summaryrefslogtreecommitdiff
path: root/drivers/gpu/host1x/hw/channel_hw.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-09-01 11:26:46 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-09-01 11:26:46 -0700
commit477f70cd2a67904e04c2c2b9bd0fa2e95222f2f6 (patch)
tree1897dd1de49e1ea24897163533e2d8ead5dad0ad /drivers/gpu/host1x/hw/channel_hw.c
parent835d31d319d9c8c4eb6cac074643360ba0ecab10 (diff)
parent8f0284f190e6a0aa09015090568c03f18288231a (diff)
Merge tag 'drm-next-2021-08-31-1' of git://anongit.freedesktop.org/drm/drm
Pull drm updates from Dave Airlie: "Highlights: - i915 has seen a lot of refactoring and uAPI cleanups due to a change in the upstream direction going forward This has all been audited with known userspace, but there may be some pitfalls that were missed. - i915 now uses common TTM to enable discrete memory on DG1/2 GPUs - i915 enables Jasper and Elkhart Lake by default and has preliminary XeHP/DG2 support - amdgpu adds support for Cyan Skillfish - lots of implicit fencing rules documented and fixed up in drivers - msm now uses the core scheduler - the irq midlayer has been removed for non-legacy drivers - the sysfb code now works on more than x86. Otherwise the usual smattering of stuff everywhere, panels, bridges, refactorings. Detailed summary: core: - extract i915 eDP backlight into core - DP aux bus support - drm_device.irq_enabled removed - port drivers to native irq interfaces - export gem shadow plane handling for vgem - print proper driver name in framebuffer registration - driver fixes for implicit fencing rules - ARM fixed rate compression modifier added - updated fb damage handling - rmfb ioctl logging/docs - drop drm_gem_object_put_locked - define DRM_FORMAT_MAX_PLANES - add gem fb vmap/vunmap helpers - add lockdep_assert(once) helpers - mark drm irq midlayer as legacy - use offset adjusted bo mapping conversion vgaarb: - cleanups fbdev: - extend efifb handling to all arches - div by 0 fixes for multiple drivers udmabuf: - add hugepage mapping support dma-buf: - non-dynamic exporter fixups - document implicit fencing rules amdgpu: - Initial Cyan Skillfish support - switch virtual DCE over to vkms based atomic - VCN/JPEG power down fixes - NAVI PCIE link handling fixes - AMD HDMI freesync fixes - Yellow Carp + Beige Goby fixes - Clockgating/S0ix/SMU/EEPROM fixes - embed hw fence in job - rework dma-resv handling - ensure eviction to system ram amdkfd: - uapi: SVM address range query added - sysfs leak fix - GPUVM TLB optimizations - vmfault/migration counters i915: - Enable JSL and EHL by default - preliminary XeHP/DG2 support - remove all CNL support (never shipped) - move to TTM for discrete memory support - allow mixed object mmap handling - GEM uAPI spring cleaning - add I915_MMAP_OBJECT_FIXED - reinstate ADL-P mmap ioctls - drop a bunch of unused by userspace features - disable and remove GPU relocations - revert some i915 misfeatures - major refactoring of GuC for Gen11+ - execbuffer object locking separate step - reject caching/set-domain on discrete - Enable pipe DMC loading on XE-LPD and ADL-P - add PSF GV point support - Refactor and fix DDI buffer translations - Clean up FBC CFB allocation code - Finish INTEL_GEN() and friends macro conversions nouveau: - add eDP backlight support - implicit fence fix msm: - a680/7c3 support - drm/scheduler conversion panfrost: - rework GPU reset virtio: - fix fencing for planes ast: - add detect support bochs: - move to tiny GPU driver vc4: - use hotplug irqs - HDMI codec support vmwgfx: - use internal vmware device headers ingenic: - demidlayering irq rcar-du: - shutdown fixes - convert to bridge connector helpers zynqmp-dsub: - misc fixes mgag200: - convert PLL handling to atomic mediatek: - MT8133 AAL support - gem mmap object support - MT8167 support etnaviv: - NXP Layerscape LS1028A SoC support - GEM mmap cleanups tegra: - new user API exynos: - missing unlock fix - build warning fix - use refcount_t" * tag 'drm-next-2021-08-31-1' of git://anongit.freedesktop.org/drm/drm: (1318 commits) drm/amd/display: Move AllowDRAMSelfRefreshOrDRAMClockChangeInVblank to bounding box drm/amd/display: Remove duplicate dml init drm/amd/display: Update bounding box states (v2) drm/amd/display: Update number of DCN3 clock states drm/amdgpu: disable GFX CGCG in aldebaran drm/amdgpu: Clear RAS interrupt status on aldebaran drm/amdgpu: Add support for RAS XGMI err query drm/amdkfd: Account for SH/SE count when setting up cu masks. drm/amdgpu: rename amdgpu_bo_get_preferred_pin_domain drm/amdgpu: drop redundant cancel_delayed_work_sync call drm/amdgpu: add missing cleanups for more ASICs on UVD/VCE suspend drm/amdgpu: add missing cleanups for Polaris12 UVD/VCE on suspend drm/amdkfd: map SVM range with correct access permission drm/amdkfd: check access permisson to restore retry fault drm/amdgpu: Update RAS XGMI Error Query drm/amdgpu: Add driver infrastructure for MCA RAS drm/amd/display: Add Logging for HDMI color depth information drm/amd/amdgpu: consolidate PSP TA init shared buf functions drm/amd/amdgpu: add name field back to ras_common_if drm/amdgpu: Fix build with missing pm_suspend_target_state module export ...
