diff options
| author | Dave Airlie <airlied@redhat.com> | 2016-02-09 10:27:41 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2016-02-09 10:27:41 +1000 |
| commit | b039d6d02500ba8fe22e545b55b4961c1ef0f32d (patch) | |
| tree | a8e5b387d79a21afa42e6bb905ea1b188f91f5c8 | |
| parent | 388f7b1d6e8ca06762e2454d28d6c3c55ad0fe95 (diff) | |
| parent | 947eaebc318d63ada82901cea86c586ac3d854f0 (diff) | |
Merge tag 'drm-intel-next-2016-01-24' of git://anongit.freedesktop.org/drm-intel into drm-next
- support for v3 vbt dsi blocks (Jani)
- improve mmio debug checks (Mika Kuoppala)
- reorg the ddi port translation table entries and related code (Ville)
- reorg gen8 interrupt handling for future platforms (Tvrtko)
- refactor tile width/height computations for framebuffers (Ville)
- kerneldoc integration for intel_pm.c (Jani)
- move default context from engines to device-global dev_priv (Dave Gordon)
- make seqno/irq ordering coherent with execlist (Chris)
- decouple internal engine number from UABI (Chris&Tvrtko)
- tons of small fixes all over, as usual
* tag 'drm-intel-next-2016-01-24' of git://anongit.freedesktop.org/drm-intel: (148 commits)
drm/i915: Update DRIVER_DATE to 20160124
drm/i915: Seal busy-ioctl uABI and prevent leaking of internal ids
drm/i915: Decouple execbuf uAPI from internal implementation
drm/i915: Use ordered seqno write interrupt generation on gen8+ execlists
drm/i915: Limit the auto arming of mmio debugs on vlv/chv
drm/i915: Tune down "GT register while GT waking disabled" message
drm/i915: tidy up a few leftovers
drm/i915: abolish separate per-ring default_context pointers
drm/i915: simplify allocation of driver-internal requests
drm/i915: Fix NULL plane->fb oops on SKL
drm/i915: Do not put big intel_crtc_state on the stack
Revert "drm/i915: Add two-stage ILK-style watermark programming (v10)"
drm/i915: add DOC: headline to RC6 kernel-doc
drm/i915: turn some bogus kernel-doc comments to normal comments
drm/i915/sdvo: revert bogus kernel-doc comments to normal comments
drm/i915/gen9: Correct max save/restore register count during gpu reset with GuC
drm/i915: Demote user facing DMC firmware load failure message
drm/i915: use hlist_for_each_entry
drm/i915: skl_update_scaler() wants a rotation bitmask instead of bit number
drm/i915: Don't reject primary plane windowing with color keying enabled on SKL+
...
50 files changed, 2704 insertions, 1851 deletions
diff --git a/Documentation/DocBook/gpu.tmpl b/Documentation/DocBook/gpu.tmpl index a8669330b456..351e801cead9 100644 --- a/Documentation/DocBook/gpu.tmpl +++ b/Documentation/DocBook/gpu.tmpl @@ -3319,6 +3319,12 @@ int num_ioctls;</synopsis> !Pdrivers/gpu/drm/i915/intel_csr.c csr support for dmc !Idrivers/gpu/drm/i915/intel_csr.c </sect2> + <sect2> + <title>Video BIOS Table (VBT)</title> +!Pdrivers/gpu/drm/i915/intel_bios.c Video BIOS Table (VBT) +!Idrivers/gpu/drm/i915/intel_bios.c +!Idrivers/gpu/drm/i915/intel_bios.h + </sect2> </sect1> <sect1> diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 0fc38bb7276c..c5db23511184 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -1331,7 +1331,8 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused) struct intel_engine_cs *ring; u64 acthd[I915_NUM_RINGS]; u32 seqno[I915_NUM_RINGS]; - int i; + u32 instdone[I915_NUM_INSTDONE_REG]; + int i, j; if (!i915.enable_hangcheck) { seq_printf(m, "Hangcheck disabled\n"); @@ -1345,6 +1346,8 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused) acthd[i] = intel_ring_get_active_head(ring); } + i915_get_extra_instdone(dev, instdone); + intel_runtime_pm_put(dev_priv); if (delayed_work_pending(&dev_priv->gpu_error.hangcheck_work)) { @@ -1365,6 +1368,21 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused) (long long)ring->hangcheck.max_acthd); seq_printf(m, "\tscore = %d\n", ring->hangcheck.score); seq_printf(m, "\taction = %d\n", ring->hangcheck.action); + + if (ring->id == RCS) { + seq_puts(m, "\tinstdone read ="); + + for (j = 0; j < I915_NUM_INSTDONE_REG; j++) + seq_printf(m, " 0x%08x", instdone[j]); + + seq_puts(m, "\n\tinstdone accu ="); + + for (j = 0; j < I915_NUM_INSTDONE_REG; j++) + seq_printf(m, " 0x%08x", + ring->hangcheck.instdone[j]); + + seq_puts(m, "\n"); + } } return 0; @@ -1942,11 +1960,8 @@ static int i915_context_status(struct seq_file *m, void *unused) seq_puts(m, "HW context "); describe_ctx(m, ctx); - for_each_ring(ring, dev_priv, i) { - if (ring->default_context == ctx) - seq_printf(m, "(default context %s) ", - ring->name); - } + if (ctx == dev_priv->kernel_context) + seq_printf(m, "(kernel context) "); if (i915.enable_execlists) { seq_putc(m, '\n'); @@ -1976,12 +1991,13 @@ static int i915_context_status(struct seq_file *m, void *unused) } static void i915_dump_lrc_obj(struct seq_file *m, - struct intel_engine_cs *ring, - struct drm_i915_gem_object *ctx_obj) + struct intel_context *ctx, + struct intel_engine_cs *ring) { struct page *page; uint32_t *reg_state; int j; + struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state; unsigned long ggtt_offset = 0; if (ctx_obj == NULL) { @@ -1991,7 +2007,7 @@ static void i915_dump_lrc_obj(struct seq_file *m, } seq_printf(m, "CONTEXT: %s %u\n", ring->name, - intel_execlists_ctx_id(ctx_obj)); + intel_execlists_ctx_id(ctx, ring)); if (!i915_gem_obj_ggtt_bound(ctx_obj)) seq_puts(m, "\tNot bound in GGTT\n"); @@ -2037,13 +2053,10 @@ static int i915_dump_lrc(struct seq_file *m, void *unused) if (ret) return ret; - list_for_each_entry(ctx, &dev_priv->context_list, link) { - for_each_ring(ring, dev_priv, i) { - if (ring->default_context != ctx) - i915_dump_lrc_obj(m, ring, - ctx->engine[i].state); - } - } + list_for_each_entry(ctx, &dev_priv->context_list, link) + if (ctx != dev_priv->kernel_context) + for_each_ring(ring, dev_priv, i) + i915_dump_lrc_obj(m, ctx, ring); mutex_unlock(&dev->struct_mutex); @@ -2092,13 +2105,13 @@ static int i915_execlists(struct seq_file *m, void *data) seq_printf(m, "\tStatus pointer: 0x%08X\n", status_pointer); read_pointer = ring->next_context_status_buffer; - write_pointer = status_pointer & 0x07; + write_pointer = GEN8_CSB_WRITE_PTR(status_pointer); if (read_pointer > write_pointer) - write_pointer += 6; + write_pointer += GEN8_CSB_ENTRIES; seq_printf(m, "\tRead pointer: 0x%08X, write pointer 0x%08X\n", read_pointer, write_pointer); - for (i = 0; i < 6; i++) { + for (i = 0; i < GEN8_CSB_ENTRIES; i++) { status = I915_READ(RING_CONTEXT_STATUS_BUF_LO(ring, i)); ctx_id = I915_READ(RING_CONTEXT_STATUS_BUF_HI(ring, i)); @@ -2115,11 +2128,8 @@ static int i915_execlists(struct seq_file *m, void *data) seq_printf(m, "\t%d requests in queue\n", count); if (head_req) { - struct drm_i915_gem_object *ctx_obj; - - ctx_obj = head_req->ctx->engine[ring_id].state; seq_printf(m, "\tHead request id: %u\n", - intel_execlists_ctx_id(ctx_obj)); + intel_execlists_ctx_id(head_req->ctx, ring)); seq_printf(m, "\tHead request tail: %u\n", head_req->tail); } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index f357058c74d9..11d8414edbbe 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1079,7 +1079,6 @@ static int bxt_resume_prepare(struct drm_i915_private *dev_priv) */ broxton_init_cdclk(dev); broxton_ddi_phy_init(dev); - intel_prepare_ddi(dev); return 0; } @@ -1338,8 +1337,8 @@ static int vlv_wait_for_gt_wells(struct drm_i915_private *dev_priv, return 0; DRM_DEBUG_KMS("waiting for GT wells to go %s (%08x)\n", - wait_for_on ? "on" : "off", - I915_READ(VLV_GTLC_PW_STATUS)); + onoff(wait_for_on), + I915_READ(VLV_GTLC_PW_STATUS)); /* * RC6 transitioning can be delayed up to 2 msec (see @@ -1348,7 +1347,7 @@ static int vlv_wait_for_gt_wells(struct drm_i915_private *dev_priv, err = wait_for(COND, 3); if (err) DRM_ERROR("timeout waiting for GT wells to go %s\n", - wait_for_on ? "on" : "off"); + onoff(wait_for_on)); return err; #undef COND @@ -1359,7 +1358,7 @@ static void vlv_check_no_gt_access(struct drm_i915_private *dev_priv) if (!(I915_READ(VLV_GTLC_PW_STATUS) & VLV_GTLC_ALLOWWAKEERR)) return; - DRM_ERROR("GT register access while GT waking disabled\n"); + DRM_DEBUG_DRIVER("GT register access while GT waking disabled\n"); I915_WRITE(VLV_GTLC_PW_STATUS, VLV_GTLC_ALLOWWAKEERR); } @@ -1503,6 +1502,10 @@ static int intel_runtime_suspend(struct device *device) enable_rpm_wakeref_asserts(dev_priv); WARN_ON_ONCE(atomic_read(&dev_priv->pm.wakeref_count)); + + if (intel_uncore_arm_unclaimed_mmio_detection(dev_priv)) + DRM_ERROR("Unclaimed access detected prior to suspending\n"); + dev_priv->pm.suspended = true; /* @@ -1551,6 +1554,8 @@ static int intel_runtime_resume(struct device *device) intel_opregion_notify_adapter(dev, PCI_D0); dev_priv->pm.suspended = false; + if (intel_uncore_unclaimed_mmio(dev_priv)) + DRM_DEBUG_DRIVER("Unclaimed access during suspend, bios?\n"); intel_guc_resume(dev); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index f0f75d7c0d94..afb0beee9975 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -34,6 +34,7 @@ #include <uapi/drm/drm_fourcc.h> #include <drm/drmP.h> +#include "i915_params.h" #include "i915_reg.h" #include "intel_bios.h" #include "intel_ringbuffer.h" @@ -58,7 +59,7 @@ #define DRIVER_NAME "i915" #define DRIVER_DESC "Intel Graphics" -#define DRIVER_DATE "20151218" +#define DRIVER_DATE "20160124" #undef WARN_ON /* Many gcc seem to no see through this and fall over :( */ @@ -69,11 +70,11 @@ BUILD_BUG_ON(__i915_warn_cond); \ WARN(__i915_warn_cond, "WARN_ON(" #x ")"); }) #else -#define WARN_ON(x) WARN((x), "WARN_ON(%s)", #x ) +#define WARN_ON(x) WARN((x), "%s", "WARN_ON(" __stringify(x) ")") #endif #undef WARN_ON_ONCE -#define WARN_ON_ONCE(x) WARN_ONCE((x), "WARN_ON_ONCE(%s)", #x ) +#define WARN_ON_ONCE(x) WARN_ONCE((x), "%s", "WARN_ON_ONCE(" __stringify(x) ")") #define MISSING_CASE(x) WARN(1, "Missing switch case (%lu) in %s\n", \ (long) (x), __func__); @@ -87,31 +88,25 @@ */ #define I915_STATE_WARN(condition, format...) ({ \ int __ret_warn_on = !!(condition); \ - if (unlikely(__ret_warn_on)) { \ - if (i915.verbose_state_checks) \ - WARN(1, format); \ - else \ + if (unlikely(__ret_warn_on)) \ + if (!WARN(i915.verbose_state_checks, format)) \ DRM_ERROR(format); \ - } \ unlikely(__ret_warn_on); \ }) -#define I915_STATE_WARN_ON(condition) ({ \ - int __ret_warn_on = !!(condition); \ - if (unlikely(__ret_warn_on)) { \ - if (i915.verbose_state_checks) \ - WARN(1, "WARN_ON(" #condition ")\n"); \ - else \ - DRM_ERROR("WARN_ON(" #condition ")\n"); \ - } \ - unlikely(__ret_warn_on); \ -}) +#define I915_STATE_WARN_ON(x) \ + I915_STATE_WARN((x), "%s", "WARN_ON(" __stringify(x) ")") static inline const char *yesno(bool v) { return v ? "yes" : "no"; } +static inline const char *onoff(bool v) +{ + return v ? "on" : "off"; +} + enum pipe { INVALID_PIPE = -1, PIPE_A = 0, @@ -339,7 +334,7 @@ struct drm_i915_file_private { unsigned boosts; } rps; - struct intel_engine_cs *bsd_ring; + unsigned int bsd_ring; }; enum intel_dpll_id { @@ -633,6 +628,7 @@ struct drm_i915_display_funcs { struct dpll *best_clock); int (*compute_pipe_wm)(struct intel_crtc *crtc, struct drm_atomic_state *state); + void (*program_watermarks)(struct intel_crtc_state *cstate); void (*update_wm)(struct drm_crtc *crtc); int (*modeset_calc_cdclk)(struct drm_atomic_state *state); void (*modeset_commit_cdclk)(struct drm_atomic_state *state); @@ -657,9 +653,6 @@ struct drm_i915_display_funcs { struct drm_i915_gem_object *obj, struct drm_i915_gem_request *req, uint32_t flags); - void (*update_primary_plane)(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int x, int y); void (*hpd_irq_setup)(struct drm_device *dev); /* clock updates for mode set */ /* cursor updates */ @@ -726,6 +719,8 @@ struct intel_uncore { i915_reg_t reg_post; u32 val_reset; } fw_domain[FW_DOMAIN_ID_COUNT]; + + int unclaimed_mmio_check; }; /* Iterate over initialised fw domains */ @@ -889,6 +884,9 @@ struct intel_context { struct drm_i915_gem_object *state; struct intel_ringbuffer *ringbuf; int pin_count; + struct i915_vma *lrc_vma; + u64 lrc_desc; + uint32_t *lrc_reg_state; } engine[I915_NUM_RINGS]; struct list_head link; @@ -1301,7 +1299,7 @@ struct i915_gem_mm { bool busy; /* the indicator for dispatch video commands on two BSD rings */ - int bsd_ring_dispatch_index; + unsigned int bsd_ring_dispatch_index; /** Bit 6 swizzling required for X tiling */ uint32_t bit_6_swizzle_x; @@ -1487,7 +1485,7 @@ struct intel_vbt_data { u8 seq_version; u32 size; u8 *data; - u8 *sequence[MIPI_SEQ_MAX]; + const u8 *sequence[MIPI_SEQ_MAX]; } dsi; int crt_ddc_pin; @@ -1784,7 +1782,7 @@ struct drm_i915_private { unsigned int fsb_freq, mem_freq, is_ddr3; unsigned int skl_boot_cdclk; - unsigned int cdclk_freq, max_cdclk_freq; + unsigned int cdclk_freq, max_cdclk_freq, atomic_cdclk_freq; unsigned int max_dotclk_freq; unsigned int hpll_freq; unsigned int czclk_freq; @@ -1829,8 +1827,13 @@ struct drm_i915_private { struct intel_pipe_crc pipe_crc[I915_MAX_PIPES]; #endif + /* dpll and cdclk state is protected by connection_mutex */ int num_shared_dpll; struct intel_shared_dpll shared_dplls[I915_NUM_PLLS]; + + unsigned int active_crtcs; + unsigned int min_pixclk[I915_MAX_PIPES]; + int dpio_phy_iosf_port[I915_NUM_PHYS_VLV]; struct i915_workarounds workarounds; @@ -1945,6 +1948,8 @@ struct drm_i915_private { void (*stop_ring)(struct intel_engine_cs *ring); } gt; + struct intel_context *kernel_context; + bool edp_low_vswing; /* perform PHY state sanity checks? */ @@ -2265,9 +2270,9 @@ struct drm_i915_gem_request { }; -int i915_gem_request_alloc(struct intel_engine_cs *ring, - struct intel_context *ctx, - struct drm_i915_gem_request **req_out); +struct drm_i915_gem_request * __must_check +i915_gem_request_alloc(struct intel_engine_cs *engine, + struct intel_context *ctx); void i915_gem_request_cancel(struct drm_i915_gem_request *req); void i915_gem_request_free(struct kref *req_ref); int i915_gem_request_add_to_client(struct drm_i915_gem_request *req, @@ -2576,6 +2581,11 @@ struct drm_i915_cmd_table { /* Early gen2 have a totally busted CS tlb and require pinned batches. */ #define HAS_BROKEN_CS_TLB(dev) (IS_I830(dev) || IS_845G(dev)) + +/* WaRsDisableCoarsePowerGating:skl,bxt */ +#define NEEDS_WaRsDisableCoarsePowerGating(dev) (IS_BXT_REVID(dev, 0, BXT_REVID_A1) || \ + ((IS_SKL_GT3(dev) || IS_SKL_GT4(dev)) && \ + IS_SKL_REVID(dev, 0, SKL_REVID_F0))) /* * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts * even when in MSI mode. This results in spurious interrupt warnings if the @@ -2665,44 +2675,7 @@ extern int i915_max_ioctl; extern int i915_suspend_switcheroo(struct drm_device *dev, pm_message_t state); extern int i915_resume_switcheroo(struct drm_device *dev); -/* i915_params.c */ -struct i915_params { - int modeset; - int panel_ignore_lid; - int semaphores; - int lvds_channel_mode; - int panel_use_ssc; - int vbt_sdvo_panel_type; - int enable_rc6; - int enable_dc; - int enable_fbc; - int enable_ppgtt; - int enable_execlists; - int enable_psr; - unsigned int preliminary_hw_support; - int disable_power_well; - int enable_ips; - int invert_brightness; - int enable_cmd_parser; - /* leave bools at the end to not create holes */ - bool enable_hangcheck; - bool fastboot; - bool prefault_disable; - bool load_detect_test; - bool reset; - bool disable_display; - bool disable_vtd_wa; - bool enable_guc_submission; - int guc_log_level; - int use_mmio_flip; - int mmio_debug; - bool verbose_state_checks; - bool nuclear_pageflip; - int edp_vswing; -}; -extern struct i915_params i915 __read_mostly; - - /* i915_dma.c */ +/* i915_dma.c */ extern int i915_driver_load(struct drm_device *, unsigned long flags); extern int i915_driver_unload(struct drm_device *); extern int i915_driver_open(struct drm_device *dev, struct drm_file *file); @@ -2745,7 +2718,8 @@ extern void intel_uncore_sanitize(struct drm_device *dev); extern void intel_uncore_early_sanitize(struct drm_device *dev, bool restore_forcewake); extern void intel_uncore_init(struct drm_device *dev); -extern void intel_uncore_check_errors(struct drm_device *dev); +extern bool intel_uncore_unclaimed_mmio(struct drm_i915_private *dev_priv); +extern bool intel_uncore_arm_unclaimed_mmio_detection(struct drm_i915_private *dev_priv); extern void intel_uncore_fini(struct drm_device *dev); extern void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore); const char *intel_uncore_forcewake_domain_to_str(const enum forcewake_domain_id id); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index ddc21d4b388d..371bbb28c471 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1251,7 +1251,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req, int state = interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE; DEFINE_WAIT(wait); unsigned long timeout_expire; - s64 before, now; + s64 before = 0; /* Only to silence a compiler warning. */ int ret; WARN(!intel_irqs_enabled(dev_priv), "IRQs disabled"); @@ -1271,14 +1271,17 @@ int __i915_wait_request(struct drm_i915_gem_request *req, return -ETIME; timeout_expire = jiffies + nsecs_to_jiffies_timeout(*timeout); + + /* + * Record current time in case interrupted by signal, or wedged. + */ + before = ktime_get_raw_ns(); } if (INTEL_INFO(dev_priv)->gen >= 6) gen6_rps_boost(dev_priv, rps, req->emitted_jiffies); - /* Record current time in case interrupted by signal, or wedged */ trace_i915_gem_request_wait_begin(req); - before = ktime_get_raw_ns(); /* Optimistic spin for the next jiffie before touching IRQs */ ret = __i915_spin_request(req, state); @@ -1343,11 +1346,10 @@ int __i915_wait_request(struct drm_i915_gem_request *req, finish_wait(&ring->irq_queue, &wait); out: - now = ktime_get_raw_ns(); trace_i915_gem_request_wait_end(req); if (timeout) { - s64 tres = *timeout - (now - before); + s64 tres = *timeout - (ktime_get_raw_ns() - before); *timeout = tres < 0 ? 0 : tres; @@ -2677,10 +2679,8 @@ void i915_gem_request_free(struct kref *req_ref) i915_gem_request_remove_from_client(req); if (ctx) { - if (i915.enable_execlists) { - if (ctx != req->ring->default_context) - intel_lr_context_unpin(req); - } + if (i915.enable_execlists && ctx != req->i915->kernel_context) + intel_lr_context_unpin(req); i915_gem_context_unreference(ctx); } @@ -2688,9 +2688,10 @@ void i915_gem_request_free(struct kref *req_ref) kmem_cache_free(req->i915->requests, req); } -int i915_gem_request_alloc(struct intel_engine_cs *ring, - struct intel_context *ctx, - struct drm_i915_gem_request **req_out) +static inline int +__i915_gem_request_alloc(struct intel_engine_cs *ring, + struct intel_context *ctx, + struct drm_i915_gem_request **req_out) { struct drm_i915_private *dev_priv = to_i915(ring->dev); struct drm_i915_gem_request *req; @@ -2753,6 +2754,31 @@ err: return ret; } +/** + * i915_gem_request_alloc - allocate a request structure + * + * @engine: engine that we wish to issue the request on. + * @ctx: context that the request will be associated with. + * This can be NULL if the request is not directly related to + * any specific user context, in which case this function will + * choose an appropriate context to use. + * + * Returns a pointer to the allocated request if successful, + * or an error code if not. + */ +struct drm_i915_gem_request * +i915_gem_request_alloc(struct intel_engine_cs *engine, + struct intel_context *ctx) +{ + struct drm_i915_gem_request *req; + int err; + + if (ctx == NULL) + ctx = to_i915(engine->dev)->kernel_context; + err = __i915_gem_request_alloc(engine, ctx, &req); + return err ? ERR_PTR(err) : req; +} + void i915_gem_request_cancel(struct drm_i915_gem_request *req) { intel_ring_reserved_space_cancel(req->ringbuf); @@ -3170,9 +3196,13 @@ __i915_gem_object_sync(struct drm_i915_gem_object *obj, return 0; if (*to_req == NULL) { - ret = i915_gem_request_alloc(to, to->default_context, to_req); - if (ret) - return ret; + struct drm_i915_gem_request *req; + + req = i915_gem_request_alloc(to, NULL); + if (IS_ERR(req)) + return PTR_ERR(req); + + *to_req = req; } trace_i915_gem_ring_sync_to(*to_req, from, from_req); @@ -3372,9 +3402,9 @@ int i915_gpu_idle(struct drm_device *dev) if (!i915.enable_execlists) { struct drm_i915_gem_request *req; - ret = i915_gem_request_alloc(ring, ring->default_context, &req); - if (ret) - return ret; + req = i915_gem_request_alloc(ring, NULL); + if (IS_ERR(req)) + return PTR_ERR(req); ret = i915_switch_context(req); if (ret) { @@ -4328,10 +4358,20 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data, if (ret) goto unref; - BUILD_BUG_ON(I915_NUM_RINGS > 16); - args->busy = obj->active << 16; - if (obj->last_write_req) - args->busy |= obj->last_write_req->ring->id; + args->busy = 0; + if (obj->active) { + int i; + + for (i = 0; i < I915_NUM_RINGS; i++) { + struct drm_i915_gem_request *req; + + req = obj->last_read_req[i]; + if (req) + args->busy |= 1 << (16 + req->ring->exec_id); + } + if (obj->last_write_req) + args->busy |= obj->last_write_req->ring->exec_id; + } unref: drm_gem_object_unreference(&obj->base); @@ -4832,7 +4872,7 @@ i915_gem_init_hw(struct drm_device *dev) */ init_unused_rings(dev); - BUG_ON(!dev_priv->ring[RCS].default_context); + BUG_ON(!dev_priv->kernel_context); ret = i915_ppgtt_init_hw(dev); if (ret) { @@ -4869,10 +4909,9 @@ i915_gem_init_hw(struct drm_device *dev) for_each_ring(ring, dev_priv, i) { struct drm_i915_gem_request *req; - WARN_ON(!ring->default_context); - - ret = i915_gem_request_alloc(ring, ring->default_context, &req); - if (ret) { + req = i915_gem_request_alloc(ring, NULL); + if (IS_ERR(req)) { + ret = PTR_ERR(req); i915_gem_cleanup_ringbuffer(dev); goto out; } @@ -5112,6 +5151,8 @@ int i915_gem_open(struct drm_device *dev, struct drm_file *file) spin_lock_init(&file_priv->mm.lock); INIT_LIST_HEAD(&file_priv->mm.request_list); + file_priv->bsd_ring = -1; + ret = i915_gem_context_open(dev, file); if (ret) kfree(file_priv); diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index c25083c78ba7..6a4f64b03db6 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -347,22 +347,20 @@ void i915_gem_context_reset(struct drm_device *dev) i915_gem_context_unreference(lctx); ring->last_context = NULL; } - - /* Force the GPU state to be reinitialised on enabling */ - if (ring->default_context) - ring->default_context->legacy_hw_ctx.initialized = false; } + + /* Force the GPU state to be reinitialised on enabling */ + dev_priv->kernel_context->legacy_hw_ctx.initialized = false; } int i915_gem_context_init(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; struct intel_context *ctx; - int i; /* Init should only be called once per module load. Eventually the * restriction on the context_disabled check can be loosened. */ - if (WARN_ON(dev_priv->ring[RCS].default_context)) + if (WARN_ON(dev_priv->kernel_context)) return 0; if (intel_vgpu_active(dev) && HAS_LOGICAL_RING_CONTEXTS(dev)) { @@ -392,12 +390,7 @@ int i915_gem_context_init(struct drm_device *dev) return PTR_ERR(ctx); } - for (i = 0; i < I915_NUM_RINGS; i++) { - struct intel_engine_cs *ring = &dev_priv->ring[i]; - - /* NB: RCS will hold a ref for all rings */ - ring->default_context = ctx; - } + dev_priv->kernel_context = ctx; DRM_DEBUG_DRIVER("%s context support initialized\n", i915.enable_execlists ? "LR" : @@ -408,7 +401,7 @@ int i915_gem_context_init(struct drm_device *dev) void i915_gem_context_fini(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_context *dctx = dev_priv->ring[RCS].default_context; + struct intel_context *dctx = dev_priv->kernel_context; int i; if (dctx->legacy_hw_ctx.rcs_state) { @@ -435,17 +428,17 @@ void i915_gem_context_fini(struct drm_device *dev) i915_gem_object_ggtt_unpin(dctx->legacy_hw_ctx.rcs_state); } - for (i = 0; i < I915_NUM_RINGS; i++) { + for (i = I915_NUM_RINGS; --i >= 0;) { struct intel_engine_cs *ring = &dev_priv->ring[i]; - if (ring->last_context) + if (ring->last_context) { i915_gem_context_unreference(ring->last_context); - - ring->default_context = NULL; - ring->last_context = NULL; + ring->last_context = NULL; + } } i915_gem_context_unreference(dctx); + dev_priv->kernel_context = NULL; } int i915_gem_context_enable(struct drm_i915_gem_request *req) diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index dccb517361b3..2dc08ce1079a 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -193,13 +193,10 @@ static struct i915_vma *eb_get_vma(struct eb_vmas *eb, unsigned long handle) return eb->lut[handle]; } else { struct hlist_head *head; - struct hlist_node *node; + struct i915_vma *vma; head = &eb->buckets[handle & eb->and]; - hlist_for_each(node, head) { - struct i915_vma *vma; - - vma = hlist_entry(node, struct i915_vma, exec_node); + hlist_for_each_entry(vma, head, exec_node) { if (vma->exec_handle == handle) return vma; } @@ -1309,6 +1306,9 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params, exec_start = params->batch_obj_vm_offset + params->args_batch_start_offset; + if (exec_len == 0) + exec_len = params->batch_obj->base.size; + ret = ring->dispatch_execbuffer(params->request, exec_start, exec_len, params->dispatch_flags); @@ -1325,33 +1325,23 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params, /** * Find one BSD ring to dispatch the corresponding BSD command. - * The Ring ID is returned. + * The ring index is returned. */ -static int gen8_dispatch_bsd_ring(struct drm_device *dev, - struct drm_file *file) +static unsigned int +gen8_dispatch_bsd_ring(struct drm_i915_private *dev_priv, struct drm_file *file) { - struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_file_private *file_priv = file->driver_priv; - /* Check whether the file_priv is using one ring */ - if (file_priv->bsd_ring) - return file_priv->bsd_ring->id; - else { - /* If no, use the ping-pong mechanism to select one ring */ - int ring_id; - - mutex_lock(&dev->struct_mutex); - if (dev_priv->mm.bsd_ring_dispatch_index == 0) { - ring_id = VCS; - dev_priv->mm.bsd_ring_dispatch_index = 1; - } else { - ring_id = VCS2; - dev_priv->mm.bsd_ring_dispatch_index = 0; - } - file_priv->bsd_ring = &dev_priv->ring[ring_id]; - mutex_unlock(&dev->struct_mutex); - return ring_id; + /* Check whether the file_priv has already selected one ring. */ + if ((int)file_priv->bsd_ring < 0) { + /* If not, use the ping-pong mechanism to select one. */ + mutex_lock(&dev_priv->dev->struct_mutex); + file_priv->bsd_ring = dev_priv->mm.bsd_ring_dispatch_index; + dev_priv->mm.bsd_ring_dispatch_index ^= 1; + mutex_unlock(&dev_priv->dev->struct_mutex); } + + return file_priv->bsd_ring; } static struct drm_i915_gem_object * @@ -1374,6 +1364,63 @@ eb_get_batch(struct eb_vmas *eb) return vma->obj; } +#define I915_USER_RINGS (4) + +static const enum intel_ring_id user_ring_map[I915_USER_RINGS + 1] = { + [I915_EXEC_DEFAULT] = RCS, + [I915_EXEC_RENDER] = RCS, + [I915_EXEC_BLT] = BCS, + [I915_EXEC_BSD] = VCS, + [I915_EXEC_VEBOX] = VECS +}; + +static int +eb_select_ring(struct drm_i915_private *dev_priv, + struct drm_file *file, + struct drm_i915_gem_execbuffer2 *args, + struct intel_engine_cs **ring) +{ + unsigned int user_ring_id = args->flags & I915_EXEC_RING_MASK; + + if (user_ring_id > I915_USER_RINGS) { + DRM_DEBUG("execbuf with unknown ring: %u\n", user_ring_id); + return -EINVAL; + } + + if ((user_ring_id != I915_EXEC_BSD) && + ((args->flags & I915_EXEC_BSD_MASK) != 0)) { + DRM_DEBUG("execbuf with non bsd ring but with invalid " + "bsd dispatch flags: %d\n", (int)(args->flags)); + return -EINVAL; + } + + if (user_ring_id == I915_EXEC_BSD && HAS_BSD2(dev_priv)) { + unsigned int bsd_idx = args->flags & I915_EXEC_BSD_MASK; + + if (bsd_idx == I915_EXEC_BSD_DEFAULT) { + bsd_idx = gen8_dispatch_bsd_ring(dev_priv, file); + } else if (bsd_idx >= I915_EXEC_BSD_RING1 && + bsd_idx <= I915_EXEC_BSD_RING2) { + bsd_idx--; + } else { + DRM_DEBUG("execbuf with unknown bsd ring: %u\n", + bsd_idx); + return -EINVAL; + } + + *ring = &dev_priv->ring[_VCS(bsd_idx)]; + } else { + *ring = &dev_priv->ring[user_ring_map[user_ring_id]]; + } + + if (!intel_ring_initialized(*ring)) { + DRM_DEBUG("execbuf with invalid ring: %u\n", user_ring_id); + return -EINVAL; + } + + return 0; +} + static int i915_gem_do_execbuffer(struct drm_device *dev, void *data, struct drm_file *file, @@ -1381,6 +1428,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, struct drm_i915_gem_exec_object2 *exec) { struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_gem_request *req = NULL; struct eb_vmas *eb; struct drm_i915_gem_object *batch_obj; struct drm_i915_gem_exec_object2 shadow_exec_entry; @@ -1411,51 +1459,9 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, if (args->flags & I915_EXEC_IS_PINNED) dispatch_flags |= I915_DISPATCH_PINNED; - if ((args->flags & I915_EXEC_RING_MASK) > LAST_USER_RING) { - DRM_DEBUG("execbuf with unknown ring: %d\n", - (int)(args->flags & I915_EXEC_RING_MASK)); - return -EINVAL; - } - - if (((args->flags & I915_EXEC_RING_MASK) != I915_EXEC_BSD) && - ((args->flags & I915_EXEC_BSD_MASK) != 0)) { - DRM_DEBUG("execbuf with non bsd ring but with invalid " - "bsd dispatch flags: %d\n", (int)(args->flags)); - return -EINVAL; - } - - if ((args->flags & I915_EXEC_RING_MASK) == I915_EXEC_DEFAULT) - ring = &dev_priv->ring[RCS]; - else if ((args->flags & I915_EXEC_RING_MASK) == I915_EXEC_BSD) { - if (HAS_BSD2(dev)) { - int ring_id; - - switch (args->flags & I915_EXEC_BSD_MASK) { - case I915_EXEC_BSD_DEFAULT: - ring_id = gen8_dispatch_bsd_ring(dev, file); - ring = &dev_priv->ring[ring_id]; - break; - case I915_EXEC_BSD_RING1: - ring = &dev_priv->ring[VCS]; - break; - case I915_EXEC_BSD_RING2: - ring = &dev_priv->ring[VCS2]; - break; - default: - DRM_DEBUG("execbuf with unknown bsd ring: %d\n", - (int)(args->flags & I915_EXEC_BSD_MASK)); - return -EINVAL; - } - } else - ring = &dev_priv->ring[VCS]; - } else - ring = &dev_priv->ring[(args->flags & I915_EXEC_RING_MASK) - 1]; - - if (!intel_ring_initialized(ring)) { - DRM_DEBUG("execbuf with invalid ring: %d\n", - (int)(args->flags & I915_EXEC_RING_MASK)); - return -EINVAL; - } + ret = eb_select_ring(dev_priv, file, args, &ring); + if (ret) + return ret; if (args->buffer_count < 1) { DRM_DEBUG("execbuf with %d buffers\n", args->buffer_count); @@ -1602,11 +1608,13 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, params->batch_obj_vm_offset = i915_gem_obj_offset(batch_obj, vm); /* Allocate a request for this batch buffer nice and early. */ - ret = i915_gem_request_alloc(ring, ctx, ¶ms->request); - if (ret) + req = i915_gem_request_alloc(ring, ctx); + if (IS_ERR(req)) { + ret = PTR_ERR(req); goto err_batch_unpin; + } - ret = i915_gem_request_add_to_client(params->request, file); + ret = i915_gem_request_add_to_client(req, file); if (ret) goto err_batch_unpin; @@ -1622,6 +1630,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, params->dispatch_flags = dispatch_flags; params->batch_obj = batch_obj; params->ctx = ctx; + params->request = req; ret = dev_priv->gt.execbuf_submit(params, args, &eb->vmas); @@ -1645,8 +1654,8 @@ err: * must be freed again. If it was submitted then it is being tracked * on the active request list and no clean up is required here. */ - if (ret && params->request) - i915_gem_request_cancel(params->request); + if (ret && req) + i915_gem_request_cancel(req); mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 56f4f2e58d53..7377b6725c33 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -96,9 +96,11 @@ static int i915_get_ggtt_vma_pages(struct i915_vma *vma); -const struct i915_ggtt_view i915_ggtt_view_normal; +const struct i915_ggtt_view i915_ggtt_view_normal = { + .type = I915_GGTT_VIEW_NORMAL, +}; const struct i915_ggtt_view i915_ggtt_view_rotated = { - .type = I915_GGTT_VIEW_ROTATED + .type = I915_GGTT_VIEW_ROTATED, }; static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt) @@ -3329,7 +3331,7 @@ i915_gem_obj_lookup_or_create_ggtt_vma(struct drm_i915_gem_object *obj, } static struct scatterlist * -rotate_pages(dma_addr_t *in, unsigned int offset, +rotate_pages(const dma_addr_t *in, unsigned int offset, unsigned int width, unsigned int height, struct sg_table *st, struct scatterlist *sg) { diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index b448ad832dcf..e5737963ab79 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -44,7 +44,6 @@ typedef uint64_t gen8_ppgtt_pml4e_t; #define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT) - /* gen6-hsw has bit 11-4 for physical addr bit 39-32 */ #define GEN6_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0xff0)) #define GEN6_PTE_ADDR_ENCODE(addr) GEN6_GTT_ADDR_ENCODE(addr) diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index f7df54a8ee2b..16da9c1422cc 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -47,6 +47,46 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task) #endif } +static int num_vma_bound(struct drm_i915_gem_object *obj) +{ + struct i915_vma *vma; + int count = 0; + + list_for_each_entry(vma, &obj->vma_list, vma_link) { + if (drm_mm_node_allocated(&vma->node)) + count++; + if (vma->pin_count) + count++; + } + + return count; +} + +static bool swap_available(void) +{ + return get_nr_swap_pages() > 0; +} + +static bool can_release_pages(struct drm_i915_gem_object *obj) +{ + /* Only report true if by unbinding the object and putting its pages + * we can