the shrinker list, we need to mark the object with shrink_pin so that the counter is consistent across calls to madvise. v2: in the madvise ioctl we need to check if the object is currently shrinkable/purgeable, not if the object type supports shrinking Fixes: 0175969e489a ("drm/i915/gem: Use shrinkable status for unknown swizzle quirks") References: https://gitlab.freedesktop.org/drm/intel/-/issues/3293 References: https://gitlab.freedesktop.org/drm/intel/-/issues/3450 Reported-by: Ville Syrjälä Tested-by: Ville Syrjälä Signed-off-by: Chris Wilson Reviewed-by: Matthew Auld Signed-off-by: Matthew Auld Cc: # v5.12+ Link: https://patchwork.freedesktop.org/patch/msgid/20210517084640.18862-1-matthew.auld@intel.com --- drivers/gpu/drm/i915/gem/i915_gem_pages.c | 2 ++ drivers/gpu/drm/i915/i915_gem.c | 11 +++++------ 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index aed8a37ccdc9..7361971c177d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -63,6 +63,8 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, i915->quirks & QUIRK_PIN_SWIZZLED_PAGES) { GEM_BUG_ON(i915_gem_object_has_tiling_quirk(obj)); i915_gem_object_set_tiling_quirk(obj); + GEM_BUG_ON(!list_empty(&obj->mm.link)); + atomic_inc(&obj->mm.shrink_pin); shrinkable = false; } diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index d0018c5f88bd..cffd7f4f87dc 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1009,12 +1009,11 @@ i915_gem_madvise_ioctl(struct drm_device *dev, void *data, obj->mm.madv = args->madv; if (i915_gem_object_has_pages(obj)) { - struct list_head *list; + unsigned long flags; - if (i915_gem_object_is_shrinkable(obj)) { - unsigned long flags; - - spin_lock_irqsave(&i915->mm.obj_lock, flags); + spin_lock_irqsave(&i915->mm.obj_lock, flags); + if (!list_empty(&obj->mm.link)) { + struct list_head *list; if (obj->mm.madv != I915_MADV_WILLNEED) list = &i915->mm.purge_list; @@ -1022,8 +1021,8 @@ i915_gem_madvise_ioctl(struct drm_device *dev, void *data, list = &i915->mm.shrink_list; list_move_tail(&obj->mm.link, list); - spin_unlock_irqrestore(&i915->mm.obj_lock, flags); } + spin_unlock_irqrestore(&i915->mm.obj_lock, flags); } /* if the object is no longer attached, discard its backing storage */ -- cgit 1.4.1 From 50c3ffb49c953a203b5a16d4e4d55b03c57e8883 Mon Sep 17 00:00:00 2001 From: wengjianfeng Date: Thu, 20 May 2021 16:06:46 +0800 Subject: drm/i915/gt: fix typo issue Change 'freqency' to 'frequency'. Signed-off-by: wengjianfeng Reviewed-by: Matthew Auld Signed-off-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20210520080646.24132-1-samirweng1979@163.com --- drivers/gpu/drm/i915/gt/selftest_rps.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c index adf7fdbc00f7..3ca1bd5793c3 100644 --- a/drivers/gpu/drm/i915/gt/selftest_rps.c +++ b/drivers/gpu/drm/i915/gt/selftest_rps.c @@ -606,7 +606,7 @@ int live_rps_frequency_cs(void *arg) int err = 0; /* - * The premise is that the GPU does change freqency at our behest. + * The premise is that the GPU does change frequency at our behest. * Let's check there is a correspondence between the requested * frequency, the actual frequency, and the observed clock rate. */ @@ -747,7 +747,7 @@ int live_rps_frequency_srm(void *arg) int err = 0; /* - * The premise is that the GPU does change freqency at our behest. + * The premise is that the GPU does change frequency at our behest. * Let's check there is a correspondence between the requested * frequency, the actual frequency, and the observed clock rate. */ -- cgit 1.4.1 From 0db3633f615944a8106f48a4945aa0770a71304d Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 21 May 2021 11:32:13 -0700 Subject: drm/i915/gt: Move engine setup out of set_default_submission Now that we no longer switch back and forth between guc and execlists, we no longer need to restore the backend's vfunc and can leave them set after initialisation. The only catch is that we lose the submission on wedging and still need to reset the submit_request vfunc on unwedging. Signed-off-by: Matthew Brost Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Reviewed-by: Matthew Brost Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210521183215.65451-2-matthew.brost@intel.com --- .../gpu/drm/i915/gt/intel_execlists_submission.c | 46 ++++++++++---------- drivers/gpu/drm/i915/gt/intel_ring_submission.c | 4 -- drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 50 +++++++++------------- 3 files changed, 44 insertions(+), 56 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index de124870af44..1108c193ab65 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -3076,29 +3076,6 @@ static void execlists_set_default_submission(struct intel_engine_cs *engine) engine->submit_request = execlists_submit_request; engine->schedule = i915_schedule; engine->execlists.tasklet.callback = execlists_submission_tasklet; - - engine->reset.prepare = execlists_reset_prepare; - engine->reset.rewind = execlists_reset_rewind; - engine->reset.cancel = execlists_reset_cancel; - engine->reset.finish = execlists_reset_finish; - - engine->park = execlists_park; - engine->unpark = NULL; - - engine->flags |= I915_ENGINE_SUPPORTS_STATS; - if (!intel_vgpu_active(engine->i915)) { - engine->flags |= I915_ENGINE_HAS_SEMAPHORES; - if (can_preempt(engine)) { - engine->flags |= I915_ENGINE_HAS_PREEMPTION; - if (IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) - engine->flags |= I915_ENGINE_HAS_TIMESLICES; - } - } - - if (intel_engine_has_preemption(engine)) - engine->emit_bb_start = gen8_emit_bb_start; - else - engine->emit_bb_start = gen8_emit_bb_start_noarb; } static void execlists_shutdown(struct intel_engine_cs *engine) @@ -3129,6 +3106,14 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine) engine->cops = &execlists_context_ops; engine->request_alloc = execlists_request_alloc; + engine->reset.prepare = execlists_reset_prepare; + engine->reset.rewind = execlists_reset_rewind; + engine->reset.cancel = execlists_reset_cancel; + engine->reset.finish = execlists_reset_finish; + + engine->park = execlists_park; + engine->unpark = NULL; + engine->emit_flush = gen8_emit_flush_xcs; engine->emit_init_breadcrumb = gen8_emit_init_breadcrumb; engine->emit_fini_breadcrumb = gen8_emit_fini_breadcrumb_xcs; @@ -3149,6 +3134,21 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine) * until a more refined solution exists. */ } + + engine->flags |= I915_ENGINE_SUPPORTS_STATS; + if (!intel_vgpu_active(engine->i915)) { + engine->flags |= I915_ENGINE_HAS_SEMAPHORES; + if (can_preempt(engine)) { + engine->flags |= I915_ENGINE_HAS_PREEMPTION; + if (IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + engine->flags |= I915_ENGINE_HAS_TIMESLICES; + } + } + + if (intel_engine_has_preemption(engine)) + engine->emit_bb_start = gen8_emit_bb_start; + else + engine->emit_bb_start = gen8_emit_bb_start_noarb; } static void logical_ring_default_irqs(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index 9585546556ee..5f4f7f1df48f 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -989,14 +989,10 @@ static void gen6_bsd_submit_request(struct i915_request *request) static void i9xx_set_default_submission(struct intel_engine_cs *engine) { engine->submit_request = i9xx_submit_request; - - engine->park = NULL; - engine->unpark = NULL; } static void gen6_bsd_set_default_submission(struct intel_engine_cs *engine) { - i9xx_set_default_submission(engine); engine->submit_request = gen6_bsd_submit_request; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 92688a9b6717..f72faa0b8339 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -608,35 +608,6 @@ static int guc_resume(struct intel_engine_cs *engine) static void guc_set_default_submission(struct intel_engine_cs *engine) { engine->submit_request = guc_submit_request; - engine->schedule = i915_schedule; - engine->execlists.tasklet.callback = guc_submission_tasklet; - - engine->reset.prepare = guc_reset_prepare; - engine->reset.rewind = guc_reset_rewind; - engine->reset.cancel = guc_reset_cancel; - engine->reset.finish = guc_reset_finish; - - engine->flags |= I915_ENGINE_NEEDS_BREADCRUMB_TASKLET; - engine->flags |= I915_ENGINE_HAS_PREEMPTION; - - /* - * TODO: GuC supports timeslicing and semaphores as well, but they're - * handled by the firmware so some minor tweaks are required before - * enabling. - * - * engine->flags |= I915_ENGINE_HAS_TIMESLICES; - * engine->flags |= I915_ENGINE_HAS_SEMAPHORES; - */ - - engine->emit_bb_start = gen8_emit_bb_start; - - /* - * For the breadcrumb irq to work we need the interrupts to stay - * enabled. However, on all platforms on which we'll have support for - * GuC submission we don't allow disabling the interrupts at runtime, so - * we're always safe with the current flow. - */ - GEM_BUG_ON(engine->irq_enable || engine->irq_disable); } static void guc_release(struct intel_engine_cs *engine) @@ -658,6 +629,13 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine) engine->cops = &guc_context_ops; engine->request_alloc = guc_request_alloc; + engine->schedule = i915_schedule; + + engine->reset.prepare = guc_reset_prepare; + engine->reset.rewind = guc_reset_rewind; + engine->reset.cancel = guc_reset_cancel; + engine->reset.finish = guc_reset_finish; + engine->emit_flush = gen8_emit_flush_xcs; engine->emit_init_breadcrumb = gen8_emit_init_breadcrumb; engine->emit_fini_breadcrumb = gen8_emit_fini_breadcrumb_xcs; @@ -666,6 +644,20 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine) engine->emit_flush = gen12_emit_flush_xcs; } engine->set_default_submission = guc_set_default_submission; + + engine->flags |= I915_ENGINE_NEEDS_BREADCRUMB_TASKLET; + engine->flags |= I915_ENGINE_HAS_PREEMPTION; + + /* + * TODO: GuC supports timeslicing and semaphores as well, but they're + * handled by the firmware so some minor tweaks are required before + * enabling. + * + * engine->flags |= I915_ENGINE_HAS_TIMESLICES; + * engine->flags |= I915_ENGINE_HAS_SEMAPHORES; + */ + + engine->emit_bb_start = gen8_emit_bb_start; } static void rcs_submission_override(struct intel_engine_cs *engine) -- cgit 1.4.1 From c92c36ed8d92b0bad1cbd482a8b2e9871a8cb28b Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 21 May 2021 11:32:14 -0700 Subject: drm/i915/gt: Move submission_method into intel_gt Since we setup the submission method for the engines once, it is easy to assign an enum and use that instead of probing into the backends. Signed-off-by: Matthew Brost Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Reviewed-by: Matthew Brost Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210521183215.65451-3-matthew.brost@intel.com --- drivers/gpu/drm/i915/gt/intel_engine.h | 8 +++++++- drivers/gpu/drm/i915/gt/intel_engine_cs.c | 12 ++++++++---- drivers/gpu/drm/i915/gt/intel_execlists_submission.c | 8 -------- drivers/gpu/drm/i915/gt/intel_execlists_submission.h | 3 --- drivers/gpu/drm/i915/gt/intel_gt_types.h | 7 +++++++ drivers/gpu/drm/i915/gt/intel_reset.c | 7 +++---- drivers/gpu/drm/i915/gt/selftest_execlists.c | 2 +- drivers/gpu/drm/i915/gt/selftest_ring_submission.c | 2 +- drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 5 ----- drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h | 1 - drivers/gpu/drm/i915/i915_perf.c | 10 +++++----- 11 files changed, 32 insertions(+), 33 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index 47ee8578e511..8d9184920c51 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -13,8 +13,9 @@ #include "i915_reg.h" #include "i915_request.h" #include "i915_selftest.h" -#include "gt/intel_timeline.h" #include "intel_engine_types.h" +#include "intel_gt_types.h" +#include "intel_timeline.h" #include "intel_workarounds.h" struct drm_printer; @@ -262,6 +263,11 @@ void intel_engine_init_active(struct intel_engine_cs *engine, #define ENGINE_MOCK 1 #define ENGINE_VIRTUAL 