@@ -108,6 +108,7 @@ gt-y += \
gt/intel_gtt.o \
gt/intel_llc.o \
gt/intel_lrc.o \
+ gt/intel_migrate.o \
gt/intel_mocs.o \
gt/intel_ppgtt.o \
gt/intel_rc6.o \
@@ -188,6 +188,7 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)
#define I915_GEM_HWS_PREEMPT_ADDR (I915_GEM_HWS_PREEMPT * sizeof(u32))
#define I915_GEM_HWS_SEQNO 0x40
#define I915_GEM_HWS_SEQNO_ADDR (I915_GEM_HWS_SEQNO * sizeof(u32))
+#define I915_GEM_HWS_MIGRATE (0x42 * sizeof(u32))
#define I915_GEM_HWS_SCRATCH 0x80
#define I915_HWS_CSB_BUF0_INDEX 0x10
@@ -123,8 +123,10 @@
#define MI_SEMAPHORE_SAD_NEQ_SDD (5 << 12)
#define MI_SEMAPHORE_TOKEN_MASK REG_GENMASK(9, 5)
#define MI_SEMAPHORE_TOKEN_SHIFT 5
+#define MI_STORE_DATA_IMM MI_INSTR(0x20, 0)
#define MI_STORE_DWORD_IMM MI_INSTR(0x20, 1)
#define MI_STORE_DWORD_IMM_GEN4 MI_INSTR(0x20, 2)
+#define MI_STORE_QWORD_IMM_GEN8 (MI_INSTR(0x20, 3) | REG_BIT(21))
#define MI_MEM_VIRTUAL (1 << 22) /* 945,g33,965 */
#define MI_USE_GGTT (1 << 22) /* g4x+ */
#define MI_STORE_DWORD_INDEX MI_INSTR(0x21, 1)
new file mode 100644
@@ -0,0 +1,544 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "intel_context.h"
+#include "intel_gpu_commands.h"
+#include "intel_gt.h"
+#include "intel_gtt.h"
+#include "intel_migrate.h"
+#include "intel_ring.h"
+
+struct insert_pte_data {
+ u64 offset;
+ bool is_lmem;
+};
+
+#define CHUNK_SZ SZ_8M /* ~1ms at 8GiB/s preemption delay */
+
+static bool engine_supports_migration(struct intel_engine_cs *engine)
+{
+ if (!engine)
+ return false;
+
+ /*
+ * We need the ability to prevent aribtration (MI_ARB_ON_OFF),
+ * the ability to write PTE using inline data (MI_STORE_DATA)
+ * and of course the ability to do the block transfer (blits).
+ */
+ GEM_BUG_ON(engine->class != COPY_ENGINE_CLASS);
+
+ return true;
+}
+
+static void insert_pte(struct i915_address_space *vm,
+ struct i915_page_table *pt,
+ void *data)
+{
+ struct insert_pte_data *d = data;
+
+ vm->insert_page(vm, px_dma(pt), d->offset, I915_CACHE_NONE,
+ d->is_lmem ? PTE_LM : 0);
+ d->offset += PAGE_SIZE;
+}
+
+static struct i915_address_space *migrate_vm(struct intel_gt *gt)
+{
+ struct i915_vm_pt_stash stash = {};
+ struct i915_ppgtt *vm;
+ int err;
+ int i;
+
+ /*
+ * We construct a very special VM for use by all migration contexts,
+ * it is kept pinned so that it can be used at any time. As we need
+ * to pre-allocate the page directories for the migration VM, this
+ * limits us to only using a small number of prepared vma.
+ *
+ * To be able to pipeline and reschedule migration operations while
+ * avoiding unnecessary contention on the vm itself, the PTE updates
+ * are inline with the blits. All the blits use the same fixed
+ * addresses, with the backing store redirection being updated on the
+ * fly. Only 2 implicit vma are used for all migration operations.
+ *
+ * We lay the ppGTT out as:
+ *
+ * [0, CHUNK_SZ) -> first object
+ * [CHUNK_SZ, 2 * CHUNK_SZ) -> second object
+ * [2 * CHUNK_SZ, 2 * CHUNK_SZ + 2 * CHUNK_SZ >> 9] -> PTE
+ *
+ * By exposing the dma addresses of the page directories themselves
+ * within the ppGTT, we are then able to rewrite the PTE prior to use.
+ * But the PTE update and subsequent migration operation must be atomic,
+ * i.e. within the same non-preemptible window so that we do not switch
+ * to another migration context that overwrites the PTE.