actually make forward progress towards freeing physical + * pages. + * + * If the pages are pinned for any other reason than being bound + * to the GPU, simply unbinding from the GPU is not going to succeed + * in releasing our pin count on the pages themselves. + */ + if (obj->pages_pin_count != num_vma_bound(obj)) + return false; + + /* We can only return physical pages to the system if we can either + * discard the contents (because the user has marked them as being + * purgeable) or if we can move their contents out to swap. + */ + return swap_available() || obj->madv == I915_MADV_DONTNEED; +} + /** * i915_gem_shrink - Shrink buffer object caches * @dev_priv: i915 device @@ -129,6 +169,9 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, if ((flags & I915_SHRINK_ACTIVE) == 0 && obj->active) continue; + if (!can_release_pages(obj)) + continue; + drm_gem_object_reference(&obj->base); /* For the unbound phase, this should be a no-op! */ @@ -188,21 +231,6 @@ static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock) return true; } -static int num_vma_bound(struct drm_i915_gem_object *obj) -{ - struct i915_vma *vma; - int count = 0; - - list_for_each_entry(vma, &obj->vma_list, vma_link) { - if (drm_mm_node_allocated(&vma->node)) - count++; - if (vma->pin_count) - count++; - } - - return count; -} - static unsigned long i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) { @@ -222,7 +250,7 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) count += obj->base.size >> PAGE_SHIFT; list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { - if (!obj->active && obj->pages_pin_count == num_vma_bound(obj)) + if (!obj->active && can_release_pages(obj)) count += obj->base.size >> PAGE_SHIFT; } diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index 3476877fc0d6..c384dc9c8a63 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -569,6 +569,9 @@ _i915_gem_object_create_stolen(struct drm_device *dev, if (obj->pages == NULL) goto cleanup; + obj->get_page.sg = obj->pages->sgl; + obj->get_page.last = 0; + i915_gem_object_pin_pages(obj); obj->stolen = stolen; diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 06ca4082735b..7eeb24427785 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1050,7 +1050,7 @@ static void i915_gem_record_rings(struct drm_device *dev, if (request) rbuf = request->ctx->engine[ring->id].ringbuf; else - rbuf = ring->default_context->engine[ring->id].ringbuf; + rbuf = dev_priv->kernel_context->engine[ring->id].ringbuf; } else rbuf = ring->buffer; diff --git a/drivers/gpu/drm/i915/i915_guc_reg.h b/drivers/gpu/drm/i915/i915_guc_reg.h index 685c7991e24f..e4ba5822289b 100644 --- a/drivers/gpu/drm/i915/i915_guc_reg.h +++ b/drivers/gpu/drm/i915/i915_guc_reg.h @@ -40,6 +40,7 @@ #define GS_MIA_CORE_STATE (1 << GS_MIA_SHIFT) #define SOFT_SCRATCH(n) _MMIO(0xc180 + (n) * 4) +#define SOFT_SCRATCH_COUNT 16 #define UOS_RSA_SCRATCH(i) _MMIO(0xc200 + (i) * 4) #define UOS_RSA_SCRATCH_MAX_COUNT 64 diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c index 05aa7e61cbe0..51ae5c1f806d 100644 --- a/drivers/gpu/drm/i915/i915_guc_submission.c +++ b/drivers/gpu/drm/i915/i915_guc_submission.c @@ -158,10 +158,8 @@ static int host2guc_sample_forcewake(struct intel_guc *guc, data[0] = HOST2GUC_ACTION_SAMPLE_FORCEWAKE; /* WaRsDisableCoarsePowerGating:skl,bxt */ - if (!intel_enable_rc6(dev_priv->dev) || - IS_BXT_REVID(dev, 0, BXT_REVID_A1) || - (IS_SKL_GT3(dev) && IS_SKL_REVID(dev, 0, SKL_REVID_E0)) || - (IS_SKL_GT4(dev) && IS_SKL_REVID(dev, 0, SKL_REVID_E0))) + if (!intel_enable_rc6(dev) || + NEEDS_WaRsDisableCoarsePowerGating(dev)) data[1] = 0; else /* bit 0 and 1 are for Render and Media domain separately */ @@ -246,6 +244,9 @@ static int guc_ring_doorbell(struct i915_guc_client *gc) db_exc.cookie = 1; } + /* Finally, update the cached copy of the GuC's WQ head */ + gc->wq_head = desc->head; + kunmap_atomic(base); return ret; } @@ -471,28 +472,30 @@ static void guc_fini_ctx_desc(struct intel_guc *guc, sizeof(desc) * client->ctx_index); } -/* Get valid workqueue item and return it back to offset */ -static int guc_get_workqueue_space(struct i915_guc_client *gc, u32 *offset) +int i915_guc_wq_check_space(struct i915_guc_client *gc) { struct guc_process_desc *desc; void *base; u32 size = sizeof(struct guc_wq_item); int ret = -ETIMEDOUT, timeout_counter = 200; + if (!gc) + return 0; + + /* Quickly return if wq space is available since last time we cache the + * head position. */ + if (CIRC_SPACE(gc->wq_tail, gc->wq_head, gc->wq_size) >= size) + return 0; + base = kmap_atomic(i915_gem_object_get_page(gc->client_obj, 0)); desc = base + gc->proc_desc_offset; while (timeout_counter-- > 0) { - if (CIRC_SPACE(gc->wq_tail, desc->head, gc->wq_size) >= size) { - *offset = gc->wq_tail; - - /* advance the tail for next workqueue item */ - gc->wq_tail += size; - gc->wq_tail &= gc->wq_size - 1; + gc->wq_head = desc->head; - /* this will break the loop */ - timeout_counter = 0; + if (CIRC_SPACE(gc->wq_tail, gc->wq_head, gc->wq_size) >= size) { ret = 0; + break; } if (timeout_counter) @@ -510,12 +513,16 @@ static int guc_add_workqueue_item(struct i915_guc_client *gc, enum intel_ring_id ring_id = rq->ring->id; struct guc_wq_item *wqi; void *base; - u32 tail, wq_len, wq_off = 0; - int ret; + u32 tail, wq_len, wq_off, space; + + space = CIRC_SPACE(gc->wq_tail, gc->wq_head, gc->wq_size); + if (WARN_ON(space < sizeof(struct guc_wq_item))) + return -ENOSPC; /* shouldn't happen */ - ret = guc_get_workqueue_space(gc, &wq_off); - if (ret) - return ret; + /* postincrement WQ tail for next time */ + wq_off = gc->wq_tail; + gc->wq_tail += sizeof(struct guc_wq_item); + gc->wq_tail &= gc->wq_size - 1; /* For now workqueue item is 4 DWs; workqueue buffer is 2 pages. So we * should not have the case where structure wqi is across page, neither @@ -832,6 +839,96 @@ static void guc_create_log(struct intel_guc *guc) guc->log_flags = (offset << GUC_LOG_BUF_ADDR_SHIFT) | flags; } +static void init_guc_policies(struct guc_policies *policies) +{ + struct guc_policy *policy; + u32 p, i; + + policies->dpc_promote_time = 500000; + policies->max_num_work_items = POLICY_MAX_NUM_WI; + + for (p = 0; p < GUC_CTX_PRIORITY_NUM; p++) { + for (i = 0; i < I915_NUM_RINGS; i++) { + policy = &policies->policy[p][i]; + + policy->execution_quantum = 1000000; + policy->preemption_time = 500000; + policy->fault_time = 250000; + policy->policy_flags = 0; + } + } + + policies->is_valid = 1; +} + +static void guc_create_ads(struct intel_guc *guc) +{ + struct drm_i915_private *dev_priv = guc_to_i915(guc); + struct drm_i915_gem_object *obj; + struct guc_ads *ads; + struct guc_policies *policies; + struct guc_mmio_reg_state *reg_state; + struct intel_engine_cs *ring; + struct page *page; + u32 size, i; + + /* The ads obj includes the struct itself and buffers passed to GuC */ + size = sizeof(struct guc_ads) + sizeof(struct guc_policies) + + sizeof(struct guc_mmio_reg_state) + + GUC_S3_SAVE_SPACE_PAGES * PAGE_SIZE; + + obj = guc->ads_obj; + if (!obj) { + obj = gem_allocate_guc_obj(dev_priv->dev, PAGE_ALIGN(size)); + if (!obj) + return; + + guc->ads_obj = obj; + } + + page = i915_gem_object_get_page(obj, 0); + ads = kmap(page); + + /* + * The GuC requires a "Golden Context" when it reinitialises + * engines after a reset. Here we use the Render ring default + * context, which must already exist and be pinned in the GGTT, + * so its address won't change after we've told the GuC where + * to find it. + */ + ring = &dev_priv->ring[RCS]; + ads->golden_context_lrca = ring->status_page.gfx_addr; + + for_each_ring(ring, dev_priv, i) + ads->eng_state_size[i] = intel_lr_context_size(ring); + + /* GuC scheduling policies */ + policies = (void *)ads + sizeof(struct guc_ads); + init_guc_policies(policies); + + ads->scheduler_policies = i915_gem_obj_ggtt_offset(obj) + + sizeof(struct guc_ads); + + /* MMIO reg state */ + reg_state = (void *)policies + sizeof(struct guc_policies); + + for (i = 0; i < I915_NUM_RINGS; i++) { + reg_state->mmio_white_list[i].mmio_start = + dev_priv->ring[i].mmio_base + GUC_MMIO_WHITE_LIST_START; + + /* Nothing to be saved or restored for now. */ + reg_state->mmio_white_list[i].count = 0; + } + + ads->reg_state_addr = ads->scheduler_policies + + sizeof(struct guc_policies); + + ads->reg_state_buffer = ads->reg_state_addr + + sizeof(struct guc_mmio_reg_state); + + kunmap(page); +} + /* * Set up the memory resources to be shared with the GuC. At this point, * we require just one object that can be mapped through the GGTT. @@ -858,6 +955,8 @@ int i915_guc_submission_init(struct drm_device *dev) guc_create_log(guc); + guc_create_ads(guc); + return 0; } @@ -865,7 +964,7 @@ int i915_guc_submission_enable(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; struct intel_guc *guc = &dev_priv->guc; - struct intel_context *ctx = dev_priv->ring[RCS].default_context; + struct intel_context *ctx = dev_priv->kernel_context; struct i915_guc_client *client; /* client for execbuf submission */ @@ -896,6 +995,9 @@ void i915_guc_submission_fini(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_guc *guc = &dev_priv->guc; + gem_release_guc_obj(dev_priv->guc.ads_obj); + guc->ads_obj = NULL; + gem_release_guc_obj(dev_priv->guc.log_obj); guc->log_obj = NULL; @@ -919,7 +1021,7 @@ int intel_guc_suspend(struct drm_device *dev) if (!i915.enable_guc_submission) return 0; - ctx = dev_priv->ring[RCS].default_context; + ctx = dev_priv->kernel_context; data[0] = HOST2GUC_ACTION_ENTER_S_STATE; /* any value greater than GUC_POWER_D0 */ @@ -945,7 +1047,7 @@ int intel_guc_resume(struct drm_device *dev) if (!i915.enable_guc_submission) return 0; - ctx = dev_priv->ring[RCS].default_context; + ctx = dev_priv->kernel_context; data[0] = HOST2GUC_ACTION_EXIT_S_STATE; data[1] = GUC_POWER_D0; diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index fa8afa7860ae..25a89373df63 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -2188,10 +2188,6 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg) /* IRQs are synced during runtime_suspend, we don't require a wakeref */ disable_rpm_wakeref_asserts(dev_priv); - /* We get interrupts on unclaimed registers, so check for this before we - * do any I915_{READ,WRITE}. */ - intel_uncore_check_errors(dev); - /* disable master interrupt before clearing iir */ de_ier = I915_READ(DEIER); I915_WRITE(DEIER, de_ier & ~DE_MASTER_IRQ_CONTROL); @@ -2268,43 +2264,20 @@ static void bxt_hpd_irq_handler(struct drm_device *dev, u32 hotplug_trigger, intel_hpd_irq_handler(dev, pin_mask, long_mask); } -static irqreturn_t gen8_irq_handler(int irq, void *arg) +static irqreturn_t +gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl) { - struct drm_device *dev = arg; - struct drm_i915_private *dev_priv = dev->dev_private; - u32 master_ctl; + struct drm_device *dev = dev_priv->dev; irqreturn_t ret = IRQ_NONE; - uint32_t tmp = 0; + u32 iir; enum pipe pipe; - u32 aux_mask = GEN8_AUX_CHANNEL_A; - - if (!intel_irqs_enabled(dev_priv)) - return IRQ_NONE; - - /* IRQs are synced during runtime_suspend, we don't require a wakeref */ - disable_rpm_wakeref_asserts(dev_priv); - - if (INTEL_INFO(dev_priv)->gen >= 9) - aux_mask |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C | - GEN9_AUX_CHANNEL_D; - - master_ctl = I915_READ_FW(GEN8_MASTER_IRQ); - master_ctl &= ~GEN8_MASTER_IRQ_CONTROL; - if (!master_ctl) - goto out; - - I915_WRITE_FW(GEN8_MASTER_IRQ, 0); - - /* Find, clear, then process each source of interrupt */ - - ret = gen8_gt_irq_handler(dev_priv, master_ctl); if (master_ctl & GEN8_DE_MISC_IRQ) { - tmp = I915_READ(GEN8_DE_MISC_IIR); - if (tmp) { - I915_WRITE(GEN8_DE_MISC_IIR, tmp); + iir = I915_READ(GEN8_DE_MISC_IIR); + if (iir) { + I915_WRITE(GEN8_DE_MISC_IIR, iir); ret = IRQ_HANDLED; - if (tmp & GEN8_DE_MISC_GSE) + if (iir & GEN8_DE_MISC_GSE) intel_opregion_asle_intr(dev); else DRM_ERROR("Unexpected DE Misc interrupt\n"); @@ -2314,33 +2287,40 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) } if (master_ctl & GEN8_DE_PORT_IRQ) { - tmp = I915_READ(GEN8_DE_PORT_IIR); - if (tmp) { + iir = I915_READ(GEN8_DE_PORT_IIR); + if (iir) { + u32 tmp_mask; bool found = false; - u32 hotplug_trigger = 0; - - if (IS_BROXTON(dev_priv)) - hotplug_trigger = tmp & BXT_DE_PORT_HOTPLUG_MASK; - else if (IS_BROADWELL(dev_priv)) - hotplug_trigger = tmp & GEN8_PORT_DP_A_HOTPLUG; - I915_WRITE(GEN8_DE_PORT_IIR, tmp); + I915_WRITE(GEN8_DE_PORT_IIR, iir); ret = IRQ_HANDLED; - if (tmp & aux_mask) { + tmp_mask = GEN8_AUX_CHANNEL_A; + if (INTEL_INFO(dev_priv)->gen >= 9) + tmp_mask |= GEN9_AUX_CHANNEL_B | + GEN9_AUX_CHANNEL_C | + GEN9_AUX_CHANNEL_D; + + if (iir & tmp_mask) { dp_aux_irq_handler(dev); found = true; } - if (hotplug_trigger) { - if (IS_BROXTON(dev)) - bxt_hpd_irq_handler(dev, hotplug_trigger, hpd_bxt); - else - ilk_hpd_irq_handler(dev, hotplug_trigger, hpd_bdw); - found = true; + if (IS_BROXTON(dev_priv)) { + tmp_mask = iir & BXT_DE_PORT_HOTPLUG_MASK; + if (tmp_mask) { + bxt_hpd_irq_handler(dev, tmp_mask, hpd_bxt); + found = true; + } + } else if (IS_BROADWELL(dev_priv)) { + tmp_mask = iir & GEN8_PORT_DP_A_HOTPLUG; + if (tmp_mask) { + ilk_hpd_irq_handler(dev, tmp_mask, hpd_bdw); + found = true; + } } - if (IS_BROXTON(dev) && (tmp & BXT_DE_PORT_GMBUS)) { + if (IS_BROXTON(dev) && (iir & BXT_DE_PORT_GMBUS)) { gmbus_irq_handler(dev); found = true; } @@ -2353,49 +2333,51 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) } for_each_pipe(dev_priv, pipe) { - uint32_t pipe_iir, flip_done = 0, fault_errors = 0; + u32 flip_done, fault_errors; if (!(master_ctl & GEN8_DE_PIPE_IRQ(pipe))) continue; - pipe_iir = I915_READ(GEN8_DE_PIPE_IIR(pipe)); - if (pipe_iir) { - ret = IRQ_HANDLED; - I915_WRITE(GEN8_DE_PIPE_IIR(pipe), pipe_iir); + iir = I915_READ(GEN8_DE_PIPE_IIR(pipe)); + if (!iir) { + DRM_ERROR("The master control interrupt lied (DE PIPE)!\n"); + continue; + } - if (pipe_iir & GEN8_PIPE_VBLANK && - intel_pipe_handle_vblank(dev, pipe)) - intel_check_page_flip(dev, pipe); + ret = IRQ_HANDLED; + I915_WRITE(GEN8_DE_PIPE_IIR(pipe), iir); - if (INTEL_INFO(dev_priv)->gen >= 9) - flip_done = pipe_iir & GEN9_PIPE_PLANE1_FLIP_DONE; - else - flip_done = pipe_iir & GEN8_PIPE_PRIMARY_FLIP_DONE; + if (iir & GEN8_PIPE_VBLANK && + intel_pipe_handle_vblank(dev, pipe)) + intel_check_page_flip(dev, pipe); - if (flip_done) { - intel_prepare_page_flip(dev, pipe); - intel_finish_page_flip_plane(dev, pipe); - } + flip_done = iir; + if (INTEL_INFO(dev_priv)->gen >= 9) + flip_done &= GEN9_PIPE_PLANE1_FLIP_DONE; + else + flip_done &= GEN8_PIPE_PRIMARY_FLIP_DONE; - if (pipe_iir & GEN8_PIPE_CDCLK_CRC_DONE) - hsw_pipe_crc_irq_handler(dev, pipe); + if (flip_done) { + intel_prepare_page_flip(dev, pipe); + intel_finish_page_flip_plane(dev, pipe); + } - if (pipe_iir & GEN8_PIPE_FIFO_UNDERRUN) - intel_cpu_fifo_underrun_irq_handler(dev_priv, - pipe); + if (iir & GEN8_PIPE_CDCLK_CRC_DONE) + hsw_pipe_crc_irq_handler(dev, pipe); + if (iir & GEN8_PIPE_FIFO_UNDERRUN) + intel_cpu_fifo_underrun_irq_handler(dev_priv, pipe); - if (INTEL_INFO(dev_priv)->gen >= 9) - fault_errors = pipe_iir & GEN9_DE_PIPE_IRQ_FAULT_ERRORS; - else - fault_errors = pipe_iir & GEN8_DE_PIPE_IRQ_FAULT_ERRORS; + fault_errors = iir; + if (INTEL_INFO(dev_priv)->gen >= 9) + fault_errors &= GEN9_DE_PIPE_IRQ_FAULT_ERRORS; + else + fault_errors &= GEN8_DE_PIPE_IRQ_FAULT_ERRORS; - if (fault_errors) - DRM_ERROR("Fault errors on pipe %c\n: 0x%08x", - pipe_name(pipe), - pipe_iir & GEN8_DE_PIPE_IRQ_FAULT_ERRORS); - } else - DRM_ERROR("The master control interrupt lied (DE PIPE)!\n"); + if (fault_errors) + DRM_ERROR("Fault errors on pipe %c\n: 0x%08x", + pipe_name(pipe), + fault_errors); } if (HAS_PCH_SPLIT(dev) && !HAS_PCH_NOP(dev) && @@ -2405,15 +2387,15 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) * scheme also closed the SDE interrupt handling race we've seen * on older pch-split platforms. But this needs testing. */ - u32 pch_iir = I915_READ(SDEIIR); - if (pch_iir) { - I915_WRITE(SDEIIR, pch_iir); + iir = I915_READ(SDEIIR); + if (iir) { + I915_WRITE(SDEIIR, iir); ret = IRQ_HANDLED; if (HAS_PCH_SPT(dev_priv)) - spt_irq_handler(dev, pch_iir); + spt_irq_handler(dev, iir); else - cpt_irq_handler(dev, pch_iir); + cpt_irq_handler(dev, iir); } else { /* * Like on previous PCH there seems to be something @@ -2423,10 +2405,36 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) } } + return ret; +} + +static irqreturn_t gen8_irq_handler(int irq, void *arg) +{ + struct drm_device *dev = arg; + struct drm_i915_private *dev_priv = dev->dev_private; + u32 master_ctl; + irqreturn_t ret; + + if (!intel_irqs_enabled(dev_priv)) + return IRQ_NONE; + + master_ctl = I915_READ_FW(GEN8_MASTER_IRQ); + master_ctl &= ~GEN8_MASTER_IRQ_CONTROL; + if (!master_ctl) + return IRQ_NONE; + + I915_WRITE_FW(GEN8_MASTER_IRQ, 0); + + /* IRQs are synced during runtime_suspend, we don't require a wakeref */ + disable_rpm_wakeref_asserts(dev_priv); + + /* Find, clear, then process each source of interrupt */ + ret = gen8_gt_irq_handler(dev_priv, master_ctl); + ret |= gen8_de_irq_handler(dev_priv, master_ctl); + I915_WRITE_FW(GEN8_MASTER_IRQ, GEN8_MASTER_IRQ_CONTROL); POSTING_READ_FW(GEN8_MASTER_IRQ); -out: enable_rpm_wakeref_asserts(dev_priv); return ret; @@ -2949,14 +2957,44 @@ static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv) ring->hangcheck.deadlock = 0; } -static enum intel_ring_hangcheck_action -ring_stuck(struct intel_engine_cs *ring, u64 acthd) +static bool subunits_stuck(struct intel_engine_cs *ring) { - struct drm_device *dev = ring->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - u32 tmp; + u32 instdone[I915_NUM_INSTDONE_REG]; + bool stuck; + int i; + + if (ring->id != RCS) + return true; + + i915_get_extra_instdone(ring->dev, instdone); + + /* There might be unstable subunit states even when + * actual head is not moving. Filter out the unstable ones by + * accumulating the undone -> done transitions and only + * consider those as progress. + */ + stuck = true; + for (i = 0; i < I915_NUM_INSTDONE_REG; i++) { + const u32 tmp = instdone[i] | ring->hangcheck.instdone[i]; + + if (tmp != ring->hangcheck.instdone[i]) + stuck = false; + + ring->hangcheck.instdone[i] |= tmp; + } + return stuck; +} + +static enum intel_ring_hangcheck_action +head_stuck(struct intel_engine_cs *ring, u64 acthd) +{ if (acthd != ring->hangcheck.acthd) { + + /* Clear subunit states on head movement */ + memset(ring->hangcheck.instdone, 0, + sizeof(ring->hangcheck.instdone)); + if (acthd > ring->hangcheck.max_acthd) { ring->hangcheck.max_acthd = acthd; return HANGCHECK_ACTIVE; @@ -2965,6 +3003,24 @@ ring_stuck(struct intel_engine_cs *ring, u64 acthd) return HANGCHECK_ACTIVE_LOOP; } + if (!subunits_stuck(ring)) + return HANGCHECK_ACTIVE; + + return HANGCHECK_HUNG; +} + +static enum intel_ring_hangcheck_action +ring_stuck(struct intel_engine_cs *ring, u64 acthd) +{ + struct drm_device *dev = ring->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + enum intel_ring_hangcheck_action ha; + u32 tmp; + + ha = head_stuck(ring, acthd); + if (ha != HANGCHECK_HUNG) + return ha; + if (IS_GEN2(dev)) return HANGCHECK_HUNG; @@ -3032,6 +3088,12 @@ static void i915_hangcheck_elapsed(struct work_struct *work) */ DISABLE_RPM_WAKEREF_ASSERTS(dev_priv); + /* As enabling the GPU requires fairly extensive mmio access, + * periodically arm the mmio checker to see if we are triggering + * any invalid access. + */ + intel_uncore_arm_unclaimed_mmio_detection(dev_priv); + for_each_ring(ring, dev_priv, i) { u64 acthd; u32 seqno; @@ -3106,7 +3168,11 @@ static void i915_hangcheck_elapsed(struct work_struct *work) if (ring->hangcheck.score > 0) ring->hangcheck.score--; + /* Clear head and subunit states on seqno movement */ ring->hangcheck.acthd = ring->hangcheck.max_acthd = 0; + + memset(ring->hangcheck.instdone, 0, + sizeof(ring->hangcheck.instdone)); } ring->hangcheck.seqno = seqno; diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c index 835d6099c769..8d90c256520a 100644 --- a/drivers/gpu/drm/i915/i915_params.c +++ b/drivers/gpu/drm/i915/i915_params.c @@ -22,6 +22,7 @@ * IN THE SOFTWARE. */ +#include "i915_params.h" #include "i915_drv.h" struct i915_params i915 __read_mostly = { diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h new file mode 100644 index 000000000000..529929073120 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_params.h @@ -0,0 +1,68 @@ +/* + * Copyright © 2015 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + */ + +#ifndef _I915_PARAMS_H_ +#define _I915_PARAMS_H_ + +#include <linux/cache.h> /* for __read_mostly */ + +struct i915_params { + int modeset; + int panel_ignore_lid; + int semaphores; + int lvds_channel_mode; + int panel_use_ssc; + int vbt_sdvo_panel_type; + int enable_rc6; + int enable_dc; + int enable_fbc; + int enable_ppgtt; + int enable_execlists; + int enable_psr; + unsigned int preliminary_hw_support; + int disable_power_well; + int enable_ips; + int invert_brightness; + int enable_cmd_parser; + int guc_log_level; + int use_mmio_flip; + int mmio_debug; + int edp_vswing; + /* leave bools at the end to not create holes */ + bool enable_hangcheck; + bool fastboot; + bool prefault_disable; + bool load_detect_test; + bool reset; + bool disable_display; + bool disable_vtd_wa; + bool enable_guc_submission; + bool verbose_state_checks; + bool nuclear_pageflip; +}; + +extern struct i915_params i915 __read_mostly; + +#endif + diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 007ae83a4086..0a988895165f 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1711,6 +1711,11 @@ enum skl_disp_power_wells { #define FPGA_DBG _MMIO(0x42300) #define FPGA_DBG_RM_NOCLAIM (1<<31) +#define CLAIM_ER _MMIO(VLV_DISPLAY_BASE + 0x2028) +#define CLAIM_ER_CLR (1 << 31) +#define CLAIM_ER_OVERFLOW (1 << 16) +#define CLAIM_ER_CTR_MASK 0xffff + #define DERRMR _MMIO(0x44050) /* Note that HBLANK events are reserved on bdw+ */ #define DERRMR_PIPEA_SCANLINE (1<<0) diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index 37e3f0ddf8e0..c6188dddb341 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -164,7 +164,7 @@ i915_l3_read(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t offset, size_t count) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct drm_minor *dminor = dev_to_drm_minor(dev); struct drm_device *drm_dev = dminor->dev; struct drm_i915_private *dev_priv = drm_dev->dev_private; @@ -200,7 +200,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t offset, size_t count) { - struct device *dev = container_of(kobj, struct device, kobj); + struct device *dev = kobj_to_dev(kobj); struct drm_minor *dminor = dev_to_drm_minor(dev); struct drm_device *drm_dev = dminor->dev; struct drm_i915_private *dev_priv = drm_dev->dev_private; @@ -521,7 +521,7 @@ static ssize_t error_state_read(struct file *filp, struct kobject *kobj, loff_t off, size_t count) { - struct device *kdev = container_of(kobj, struct device, kobj); + struct device *kdev = kobj_to_dev(kobj); struct drm_minor *minor = dev_to_drm_minor(kdev); struct drm_device *dev = minor->dev; struct i915_error_state_file_priv error_priv; @@ -556,7 +556,7 @@ static ssize_t error_state_write(struct file *file, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { - struct device *kdev = container_of(kobj, struct device, kobj); + struct device *kdev = kobj_to_dev(kobj); struct drm_minor *minor = dev_to_drm_minor(kdev); struct drm_device *dev = minor->dev; int ret; diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c index d0b1c9afa35e..4625f8a9ba12 100644 --- a/drivers/gpu/drm/i915/intel_atomic.c +++ b/drivers/gpu/drm/i915/intel_atomic.c @@ -308,5 +308,5 @@ void intel_atomic_state_clear(struct drm_atomic_state *s) { struct intel_atomic_state *state = to_intel_atomic_state(s); drm_atomic_state_default_clear(&state->base); - state->dpll_set = false; + state->dpll_set = state->modeset = false; } diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c index c6bb0fc1edfb..e0b851a0004a 100644 --- a/drivers/gpu/drm/i915/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/intel_atomic_plane.c @@ -152,9 +152,9 @@ static int intel_plane_atomic_check(struct drm_plane *plane, intel_state->clip.x1 = 0; intel_state->clip.y1 = 0; intel_state->clip.x2 = - crtc_state->base.active ? crtc_state->pipe_src_w : 0; + crtc_state->base.enable ? crtc_state->pipe_src_w : 0; intel_state->clip.y2 = - crtc_state->base.active ? crtc_state->pipe_src_h : 0; + crtc_state->base.enable ? crtc_state->pipe_src_h : 0; if (state->fb && intel_rotation_90_or_270(state->rotation)) { if (!(state->fb->modifier[0] == I915_FORMAT_MOD_Y_TILED || @@ -194,8 +194,16 @@ static void intel_plane_atomic_update(struct drm_plane *plane, struct intel_plane *intel_plane = to_intel_plane(plane); struct intel_plane_state *intel_state = to_intel_plane_state(plane->state); + struct drm_crtc *crtc = plane->state->crtc ?: old_state->crtc; + struct drm_crtc_state *crtc_state = + drm_atomic_get_existing_crtc_state(old_state->state, crtc); - intel_plane->commit_plane(plane, intel_state); + if (intel_state->visible) + intel_plane->update_plane(plane, + to_intel_crtc_state(crtc_state), + intel_state); + else + intel_plane->disable_plane(plane, crtc); } const struct drm_plane_helper_funcs intel_plane_helper_funcs = { diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index eba3e0f87181..bf62a19c8f69 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -31,11 +31,49 @@ #include "i915_drv.h" #include "intel_bios.h" +/** + * DOC: Video BIOS Table (VBT) + * + * The Video BIOS Table, or VBT, provides platform and board specific + * configuration information to the driver that is not discoverable or available + * through other means. The configuration is mostly related to display + * hardware. The VBT is available via the ACPI OpRegion or, on older systems, in + * the PCI ROM. + * + * The VBT consists of a VBT Header (defined as &struct vbt_header), a BDB + * Header (&struct bdb_header), and a number of BIOS Data Blocks (BDB) that + * contain the actual configuration information. The VBT Header, and thus the + * VBT, begins with "$VBT" signature. The VBT Header contains the offset of the + * BDB Header. The data blocks are concatenated after the BDB Header. The data + * blocks have a 1-byte Block ID, 2-byte Block Size, and Block Size bytes of + * data. (Block 53, the MIPI Sequence Block is an exception.) + * + * The driver parses the VBT during load. The relevant information is stored in + * driver private data for ease of use, and the actual VBT is not read after + * that. + */ + #define SLAVE_ADDR1 0x70 #define SLAVE_ADDR2 0x72 static int panel_type; +/* Get BDB block size given a pointer to Block ID. */ +static u32 _get_blocksize(const u8 *block_base) +{ + /* The MIPI Sequence Block v3+ has a separate size field. */ + if (*block_base == BDB_MIPI_SEQUENCE && *(block_base + 3) >= 3) + return *((const u32 *)(block_base + 4)); + else + return *((const u16 *)(block_base + 1)); +} + +/* Get BDB block size give a pointer to data after Block ID and Block Size. */ +static u32 get_blocksize(const void *block_data) +{ + return _get_blocksize(block_data - 3); +} + static const void * find_section(const void *_bdb, int section_id) { @@ -52,14 +90,8 @@ find_section(const void *_bdb, int section_id) /* walk the sections looking for section_id */ while (index + 3 < total) { current_id = *(base + index); - index++; - - current_size = *((const u16 *)(base + index)); - index += 2; - - /* The MIPI Sequence Block v3+ has a separate size field. */ - if (current_id == BDB_MIPI_SEQUENCE && *(base + index) >= 3) - current_size = *((const u32 *)(base + index + 1)); + current_size = _get_blocksize(base + index); + index += 3; if (index + current_size > total) return NULL; @@ -73,16 +105,6 @@ find_section(const void *_bdb, int section_id) return NULL; } -static u16 -get_blocksize(const void *p) -{ - u16 *block_ptr, block_size; - - block_ptr = (u16 *)((char *)p - 2); - block_size = *block_ptr; - return block_size; -} - static void fill_detail_timing_data(struct drm_display_mode *panel_fixed_mode, const struct lvds_dvo_timing *dvo_timing) @@ -675,84 +697,13 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb) dev_priv->vbt.psr.tp2_tp3_wakeup_time = psr_table->tp2_tp3_wakeup_time; } -static u8 *goto_next_sequence(u8 *data, int *size) -{ - u16 len; - int tmp = *size; - - if (--tmp < 0) - return NULL; - - /* goto first element */ - data++; - while (1) { - switch (*data) { - case MIPI_SEQ_ELEM_SEND_PKT: - /* - * skip by this element payload size - * skip elem id, command flag and data type - */ - tmp -= 5; - if (tmp < 0) - return NULL; - - data += 3; - len = *((u16 *)data); - - tmp -= len; - if (tmp < 0) - return NULL; - - /* skip by len */ - data = data + 2 + len; - break; - case MIPI_SEQ_ELEM_DELAY: - /* skip by elem id, and delay is 4 bytes */ - tmp -= 5; - if (tmp < 0) - return NULL; - - data += 5; - break; - case MIPI_SEQ_ELEM_GPIO: - tmp -= 3; - if (tmp < 0) - return NULL; - - data += 3; - break; - default: - DRM_ERROR("Unknown element\n"); - return NULL; - } - - /* end of sequence ? */ - if (*data == 0) - break; - } - - /* goto next sequence or end of block byte */ - if (--tmp < 0) - return NULL; - - data++; - - /* update amount of data left for the sequence block to be parsed */ - *size = tmp; - return data; -} - static void -parse_mipi(struct drm_i915_private *dev_priv, const struct bdb_header *bdb) +parse_mipi_config(struct drm_i915_private *dev_priv, + const struct bdb_header *bdb) { const struct bdb_mipi_config *start; - const struct bdb_mipi_sequence *sequence; const struct mipi_config *config; const struct mipi_pps_data *pps; - u8 *data; - const u8 *seq_data; - int i, panel_id, seq_size; - u16 block_size; /* parse MIPI blocks only if LFP type is MIPI */ if (!dev_priv->vbt.has_mipi) @@ -798,104 +749,233 @@ parse_mipi(struct drm_i915_private *dev_priv, const struct bdb_header *bdb) /* We have mandatory mipi config blocks. Initialize as generic panel */ dev_priv->vbt.dsi.panel_id = MIPI_DSI_GENERIC_PANEL_ID; +} - /* Check if we have sequence block as well */ - sequence = find_section(bdb, BDB_MIPI_SEQUENCE); - if (!sequence) { - DRM_DEBUG_KMS("No MIPI Sequence found, parsing complete\n"); - return; +/* Find the sequence block and size for the given panel. */ +static const u8 * +find_panel_sequence_block(const struct bdb_mipi_sequence *sequence, + u16 panel_id, u32 *seq_size) +{ + u32 total = get_blocksize(sequence); + const u8 *data = &sequence->data[0]; + u8 current_id; + u32 current_size; + int header_size = sequence->version >= 3 ? 