2 +static inline bool intel_engine_uses_guc(const struct intel_engine_cs *engine) +{ + return engine->gt->submission_method >= INTEL_SUBMISSION_GUC; +} + static inline bool intel_engine_has_preempt_reset(const struct intel_engine_cs *engine) { diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index eba2da9679a5..e54a2a4df87c 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -909,12 +909,16 @@ int intel_engines_init(struct intel_gt *gt) enum intel_engine_id id; int err; - if (intel_uc_uses_guc_submission(>->uc)) + if (intel_uc_uses_guc_submission(>->uc)) { + gt->submission_method = INTEL_SUBMISSION_GUC; setup = intel_guc_submission_setup; - else if (HAS_EXECLISTS(gt->i915)) + } else if (HAS_EXECLISTS(gt->i915)) { + gt->submission_method = INTEL_SUBMISSION_ELSP; setup = intel_execlists_submission_setup; - else + } else { + gt->submission_method = INTEL_SUBMISSION_RING; setup = intel_ring_submission_setup; + } for_each_engine(engine, gt, id) { err = engine_setup_common(engine); @@ -1479,7 +1483,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, drm_printf(m, "\tIPEHR: 0x%08x\n", ENGINE_READ(engine, IPEHR)); } - if (intel_engine_in_guc_submission_mode(engine)) { + if (intel_engine_uses_guc(engine)) { /* nothing to print yet */ } else if (HAS_EXECLISTS(dev_priv)) { struct i915_request * const *port, *rq; diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 1108c193ab65..9d2da5ccaef6 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -1768,7 +1768,6 @@ process_csb(struct intel_engine_cs *engine, struct i915_request **inactive) */ GEM_BUG_ON(!tasklet_is_locked(&execlists->tasklet) && !reset_in_progress(execlists)); - GEM_BUG_ON(!intel_engine_in_execlists_submission_mode(engine)); /* * Note that csb_write, csb_status may be either in HWSP or mmio. @@ -3884,13 +3883,6 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine, spin_unlock_irqrestore(&engine->active.lock, flags); } -bool -intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine) -{ - return engine->set_default_submission == - execlists_set_default_submission; -} - #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftest_execlists.c" #endif diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h index fd61dae820e9..4ca9b475e252 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h @@ -43,7 +43,4 @@ int intel_virtual_engine_attach_bond(struct intel_engine_cs *engine, const struct intel_engine_cs *master, const struct intel_engine_cs *sibling); -bool -intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine); - #endif /* __INTEL_EXECLISTS_SUBMISSION_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index 0caf6ca0a784..fecfacf551d5 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -31,6 +31,12 @@ struct i915_ggtt; struct intel_engine_cs; struct intel_uncore; +enum intel_submission_method { + INTEL_SUBMISSION_RING, + INTEL_SUBMISSION_ELSP, + INTEL_SUBMISSION_GUC, +}; + struct intel_gt { struct drm_i915_private *i915; struct intel_uncore *uncore; @@ -118,6 +124,7 @@ struct intel_gt { struct intel_engine_cs *engine[I915_NUM_ENGINES]; struct intel_engine_cs *engine_class[MAX_ENGINE_CLASS + 1] [MAX_ENGINE_INSTANCE + 1]; + enum intel_submission_method submission_method; /* * Default address space (either GGTT or ppGTT depending on arch). diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index a377c4588aaa..d5094be6d90f 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -1118,7 +1118,6 @@ static int intel_gt_reset_engine(struct intel_engine_cs *engine) int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg) { struct intel_gt *gt = engine->gt; - bool uses_guc = intel_engine_in_guc_submission_mode(engine); int ret; ENGINE_TRACE(engine, "flags=%lx\n", gt->reset.flags); @@ -1134,10 +1133,10 @@ int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg) "Resetting %s for %s\n", engine->name, msg); atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]); - if (!uses_guc) - ret = intel_gt_reset_engine(engine); - else + if (intel_engine_uses_guc(engine)) ret = intel_guc_reset_engine(&engine->gt->uc.guc, engine); + else + ret = intel_gt_reset_engine(engine); if (ret) { /* If we fail here, we expect to fallback to a global reset */ ENGINE_TRACE(engine, "Failed to reset, err: %d\n", ret); diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c index 1081cd36a2bd..1f93591a8c69 100644 --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c @@ -4716,7 +4716,7 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915) SUBTEST(live_virtual_reset), }; - if (!HAS_EXECLISTS(i915)) + if (i915->gt.submission_method != INTEL_SUBMISSION_ELSP) return 0; if (intel_gt_is_wedged(&i915->gt)) diff --git a/drivers/gpu/drm/i915/gt/selftest_ring_submission.c b/drivers/gpu/drm/i915/gt/selftest_ring_submission.c index 99609271c3a7..c12e74171b63 100644 --- a/drivers/gpu/drm/i915/gt/selftest_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/selftest_ring_submission.c @@ -291,7 +291,7 @@ int intel_ring_submission_live_selftests(struct drm_i915_private *i915) SUBTEST(live_ctx_switch_wa), }; - if (HAS_EXECLISTS(i915)) + if (i915->gt.submission_method > INTEL_SUBMISSION_RING) return 0; return intel_gt_live_subtests(tests, &i915->gt); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index f72faa0b8339..17b551a0c89f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -745,8 +745,3 @@ void intel_guc_submission_init_early(struct intel_guc *guc) { guc->submission_selected = __guc_submission_selected(guc); } - -bool intel_engine_in_guc_submission_mode(const struct intel_engine_cs *engine) -{ - return engine->set_default_submission == guc_set_default_submission; -} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h index 5f7b9e6347d0..3f7005018939 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h @@ -20,7 +20,6 @@ void intel_guc_submission_fini(struct intel_guc *guc); int intel_guc_preempt_work_create(struct intel_guc *guc); void intel_guc_preempt_work_destroy(struct intel_guc *guc); int intel_guc_submission_setup(struct intel_engine_cs *engine); -bool intel_engine_in_guc_submission_mode(const struct intel_engine_cs *engine); static inline bool intel_guc_submission_is_supported(struct intel_guc *guc) { diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 85ad62dbabfa..66f1f25119b5 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1257,11 +1257,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) case 8: case 9: case 10: - if (intel_engine_in_execlists_submission_mode(ce->engine)) { - stream->specific_ctx_id_mask = - (1U << GEN8_CTX_ID_WIDTH) - 1; - stream->specific_ctx_id = stream->specific_ctx_id_mask; - } else { + if (intel_engine_uses_guc(ce->engine)) { /* * When using GuC, the context descriptor we write in * i915 is read by GuC and rewritten before it's @@ -1280,6 +1276,10 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) */ stream->specific_ctx_id_mask = (1U << (GEN8_CTX_ID_WIDTH - 1)) - 1; + } else { + stream->specific_ctx_id_mask = + (1U << GEN8_CTX_ID_WIDTH) - 1; + stream->specific_ctx_id = stream->specific_ctx_id_mask; } break; -- cgit 1.4.1 From 0669a6e1f11500ba9e6ddebe67c449c0444daa3a Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 21 May 2021 11:32:15 -0700 Subject: drm/i915/gt: Move CS interrupt handler to the backend The different submission backends each have their own preferred behaviour and interrupt setup. Let each handle their own interrupts. This becomes more useful later as we to extract the use of auxiliary state in the interrupt handler that is backend specific. Signed-off-by: Matthew Brost Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Reviewed-by: Matthew Brost Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210521183215.65451-4-matthew.brost@intel.com --- drivers/gpu/drm/i915/gt/intel_engine_cs.c | 7 ++ drivers/gpu/drm/i915/gt/intel_engine_types.h | 14 ++-- .../gpu/drm/i915/gt/intel_execlists_submission.c | 41 +++++++++++ drivers/gpu/drm/i915/gt/intel_gt_irq.c | 82 +++++++--------------- drivers/gpu/drm/i915/gt/intel_gt_irq.h | 23 ++++++ drivers/gpu/drm/i915/gt/intel_ring_submission.c | 8 +++ drivers/gpu/drm/i915/gt/intel_rps.c | 2 +- drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 11 ++- drivers/gpu/drm/i915/i915_irq.c | 10 +-- 9 files changed, 124 insertions(+), 74 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index e54a2a4df87c..3f9a811eb02b 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -255,6 +255,11 @@ static void intel_engine_sanitize_mmio(struct intel_engine_cs *engine) intel_engine_set_hwsp_writemask(engine, ~0u); } +static void nop_irq_handler(struct intel_engine_cs *engine, u16 iir) +{ + GEM_DEBUG_WARN_ON(iir); +} + static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id) { const struct engine_info *info = &intel_engines[id]; @@ -292,6 +297,8 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id) engine->hw_id = info->hw_id; engine->guc_id = MAKE_GUC_ID(info->class, info->instance); + engine->irq_handler = nop_irq_handler; + engine->class = info->class; engine->instance = info->instance; __sprint_engine_name(engine); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 883bafc44902..9ef349cd5cea 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -402,6 +402,7 @@ struct intel_engine_cs { u32 irq_enable_mask; /* bitmask to enable ring interrupt */ void (*irq_enable)(struct intel_engine_cs *engine); void (*irq_disable)(struct intel_engine_cs *engine); + void (*irq_handler)(struct intel_engine_cs *engine, u16 iir); void (*sanitize)(struct intel_engine_cs *engine); int (*resume)(struct intel_engine_cs *engine); @@ -481,10 +482,9 @@ struct intel_engine_cs { #define I915_ENGINE_HAS_PREEMPTION BIT(2) #define I915_ENGINE_HAS_SEMAPHORES BIT(3) #define I915_ENGINE_HAS_TIMESLICES BIT(4) -#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(5) -#define I915_ENGINE_IS_VIRTUAL BIT(6) -#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(7) -#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(8) +#define I915_ENGINE_IS_VIRTUAL BIT(5) +#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(6) +#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7) unsigned int flags; /* @@ -593,12 +593,6 @@ intel_engine_has_timeslices(const struct intel_engine_cs *engine) return engine->flags & I915_ENGINE_HAS_TIMESLICES; } -static inline bool -intel_engine_needs_breadcrumb_tasklet(const struct intel_engine_cs *engine) -{ - return engine->flags & I915_ENGINE_NEEDS_BREADCRUMB_TASKLET; -} - static inline bool intel_engine_is_virtual(const struct intel_engine_cs *engine) { diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 9d2da5ccaef6..8db200422950 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -118,6 +118,7 @@ #include "intel_engine_stats.h" #include "intel_execlists_submission.h" #include "intel_gt.h" +#include "intel_gt_irq.h" #include "intel_gt_pm.h" #include "intel_gt_requests.h" #include "intel_lrc.h" @@ -2384,6 +2385,45 @@ static void execlists_submission_tasklet(struct tasklet_struct *t) rcu_read_unlock(); } +static void execlists_irq_handler(struct intel_engine_cs *engine, u16 iir) +{ + bool tasklet = false; + + if (unlikely(iir & GT_CS_MASTER_ERROR_INTERRUPT)) { + u32 eir; + + /* Upper 16b are the enabling mask, rsvd for internal errors */ + eir = ENGINE_READ(engine, RING_EIR) & GENMASK(15, 0); + ENGINE_TRACE(engine, "CS error: %x\n", eir); + + /* Disable the error interrupt until after the reset */ + if (likely(eir)) { + ENGINE_WRITE(engine, RING_EMR, ~0u); + ENGINE_WRITE(engine, RING_EIR, eir); + WRITE_ONCE(engine->execlists.error_interrupt, eir); + tasklet = true; + } + } + + if (iir & GT_WAIT_SEMAPHORE_INTERRUPT) { + WRITE_ONCE(engine->execlists.yield, + ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI)); + ENGINE_TRACE(engine, "semaphore yield: %08x\n", + engine->execlists.yield); + if (del_timer(&engine->execlists.timer)) + tasklet = true; + } + + if (iir & GT_CONTEXT_SWITCH_INTERRUPT) + tasklet = true; + + if (iir & GT_RENDER_USER_INTERRUPT) + intel_engine_signal_breadcrumbs(engine); + + if (tasklet) + tasklet_hi_schedule(&engine->execlists.tasklet); +} + static void __execlists_kick(struct intel_engine_execlists *execlists) { /* Kick the tasklet for some interrupt coalescing and reset handling */ @@ -3133,6 +3173,7 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine) * until a more refined solution exists. */ } + intel_engine_set_irq_handler(engine, execlists_irq_handler); engine->flags |= I915_ENGINE_SUPPORTS_STATS; if (!intel_vgpu_active(engine->i915)) { diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c index 9fc6c912a4e5..d29126c458ba 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c @@ -20,48 +20,6 @@ static void guc_irq_handler(struct intel_guc *guc, u16 iir) intel_guc_to_host_event_handler(guc); } -static void -cs_irq_handler(struct intel_engine_cs *engine, u32 iir) -{ - bool tasklet = false; - - if (unlikely(iir & GT_CS_MASTER_ERROR_INTERRUPT)) { - u32 eir; - - /* Upper 16b are the enabling mask, rsvd for internal errors */ - eir = ENGINE_READ(engine, RING_EIR) & GENMASK(15, 0); - ENGINE_TRACE(engine, "CS error: %x\n", eir); - - /* Disable the error interrupt until after the reset */ - if (likely(eir)) { - ENGINE_WRITE(engine, RING_EMR, ~0u); - ENGINE_WRITE(engine, RING_EIR, eir); - WRITE_ONCE(engine->execlists.error_interrupt, eir); - tasklet = true; - } - } - - if (iir & GT_WAIT_SEMAPHORE_INTERRUPT) { - WRITE_ONCE(engine->execlists.yield, - ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI)); - ENGINE_TRACE(engine, "semaphore yield: %08x\n", - engine->execlists.yield); - if (del_timer(&engine->execlists.timer)) - tasklet = true; - } - - if (iir & GT_CONTEXT_SWITCH_INTERRUPT) - tasklet = true; - - if (iir & GT_RENDER_USER_INTERRUPT) { - intel_engine_signal_breadcrumbs(engine); - tasklet |= intel_engine_needs_breadcrumb_tasklet(engine); - } - - if (tasklet) - tasklet_hi_schedule(&engine->execlists.tasklet); -} - static u32 gen11_gt_engine_identity(struct intel_gt *gt, const unsigned int bank, const unsigned int bit) @@ -122,7 +80,7 @@ gen11_engine_irq_handler(struct intel_gt *gt, const u8 class, engine = NULL; if (likely(engine)) - return cs_irq_handler(engine, iir); + return intel_engine_cs_irq(engine, iir); WARN_ONCE(1, "unhandled engine interrupt class=0x%x, instance=0x%x\n", class, instance); @@ -275,9 +233,12 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) void gen5_gt_irq_handler(struct intel_gt *gt, u32 gt_iir) { if (gt_iir & GT_RENDER_USER_INTERRUPT) - intel_engine_signal_breadcrumbs(gt->engine_class[RENDER_CLASS][0]); + intel_engine_cs_irq(gt->engine_class[RENDER_CLASS][0], + gt_iir); + if (gt_iir & ILK_BSD_USER_INTERRUPT) - intel_engine_signal_breadcrumbs(gt->engine_class[VIDEO_DECODE_CLASS][0]); + intel_engine_cs_irq(gt->engine_class[VIDEO_DECODE_CLASS][0], + gt_iir); } static void gen7_parity_error_irq_handler(struct intel_gt *gt, u32 iir) @@ -301,11 +262,16 @@ static void gen7_parity_error_irq_handler(struct intel_gt *gt, u32 iir) void gen6_gt_irq_handler(struct intel_gt *gt, u32 gt_iir) { if (gt_iir & GT_RENDER_USER_INTERRUPT) - intel_engine_signal_breadcrumbs(gt->engine_class[RENDER_CLASS][0]); + intel_engine_cs_irq(gt->engine_class[RENDER_CLASS][0], + gt_iir); + if (gt_iir & GT_BSD_USER_INTERRUPT) - intel_engine_signal_breadcrumbs(gt->engine_class[VIDEO_DECODE_CLASS][0]); + intel_engine_cs_irq(gt->engine_class[VIDEO_DECODE_CLASS][0], + gt_iir >> 12); + if (gt_iir & GT_BLT_USER_INTERRUPT) - intel_engine_signal_breadcrumbs(gt->engine_class[COPY_ENGINE_CLASS][0]); + intel_engine_cs_irq(gt->engine_class[COPY_ENGINE_CLASS][0], + gt_iir >> 22); if (gt_iir & (GT_BLT_CS_ERROR_INTERRUPT | GT_BSD_CS_ERROR_INTERRUPT | @@ -324,10 +290,10 @@ void gen8_gt_irq_handler(struct intel_gt *gt, u32 master_ctl) if (master_ctl & (GEN8_GT_RCS_IRQ | GEN8_GT_BCS_IRQ)) { iir = raw_reg_read(regs, GEN8_GT_IIR(0)); if (likely(iir)) { - cs_irq_handler(gt->engine_class[RENDER_CLASS][0], - iir >> GEN8_RCS_IRQ_SHIFT); - cs_irq_handler(gt->engine_class[COPY_ENGINE_CLASS][0], - iir >> GEN8_BCS_IRQ_SHIFT); + intel_engine_cs_irq(gt->engine_class[RENDER_CLASS][0], + iir >> GEN8_RCS_IRQ_SHIFT); + intel_engine_cs_irq(gt->engine_class[COPY_ENGINE_CLASS][0], + iir >> GEN8_BCS_IRQ_SHIFT); raw_reg_write(regs, GEN8_GT_IIR(0), iir); } } @@ -335,10 +301,10 @@ void gen8_gt_irq_handler(struct intel_gt *gt, u32 master_ctl) if (master_ctl & (GEN8_GT_VCS0_IRQ | GEN8_GT_VCS1_IRQ)) { iir = raw_reg_read(regs, GEN8_GT_IIR(1)); if (likely(iir)) { - cs_irq_handler(gt->engine_class[VIDEO_DECODE_CLASS][0], - iir >> GEN8_VCS0_IRQ_SHIFT); - cs_irq_handler(gt->engine_class[VIDEO_DECODE_CLASS][1], - iir >> GEN8_VCS1_IRQ_SHIFT); + intel_engine_cs_irq(gt->engine_class[VIDEO_DECODE_CLASS][0], + iir >> GEN8_VCS0_IRQ_SHIFT); + intel_engine_cs_irq(gt->engine_class[VIDEO_DECODE_CLASS][1], + iir >> GEN8_VCS1_IRQ_SHIFT); raw_reg_write(regs, GEN8_GT_IIR(1), iir); } } @@ -346,8 +312,8 @@ void gen8_gt_irq_handler(struct intel_gt *gt, u32 master_ctl) if (master_ctl & GEN8_GT_VECS_IRQ) { iir = raw_reg_read(regs, GEN8_GT_IIR(3)); if (likely(iir)) { - cs_irq_handler(gt->engine_class[VIDEO_ENHANCEMENT_CLASS][0], - iir >> GEN8_VECS_IRQ_SHIFT); + intel_engine_cs_irq(gt->engine_class[VIDEO_ENHANCEMENT_CLASS][0], + iir >> GEN8_VECS_IRQ_SHIFT); raw_reg_write(regs, GEN8_GT_IIR(3), iir); } } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.h b/drivers/gpu/drm/i915/gt/intel_gt_irq.h index f667e976fb2b..41cad38668c5 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.h @@ -8,6 +8,8 @@ #include +#include "intel_engine_types.h" + struct intel_gt; #define GEN8_GT_IRQS (GEN8_GT_RCS_IRQ | \ @@ -39,4 +41,25 @@ void gen8_gt_irq_handler(struct intel_gt *gt, u32 master_ctl); void gen8_gt_irq_reset(struct intel_gt *gt); void gen8_gt_irq_postinstall(struct intel_gt *gt); +static inline void intel_engine_cs_irq(struct intel_engine_cs *engine, u16 iir) +{ + if (iir) + engine->irq_handler(engine, iir); +} + +static inline void +intel_engine_set_irq_handler(struct intel_engine_cs *engine, + void (*fn)(struct intel_engine_cs *engine, + u16 iir)) +{ + /* + * As the interrupt is live as allocate and setup the engines, + * err on the side of caution and apply barriers to updating + * the irq handler callback. This assures that when we do use + * the engine, we will receive interrupts only to ourselves, + * and not lose any. + */ + smp_store_mb(engine->irq_handler, fn); +} + #endif /* INTEL_GT_IRQ_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index 5f4f7f1df48f..2b6dffcc2262 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -12,6 +12,7 @@ #include "intel_breadcrumbs.h" #include "intel_context.h" #include "intel_gt.h" +#include "intel_gt_irq.h" #include "intel_reset.h" #include "intel_ring.h" #include "shmem_utils.h" @@ -1017,10 +1018,17 @@ static void ring_release(struct intel_engine_cs *engine) intel_timeline_put(engine->legacy.timeline); } +static void irq_handler(struct intel_engine_cs *engine, u16 iir) +{ + intel_engine_signal_breadcrumbs(engine); +} + static void setup_irq(struct intel_engine_cs *engine) { struct drm_i915_private *i915 = engine->i915; + intel_engine_set_irq_handler(engine, irq_handler); + if (INTEL_GEN(i915) >= 6) { engine->irq_enable = gen6_irq_enable; engine->irq_disable = gen6_irq_disable; diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 405d814e9040..97cab1b99871 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -1774,7 +1774,7 @@ void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir) return; if (pm_iir & PM_VEBOX_USER_INTERRUPT) - intel_engine_signal_breadcrumbs(gt->engine[VECS0]); + intel_engine_cs_irq(gt->engine[VECS0], pm_iir >> 10); if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT) DRM_DEBUG("Command parser error, pm_iir 0x%08x\n", pm_iir); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 17b551a0c89f..335719f17490 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -11,6 +11,7 @@ #include "gt/intel_context.h" #include "gt/intel_engine_pm.h" #include "gt/intel_gt.h" +#include "gt/intel_gt_irq.h" #include "gt/intel_gt_pm.h" #include "gt/intel_lrc.h" #include "gt/intel_mocs.h" @@ -264,6 +265,14 @@ static void guc_submission_tasklet(struct tasklet_struct *t) spin_unlock_irqrestore(&engine->active.lock, flags); } +static void cs_irq_handler(struct intel_engine_cs *engine, u16 iir) +{ + if (iir & GT_RENDER_USER_INTERRUPT) { + intel_engine_signal_breadcrumbs(engine); + tasklet_hi_schedule(&engine->execlists.tasklet); + } +} + static void guc_reset_prepare(struct intel_engine_cs *engine) { struct intel_engine_execlists * const execlists = &engine->execlists; @@ -645,7 +654,6 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine) } engine->set_default_submission = guc_set_default_submission; - engine->flags |= I915_ENGINE_NEEDS_BREADCRUMB_TASKLET; engine->flags |= I915_ENGINE_HAS_PREEMPTION; /* @@ -681,6 +689,7 @@ static void rcs_submission_override(struct intel_engine_cs *engine) static inline void guc_default_irqs(struct intel_engine_cs *engine) { engine->irq_keep_mask = GT_RENDER_USER_INTERRUPT; + intel_engine_set_irq_handler(engine, cs_irq_handler); } int intel_guc_submission_setup(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index ef1911f11739..71331d4d0ca8 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -3988,7 +3988,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg) intel_uncore_write16(&dev_priv->uncore, GEN2_IIR, iir); if (iir & I915_USER_INTERRUPT) - intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]); + intel_engine_cs_irq(dev_priv->gt.engine[RCS0], iir); if (iir & I915_MASTER_ERROR_INTERRUPT) i8xx_error_irq_handler(dev_priv, eir, eir_stuck); @@ -4096,7 +4096,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg) intel_uncore_write(&dev_priv->uncore, GEN2_IIR, iir); if (iir & I915_USER_INTERRUPT) - intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]); + intel_engine_cs_irq(dev_priv->gt.engine[RCS0], iir); if (iir & I915_MASTER_ERROR_INTERRUPT) i9xx_error_irq_handler(dev_priv, eir, eir_stuck); @@ -4241,10 +4241,12 @@ static irqreturn_t i965_irq_handler(int irq, void *arg) intel_uncore_write(&dev_priv->uncore, GEN2_IIR, iir); if (iir & I915_USER_INTERRUPT) - intel_engine_signal_breadcrumbs(dev_priv->gt.engine[RCS0]); + intel_engine_cs_irq(dev_priv->gt.engine[RCS0], + iir); if (iir & I915_BSD_USER_INTERRUPT) - intel_engine_signal_breadcrumbs(dev_priv->gt.engine[VCS0]); + intel_engine_cs_irq(dev_priv->gt.engine[VCS0], + iir >> 25); if (iir & I915_MASTER_ERROR_INTERRUPT) i9xx_error_irq_handler(dev_priv, eir, eir_stuck); -- cgit 1.4.1 From 615160334f3f09d508511aae1297106fb4f49b1e Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Wed, 26 May 2021 15:19:46 +0100 Subject: drm/i915/params: Align visibility of device level and global modparams MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We have a few modparams which get conditionally exposed based on a Kconfig options and in most cases this also means portions of the driver implementing the respective feature are also left out. Align the visibility of device level and global modparams to make them consistent in this respect. v2: * Fix misplaced parentheses. Signed-off-by: Tvrtko Ursulin Cc: Jani Nikula Cc: Ville Syrjälä Reviewed-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20210526141946.2347085-1-tvrtko.ursulin@linux.intel.com --- drivers/gpu/drm/i915/i915_params.