Diffstat (limited to 'drivers/gpu/host1x/hw/channel_hw.c')
-rw-r--r--drivers/gpu/host1x/hw/channel_hw.c87
1 files changed, 66 insertions, 21 deletions
diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c
index d4c28faf27d1..1999780a7203 100644
--- a/drivers/gpu/host1x/hw/channel_hw.c
+++ b/drivers/gpu/host1x/hw/channel_hw.c
@@ -47,39 +47,84 @@ static void trace_write_gather(struct host1x_cdma *cdma, struct host1x_bo *bo,
}
}
-static void submit_gathers(struct host1x_job *job)
+static void submit_wait(struct host1x_cdma *cdma, u32 id, u32 threshold,
+ u32 next_class)
+{
+#if HOST1X_HW >= 2
+ host1x_cdma_push_wide(cdma,
+ host1x_opcode_setclass(
+ HOST1X_CLASS_HOST1X,
+ HOST1X_UCLASS_LOAD_SYNCPT_PAYLOAD_32,
+ /* WAIT_SYNCPT_32 is at SYNCPT_PAYLOAD_32+2 */
+ BIT(0) | BIT(2)
+ ),
+ threshold,
+ id,
+ host1x_opcode_setclass(next_class, 0, 0)
+ );
+#else
+ /* TODO add waitchk or use waitbases or other mitigation */
+ host1x_cdma_push(cdma,
+ host1x_opcode_setclass(
+ HOST1X_CLASS_HOST1X,
+ host1x_uclass_wait_syncpt_r(),
+ BIT(0)
+ ),
+ host1x_class_host_wait_syncpt(id, threshold)
+ );
+ host1x_cdma_push(cdma,
+ host1x_opcode_setclass(next_class, 0, 0),
+ HOST1X_OPCODE_NOP
+ );
+#endif
+}
+
+static void submit_gathers(struct host1x_job *job, u32 job_syncpt_base)
{
struct host1x_cdma *cdma = &job->channel->cdma;
#if HOST1X_HW < 6
struct device *dev = job->channel->dev;
#endif
unsigned int i;
+ u32 threshold;
- for (i = 0; i < job->num_gathers; i++) {
- struct host1x_job_gather *g = &job->gathers[i];
- dma_addr_t addr = g->base + g->offset;
- u32 op2, op3;
+ for (i = 0; i < job->num_cmds; i++) {
+ struct host1x_job_cmd *cmd = &job->cmds[i];
- op2 = lower_32_bits(addr);
- op3 = upper_32_bits(addr);
+ if (cmd->is_wait) {
+ if (cmd->wait.relative)
+ threshold = job_syncpt_base + cmd->wait.threshold;
+ else
+ threshold = cmd->wait.threshold;
- trace_write_gather(cdma, g->bo, g->offset, g->words);
+ submit_wait(cdma, cmd->wait.id, threshold, cmd->wait.next_class);
+ } else {
+ struct host1x_job_gather *g = &cmd->gather;
+
+ dma_addr_t addr = g->base + g->offset;
+ u32 op2, op3;
+
+ op2 = lower_32_bits(addr);
+ op3 = upper_32_bits(addr);
- if (op3 != 0) {
+ trace_write_gather(cdma, g->bo, g->offset, g->words);
+
+ if (op3 != 0) {
#if HOST1X_HW >= 6
- u32 op1 = host1x_opcode_gather_wide(g->words);
- u32 op4 = HOST1X_OPCODE_NOP;
+ u32 op1 = host1x_opcode_gather_wide(g->words);
+ u32 op4 = HOST1X_OPCODE_NOP;
- host1x_cdma_push_wide(cdma, op1, op2, op3, op4);
+ host1x_cdma_push_wide(cdma, op1, op2, op3, op4);
#else
- dev_err(dev, "invalid gather for push buffer %pad\n",
- &addr);
- continue;
+ dev_err(dev, "invalid gather for push buffer %pad\n",
+ &addr);
+ continue;
#endif
- } else {
- u32 op1 = host1x_opcode_gather(g->words);
+ } else {
+ u32 op1 = host1x_opcode_gather(g->words);
- host1x_cdma_push(cdma, op1, op2);
+ host1x_cdma_push(cdma, op1, op2);
+ }
}
}
}
@@ -126,7 +171,7 @@ static int channel_submit(struct host1x_job *job)
struct host1x *host = dev_get_drvdata(ch->dev->parent);
trace_host1x_channel_submit(dev_name(ch->dev),
- job->num_gathers, job->num_relocs,
+ job->num_cmds, job->num_relocs,
job->syncpt->id, job->syncpt_incrs);
/* before error checks, return current max */
@@ -181,7 +226,7 @@ static int channel_submit(struct host1x_job *job)
host1x_opcode_setclass(job->class, 0, 0),
HOST1X_OPCODE_NOP);
- submit_gathers(job);
+ submit_gathers(job, syncval - user_syncpt_incrs);
/* end CDMA submit & stash pinned hMems into sync queue */
host1x_cdma_end(&ch->cdma, job);
@@ -191,7 +236,7 @@ static int channel_submit(struct host1x_job *job)
/* schedule a submit complete interrupt */
err = host1x_intr_add_action(host, sp, syncval,
HOST1X_INTR_ACTION_SUBMIT_COMPLETE, ch,
- completed_waiter, NULL);
+ completed_waiter, &job->waiter);
completed_waiter = NULL;
WARN(err, "Failed to set submit complete interrupt");