5 : 3; + int index = 0; + int i; + + /* skip new block size */ + if (sequence->version >= 3) + data += 4; + + for (i = 0; i < MAX_MIPI_CONFIGURATIONS && index < total; i++) { + if (index + header_size > total) { + DRM_ERROR("Invalid sequence block (header)\n"); + return NULL; + } + + current_id = *(data + index); + if (sequence->version >= 3) + current_size = *((const u32 *)(data + index + 1)); + else + current_size = *((const u16 *)(data + index + 1)); + + index += header_size; + + if (index + current_size > total) { + DRM_ERROR("Invalid sequence block\n"); + return NULL; + } + + if (current_id == panel_id) { + *seq_size = current_size; + return data + index; + } + + index += current_size; } - /* Fail gracefully for forward incompatible sequence block. */ - if (sequence->version >= 3) { - DRM_ERROR("Unable to parse MIPI Sequence Block v3+\n"); - return; + DRM_ERROR("Sequence block detected but no valid configuration\n"); + + return NULL; +} + +static int goto_next_sequence(const u8 *data, int index, int total) +{ + u16 len; + + /* Skip Sequence Byte. */ + for (index = index + 1; index < total; index += len) { + u8 operation_byte = *(data + index); + index++; + + switch (operation_byte) { + case MIPI_SEQ_ELEM_END: + return index; + case MIPI_SEQ_ELEM_SEND_PKT: + if (index + 4 > total) + return 0; + + len = *((const u16 *)(data + index + 2)) + 4; + break; + case MIPI_SEQ_ELEM_DELAY: + len = 4; + break; + case MIPI_SEQ_ELEM_GPIO: + len = 2; + break; + case MIPI_SEQ_ELEM_I2C: + if (index + 7 > total) + return 0; + len = *(data + index + 6) + 7; + break; + default: + DRM_ERROR("Unknown operation byte\n"); + return 0; + } } - DRM_DEBUG_DRIVER("Found MIPI sequence block\n"); + return 0; +} - block_size = get_blocksize(sequence); +static int goto_next_sequence_v3(const u8 *data, int index, int total) +{ + int seq_end; + u16 len; + u32 size_of_sequence; /* - * parse the sequence block for individual sequences + * Could skip sequence based on Size of Sequence alone, but also do some + * checking on the structure. */ - dev_priv->vbt.dsi.seq_version = sequence->version; + if (total < 5) { + DRM_ERROR("Too small sequence size\n"); + return 0; + } - seq_data = &sequence->data[0]; + /* Skip Sequence Byte. */ + index++; /* - * sequence block is variable length and hence we need to parse and - * get the sequence data for specific panel id + * Size of Sequence. Excludes the Sequence Byte and the size itself, + * includes MIPI_SEQ_ELEM_END byte, excludes the final MIPI_SEQ_END + * byte. */ - for (i = 0; i < MAX_MIPI_CONFIGURATIONS; i++) { - panel_id = *seq_data; - seq_size = *((u16 *) (seq_data + 1)); - if (panel_id == panel_type) - break; + size_of_sequence = *((const uint32_t *)(data + index)); + index += 4; - /* skip the sequence including seq header of 3 bytes */ - seq_data = seq_data + 3 + seq_size; - if ((seq_data - &sequence->data[0]) > block_size) { - DRM_ERROR("Sequence start is beyond sequence block size, corrupted sequence block\n"); - return; + seq_end = index + size_of_sequence; + if (seq_end > total) { + DRM_ERROR("Invalid sequence size\n"); + return 0; + } + + for (; index < total; index += len) { + u8 operation_byte = *(data + index); + index++; + + if (operation_byte == MIPI_SEQ_ELEM_END) { + if (index != seq_end) { + DRM_ERROR("Invalid element structure\n"); + return 0; + } + return index; + } + + len = *(data + index); + index++; + + /* + * FIXME: Would be nice to check elements like for v1/v2 in + * goto_next_sequence() above. + */ + switch (operation_byte) { + case MIPI_SEQ_ELEM_SEND_PKT: + case MIPI_SEQ_ELEM_DELAY: + case MIPI_SEQ_ELEM_GPIO: + case MIPI_SEQ_ELEM_I2C: + case MIPI_SEQ_ELEM_SPI: + case MIPI_SEQ_ELEM_PMIC: + break; + default: + DRM_ERROR("Unknown operation byte %u\n", + operation_byte); + break; } } - if (i == MAX_MIPI_CONFIGURATIONS) { - DRM_ERROR("Sequence block detected but no valid configuration\n"); + return 0; +} + +static void +parse_mipi_sequence(struct drm_i915_private *dev_priv, + const struct bdb_header *bdb) +{ + const struct bdb_mipi_sequence *sequence; + const u8 *seq_data; + u32 seq_size; + u8 *data; + int index = 0; + + /* Only our generic panel driver uses the sequence block. */ + if (dev_priv->vbt.dsi.panel_id != MIPI_DSI_GENERIC_PANEL_ID) + return; + + sequence = find_section(bdb, BDB_MIPI_SEQUENCE); + if (!sequence) { + DRM_DEBUG_KMS("No MIPI Sequence found, parsing complete\n"); return; } - /* check if found sequence is completely within the sequence block - * just being paranoid */ - if (seq_size > block_size) { - DRM_ERROR("Corrupted sequence/size, bailing out\n"); + /* Fail gracefully for forward incompatible sequence block. */ + if (sequence->version >= 4) { + DRM_ERROR("Unable to parse MIPI Sequence Block v%u\n", + sequence->version); return; } - /* skip the panel id(1 byte) and seq size(2 bytes) */ - dev_priv->vbt.dsi.data = kmemdup(seq_data + 3, seq_size, GFP_KERNEL); - if (!dev_priv->vbt.dsi.data) + DRM_DEBUG_DRIVER("Found MIPI sequence block v%u\n", sequence->version); + + seq_data = find_panel_sequence_block(sequence, panel_type, &seq_size); + if (!seq_data) return; - /* - * loop into the sequence data and split into multiple sequneces - * There are only 5 types of sequences as of now - */ - data = dev_priv->vbt.dsi.data; - dev_priv->vbt.dsi.size = seq_size; + data = kmemdup(seq_data, seq_size, GFP_KERNEL); + if (!data) + return; - /* two consecutive 0x00 indicate end of all sequences */ - while (1) { - int seq_id = *data; - if (MIPI_SEQ_MAX > seq_id && seq_id > MIPI_SEQ_UNDEFINED) { - dev_priv->vbt.dsi.sequence[seq_id] = data; - DRM_DEBUG_DRIVER("Found mipi sequence - %d\n", seq_id); - } else { - DRM_ERROR("undefined sequence\n"); + /* Parse the sequences, store pointers to each sequence. */ + for (;;) { + u8 seq_id = *(data + index); + if (seq_id == MIPI_SEQ_END) + break; + + if (seq_id >= MIPI_SEQ_MAX) { + DRM_ERROR("Unknown sequence %u\n", seq_id); goto err; } - /* partial parsing to skip elements */ - data = goto_next_sequence(data, &seq_size); + dev_priv->vbt.dsi.sequence[seq_id] = data + index; - if (data == NULL) { - DRM_ERROR("Sequence elements going beyond block itself. Sequence block parsing failed\n"); + if (sequence->version >= 3) + index = goto_next_sequence_v3(data, index, seq_size); + else + index = goto_next_sequence(data, index, seq_size); + if (!index) { + DRM_ERROR("Invalid sequence %u\n", seq_id); goto err; } - - if (*data == 0) - break; /* end of sequence reached */ } - DRM_DEBUG_DRIVER("MIPI related vbt parsing complete\n"); + dev_priv->vbt.dsi.data = data; + dev_priv->vbt.dsi.size = seq_size; + dev_priv->vbt.dsi.seq_version = sequence->version; + + DRM_DEBUG_DRIVER("MIPI related VBT parsing complete\n"); return; -err: - kfree(dev_priv->vbt.dsi.data); - dev_priv->vbt.dsi.data = NULL; - /* error during parsing so set all pointers to null - * because of partial parsing */ +err: + kfree(data); memset(dev_priv->vbt.dsi.sequence, 0, sizeof(dev_priv->vbt.dsi.sequence)); } @@ -1088,7 +1168,12 @@ parse_device_mapping(struct drm_i915_private *dev_priv, DRM_DEBUG_KMS("No general definition block is found, no devices defined.\n"); return; } - if (bdb->version < 195) { + if (bdb->version < 106) { + expected_size = 22; + } else if (bdb->version < 109) { + expected_size = 27; + } else if (bdb->version < 195) { + BUILD_BUG_ON(sizeof(struct old_child_dev_config) != 33); expected_size = sizeof(struct old_child_dev_config); } else if (bdb->version == 195) { expected_size = 37; @@ -1101,18 +1186,18 @@ parse_device_mapping(struct drm_i915_private *dev_priv, bdb->version, expected_size); } - /* The legacy sized child device config is the minimum we need. */ - if (p_defs->child_dev_size < sizeof(struct old_child_dev_config)) { - DRM_ERROR("Child device config size %u is too small.\n", - p_defs->child_dev_size); - return; - } - /* Flag an error for unexpected size, but continue anyway. */ if (p_defs->child_dev_size != expected_size) DRM_ERROR("Unexpected child device config size %u (expected %u for VBT version %u)\n", p_defs->child_dev_size, expected_size, bdb->version); + /* The legacy sized child device config is the minimum we need. */ + if (p_defs->child_dev_size < sizeof(struct old_child_dev_config)) { + DRM_DEBUG_KMS("Child device config size %u is too small.\n", + p_defs->child_dev_size); + return; + } + /* get the block size of general definitions */ block_size = get_blocksize(p_defs); /* get the number of child device */ @@ -1285,7 +1370,7 @@ static const struct vbt_header *find_vbt(void __iomem *bios, size_t size) /** * intel_bios_init - find VBT and initialize settings from the BIOS - * @dev: DRM device + * @dev_priv: i915 device instance * * Loads the Video BIOS and checks that the VBT exists. Sets scratch registers * to appropriate values. @@ -1337,7 +1422,8 @@ intel_bios_init(struct drm_i915_private *dev_priv) parse_driver_features(dev_priv, bdb); parse_edp(dev_priv, bdb); parse_psr(dev_priv, bdb); - parse_mipi(dev_priv, bdb); + parse_mipi_config(dev_priv, bdb); + parse_mipi_sequence(dev_priv, bdb); parse_ddi_ports(dev_priv, bdb); if (bios) diff --git a/drivers/gpu/drm/i915/intel_bios.h b/drivers/gpu/drm/i915/intel_bios.h index 54eac1003a1e..350d4e0f75a4 100644 --- a/drivers/gpu/drm/i915/intel_bios.h +++ b/drivers/gpu/drm/i915/intel_bios.h @@ -25,25 +25,43 @@ * */ -#ifndef _I830_BIOS_H_ -#define _I830_BIOS_H_ - +#ifndef _INTEL_BIOS_H_ +#define _INTEL_BIOS_H_ + +/** + * struct vbt_header - VBT Header structure + * @signature: VBT signature, always starts with "$VBT" + * @version: Version of this structure + * @header_size: Size of this structure + * @vbt_size: Size of VBT (VBT Header, BDB Header and data blocks) + * @vbt_checksum: Checksum + * @reserved0: Reserved + * @bdb_offset: Offset of &struct bdb_header from beginning of VBT + * @aim_offset: Offsets of add-in data blocks from beginning of VBT + */ struct vbt_header { - u8 signature[20]; /**< Always starts with 'VBT$' */ - u16 version; /**< decimal */ - u16 header_size; /**< in bytes */ - u16 vbt_size; /**< in bytes */ + u8 signature[20]; + u16 version; + u16 header_size; + u16 vbt_size; u8 vbt_checksum; u8 reserved0; - u32 bdb_offset; /**< from beginning of VBT */ - u32 aim_offset[4]; /**< from beginning of VBT */ + u32 bdb_offset; + u32 aim_offset[4]; } __packed; +/** + * struct bdb_header - BDB Header structure + * @signature: BDB signature "BIOS_DATA_BLOCK" + * @version: Version of the data block definitions + * @header_size: Size of this structure + * @bdb_size: Size of BDB (BDB Header and data blocks) + */ struct bdb_header { - u8 signature[16]; /**< Always 'BIOS_DATA_BLOCK' */ - u16 version; /**< decimal */ - u16 header_size; /**< in bytes */ - u16 bdb_size; /**< in bytes */ + u8 signature[16]; + u16 version; + u16 header_size; + u16 bdb_size; } __packed; /* strictly speaking, this is a "skip" block, but it has interesting info */ @@ -936,21 +954,29 @@ struct bdb_mipi_sequence { /* MIPI Sequnece Block definitions */ enum mipi_seq { - MIPI_SEQ_UNDEFINED = 0, + MIPI_SEQ_END = 0, MIPI_SEQ_ASSERT_RESET, MIPI_SEQ_INIT_OTP, MIPI_SEQ_DISPLAY_ON, MIPI_SEQ_DISPLAY_OFF, MIPI_SEQ_DEASSERT_RESET, + MIPI_SEQ_BACKLIGHT_ON, /* sequence block v2+ */ + MIPI_SEQ_BACKLIGHT_OFF, /* sequence block v2+ */ + MIPI_SEQ_TEAR_ON, /* sequence block v2+ */ + MIPI_SEQ_TEAR_OFF, /* sequence block v3+ */ + MIPI_SEQ_POWER_ON, /* sequence block v3+ */ + MIPI_SEQ_POWER_OFF, /* sequence block v3+ */ MIPI_SEQ_MAX }; enum mipi_seq_element { - MIPI_SEQ_ELEM_UNDEFINED = 0, + MIPI_SEQ_ELEM_END = 0, MIPI_SEQ_ELEM_SEND_PKT, MIPI_SEQ_ELEM_DELAY, MIPI_SEQ_ELEM_GPIO, - MIPI_SEQ_ELEM_STATUS, + MIPI_SEQ_ELEM_I2C, /* sequence block v2+ */ + MIPI_SEQ_ELEM_SPI, /* sequence block v3+ */ + MIPI_SEQ_ELEM_PMIC, /* sequence block v3+ */ MIPI_SEQ_ELEM_MAX }; @@ -965,4 +991,4 @@ enum mipi_gpio_pin_index { MIPI_GPIO_MAX }; -#endif /* _I830_BIOS_H_ */ +#endif /* _INTEL_BIOS_H_ */ diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 9bb63a85997a..5c2f9a40c81b 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -44,6 +44,8 @@ #define I915_CSR_SKL "i915/skl_dmc_ver1.bin" #define I915_CSR_BXT "i915/bxt_dmc_ver1.bin" +#define FIRMWARE_URL "https://01.org/linuxgraphics/intel-linux-graphics-firmwares" + MODULE_FIRMWARE(I915_CSR_SKL); MODULE_FIRMWARE(I915_CSR_BXT); @@ -278,10 +280,11 @@ static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv, csr->version = css_header->version; - if (IS_SKYLAKE(dev) && csr->version < SKL_CSR_VERSION_REQUIRED) { + if ((IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) && + csr->version < SKL_CSR_VERSION_REQUIRED) { DRM_INFO("Refusing to load old Skylake DMC firmware v%u.%u," " please upgrade to v%u.%u or later" - " [https://01.org/linuxgraphics/intel-linux-graphics-firmwares].\n", + " [" FIRMWARE_URL "].\n", CSR_VERSION_MAJOR(csr->version), CSR_VERSION_MINOR(csr->version), CSR_VERSION_MAJOR(SKL_CSR_VERSION_REQUIRED), @@ -399,7 +402,10 @@ out: CSR_VERSION_MAJOR(csr->version), CSR_VERSION_MINOR(csr->version)); } else { - DRM_ERROR("Failed to load DMC firmware, disabling rpm\n"); + dev_notice(dev_priv->dev->dev, + "Failed to load DMC firmware" + " [" FIRMWARE_URL "]," + " disabling runtime power management.\n"); } release_firmware(fw); @@ -421,7 +427,7 @@ void intel_csr_ucode_init(struct drm_i915_private *dev_priv) if (!HAS_CSR(dev_priv)) return; - if (IS_SKYLAKE(dev_priv)) + if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) csr->fw_path = I915_CSR_SKL; else if (IS_BROXTON(dev_priv)) csr->fw_path = I915_CSR_BXT; diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index e6408e5583d7..1f9a3687b540 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -133,38 +133,38 @@ static const struct ddi_buf_trans skl_ddi_translations_dp[] = { { 0x00002016, 0x000000A0, 0x0 }, { 0x00005012, 0x0000009B, 0x0 }, { 0x00007011, 0x00000088, 0x0 }, - { 0x80009010, 0x000000C0, 0x1 }, /* Uses I_boost level 0x1 */ + { 0x80009010, 0x000000C0, 0x1 }, { 0x00002016, 0x0000009B, 0x0 }, { 0x00005012, 0x00000088, 0x0 }, - { 0x80007011, 0x000000C0, 0x1 }, /* Uses I_boost level 0x1 */ + { 0x80007011, 0x000000C0, 0x1 }, { 0x00002016, 0x000000DF, 0x0 }, - { 0x80005012, 0x000000C0, 0x1 }, /* Uses I_boost level 0x1 */ + { 0x80005012, 0x000000C0, 0x1 }, }; /* Skylake U */ static const struct ddi_buf_trans skl_u_ddi_translations_dp[] = { { 0x0000201B, 0x000000A2, 0x0 }, { 0x00005012, 0x00000088, 0x0 }, - { 0x00007011, 0x00000087, 0x0 }, - { 0x80009010, 0x000000C0, 0x1 }, /* Uses I_boost level 0x1 */ + { 0x80007011, 0x000000CD, 0x0 }, + { 0x80009010, 0x000000C0, 0x1 }, { 0x0000201B, 0x0000009D, 0x0 }, - { 0x80005012, 0x000000C0, 0x1 }, /* Uses I_boost level 0x1 */ - { 0x80007011, 0x000000C0, 0x1 }, /* Uses I_boost level 0x1 */ + { 0x80005012, 0x000000C0, 0x1 }, + { 0x80007011, 0x000000C0, 0x1 }, { 0x00002016, 0x00000088, 0x0 }, - { 0x80005012, 0x000000C0, 0x1 }, /* Uses I_boost level 0x1 */ + { 0x80005012, 0x000000C0, 0x1 }, }; /* Skylake Y */ static const struct ddi_buf_trans skl_y_ddi_translations_dp[] = { { 0x00000018, 0x000000A2, 0x0 }, { 0x00005012, 0x00000088, 0x0 }, - { 0x00007011, 0x00000087, 0x0 }, - { 0x80009010, 0x000000C0, 0x3 }, /* Uses I_boost level 0x3 */ + { 0x80007011, 0x000000CD, 0x0 }, + { 0x80009010, 0x000000C0, 0x3 }, { 0x00000018, 0x0000009D, 0x0 }, - { 0x80005012, 0x000000C0, 0x3 }, /* Uses I_boost level 0x3 */ - { 0x80007011, 0x000000C0, 0x3 }, /* Uses I_boost level 0x3 */ + { 0x80005012, 0x000000C0, 0x3 }, + { 0x80007011, 0x000000C0, 0x3 }, { 0x00000018, 0x00000088, 0x0 }, - { 0x80005012, 0x000000C0, 0x3 }, /* Uses I_boost level 0x3 */ + { 0x80005012, 0x000000C0, 0x3 }, }; /* @@ -226,26 +226,26 @@ static const struct ddi_buf_trans skl_ddi_translations_hdmi[] = { { 0x00000018, 0x000000A1, 0x0 }, { 0x00000018, 0x00000098, 0x0 }, { 0x00004013, 0x00000088, 0x0 }, - { 0x00006012, 0x00000087, 0x0 }, + { 0x80006012, 0x000000CD, 0x1 }, { 0x00000018, 0x000000DF, 0x0 }, - { 0x00003015, 0x00000087, 0x0 }, /* Default */ - { 0x00003015, 0x000000C7, 0x0 }, - { 0x00000018, 0x000000C7, 0x0 }, + { 0x80003015, 0x000000CD, 0x1 }, /* Default */ + { 0x80003015, 0x000000C0, 0x1 }, + { 0x80000018, 0x000000C0, 0x1 }, }; /* Skylake Y */ static const struct ddi_buf_trans skl_y_ddi_translations_hdmi[] = { { 0x00000018, 0x000000A1, 0x0 }, { 0x00005012, 0x000000DF, 0x0 }, - { 0x00007011, 0x00000084, 0x0 }, + { 0x80007011, 0x000000CB, 0x3 }, { 0x00000018, 0x000000A4, 0x0 }, { 0x00000018, 0x0000009D, 0x0 }, { 0x00004013, 0x00000080, 0x0 }, - { 0x00006013, 0x000000C7, 0x0 }, + { 0x80006013, 0x000000C0, 0x3 }, { 0x00000018, 0x0000008A, 0x0 }, - { 0x00003015, 0x000000C7, 0x0 }, /* Default */ - { 0x80003015, 0x000000C7, 0x7 }, /* Uses I_boost level 0x7 */ - { 0x00000018, 0x000000C7, 0x0 }, + { 0x80003015, 0x000000C0, 0x3 }, /* Default */ + { 0x80003015, 0x000000C0, 0x3 }, + { 0x80000018, 0x000000C0, 0x3 }, }; struct bxt_ddi_buf_trans { @@ -301,8 +301,8 @@ static const struct bxt_ddi_buf_trans bxt_ddi_translations_hdmi[] = { { 154, 0x9A, 1, 128, true }, /* 9: 1200 0 */ }; -static void bxt_ddi_vswing_sequence(struct drm_device *dev, u32 level, - enum port port, int type); +static void bxt_ddi_vswing_sequence(struct drm_i915_private *dev_priv, + u32 level, enum port port, int type); static void ddi_get_encoder_port(struct intel_encoder *intel_encoder, struct intel_digital_port **dig_port, @@ -342,81 +342,50 @@ enum port intel_ddi_get_encoder_port(struct intel_encoder *intel_encoder) return port; } -static bool -intel_dig_port_supports_hdmi(const struct intel_digital_port *intel_dig_port) -{ - return i915_mmio_reg_valid(intel_dig_port->hdmi.hdmi_reg); -} - -static const struct ddi_buf_trans *skl_get_buf_trans_dp(struct drm_device *dev, - int *n_entries) +static const struct ddi_buf_trans * +skl_get_buf_trans_dp(struct drm_i915_private *dev_priv, int *n_entries) { - const struct ddi_buf_trans *ddi_translations; - - if (IS_SKL_ULX(dev) || IS_KBL_ULX(dev)) { - ddi_translations = skl_y_ddi_translations_dp; + if (IS_SKL_ULX(dev_priv) || IS_KBL_ULX(dev_priv)) { *n_entries = ARRAY_SIZE(skl_y_ddi_translations_dp); - } else if (IS_SKL_ULT(dev) || IS_KBL_ULT(dev)) { - ddi_translations = skl_u_ddi_translations_dp; + return skl_y_ddi_translations_dp; + } else if (IS_SKL_ULT(dev_priv) || IS_KBL_ULT(dev_priv)) { *n_entries = ARRAY_SIZE(skl_u_ddi_translations_dp); + return skl_u_ddi_translations_dp; } else { - ddi_translations = skl_ddi_translations_dp; *n_entries = ARRAY_SIZE(skl_ddi_translations_dp); + return skl_ddi_translations_dp; } - - return ddi_translations; } -static const struct ddi_buf_trans *skl_get_buf_trans_edp(struct drm_device *dev, - int *n_entries) +static const struct ddi_buf_trans * +skl_get_buf_trans_edp(struct drm_i915_private *dev_priv, int *n_entries) { - struct drm_i915_private *dev_priv = dev->dev_private; - const struct ddi_buf_trans *ddi_translations; - - if (IS_SKL_ULX(dev) || IS_KBL_ULX(dev)) { - if (dev_priv->edp_low_vswing) { - ddi_translations = skl_y_ddi_translations_edp; + if (dev_priv->edp_low_vswing) { + if (IS_SKL_ULX(dev_priv) || IS_KBL_ULX(dev_priv)) { *n_entries = ARRAY_SIZE(skl_y_ddi_translations_edp); - } else { - ddi_translations = skl_y_ddi_translations_dp; - *n_entries = ARRAY_SIZE(skl_y_ddi_translations_dp); - } - } else if (IS_SKL_ULT(dev) || IS_KBL_ULT(dev)) { - if (dev_priv->edp_low_vswing) { - ddi_translations = skl_u_ddi_translations_edp; + return skl_y_ddi_translations_edp; + } else if (IS_SKL_ULT(dev_priv) || IS_KBL_ULT(dev_priv)) { *n_entries = ARRAY_SIZE(skl_u_ddi_translations_edp); + return skl_u_ddi_translations_edp; } else { - ddi_translations = skl_u_ddi_translations_dp; - *n_entries = ARRAY_SIZE(skl_u_ddi_translations_dp); - } - } else { - if (dev_priv->edp_low_vswing) { - ddi_translations = skl_ddi_translations_edp; *n_entries = ARRAY_SIZE(skl_ddi_translations_edp); - } else { - ddi_translations = skl_ddi_translations_dp; - *n_entries = ARRAY_SIZE(skl_ddi_translations_dp); + return skl_ddi_translations_edp; } } - return ddi_translations; + return skl_get_buf_trans_dp(dev_priv, n_entries); } static const struct ddi_buf_trans * -skl_get_buf_trans_hdmi(struct drm_device *dev, - int *n_entries) +skl_get_buf_trans_hdmi(struct drm_i915_private *dev_priv, int *n_entries) { - const struct ddi_buf_trans *ddi_translations; - - if (IS_SKL_ULX(dev) || IS_KBL_ULX(dev)) { - ddi_translations = skl_y_ddi_translations_hdmi; + if (IS_SKL_ULX(dev_priv) || IS_KBL_ULX(dev_priv)) { *n_entries = ARRAY_SIZE(skl_y_ddi_translations_hdmi); + return skl_y_ddi_translations_hdmi; } else { - ddi_translations = skl_ddi_translations_hdmi; *n_entries = ARRAY_SIZE(skl_ddi_translations_hdmi); + return skl_ddi_translations_hdmi; } - - return ddi_translations; } /* @@ -426,42 +395,52 @@ skl_get_buf_trans_hdmi(struct drm_device *dev, * in either FDI or DP modes only, as HDMI connections will work with both * of those */ -static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port, - bool supports_hdmi) +void intel_prepare_ddi_buffer(struct intel_encoder *encoder) { - struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); u32 iboost_bit = 0; int i, n_hdmi_entries, n_dp_entries, n_edp_entries, hdmi_default_entry, size; - int hdmi_level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift; + int hdmi_level; + enum port port; const struct ddi_buf_trans *ddi_translations_fdi; const struct ddi_buf_trans *ddi_translations_dp; const struct ddi_buf_trans *ddi_translations_edp; const struct ddi_buf_trans *ddi_translations_hdmi; const struct ddi_buf_trans *ddi_translations; - if (IS_BROXTON(dev)) { - if (!supports_hdmi) + port = intel_ddi_get_encoder_port(encoder); + hdmi_level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift; + + if (IS_BROXTON(dev_priv)) { + if (encoder->type != INTEL_OUTPUT_HDMI) return; /* Vswing programming for HDMI */ - bxt_ddi_vswing_sequence(dev, hdmi_level, port, + bxt_ddi_vswing_sequence(dev_priv, hdmi_level, port, INTEL_OUTPUT_HDMI); return; - } else if (IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) { + } + + if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) { ddi_translations_fdi = NULL; ddi_translations_dp = - skl_get_buf_trans_dp(dev, &n_dp_entries); + skl_get_buf_trans_dp(dev_priv, &n_dp_entries); ddi_translations_edp = - skl_get_buf_trans_edp(dev, &n_edp_entries); + skl_get_buf_trans_edp(dev_priv, &n_edp_entries); ddi_translations_hdmi = - skl_get_buf_trans_hdmi(dev, &n_hdmi_entries); + skl_get_buf_trans_hdmi(dev_priv, &n_hdmi_entries); hdmi_default_entry = 8; /* If we're boosting the current, set bit 31 of trans1 */ if (dev_priv->vbt.ddi_port_info[port].hdmi_boost_level || dev_priv->vbt.ddi_port_info[port].dp_boost_level) iboost_bit = 1<<31; - } else if (IS_BROADWELL(dev)) { + + if (WARN_ON(encoder->type == INTEL_OUTPUT_EDP && + port != PORT_A && port != PORT_E && + n_edp_entries > 9)) + n_edp_entries = 9; + } else if (IS_BROADWELL(dev_priv)) { ddi_translations_fdi = bdw_ddi_translations_fdi; ddi_translations_dp = bdw_ddi_translations_dp; ddi_translations_edp = bdw_ddi_translations_edp; @@ -470,7 +449,7 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port, n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); hdmi_default_entry = 7; - } else if (IS_HASWELL(dev)) { + } else if (IS_HASWELL(dev_priv)) { ddi_translations_fdi = hsw_ddi_translations_fdi; ddi_translations_dp = hsw_ddi_translations_dp; ddi_translations_edp = hsw_ddi_translations_dp; @@ -490,30 +469,18 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port, hdmi_default_entry = 7; } - switch (port) { - case PORT_A: + switch (encoder->type) { + case INTEL_OUTPUT_EDP: ddi_translations = ddi_translations_edp; size = n_edp_entries; break; - case PORT_B: - case PORT_C: + case INTEL_OUTPUT_DISPLAYPORT: + case INTEL_OUTPUT_HDMI: ddi_translations = ddi_translations_dp; size = n_dp_entries; break; - case PORT_D: - if (intel_dp_is_edp(dev, PORT_D)) { - ddi_translations = ddi_translations_edp; - size = n_edp_entries; - } else { - ddi_translations = ddi_translations_dp; - size = n_dp_entries; - } - break; - case PORT_E: - if (ddi_translations_fdi) - ddi_translations = ddi_translations_fdi; - else - ddi_translations = ddi_translations_dp; + case INTEL_OUTPUT_ANALOG: + ddi_translations = ddi_translations_fdi; size = n_dp_entries; break; default: @@ -527,7 +494,7 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port, ddi_translations[i].trans2); } - if (!supports_hdmi) + if (encoder->type != INTEL_OUTPUT_HDMI) return; /* Choose a good default if VBT is badly populated */ @@ -542,37 +509,6 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port, ddi_translations_hdmi[hdmi_level].trans2); } -/* Program DDI buffers translations for DP. By default, program ports A-D in DP - * mode and port E for FDI. - */ -void intel_prepare_ddi(struct drm_device *dev) -{ - struct intel_encoder *intel_encoder; - bool visited[I915_MAX_PORTS] = { 0, }; - - if (!HAS_DDI(dev)) - return; - - for_each_intel_encoder(dev, intel_encoder) { - struct intel_digital_port *intel_dig_port; - enum port port; - bool supports_hdmi; - - if (intel_encoder->type == INTEL_OUTPUT_DSI) - continue; - - ddi_get_encoder_port(intel_encoder, &intel_dig_port, &port); - if (visited[port]) - continue; - - supports_hdmi = intel_dig_port && - intel_dig_port_supports_hdmi(intel_dig_port); - - intel_prepare_ddi_buffers(dev, port, supports_hdmi); - visited[port] = true; - } -} - static void intel_wait_ddi_buf_idle(struct drm_i915_private *dev_priv, enum port port) { @@ -601,8 +537,14 @@ void hsw_fdi_link_train(struct drm_crtc *crtc) struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_encoder *encoder; u32 temp, i, rx_ctl_val; + for_each_encoder_on_crtc(dev, crtc, encoder) { + WARN_ON(encoder->type != INTEL_OUTPUT_ANALOG); + intel_prepare_ddi_buffer(encoder); + } + /* Set the FDI_RX_MISC pwrdn lanes and the 2 workarounds listed at the * mode set "sequence for CRT port" document: * - TP1 to TP2 time with the default value @@ -2085,10 +2027,9 @@ void intel_ddi_disable_pipe_clock(struct intel_crtc *intel_crtc) TRANS_CLK_SEL_DISABLED); } -static void skl_ddi_set_iboost(struct drm_device *dev, u32 level, - enum port port, int type) +static void skl_ddi_set_iboost(struct drm_i915_private *dev_priv, + u32 level, enum port port, int type) { - struct drm_i915_private *dev_priv = dev->dev_private; const struct ddi_buf_trans *ddi_translations; uint8_t iboost; uint8_t dp_iboost, hdmi_iboost; @@ -2103,21 +2044,26 @@ static void skl_ddi_set_iboost(struct drm_device *dev, u32 level, if (dp_iboost) { iboost = dp_iboost; } else { - ddi_translations = skl_get_buf_trans_dp(dev, &n_entries); + ddi_translations = skl_get_buf_trans_dp(dev_priv, &n_entries); iboost = ddi_translations[level].i_boost; } } else if (type == INTEL_OUTPUT_EDP) { if (dp_iboost) { iboost = dp_iboost; } else { - ddi_translations = skl_get_buf_trans_edp(dev, &n_entries); + ddi_translations = skl_get_buf_trans_edp(dev_priv, &n_entries); + + if (WARN_ON(port != PORT_A && + port != PORT_E && n_entries > 9)) + n_entries = 9; + iboost = ddi_translations[level].i_boost; } } else if (type == INTEL_OUTPUT_HDMI) { if (hdmi_iboost) { iboost = hdmi_iboost; } else { - ddi_translations = skl_get_buf_trans_hdmi(dev, &n_entries); + ddi_translations = skl_get_buf_trans_hdmi(dev_priv, &n_entries); iboost = ddi_translations[level].i_boost; } } else { @@ -2142,10 +2088,9 @@ static void skl_ddi_set_iboost(struct drm_device *dev, u32 level, I915_WRITE(DISPIO_CR_TX_BMU_CR0, reg); } -static void bxt_ddi_vswing_sequence(struct drm_device *dev, u32 level, - enum port port, int type) +static void bxt_ddi_vswing_sequence(struct drm_i915_private *dev_priv, + u32 level, enum port port, int type) { - struct drm_i915_private *dev_priv = dev->dev_private; const struct bxt_ddi_buf_trans *ddi_translations; u32 n_entries, i; uint32_t val; @@ -2260,7 +2205,7 @@ static uint32_t translate_signal_level(int signal_levels) uint32_t ddi_signal_levels(struct intel_dp *intel_dp) { struct intel_digital_port *dport = dp_to_dig_port(intel_dp); - struct drm_device *dev = dport->base.base.dev; + struct drm_i915_private *dev_priv = to_i915(dport->base.base.dev); struct intel_encoder *encoder = &dport->base; uint8_t train_set = intel_dp->train_set[0]; int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK | @@ -2270,10 +2215,10 @@ uint32_t ddi_signal_levels(struct intel_dp *intel_dp) level = translate_signal_level(signal_levels); - if (IS_SKYLAKE(dev) || IS_KABYLAKE(dev)) - skl_ddi_set_iboost(dev, level, port, encoder->type); - else if (IS_BROXTON(dev)) - bxt_ddi_vswing_sequence(dev, level, port, encoder->type); + if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) + skl_ddi_set_iboost(dev_priv, level, port, encoder->type); + else if (IS_BROXTON(dev_priv)) + bxt_ddi_vswing_sequence(dev_priv, level, port, encoder->type); return DDI_BUF_TRANS_SELECT(level); } @@ -2325,12 +2270,12 @@ void intel_ddi_clk_select(struct intel_encoder *encoder, static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder) { struct drm_encoder *encoder = &intel_encoder->base; - struct drm_device *dev = encoder->dev; - struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_private *dev_priv = to_i915(encoder->dev); struct intel_crtc *crtc = to_intel_crtc(encoder->crtc); enum port port = intel_ddi_get_encoder_port(intel_encoder); int type = intel_encoder->type; - int hdmi_level; + + intel_prepare_ddi_buffer(intel_encoder); if (type == INTEL_OUTPUT_EDP) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); @@ -2348,17 +2293,11 @@ static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder) intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON); intel_dp_start_link_train(intel_dp); - if (port != PORT_A || INTEL_INFO(dev)->gen >= 9) + if (port != PORT_A || INTEL_INFO(dev_priv)->gen >= 9) intel_dp_stop_link_train(intel_dp); } else if (type == INTEL_OUTPUT_HDMI) { struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); - if (IS_BROXTON(dev)) { - hdmi_level = dev_priv->vbt. - ddi_port_info[port].hdmi_level_shift; - bxt_ddi_vswing_sequence(dev, hdmi_level, port, - INTEL_OUTPUT_HDMI); - } intel_hdmi->set_infoframes(encoder, crtc->config->has_hdmi_sink, &crtc->config->base.adjusted_mode); @@ -3282,6 +3221,33 @@ void intel_ddi_init(struct drm_device *dev, enum port port) struct intel_encoder *intel_encoder; struct drm_encoder *encoder; bool init_hdmi, init_dp; + int max_lanes; + + if (I915_READ(DDI_BUF_CTL(PORT_A)) & DDI_A_4_LANES) { + switch (port) { + case PORT_A: + max_lanes = 4; + break; + case PORT_E: + max_lanes = 0; + break; + default: + max_lanes = 4; + break; + } + } else { + switch (port) { + case PORT_A: + max_lanes = 2; + break; + case PORT_E: + max_lanes = 2; + break; + default: + max_lanes = 4; + break; + } + } init_hdmi = (dev_priv->vbt.ddi_port_info[port].supports_dvi || dev_priv->vbt.ddi_port_info[port].supports_hdmi); @@ -3315,6 +3281,7 @@ void intel_ddi_init(struct drm_device *dev, enum port port) intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) & (DDI_BUF_PORT_REVERSAL | DDI_A_4_LANES); + intel_dig_port->max_lanes = max_lanes; /* * Bspec says that DDI_A_4_LANES is the only supported configuration diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 5feb65725c04..8104511ad302 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -85,8 +85,6 @@ static const uint32_t intel_cursor_formats[] = { DRM_FORMAT_ARGB8888, }; -static void intel_crtc_update_cursor(struct drm_crtc *crtc, bool on); - static void i9xx_crtc_clock_get(struct intel_crtc *crtc, struct intel_crtc_state *pipe_config); static void ironlake_pch_clock_get(struct intel_crtc *crtc, @@ -1152,11 +1150,6 @@ static void intel_wait_for_pipe_off(struct intel_crtc *crtc) } } -static const char *state_string(bool enabled) -{ - return enabled ? "on" : "off"; -} - /* Only for pre-ILK configs */ void assert_pll(struct drm_i915_private *dev_priv, enum pipe pipe, bool state) @@ -1168,7 +1161,7 @@ void assert_pll(struct drm_i915_private *dev_priv, cur_state = !!(val & DPLL_VCO_ENABLE); I915_STATE_WARN(cur_state != state, "PLL state assertion failure (expected %s, current %s)\n", - state_string(state), state_string(cur_state)); + onoff(state), onoff(cur_state)); } /* XXX: the dsi pll is shared between MIPI DSI ports */ @@ -1184,7 +1177,7 @@ static void assert_dsi_pll(struct drm_i915_private *dev_priv, bool state) cur_state = val & DSI_PLL_VCO_EN; I915_STATE_WARN(cur_state != state, "DSI PLL state assertion failure (expected %s, current %s)\n", - state_string(state), state_string(cur_state)); + onoff(state), onoff(cur_state)); } #define assert_dsi_pll_enabled(d) assert_dsi_pll(d, true) #define assert_dsi_pll_disabled(d) assert_dsi_pll(d, false) @@ -1208,14 +1201,13 @@ void assert_shared_dpll(struct drm_i915_private *dev_priv, bool cur_state; struct intel_dpll_hw_state hw_state; - if (WARN (!pll, - "asserting DPLL %s with no DPLL\n", state_string(state))) + if (WARN(!pll, "asserting DPLL %s with no DPLL\n", onoff(state))) return; cur_state = pll->get_hw_state(dev_priv, pll, &hw_state); I915_STATE_WARN(cur_state != state, "%s assertion failure (expected %s, current %s)\n", - pll->name, state_string(state), state_string(cur_state)); + pll->name, onoff(state), onoff(cur_state)); } static void assert_fdi_tx(struct drm_i915_private *dev_priv, @@ -1235,7 +1227,7 @@ static void assert_fdi_tx(struct drm_i915_private *dev_priv, } I915_STATE_WARN(cur_state != state, "FDI TX state assertion failure (expected %s, current %s)\n", - state_string(state), state_string(cur_state)); + onoff(state), onoff(cur_state)); } #define assert_fdi_tx_enabled(d, p) assert_fdi_tx(d, p, true) #define assert_fdi_tx_disabled(d, p) assert_fdi_tx(d, p, false) @@ -1250,7 +1242,7 @@ static void assert_fdi_rx(struct drm_i915_private *dev_priv, cur_state = !!(val & FDI_RX_ENABLE); I915_STATE_WARN(cur_state != state, "FDI RX state assertion failure (expected %s, current %s)\n", - state_string(state), state_string(cur_state)); + onoff(state), onoff(cur_state)); } #define assert_fdi_rx_enabled(d, p) assert_fdi_rx(d, p, true) #define assert_fdi_rx_disabled(d, p) assert_fdi_rx(d, p, false) @@ -1282,7 +1274,7 @@ void assert_fdi_rx_pll(struct drm_i915_private *dev_priv, cur_state = !!(val & FDI_RX_PLL_ENABLE); I915_STATE_WARN(cur_state != state, "FDI RX PLL assertion failure (expected %s, current %s)\n", - state_string(state), state_string(cur_state)); + onoff(state), onoff(cur_state)); } void assert_panel_unlocked(struct drm_i915_private *dev_priv, @@ -1340,7 +1332,7 @@ static void assert_cursor(struct drm_i915_private *dev_priv, I915_STATE_WARN(cur_state != state, "cursor on pipe %c assertion failure (expected %s, current %s)\n", - pipe_name(pipe), state_string(state), state_string(cur_state)); + pipe_name(pipe), onoff(state), onoff(cur_state)); } #define assert_cursor_enabled(d, p) assert_cursor(d, p, true) #define assert_cursor_disabled(d, p) assert_cursor(d, p, false) @@ -1367,7 +1359,7 @@ void assert_pipe(struct drm_i915_private *dev_priv, I915_STATE_WARN(cur_state != state, "pipe %c assertion failure (expected %s, current %s)\n", - pipe_name(pipe), state_string(state), state_string(cur_state)); + pipe_name(pipe), onoff(state), onoff(cur_state)); } static void assert_plane(struct drm_i915_private *dev_priv, @@ -1380,7 +1372,7 @@ static void assert_plane(struct drm_i915_private *dev_priv, cur_state = !!