+ *
+ * TODO: Add support for huge LMEM PTEs
+ */
+
+ vm = i915_ppgtt_create(gt);
+ if (IS_ERR(vm))
+ return ERR_CAST(vm);
+
+ if (!vm->vm.allocate_va_range || !vm->vm.foreach) {
+ err = -ENODEV;
+ goto err_vm;
+ }
+
+ /*
+ * Each engine instance is assigned its own chunk in the VM, so
+ * that we can run multiple instances concurrently
+ */
+ for (i = 0; i < ARRAY_SIZE(gt->engine_class[COPY_ENGINE_CLASS]); i++) {
+ struct intel_engine_cs *engine;
+ u64 base = (u64)i << 32;
+ struct insert_pte_data d = {};
+ struct i915_gem_ww_ctx ww;
+ u64 sz;
+
+ engine = gt->engine_class[COPY_ENGINE_CLASS][i];
+ if (!engine_supports_migration(engine))
+ continue;
+
+ /*
+ * We copy in 8MiB chunks. Each PDE covers 2MiB, so we need
+ * 4x2 page directories for source/destination.
+ */
+ sz = 2 * CHUNK_SZ;
+ d.offset = base + sz;
+
+ /*
+ * We need another page directory setup so that we can write
+ * the 8x512 PTE in each chunk.
+ */
+ sz += (sz >> 12) * sizeof(u64);
+
+ err = i915_vm_alloc_pt_stash(&vm->vm, &stash, sz);
+ if (err)
+ goto err_vm;
+
+ for_i915_gem_ww(&ww, err, true) {
+ err = i915_vm_lock_objects(&vm->vm, &ww);
+ if (err)
+ continue;
+ err = i915_vm_map_pt_stash(&vm->vm, &stash);
+ if (err)
+ continue;
+
+ vm->vm.allocate_va_range(&vm->vm, &stash, base, base + sz);
+ }
+ i915_vm_free_pt_stash(&vm->vm, &stash);
+ if (err)
+ goto err_vm;
+
+ /* Now allow the GPU to rewrite the PTE via its own ppGTT */
+ d.is_lmem = i915_gem_object_is_lmem(vm->vm.scratch[0]);
+ vm->vm.foreach(&vm->vm, base, base + sz, insert_pte, &d);
+ }
+
+ return &vm->vm;
+
+err_vm:
+ i915_vm_put(&vm->vm);
+ return ERR_PTR(err);
+}
+
+static struct intel_engine_cs *first_copy_engine(struct intel_gt *gt)
+{
+ struct intel_engine_cs *engine;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(gt->engine_class[COPY_ENGINE_CLASS]); i++) {
+ engine = gt->engine_class[COPY_ENGINE_CLASS][i];
+ if (engine_supports_migration(engine))
+ return engine;
+ }
+
+ return NULL;
+}
+
+static struct intel_context *pinned_context(struct intel_gt *gt)
+{
+ static struct lock_class_key key;
+ struct intel_engine_cs *engine;
+ struct i915_address_space *vm;
+ struct intel_context *ce;
+
+ engine = first_copy_engine(gt);
+ if (!engine)
+ return ERR_PTR(-ENODEV);
+
+ vm = migrate_vm(gt);
+ if (IS_ERR(vm))
+ return ERR_CAST(vm);
+
+ ce = intel_engine_create_pinned_context(engine, vm, SZ_512K,
+ I915_GEM_HWS_MIGRATE,
+ &key, "migrate");
+ i915_vm_put(ce->vm);
+ return ce;
+}
+
+int intel_migrate_init(struct intel_migrate *m, struct intel_gt *gt)
+{
+ struct intel_context *ce;
+
+ memset(m, 0, sizeof(*m));
+
+ ce = pinned_context(gt);
+ if (IS_ERR(ce))
+ return PTR_ERR(ce);
+
+ m->context = ce;
+ return 0;
+}
+
+static int random_index(unsigned int max)
+{
+ return upper_32_bits(mul_u32_u32(get_random_u32(), max));
+}
+
+static struct intel_context *__migrate_engines(struct intel_gt *gt)
+{
+ struct intel_engine_cs *engines[MAX_ENGINE_INSTANCE];
+ struct intel_engine_cs *engine;
+ unsigned int count, i;
+
+ count = 0;
+ for (i = 0; i < ARRAY_SIZE(gt->engine_class[COPY_ENGINE_CLASS]); i++) {
+ engine = gt->engine_class[COPY_ENGINE_CLASS][i];
+ if (engine_supports_migration(engine))
+ engines[count++] = engine;
+ }
+
+ return intel_context_create(engines[random_index(count)]);
+}
+
+struct intel_context *intel_migrate_create_context(struct intel_migrate *m)
+{
+ struct intel_context *ce;
+
+ /*
+ * We randomly distribute contexts across the engines upon constrction,
+ * as they all share the same pinned vm, and so in order to allow
+ * multiple blits to run in parallel, we must construct each blit
+ * to use a different range of the vm for its GTT. This has to be
+ * known at construction, so we can not use the late greedy load
+ * balancing of the virtual-engine.