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h index 34ebb0662547..01121d841013 100644 --- a/drivers/gpu/drm/i915/i915_params.h +++ b/drivers/gpu/drm/i915/i915_params.h @@ -71,18 +71,18 @@ struct drm_printer; param(int, fastboot, -1, 0600) \ param(int, enable_dpcd_backlight, -1, 0600) \ param(char *, force_probe, CONFIG_DRM_I915_FORCE_PROBE, 0400) \ - param(unsigned long, fake_lmem_start, 0, 0400) \ - param(unsigned int, request_timeout_ms, CONFIG_DRM_I915_REQUEST_TIMEOUT, 0600) \ + param(unsigned long, fake_lmem_start, 0, IS_ENABLED(CONFIG_DRM_I915_UNSTABLE_FAKE_LMEM) ? 0400 : 0) \ + param(unsigned int, request_timeout_ms, CONFIG_DRM_I915_REQUEST_TIMEOUT, CONFIG_DRM_I915_REQUEST_TIMEOUT ? 0600 : 0) \ /* leave bools at the end to not create holes */ \ param(bool, enable_hangcheck, true, 0600) \ param(bool, load_detect_test, false, 0600) \ param(bool, force_reset_modeset_test, false, 0600) \ - param(bool, error_capture, true, 0600) \ + param(bool, error_capture, true, IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) ? 0600 : 0) \ param(bool, disable_display, false, 0400) \ param(bool, verbose_state_checks, true, 0) \ param(bool, nuclear_pageflip, false, 0400) \ param(bool, enable_dp_mst, true, 0600) \ - param(bool, enable_gvt, false, 0400) + param(bool, enable_gvt, false, IS_ENABLED(CONFIG_DRM_I915_GVT) ? 0400 : 0) #define MEMBER(T, member, ...) T member; struct i915_params { -- cgit 1.4.1 From 5b26d57fdb499c2363f3d895ef008e73ec02eb9b Mon Sep 17 00:00:00 2001 From: Aditya Swarup Date: Wed, 26 May 2021 02:48:52 -0700 Subject: drm/i915: Add Wa_14010733141 The WA requires the following procedure for VDBox SFC reset: If (MFX-SFC usage is 1) { 1.Issue a MFX-SFC forced lock 2.Wait for MFX-SFC forced lock ack 3.Check the MFX-SFC usage bit If (MFX-SFC usage bit is 1) Reset VDBOX and SFC else Reset VDBOX Release the force lock MFX-SFC } else if(HCP+SFC usage is 1) { 1.Issue a VE-SFC forced lock 2.Wait for SFC forced lock ack 3.Check the VE-SFC usage bit If (VE-SFC usage bit is 1) Reset VDBOX else Reset VDBOX and SFC Release the force lock VE-SFC. } else Reset VDBOX - Restructure: the changes to the original code flow should stay relatively minimal; we only need to do an extra HCP check after the usual VD-MFX check and, if true, switch the register/bit we're performing the lock on.(MattR) v2: - Assign unlock mask using paired_engine->mask instead of using BIT(paired_vecs->id). (Daniele) Bspec: 52890, 53509 Cc: Tvrtko Ursulin Cc: Matt Roper Cc: Daniele Ceraolo Spurio Cc: Lucas De Marchi Signed-off-by: Aditya Swarup Co-developed-by: Matt Roper Signed-off-by: Matt Roper Reviewed-by: Daniele Ceraolo Spurio Link: https://patchwork.freedesktop.org/patch/msgid/20210526094852.286424-2-aditya.swarup@intel.com --- drivers/gpu/drm/i915/gt/intel_reset.c | 194 +++++++++++++++++++++++----------- drivers/gpu/drm/i915/i915_reg.h | 6 ++ 2 files changed, 137 insertions(+), 63 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index d5094be6d90f..8091846d955b 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -338,15 +338,69 @@ static int gen6_reset_engines(struct intel_gt *gt, return gen6_hw_domain_reset(gt, hw_mask); } -static int gen11_lock_sfc(struct intel_engine_cs *engine, u32 *hw_mask) +static struct intel_engine_cs *find_sfc_paired_vecs_engine(struct intel_engine_cs *engine) +{ + int vecs_id; + + GEM_BUG_ON(engine->class != VIDEO_DECODE_CLASS); + + vecs_id = _VECS((engine->instance) / 2); + + return engine->gt->engine[vecs_id]; +} + +struct sfc_lock_data { + i915_reg_t lock_reg; + i915_reg_t ack_reg; + i915_reg_t usage_reg; + u32 lock_bit; + u32 ack_bit; + u32 usage_bit; + u32 reset_bit; +}; + +static void get_sfc_forced_lock_data(struct intel_engine_cs *engine, + struct sfc_lock_data *sfc_lock) +{ + switch (engine->class) { + default: + MISSING_CASE(engine->class); + fallthrough; + case VIDEO_DECODE_CLASS: + sfc_lock->lock_reg = GEN11_VCS_SFC_FORCED_LOCK(engine); + sfc_lock->lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT; + + sfc_lock->ack_reg = GEN11_VCS_SFC_LOCK_STATUS(engine); + sfc_lock->ack_bit = GEN11_VCS_SFC_LOCK_ACK_BIT; + + sfc_lock->usage_reg = GEN11_VCS_SFC_LOCK_STATUS(engine); + sfc_lock->usage_bit = GEN11_VCS_SFC_USAGE_BIT; + sfc_lock->reset_bit = GEN11_VCS_SFC_RESET_BIT(engine->instance); + + break; + case VIDEO_ENHANCEMENT_CLASS: + sfc_lock->lock_reg = GEN11_VECS_SFC_FORCED_LOCK(engine); + sfc_lock->lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT; + + sfc_lock->ack_reg = GEN11_VECS_SFC_LOCK_ACK(engine); + sfc_lock->ack_bit = GEN11_VECS_SFC_LOCK_ACK_BIT; + + sfc_lock->usage_reg = GEN11_VECS_SFC_USAGE(engine); + sfc_lock->usage_bit = GEN11_VECS_SFC_USAGE_BIT; + sfc_lock->reset_bit = GEN11_VECS_SFC_RESET_BIT(engine->instance); + + break; + } +} + +static int gen11_lock_sfc(struct intel_engine_cs *engine, + u32 *reset_mask, + u32 *unlock_mask) { struct intel_uncore *uncore = engine->uncore; u8 vdbox_sfc_access = engine->gt->info.vdbox_sfc_access; - i915_reg_t sfc_forced_lock, sfc_forced_lock_ack; - u32 sfc_forced_lock_bit, sfc_forced_lock_ack_bit; - i915_reg_t sfc_usage; - u32 sfc_usage_bit; - u32 sfc_reset_bit; + struct sfc_lock_data sfc_lock; + bool lock_obtained, lock_to_other = false; int ret; switch (engine->class) { @@ -354,53 +408,72 @@ static int gen11_lock_sfc(struct intel_engine_cs *engine, u32 *hw_mask) if ((BIT(engine->instance) & vdbox_sfc_access) == 0) return 0; - sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine); - sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT; - - sfc_forced_lock_ack = GEN11_VCS_SFC_LOCK_STATUS(engine); - sfc_forced_lock_ack_bit = GEN11_VCS_SFC_LOCK_ACK_BIT; + fallthrough; + case VIDEO_ENHANCEMENT_CLASS: + get_sfc_forced_lock_data(engine, &sfc_lock); - sfc_usage = GEN11_VCS_SFC_LOCK_STATUS(engine); - sfc_usage_bit = GEN11_VCS_SFC_USAGE_BIT; - sfc_reset_bit = GEN11_VCS_SFC_RESET_BIT(engine->instance); break; + default: + return 0; + } - case VIDEO_ENHANCEMENT_CLASS: - sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine); - sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT; + if (!