(val & DISPLAY_PLANE_ENABLE); I915_STATE_WARN(cur_state != state, "plane %c assertion failure (expected %s, current %s)\n", - plane_name(plane), state_string(state), state_string(cur_state)); + plane_name(plane), onoff(state), onoff(cur_state)); } #define assert_plane_enabled(d, p) assert_plane(d, p, true) @@ -2153,6 +2145,17 @@ static void intel_enable_pipe(struct intel_crtc *crtc) I915_WRITE(reg, val | PIPECONF_ENABLE); POSTING_READ(reg); + + /* + * Until the pipe starts DSL will read as 0, which would cause + * an apparent vblank timestamp jump, which messes up also the + * frame count when it's derived from the timestamps. So let's + * wait for the pipe to start properly before we call + * drm_crtc_vblank_on() + */ + if (dev->max_vblank_count == 0 && + wait_for(intel_get_crtc_scanline(crtc) != crtc->scanline_offset, 50)) + DRM_ERROR("pipe %c didn't start\n", pipe_name(pipe)); } /** @@ -2214,67 +2217,75 @@ static bool need_vtd_wa(struct drm_device *dev) return false; } -unsigned int -intel_tile_height(struct drm_device *dev, uint32_t pixel_format, - uint64_t fb_format_modifier, unsigned int plane) +static unsigned int intel_tile_size(const struct drm_i915_private *dev_priv) { - unsigned int tile_height; - uint32_t pixel_bytes; + return IS_GEN2(dev_priv) ? 2048 : 4096; +} - switch (fb_format_modifier) { +static unsigned int intel_tile_width(const struct drm_i915_private *dev_priv, + uint64_t fb_modifier, unsigned int cpp) +{ + switch (fb_modifier) { case DRM_FORMAT_MOD_NONE: - tile_height = 1; - break; + return cpp; case I915_FORMAT_MOD_X_TILED: - tile_height = IS_GEN2(dev) ? 16 : 8; - break; + if (IS_GEN2(dev_priv)) + return 128; + else + return 512; case I915_FORMAT_MOD_Y_TILED: - tile_height = 32; - break; + if (IS_GEN2(dev_priv) || HAS_128_BYTE_Y_TILING(dev_priv)) + return 128; + else + return 512; case I915_FORMAT_MOD_Yf_TILED: - pixel_bytes = drm_format_plane_cpp(pixel_format, plane); - switch (pixel_bytes) { - default: + switch (cpp) { case 1: - tile_height = 64; - break; + return 64; case 2: case 4: - tile_height = 32; - break; + return 128; case 8: - tile_height = 16; - break; case 16: - WARN_ONCE(1, - "128-bit pixels are not supported for display!"); - tile_height = 16; - break; + return 256; + default: + MISSING_CASE(cpp); + return cpp; } break; default: - MISSING_CASE(fb_format_modifier); - tile_height = 1; - break; + MISSING_CASE(fb_modifier); + return cpp; } +} - return tile_height; +unsigned int intel_tile_height(const struct drm_i915_private *dev_priv, + uint64_t fb_modifier, unsigned int cpp) +{ + if (fb_modifier == DRM_FORMAT_MOD_NONE) + return 1; + else + return intel_tile_size(dev_priv) / + intel_tile_width(dev_priv, fb_modifier, cpp); } unsigned int intel_fb_align_height(struct drm_device *dev, unsigned int height, - uint32_t pixel_format, uint64_t fb_format_modifier) + uint32_t pixel_format, uint64_t fb_modifier) { - return ALIGN(height, intel_tile_height(dev, pixel_format, - fb_format_modifier, 0)); + unsigned int cpp = drm_format_plane_cpp(pixel_format, 0); + unsigned int tile_height = intel_tile_height(to_i915(dev), fb_modifier, cpp); + + return ALIGN(height, tile_height); } static void intel_fill_fb_ggtt_view(struct i915_ggtt_view *view, struct drm_framebuffer *fb, const struct drm_plane_state *plane_state) { + struct drm_i915_private *dev_priv = to_i915(fb->dev); struct intel_rotation_info *info = &view->params.rotation_info; - unsigned int tile_height, tile_pitch; + unsigned int tile_size, tile_width, tile_height, cpp; *view = i915_ggtt_view_normal; @@ -2292,26 +2303,28 @@ intel_fill_fb_ggtt_view(struct i915_ggtt_view *view, struct drm_framebuffer *fb, info->uv_offset = fb->offsets[1]; info->fb_modifier = fb->modifier[0]; - tile_height = intel_tile_height(fb->dev, fb->pixel_format, - fb->modifier[0], 0); - tile_pitch = PAGE_SIZE / tile_height; - info->width_pages = DIV_ROUND_UP(fb->pitches[0], tile_pitch); + tile_size = intel_tile_size(dev_priv); + + cpp = drm_format_plane_cpp(fb->pixel_format, 0); + tile_width = intel_tile_width(dev_priv, cpp, fb->modifier[0]); + tile_height = tile_size / tile_width; + + info->width_pages = DIV_ROUND_UP(fb->pitches[0], tile_width); info->height_pages = DIV_ROUND_UP(fb->height, tile_height); - info->size = info->width_pages * info->height_pages * PAGE_SIZE; + info->size = info->width_pages * info->height_pages * tile_size; if (info->pixel_format == DRM_FORMAT_NV12) { - tile_height = intel_tile_height(fb->dev, fb->pixel_format, - fb->modifier[0], 1); - tile_pitch = PAGE_SIZE / tile_height; - info->width_pages_uv = DIV_ROUND_UP(fb->pitches[0], tile_pitch); - info->height_pages_uv = DIV_ROUND_UP(fb->height / 2, - tile_height); - info->size_uv = info->width_pages_uv * info->height_pages_uv * - PAGE_SIZE; + cpp = drm_format_plane_cpp(fb->pixel_format, 1); + tile_width = intel_tile_width(dev_priv, fb->modifier[1], cpp); + tile_height = tile_size / tile_width; + + info->width_pages_uv = DIV_ROUND_UP(fb->pitches[1], tile_width); + info->height_pages_uv = DIV_ROUND_UP(fb->height / 2, tile_height); + info->size_uv = info->width_pages_uv * info->height_pages_uv * tile_size; } } -static unsigned int intel_linear_alignment(struct drm_i915_private *dev_priv) +static unsigned int intel_linear_alignment(const struct drm_i915_private *dev_priv) { if (INTEL_INFO(dev_priv)->gen >= 9) return 256 * 1024; @@ -2324,6 +2337,25 @@ static unsigned int intel_linear_alignment(struct drm_i915_private *dev_priv) return 0; } +static unsigned int intel_surf_alignment(const struct drm_i915_private *dev_priv, + uint64_t fb_modifier) +{ + switch (fb_modifier) { + case DRM_FORMAT_MOD_NONE: + return intel_linear_alignment(dev_priv); + case I915_FORMAT_MOD_X_TILED: + if (INTEL_INFO(dev_priv)->gen >= 9) + return 256 * 1024; + return 0; + case I915_FORMAT_MOD_Y_TILED: + case I915_FORMAT_MOD_Yf_TILED: + return 1 * 1024 * 1024; + default: + MISSING_CASE(fb_modifier); + return 0; + } +} + int intel_pin_and_fence_fb_obj(struct drm_plane *plane, struct drm_framebuffer *fb, @@ -2338,29 +2370,7 @@ intel_pin_and_fence_fb_obj(struct drm_plane *plane, WARN_ON(!mutex_is_locked(&dev->struct_mutex)); - switch (fb->modifier[0]) { - case DRM_FORMAT_MOD_NONE: - alignment = intel_linear_alignment(dev_priv); - break; - case I915_FORMAT_MOD_X_TILED: - if (INTEL_INFO(dev)->gen >= 9) - alignment = 256 * 1024; - else { - /* pin() will align the object as required by fence */ - alignment = 0; - } - break; - case I915_FORMAT_MOD_Y_TILED: - case I915_FORMAT_MOD_Yf_TILED: - if (WARN_ONCE(INTEL_INFO(dev)->gen < 9, - "Y tiling bo slipped through, driver bug!\n")) - return -EINVAL; - alignment = 1 * 1024 * 1024; - break; - default: - MISSING_CASE(fb->modifier[0]); - return -EINVAL; - } + alignment = intel_surf_alignment(dev_priv, fb->modifier[0]); intel_fill_fb_ggtt_view(&view, fb, plane_state); @@ -2438,22 +2448,27 @@ static void intel_unpin_fb_obj(struct drm_framebuffer *fb, /* Computes the linear offset to the base tile and adjusts x, y. bytes per pixel * is assumed to be a power-of-two. */ -unsigned long intel_gen4_compute_page_offset(struct drm_i915_private *dev_priv, - int *x, int *y, - unsigned int tiling_mode, - unsigned int cpp, - unsigned int pitch) -{ - if (tiling_mode != I915_TILING_NONE) { +unsigned long intel_compute_tile_offset(struct drm_i915_private *dev_priv, + int *x, int *y, + uint64_t fb_modifier, + unsigned int cpp, + unsigned int pitch) +{ + if (fb_modifier != DRM_FORMAT_MOD_NONE) { + unsigned int tile_size, tile_width, tile_height; unsigned int tile_rows, tiles; - tile_rows = *y / 8; - *y %= 8; + tile_size = intel_tile_size(dev_priv); + tile_width = intel_tile_width(dev_priv, fb_modifier, cpp); + tile_height = tile_size / tile_width; - tiles = *x / (512/cpp); - *x %= 512/cpp; + tile_rows = *y / tile_height; + *y %= tile_height; - return tile_rows * pitch * 8 + tiles * 4096; + tiles = *x / (tile_width/cpp); + *x %= tile_width/cpp; + + return tile_rows * pitch * tile_height + tiles * tile_size; } else { unsigned int alignment = intel_linear_alignment(dev_priv) - 1; unsigned int offset; @@ -2598,6 +2613,8 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc, struct drm_plane_state *plane_state = primary->state; struct drm_crtc_state *crtc_state = intel_crtc->base.state; struct intel_plane *intel_plane = to_intel_plane(primary); + struct intel_plane_state *intel_state = + to_intel_plane_state(plane_state); struct drm_framebuffer *fb; if (!plane_config->fb) @@ -2659,6 +2676,15 @@ valid_fb: plane_state->crtc_w = fb->width; plane_state->crtc_h = fb->height; + intel_state->src.x1 = plane_state->src_x; + intel_state->src.y1 = plane_state->src_y; + intel_state->src.x2 = plane_state->src_x + plane_state->src_w; + intel_state->src.y2 = plane_state->src_y + plane_state->src_h; + intel_state->dst.x1 = plane_state->crtc_x; + intel_state->dst.y1 = plane_state->crtc_y; + intel_state->dst.x2 = plane_state->crtc_x + plane_state->crtc_w; + intel_state->dst.y2 = plane_state->crtc_y + plane_state->crtc_h; + obj = intel_fb_obj(fb); if (obj->tiling_mode != I915_TILING_NONE) dev_priv->preserve_bios_swizzle = true; @@ -2670,36 +2696,23 @@ valid_fb: obj->frontbuffer_bits |= to_intel_plane(primary)->frontbuffer_bit; } -static void i9xx_update_primary_plane(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int x, int y) +static void i9xx_update_primary_plane(struct drm_plane *primary, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { - struct drm_device *dev = crtc->dev; + struct drm_device *dev = primary->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct drm_plane *primary = crtc->primary; - bool visible = to_intel_plane_state(primary->state)->visible; - struct drm_i915_gem_object *obj; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc); + struct drm_framebuffer *fb = plane_state->base.fb; + struct drm_i915_gem_object *obj = intel_fb_obj(fb); int plane = intel_crtc->plane; unsigned long linear_offset; + int x = plane_state->src.x1 >> 16; + int y = plane_state->src.y1 >> 16; u32 dspcntr; i915_reg_t reg = DSPCNTR(plane); int pixel_size; - if (!visible || !fb) { - I915_WRITE(reg, 0); - if (INTEL_INFO(dev)->gen >= 4) - I915_WRITE(DSPSURF(plane), 0); - else - I915_WRITE(DSPADDR(plane), 0); - POSTING_READ(reg); - return; - } - - obj = intel_fb_obj(fb); - if (WARN_ON(obj == NULL)) - return; - pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); dspcntr = DISPPLANE_GAMMA_ENABLE; @@ -2714,13 +2727,13 @@ static void i9xx_update_primary_plane(struct drm_crtc *crtc, * which should always be the user's requested size. */ I915_WRITE(DSPSIZE(plane), - ((intel_crtc->config->pipe_src_h - 1) << 16) | - (intel_crtc->config->pipe_src_w - 1)); + ((crtc_state->pipe_src_h - 1) << 16) | + (crtc_state->pipe_src_w - 1)); I915_WRITE(DSPPOS(plane), 0); } else if (IS_CHERRYVIEW(dev) && plane == PLANE_B) { I915_WRITE(PRIMSIZE(plane), - ((intel_crtc->config->pipe_src_h - 1) << 16) | - (intel_crtc->config->pipe_src_w - 1)); + ((crtc_state->pipe_src_h - 1) << 16) | + (crtc_state->pipe_src_w - 1)); I915_WRITE(PRIMPOS(plane), 0); I915_WRITE(PRIMCNSTALPHA(plane), 0); } @@ -2762,26 +2775,26 @@ static void i9xx_update_primary_plane(struct drm_crtc *crtc, if (INTEL_INFO(dev)->gen >= 4) { intel_crtc->dspaddr_offset = - intel_gen4_compute_page_offset(dev_priv, - &x, &y, obj->tiling_mode, - pixel_size, - fb->pitches[0]); + intel_compute_tile_offset(dev_priv, &x, &y, + fb->modifier[0], + pixel_size, + fb->pitches[0]); linear_offset -= intel_crtc->dspaddr_offset; } else { intel_crtc->dspaddr_offset = linear_offset; } - if (crtc->primary->state->rotation == BIT(DRM_ROTATE_180)) { + if (plane_state->base.rotation == BIT(DRM_ROTATE_180)) { dspcntr |= DISPPLANE_ROTATE_180; - x += (intel_crtc->config->pipe_src_w - 1); - y += (intel_crtc->config->pipe_src_h - 1); + x += (crtc_state->pipe_src_w - 1); + y += (crtc_state->pipe_src_h - 1); /* Finding the last pixel of the last line of the display data and adding to linear_offset*/ linear_offset += - (intel_crtc->config->pipe_src_h - 1) * fb->pitches[0] + - (intel_crtc->config->pipe_src_w - 1) * pixel_size; + (crtc_state->pipe_src_h - 1) * fb->pitches[0] + + (crtc_state->pipe_src_w - 1) * pixel_size; } intel_crtc->adjusted_x = x; @@ -2800,37 +2813,40 @@ static void i9xx_update_primary_plane(struct drm_crtc *crtc, POSTING_READ(reg); } -static void ironlake_update_primary_plane(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int x, int y) +static void i9xx_disable_primary_plane(struct drm_plane *primary, + struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct drm_plane *primary = crtc->primary; - bool visible = to_intel_plane_state(primary->state)->visible; - struct drm_i915_gem_object *obj; int plane = intel_crtc->plane; - unsigned long linear_offset; - u32 dspcntr; - i915_reg_t reg = DSPCNTR(plane); - int pixel_size; - if (!visible || !fb) { - I915_WRITE(reg, 0); + I915_WRITE(DSPCNTR(plane), 0); + if (INTEL_INFO(dev_priv)->gen >= 4) I915_WRITE(DSPSURF(plane), 0); - POSTING_READ(reg); - return; - } - - obj = intel_fb_obj(fb); - if (WARN_ON(obj == NULL)) - return; + else + I915_WRITE(DSPADDR(plane), 0); + POSTING_READ(DSPCNTR(plane)); +} - pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); +static void ironlake_update_primary_plane(struct drm_plane *primary, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) +{ + struct drm_device *dev = primary->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc); + struct drm_framebuffer *fb = plane_state->base.fb; + struct drm_i915_gem_object *obj = intel_fb_obj(fb); + int plane = intel_crtc->plane; + unsigned long linear_offset; + u32 dspcntr; + i915_reg_t reg = DSPCNTR(plane); + int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); + int x = plane_state->src.x1 >> 16; + int y = plane_state->src.y1 >> 16; dspcntr = DISPPLANE_GAMMA_ENABLE; - dspcntr |= DISPLAY_PLANE_ENABLE; if (IS_HASWELL(dev) || IS_BROADWELL(dev)) @@ -2867,23 +2883,23 @@ static void ironlake_update_primary_plane(struct drm_crtc *crtc, linear_offset = y * fb->pitches[0] + x * pixel_size; intel_crtc->dspaddr_offset = - intel_gen4_compute_page_offset(dev_priv, - &x, &y, obj->tiling_mode, - pixel_size, - fb->pitches[0]); + intel_compute_tile_offset(dev_priv, &x, &y, + fb->modifier[0], + pixel_size, + fb->pitches[0]); linear_offset -= intel_crtc->dspaddr_offset; - if (crtc->primary->state->rotation == BIT(DRM_ROTATE_180)) { + if (plane_state->base.rotation == BIT(DRM_ROTATE_180)) { dspcntr |= DISPPLANE_ROTATE_180; if (!IS_HASWELL(dev) && !IS_BROADWELL(dev)) { - x += (intel_crtc->config->pipe_src_w - 1); - y += (intel_crtc->config->pipe_src_h - 1); + x += (crtc_state->pipe_src_w - 1); + y += (crtc_state->pipe_src_h - 1); /* Finding the last pixel of the last line of the display data and adding to linear_offset*/ linear_offset += - (intel_crtc->config->pipe_src_h - 1) * fb->pitches[0] + - (intel_crtc->config->pipe_src_w - 1) * pixel_size; + (crtc_state->pipe_src_h - 1) * fb->pitches[0] + + (crtc_state->pipe_src_w - 1) * pixel_size; } } @@ -2904,37 +2920,15 @@ static void ironlake_update_primary_plane(struct drm_crtc *crtc, POSTING_READ(reg); } -u32 intel_fb_stride_alignment(struct drm_device *dev, uint64_t fb_modifier, - uint32_t pixel_format) +u32 intel_fb_stride_alignment(const struct drm_i915_private *dev_priv, + uint64_t fb_modifier, uint32_t pixel_format) { - u32 bits_per_pixel = drm_format_plane_cpp(pixel_format, 0) * 8; - - /* - * The stride is either expressed as a multiple of 64 bytes - * chunks for linear buffers or in number of tiles for tiled - * buffers. - */ - switch (fb_modifier) { - case DRM_FORMAT_MOD_NONE: - return 64; - case I915_FORMAT_MOD_X_TILED: - if (INTEL_INFO(dev)->gen == 2) - return 128; - return 512; - case I915_FORMAT_MOD_Y_TILED: - /* No need to check for old gens and Y tiling since this is - * about the display engine and those will be blocked before - * we get here. - */ - return 128; - case I915_FORMAT_MOD_Yf_TILED: - if (bits_per_pixel == 8) - return 64; - else - return 128; - default: - MISSING_CASE(fb_modifier); + if (fb_modifier == DRM_FORMAT_MOD_NONE) { return 64; + } else { + int cpp = drm_format_plane_cpp(pixel_format, 0); + + return intel_tile_width(dev_priv, fb_modifier, cpp); } } @@ -3074,36 +3068,30 @@ u32 skl_plane_ctl_rotation(unsigned int rotation) return 0; } -static void skylake_update_primary_plane(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int x, int y) +static void skylake_update_primary_plane(struct drm_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { - struct drm_device *dev = crtc->dev; + struct drm_device *dev = plane->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct drm_plane *plane = crtc->primary; - bool visible = to_intel_plane_state(plane->state)->visible; - struct drm_i915_gem_object *obj; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc); + struct drm_framebuffer *fb = plane_state->base.fb; + struct drm_i915_gem_object *obj = intel_fb_obj(fb); int pipe = intel_crtc->pipe; u32 plane_ctl, stride_div, stride; u32 tile_height, plane_offset, plane_size; - unsigned int rotation; + unsigned int rotation = plane_state->base.rotation; int x_offset, y_offset; u32 surf_addr; - struct intel_crtc_state *crtc_state = intel_crtc->config; - struct intel_plane_state *plane_state; - int src_x = 0, src_y = 0, src_w = 0, src_h = 0; - int dst_x = 0, dst_y = 0, dst_w = 0, dst_h = 0; - int scaler_id = -1; - - plane_state = to_intel_plane_state(plane->state); - - if (!visible || !fb) { - I915_WRITE(PLANE_CTL(pipe, 0), 0); - I915_WRITE(PLANE_SURF(pipe, 0), 0); - POSTING_READ(PLANE_CTL(pipe, 0)); - return; - } + int scaler_id = plane_state->scaler_id; + int src_x = plane_state->src.x1 >> 16; + int src_y = plane_state->src.y1 >> 16; + int src_w = drm_rect_width(&plane_state->src) >> 16; + int src_h = drm_rect_height(&plane_state->src) >> 16; + int dst_x = plane_state->dst.x1; + int dst_y = plane_state->dst.y1; + int dst_w = drm_rect_width(&plane_state->dst); + int dst_h = drm_rect_height(&plane_state->dst); plane_ctl = PLANE_CTL_ENABLE | PLANE_CTL_PIPE_GAMMA_ENABLE | @@ -3112,41 +3100,27 @@ static void skylake_update_primary_plane(struct drm_crtc *crtc, plane_ctl |= skl_plane_ctl_format(fb->pixel_format); plane_ctl |= skl_plane_ctl_tiling(fb->modifier[0]); plane_ctl |= PLANE_CTL_PLANE_GAMMA_DISABLE; - - rotation = plane->state->rotation; plane_ctl |= skl_plane_ctl_rotation(rotation); - obj = intel_fb_obj(fb); - stride_div = intel_fb_stride_alignment(dev, fb->modifier[0], + stride_div = intel_fb_stride_alignment(dev_priv, fb->modifier[0], fb->pixel_format); surf_addr = intel_plane_obj_offset(to_intel_plane(plane), obj, 0); WARN_ON(drm_rect_width(&plane_state->src) == 0); - scaler_id = plane_state->scaler_id; - src_x = plane_state->src.x1 >> 16; - src_y = plane_state->src.y1 >> 16; - src_w = drm_rect_width(&plane_state->src) >> 16; - src_h = drm_rect_height(&plane_state->src) >> 16; - dst_x = plane_state->dst.x1; - dst_y = plane_state->dst.y1; - dst_w = drm_rect_width(&plane_state->dst); - dst_h = drm_rect_height(&plane_state->dst); - - WARN_ON(x != src_x || y != src_y); - if (intel_rotation_90_or_270(rotation)) { + int cpp = drm_format_plane_cpp(fb->pixel_format, 0); + /* stride = Surface height in tiles */ - tile_height = intel_tile_height(dev, fb->pixel_format, - fb->modifier[0], 0); + tile_height = intel_tile_height(dev_priv, fb->modifier[0], cpp); stride = DIV_ROUND_UP(fb->height, tile_height); - x_offset = stride * tile_height - y - src_h; - y_offset = x; + x_offset = stride * tile_height - src_y - src_h; + y_offset = src_x; plane_size = (src_w - 1) << 16 | (src_h - 1); } else { stride = fb->pitches[0] / stride_div; - x_offset = x; - y_offset = y; + x_offset = src_x; + y_offset = src_y; plane_size = (src_h - 1) << 16 | (src_w - 1); } plane_offset = y_offset << 16 | x_offset; @@ -3179,20 +3153,30 @@ static void skylake_update_primary_plane(struct drm_crtc *crtc, POSTING_READ(PLANE_SURF(pipe, 0)); } -/* Assume fb object is pinned & idle & fenced and just update base pointers */ -static int -intel_pipe_set_base_atomic(struct drm_crtc *crtc, struct drm_framebuffer *fb, - int x, int y, enum mode_set_atomic state) +static void skylake_disable_primary_plane(struct drm_plane *primary, + struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; + int pipe = to_intel_crtc(crtc)->pipe; if (dev_priv->fbc.deactivate) dev_priv->fbc.deactivate(dev_priv); - dev_priv->display.update_primary_plane(crtc, fb, x, y); + I915_WRITE(PLANE_CTL(pipe, 0), 0); + I915_WRITE(PLANE_SURF(pipe, 0), 0); + POSTING_READ(PLANE_SURF(pipe, 0)); +} - return 0; +/* Assume fb object is pinned & idle & fenced and just update base pointers */ +static int +intel_pipe_set_base_atomic(struct drm_crtc *crtc, struct drm_framebuffer *fb, + int x, int y, enum mode_set_atomic state) +{ + /* Support for kgdboc is disabled, this needs a major rework. */ + DRM_ERROR("legacy panic handler not supported any more.\n"); + + return -ENODEV; } static void intel_complete_page_flips(struct drm_device *dev) @@ -3219,8 +3203,10 @@ static void intel_update_primary_planes(struct drm_device *dev) drm_modeset_lock_crtc(crtc, &plane->base); plane_state = to_intel_plane_state(plane->base.state); - if (crtc->state->active && plane_state->base.fb) - plane->commit_plane(&plane->base, plane_state); + if (plane_state->visible) + plane->update_plane(&plane->base, + to_intel_crtc_state(crtc->state), + plane_state); drm_modeset_unlock_crtc(crtc); } @@ -4452,7 +4438,7 @@ int skl_update_scaler_crtc(struct intel_crtc_state *state) intel_crtc->base.base.id, intel_crtc->pipe, SKL_CRTC_INDEX); return skl_update_scaler(state, !state->base.active, SKL_CRTC_INDEX, - &state->scaler_state.scaler_id, DRM_ROTATE_0, + &state->scaler_state.scaler_id, BIT(DRM_ROTATE_0), state->pipe_src_w, state->pipe_src_h, adjusted_mode->crtc_hdisplay, adjusted_mode->crtc_vdisplay); } @@ -5370,6 +5356,7 @@ static void modeset_put_power_domains(struct drm_i915_private *dev_priv, static void modeset_update_crtc_power_domains(struct drm_atomic_state *state) { + struct intel_atomic_state *intel_state = to_intel_atomic_state(state); struct drm_device *dev = state->dev; struct drm_i915_private *dev_priv = dev->dev_private; unsigned long put_domains[I915_MAX_PIPES] = {}; @@ -5383,13 +5370,9 @@ static void modeset_update_crtc_power_domains(struct drm_atomic_state *state) modeset_get_crtc_power_domains(crtc); } - if (dev_priv->display.modeset_commit_cdclk) { - unsigned int cdclk = to_intel_atomic_state(state)->cdclk; - - if (cdclk != dev_priv->cdclk_freq && - !WARN_ON(!state->allow_modeset)) - dev_priv->display.modeset_commit_cdclk(state); - } + if (dev_priv->display.modeset_commit_cdclk && + intel_state->dev_cdclk != dev_priv->cdclk_freq) + dev_priv->display.modeset_commit_cdclk(state); for (i = 0; i < I915_MAX_PIPES; i++) if (put_domains[i]) @@ -6063,22 +6046,31 @@ static int broxton_calc_cdclk(struct drm_i915_private *dev_priv, static int intel_mode_max_pixclk(struct drm_device *dev, struct drm_atomic_state *state) { - struct intel_crtc *intel_crtc; - struct intel_crtc_state *crtc_state; - int max_pixclk = 0; + struct intel_atomic_state *intel_state = to_intel_atomic_state(state); + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_crtc *crtc; + struct drm_crtc_state *crtc_state; + unsigned max_pixclk = 0, i; + enum pipe pipe; - for_each_intel_crtc(dev, intel_crtc) { - crtc_state = intel_atomic_get_crtc_state(state, intel_crtc); - if (IS_ERR(crtc_state)) - return PTR_ERR(crtc_state); + memcpy(intel_state->min_pixclk, dev_priv->min_pixclk, + sizeof(intel_state->min_pixclk)); - if (!crtc_state->base.enable) - continue; + for_each_crtc_in_state(state, crtc, crtc_state, i) { + int pixclk = 0; - max_pixclk = max(max_pixclk, - crtc_state->base.adjusted_mode.crtc_clock); + if (crtc_state->enable) + pixclk = crtc_state->adjusted_mode.crtc_clock; + + intel_state->min_pixclk[i] = pixclk; } + if (!intel_state->active_crtcs) + return 0; + + for_each_pipe(dev_priv, pipe) + max_pixclk = max(intel_state->min_pixclk[pipe], max_pixclk); + return max_pixclk; } @@ -6087,13 +6079,18 @@ static int valleyview_modeset_calc_cdclk(struct drm_atomic_state *state) struct drm_device *dev = state->dev; struct drm_i915_private *dev_priv = dev->dev_private; int max_pixclk = intel_mode_max_pixclk(dev, state); + struct intel_atomic_state *intel_state = + to_intel_atomic_state(state); if (max_pixclk < 0) return max_pixclk; - to_intel_atomic_state(state)->cdclk = + intel_state->cdclk = intel_state->dev_cdclk = valleyview_calc_cdclk(dev_priv, max_pixclk); + if (!intel_state->active_crtcs) + intel_state->dev_cdclk = valleyview_calc_cdclk(dev_priv, 0); + return 0; } @@ -6102,13 +6099,18 @@ static int broxton_modeset_calc_cdclk(struct drm_atomic_state *state) struct drm_device *dev = state->dev; struct drm_i915_private *dev_priv = dev->dev_private; int max_pixclk = intel_mode_max_pixclk(dev, state); + struct intel_atomic_state *intel_state = + to_intel_atomic_state(state); if (max_pixclk < 0) return max_pixclk; - to_intel_atomic_state(state)->cdclk = + intel_state->cdclk = intel_state->dev_cdclk = broxton_calc_cdclk(dev_priv, max_pixclk); + if (!intel_state->active_crtcs) + intel_state->dev_cdclk = broxton_calc_cdclk(dev_priv, 0); + return 0; } @@ -6151,8 +6153,10 @@ static void vlv_program_pfi_credits(struct drm_i915_private *dev_priv) static void valleyview_modeset_commit_cdclk(struct drm_atomic_state *old_state) { struct drm_device *dev = old_state->dev; - unsigned int req_cdclk = to_intel_atomic_state(old_state)->cdclk; struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_atomic_state *old_intel_state = + to_intel_atomic_state(old_state); + unsigned req_cdclk = old_intel_state->dev_cdclk; /* * FIXME: We can end up here with all power domains off, yet @@ -6383,6 +6387,9 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc) for_each_power_domain(domain, domains) intel_display_power_put(dev_priv, domain); intel_crtc->enabled_power_domains = 0; + + dev_priv->active_crtcs &= ~(1 << intel_crtc->pipe); + dev_priv->min_pixclk[intel_crtc->pipe] = 0; } /* @@ -7593,26 +7600,34 @@ static void chv_prepare_pll(struct intel_crtc *crtc, * in cases where we need the PLL enabled even when @pipe is not going to * be enabled. */ -void vlv_force_pll_on(struct drm_device *dev, enum pipe pipe, - const struct dpll *dpll) +int vlv_force_pll_on(struct drm_device *dev, enum pipe pipe, + const struct dpll *dpll) { struct intel_crtc *crtc = to_intel_crtc(intel_get_crtc_for_pipe(dev, pipe)); - struct intel_crtc_state pipe_config = { - .base.crtc = &crtc->base, - .pixel_multiplier = 1, - .dpll = *dpll, - }; + struct intel_crtc_state *pipe_config; + + pipe_config = kzalloc(sizeof(*pipe_config), GFP_KERNEL); + if (!pipe_config) + return -ENOMEM; + + pipe_config->base.crtc = &crtc->base; + pipe_config->pixel_multiplier = 1; + pipe_config->dpll = *dpll; if (IS_CHERRYVIEW(dev)) { - chv_compute_dpll(crtc, &pipe_config); - chv_prepare_pll(crtc, &pipe_config); - chv_enable_pll(crtc, &pipe_config); + chv_compute_dpll(crtc, pipe_config); + chv_prepare_pll(crtc, pipe_config); + chv_enable_pll(crtc, pipe_config); } else { - vlv_compute_dpll(crtc, &pipe_config); - vlv_prepare_pll(crtc, &pipe_config); - vlv_enable_pll(crtc, &pipe_config); + vlv_compute_dpll(crtc, pipe_config); + vlv_prepare_pll(crtc, pipe_config); + vlv_enable_pll(crtc, pipe_config); } + + kfree(pipe_config); + + return 0; } /** @@ -9246,7 +9261,7 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc, fb->width = ((val >> 0) & 0x1fff) + 1; val = I915_READ(PLANE_STRIDE(pipe, 0)); - stride_mult = intel_fb_stride_alignment(dev, fb->modifier[0], + stride_mult = intel_fb_stride_alignment(dev_priv, fb->modifier[0], fb->pixel_format); fb->pitches[0] = (val & 0x3ff) * stride_mult; @@ -9662,14 +9677,14 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv) val |= PCH_LP_PARTITION_LEVEL_DISABLE; I915_WRITE(SOUTH_DSPCLK_GATE_D, val); } - - intel_prepare_ddi(dev); } static void broxton_modeset_commit_cdclk(struct drm_atomic_state *old_state) { struct drm_device *dev = old_state->dev; - unsigned int req_cdclk = to_intel_atomic_state(old_state)->cdclk; + struct intel_atomic_state *old_intel_state = + to_intel_atomic_state(old_state); + unsigned int req_cdclk = old_intel_state->dev_cdclk; broxton_set_cdclk(dev, req_cdclk); } @@ -9677,29 +9692,41 @@ static void broxton_modeset_commit_cdclk(struct drm_atomic_state *old_state) /* compute the max rate for new configuration */ static int ilk_max_pixel_rate(struct drm_atomic_state *state) { - struct intel_crtc *intel_crtc; + struct intel_atomic_state *intel_state = to_intel_atomic_state(state); + struct drm_i915_private *dev_priv = state->dev->dev_private; + struct drm_crtc *crtc; + struct drm_crtc_state *cstate; struct intel_crtc_state *crtc_state; - int max_pixel_rate = 0; + unsigned max_pixel_rate = 0, i; + enum pipe pipe; - for_each_intel_crtc(state->dev, intel_crtc) { - int pixel_rate; + memcpy(intel_state->min_pixclk, dev_priv->min_pixclk, + sizeof(intel_state->min_pixclk)); - crtc_state = intel_atomic_get_crtc_state(state, intel_crtc); - if (IS_ERR(crtc_state)) - return PTR_ERR(crtc_state); + for_each_crtc_in_state(state, crtc, cstate, i) { + int pixel_rate; - if (!crtc_state->base.enable) + crtc_state = to_intel_crtc_state(cstate); + if (!crtc_state->base.enable) { + intel_state->min_pixclk[i] = 0; continue; + } pixel_rate = ilk_pipe_pixel_rate(crtc_state); /* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */ - if (IS_BROADWELL(state->dev) && crtc_state->ips_enabled) + if (IS_BROADWELL(dev_priv) && crtc_state->ips_enabled) pixel_rate = DIV_ROUND_UP(pixel_rate * 100, 95); - max_pixel_rate = max(max_pixel_rate, pixel_rate); + intel_state->min_pixclk[i] = pixel_rate; } + if (!intel_state->active_crtcs) + return 0; + + for_each_pipe(dev_priv, pipe) + max_pixel_rate = max(intel_state->min_pixclk[pipe], max_pixel_rate); + return max_pixel_rate; } @@ -9783,6 +9810,7 @@ static void broadwell_set_cdclk(struct drm_device *dev, int cdclk) static int broadwell_modeset_calc_cdclk(struct drm_atomic_state *state) { struct drm_i915_private *dev_priv = to_i915(state->dev); + struct intel_atomic_state *intel_state = to_intel_atomic_state(state); int max_pixclk = ilk_max_pixel_rate(state); int cdclk; @@ -9805,7 +9833,9 @@ static int broadwell_modeset_calc_cdclk(struct drm_atomic_state *state) return -EINVAL; } - to_intel_atomic_state(state)->cdclk = cdclk; + intel_state->cdclk = intel_state->dev_cdclk = cdclk; + if (!intel_state->active_crtcs) + intel_state->dev_cdclk = 337500; return 0; } @@ -9813,7 +9843,9 @@ static int broadwell_modeset_calc_cdclk(struct drm_atomic_state *state) static void broadwell_modeset_commit_cdclk(struct drm_atomic_state *old_state) { struct drm_device *dev = old_state->dev; - unsigned int req_cdclk = to_intel_atomic_state(old_state)->cdclk; + struct intel_atomic_state *old_intel_state = + to_intel_atomic_state(old_state); + unsigned req_cdclk = old_intel_state->dev_cdclk; broadwell_set_cdclk(dev, req_cdclk); } @@ -10026,16 +10058,17 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, return true; } -static void i845_update_cursor(struct drm_crtc *crtc, u32 base, bool on) +static void i845_update_cursor(struct drm_crtc *crtc, u32 base, + const struct intel_plane_state *plane_state) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); uint32_t cntl = 0, size = 0; - if (on) { - unsigned int width = intel_crtc->base.cursor->state->crtc_w; - unsigned int height = intel_crtc->base.cursor->state->crtc_h; + if (plane_state && plane_state->visible) { + unsigned int width = plane_state->base.crtc_w; + unsigned int height = plane_state->base.crtc_h; unsigned int stride = roundup_pow_of_two(width) * 4; switch (stride) { @@ -10088,7 +10121,8 @@ static void i845_update_cursor(struct drm_crtc *crtc, u32 base, bool on) } } -static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base, bool on) +static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base, + const struct intel_plane_state *plane_state) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -10096,9 +10130,9 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base, bool on) int pipe = intel_crtc->pipe; uint32_t cntl = 0; - if (on) { + if (plane_state && plane_state->visible) { cntl = MCURSOR_GAMMA_ENABLE; - switch (intel_crtc->base.cursor->state->crtc_w) { + switch (plane_state->base.crtc_w) { case 64: cntl |= CURSOR_MODE_64_ARGB_AX; break; @@ -10109,17 +10143,17 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base, bool on) cntl |= CURSOR_MODE_256_ARGB_AX; break; default: - MISSING_CASE(intel_crtc->base.cursor->state->crtc_w); + MISSING_CASE(plane_state->base.crtc_w); return; } cntl |= pipe << 28; /* Connect to correct pipe */ if (HAS_DDI(dev)) cntl |= CURSOR_PIPE_CSC_ENABLE; - } - if (crtc->cursor->state->rotation == BIT(DRM_ROTATE_180)) - cntl |= CURSOR_ROTATE_180; + if (plane_state->base.rotation == BIT(DRM_ROTATE_180)) + cntl |= CURSOR_ROTATE_180; + } if (intel_crtc->cursor_cntl != cntl) { I915_WRITE(CURCNTR(pipe), cntl); @@ -10136,56 +10170,45 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base, bool on) /* If no-part of the cursor is visible on the framebuffer, then the GPU may hang... */ static void intel_crtc_update_cursor(struct drm_crtc *crtc, - bool on) + const struct intel_plane_state *plane_state) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int pipe = intel_crtc->pipe; - struct drm_plane_state *cursor_state = crtc->cursor->state; - int x = cursor_state->crtc_x; - int y = cursor_state->crtc_y; - u32 base = 0, pos = 0; - - base = intel_crtc->cursor_addr; + u32 base = intel_crtc->cursor_addr; + u32 