* Copyright © 2019 Intel Corporation
*/
-#include "debugfs_gt.h"
+#include <drm/intel-gtt.h>
+
+#include "intel_gt_debugfs.h"
#include "gem/i915_gem_lmem.h"
#include "i915_drv.h"
#include "intel_gt_requests.h"
#include "intel_migrate.h"
#include "intel_mocs.h"
+#include "intel_pm.h"
#include "intel_rc6.h"
#include "intel_renderstate.h"
#include "intel_rps.h"
#include "intel_uncore.h"
-#include "intel_pm.h"
#include "shmem_utils.h"
+#include "pxp/intel_pxp.h"
-void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
+void __intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
{
- gt->i915 = i915;
- gt->uncore = &i915->uncore;
-
spin_lock_init(>->irq_lock);
+ mutex_init(>->tlb_invalidate_lock);
+
INIT_LIST_HEAD(>->closed_vma);
spin_lock_init(>->closed_lock);
intel_rps_init_early(>->rps);
}
+void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
+{
+ gt->i915 = i915;
+ gt->uncore = &i915->uncore;
+}
+
int intel_gt_probe_lmem(struct intel_gt *gt)
{
struct drm_i915_private *i915 = gt->i915;
{
intel_rps_driver_register(>->rps);
- debugfs_gt_register(gt);
+ intel_gt_debugfs_register(gt);
}
static int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size)
static struct i915_address_space *kernel_vm(struct intel_gt *gt)
{
if (INTEL_PPGTT(gt->i915) > INTEL_PPGTT_ALIASING)
- return &i915_ppgtt_create(gt)->vm;
+ return &i915_ppgtt_create(gt, I915_BO_ALLOC_PM_EARLY)->vm;
else
return i915_vm_get(>->ggtt->vm);
}
if (err)
return err;
+ intel_gt_init_workarounds(gt);
+
/*
* This is just a security blanket to placate dragons.
* On some systems, we very sporadically observe that the first TLBs
goto err_pm;
}
+ intel_set_mocs_index(gt);
+
err = intel_engines_init(gt);
if (err)
goto err_engines;
intel_migrate_init(>->migrate, gt);
+ intel_pxp_init(>->pxp);
+
goto out_fw;
err_gt:
__intel_gt_disable(gt);
intel_uc_driver_remove(>->uc);
intel_engines_release(gt);
+
+ intel_gt_flush_buffer_pool(gt);
}
void intel_gt_driver_unregister(struct intel_gt *gt)
intel_rps_driver_unregister(>->rps);
+ intel_pxp_fini(>->pxp);
+
/*
* Upon unregistering the device to prevent any new users, cancel
* all in-flight requests so that we can quickly unbind the active
* resources.
*/
- intel_gt_set_wedged(gt);
+ intel_gt_set_wedged_on_fini(gt);
/* Scrub all HW state upon release */
with_intel_runtime_pm(gt->uncore->rpm, wakeref)
if (vm) /* FIXME being called twice on error paths :( */
i915_vm_put(vm);
+ intel_wa_list_free(>->wa_list);
intel_gt_pm_fini(gt);
intel_gt_fini_scratch(gt);
intel_gt_fini_buffer_pool(gt);
intel_sseu_dump(&info->sseu, p);
}
+
+struct reg_and_bit {
+ i915_reg_t reg;
+ u32 bit;
+};
+
+static struct reg_and_bit
+get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8,
+ const i915_reg_t *regs, const unsigned int num)
+{
+ const unsigned int class = engine->class;
+ struct reg_and_bit rb = { };
+
+ if (drm_WARN_ON_ONCE(&engine->i915->drm,
+ class >= num || !regs[class].reg))
+ return rb;
+
+ rb.reg = regs[class];
+ if (gen8 && class == VIDEO_DECODE_CLASS)
+ rb.reg.reg += 4 * engine->instance; /* GEN8_M2TCR */
+ else
+ rb.bit = engine->instance;
+
+ rb.bit = BIT(rb.bit);
+
+ return rb;
+}
+
+void intel_gt_invalidate_tlbs(struct intel_gt *gt)
+{
+ static const i915_reg_t gen8_regs[] = {
+ [RENDER_CLASS] = GEN8_RTCR,
+ [VIDEO_DECODE_CLASS] = GEN8_M1TCR, /* , GEN8_M2TCR */
+ [VIDEO_ENHANCEMENT_CLASS] = GEN8_VTCR,
+ [COPY_ENGINE_CLASS] = GEN8_BTCR,
+ };
+ static const i915_reg_t gen12_regs[] = {
+ [RENDER_CLASS] = GEN12_GFX_TLB_INV_CR,
+ [VIDEO_DECODE_CLASS] = GEN12_VD_TLB_INV_CR,
+ [VIDEO_ENHANCEMENT_CLASS] = GEN12_VE_TLB_INV_CR,
+ [COPY_ENGINE_CLASS] = GEN12_BLT_TLB_INV_CR,
+ };
+ struct drm_i915_private *i915 = gt->i915;
+ struct intel_uncore *uncore = gt->uncore;
+ struct intel_engine_cs *engine;
+ enum intel_engine_id id;
+ const i915_reg_t *regs;
+ unsigned int num = 0;
+
+ if (I915_SELFTEST_ONLY(gt->awake == -ENODEV))
+ return;
+
+ if (GRAPHICS_VER(i915) == 12) {
+ regs = gen12_regs;
+ num = ARRAY_SIZE(gen12_regs);
+ } else if (GRAPHICS_VER(i915) >= 8 && GRAPHICS_VER(i915) <= 11) {
+ regs = gen8_regs;
+ num = ARRAY_SIZE(gen8_regs);
+ } else if (GRAPHICS_VER(i915) < 8) {
+ return;
+ }
+
+ if (drm_WARN_ONCE(&i915->drm, !num,
+ "Platform does not implement TLB invalidation!"))
+ return;
+
+ GEM_TRACE("\n");
+
+ assert_rpm_wakelock_held(&i915->runtime_pm);
+
+ mutex_lock(>->tlb_invalidate_lock);
+ intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
+
+ for_each_engine(engine, gt, id) {
+ /*
+ * HW architecture suggest typical invalidation time at 40us,
+ * with pessimistic cases up to 100us and a recommendation to
+ * cap at 1ms. We go a bit higher just in case.
+ */
+ const unsigned int timeout_us = 100;
+ const unsigned int timeout_ms = 4;
+ struct reg_and_bit rb;
+
+ rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
+ if (!i915_mmio_reg_offset(rb.reg))
+ continue;
+
+ intel_uncore_write_fw(uncore, rb.reg, rb.bit);
+ if (__intel_wait_for_register_fw(uncore,
+ rb.reg, rb.bit, 0,
+ timeout_us, timeout_ms,
+ NULL))
+ drm_err_ratelimited(>->i915->drm,
+ "%s TLB invalidation did not complete in %ums!\n",
+ engine->name, timeout_ms);
+ }
+
+ /*
+ * Use delayed put since a) we mostly expect a flurry of TLB
+ * invalidations so it is good to avoid paying the forcewake cost and
+ * b) it works around a bug in Icelake which cannot cope with too rapid
+ * transitions.
+ */
+ intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
+ mutex_unlock(>->tlb_invalidate_lock);
+}