(intel_uncore_read_fw(uncore, sfc_lock.usage_reg) & sfc_lock.usage_bit)) { + struct intel_engine_cs *paired_vecs; - sfc_forced_lock_ack = GEN11_VECS_SFC_LOCK_ACK(engine); - sfc_forced_lock_ack_bit = GEN11_VECS_SFC_LOCK_ACK_BIT; + if (engine->class != VIDEO_DECODE_CLASS || + !IS_GEN(engine->i915, 12)) + return 0; - sfc_usage = GEN11_VECS_SFC_USAGE(engine); - sfc_usage_bit = GEN11_VECS_SFC_USAGE_BIT; - sfc_reset_bit = GEN11_VECS_SFC_RESET_BIT(engine->instance); - break; + /* + * Wa_14010733141 + * + * If the VCS-MFX isn't using the SFC, we also need to check + * whether VCS-HCP is using it. If so, we need to issue a *VE* + * forced lock on the VE engine that shares the same SFC. + */ + if (!(intel_uncore_read_fw(uncore, + GEN12_HCP_SFC_LOCK_STATUS(engine)) & + GEN12_HCP_SFC_USAGE_BIT)) + return 0; - default: - return 0; + paired_vecs = find_sfc_paired_vecs_engine(engine); + get_sfc_forced_lock_data(paired_vecs, &sfc_lock); + lock_to_other = true; + *unlock_mask |= paired_vecs->mask; + } else { + *unlock_mask |= engine->mask; } /* - * If the engine is using a SFC, tell the engine that a software reset + * If the engine is using an SFC, tell the engine that a software reset * is going to happen. The engine will then try to force lock the SFC. * If SFC ends up being locked to the engine we want to reset, we have * to reset it as well (we will unlock it once the reset sequence is * completed). */ - if (!(intel_uncore_read_fw(uncore, sfc_usage) & sfc_usage_bit)) - return 0; - - rmw_set_fw(uncore, sfc_forced_lock, sfc_forced_lock_bit); + rmw_set_fw(uncore, sfc_lock.lock_reg, sfc_lock.lock_bit); ret = __intel_wait_for_register_fw(uncore, - sfc_forced_lock_ack, - sfc_forced_lock_ack_bit, - sfc_forced_lock_ack_bit, + sfc_lock.ack_reg, + sfc_lock.ack_bit, + sfc_lock.ack_bit, 1000, 0, NULL); - /* Was the SFC released while we were trying to lock it? */ - if (!(intel_uncore_read_fw(uncore, sfc_usage) & sfc_usage_bit)) + /* + * Was the SFC released while we were trying to lock it? + * + * We should reset both the engine and the SFC if: + * - We were locking the SFC to this engine and the lock succeeded + * OR + * - We were locking the SFC to a different engine (Wa_14010733141) + * but the SFC was released before the lock was obtained. + * + * Otherwise we need only reset the engine by itself and we can + * leave the SFC alone. + */ + lock_obtained = (intel_uncore_read_fw(uncore, sfc_lock.usage_reg) & + sfc_lock.usage_bit) != 0; + if (lock_obtained == lock_to_other) return 0; if (ret) { @@ -408,7 +481,7 @@ static int gen11_lock_sfc(struct intel_engine_cs *engine, u32 *hw_mask) return ret; } - *hw_mask |= sfc_reset_bit; + *reset_mask |= sfc_lock.reset_bit; return 0; } @@ -416,28 +489,19 @@ static void gen11_unlock_sfc(struct intel_engine_cs *engine) { struct intel_uncore *uncore = engine->uncore; u8 vdbox_sfc_access = engine->gt->info.vdbox_sfc_access; - i915_reg_t sfc_forced_lock; - u32 sfc_forced_lock_bit; - - switch (engine->class) { - case VIDEO_DECODE_CLASS: - if ((BIT(engine->instance) & vdbox_sfc_access) == 0) - return; - - sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine); - sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT; - break; + struct sfc_lock_data sfc_lock = {}; - case VIDEO_ENHANCEMENT_CLASS: - sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine); - sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT; - break; + if (engine->class != VIDEO_DECODE_CLASS && + engine->class != VIDEO_ENHANCEMENT_CLASS) + return; - default: + if (engine->class == VIDEO_DECODE_CLASS && + (BIT(engine->instance) & vdbox_sfc_access) == 0) return; - } - rmw_clear_fw(uncore, sfc_forced_lock, sfc_forced_lock_bit); + get_sfc_forced_lock_data(engine, &sfc_lock); + + rmw_clear_fw(uncore, sfc_lock.lock_reg, sfc_lock.lock_bit); } static int gen11_reset_engines(struct intel_gt *gt, @@ -456,23 +520,23 @@ static int gen11_reset_engines(struct intel_gt *gt, }; struct intel_engine_cs *engine; intel_engine_mask_t tmp; - u32 hw_mask; + u32 reset_mask, unlock_mask = 0; int ret; if (engine_mask == ALL_ENGINES) { - hw_mask = GEN11_GRDOM_FULL; + reset_mask = GEN11_GRDOM_FULL; } else { - hw_mask = 0; + reset_mask = 0; for_each_engine_masked(engine, gt, engine_mask, tmp) { GEM_BUG_ON(engine->id >= ARRAY_SIZE(hw_engine_mask)); - hw_mask |= hw_engine_mask[engine->id]; - ret = gen11_lock_sfc(engine, &hw_mask); + reset_mask |= hw_engine_mask[engine->id]; + ret = gen11_lock_sfc(engine, &reset_mask, &unlock_mask); if (ret) goto sfc_unlock; } } - ret = gen6_hw_domain_reset(gt, hw_mask); + ret = gen6_hw_domain_reset(gt, reset_mask); sfc_unlock: /* @@ -480,10 +544,14 @@ sfc_unlock: * gen11_lock_sfc to make sure that we clean properly if something * wrong happened during the lock (e.g. lock acquired after timeout * expiration). + * + * Due to Wa_14010733141, we may have locked an SFC to an engine that + * wasn't being reset. So instead of calling gen11_unlock_sfc() + * on engine_mask, we instead call it on the mask of engines that our + * gen11_lock_sfc() calls told us actually had locks attempted. */ - if (engine_mask != ALL_ENGINES) - for_each_engine_masked(engine, gt, engine_mask, tmp) - gen11_unlock_sfc(engine); + for_each_engine_masked(engine, gt, unlock_mask, tmp) + gen11_unlock_sfc(engine); return ret; } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 1ed097b8316a..aca1b0e0e935 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -416,6 +416,12 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN11_VECS_SFC_USAGE(engine) _MMIO((engine)->mmio_base + 0x2014) #define GEN11_VECS_SFC_USAGE_BIT (1 << 0) +#define GEN12_HCP_SFC_FORCED_LOCK(engine) _MMIO((engine)->mmio_base + 0x2910) +#define GEN12_HCP_SFC_FORCED_LOCK_BIT REG_BIT(0) +#define GEN12_HCP_SFC_LOCK_STATUS(engine) _MMIO((engine)->mmio_base + 0x2914) +#define GEN12_HCP_SFC_LOCK_ACK_BIT REG_BIT(1) +#define GEN12_HCP_SFC_USAGE_BIT REG_BIT(0) + #define GEN12_SFC_DONE(n) _MMIO(0x1cc00 + (n) * 0x100) #define GEN12_SFC_DONE_MAX 4 -- cgit 1.4.1