pos = 0; - if (x >= intel_crtc->config->pipe_src_w) - on = false; + if (plane_state) { + int x = plane_state->base.crtc_x; + int y = plane_state->base.crtc_y; - if (y >= intel_crtc->config->pipe_src_h) - on = false; - - if (x < 0) { - if (x + cursor_state->crtc_w <= 0) - on = false; - - pos |= CURSOR_POS_SIGN << CURSOR_X_SHIFT; - x = -x; - } - pos |= x << CURSOR_X_SHIFT; + if (x < 0) { + pos |= CURSOR_POS_SIGN << CURSOR_X_SHIFT; + x = -x; + } + pos |= x << CURSOR_X_SHIFT; - if (y < 0) { - if (y + cursor_state->crtc_h <= 0) - on = false; + if (y < 0) { + pos |= CURSOR_POS_SIGN << CURSOR_Y_SHIFT; + y = -y; + } + pos |= y << CURSOR_Y_SHIFT; - pos |= CURSOR_POS_SIGN << CURSOR_Y_SHIFT; - y = -y; + /* ILK+ do this automagically */ + if (HAS_GMCH_DISPLAY(dev) && + plane_state->base.rotation == BIT(DRM_ROTATE_180)) { + base += (plane_state->base.crtc_h * + plane_state->base.crtc_w - 1) * 4; + } } - pos |= y << CURSOR_Y_SHIFT; I915_WRITE(CURPOS(pipe), pos); - /* ILK+ do this automagically */ - if (HAS_GMCH_DISPLAY(dev) && - crtc->cursor->state->rotation == BIT(DRM_ROTATE_180)) { - base += (cursor_state->crtc_h * - cursor_state->crtc_w - 1) * 4; - } - if (IS_845G(dev) || IS_I865G(dev)) - i845_update_cursor(crtc, base, on); + i845_update_cursor(crtc, base, plane_state); else - i9xx_update_cursor(crtc, base, on); + i9xx_update_cursor(crtc, base, plane_state); } static bool cursor_size_ok(struct drm_device *dev, @@ -10778,7 +10801,7 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev, struct intel_crtc *intel_crtc = to_intel_crtc(crtc); enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder; struct drm_display_mode *mode; - struct intel_crtc_state pipe_config; + struct intel_crtc_state *pipe_config; int htot = I915_READ(HTOTAL(cpu_transcoder)); int hsync = I915_READ(HSYNC(cpu_transcoder)); int vtot = I915_READ(VTOTAL(cpu_transcoder)); @@ -10789,6 +10812,12 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev, if (!mode) return NULL; + pipe_config = kzalloc(sizeof(*pipe_config), GFP_KERNEL); + if (!pipe_config) { + kfree(mode); + return NULL; + } + /* * Construct a pipe_config sufficient for getting the clock info * back out of crtc_clock_get. @@ -10796,14 +10825,14 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev, * Note, if LVDS ever uses a non-1 pixel multiplier, we'll need * to use a real value here instead. */ - pipe_config.cpu_transcoder = (enum transcoder) pipe; - pipe_config.pixel_multiplier = 1; - pipe_config.dpll_hw_state.dpll = I915_READ(DPLL(pipe)); - pipe_config.dpll_hw_state.fp0 = I915_READ(FP0(pipe)); - pipe_config.dpll_hw_state.fp1 = I915_READ(FP1(pipe)); - i9xx_crtc_clock_get(intel_crtc, &pipe_config); - - mode->clock = pipe_config.port_clock / pipe_config.pixel_multiplier; + pipe_config->cpu_transcoder = (enum transcoder) pipe; + pipe_config->pixel_multiplier = 1; + pipe_config->dpll_hw_state.dpll = I915_READ(DPLL(pipe)); + pipe_config->dpll_hw_state.fp0 = I915_READ(FP0(pipe)); + pipe_config->dpll_hw_state.fp1 = I915_READ(FP1(pipe)); + i9xx_crtc_clock_get(intel_crtc, pipe_config); + + mode->clock = pipe_config->port_clock / pipe_config->pixel_multiplier; mode->hdisplay = (htot & 0xffff) + 1; mode->htotal = ((htot & 0xffff0000) >> 16) + 1; mode->hsync_start = (hsync & 0xffff) + 1; @@ -10815,6 +10844,8 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev, drm_mode_set_name(mode); + kfree(pipe_config); + return mode; } @@ -11319,13 +11350,12 @@ static void skl_do_mmio_flip(struct intel_crtc *intel_crtc, */ if (intel_rotation_90_or_270(rotation)) { /* stride = Surface height in tiles */ - tile_height = intel_tile_height(dev, fb->pixel_format, - fb->modifier[0], 0); + tile_height = intel_tile_height(dev_priv, fb->modifier[0], 0); stride = DIV_ROUND_UP(fb->height, tile_height); } else { stride = fb->pitches[0] / - intel_fb_stride_alignment(dev, fb->modifier[0], - fb->pixel_format); + intel_fb_stride_alignment(dev_priv, fb->modifier[0], + fb->pixel_format); } /* @@ -11660,9 +11690,11 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, obj->last_write_req); } else { if (!request) { - ret = i915_gem_request_alloc(ring, ring->default_context, &request); - if (ret) + request = i915_gem_request_alloc(ring, NULL); + if (IS_ERR(request)) { + ret = PTR_ERR(request); goto cleanup_unpin; + } } ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, request, @@ -11831,8 +11863,13 @@ int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state, if (!was_crtc_enabled && WARN_ON(was_visible)) was_visible = false; - if (!is_crtc_enabled && WARN_ON(visible)) - visible = false; + /* + * Visibility is calculated as if the crtc was on, but + * after scaler setup everything depends on it being off + * when the crtc isn't active. + */ + if (!is_crtc_enabled) + to_intel_plane_state(plane_state)->visible = visible = false; if (!was_visible && !visible) return 0; @@ -12529,19 +12566,22 @@ intel_compare_m_n(unsigned int m, unsigned int n, BUILD_BUG_ON(DATA_LINK_M_N_MASK > INT_MAX); - if (m > m2) { - while (m > m2) { + if (n > n2) { + while (n > n2) { m2 <<= 1; n2 <<= 1; } - } else if (m < m2) { - while (m < m2) { + } else if (n < n2) { + while (n < n2) { m <<= 1; n <<= 1; } } - return m == m2 && n == n2; + if (n != n2) + return false; + + return intel_fuzzy_clock_check(m, m2); } static bool @@ -13216,15 +13256,27 @@ static int intel_modeset_all_pipes(struct drm_atomic_state *state) static int intel_modeset_checks(struct drm_atomic_state *state) { - struct drm_device *dev = state->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - int ret; + struct intel_atomic_state *intel_state = to_intel_atomic_state(state); + struct drm_i915_private *dev_priv = state->dev->dev_private; + struct drm_crtc *crtc; + struct drm_crtc_state *crtc_state; + int ret = 0, i; if (!check_digital_port_conflicts(state)) { DRM_DEBUG_KMS("rejecting conflicting digital port configuration\n"); return -EINVAL; } + intel_state->modeset = true; + intel_state->active_crtcs = dev_priv->active_crtcs; + + for_each_crtc_in_state(state, crtc, crtc_state, i) { + if (crtc_state->active) + intel_state->active_crtcs |= 1 << i; + else + intel_state->active_crtcs &= ~(1 << i); + } + /* * See if the config requires any additional preparation, e.g. * to adjust global state with pipes off. We need to do this @@ -13233,22 +13285,19 @@ static int intel_modeset_checks(struct drm_atomic_state *state) * adjusted_mode bits in the crtc directly. */ if (dev_priv->display.modeset_calc_cdclk) { - unsigned int cdclk; - ret = dev_priv->display.modeset_calc_cdclk(state); - cdclk = to_intel_atomic_state(state)->cdclk; - if (!ret && cdclk != dev_priv->cdclk_freq) + if (!ret && intel_state->dev_cdclk != dev_priv->cdclk_freq) ret = intel_modeset_all_pipes(state); if (ret < 0) return ret; } else - to_intel_atomic_state(state)->cdclk = dev_priv->cdclk_freq; + to_intel_atomic_state(state)->cdclk = dev_priv->atomic_cdclk_freq; intel_modeset_clear_plls(state); - if (IS_HASWELL(dev)) + if (IS_HASWELL(dev_priv)) return haswell_mode_set_planes_workaround(state); return 0; @@ -13466,12 +13515,12 @@ static int intel_atomic_commit(struct drm_device *dev, struct drm_atomic_state *state, bool async) { + struct intel_atomic_state *intel_state = to_intel_atomic_state(state); struct drm_i915_private *dev_priv = dev->dev_private; struct drm_crtc_state *crtc_state; struct drm_crtc *crtc; - int ret = 0; - int i; - bool any_ms = false; + int ret = 0, i; + bool hw_check = intel_state->modeset; ret = intel_atomic_prepare_commit(dev, state, async); if (ret) { @@ -13482,13 +13531,19 @@ static int intel_atomic_commit(struct drm_device *dev, drm_atomic_helper_swap_state(dev, state); dev_priv->wm.config = to_intel_atomic_state(state)->wm_config; + if (intel_state->modeset) { + memcpy(dev_priv->min_pixclk, intel_state->min_pixclk, + sizeof(intel_state->min_pixclk)); + dev_priv->active_crtcs = intel_state->active_crtcs; + dev_priv->atomic_cdclk_freq = intel_state->cdclk; + } + for_each_crtc_in_state(state, crtc, crtc_state, i) { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); if (!needs_modeset(crtc->state)) continue; - any_ms = true; intel_pre_plane_update(intel_crtc); if (crtc_state->active) { @@ -13513,7 +13568,7 @@ static int intel_atomic_commit(struct drm_device *dev, * update the the output configuration. */ intel_modeset_update_crtc_state(state); - if (any_ms) { + if (intel_state->modeset) { intel_shared_dpll_commit(state); drm_atomic_helper_update_legacy_modeset_state(state->dev, state); @@ -13540,7 +13595,7 @@ static int intel_atomic_commit(struct drm_device *dev, put_domains = modeset_get_crtc_power_domains(crtc); /* make sure intel_modeset_check_state runs */ - any_ms = true; + hw_check = true; } if (!modeset) @@ -13567,11 +13622,24 @@ static int intel_atomic_commit(struct drm_device *dev, drm_atomic_helper_cleanup_planes(dev, state); mutex_unlock(&dev->struct_mutex); - if (any_ms) + if (hw_check) intel_modeset_check_state(dev, state); drm_atomic_state_free(state); + /* As one of the primary mmio accessors, KMS has a high likelihood + * of triggering bugs in unclaimed access. After we finish + * modesetting, see if an error has been flagged, and if so + * enable debugging for the next modeset - and hope we catch + * the culprit. + * + * XXX note that we assume display power is on at this point. + * This might hold true now but we need to add pm helper to check + * unclaimed only when the hardware is on, as atomic commits + * can happen also when the device is completely off. + */ + intel_uncore_arm_unclaimed_mmio_detection(dev_priv); + return 0; } @@ -13860,7 +13928,7 @@ skl_max_scale(struct intel_crtc *intel_crtc, struct intel_crtc_state *crtc_state struct drm_i915_private *dev_priv; int crtc_clock, cdclk; - if (!intel_crtc || !crtc_state) + if (!intel_crtc || !crtc_state->base.enable) return DRM_PLANE_HELPER_NO_SCALING; dev = intel_crtc->base.dev; @@ -13909,32 +13977,6 @@ intel_check_primary_plane(struct drm_plane *plane, &state->visible); } -static void -intel_commit_primary_plane(struct drm_plane *plane, - struct intel_plane_state *state) -{ - struct drm_crtc *crtc = state->base.crtc; - struct drm_framebuffer *fb = state->base.fb; - struct drm_device *dev = plane->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - - crtc = crtc ? crtc : plane->crtc; - - dev_priv->display.update_primary_plane(crtc, fb, - state->src.x1 >> 16, - state->src.y1 >> 16); -} - -static void -intel_disable_primary_plane(struct drm_plane *plane, - struct drm_crtc *crtc) -{ - struct drm_device *dev = plane->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - - dev_priv->display.update_primary_plane(crtc, NULL, 0, 0); -} - static void intel_begin_crtc_commit(struct drm_crtc *crtc, struct drm_crtc_state *old_crtc_state) { @@ -14019,20 +14061,33 @@ static struct drm_plane *intel_primary_plane_create(struct drm_device *dev, primary->plane = pipe; primary->frontbuffer_bit = INTEL_FRONTBUFFER_PRIMARY(pipe); primary->check_plane = intel_check_primary_plane; - primary->commit_plane = intel_commit_primary_plane; - primary->disable_plane = intel_disable_primary_plane; if (HAS_FBC(dev) && INTEL_INFO(dev)->gen < 4) primary->plane = !pipe; if (INTEL_INFO(dev)->gen >= 9) { intel_primary_formats = skl_primary_formats; num_formats = ARRAY_SIZE(skl_primary_formats); + + primary->update_plane = skylake_update_primary_plane; + primary->disable_plane = skylake_disable_primary_plane; + } else if (HAS_PCH_SPLIT(dev)) { + intel_primary_formats = i965_primary_formats; + num_formats = ARRAY_SIZE(i965_primary_formats); + + primary->update_plane = ironlake_update_primary_plane; + primary->disable_plane = i9xx_disable_primary_plane; } else if (INTEL_INFO(dev)->gen >= 4) { intel_primary_formats = i965_primary_formats; num_formats = ARRAY_SIZE(i965_primary_formats); + + primary->update_plane = i9xx_update_primary_plane; + primary->disable_plane = i9xx_disable_primary_plane; } else { intel_primary_formats = i8xx_primary_formats; num_formats = ARRAY_SIZE(i8xx_primary_formats); + + primary->update_plane = i9xx_update_primary_plane; + primary->disable_plane = i9xx_disable_primary_plane; } drm_universal_plane_init(dev, &primary->base, 0, @@ -14131,22 +14186,23 @@ static void intel_disable_cursor_plane(struct drm_plane *plane, struct drm_crtc *crtc) { - intel_crtc_update_cursor(crtc, false); + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + + intel_crtc->cursor_addr = 0; + intel_crtc_update_cursor(crtc, NULL); } static void -intel_commit_cursor_plane(struct drm_plane *plane, - struct intel_plane_state *state) +intel_update_cursor_plane(struct drm_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *state) { - struct drm_crtc *crtc = state->base.crtc; + struct drm_crtc *crtc = crtc_state->base.crtc; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct drm_device *dev = plane->dev; - struct intel_crtc *intel_crtc; struct drm_i915_gem_object *obj = intel_fb_obj(state->base.fb); uint32_t addr; - crtc = crtc ? crtc : plane->crtc; - intel_crtc = to_intel_crtc(crtc); - if (!obj) addr = 0; else if (!INTEL_INFO(dev)->cursor_needs_physical) @@ -14155,9 +14211,7 @@ intel_commit_cursor_plane(struct drm_plane *plane, addr = obj->phys_handle->busaddr; intel_crtc->cursor_addr = addr; - - if (crtc->state->active) - intel_crtc_update_cursor(crtc, state->visible); + intel_crtc_update_cursor(crtc, state); } static struct drm_plane *intel_cursor_plane_create(struct drm_device *dev, @@ -14183,7 +14237,7 @@ static struct drm_plane *intel_cursor_plane_create(struct drm_device *dev, cursor->plane = pipe; cursor->frontbuffer_bit = INTEL_FRONTBUFFER_CURSOR(pipe); cursor->check_plane = intel_check_cursor_plane; - cursor->commit_plane = intel_commit_cursor_plane; + cursor->update_plane = intel_update_cursor_plane; cursor->disable_plane = intel_disable_cursor_plane; drm_universal_plane_init(dev, &cursor->base, 0, @@ -14657,6 +14711,7 @@ static int intel_framebuffer_init(struct drm_device *dev, struct drm_mode_fb_cmd2 *mode_cmd, struct drm_i915_gem_object *obj) { + struct drm_i915_private *dev_priv = to_i915(dev); unsigned int aligned_height; int ret; u32 pitch_limit, stride_alignment; @@ -14698,7 +14753,8 @@ static int intel_framebuffer_init(struct drm_device *dev, return -EINVAL; } - stride_alignment = intel_fb_stride_alignment(dev, mode_cmd->modifier[0], + stride_alignment = intel_fb_stride_alignment(dev_priv, + mode_cmd->modifier[0], mode_cmd->pixel_format); if (mode_cmd->pitches[0] & (stride_alignment - 1)) { DRM_DEBUG("pitch (%d) must be at least %u byte aligned\n", @@ -14790,7 +14846,6 @@ static int intel_framebuffer_init(struct drm_device *dev, drm_helper_mode_fill_fb_struct(&intel_fb->base, mode_cmd); intel_fb->obj = obj; - intel_fb->obj->framebuffer_references++; ret = drm_framebuffer_init(dev, &intel_fb->base, &intel_fb_funcs); if (ret) { @@ -14798,6 +14853,8 @@ static int intel_framebuffer_init(struct drm_device *dev, return ret; } + intel_fb->obj->framebuffer_references++; + return 0; } @@ -14861,8 +14918,6 @@ static void intel_init_display(struct drm_device *dev) haswell_crtc_compute_clock; dev_priv->display.crtc_enable = haswell_crtc_enable; dev_priv->display.crtc_disable = haswell_crtc_disable; - dev_priv->display.update_primary_plane = - skylake_update_primary_plane; } else if (HAS_DDI(dev)) { dev_priv->display.get_pipe_config = haswell_get_pipe_config; dev_priv->display.get_initial_plane_config = @@ -14871,8 +14926,6 @@ static void intel_init_display(struct drm_device *dev) haswell_crtc_compute_clock; dev_priv->display.crtc_enable = haswell_crtc_enable; dev_priv->display.crtc_disable = haswell_crtc_disable; - dev_priv->display.update_primary_plane = - ironlake_update_primary_plane; } else if (HAS_PCH_SPLIT(dev)) { dev_priv->display.get_pipe_config = ironlake_get_pipe_config; dev_priv->display.get_initial_plane_config = @@ -14881,8 +14934,6 @@ static void intel_init_display(struct drm_device *dev) ironlake_crtc_compute_clock; dev_priv->display.crtc_enable = ironlake_crtc_enable; dev_priv->display.crtc_disable = ironlake_crtc_disable; - dev_priv->display.update_primary_plane = - ironlake_update_primary_plane; } else if (IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) { dev_priv->display.get_pipe_config = i9xx_get_pipe_config; dev_priv->display.get_initial_plane_config = @@ -14890,8 +14941,6 @@ static void intel_init_display(struct drm_device *dev) dev_priv->display.crtc_compute_clock = i9xx_crtc_compute_clock; dev_priv->display.crtc_enable = valleyview_crtc_enable; dev_priv->display.crtc_disable = i9xx_crtc_disable; - dev_priv->display.update_primary_plane = - i9xx_update_primary_plane; } else { dev_priv->display.get_pipe_config = i9xx_get_pipe_config; dev_priv->display.get_initial_plane_config = @@ -14899,8 +14948,6 @@ static void intel_init_display(struct drm_device *dev) dev_priv->display.crtc_compute_clock = i9xx_crtc_compute_clock; dev_priv->display.crtc_enable = i9xx_crtc_enable; dev_priv->display.crtc_disable = i9xx_crtc_disable; - dev_priv->display.update_primary_plane = - i9xx_update_primary_plane; } /* Returns the core display clock speed */ @@ -15206,12 +15253,89 @@ static void i915_disable_vga(struct drm_device *dev) void intel_modeset_init_hw(struct drm_device *dev) { + struct drm_i915_private *dev_priv = dev->dev_private; + intel_update_cdclk(dev); - intel_prepare_ddi(dev); + + dev_priv->atomic_cdclk_freq = dev_priv->cdclk_freq; + intel_init_clock_gating(dev); intel_enable_gt_powersave(dev); } +/* + * Calculate what we think the watermarks should be for the state we've read + * out of the hardware and then immediately program those watermarks so that + * we ensure the hardware settings match our internal state. + * + * We can calculate what we think WM's should be by creating a duplicate of the + * current state (which was constructed during hardware readout) and running it + * through the atomic check code to calculate new watermark values in the + * state object. + */ +static void sanitize_watermarks(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_atomic_state *state; + struct drm_crtc *crtc; + struct drm_crtc_state *cstate; + struct drm_modeset_acquire_ctx ctx; + int ret; + int i; + + /* Only supported on platforms that use atomic watermark design */ + if (!dev_priv->display.program_watermarks) + return; + + /* + * We need to hold connection_mutex before calling duplicate_state so + * that the connector loop is protected. + */ + drm_modeset_acquire_init(&ctx, 0); +retry: + ret = drm_modeset_lock_all_ctx(dev, &ctx); + if (ret == -EDEADLK) { + drm_modeset_backoff(&ctx); + goto retry; + } else if (WARN_ON(ret)) { + goto fail; + } + + state = drm_atomic_helper_duplicate_state(dev, &ctx); + if (WARN_ON(IS_ERR(state))) + goto fail; + + ret = intel_atomic_check(dev, state); + if (ret) { + /* + * If we fail here, it means that the hardware appears to be + * programmed in a way that shouldn't be possible, given our + * understanding of watermark requirements. This might mean a + * mistake in the hardware readout code or a mistake in the + * watermark calculations for a given platform. Raise a WARN + * so that this is noticeable. + * + * If this actually happens, we'll have to just leave the + * BIOS-programmed watermarks untouched and hope for the best. + */ + WARN(true, "Could not determine valid watermarks for inherited state\n"); + goto fail; + } + + /* Write calculated watermark values back */ + to_i915(dev)->wm.config = to_intel_atomic_state(state)->wm_config; + for_each_crtc_in_state(state, crtc, cstate, i) { + struct intel_crtc_state *cs = to_intel_crtc_state(cstate); + + dev_priv->display.program_watermarks(cs); + } + + drm_atomic_state_free(state); +fail: + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); +} + void intel_modeset_init(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -15332,6 +15456,13 @@ void intel_modeset_init(struct drm_device *dev) */ intel_find_initial_plane_obj(crtc, &plane_config); } + + /* + * Make sure hardware watermarks really match the state we read out. + * Note that we need to do this after reconstructing the BIOS fb's + * since the watermark calculation done here will use pstate->fb. + */ + sanitize_watermarks(dev); } static void intel_enable_pipe_a(struct drm_device *dev) @@ -15604,16 +15735,40 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) struct intel_connector *connector; int i; + dev_priv->active_crtcs = 0; + for_each_intel_crtc(dev, crtc) { - __drm_atomic_helper_crtc_destroy_state(&crtc->base, crtc->base.state); - memset(crtc->config, 0, sizeof(*crtc->config)); - crtc->config->base.crtc = &crtc->base; + struct intel_crtc_state *crtc_state = crtc->config; + int pixclk = 0; - crtc->active = dev_priv->display.get_pipe_config(crtc, - crtc->config); + __drm_atomic_helper_crtc_destroy_state(&crtc->base, &crtc_state->base); + memset(crtc_state, 0, sizeof(*crtc_state)); + crtc_state->base.crtc = &crtc->base; - crtc->base.state->active = crtc->active; - crtc->base.enabled = crtc->active; + crtc_state->base.active = crtc_state->base.enable = + dev_priv->display.get_pipe_config(crtc, crtc_state); + + crtc->base.enabled = crtc_state->base.enable; + crtc->active = crtc_state->base.active; + + if (crtc_state->base.active) { + dev_priv->active_crtcs |= 1 << crtc->pipe; + + if (IS_BROADWELL(dev_priv)) { + pixclk = ilk_pipe_pixel_rate(crtc_state); + + /* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */ + if (crtc_state->ips_enabled) + pixclk = DIV_ROUND_UP(pixclk * 100, 95); + } else if (IS_VALLEYVIEW(dev_priv) || + IS_CHERRYVIEW(dev_priv) || + IS_BROXTON(dev_priv)) + pixclk = crtc_state->base.adjusted_mode.crtc_clock; + else + WARN_ON(dev_priv->display.modeset_calc_cdclk); + } + + dev_priv->min_pixclk[crtc->pipe] = pixclk; readout_plane_state(crtc); @@ -16117,7 +16272,7 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m, for_each_pipe(dev_priv, i) { err_printf(m, "Pipe [%d]:\n", i); err_printf(m, " Power: %s\n", - error->pipe[i].power_domain_on ? "on" : "off"); + onoff(error->pipe[i].power_domain_on)); err_printf(m, " SRC: %08x\n", error->pipe[i].source); err_printf(m, " STAT: %08x\n", error->pipe[i].stat); @@ -16145,7 +16300,7 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m, err_printf(m, "CPU transcoder: %c\n", transcoder_name(error->transcoder[i].cpu_transcoder)); err_printf(m, " Power: %s\n", - error->transcoder[i].power_domain_on ? "on" : "off"); + onoff(error->transcoder[i].power_domain_on)); err_printf(m, " CONF: %08x\n", error->transcoder[i].conf); err_printf(m, " HTOTAL: %08x\n", error->transcoder[i].htotal); err_printf(m, " HBLANK: %08x\n", error->transcoder[i].hblank); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 796e3d313cb9..e2bea710614f 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -157,14 +157,9 @@ intel_dp_max_link_bw(struct intel_dp *intel_dp) static u8 intel_dp_max_lane_count(struct intel_dp *intel_dp) { struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); - struct drm_device *dev = intel_dig_port->base.base.dev; u8 source_max, sink_max; - source_max = 4; - if (HAS_DDI(dev) && intel_dig_port->port == PORT_A && - (intel_dig_port->saved_port_bits & DDI_A_4_LANES) == 0) - source_max = 2; - + source_max = intel_dig_port->max_lanes; sink_max = drm_dp_max_lane_count(intel_dp->dpcd); return min(source_max, sink_max); @@ -340,8 +335,12 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp) release_cl_override = IS_CHERRYVIEW(dev) && !chv_phy_powergate_ch(dev_priv, phy, ch, true); - vlv_force_pll_on(dev, pipe, IS_CHERRYVIEW(dev) ? - &chv_dpll[0].dpll : &vlv_dpll[0].dpll); + if (vlv_force_pll_on(dev, pipe, IS_CHERRYVIEW(dev) ? + &chv_dpll[0].dpll : &vlv_dpll[0].dpll)) { + DRM_ERROR("Failed to force on pll for pipe %c!\n", + pipe_name(pipe)); + return; + } } /* @@ -2243,11 +2242,6 @@ static void intel_edp_backlight_power(struct intel_connector *connector, _intel_edp_backlight_off(intel_dp); } -static const char *state_string(bool enabled) -{ - return enabled ? "on" : "off"; -} - static void assert_dp_port(struct intel_dp *intel_dp, bool state) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); @@ -2257,7 +2251,7 @@ static void assert_dp_port(struct intel_dp *intel_dp, bool state) I915_STATE_WARN(cur_state != state, "DP port %c state assertion failure (expected %s, current %s)\n", port_name(dig_port->port), - state_string(state), state_string(cur_state)); + onoff(state), onoff(cur_state)); } #define assert_dp_port_disabled(d) assert_dp_port((d), false) @@ -2267,7 +2261,7 @@ static void assert_edp_pll(struct drm_i915_private *dev_priv, bool state) I915_STATE_WARN(cur_state != state, "eDP PLL state assertion failure (expected %s, current %s)\n", - state_string(state), state_string(cur_state)); + onoff(state), onoff(cur_state)); } #define assert_edp_pll_enabled(d) assert_edp_pll((d), true) #define assert_edp_pll_disabled(d) assert_edp_pll((d), false) @@ -5839,6 +5833,11 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port, enum port port = intel_dig_port->port; int type, ret; + if (WARN(intel_dig_port->max_lanes < 1, + "Not enough lanes (%d) for DP on port %c\n", + intel_dig_port->max_lanes, port_name(port))) + return false; + intel_dp->pps_pipe = INVALID_PIPE; /* intel_dp vfuncs */ @@ -6037,6 +6036,7 @@ intel_dp_init(struct drm_device *dev, intel_dig_port->port = port; dev_priv->dig_port_map[port] = intel_encoder; intel_dig_port->dp.output_reg = output_reg; + intel_dig_port->max_lanes = 4; intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT; if (IS_CHERRYVIEW(dev)) { diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index fa0dabf578dc..2a2ab306ad84 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -184,7 +184,9 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder) intel_mst->port = found->port; if (intel_dp->active_mst_links == 0) { - intel_ddi_clk_select(encoder, intel_crtc->config); + intel_prepare_ddi_buffer(&intel_dig_port->base); + + intel_ddi_clk_select(&intel_dig_port->base, intel_crtc->config); intel_dp_set_link_params(intel_dp, intel_crtc->config); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index ea5415851c6e..bc970125ec76 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -246,7 +246,18 @@ struct intel_atomic_state { struct drm_atomic_state base; unsigned int cdclk; - bool dpll_set; + + /* + * Calculated device cdclk, can be different from cdclk + * only when all crtc's are DPMS off. + */ + unsigned int dev_cdclk; + + bool dpll_set, modeset; + + unsigned int active_crtcs; + unsigned int min_pixclk[I915_MAX_PIPES]; + struct intel_shared_dpll_config shared_dpll[I915_NUM_PLLS]; struct intel_wm_config wm_config; }; @@ -647,23 +658,17 @@ struct intel_plane { /* * NOTE: Do not place new plane state fields here (e.g., when adding * new plane properties). New runtime state should now be placed in - * the intel_plane_state structure and accessed via drm_plane->state. + * the intel_plane_state structure and accessed via plane_state. */ void (*update_plane)(struct drm_plane *plane, - struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int crtc_x, int crtc_y, - unsigned int crtc_w, unsigned int crtc_h, - uint32_t x, uint32_t y, - uint32_t src_w, uint32_t src_h); + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state); void (*disable_plane)(struct drm_plane *plane, struct drm_crtc *crtc); int (*check_plane)(struct drm_plane *plane, struct intel_crtc_state *crtc_state, struct intel_plane_state *state); - void (*commit_plane)(struct drm_plane *plane, - struct intel_plane_state *state); }; struct intel_watermark_params { @@ -817,6 +822,7 @@ struct intel_digital_port { struct intel_hdmi hdmi; enum irqreturn (*hpd_pulse)(struct intel_digital_port *, bool); bool release_cl2_override; + uint8_t max_lanes; /* for communication with audio component; protected by av_mutex */ const struct drm_connector *audio_connector; }; @@ -996,7 +1002,7 @@ void intel_crt_init(struct drm_device *dev); /* intel_ddi.c */ void intel_ddi_clk_select(struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config); -void intel_prepare_ddi(struct drm_device *dev); +void intel_prepare_ddi_buffer(struct intel_encoder *encoder); void hsw_fdi_link_train(struct drm_crtc *crtc); void intel_ddi_init(struct drm_device *dev, enum port port); enum port intel_ddi_get_encoder_port(struct intel_encoder *intel_encoder); @@ -1041,8 +1047,8 @@ unsigned int intel_fb_align_height(struct drm_device *dev, uint64_t fb_format_modifier); void intel_fb_obj_flush(struct drm_i915_gem_object *obj, bool retire, enum fb_op_origin origin); -u32 intel_fb_stride_alignment(struct drm_device *dev, uint64_t fb_modifier, - uint32_t pixel_format); +u32 intel_fb_stride_alignment(const struct drm_i915_private *dev_priv, + uint64_t fb_modifier, uint32_t pixel_format); /* intel_audio.c */ void intel_init_audio(struct drm_device *dev); @@ -1126,9 +1132,8 @@ int intel_plane_atomic_set_property(struct drm_plane *plane, int intel_plane_atomic_calc_changes(struct drm_crtc_state *crtc_state, struct drm_plane_state *plane_state); -unsigned int -intel_tile_height(struct drm_device *dev, uint32_t pixel_format, - uint64_t fb_format_modifier, unsigned int plane); +unsigned int intel_tile_height(const struct drm_i915_private *dev_priv, + uint64_t fb_modifier, unsigned int cpp); static inline bool intel_rotation_90_or_270(unsigned int rotation) @@ -1149,8 +1154,8 @@ void assert_shared_dpll(struct drm_i915_private *dev_priv, struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc, struct intel_crtc_state *state); -void vlv_force_pll_on(struct drm_device *dev, enum pipe pipe, - const struct dpll *dpll); +int vlv_force_pll_on(struct drm_device *dev, enum pipe pipe, + const struct dpll *dpll); void vlv_force_pll_off(struct drm_device *dev, enum pipe pipe); /* modesetting asserts */ @@ -1167,11 +1172,11 @@ void assert_fdi_rx_pll(struct drm_i915_private *dev_priv, void assert_pipe(struct drm_i915_private *dev_priv, enum pipe pipe, bool state); #define assert_pipe_enabled(d, p) assert_pipe(d, p, true) #define assert_pipe_disabled(d, p) assert_pipe(d, p, false) -unsigned long intel_gen4_compute_page_offset(struct drm_i915_private *dev_priv, - int *x, int *y, - unsigned int tiling_mode, - unsigned int bpp, - unsigned int pitch); +unsigned long intel_compute_tile_offset(struct drm_i915_private *dev_priv, + int *x, int *y, + uint64_t fb_modifier, + unsigned int cpp, + unsigned int pitch); void intel_prepare_reset(struct drm_device *dev); void intel_finish_reset(struct drm_device *dev); void hsw_enable_pc8(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index 44742fa2f616..91cef3525c93 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -702,7 +702,7 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder, static void intel_dsi_get_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { - u32 pclk = 0; + u32 pclk; DRM_DEBUG_KMS("\n"); pipe_config->has_dsi_encoder = true; @@ -713,12 +713,7 @@ static void intel_dsi_get_config(struct intel_encoder *encoder, */ pipe_config->dpll_hw_state.dpll_md = 0; - if (IS_BROXTON(encoder->base.dev)) - pclk = bxt_get_dsi_pclk(encoder, pipe_config->pipe_bpp); - else if (IS_VALLEYVIEW(encoder->base.dev) || - IS_CHERRYVIEW(encoder->base.dev)) - pclk = vlv_get_dsi_pclk(encoder, pipe_config->pipe_bpp); - + pclk = intel_dsi_get_pclk(encoder, pipe_config->pipe_bpp); if (!pclk) return; diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h index 02551ff228c2..de7be7f3fb42 100644 --- a/drivers/gpu/drm/i915/intel_dsi.h +++ b/drivers/gpu/drm/i915/intel_dsi.h @@ -126,8 +126,7 @@ static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder) extern void intel_enable_dsi_pll(struct intel_encoder *encoder); extern void intel_disable_dsi_pll(struct intel_encoder *encoder); -extern u32 vlv_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp); -extern u32 bxt_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp); +extern u32 intel_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp); extern void intel_dsi_reset_clocks(struct intel_encoder *encoder, enum port port); diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c index a5e99ac305da..1d43e6f37fc1 100644 --- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c +++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c @@ -229,14 +229,18 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) return data; } +static const u8 *mipi_exec_i2c_skip(struct intel_dsi *intel_dsi, const u8 *data) +{ + return data + *(data + 6) + 7; +} + typedef const u8 * (*fn_mipi_elem_exec)(struct intel_dsi *intel_dsi, const u8 *data); static const fn_mipi_elem_exec exec_elem[] = { - NULL, /* reserved */ - mipi_exec_send_packet, - mipi_exec_delay, - mipi_exec_gpio, - NULL, /* status read; later */ + [MIPI_SEQ_ELEM_SEND_PKT] = mipi_exec_send_packet, + [MIPI_SEQ_ELEM_DELAY] = mipi_exec_delay, + [MIPI_SEQ_ELEM_GPIO] = mipi_exec_gpio, + [MIPI_SEQ_ELEM_I2C] = mipi_exec_i2c_skip, }; /* @@ -246,107 +250,114 @@ static const fn_mipi_elem_exec exec_elem[] = { */ static const char * const seq_name[] = { - "UNDEFINED", - "MIPI_SEQ_ASSERT_RESET", - "MIPI_SEQ_INIT_OTP", - "MIPI_SEQ_DISPLAY_ON", - "MIPI_SEQ_DISPLAY_OFF", - "MIPI_SEQ_DEASSERT_RESET" + [MIPI_SEQ_ASSERT_RESET] = "MIPI_SEQ_ASSERT_RESET", + [MIPI_SEQ_INIT_OTP] = "MIPI_SEQ_INIT_OTP", + [MIPI_SEQ_DISPLAY_ON] = "MIPI_SEQ_DISPLAY_ON", + [MIPI_SEQ_DISPLAY_OFF] = "MIPI_SEQ_DISPLAY_OFF", + [MIPI_SEQ_DEASSERT_RESET] = "MIPI_SEQ_DEASSERT_RESET", + [MIPI_SEQ_BACKLIGHT_ON] = "MIPI_SEQ_BACKLIGHT_ON", + [MIPI_SEQ_BACKLIGHT_OFF] = "MIPI_SEQ_BACKLIGHT_OFF", + [MIPI_SEQ_TEAR_ON] = "MIPI_SEQ_TEAR_ON", + [MIPI_SEQ_TEAR_OFF] = "MIPI_SEQ_TEAR_OFF", + [MIPI_SEQ_POWER_ON] = "MIPI_SEQ_POWER_ON", + [MIPI_SEQ_POWER_OFF] = "MIPI_SEQ_POWER_OFF", }; -static void generic_exec_sequence(struct intel_dsi *intel_dsi, const u8 *data) +static const char *sequence_name(enum mipi_seq seq_id) { + if (seq_id < ARRAY_SIZE(seq_name) && seq_name[seq_id]) + return seq_name[seq_id]; + else + return "(unknown)"; +} + +static void generic_exec_sequence(struct drm_panel *panel, enum mipi_seq seq_id) +{ + struct vbt_panel *vbt_panel = to_vbt_panel(panel); + struct intel_dsi *intel_dsi = vbt_panel->intel_dsi; + struct drm_i915_private *dev_priv = to_i915(intel_dsi->base.base.dev); + const u8 *data; fn_mipi_elem_exec mipi_elem_exec; - int index; - if (!data) + if (WARN_ON(seq_id >= ARRAY_SIZE(dev_priv->vbt.dsi.sequence))) + return; + + data = dev_priv->vbt.dsi.sequence[seq_id]; + if (!data) { + DRM_DEBUG_KMS("MIPI sequence %d - %s not available\n", + seq_id, sequence_name(seq_id)); return; + } - DRM_DEBUG_DRIVER("Starting MIPI sequence - %s\n", seq_name[*data]); + WARN_ON(*data != seq_id); - /* go to the first element of the sequence */ - data++; + DRM_DEBUG_KMS("Starting MIPI sequence %d - %s\n", + seq_id, sequence_name(seq_id)); - /* parse each byte till we reach end of sequence byte - 0x00 */ - while (1) { - index = *data; - mipi_elem_exec = exec_elem[index]; - if (!mipi_elem_exec) { - DRM_ERROR("Unsupported MIPI element, skipping sequence execution\n"); - return; - } + /* Skip Sequence Byte. */ + data++; - /* goto element payload */ - data++; + /* Skip Size of Sequence. */ + if (dev_priv->vbt.dsi.seq_version >= 3) + data += 4; - /* execute the element specific rotines */ - data = mipi_elem_exec(intel_dsi, data); + while (1) { + u8 operation_byte = *data++; + u8 operation_size = 0; - /* - * After processing the element, data should point to - * next element or end of sequence - * check if have we reached end of sequence - */ - if (*data == 0x00) + if (operation_byte == MIPI_SEQ_ELEM_END) break; + + if (operation_byte < ARRAY_SIZE(exec_elem)) + mipi_elem_exec = exec_elem[operation_byte]; + else + mipi_elem_exec = NULL; + + /* Size of Operation. */ + if (dev_priv->vbt.dsi.seq_version >= 3) + operation_size = *data++; + + if (mipi_elem_exec) { + data = mipi_elem_exec(intel_dsi, data); + } else if (operation_size) { + /* We have size, skip. */ + DRM_DEBUG_KMS("Unsupported MIPI operation byte %u\n", + operation_byte); + data += operation_size; + } else { + /* No size, can't skip without parsing. */ + DRM_ERROR("Unsupported MIPI operation byte %u\n", + operation_byte); + return; + } } } static int vbt_panel_prepare(struct drm_panel *panel) { - struct vbt_panel *vbt_panel = to_vbt_panel(panel); - struct intel_dsi *intel_dsi = vbt_panel->intel_dsi; - struct drm_device *dev = intel_dsi->base.base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - const u8 *sequence; - - sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_ASSERT_RESET]; - generic_exec_sequence(intel_dsi, sequence); - - sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP]; - generic_exec_sequence(intel_dsi, sequence); + generic_exec_sequence(panel, MIPI_SEQ_ASSERT_RESET); + generic_exec_sequence(panel, MIPI_SEQ_INIT_OTP); return 0; } static int vbt_panel_unprepare(struct drm_panel *panel) { - struct vbt_panel *vbt_panel = to_vbt_panel(panel); - struct intel_dsi *intel_dsi = vbt_panel->intel_dsi; - struct drm_device *dev = intel_dsi->base.base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - const u8 *sequence; - - sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET]; - generic_exec_sequence(intel_dsi, sequence); + generic_exec_sequence(panel, MIPI_SEQ_DEASSERT_RESET); return 0; } static int vbt_panel_enable(struct drm_panel *panel) { - struct vbt_panel *vbt_panel = to_vbt_panel(panel); - struct intel_dsi *intel_dsi = vbt_panel->intel_dsi; - struct drm_device *dev = intel_dsi->base.base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - const u8 *sequence; - - sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_ON]; - generic_exec_sequence(intel_dsi, sequence); + generic_exec_sequence(panel, MIPI_SEQ_DISPLAY_ON); return 0; } static int vbt_panel_disable(struct drm_panel *panel) { - struct vbt_panel *vbt_panel = to_vbt_panel(panel); - struct intel_dsi *intel_dsi = vbt_panel->intel_dsi; - struct drm_device *dev = intel_dsi->base.base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - const u8 *sequence; - - sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_OFF]; - generic_exec_sequence(intel_dsi, sequence); + generic_exec_sequence(panel, MIPI_SEQ_DISPLAY_OFF); return 0; } @@ -666,6 +677,8 @@ struct drm_panel *vbt_panel_init(struct intel_dsi *intel_dsi, u16 panel_id) /* This is cheating a bit with the cleanup. */ vbt_panel = devm_kzalloc(dev->dev, sizeof(*vbt_panel), GFP_KERNEL); + if (!vbt_panel) + return NULL; vbt_panel->intel_dsi = intel_dsi; drm_panel_init(&vbt_panel->panel); diff --git a/drivers/gpu/drm/i915/intel_dsi_pll.c b/drivers/gpu/drm/i915/intel_dsi_pll.c index fbd2b51810ca..bb5e95a1a453 100644 --- a/drivers/gpu/drm/i915/intel_dsi_pll.c +++ b/drivers/gpu/drm/i915/intel_dsi_pll.c @@ -30,14 +30,6 @@ #include "i915_drv.h" #include "intel_dsi.h" -#define DSI_HSS_PACKET_SIZE 4 -#define DSI_HSE_PACKET_SIZE 4 -#define DSI_HSA_PACKET_EXTRA_SIZE 6 -#define DSI_HBP_PACKET_EXTRA_SIZE 6 -#define DSI_HACTIVE_PACKET_EXTRA_SIZE 6 -#define DSI_HFP_PACKET_EXTRA_SIZE 6 -#define DSI_EOTP_PACKET_SIZE 4 - static int dsi_pixel_format_bpp(int pixel_format) { int bpp; @@ -71,77 +63,6 @@ static const u32 lfsr_converts[] = { 71, 35, 273, 136, 324, 418, 465, 488, 500, 506 /* 91 - 100 */ }; -#ifdef DSI_CLK_FROM_RR - -static u32 dsi_rr_formula(const struct drm_display_mode *mode, - int pixel_format, int video_mode_format, - int lane_count, bool eotp) -{ - u32 bpp; - u32 hactive, vactive, hfp, hsync, hbp, vfp, vsync, vbp; - u32 hsync_bytes, hbp_bytes, hactive_bytes, hfp_bytes; - u32 bytes_per_line, bytes_per_frame; - u32 num_frames; - u32 bytes_per_x_frames, bytes_per_x_frames_x_lanes; - u32 dsi_bit_clock_hz; - u32 dsi_clk; - - bpp = dsi_pixel_format_bpp(pixel_format); - - hactive = mode->hdisplay; - vactive = mode->vdisplay; - hfp = mode->hsync_start - mode->hdisplay; - hsync = mode->hsync_end - mode->hsync_start; - hbp = mode->htotal - mode->hsync_end; - - vfp = mode->vsync_start - mode->vdisplay; - vsync = mode->vsync_end - mode->vsync_start; - vbp = mode->vtotal - mode->vsync_end; - - hsync_bytes = DIV_ROUND_UP(hsync * bpp, 8); - hbp_bytes = DIV_ROUND_UP(hbp * bpp, 8); - hactive_bytes = DIV_ROUND_UP(hactive * bpp, 8); - hfp_bytes = DIV_ROUND_UP(hfp * bpp, 8); - - bytes_per_line = DSI_HSS_PACKET_SIZE + hsync_bytes + - DSI_HSA_PACKET_EXTRA_SIZE + DSI_HSE_PACKET_SIZE + - hbp_bytes + DSI_HBP_PACKET_EXTRA_SIZE + - hactive_bytes + DSI_HACTIVE_PACKET_EXTRA_SIZE + - hfp_bytes + DSI_HFP_PACKET_EXTRA_SIZE; - - /* - * XXX: Need to accurately calculate LP to HS transition timeout and add - * it to bytes_per_line/bytes_per_frame. - */ - - if (eotp && video_mode_format == VIDEO_MODE_BURST) - bytes_per_line += DSI_EOTP_PACKET_SIZE; - - bytes_per_frame = vsync * bytes_per_line + vbp * bytes_per_line + - vactive * bytes_per_line + vfp * bytes_per_line; - - if (eotp && - (video_mode_format == VIDEO_MODE_NON_BURST_WITH_SYNC_PULSE || - video_mode_format == VIDEO_MODE_NON_BURST_WITH_SYNC_EVENTS)) - bytes_per_frame += DSI_EOTP_PACKET_SIZE; - - num_frames = drm_mode_vrefresh(mode); - bytes_per_x_frames = num_frames * bytes_per_frame; - - bytes_per_x_frames_x_lanes = bytes_per_x_frames / lane_count; - - /* the dsi clock is divided by 2 in the hardware to get dsi ddr clock */ - dsi_bit_clock_hz = bytes_per_x_frames_x_lanes * 8; - dsi_clk = dsi_bit_clock_hz / 1000; - - if (eotp && video_mode_format == VIDEO_MODE_BURST) - dsi_clk *= 2; - - return dsi_clk; -} - -#else - /* Get DSI clock from pixel clock */ static u32 dsi_clk_from_pclk(u32 pclk, int pixel_format, int lane_count) { @@ -155,8 +76,6 @@ static u32 dsi_clk_from_pclk(u32 pclk, int pixel_format, int lane_count) return dsi_clk_khz; } -#endif - static int dsi_calc_mnp(struct drm_i915_private *dev_priv, struct dsi_mnp *dsi_mnp, int target_dsi_clk) { @@ -322,7 +241,7 @@ static void assert_bpp_mismatch(int pixel_format, int pipe_bpp) bpp, pipe_bpp); } -u32 vlv_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp) +static u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp) { struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); @@ -384,7 +303,7 @@ u32 vlv_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp) return pclk; } -u32 bxt_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp) +static u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp) { u32 pclk; u32 dsi_clk; @@ -419,6 +338,14 @@ u32 bxt_get_dsi_pclk(struct intel_encoder *encoder, int pipe_bpp) return pclk; } +u32 intel_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp) +{ + if (IS_BROXTON(encoder->base.dev)) + return bxt_dsi_get_pclk(encoder, pipe_bpp); + else + return vlv_dsi_get_pclk(encoder, pipe_bpp); +} + static void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port) { u32 temp; diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index bea75cafc623..09840f4380f9 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -119,7 +119,7 @@ static int intelfb_alloc(struct drm_fb_helper *helper, { struct intel_fbdev *ifbdev = container_of(helper, struct intel_fbdev, helper); - struct drm_framebuffer *fb = NULL; + struct drm_framebuffer *fb; struct drm_device *dev = helper->dev; struct drm_i915_private *dev_priv = to_i915(dev); struct drm_mode_fb_cmd2 mode_cmd = {}; @@ -171,8 +171,6 @@ static int intelfb_alloc(struct drm_fb_helper *helper, out: mutex_unlock(&dev->struct_mutex); - if (!IS_ERR_OR_NULL(fb)) - drm_framebuffer_unreference(fb); return ret; } diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h index 822952235dcf..045b1491ff7a 100644 --- a/drivers/gpu/drm/i915/intel_guc.h +++ b/drivers/gpu/drm/i915/intel_guc.h @@ -43,6 +43,7 @@ struct i915_guc_client { uint32_t wq_offset; uint32_t wq_size; uint32_t wq_tail; + uint32_t wq_head; /* GuC submission statistics & status */ uint64_t submissions[I915_NUM_RINGS]; @@ -88,6 +89,8 @@ struct intel_guc { uint32_t log_flags; struct drm_i915_gem_object *log_obj; + struct drm_i915_gem_object *ads_obj; + struct drm_i915_gem_object *ctx_pool_obj; struct ida ctx_ids; @@ -122,5 +125,6 @@ int i915_guc_submit(struct i915_guc_client *client, struct drm_i915_gem_request *rq); void i915_guc_submission_disable(struct drm_device *dev); void i915_guc_submission_fini(struct drm_device *dev); +int i915_guc_wq_check_space(struct i915_guc_client *client); #endif diff --git a/drivers/gpu/drm/i915/intel_guc_fwif.h b/drivers/gpu/drm/i915/intel_guc_fwif.h index 40b2ea572e16..1856a4740b83 100644 --- a/drivers/gpu/drm/i915/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/intel_guc_fwif.h @@ -39,6 +39,7 @@ #define GUC_CTX_PRIORITY_HIGH 1 #define GUC_CTX_PRIORITY_KMD_NORMAL 2 #define GUC_CTX_PRIORITY_NORMAL 3 +#define GUC_CTX_PRIORITY_NUM 4 #define GUC_MAX_GPU_CONTEXTS 1024 #define GUC_INVALID_CTX_ID GUC_MAX_GPU_CONTEXTS @@ -81,11 +82,14 @@ #define GUC_CTL_CTXINFO 0 #define GUC_CTL_CTXNUM_IN16_SHIFT 0 #define GUC_CTL_BASE_ADDR_SHIFT 12 + #define GUC_CTL_ARAT_HIGH 1 #define GUC_CTL_ARAT_LOW 2 + #define GUC_CTL_DEVICE_INFO 3 #define GUC_CTL_GTTYPE_SHIFT 0 #define GUC_CTL_COREFAMILY_SHIFT 7 + #define GUC_CTL_LOG_PARAMS 4 #define GUC_LOG_VALID (1 << 0) #define GUC_LOG_NOTIFY_ON_HALF_FULL (1 << 1) @@ -97,9 +101,12 @@ #define GUC_LOG_ISR_PAGES 3 #define GUC_LOG_ISR_SHIFT 9 #define GUC_LOG_BUF_ADDR_SHIFT 12 + #define GUC_CTL_PAGE_FAULT_CONTROL 5 + #define GUC_CTL_WA 6 #define GUC_CTL_WA_UK_BY_DRIVER (1 << 3) + #define GUC_CTL_FEATURE 7 #define GUC_CTL_VCS2_ENABLED (1 << 0) #define GUC_CTL_KERNEL_SUBMISSIONS (1 << 1) @@ -109,6 +116,7 @@ #define GUC_CTL_PREEMPTION_LOG (1 << 5) #define GUC_CTL_ENABLE_SLPC (1 << 7) #define GUC_CTL_RESET_ON_PREMPT_FAILURE (1 << 8) + #define GUC_CTL_DEBUG 8 #define GUC_LOG_VERBOSITY_SHIFT 0 #define GUC_LOG_VERBOSITY_LOW (0 << GUC_LOG_VERBOSITY_SHIFT) @@ -118,9 +126,19 @@ /* Verbosity range-check limits, without the shift */ #define GUC_LOG_VERBOSITY_MIN 0 #define GUC_LOG_VERBOSITY_MAX 3 +#define GUC_LOG_VERBOSITY_MASK 0x0000000f +#define GUC_LOG_DESTINATION_MASK (3 << 4) +#define GUC_LOG_DISABLED (1 << 6) +#define GUC_PROFILE_ENABLED (1 << 7) +#define GUC_WQ_TRACK_ENABLED (1 << 8) +#define GUC_ADS_ENABLED (1 << 9) +#define GUC_DEBUG_RESERVED (1 << 10) +#define GUC_ADS_ADDR_SHIFT 11 +#define GUC_ADS_ADDR_MASK 0xfffff800 + #define GUC_CTL_RSRVD 9 -#define GUC_CTL_MAX_DWORDS (GUC_CTL_RSRVD + 1) +#define GUC_CTL_MAX_DWORDS (SOFT_SCRATCH_COUNT - 2) /* [1..14] */ /** * DOC: GuC Firmware Layout @@ -299,6 +317,99 @@ struct guc_context_desc { #define GUC_POWER_D2 3 #define GUC_POWER_D3 4 +/* Scheduling policy settings */ + +/* Reset engine upon preempt failure */ +#define POLICY_RESET_ENGINE (1<<0) +/* Preempt to idle on quantum expiry */ +#define POLICY_PREEMPT_TO_IDLE (1<<1) + +#define POLICY_MAX_NUM_WI 15 + +struct guc_policy { + /* Time for one workload to execute. (in micro seconds) */ + u32 execution_quantum; + u32 reserved1; + + /* Time to wait for a preemption request to completed before issuing a + * reset. (in micro seconds). */ + u32 preemption_time; + + /* How much time to allow to run after the first fault is observed. + * Then preempt afterwards. (in micro seconds) */ + u32 fault_time; + + u32 policy_flags; + u32 reserved[2]; +} __packed; + +struct guc_policies { + struct guc_policy policy[GUC_CTX_PRIORITY_NUM][I915_NUM_RINGS]; + + /* In micro seconds. How much time to allow before DPC processing is + * called back via interrupt (to prevent DPC queue drain starving). + * Typically 1000s of micro seconds (example only, not granularity). */ + u32 dpc_promote_time; + + /* Must be set to take these new values. */ + u32 is_valid; + + /* Max number of WIs to process per call. A large value may keep CS + * idle. */ + u32 max_num_work_items; + + u32 reserved[19]; +} __packed; + +/* GuC MMIO reg state struct */ + +#define GUC_REGSET_FLAGS_NONE 0x0 +#define GUC_REGSET_POWERCYCLE 0x1 +#define GUC_REGSET_MASKED 0x2 +#define GUC_REGSET_ENGINERESET 0x4 +#define GUC_REGSET_SAVE_DEFAULT_VALUE 0x8 +#define GUC_REGSET_SAVE_CURRENT_VALUE 0x10 + +#define GUC_REGSET_MAX_REGISTERS 25 +#define GUC_MMIO_WHITE_LIST_START 0x24d0 +#define GUC_MMIO_WHITE_LIST_MAX 12 +#define GUC_S3_SAVE_SPACE_PAGES 10 + +struct guc_mmio_regset { + struct __packed { + u32 offset; + u32 value; + u32 flags; + } registers[GUC_REGSET_MAX_REGISTERS]; + + u32 values_valid; + u32 number_of_registers; +} __packed; + +struct guc_mmio_reg_state { + struct guc_mmio_regset global_reg; + struct guc_mmio_regset engine_reg[I915_NUM_RINGS]; + + /* MMIO registers that are set as non privileged */ + struct __packed { + u32 mmio_start; + u32 offsets[GUC_MMIO_WHITE_LIST_MAX]; + u32 count; + } mmio_white_list[I915_NUM_RINGS]; +} __packed; + +/* GuC Additional Data Struct */ + +struct guc_ads { + u32 reg_state_addr; + u32 reg_state_buffer; + u32 golden_context_lrca; + u32 scheduler_policies; + u32 reserved0[3]; + u32 eng_state_size[I915_NUM_RINGS]; + u32 reserved2[4]; +} __packed; + /* This Action will be programmed in C180 - SOFT_SCRATCH_O_REG */ enum host2guc_action { HOST2GUC_ACTION_DEFAULT = 0x0, diff --git a/drivers/gpu/drm/i915/intel_guc_loader.c b/drivers/gpu/drm/i915/intel_guc_loader.c index 550921f2ef7d..3accd914490f 100644 --- a/drivers/gpu/drm/i915/intel_guc_loader.c +++ b/drivers/gpu/drm/i915/intel_guc_loader.c @@ -165,6 +165,13 @@ static void set_guc_init_params(struct drm_i915_private *dev_priv) i915.guc_log_level << GUC_LOG_VERBOSITY_SHIFT; } + if (guc->ads_obj) { + u32 ads = (u32)i915_gem_obj_ggtt_offset(guc->ads_obj) + >> PAGE_SHIFT; + params[GUC_CTL_DEBUG] |= ads << GUC_ADS_ADDR_SHIFT; + params[GUC_CTL_DEBUG] |= GUC_ADS_ENABLED; + } + /* If GuC submission is enabled, set up additional parameters here */ if (i915.enable_guc_submission) { u32 pgs = i915_gem_obj_ggtt_offset(dev_priv->guc.ctx_pool_obj); @@ -438,6 +445,7 @@ fail: direct_interrupts_to_host(dev_priv); i915_guc_submission_disable(dev); + i915_guc_submission_fini(dev); return err; } @@ -554,10 +562,12 @@ fail: DRM_ERROR("Failed to fetch GuC firmware from %s (error %d)\n", guc_fw->guc_fw_path, err); + mutex_lock(&dev->struct_mutex); obj = guc_fw->guc_fw_obj; if (obj) drm_gem_object_unreference(&obj->base); guc_fw->guc_fw_obj = NULL; + mutex_unlock(&dev->struct_mutex); release_firmware(fw); /* OK even if fw is NULL */ guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_FAIL; @@ -624,10 +634,11 @@ void intel_guc_ucode_fini(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw; + mutex_lock(&dev->struct_mutex); direct_interrupts_to_host(dev_priv); + i915_guc_submission_disable(dev); i915_guc_submission_fini(dev); - mutex_lock(&dev->struct_mutex); if (guc_fw->guc_fw_obj) drm_gem_object_unreference(&guc_fw->guc_fw_obj->base); guc_fw->guc_fw_obj = NULL; diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 4a77639a489d..8698a643d027 100644..100755 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -2033,6 +2033,11 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, enum port port = intel_dig_port->port; uint8_t alternate_ddc_pin; + if (WARN(intel_dig_port->max_lanes < 4, + "Not enough lanes (%d) for HDMI on port %c\n", + intel_dig_port->max_lanes, port_name(port))) + return; + drm_connector_init(dev, connector, &intel_hdmi_connector_funcs, DRM_MODE_CONNECTOR_HDMIA); drm_connector_helper_add(connector, &intel_hdmi_connector_helper_funcs); @@ -2218,6 +2223,7 @@ void intel_hdmi_init(struct drm_device *dev, dev_priv->dig_port_map[port] = intel_encoder; intel_dig_port->hdmi.hdmi_reg = hdmi_reg; intel_dig_port->dp.output_reg = INVALID_MMIO_REG; + intel_dig_port->max_lanes = 4; intel_hdmi_init_connector(intel_dig_port, intel_connector); } diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index f1fa756c5d5d..73d4347429df 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -263,65 +263,92 @@ int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists return 0; } +static void +logical_ring_init_platform_invariants(struct intel_engine_cs *ring) +{ + struct drm_device *dev = ring->dev; + + ring->disable_lite_restore_wa = (IS_SKL_REVID(dev, 0, SKL_REVID_B0) || + IS_BXT_REVID(dev, 0, BXT_REVID_A1)) && + (ring->id == VCS || ring->id == VCS2); + + ring->ctx_desc_template = GEN8_CTX_VALID; + ring->ctx_desc_template |= GEN8_CTX_ADDRESSING_MODE(dev) << + GEN8_CTX_ADDRESSING_MODE_SHIFT; + if (IS_GEN8(dev)) + ring->ctx_desc_template |= GEN8_CTX_L3LLC_COHERENT; + ring->ctx_desc_template |= GEN8_CTX_PRIVILEGE; + + /* TODO: WaDisableLiteRestore when we start using semaphore + * signalling between Command Streamers */ + /* ring->ctx_desc_template |= GEN8_CTX_FORCE_RESTORE; */ + + /* WaEnableForceRestoreInCtxtDescForVCS:skl */ + /* WaEnableForceRestoreInCtxtDescForVCS:bxt */ + if (ring->disable_lite_restore_wa) + ring->ctx_desc_template |= GEN8_CTX_FORCE_RESTORE; +} + /** - * intel_execlists_ctx_id() - get the Execlists Context ID - * @ctx_obj: Logical Ring Context backing object. + * intel_lr_context_descriptor_update() - calculate & cache the descriptor + * descriptor for a pinned context * - * Do not confuse with ctx->id! Unfortunately we have a name overload - * here: the old context ID we pass to userspace as a handler so that - * they can refer to a context, and the new context ID we pass to the - * ELSP so that the GPU can inform us of the context status via - * interrupts. + * @ctx: Context to work on + * @ring: Engine the descriptor will be used with * - * Return: 20-bits globally unique context ID. + * The context descriptor encodes various attributes of a context, + * including its GTT address and some flags. Because it's fairly + * expensive to calculate, we'll just do it once and cache the result, + * which remains valid until the context is unpinned. + * + * This is what a descriptor looks like, from LSB to MSB: + * bits 0-11: flags, GEN8_CTX_* (cached in ctx_desc_template) + * bits 12-31: LRCA, GTT address of (the HWSP of) this context + * bits 32-51: ctx ID, a globally unique tag (the LRCA again!) + * bits 52-63: reserved, may encode the engine ID (for GuC) */ -u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj) +static void +intel_lr_context_descriptor_update(struct intel_context *ctx, + struct intel_engine_cs *ring) { - u32 lrca = i915_gem_obj_ggtt_offset(ctx_obj) + - LRC_PPHWSP_PN * PAGE_SIZE; + uint64_t lrca, desc; - /* LRCA is required to be 4K aligned so the more significant 20 bits - * are globally unique */ - return lrca >> 12; -} + lrca = ctx->engine[ring->id].lrc_vma->node.start + + LRC_PPHWSP_PN * PAGE_SIZE; -static bool disable_lite_restore_wa(struct intel_engine_cs *ring) -{ - struct drm_device *dev = ring->dev; + desc = ring->ctx_desc_template; /* bits 0-11 */ + desc |= lrca; /* bits 12-31 */ + desc |= (lrca >> PAGE_SHIFT) << GEN8_CTX_ID_SHIFT; /* bits 32-51 */ - return (IS_SKL_REVID(dev, 0, SKL_REVID_B0) || - IS_BXT_REVID(dev, 0, BXT_REVID_A1)) && - (ring->id == VCS || ring->id == VCS2); + ctx->engine[ring->id].lrc_desc = desc; } uint64_t intel_lr_context_descriptor(struct intel_context *ctx, struct intel_engine_cs *ring) { - struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state; - uint64_t desc; - uint64_t lrca = i915_gem_obj_ggtt_offset(ctx_obj) + - LRC_PPHWSP_PN * PAGE_SIZE; - - WARN_ON(lrca & 0xFFFFFFFF00000FFFULL); - - desc = GEN8_CTX_VALID; - desc |= GEN8_CTX_ADDRESSING_MODE(dev) << GEN8_CTX_ADDRESSING_MODE_SHIFT; - if (IS_GEN8(ctx_obj->base.dev)) - desc |= GEN8_CTX_L3LLC_COHERENT; - desc |= GEN8_CTX_PRIVILEGE; - desc |= lrca; - desc |= (u64)intel_execlists_ctx_id(ctx_obj) << GEN8_CTX_ID_SHIFT; - - /* TODO: WaDisableLiteRestore when we start using semaphore - * signalling between Command Streamers */ - /* desc |= GEN8_CTX_FORCE_RESTORE; */ - - /* WaEnableForceRestoreInCtxtDescForVCS:skl */ - /* WaEnableForceRestoreInCtxtDescForVCS:bxt */ - if (disable_lite_restore_wa(ring)) - desc |= GEN8_CTX_FORCE_RESTORE; + return ctx->engine[ring->id].lrc_desc; +} - return desc; +/** + * intel_execlists_ctx_id() - get the Execlists Context ID + * @ctx: Context to get the ID for + * @ring: Engine to get the ID for + * + * Do not confuse with ctx->id! Unfortunately we have a name overload + * here: the old context ID we pass to userspace as a handler so that + * they can refer to a context, and the new context ID we pass to the + * ELSP so that the GPU can inform us of the context status via + * interrupts. + * + * The context ID is a portion of the context descriptor, so we can + * just extract the required part from the cached descriptor. + * + * Return: 20-bits globally unique context ID. + */ +u32 intel_execlists_ctx_id(struct intel_context *ctx, + struct intel_engine_cs *ring) +{ + return intel_lr_context_descriptor(ctx, ring) >> GEN8_CTX_ID_SHIFT; } static void execlists_elsp_write(struct drm_i915_gem_request *rq0, @@ -363,20 +390,10 @@ static int execlists_update_context(struct drm_i915_gem_request *rq) { struct intel_engine_cs *ring = rq->ring; struct i915_hw_ppgtt *ppgtt = rq->ctx->ppgtt; - struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring->id].state; - struct drm_i915_gem_object *rb_obj = rq->ringbuf->obj; - struct page *page; - uint32_t *reg_state; - - BUG_ON(!ctx_obj); - WARN_ON(!i915_gem_obj_is_pinned(ctx_obj)); - WARN_ON(!i915_gem_obj_is_pinned(rb_obj)); - - page = i915_gem_object_get_dirty_page(ctx_obj, LRC_STATE_PN); - reg_state = kmap_atomic(page); + uint32_t *reg_state = rq->ctx->engine[ring->id].lrc_reg_state; reg_state[CTX_RING_TAIL+1] = rq->tail; - reg_state[CTX_RING_BUFFER_START+1] = i915_gem_obj_ggtt_offset(rb_obj); + reg_state[CTX_RING_BUFFER_START+1] = rq->ringbuf->vma->node.start; if (ppgtt && !USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) { /* True 32b PPGTT with dynamic page allocation: update PDP @@ -390,8 +407,6 @@ static int execlists_update_context(struct drm_i915_gem_request *rq) ASSIGN_CTX_PDP(ppgtt, reg_state, 0); } - kunmap_atomic(reg_state); - return 0; } @@ -431,9 +446,8 @@ static void execlists_context_unqueue(struct intel_engine_cs *ring) /* Same ctx: ignore first request, as second request * will update tail past first request's workload */ cursor->elsp_submitted = req0->elsp_submitted; - list_del(&req0->execlist_link); - list_add_tail(&req0->execlist_link, - &ring->execlist_retired_req_list); + list_move_tail(&req0->execlist_link, + &ring->execlist_retired_req_list); req0 = cursor; } else { req1 = cursor; @@ -478,16 +492,13 @@ static bool execlists_check_remove_request(struct intel_engine_cs *ring, execlist_link); if (head_req != NULL) { - struct drm_i915_gem_object *ctx_obj = - head_req->ctx->engine[ring->id].state; - if (intel_execlists_ctx_id(ctx_obj) == request_id) { + if (intel_execlists_ctx_id(head_req->ctx, ring) == request_id) { WARN(head_req->elsp_submitted == 0, "Never submitted head request\n"); if (--head_req->elsp_submitted <= 0) { - list_del(&head_req->execlist_link); - list_add_tail(&head_req->execlist_link, - &ring->execlist_retired_req_list); + list_move_tail(&head_req->execlist_link, + &ring->execlist_retired_req_list); return true; } } @@ -496,6 +507,19 @@ static bool execlists_check_remove_request(struct intel_engine_cs *ring, return false; } +static void get_context_status(struct intel_engine_cs *ring, + u8 read_pointer, + u32 *status, u32 *context_id) +{ + struct drm_i915_private *dev_priv = ring->dev->dev_private; + + if (WARN_ON(read_pointer >= GEN8_CSB_ENTRIES)) + return; + + *status = I915_READ(RING_CONTEXT_STATUS_BUF_LO(ring, read_pointer)); + *context_id = I915_READ(RING_CONTEXT_STATUS_BUF_HI(ring, read_pointer)); +} + /** * intel_lrc_irq_handler() - handle Context Switch interrupts * @ring: Engine Command Streamer to handle. @@ -516,16 +540,16 @@ void intel_lrc_irq_handler(struct intel_engine_cs *ring) status_pointer = I915_READ(RING_CONTEXT_STATUS_PTR(ring)); read_pointer = ring->next_context_status_buffer; - write_pointer = status_pointer & GEN8_CSB_PTR_MASK; + write_pointer = GEN8_CSB_WRITE_PTR(status_pointer); if (read_pointer > write_pointer) write_pointer += GEN8_CSB_ENTRIES; spin_lock(&ring->execlist_lock); while (read_pointer < write_pointer) { - read_pointer++; - status = I915_READ(RING_CONTEXT_STATUS_BUF_LO(ring, read_pointer % GEN8_CSB_ENTRIES)); - status_id = I915_READ(RING_CONTEXT_STATUS_BUF_HI(ring, read_pointer % GEN8_CSB_ENTRIES)); + + get_context_status(ring, ++read_pointer % GEN8_CSB_ENTRIES, + &status, &status_id); if (status & GEN8_CTX_STATUS_IDLE_ACTIVE) continue; @@ -538,14 +562,14 @@ void intel_lrc_irq_handler(struct intel_engine_cs *ring) WARN(1, "Preemption without Lite Restore\n"); } - if ((status & GEN8_CTX_STATUS_ACTIVE_IDLE) || - (status & GEN8_CTX_STATUS_ELEMENT_SWITCH)) { + if ((status & GEN8_CTX_STATUS_ACTIVE_IDLE) || + (status & GEN8_CTX_STATUS_ELEMENT_SWITCH)) { if (execlists_check_remove_request(ring, status_id)) submit_contexts++; } } - if (disable_lite_restore_wa(ring)) { + if (ring->disable_lite_restore_wa) { /* Prevent a ctx to preempt itself */ if ((status & GEN8_CTX_STATUS_ACTIVE_IDLE) && (submit_contexts != 0)) @@ -556,13 +580,16 @@ void intel_lrc_irq_handler(struct intel_engine_cs *ring) spin_unlock(&ring->execlist_lock); - WARN(submit_contexts > 2, "More than two context complete events?\n"); + if (unlikely(submit_contexts > 2)) + DRM_ERROR("More than two context complete events?\n"); + ring->next_context_status_buffer = write_pointer % GEN8_CSB_ENTRIES; + /* Update the read pointer to the old write pointer. Manual ringbuffer + * management ftw </sarcasm> */ I915_WRITE(RING_CONTEXT_STATUS_PTR(ring), - _MASKED_FIELD(GEN8_CSB_PTR_MASK << 8, - ((u32)ring->next_context_status_buffer & - GEN8_CSB_PTR_MASK) << 8)); + _MASKED_FIELD(GEN8_CSB_READ_PTR_MASK, + ring->next_context_status_buffer << 8)); } static int execlists_context_queue(struct drm_i915_gem_request *request) @@ -571,7 +598,7 @@ static int execlists_context_queue(struct drm_i915_gem_request *request) struct drm_i915_gem_request *cursor; int num_elements = 0; - if (request->ctx != ring->default_context) + if (request->ctx != request->i915->kernel_context) intel_lr_context_pin(request); i915_gem_request_reference(request); @@ -592,9 +619,8 @@ static int execlists_context_queue(struct drm_i915_gem_request *request) if (request->ctx == tail_req->ctx) { WARN(tail_req->elsp_submitted != 0, "More than 2 already-submitted reqs queued\n"); - list_del(&tail_req->execlist_link); - list_add_tail(&tail_req->execlist_link, - &ring->execlist_retired_req_list); + list_move_tail(&tail_req->execlist_link, + &ring->execlist_retired_req_list); } } @@ -660,17 +686,27 @@ static int execlists_move_to_gpu(struct drm_i915_gem_request *req, int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request) { - int ret; + int ret = 0; request->ringbuf = request->ctx->engine[request->ring->id].ringbuf; - if (request->ctx != request->ring->default_context) { - ret = intel_lr_context_pin(request); + if (i915.enable_guc_submission) { + /* + * Check that the GuC has space for the request before + * going any further, as the i915_add_request() call + * later on mustn't fail ... + */ + struct intel_guc *guc = &request->i915->guc; + + ret = i915_guc_wq_check_space(guc->execbuf_client); if (ret) return ret; } - return 0; + if (request->ctx != request->i915->kernel_context) + ret = intel_lr_context_pin(request); + + return ret; } static int logical_ring_wait_for_space(struct drm_i915_gem_request *req, @@ -724,23 +760,34 @@ static int logical_ring_wait_for_space(struct drm_i915_gem_request *req, * on a queue waiting for the ELSP to be ready to accept a new context submission. At that * point, the tail *inside* the context is updated and the ELSP written to. */ -static void +static int intel_logical_ring_advance_and_submit(struct drm_i915_gem_request *request) { - struct intel_engine_cs *ring = request->ring; + struct intel_ringbuffer *ringbuf = request->ringbuf; struct drm_i915_private *dev_priv = request->i915; - intel_logical_ring_advance(request->ringbuf); + intel_logical_ring_advance(ringbuf); + request->tail = ringbuf->tail; - request->tail = request->ringbuf->tail; + /* + * Here we add two extra NOOPs as padding to avoid + * lite restore of a context with HEAD==TAIL. + * + * Caller must reserve WA_TAIL_DWORDS for us! + */ + intel_logical_ring_emit(ringbuf, MI_NOOP); + intel_logical_ring_emit(ringbuf, MI_NOOP); + intel_logical_ring_advance(ringbuf); - if (intel_ring_stopped(ring)) - return; + if (intel_ring_stopped(request->ring)) + return 0; if (dev_priv->guc.execbuf_client) i915_guc_submit(dev_priv->guc.execbuf_client, request); else execlists_context_queue(request); + + return 0; } static void __wrap_ring_buffer(struct intel_ringbuffer *ringbuf) @@ -967,7 +1014,7 @@ void intel_execlists_retire_requests(struct intel_engine_cs *ring) struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state; - if (ctx_obj && (ctx != ring->default_context)) + if (ctx_obj && (ctx != req->i915->kernel_context)) intel_lr_context_unpin(req); list_del(&req->execlist_link); i915_gem_request_unreference(req); @@ -1013,23 +1060,35 @@ int logical_ring_flush_all_caches(struct drm_i915_gem_request *req) } static int intel_lr_context_do_pin(struct intel_engine_cs *ring, - struct drm_i915_gem_object *ctx_obj, - struct intel_ringbuffer *ringbuf) + struct intel_context *ctx) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; - int ret = 0; + struct drm_i915_gem_object *ctx_obj = ctx->engine[ring->id].state; + struct intel_ringbuffer *ringbuf = ctx->engine[ring->id].ringbuf; + struct page *lrc_state_page; + int ret; WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex)); + ret = i915_gem_obj_ggtt_pin(ctx_obj, GEN8_LR_CONTEXT_ALIGN, PIN_OFFSET_BIAS | GUC_WOPCM_TOP); if (ret) return ret; + lrc_state_page = i915_gem_object_get_dirty_page(ctx_obj, LRC_STATE_PN); + if (WARN_ON(!lrc_state_page)) { + ret = -ENODEV; + goto unpin_ctx_obj; + } + ret = intel_pin_and_map_ringbuffer_obj(ring->dev, ringbuf); if (ret) goto unpin_ctx_obj; + ctx->engine[ring->id].lrc_vma = i915_gem_obj_to_ggtt(ctx_obj); + intel_lr_context_descriptor_update(ctx, ring); + ctx->engine[ring->id].lrc_reg_state = kmap(lrc_state_page); ctx_obj->dirty = true; /* Invalidate GuC TLB. */ @@ -1048,11 +1107,9 @@ static int intel_lr_context_pin(struct drm_i915_gem_request *rq) { int ret = 0; struct intel_engine_cs *ring = rq->ring; - struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring->id].state; - struct intel_ringbuffer *ringbuf = rq->ringbuf; if (rq->ctx->engine[ring->id].pin_count++ == 0) { - ret = intel_lr_context_do_pin(ring, ctx_obj, ringbuf); + ret = intel_lr_context_do_pin(ring, rq->ctx); if (ret) goto reset_pin_count; } @@ -1069,12 +1126,18 @@ void intel_lr_context_unpin(struct drm_i915_gem_request *rq) struct drm_i915_gem_object *ctx_obj = rq->ctx->engine[ring->id].state; struct intel_ringbuffer *ringbuf = rq->ringbuf; - if (ctx_obj) { - WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex)); - if (--rq->ctx->engine[ring->id].pin_count == 0) { - intel_unpin_ringbuffer_obj(ringbuf); - i915_gem_object_ggtt_unpin(ctx_obj); - } + WARN_ON(!mutex_is_locked(&ring->dev->struct_mutex)); + + if (!ctx_obj) + return; + + if (--rq->ctx->engine[ring->id].pin_count == 0) { + kunmap(kmap_to_page(rq->ctx->engine[ring->id].lrc_reg_state)); + intel_unpin_ringbuffer_obj(ringbuf); + i915_gem_object_ggtt_unpin(ctx_obj); + rq->ctx->engine[ring->id].lrc_vma = NULL; + rq->ctx->engine[ring->id].lrc_desc = 0; + rq->ctx->engine[ring->id].lrc_reg_state = NULL; } } @@ -1087,7 +1150,7 @@ static int intel_logical_ring_workarounds_emit(struct drm_i915_gem_request *req) struct drm_i915_private *dev_priv = dev->dev_private; struct i915_workarounds *w = &dev_priv->workarounds; - if (WARN_ON_ONCE(w->count == 0)) + if (w->count == 0) return 0; ring->gpu_caches_dirty = true; @@ -1474,7 +1537,7 @@ static int gen8_init_common_ring(struct intel_engine_cs *ring) u8 next_context_status_buffer_hw; lrc_setup_hardware_status_page(ring, - ring->default_context->engine[ring->id].state); + dev_priv->kernel_context->engine[ring->id].state); I915_WRITE_IMR(ring, ~(ring->irq_enable_mask | ring->irq_keep_mask)); I915_WRITE(RING_HWSTAM(ring->mmio_base), 0xffffffff); @@ -1493,9 +1556,11 @@ static int gen8_init_common_ring(struct intel_engine_cs *ring) * | Suspend-to-idle (freeze) | Suspend-to-RAM (mem) | * BDW | CSB regs not reset | CSB regs reset | * CHT | CSB regs not reset | CSB regs not reset | + * SKL | ? | ? | + * BXT | ? | ? | */ - next_context_status_buffer_hw = (I915_READ(RING_CONTEXT_STATUS_PTR(ring)) - & GEN8_CSB_PTR_MASK); + next_context_status_buffer_hw = + GEN8_CSB_WRITE_PTR(I915_READ(RING_CONTEXT_STATUS_PTR(ring))); /* * When the CSB registers are reset (also after power-up / gpu reset), @@ -1698,7 +1763,7 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, struct intel_ringbuffer *ringbuf = request->ringbuf; struct intel_engine_cs *ring = ringbuf->ring; u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES; - bool vf_flush_wa; + bool vf_flush_wa = false; u32 flags = 0; int ret; @@ -1720,14 +1785,14 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE; flags |= PIPE_CONTROL_QW_WRITE; flags |= PIPE_CONTROL_GLOBAL_GTT_IVB; - } - /* - * On GEN9+ Before VF_CACHE_INVALIDATE we need to emit a NULL pipe - * control. - */ - vf_flush_wa = INTEL_INFO(ring->dev)->gen >= 9 && - flags & PIPE_CONTROL_VF_CACHE_INVALIDATE; + /* + * On GEN9: before VF_CACHE_INVALIDATE we need to emit a NULL + * pipe control. + */ + if (IS_GEN9(ring->dev)) + vf_flush_wa = true; + } ret = intel_logical_ring_begin(request, vf_flush_wa ? 12 : 6); if (ret) @@ -1791,44 +1856,65 @@ static void bxt_a_set_seqno(struct intel_engine_cs *ring, u32 seqno) intel_flush_status_page(ring, I915_GEM_HWS_INDEX); } +/* + * Reserve space for 2 NOOPs at the end of each request to be + * used as a workaround for not being allowed to do lite + * restore with HEAD==TAIL (WaIdleLiteRestore). + */ +#define WA_TAIL_DWORDS 2 + +static inline u32 hws_seqno_address(struct intel_engine_cs *engine) +{ + return engine->status_page.gfx_addr + I915_GEM_HWS_INDEX_ADDR; +} + static int gen8_emit_request(struct drm_i915_gem_request *request) { struct intel_ringbuffer *ringbuf = request->ringbuf; - struct intel_engine_cs *ring = ringbuf->ring; - u32 cmd; int ret; - /* - * Reserve space for 2 NOOPs at the end of each request to be - * used as a workaround for not being allowed to do lite - * restore with HEAD==TAIL (WaIdleLiteRestore). - */ - ret = intel_logical_ring_begin(request, 8); + ret = intel_logical_ring_begin(request, 6 + WA_TAIL_DWORDS); if (ret) return ret; - cmd = MI_STORE_DWORD_IMM_GEN4; - cmd |= MI_GLOBAL_GTT; + /* w/a: bit 5 needs to be zero for MI_FLUSH_DW address. */ + BUILD_BUG_ON(I915_GEM_HWS_INDEX_ADDR & (1 << 5)); - intel_logical_ring_emit(ringbuf, cmd); intel_logical_ring_emit(ringbuf, - (ring->status_page.gfx_addr + - (I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT))); + (MI_FLUSH_DW + 1) | MI_FLUSH_DW_OP_STOREDW); + intel_logical_ring_emit(ringbuf, + hws_seqno_address(request->ring) | + MI_FLUSH_DW_USE_GTT); intel_logical_ring_emit(ringbuf, 0); intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request)); intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT); intel_logical_ring_emit(ringbuf, MI_NOOP); - intel_logical_ring_advance_and_submit(request); + return intel_logical_ring_advance_and_submit(request); +} - /* - * Here we add two extra NOOPs as padding to avoid - * lite restore of a context with HEAD==TAIL. - */ - intel_logical_ring_emit(ringbuf, MI_NOOP); - intel_logical_ring_emit(ringbuf, MI_NOOP); - intel_logical_ring_advance(ringbuf); +static int gen8_emit_request_render(struct drm_i915_gem_request *request) +{ + struct intel_ringbuffer *ringbuf = request->ringbuf; + int ret; - return 0; + ret = intel_logical_ring_begin(request, 6 + WA_TAIL_DWORDS); + if (ret) + return ret; + + /* w/a for post sync ops following a GPGPU operation we + * need a prior CS_STALL, which is emitted by the flush + * following the batch. + */ + intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(5)); + intel_logical_ring_emit(ringbuf, + (PIPE_CONTROL_GLOBAL_GTT_IVB | + PIPE_CONTROL_CS_STALL | + PIPE_CONTROL_QW_WRITE)); + intel_logical_ring_emit(ringbuf, hws_seqno_address(request->ring)); + intel_logical_ring_emit(ringbuf, 0); + intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request)); + intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT); + return intel_logical_ring_advance_and_submit(request); } static int intel_lr_context_render_state_init(struct drm_i915_gem_request *req) @@ -1911,12 +1997,44 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *ring) ring->status_page.obj = NULL; } + ring->disable_lite_restore_wa = false; + ring->ctx_desc_template = 0; + lrc_destroy_wa_ctx_obj(ring); ring->dev = NULL; } -static int logical_ring_init(struct drm_device *dev, struct intel_engine_cs *ring) +static void +logical_ring_default_vfuncs(struct drm_device *dev, + struct intel_engine_cs *ring) { + /* Default vfuncs which can be overriden by each engine. */ + ring->init_hw = gen8_init_common_ring; + ring->emit_request = gen8_emit_request; + ring->emit_flush = gen8_emit_flush; + ring->irq_get = gen8_logical_ring_get_irq; + ring->irq_put = gen8_logical_ring_put_irq; + ring->emit_bb_start = gen8_emit_bb_start; + if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) { + ring->get_seqno = bxt_a_get_seqno; + ring->set_seqno = bxt_a_set_seqno; + } else { + ring->get_seqno = gen8_get_seqno; + ring->set_seqno = gen8_set_seqno; + } +} + +static inline void +logical_ring_default_irqs(struct intel_engine_cs *ring, unsigned shift) +{ + ring->irq_enable_mask = GT_RENDER_USER_INTERRUPT << shift; + ring->irq_keep_mask = GT_CONTEXT_SWITCH_INTERRUPT << shift; +} + +static int +logical_ring_init(struct drm_device *dev, struct intel_engine_cs *ring) +{ + struct intel_context *dctx = to_i915(dev)->kernel_context; int ret; /* Intentionally left blank. */ @@ -1933,19 +2051,18 @@ static int logical_ring_init(struct drm_device *dev, struct intel_engine_cs *rin INIT_LIST_HEAD(&ring->execlist_retired_req_list); spin_lock_init(&ring->execlist_lock); + logical_ring_init_platform_invariants(ring); + ret = i915_cmd_parser_init_ring(ring); if (ret) goto error; - ret = intel_lr_context_deferred_alloc(ring->default_context, ring); + ret = intel_lr_context_deferred_alloc(dctx, ring); if (ret) goto error; /* As this is the default context, always pin it */ - ret = intel_lr_context_do_pin( - ring, - ring->default_context->engine[ring->id].state, - ring->default_context->engine[ring->id].ringbuf); + ret = intel_lr_context_do_pin(ring, dctx); if (ret) { DRM_ERROR( "Failed to pin and map ringbuffer %s: %d\n", @@ -1968,32 +2085,24 @@ static int logical_render_ring_init(struct drm_device *dev) ring->name = "render ring"; ring->id = RCS; + ring->exec_id = I915_EXEC_RENDER; ring->mmio_base = RENDER_RING_BASE; - ring->irq_enable_mask = - GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT; - ring->irq_keep_mask = - GT_CONTEXT_SWITCH_INTERRUPT << GEN8_RCS_IRQ_SHIFT; + + logical_ring_default_irqs(ring, GEN8_RCS_IRQ_SHIFT); if (HAS_L3_DPF(dev)) ring->irq_keep_mask |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT; + logical_ring_default_vfuncs(dev, ring); + + /* Override some for render ring. */ if (INTEL_INFO(dev)->gen >= 9) ring->init_hw = gen9_init_render_ring; else ring->init_hw = gen8_init_render_ring; ring->init_context = gen8_init_rcs_context; ring->cleanup = intel_fini_pipe_control; - if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) { - ring->get_seqno = bxt_a_get_seqno; - ring->set_seqno = bxt_a_set_seqno; - } else { - ring->get_seqno = gen8_get_seqno; - ring->set_seqno = gen8_set_seqno; - } - ring->emit_request = gen8_emit_request; ring->emit_flush = gen8_emit_flush_render; - ring->irq_get = gen8_logical_ring_get_irq; - ring->irq_put = gen8_logical_ring_put_irq; - ring->emit_bb_start = gen8_emit_bb_start; + ring->emit_request = gen8_emit_request_render; ring->dev = dev; @@ -2027,25 +2136,11 @@ static int logical_bsd_ring_init(struct drm_device *dev) ring->name = "bsd ring"; ring->id = VCS; + ring->exec_id = I915_EXEC_BSD; ring->mmio_base = GEN6_BSD_RING_BASE; - ring->irq_enable_mask = - GT_RENDER_USER_INTERRUPT << GEN8_VCS1_IRQ_SHIFT; - ring->irq_keep_mask = - GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS1_IRQ_SHIFT; - ring->init_hw = gen8_init_common_ring; - if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) { - ring->get_seqno = bxt_a_get_seqno; - ring->set_seqno = bxt_a_set_seqno; - } else { - ring->get_seqno = gen8_get_seqno; - ring->set_seqno = gen8_set_seqno; - } - ring->emit_request = gen8_emit_request; - ring->emit_flush = gen8_emit_flush; - ring->irq_get = gen8_logical_ring_get_irq; - ring->irq_put = gen8_logical_ring_put_irq; - ring->emit_bb_start = gen8_emit_bb_start; + logical_ring_default_irqs(ring, GEN8_VCS1_IRQ_SHIFT); + logical_ring_default_vfuncs(dev, ring); return logical_ring_init(dev, ring); } @@ -2055,22 +2150,13 @@ static int logical_bsd2_ring_init(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_engine_cs *ring = &dev_priv->ring[VCS2]; - ring->name = "bds2 ring"; + ring->name = "bsd2 ring"; ring->id = VCS2; + ring->exec_id = I915_EXEC_BSD; ring->mmio_base = GEN8_BSD2_RING_BASE; - ring->irq_enable_mask = - GT_RENDER_USER_INTERRUPT << GEN8_VCS2_IRQ_SHIFT; - ring->irq_keep_mask = - GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VCS2_IRQ_SHIFT; - ring->init_hw = gen8_init_common_ring; - ring->get_seqno = gen8_get_seqno; - ring->set_seqno = gen8_set_seqno; - ring->emit_request = gen8_emit_request; - ring->emit_flush = gen8_emit_flush; - ring->irq_get = gen8_logical_ring_get_irq; - ring->irq_put = gen8_logical_ring_put_irq; - ring->emit_bb_start = gen8_emit_bb_start; + logical_ring_default_irqs(ring, GEN8_VCS2_IRQ_SHIFT); + logical_ring_default_vfuncs(dev, ring); return logical_ring_init(dev, ring); } @@ -2082,25 +2168,11 @@ static int logical_blt_ring_init(struct drm_device *dev) ring->name = "blitter ring"; ring->id = BCS; + ring->exec_id = I915_EXEC_BLT; ring->mmio_base = BLT_RING_BASE; - ring->irq_enable_mask = - GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT; - ring->irq_keep_mask = - GT_CONTEXT_SWITCH_INTERRUPT << GEN8_BCS_IRQ_SHIFT; - ring->init_hw = gen8_init_common_ring; - if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) { - ring->get_seqno = bxt_a_get_seqno; - ring->set_seqno = bxt_a_set_seqno; - } else { - ring->get_seqno = gen8_get_seqno; - ring->set_seqno = gen8_set_seqno; - } - ring->emit_request = gen8_emit_request; - ring->emit_flush = gen8_emit_flush; - ring->irq_get = gen8_logical_ring_get_irq; - ring->irq_put = gen8_logical_ring_put_irq; - ring->emit_bb_start = gen8_emit_bb_start; + logical_ring_default_irqs(ring, GEN8_BCS_IRQ_SHIFT); + logical_ring_default_vfuncs(dev, ring); return logical_ring_init(dev, ring); } @@ -2112,25 +2184,11 @@ static int logical_vebox_ring_init(struct drm_device *dev) ring->name = "video enhancement ring"; ring->id = VECS; + ring->exec_id = I915_EXEC_VEBOX; ring->mmio_base = VEBOX_RING_BASE; - ring->irq_enable_mask = - GT_RENDER_USER_INTERRUPT << GEN8_VECS_IRQ_SHIFT; - ring->irq_keep_mask = - GT_CONTEXT_SWITCH_INTERRUPT << GEN8_VECS_IRQ_SHIFT; - ring->init_hw = gen8_init_common_ring; - if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) { - ring->get_seqno = bxt_a_get_seqno; - ring->set_seqno = bxt_a_set_seqno; - } else { - ring->get_seqno = gen8_get_seqno; - ring->set_seqno = gen8_set_seqno; - } - ring->emit_request = gen8_emit_request; - ring->emit_flush = gen8_emit_flush; - ring->irq_get = gen8_logical_ring_get_irq; - ring->irq_put = gen8_logical_ring_put_irq; - ring->emit_bb_start = gen8_emit_bb_start; + logical_ring_default_irqs(ring, GEN8_VECS_IRQ_SHIFT); + logical_ring_default_vfuncs(dev, ring); return logical_ring_init(dev, ring); } @@ -2368,26 +2426,39 @@ void intel_lr_context_free(struct intel_context *ctx) { int i; - for (i = 0; i < I915_NUM_RINGS; i++) { + for (i = I915_NUM_RINGS; --i >= 0; ) { + struct intel_ringbuffer *ringbuf = ctx->engine[i].ringbuf; struct drm_i915_gem_object *ctx_obj = ctx->engine[i].state; - if (ctx_obj) { - struct intel_ringbuffer *ringbuf = - ctx->engine[i].ringbuf; - struct intel_engine_cs *ring = ringbuf->ring; + if (!ctx_obj) + continue; - if (ctx == ring->default_context) { - intel_unpin_ringbuffer_obj(ringbuf); - i915_gem_object_ggtt_unpin(ctx_obj); - } - WARN_ON(ctx->engine[ring->id].pin_count); - intel_ringbuffer_free(ringbuf); - drm_gem_object_unreference(&ctx_obj->base); + if (ctx == ctx->i915->kernel_context) { + intel_unpin_ringbuffer_obj(ringbuf); + i915_gem_object_ggtt_unpin(ctx_obj); } + + WARN_ON(ctx->engine[i].pin_count); + intel_ringbuffer_free(ringbuf); + drm_gem_object_unreference(&ctx_obj->base); } } -static uint32_t get_lr_context_size(struct intel_engine_cs *ring) +/** + * intel_lr_context_size() - return the size of the context for an engine + * @ring: which engine to find the context size for + * + * Each engine may require a different amount of space for a context image, + * so when allocating (or copying) an image, this function can be used to + * find the right size for the specific engine. + * + * Return: size (in bytes) of an engine-specific context image + * + * Note: this size includes the HWSP, which is part of the context image + * in LRC mode, but does not include the "shared data page" used with + * GuC submission. The caller should account for this if using the GuC. + */ +uint32_t intel_lr_context_size(struct intel_engine_cs *ring) { int ret = 0; @@ -2444,7 +2515,7 @@ static void lrc_setup_hardware_status_page(struct intel_engine_cs *ring, */ int intel_lr_context_deferred_alloc(struct intel_context *ctx, - struct intel_engine_cs *ring) + struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_gem_object *ctx_obj; @@ -2455,7 +2526,7 @@ int intel_lr_context_deferred_alloc(struct intel_context *ctx, WARN_ON(ctx->legacy_hw_ctx.rcs_state != NULL); WARN_ON(ctx->engine[ring->id].state); - context_size = round_up(get_lr_context_size(ring), 4096); + context_size = round_up(intel_lr_context_size(ring), 4096); /* One extra page as the sharing data between driver and GuC */ context_size += PAGE_SIZE * LRC_PPHWSP_PN; @@ -2481,14 +2552,13 @@ int intel_lr_context_deferred_alloc(struct intel_context *ctx, ctx->engine[ring->id].ringbuf = ringbuf; ctx->engine[ring->id].state = ctx_obj; - if (ctx != ring->default_context && ring->init_context) { + if (ctx != ctx->i915->kernel_context && ring->init_context) { struct drm_i915_gem_request *req; - ret = i915_gem_request_alloc(ring, - ctx, &req); - if (ret) { - DRM_ERROR("ring create req: %d\n", - ret); + req = i915_gem_request_alloc(ring, ctx); + if (IS_ERR(req)) { + ret = PTR_ERR(req); + DRM_ERROR("ring create req: %d\n", ret); goto error_ringbuf; } diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h index 0b821b91723a..49af638f6213 100644 --- a/drivers/gpu/drm/i915/intel_lrc.h +++ b/drivers/gpu/drm/i915/intel_lrc.h @@ -25,8 +25,6 @@ #define _INTEL_LRC_H_ #define GEN8_LR_CONTEXT_ALIGN 4096 -#define GEN8_CSB_ENTRIES 6 -#define GEN8_CSB_PTR_MASK 0x07 /* Execlists regs */ #define RING_ELSP(ring) _MMIO((ring)->mmio_base + 0x230) @@ -40,6 +38,22 @@ #define RING_CONTEXT_STATUS_BUF_HI(ring, i) _MMIO((ring)->mmio_base + 0x370 + (i) * 8 + 4) #define RING_CONTEXT_STATUS_PTR(ring) _MMIO((ring)->mmio_base + 0x3a0) +/* The docs specify that the write pointer wraps around after 5h, "After status + * is written out to the last available status QW at offset 5h, this pointer + * wraps to 0." + * + * Therefore, one must infer than even though there are 3 bits available, 6 and + * 7 appear to be * reserved. + */ +#define GEN8_CSB_ENTRIES 6 +#define GEN8_CSB_PTR_MASK 0x7 +#define GEN8_CSB_READ_PTR_MASK (GEN8_CSB_PTR_MASK << 8) +#define GEN8_CSB_WRITE_PTR_MASK (GEN8_CSB_PTR_MASK << 0) +#define GEN8_CSB_WRITE_PTR(csb_status) \ + (((csb_status) & GEN8_CSB_WRITE_PTR_MASK) >> 0) +#define GEN8_CSB_READ_PTR(csb_status) \ + (((csb_status) & GEN8_CSB_READ_PTR_MASK) >> 8) + /* Logical Rings */ int intel_logical_ring_alloc_request_extras(struct drm_i915_gem_request *request); int intel_logical_ring_reserve_space(struct drm_i915_gem_request *request); @@ -84,6 +98,7 @@ static inline void intel_logical_ring_emit_reg(struct intel_ringbuffer *ringbuf, #define LRC_STATE_PN (LRC_PPHWSP_PN + 1) void intel_lr_context_free(struct intel_context *ctx); +uint32_t intel_lr_context_size(struct intel_engine_cs *ring); int intel_lr_context_deferred_alloc(struct intel_context *ctx, struct intel_engine_cs *ring); void intel_lr_context_unpin(struct drm_i915_gem_request *req); @@ -92,13 +107,15 @@ void intel_lr_context_reset(struct drm_device *dev, uint64_t intel_lr_context_descriptor(struct intel_context *ctx, struct intel_engine_cs *ring); +u32 intel_execlists_ctx_id(struct intel_context *ctx, + struct intel_engine_cs *ring); + /* Execlists */ int intel_sanitize_enable_execlists(struct drm_device *dev, int enable_execlists); struct i915_execbuffer_params; int intel_execlists_submission(struct i915_execbuffer_params *params, struct drm_i915_gem_execbuffer2 *args, struct list_head *vmas); -u32 intel_execlists_ctx_id(struct drm_i915_gem_object *ctx_obj); void intel_lrc_irq_handler(struct intel_engine_cs *ring); void intel_execlists_retire_requests(struct intel_engine_cs *ring); diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index 76f1980a7541..9168413fe204 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -240,9 +240,9 @@ static int intel_overlay_on(struct intel_overlay *overlay) WARN_ON(overlay->active); WARN_ON(IS_I830(dev) && !(dev_priv->quirks & QUIRK_PIPEA_FORCE)); - ret = i915_gem_request_alloc(ring, ring->default_context, &req); - if (ret) - return ret; + req = i915_gem_request_alloc(ring, NULL); + if (IS_ERR(req)) + return PTR_ERR(req); ret = intel_ring_begin(req, 4); if (ret) { @@ -283,9 +283,9 @@ static int intel_overlay_continue(struct intel_overlay *overlay, if (tmp & (1 << 17)) DRM_DEBUG("overlay underrun, DOVSTA: %x\n", tmp); - ret = i915_gem_request_alloc(ring, ring->default_context, &req); - if (ret) - return ret; + req = i915_gem_request_alloc(ring, NULL); + if (IS_ERR(req)) + return PTR_ERR(req); ret = intel_ring_begin(req, 2); if (ret) { @@ -349,9 +349,9 @@ static int intel_overlay_off(struct intel_overlay *overlay) * of the hw. Do it in both cases */ flip_addr |= OFC_UPDATE; - ret = i915_gem_request_alloc(ring, ring->default_context, &req); - if (ret) - return ret; + req = i915_gem_request_alloc(ring, NULL); + if (IS_ERR(req)) + return PTR_ERR(req); ret = intel_ring_begin(req, 6); if (ret) { @@ -423,9 +423,9 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay) /* synchronous slowpath */ struct drm_i915_gem_request *req; - ret = i915_gem_request_alloc(ring, ring->default_context, &req); - if (ret) - return ret; + req = i915_gem_request_alloc(ring, NULL); + if (IS_ERR(req)) + return PTR_ERR(req); ret = intel_ring_begin(req, 2); if (ret) { diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index eb5fa05cf476..20bf854eae8c 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -32,6 +32,8 @@ #include <linux/module.h> /** + * DOC: RC6 + * * RC6 is a special power stage which allows the GPU to enter an very * low-voltage mode when idle, using down to 0V while at this stage. This * stage is entered automatically when the GPU is idle when RC6 support is @@ -1672,6 +1674,9 @@ uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config) if (pipe_h < pfit_h) pipe_h = pfit_h; + if (WARN_ON(!pfit_w || !pfit_h)) + return pixel_rate; + pixel_rate = div_u64((uint64_t) pixel_rate * pipe_w * pipe_h, pfit_w * pfit_h); } @@ -1703,6 +1708,8 @@ static uint32_t ilk_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal, if (WARN(latency == 0, "Latency value missing\n")) return UINT_MAX; + if (WARN_ON(!pipe_htotal)) + return UINT_MAX; ret = (latency * pixel_rate) / (pipe_htotal * 10000); ret = (ret + 1) * horiz_pixels * bytes_per_pixel; @@ -1713,6 +1720,17 @@ static uint32_t ilk_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal, static uint32_t ilk_wm_fbc(uint32_t pri_val, uint32_t horiz_pixels, uint8_t bytes_per_pixel) { + /* + * Neither of these should be possible since this function shouldn't be + * called if the CRTC is off or the plane is invisible. But let's be + * extra paranoid to avoid a potential divide-by-zero if we screw up + * elsewhere in the driver. + */ + if (WARN_ON(!bytes_per_pixel)) + return 0; + if (WARN_ON(!horiz_pixels)) + return 0; + return DIV_ROUND_UP(pri_val * 64, horiz_pixels * bytes_per_pixel) + 2; } @@ -1998,14 +2016,19 @@ static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv, } static uint32_t -hsw_compute_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc) +hsw_compute_linetime_wm(struct drm_device *dev, + struct intel_crtc_state *cstate) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - const struct drm_display_mode *adjusted_mode = &intel_crtc->config->base.adjusted_mode; + const struct drm_display_mode *adjusted_mode = + &cstate->base.adjusted_mode; u32 linetime, ips_linetime; - if (!intel_crtc->active) + if (!cstate->base.active) + return 0; + if (WARN_ON(adjusted_mode->crtc_clock == 0)) + return 0; + if (WARN_ON(dev_priv->cdclk_freq == 0)) return 0; /* The WM are computed with base on how long it takes to fill a single @@ -2277,6 +2300,7 @@ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc, return PTR_ERR(cstate); pipe_wm = &cstate->wm.optimal.ilk; + memset(pipe_wm, 0, sizeof(*pipe_wm)); for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) { ps = drm_atomic_get_plane_state(state, @@ -2313,8 +2337,7 @@ static int ilk_compute_pipe_wm(struct intel_crtc *intel_crtc, pristate, sprstate, curstate, &pipe_wm->wm[0]); if (IS_HASWELL(dev) || IS_BROADWELL(dev)) - pipe_wm->linetime = hsw_compute_linetime_wm(dev, - &intel_crtc->base); + pipe_wm->linetime = hsw_compute_linetime_wm(dev, cstate); /* LP0 watermarks always use 1/2 DDB partitioning */ ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max); @@ -3597,23 +3620,45 @@ static void skl_update_wm(struct drm_crtc *crtc) dev_priv->wm.skl_hw = *results; } -static void ilk_program_watermarks(struct drm_i915_private *dev_priv) +static void ilk_compute_wm_config(struct drm_device *dev, + struct intel_wm_config *config) { - struct drm_device *dev = dev_priv->dev; + struct intel_crtc *crtc; + + /* Compute the currently _active_ config */ + for_each_intel_crtc(dev, crtc) { + const struct intel_pipe_wm *wm = &crtc->wm.active.ilk; + + if (!wm->pipe_enabled) + continue; + + config->sprites_enabled |= wm->sprites_enabled; + config->sprites_scaled |= wm->sprites_scaled; + config->num_pipes_active++; + } +} + +static void ilk_program_watermarks(struct intel_crtc_state *cstate) +{ + struct drm_crtc *crtc = cstate->base.crtc; + struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = to_i915(dev); struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm; struct ilk_wm_maximums max; - struct intel_wm_config *config = &dev_priv->wm.config; + struct intel_wm_config config = {}; struct ilk_wm_values results = {}; enum intel_ddb_partitioning partitioning; - ilk_compute_wm_maximums(dev, 1, config, INTEL_DDB_PART_1_2, &max); - ilk_wm_merge(dev, config, &max, &lp_wm_1_2); + ilk_compute_wm_config(dev, &config); + + ilk_compute_wm_maximums(dev, 1, &config, INTEL_DDB_PART_1_2, &max); + ilk_wm_merge(dev, &config, &max, &lp_wm_1_2); /* 5/6 split only in single pipe config on IVB+ */ if (INTEL_INFO(dev)->gen >= 7 && - config->num_pipes_active == 1 && config->sprites_enabled) { - ilk_compute_wm_maximums(dev, 1, config, INTEL_DDB_PART_5_6, &max); - ilk_wm_merge(dev, config, &max, &lp_wm_5_6); + config.num_pipes_active == 1 && config.sprites_enabled) { + ilk_compute_wm_maximums(dev, 1, &config, INTEL_DDB_PART_5_6, &max); + ilk_wm_merge(dev, &config, &max, &lp_wm_5_6); best_lp_wm = ilk_find_best_result(dev, &lp_wm_1_2, &lp_wm_5_6); } else { @@ -3630,7 +3675,6 @@ static void ilk_program_watermarks(struct drm_i915_private *dev_priv) static void ilk_update_wm(struct drm_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->dev); struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state); @@ -3650,7 +3694,7 @@ static void ilk_update_wm(struct drm_crtc *crtc) intel_crtc->wm.active.ilk = cstate->wm.optimal.ilk; - ilk_program_watermarks(dev_priv); + ilk_program_watermarks(cstate); } static void skl_pipe_wm_active_state(uint32_t val, @@ -4036,7 +4080,7 @@ void intel_update_watermarks(struct drm_crtc *crtc) dev_priv->display.update_wm(crtc); } -/** +/* * Lock protecting IPS related data structures */ DEFINE_SPINLOCK(mchdev_lock); @@ -4509,13 +4553,13 @@ static void intel_print_rc6_info(struct drm_device *dev, u32 mode) } if (HAS_RC6p(dev)) DRM_DEBUG_KMS("Enabling RC6 states: RC6 %s RC6p %s RC6pp %s\n", - (mode & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off", - (mode & GEN6_RC_CTL_RC6p_ENABLE) ? "on" : "off", - (mode & GEN6_RC_CTL_RC6pp_ENABLE) ? "on" : "off"); + onoff(mode & GEN6_RC_CTL_RC6_ENABLE), + onoff(mode & GEN6_RC_CTL_RC6p_ENABLE), + onoff(mode & GEN6_RC_CTL_RC6pp_ENABLE)); else DRM_DEBUG_KMS("Enabling RC6 states: RC6 %s\n", - (mode & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off"); + onoff(mode & GEN6_RC_CTL_RC6_ENABLE)); } static int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6) @@ -4693,8 +4737,7 @@ static void gen9_enable_rc6(struct drm_device *dev) /* 3a: Enable RC6 */ if (intel_enable_rc6(dev) & INTEL_RC6_ENABLE) rc6_mask = GEN6_RC_CTL_RC6_ENABLE; - DRM_INFO("RC6 %s\n", (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ? - "on" : "off"); + DRM_INFO("RC6 %s\n", onoff(rc6_mask & GEN6_RC_CTL_RC6_ENABLE)); /* WaRsUseTimeoutMode */ if (IS_SKL_REVID(dev, 0, SKL_REVID_D0) || IS_BXT_REVID(dev, 0, BXT_REVID_A1)) { @@ -4713,8 +4756,7 @@ static void gen9_enable_rc6(struct drm_device *dev) * 3b: Enable Coarse Power Gating only when RC6 is enabled. * WaRsDisableCoarsePowerGating:skl,bxt - Render/Media PG need to be disabled with RC6. */ - if ((IS_BROXTON(dev) && (INTEL_REVID(dev) < BXT_REVID_B0)) || - ((IS_SKL_GT3(dev) || IS_SKL_GT4(dev)) && (INTEL_REVID(dev) <= SKL_REVID_F0))) + if (NEEDS_WaRsDisableCoarsePowerGating(dev)) I915_WRITE(GEN9_PG_ENABLE, 0); else I915_WRITE(GEN9_PG_ENABLE, (rc6_mask & GEN6_RC_CTL_RC6_ENABLE) ? @@ -6981,6 +7023,7 @@ void intel_init_pm(struct drm_device *dev) dev_priv->wm.spr_latency[0] && dev_priv->wm.cur_latency[0])) { dev_priv->display.update_wm = ilk_update_wm; dev_priv->display.compute_pipe_wm = ilk_compute_pipe_wm; + dev_priv->display.program_watermarks = ilk_program_watermarks; } else { DRM_DEBUG_KMS("Failed to read display plane latency. " "Disable CxSR\n"); diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 40c6aff57256..9030e2bca0c0 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -1867,15 +1867,13 @@ i830_dispatch_execbuffer(struct drm_i915_gem_request *req, offset = cs_offset; } - ret = intel_ring_begin(req, 4); + ret = intel_ring_begin(req, 2); if (ret) return ret; - intel_ring_emit(ring, MI_BATCH_BUFFER); + intel_ring_emit(ring, MI_BATCH_BUFFER_START | MI_BATCH_GTT); intel_ring_emit(ring, offset | (dispatch_flags & I915_DISPATCH_SECURE ? 0 : MI_BATCH_NON_SECURE)); - intel_ring_emit(ring, offset + len - 8); - intel_ring_emit(ring, MI_NOOP); intel_ring_advance(ring); return 0; @@ -1901,6 +1899,17 @@ i915_dispatch_execbuffer(struct drm_i915_gem_request *req, return 0; } +static void cleanup_phys_status_page(struct intel_engine_cs *ring) +{ + struct drm_i915_private *dev_priv = to_i915(ring->dev); + + if (!dev_priv->status_page_dmah) + return; + + drm_pci_free(ring->dev, dev_priv->status_page_dmah); + ring->status_page.page_addr = NULL; +} + static void cleanup_status_page(struct intel_engine_cs *ring) { struct drm_i915_gem_object *obj; @@ -1917,9 +1926,9 @@ static void cleanup_status_page(struct intel_engine_cs *ring) static int init_status_page(struct intel_engine_cs *ring) { - struct drm_i915_gem_object *obj; + struct drm_i915_gem_object *obj = ring->status_page.obj; - if ((obj = ring->status_page.obj) == NULL) { + if (obj == NULL) { unsigned flags; int ret; @@ -1990,6 +1999,7 @@ void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf) else iounmap(ringbuf->virtual_start); ringbuf->virtual_start = NULL; + ringbuf->vma = NULL; i915_gem_object_ggtt_unpin(ringbuf->obj); } @@ -2056,6 +2066,8 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev, } } + ringbuf->vma = i915_gem_obj_to_ggtt(obj); + return 0; } @@ -2164,7 +2176,7 @@ static int intel_init_ring_buffer(struct drm_device *dev, if (ret) goto error; } else { - BUG_ON(ring->id != RCS); + WARN_ON(ring->id != RCS); ret = init_phys_status_page(ring); if (ret) goto error; @@ -2210,7 +2222,12 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring) if (ring->cleanup) ring->cleanup(ring); - cleanup_status_page(ring); + if (I915_NEED_GFX_HWS(ring->dev)) { + cleanup_status_page(ring); + } else { + WARN_ON(ring->id != RCS); + cleanup_phys_status_page(ring); + } i915_cmd_parser_fini_ring(ring); i915_gem_batch_pool_fini(&ring->batch_pool); @@ -2666,6 +2683,7 @@ int intel_init_render_ring_buffer(struct drm_device *dev) ring->name = "render ring"; ring->id = RCS; + ring->exec_id = I915_EXEC_RENDER; ring->mmio_base = RENDER_RING_BASE; if (INTEL_INFO(dev)->gen >= 8) { @@ -2814,6 +2832,7 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev) ring->name = "bsd ring"; ring->id = VCS; + ring->exec_id = I915_EXEC_BSD; ring->write_tail = ring_write_tail; if (INTEL_INFO(dev)->gen >= 6) { @@ -2890,6 +2909,7 @@ int intel_init_bsd2_ring_buffer(struct drm_device *dev) ring->name = "bsd2 ring"; ring->id = VCS2; + ring->exec_id = I915_EXEC_BSD; ring->write_tail = ring_write_tail; ring->mmio_base = GEN8_BSD2_RING_BASE; @@ -2920,6 +2940,7 @@ int intel_init_blt_ring_buffer(struct drm_device *dev) ring->name = "blitter ring"; ring->id = BCS; + ring->exec_id = I915_EXEC_BLT; ring->mmio_base = BLT_RING_BASE; ring->write_tail = ring_write_tail; @@ -2977,6 +2998,7 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev) ring->name = "video enhancement ring"; ring->id = VECS; + ring->exec_id = I915_EXEC_VEBOX; ring->mmio_base = VEBOX_RING_BASE; ring->write_tail = ring_write_tail; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 49574ffe54bc..b12f2aabd104 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -93,11 +93,13 @@ struct intel_ring_hangcheck { int score; enum intel_ring_hangcheck_action action; int deadlock; + u32 instdone[I915_NUM_INSTDONE_REG]; }; struct intel_ringbuffer { struct drm_i915_gem_object *obj; void __iomem *virtual_start; + struct i915_vma *vma; struct intel_engine_cs *ring; struct list_head link; @@ -147,14 +149,15 @@ struct i915_ctx_workarounds { struct intel_engine_cs { const char *name; enum intel_ring_id { - RCS = 0x0, - VCS, + RCS = 0, BCS, - VECS, - VCS2 + VCS, + VCS2, /* Keep instances of the same type engine together. */ + VECS } id; #define I915_NUM_RINGS 5 -#define LAST_USER_RING (VECS + 1) +#define _VCS(n) (VCS + (n)) + unsigned int exec_id; u32 mmio_base; struct drm_device *dev; struct intel_ringbuffer *buffer; @@ -268,6 +271,8 @@ struct intel_engine_cs { struct list_head execlist_queue; struct list_head execlist_retired_req_list; u8 next_context_status_buffer; + bool disable_lite_restore_wa; + u32 ctx_desc_template; u32 irq_keep_mask; /* bitmask for interrupts that should not be masked */ int (*emit_request)(struct drm_i915_gem_request *request); int (*emit_flush)(struct drm_i915_gem_request *request, @@ -305,7 +310,6 @@ struct intel_engine_cs { wait_queue_head_t irq_queue; - struct intel_context *default_context; struct intel_context *last_context; struct intel_ring_hangcheck hangcheck; @@ -406,7 +410,7 @@ intel_write_status_page(struct intel_engine_cs *ring, ring->status_page.page_addr[reg] = value; } -/** +/* * Reads a dword out of the status page, which is written to from the command * queue by automatic updates, MI_REPORT_HEAD, MI_STORE_DATA_INDEX, or * MI_STORE_DATA_IMM. @@ -423,6 +427,7 @@ intel_write_status_page(struct intel_engine_cs *ring, * The area from dword 0x30 to 0x3ff is available for driver usage. */ #define I915_GEM_HWS_INDEX 0x30 +#define I915_GEM_HWS_INDEX_ADDR (I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT) #define I915_GEM_HWS_SCRATCH_INDEX 0x40 #define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT) diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index ddbdbffe829a..bbca527184d0 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -532,7 +532,8 @@ static void assert_can_enable_dc5(struct drm_i915_private *dev_priv) bool pg2_enabled = intel_display_power_well_is_enabled(dev_priv, SKL_DISP_PW_2); - WARN_ONCE(!IS_SKYLAKE(dev), "Platform doesn't support DC5.\n"); + WARN_ONCE(!IS_SKYLAKE(dev) && !IS_KABYLAKE(dev), + "Platform doesn't support DC5.\n"); WARN_ONCE(!HAS_RUNTIME_PM(dev), "Runtime PM not enabled.\n"); WARN_ONCE(pg2_enabled, "PG2 not disabled to enable DC5.\n"); @@ -568,7 +569,8 @@ static void assert_can_enable_dc6(struct drm_i915_private *dev_priv) { struct drm_device *dev = dev_priv->dev; - WARN_ONCE(!IS_SKYLAKE(dev), "Platform doesn't support DC6.\n"); + WARN_ONCE(!IS_SKYLAKE(dev) && !IS_KABYLAKE(dev), + "Platform doesn't support DC6.\n"); WARN_ONCE(!HAS_RUNTIME_PM(dev), "Runtime PM not enabled.\n"); WARN_ONCE(I915_READ(UTIL_PIN_CTL) & UTIL_PIN_ENABLE, "Backlight is not disabled.\n"); @@ -595,7 +597,8 @@ static void gen9_disable_dc5_dc6(struct drm_i915_private *dev_priv) { assert_can_disable_dc5(dev_priv); - if (IS_SKYLAKE(dev_priv) && i915.enable_dc != 0 && i915.enable_dc != 1) + if ((IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) && + i915.enable_dc != 0 && i915.enable_dc != 1) assert_can_disable_dc6(dev_priv); gen9_set_dc_state(dev_priv, DC_STATE_DISABLE); @@ -623,7 +626,6 @@ void skl_disable_dc6(struct drm_i915_private *dev_priv) static void skl_set_power_well(struct drm_i915_private *dev_priv, struct i915_power_well *power_well, bool enable) { - struct drm_device *dev = dev_priv->dev; uint32_t tmp, fuse_status; uint32_t req_mask, state_mask; bool is_enabled, enable_requested, check_fuse_status = false; @@ -667,17 +669,6 @@ static void skl_set_power_well(struct drm_i915_private *dev_priv, !I915_READ(HSW_PWR_WELL_BIOS), "Invalid for power well status to be enabled, unless done by the BIOS, \ when request is to disable!\n"); - if (power_well->data == SKL_DISP_PW_2) { - /* - * DDI buffer programming unnecessary during - * driver-load/resume as it's already done - * during modeset initialization then. It's - * also invalid here as encoder list is still - * uninitialized. - */ - if (!dev_priv->power_domains.initializing) - intel_prepare_ddi(dev); - } I915_WRITE(HSW_PWR_WELL_DRIVER, tmp | req_mask); } @@ -783,7 +774,8 @@ static void gen9_dc_off_power_well_enable(struct drm_i915_private *dev_priv, static void gen9_dc_off_power_well_disable(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { - if (IS_SKYLAKE(dev_priv) && i915.enable_dc != 0 && i915.enable_dc != 1) + if ((IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) && + i915.enable_dc != 0 && i915.enable_dc != 1) skl_enable_dc6(dev_priv); else gen9_enable_dc5(dev_priv); @@ -795,7 +787,8 @@ static void gen9_dc_off_power_well_sync_hw(struct drm_i915_private *dev_priv, if (power_well->count > 0) { gen9_set_dc_state(dev_priv, DC_STATE_DISABLE); } else { - if (IS_SKYLAKE(dev_priv) && i915.enable_dc != 0 && + if ((IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) && + i915.enable_dc != 0 && i915.enable_dc != 1) gen9_set_dc_state(dev_priv, DC_STATE_EN_UPTO_DC6); else @@ -1851,7 +1844,7 @@ void skl_pw1_misc_io_init(struct drm_i915_private *dev_priv) { struct i915_power_well *well; - if (!IS_SKYLAKE(dev_priv)) + if (!(IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))) return; well = lookup_power_well(dev_priv, SKL_DISP_PW_1); @@ -1865,7 +1858,7 @@ void skl_pw1_misc_io_fini(struct drm_i915_private *dev_priv) { struct i915_power_well *well; - if (!IS_SKYLAKE(dev_priv)) + if (!(IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))) return; well = lookup_power_well(dev_priv, SKL_DISP_PW_1); diff --git a/drivers/gpu/drm/i915/intel_sdvo_regs.h b/drivers/gpu/drm/i915/intel_sdvo_regs.h index 2e2d4eb4a00d..db0ed499268a 100644 --- a/drivers/gpu/drm/i915/intel_sdvo_regs.h +++ b/drivers/gpu/drm/i915/intel_sdvo_regs.h @@ -24,8 +24,8 @@ * Eric Anholt <eric@anholt.net> */ -/** - * @file SDVO command definitions and structures. +/* + * SDVO command definitions and structures. */ #define SDVO_OUTPUT_FIRST (0) @@ -66,39 +66,39 @@ struct intel_sdvo_caps { #define DTD_FLAG_VSYNC_POSITIVE (1 << 2) #define DTD_FLAG_INTERLACE (1 << 7) -/** This matches the EDID DTD structure, more or less */ +/* This matches the EDID DTD structure, more or less */ struct intel_sdvo_dtd { struct { - u16 clock; /**< pixel clock, in 10kHz units */ - u8 h_active; /**< lower 8 bits (pixels) */ - u8 h_blank; /**< lower 8 bits (pixels) */ - u8 h_high; /**< upper 4 bits each h_active, h_blank */ - u8 v_active; /**< lower 8 bits (lines) */ - u8 v_blank; /**< lower 8 bits (lines) */ - u8 v_high; /**< upper 4 bits each v_active, v_blank */ + u16 clock; /* pixel clock, in 10kHz units */ + u8 h_active; /* lower 8 bits (pixels) */ + u8 h_blank; /* lower 8 bits (pixels) */ + u8 h_high; /* upper 4 bits each h_active, h_blank */ + u8 v_active; /* lower 8 bits (lines) */ + u8 v_blank; /* lower 8 bits (lines) */ + u8 v_high; /* upper 4 bits each v_active, v_blank */ } part1; struct { - u8 h_sync_off; /**< lower 8 bits, from hblank start */ - u8 h_sync_width; /**< lower 8 bits (pixels) */ - /** lower 4 bits each vsync offset, vsync width */ + u8 h_sync_off; /* lower 8 bits, from hblank start */ + u8 h_sync_width; /* lower 8 bits (pixels) */ + /* lower 4 bits each vsync offset, vsync width */ u8 v_sync_off_width; - /** + /* * 2 high bits of hsync offset, 2 high bits of hsync width, * bits 4-5 of vsync offset, and 2 high bits of vsync width. */ u8 sync_off_width_high; u8 dtd_flags; u8 sdvo_flags; - /** bits 6-7 of vsync offset at bits 6-7 */ + /* bits 6-7 of vsync offset at bits 6-7 */ u8 v_sync_off_high; u8 reserved; } part2; } __packed; struct intel_sdvo_pixel_clock_range { - u16 min; /**< pixel clock, in 10kHz units */ - u16 max; /**< pixel clock, in 10kHz units */ + u16 min; /* pixel clock, in 10kHz units */ + u16 max; /* pixel clock, in 10kHz units */ } __packed; struct intel_sdvo_preferred_input_timing_args { @@ -144,7 +144,7 @@ struct intel_sdvo_preferred_input_timing_args { #define SDVO_CMD_RESET 0x01 -/** Returns a struct intel_sdvo_caps */ +/* Returns a struct intel_sdvo_caps */ #define SDVO_CMD_GET_DEVICE_CAPS 0x02 #define SDVO_CMD_GET_FIRMWARE_REV 0x86 @@ -152,7 +152,7 @@ struct intel_sdvo_preferred_input_timing_args { # define SDVO_DEVICE_FIRMWARE_MAJOR SDVO_I2C_RETURN_1 # define SDVO_DEVICE_FIRMWARE_PATCH SDVO_I2C_RETURN_2 -/** +/* * Reports which inputs are trained (managed to sync). * * Devices must have trained within 2 vsyncs of a mode change. @@ -164,10 +164,10 @@ struct intel_sdvo_get_trained_inputs_response { unsigned int pad:6; } __packed; -/** Returns a struct intel_sdvo_output_flags of active outputs. */ +/* Returns a struct intel_sdvo_output_flags of active outputs. */ #define SDVO_CMD_GET_ACTIVE_OUTPUTS 0x04 -/** +/* * Sets the current set of active outputs. * * Takes a struct intel_sdvo_output_flags. Must be preceded by a SET_IN_OUT_MAP @@ -175,7 +175,7 @@ struct intel_sdvo_get_trained_inputs_response { */ #define SDVO_CMD_SET_ACTIVE_OUTPUTS 0x05 -/** +/* * Returns the current mapping of SDVO inputs to outputs on the device. * * Returns two struct intel_sdvo_output_flags structures. @@ -185,29 +185,29 @@ struct intel_sdvo_in_out_map { u16 in0, in1; }; -/** +/* * Sets the current mapping of SDVO inputs to outputs on the device. * * Takes two struct i380_sdvo_output_flags structures. */ #define SDVO_CMD_SET_IN_OUT_MAP 0x07 -/** +/* * Returns a struct intel_sdvo_output_flags of attached displays. */ #define SDVO_CMD_GET_ATTACHED_DISPLAYS 0x0b -/** +/* * Returns a struct intel_sdvo_ouptut_flags of displays supporting hot plugging. */ #define SDVO_CMD_GET_HOT_PLUG_SUPPORT 0x0c -/** +/* * Takes a struct intel_sdvo_output_flags. */ #define SDVO_CMD_SET_ACTIVE_HOT_PLUG 0x0d -/** +/* * Returns a struct intel_sdvo_output_flags of displays with hot plug * interrupts enabled. */ @@ -221,7 +221,7 @@ struct intel_sdvo_get_interrupt_event_source_response { unsigned int pad:6; } __packed; -/** +/* * Selects which input is affected by future input commands. * * Commands affected include SET_INPUT_TIMINGS_PART[12], @@ -234,7 +234,7 @@ struct intel_sdvo_set_target_input_args { unsigned int pad:7; } __packed; -/** +/* * Takes a struct intel_sdvo_output_flags of which outputs are targeted by * future output commands. * @@ -280,7 +280,7 @@ struct intel_sdvo_set_target_input_args { # define SDVO_DTD_SDVO_FLAG_SCALING_SMOOTH (2 << 4) # define SDVO_DTD_VSYNC_OFF_HIGH SDVO_I2C_ARG_6 -/** +/* * Generates a DTD based on the given width, height, and flags. * * This will be supported by any device supporting scaling or interlaced @@ -300,24 +300,24 @@ struct intel_sdvo_set_target_input_args { #define SDVO_CMD_GET_PREFERRED_INPUT_TIMING_PART1 0x1b #define SDVO_CMD_GET_PREFERRED_INPUT_TIMING_PART2 0x1c -/** Returns a struct intel_sdvo_pixel_clock_range */ +/* Returns a struct intel_sdvo_pixel_clock_range */ #define SDVO_CMD_GET_INPUT_PIXEL_CLOCK_RANGE 0x1d -/** Returns a struct intel_sdvo_pixel_clock_range */ +/* Returns a struct intel_sdvo_pixel_clock_range */ #define SDVO_CMD_GET_OUTPUT_PIXEL_CLOCK_RANGE 0x1e -/** Returns a byte bitfield containing SDVO_CLOCK_RATE_MULT_* flags */ +/* Returns a byte bitfield containing SDVO_CLOCK_RATE_MULT_* flags */ #define SDVO_CMD_GET_SUPPORTED_CLOCK_RATE_MULTS 0x1f -/** Returns a byte containing a SDVO_CLOCK_RATE_MULT_* flag */ +/* Returns a byte containing a SDVO_CLOCK_RATE_MULT_* flag */ #define SDVO_CMD_GET_CLOCK_RATE_MULT 0x20 -/** Takes a byte containing a SDVO_CLOCK_RATE_MULT_* flag */ +/* Takes a byte containing a SDVO_CLOCK_RATE_MULT_* flag */ #define SDVO_CMD_SET_CLOCK_RATE_MULT 0x21 # define SDVO_CLOCK_RATE_MULT_1X (1 << 0) # define SDVO_CLOCK_RATE_MULT_2X (1 << 1) # define SDVO_CLOCK_RATE_MULT_4X (1 << 3) #define SDVO_CMD_GET_SUPPORTED_TV_FORMATS 0x27 -/** 6 bytes of bit flags for TV formats shared by all TV format functions */ +/* 6 bytes of bit flags for TV formats shared by all TV format functions */ struct intel_sdvo_tv_format { unsigned int ntsc_m:1; unsigned int ntsc_j:1; @@ -376,7 +376,7 @@ struct intel_sdvo_tv_format { #define SDVO_CMD_SET_TV_FORMAT 0x29 -/** Returns the resolutiosn that can be used with the given TV format */ +/* Returns the resolutiosn that can be used with the given TV format */ #define SDVO_CMD_GET_SDTV_RESOLUTION_SUPPORT 0x83 struct intel_sdvo_sdtv_resolution_request { unsigned int ntsc_m:1; @@ -539,7 +539,7 @@ struct intel_sdvo_hdtv_resolution_reply { #define SDVO_CMD_GET_MAX_PANEL_POWER_SEQUENCING 0x2d #define SDVO_CMD_GET_PANEL_POWER_SEQUENCING 0x2e #define SDVO_CMD_SET_PANEL_POWER_SEQUENCING 0x2f -/** +/* * The panel power sequencing parameters are in units of milliseconds. * The high fields are bits 8:9 of the 10-bit values. */ diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 4ff7a1f4183e..0875c8e0ec0a 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -178,28 +178,33 @@ void intel_pipe_update_end(struct intel_crtc *crtc) } static void -skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int crtc_x, int crtc_y, - unsigned int crtc_w, unsigned int crtc_h, - uint32_t x, uint32_t y, - uint32_t src_w, uint32_t src_h) +skl_update_plane(struct drm_plane *drm_plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { struct drm_device *dev = drm_plane->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_plane *intel_plane = to_intel_plane(drm_plane); + struct drm_framebuffer *fb = plane_state->base.fb; struct drm_i915_gem_object *obj = intel_fb_obj(fb); const int pipe = intel_plane->pipe; const int plane = intel_plane->plane + 1; u32 plane_ctl, stride_div, stride; - const struct drm_intel_sprite_colorkey *key = - &to_intel_plane_state(drm_plane->state)->ckey; + const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; u32 surf_addr; u32 tile_height, plane_offset, plane_size; unsigned int rotation; int x_offset, y_offset; - struct intel_crtc_state *crtc_state = to_intel_crtc(crtc)->config; - int scaler_id; + int crtc_x = plane_state->dst.x1; + int crtc_y = plane_state->dst.y1; + uint32_t crtc_w = drm_rect_width(&plane_state->dst); + uint32_t crtc_h = drm_rect_height(&plane_state->dst); + uint32_t x = plane_state->src.x1 >> 16; + uint32_t y = plane_state->src.y1 >> 16; + uint32_t src_w = drm_rect_width(&plane_state->src) >> 16; + uint32_t src_h = drm_rect_height(&plane_state->src) >> 16; + const struct intel_scaler *scaler = + &crtc_state->scaler_state.scalers[plane_state->scaler_id]; plane_ctl = PLANE_CTL_ENABLE | PLANE_CTL_PIPE_GAMMA_ENABLE | @@ -208,14 +213,12 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc, plane_ctl |= skl_plane_ctl_format(fb->pixel_format); plane_ctl |= skl_plane_ctl_tiling(fb->modifier[0]); - rotation = drm_plane->state->rotation; + rotation = plane_state->base.rotation; plane_ctl |= skl_plane_ctl_rotation(rotation); - stride_div = intel_fb_stride_alignment(dev, fb->modifier[0], + stride_div = intel_fb_stride_alignment(dev_priv, fb->modifier[0], fb->pixel_format); - scaler_id = to_intel_plane_state(drm_plane->state)->scaler_id; - /* Sizes are 0 based */ src_w--; src_h--; @@ -236,9 +239,10 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc, surf_addr = intel_plane_obj_offset(intel_plane, obj, 0); if (intel_rotation_90_or_270(rotation)) { + int cpp = drm_format_plane_cpp(fb->pixel_format, 0); + /* stride: Surface height in tiles */ - tile_height = intel_tile_height(dev, fb->pixel_format, - fb->modifier[0], 0); + tile_height = intel_tile_height(dev_priv, fb->modifier[0], cpp); stride = DIV_ROUND_UP(fb->height, tile_height); plane_size = (src_w << 16) | src_h; x_offset = stride * tile_height - y - (src_h + 1); @@ -256,13 +260,13 @@ skl_update_plane(struct drm_plane *drm_plane, struct drm_crtc *crtc, I915_WRITE(PLANE_SIZE(pipe, plane), plane_size); /* program plane scaler */ - if (scaler_id >= 0) { + if (plane_state->scaler_id >= 0) { uint32_t ps_ctrl = 0; + int scaler_id = plane_state->scaler_id; DRM_DEBUG_KMS("plane = %d PS_PLANE_SEL(plane) = 0x%x\n", plane, PS_PLANE_SEL(plane)); - ps_ctrl = PS_SCALER_EN | PS_PLANE_SEL(plane) | - crtc_state->scaler_state.scalers[scaler_id].mode; + ps_ctrl = PS_SCALER_EN | PS_PLANE_SEL(plane) | scaler->mode; I915_WRITE(SKL_PS_CTRL(pipe, scaler_id), ps_ctrl); I915_WRITE(SKL_PS_PWR_GATE(pipe, scaler_id), 0); I915_WRITE(SKL_PS_WIN_POS(pipe, scaler_id), (crtc_x << 16) | crtc_y); @@ -334,24 +338,29 @@ chv_update_csc(struct intel_plane *intel_plane, uint32_t format) } static void -vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int crtc_x, int crtc_y, - unsigned int crtc_w, unsigned int crtc_h, - uint32_t x, uint32_t y, - uint32_t src_w, uint32_t src_h) +vlv_update_plane(struct drm_plane *dplane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { struct drm_device *dev = dplane->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_plane *intel_plane = to_intel_plane(dplane); + struct drm_framebuffer *fb = plane_state->base.fb; struct drm_i915_gem_object *obj = intel_fb_obj(fb); int pipe = intel_plane->pipe; int plane = intel_plane->plane; u32 sprctl; unsigned long sprsurf_offset, linear_offset; int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); - const struct drm_intel_sprite_colorkey *key = - &to_intel_plane_state(dplane->state)->ckey; + const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; + int crtc_x = plane_state->dst.x1; + int crtc_y = plane_state->dst.y1; + uint32_t crtc_w = drm_rect_width(&plane_state->dst); + uint32_t crtc_h = drm_rect_height(&plane_state->dst); + uint32_t x = plane_state->src.x1 >> 16; + uint32_t y = plane_state->src.y1 >> 16; + uint32_t src_w = drm_rect_width(&plane_state->src) >> 16; + uint32_t src_h = drm_rect_height(&plane_state->src) >> 16; sprctl = SP_ENABLE; @@ -414,14 +423,13 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc, crtc_h--; linear_offset = y * fb->pitches[0] + x * pixel_size; - sprsurf_offset = intel_gen4_compute_page_offset(dev_priv, - &x, &y, - obj->tiling_mode, - pixel_size, - fb->pitches[0]); + sprsurf_offset = intel_compute_tile_offset(dev_priv, &x, &y, + fb->modifier[0], + pixel_size, + fb->pitches[0]); linear_offset -= sprsurf_offset; - if (dplane->state->rotation == BIT(DRM_ROTATE_180)) { + if (plane_state->base.rotation == BIT(DRM_ROTATE_180)) { sprctl |= SP_ROTATE_180; x += src_w; @@ -474,23 +482,28 @@ vlv_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc) } static void -ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int crtc_x, int crtc_y, - unsigned int crtc_w, unsigned int crtc_h, - uint32_t x, uint32_t y, - uint32_t src_w, uint32_t src_h) +ivb_update_plane(struct drm_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { struct drm_device *dev = plane->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_plane *intel_plane = to_intel_plane(plane); + struct drm_framebuffer *fb = plane_state->base.fb; struct drm_i915_gem_object *obj = intel_fb_obj(fb); enum pipe pipe = intel_plane->pipe; u32 sprctl, sprscale = 0; unsigned long sprsurf_offset, linear_offset; int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); - const struct drm_intel_sprite_colorkey *key = - &to_intel_plane_state(plane->state)->ckey; + const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; + int crtc_x = plane_state->dst.x1; + int crtc_y = plane_state->dst.y1; + uint32_t crtc_w = drm_rect_width(&plane_state->dst); + uint32_t crtc_h = drm_rect_height(&plane_state->dst); + uint32_t x = plane_state->src.x1 >> 16; + uint32_t y = plane_state->src.y1 >> 16; + uint32_t src_w = drm_rect_width(&plane_state->src) >> 16; + uint32_t src_h = drm_rect_height(&plane_state->src) >> 16; sprctl = SPRITE_ENABLE; @@ -544,13 +557,13 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, sprscale = SPRITE_SCALE_ENABLE | (src_w << 16) | src_h; linear_offset = y * fb->pitches[0] + x * pixel_size; - sprsurf_offset = - intel_gen4_compute_page_offset(dev_priv, - &x, &y, obj->tiling_mode, - pixel_size, fb->pitches[0]); + sprsurf_offset = intel_compute_tile_offset(dev_priv, &x, &y, + fb->modifier[0], + pixel_size, + fb->pitches[0]); linear_offset -= sprsurf_offset; - if (plane->state->rotation == BIT(DRM_ROTATE_180)) { + if (plane_state->base.rotation == BIT(DRM_ROTATE_180)) { sprctl |= SPRITE_ROTATE_180; /* HSW and BDW does this automagically in hardware */ @@ -612,23 +625,28 @@ ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc) } static void -ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int crtc_x, int crtc_y, - unsigned int crtc_w, unsigned int crtc_h, - uint32_t x, uint32_t y, - uint32_t src_w, uint32_t src_h) +ilk_update_plane(struct drm_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { struct drm_device *dev = plane->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_plane *intel_plane = to_intel_plane(plane); + struct drm_framebuffer *fb = plane_state->base.fb; struct drm_i915_gem_object *obj = intel_fb_obj(fb); int pipe = intel_plane->pipe; unsigned long dvssurf_offset, linear_offset; u32 dvscntr, dvsscale; int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0); - const struct drm_intel_sprite_colorkey *key = - &to_intel_plane_state(plane->state)->ckey; + const struct drm_intel_sprite_colorkey *key = &plane_state->ckey; + int crtc_x = plane_state->dst.x1; + int crtc_y = plane_state->dst.y1; + uint32_t crtc_w = drm_rect_width(&plane_state->dst); + uint32_t crtc_h = drm_rect_height(&plane_state->dst); + uint32_t x = plane_state->src.x1 >> 16; + uint32_t y = plane_state->src.y1 >> 16; + uint32_t src_w = drm_rect_width(&plane_state->src) >> 16; + uint32_t src_h = drm_rect_height(&plane_state->src) >> 16; dvscntr = DVS_ENABLE; @@ -678,13 +696,13 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, dvsscale = DVS_SCALE_ENABLE | (src_w << 16) | src_h; linear_offset = y * fb->pitches[0] + x * pixel_size; - dvssurf_offset = - intel_gen4_compute_page_offset(dev_priv, - &x, &y, obj->tiling_mode, - pixel_size, fb->pitches[0]); + dvssurf_offset = intel_compute_tile_offset(dev_priv, &x, &y, + fb->modifier[0], + pixel_size, + fb->pitches[0]); linear_offset -= dvssurf_offset; - if (plane->state->rotation == BIT(DRM_ROTATE_180)) { + if (plane_state->base.rotation == BIT(DRM_ROTATE_180)) { dvscntr |= DVS_ROTATE_180; x += src_w; @@ -913,30 +931,6 @@ intel_check_sprite_plane(struct drm_plane *plane, return 0; } -static void -intel_commit_sprite_plane(struct drm_plane *plane, - struct intel_plane_state *state) -{ - struct drm_crtc *crtc = state->base.crtc; - struct intel_plane *intel_plane = to_intel_plane(plane); - struct drm_framebuffer *fb = state->base.fb; - - crtc = crtc ? crtc : plane->crtc; - - if (state->visible) { - intel_plane->update_plane(plane, crtc, fb, - state->dst.x1, state->dst.y1, - drm_rect_width(&state->dst), - drm_rect_height(&state->dst), - state->src.x1 >> 16, - state->src.y1 >> 16, - drm_rect_width(&state->src) >> 16, - drm_rect_height(&state->src) >> 16); - } else { - intel_plane->disable_plane(plane, crtc); - } -} - int intel_sprite_set_colorkey(struct drm_device *dev, void *data, struct drm_file *file_priv) { @@ -1118,7 +1112,6 @@ intel_plane_init(struct drm_device *dev, enum pipe pipe, int plane) intel_plane->plane = plane; intel_plane->frontbuffer_bit = INTEL_FRONTBUFFER_SPRITE(pipe, plane); intel_plane->check_plane = intel_check_sprite_plane; - intel_plane->commit_plane = intel_commit_sprite_plane; possible_crtcs = (1 << pipe); ret = drm_universal_plane_init(dev, &intel_plane->base, possible_crtcs, &intel_plane_funcs, diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 277e60ae0e47..bfa79e5c214e 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -327,13 +327,54 @@ static void intel_uncore_ellc_detect(struct drm_device *dev) } } +static bool +fpga_check_for_unclaimed_mmio(struct drm_i915_private *dev_priv) +{ + u32 dbg; + + dbg = __raw_i915_read32(dev_priv, FPGA_DBG); + if (likely(!(dbg & FPGA_DBG_RM_NOCLAIM))) + return false; + + __raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM); + + return true; +} + +static bool +vlv_check_for_unclaimed_mmio(struct drm_i915_private *dev_priv) +{ + u32 cer; + + cer = __raw_i915_read32(dev_priv, CLAIM_ER); + if (likely(!(cer & (CLAIM_ER_OVERFLOW | CLAIM_ER_CTR_MASK)))) + return false; + + __raw_i915_write32(dev_priv, CLAIM_ER, CLAIM_ER_CLR); + + return true; +} + +static bool +check_for_unclaimed_mmio(struct drm_i915_private *dev_priv) +{ + if (HAS_FPGA_DBG_UNCLAIMED(dev_priv)) + return fpga_check_for_unclaimed_mmio(dev_priv); + + if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) + return vlv_check_for_unclaimed_mmio(dev_priv); + + return false; +} + static void __intel_uncore_early_sanitize(struct drm_device *dev, bool restore_forcewake) { struct drm_i915_private *dev_priv = dev->dev_private; - if (HAS_FPGA_DBG_UNCLAIMED(dev)) - __raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM); + /* clear out unclaimed reg detection bit */ + if (check_for_unclaimed_mmio(dev_priv)) + DRM_DEBUG("unclaimed mmio detected on uncore init, clearing\n"); /* clear out old GT FIFO errors */ if (IS_GEN6(dev) || IS_GEN7(dev)) @@ -585,38 +626,38 @@ ilk_dummy_write(struct drm_i915_private *dev_priv) } static void -hsw_unclaimed_reg_debug(struct drm_i915_private *dev_priv, - i915_reg_t reg, bool read, bool before) +__unclaimed_reg_debug(struct drm_i915_private *dev_priv, + const i915_reg_t reg, + const bool read, + const bool before) { - const char *op = read ? "reading" : "writing to"; - const char *when = before ? "before" : "after"; - - if (!i915.mmio_debug) + /* XXX. We limit the auto arming traces for mmio + * debugs on these platforms. There are just too many + * revealed by these and CI/Bat suffers from the noise. + * Please fix and then re-enable the automatic traces. + */ + if (i915.mmio_debug < 2 && + (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))) return; - if (__raw_i915_read32(dev_priv, FPGA_DBG) & FPGA_DBG_RM_NOCLAIM) { - WARN(1, "Unclaimed register detected %s %s register 0x%x\n", - when, op, i915_mmio_reg_offset(reg)); - __raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM); + if (WARN(check_for_unclaimed_mmio(dev_priv), + "Unclaimed register detected %s %s register 0x%x\n", + before ? "before" : "after", + read ? "reading" : "writing to", + i915_mmio_reg_offset(reg))) i915.mmio_debug--; /* Only report the first N failures */ - } } -static void -hsw_unclaimed_reg_detect(struct drm_i915_private *dev_priv) +static inline void +unclaimed_reg_debug(struct drm_i915_private *dev_priv, + const i915_reg_t reg, + const bool read, + const bool before) { - static bool mmio_debug_once = true; - - if (i915.mmio_debug || !mmio_debug_once) + if (likely(!i915.mmio_debug)) return; - if (__raw_i915_read32(dev_priv, FPGA_DBG) & FPGA_DBG_RM_NOCLAIM) { - DRM_DEBUG("Unclaimed register detected, " - "enabling oneshot unclaimed register reporting. " - "Please use i915.mmio_debug=N for more information.\n"); - __raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM); - i915.mmio_debug = mmio_debug_once--; - } + __unclaimed_reg_debug(dev_priv, reg, read, before); } #define GEN2_READ_HEADER(x) \ @@ -664,9 +705,11 @@ __gen2_read(64) unsigned long irqflags; \ u##x val = 0; \ assert_rpm_wakelock_held(dev_priv); \ - spin_lock_irqsave(&dev_priv->uncore.lock, irqflags) + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); \ + unclaimed_reg_debug(dev_priv, reg, true, true) #define GEN6_READ_FOOTER \ + unclaimed_reg_debug(dev_priv, reg, true, false); \ spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); \ trace_i915_reg_rw(false, reg, val, sizeof(val), trace); \ return val @@ -699,11 +742,9 @@ static inline void __force_wake_get(struct drm_i915_private *dev_priv, static u##x \ gen6_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \ GEN6_READ_HEADER(x); \ - hsw_unclaimed_reg_debug(dev_priv, reg, true, true); \ if (NEEDS_FORCE_WAKE(offset)) \ __force_wake_get(dev_priv, FORCEWAKE_RENDER); \ val = __raw_i915_read##x(dev_priv, reg); \ - hsw_unclaimed_reg_debug(dev_priv, reg, true, false); \ GEN6_READ_FOOTER; \ } @@ -751,7 +792,6 @@ static u##x \ gen9_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \ enum forcewake_domains fw_engine; \ GEN6_READ_HEADER(x); \ - hsw_unclaimed_reg_debug(dev_priv, reg, true, true); \ if (!SKL_NEEDS_FORCE_WAKE(offset)) \ fw_engine = 0; \ else if (FORCEWAKE_GEN9_RENDER_RANGE_OFFSET(offset)) \ @@ -765,7 +805,6 @@ gen9_read##x(struct drm_i915_private *dev_priv, i915_reg_t reg, bool trace) { \ if (fw_engine) \ __force_wake_get(dev_priv, fw_engine); \ val = __raw_i915_read##x(dev_priv, reg); \ - hsw_unclaimed_reg_debug(dev_priv, reg, true, false); \ GEN6_READ_FOOTER; \ } @@ -864,9 +903,11 @@ __gen2_write(64) unsigned long irqflags; \ trace_i915_reg_rw(true, reg, val, sizeof(val), trace); \ assert_rpm_wakelock_held(dev_priv); \ - spin_lock_irqsave(&dev_priv->uncore.lock, irqflags) + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); \ + unclaimed_reg_debug(dev_priv, reg, false, true) #define GEN6_WRITE_FOOTER \ + unclaimed_reg_debug(dev_priv, reg, false, false); \ spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags) #define __gen6_write(x) \ @@ -892,13 +933,10 @@ hsw_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool t if (NEEDS_FORCE_WAKE(offset)) { \ __fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \ } \ - hsw_unclaimed_reg_debug(dev_priv, reg, false, true); \ __raw_i915_write##x(dev_priv, reg, val); \ if (unlikely(__fifo_ret)) { \ gen6_gt_check_fifodbg(dev_priv); \ } \ - hsw_unclaimed_reg_debug(dev_priv, reg, false, false); \ - hsw_unclaimed_reg_detect(dev_priv); \ GEN6_WRITE_FOOTER; \ } @@ -928,12 +966,9 @@ static bool is_gen8_shadowed(struct drm_i915_private *dev_priv, static void \ gen8_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, bool trace) { \ GEN6_WRITE_HEADER; \ - hsw_unclaimed_reg_debug(dev_priv, reg, false, true); \ if (NEEDS_FORCE_WAKE(offset) && !is_gen8_shadowed(dev_priv, reg)) \ __force_wake_get(dev_priv, FORCEWAKE_RENDER); \ __raw_i915_write##x(dev_priv, reg, val); \ - hsw_unclaimed_reg_debug(dev_priv, reg, false, false); \ - hsw_unclaimed_reg_detect(dev_priv); \ GEN6_WRITE_FOOTER; \ } @@ -987,7 +1022,6 @@ gen9_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, \ bool trace) { \ enum forcewake_domains fw_engine; \ GEN6_WRITE_HEADER; \ - hsw_unclaimed_reg_debug(dev_priv, reg, false, true); \ if (!SKL_NEEDS_FORCE_WAKE(offset) || \ is_gen9_shadowed(dev_priv, reg)) \ fw_engine = 0; \ @@ -1002,8 +1036,6 @@ gen9_write##x(struct drm_i915_private *dev_priv, i915_reg_t reg, u##x val, \ if (fw_engine) \ __force_wake_get(dev_priv, fw_engine); \ __raw_i915_write##x(dev_priv, reg, val); \ - hsw_unclaimed_reg_debug(dev_priv, reg, false, false); \ - hsw_unclaimed_reg_detect(dev_priv); \ GEN6_WRITE_FOOTER; \ } @@ -1223,6 +1255,8 @@ void intel_uncore_init(struct drm_device *dev) intel_uncore_fw_domains_init(dev); __intel_uncore_early_sanitize(dev, false); + dev_priv->uncore.unclaimed_mmio_check = 1; + switch (INTEL_INFO(dev)->gen) { default: case 9: @@ -1580,13 +1614,26 @@ bool intel_has_gpu_reset(struct drm_device *dev) return intel_get_gpu_reset(dev) != NULL; } -void intel_uncore_check_errors(struct drm_device *dev) +bool intel_uncore_unclaimed_mmio(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = dev->dev_private; + return check_for_unclaimed_mmio(dev_priv); +} + +bool +intel_uncore_arm_unclaimed_mmio_detection(struct drm_i915_private *dev_priv) +{ + if (unlikely(i915.mmio_debug || + dev_priv->uncore.unclaimed_mmio_check <= 0)) + return false; - if (HAS_FPGA_DBG_UNCLAIMED(dev) && - (__raw_i915_read32(dev_priv, FPGA_DBG) & FPGA_DBG_RM_NOCLAIM)) { - DRM_ERROR("Unclaimed register before interrupt\n"); - __raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM); + if (unlikely(intel_uncore_unclaimed_mmio(dev_priv))) { + DRM_DEBUG("Unclaimed register detected, " + "enabling oneshot unclaimed register reporting. " + "Please use i915.mmio_debug=N for more information.\n"); + i915.mmio_debug++; + dev_priv->uncore.unclaimed_mmio_check--; + return true; } + + return false; } diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index acf21026c78a..6a19371391fa 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -812,10 +812,35 @@ struct drm_i915_gem_busy { /** Handle of the buffer to check for busy */ __u32 handle; - /** Return busy status (1 if busy, 0 if idle). - * The high word is used to indicate on which rings the object - * currently resides: - * 16:31 - busy (r or r/w) rings (16 render, 17 bsd, 18 blt, etc) + /** Return busy status + * + * A return of 0 implies that the object is idle (after + * having flushed any pending activity), and a non-zero return that + * the object is still in-flight on the GPU. (The GPU has not yet + * signaled completion for all pending requests that reference the + * object.) + * + * The returned dword is split into two fields to indicate both + * the engines on which the object is being read, and the + * engine on which it is currently being written (if any). + * + * The low word (bits 0:15) indicate if the object is being written + * to by any engine (there can only be one, as the GEM implicit + * synchronisation rules force writes to be serialised). Only the + * engine for the last write is reported. + * + * The high word (bits 16:31) are a bitmask of which engines are + * currently reading from the object. Multiple engines may be + * reading from the object simultaneously. + * + * The value of each engine is the same as specified in the + * EXECBUFFER2 ioctl, i.e. I915_EXEC_RENDER, I915_EXEC_BSD etc. + * Note I915_EXEC_DEFAULT is a symbolic value and is mapped to + * the I915_EXEC_RENDER engine for execution, and so it is never + * reported as active itself. Some hardware may have parallel + * execution engines, e.g. multiple media engines, which are + * mapped to the same identifier in the EXECBUFFER2 ioctl and + * so are not separately reported for busyness. */ __u32 busy; }; diff --git a/mm/swapfile.c b/mm/swapfile.c index d2c37365e2d6..38884383ebac 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -48,6 +48,12 @@ static sector_t map_swap_entry(swp_entry_t, struct block_device**); DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; +/* + * Some modules use swappable objects and may try to swap them out under + * memory pressure (via the shrinker). Before doing so, they may wish to + * check to see if any swap space is available. + */ +EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority; |