+ */
+ ce = __migrate_engines(m->context->engine->gt);
+ if (IS_ERR(ce))
+ return ce;
+
+ ce->ring = __intel_context_ring_size(SZ_256K);
+
+ i915_vm_put(ce->vm);
+ ce->vm = i915_vm_get(m->context->vm);
+
+ return ce;
+}
+
+static inline struct sgt_dma sg_sgt(struct scatterlist *sg)
+{
+ dma_addr_t addr = sg_dma_address(sg);
+
+ return (struct sgt_dma){ sg, addr, addr + sg_dma_len(sg) };
+}
+
+static int emit_no_arbitration(struct i915_request *rq)
+{
+ u32 *cs;
+
+ cs = intel_ring_begin(rq, 2);
+ if (IS_ERR(cs))
+ return PTR_ERR(cs);
+
+ /* Explicitly disable preemption for this request. */
+ *cs++ = MI_ARB_ON_OFF;
+ *cs++ = MI_NOOP;
+ intel_ring_advance(rq, cs);
+
+ return 0;
+}
+
+static int emit_pte(struct i915_request *rq,
+ struct sgt_dma *it,
+ enum i915_cache_level cache_level,
+ bool is_lmem,
+ u64 offset,
+ int length)
+{
+ const u64 encode = rq->context->vm->pte_encode(0, cache_level,
+ is_lmem ? PTE_LM : 0);
+ struct intel_ring *ring = rq->ring;
+ int total = 0;
+ u32 *hdr, *cs;
+ int pkt;
+
+ GEM_BUG_ON(INTEL_GEN(rq->engine->i915) < 8);
+
+ /* Compute the page directory offset for the target address range */
+ offset += (u64)rq->engine->instance << 32;
+ offset >>= 12;
+ offset *= sizeof(u64);
+ offset += 2 * CHUNK_SZ;
+
+ cs = intel_ring_begin(rq, 6);
+ if (IS_ERR(cs))
+ return PTR_ERR(cs);
+
+ /* Pack as many PTE updates as possible into a single MI command */
+ pkt = min_t(int, 0x400, ring->space / sizeof(u32) + 5);
+ pkt = min_t(int, pkt, (ring->size - ring->emit) / sizeof(u32) + 5);
+
+ hdr = cs;
+ *cs++ = MI_STORE_DATA_IMM | REG_BIT(21); /* as qword elements */
+ *cs++ = lower_32_bits(offset);
+ *cs++ = upper_32_bits(offset);
+
+ do {
+ if (cs - hdr >= pkt) {
+ *hdr += cs - hdr - 2;
+ *cs++ = MI_NOOP;
+
+ ring->emit = (void *)cs - ring->vaddr;
+ intel_ring_advance(rq, cs);
+ intel_ring_update_space(ring);
+
+ cs = intel_ring_begin(rq, 6);
+ if (IS_ERR(cs))
+ return PTR_ERR(cs);
+
+ pkt = min_t(int, 0x400, ring->space / sizeof(u32) + 5);
+ pkt = min_t(int, pkt, (ring->size - ring->emit) / sizeof(u32) + 5);
+
+ hdr = cs;
+ *cs++ = MI_STORE_DATA_IMM | REG_BIT(21);
+ *cs++ = lower_32_bits(offset);
+ *cs++ = upper_32_bits(offset);
+ }
+
+ *cs++ = lower_32_bits(encode | it->dma);
+ *cs++ = upper_32_bits(encode | it->dma);
+
+ offset += 8;
+ total += I915_GTT_PAGE_SIZE;
+
+ it->dma += I915_GTT_PAGE_SIZE;
+ if (it->dma >= it->max) {
+ it->sg = __sg_next(it->sg);
+ if (!it->sg || sg_dma_len(it->sg) == 0)
+ break;
+
+ it->dma = sg_dma_address(it->sg);
+ it->max = it->dma + sg_dma_len(it->sg);
+ }
+ } while (total < length);
+
+ *hdr += cs - hdr - 2;
+ *cs++ = MI_NOOP;
+
+ ring->emit = (void *)cs - ring->vaddr;
+ intel_ring_advance(rq, cs);
+ intel_ring_update_space(ring);
+
+ return total;
+}
+
+static bool wa_1209644611_applies(int gen, u32 size)
+{
+ u32 height = size >> PAGE_SHIFT;
+
+ if (gen != 11)
+ return false;
+
+ return height % 4 == 3 && height <= 8;
+}
+
+static int emit_copy(struct i915_request *rq, int size)
+{
+ const int gen = INTEL_GEN(rq->engine->i915);
+ u32 instance = rq->engine->instance;
+ u32 *cs;
+
+ cs = intel_ring_begin(rq, gen >= 8 ? 10 : 6);
+ if (IS_ERR(cs))
+ return PTR_ERR(cs);
+
+ if (gen >= 9 && !wa_1209644611_applies(gen, size)) {
+ *cs++ = GEN9_XY_FAST_COPY_BLT_CMD | (10 - 2);
+ *cs++ = BLT_DEPTH_32 | PAGE_SIZE;
+ *cs++ = 0;
+ *cs++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
+ *cs++ = CHUNK_SZ; /* dst offset */
+ *cs++ = instance;
+ *cs++ = 0;
+ *cs++ = PAGE_SIZE;
+ *cs++ = 0; /* src offset */
+ *cs++ = instance;
+ } else if (gen >= 8) {
+ *cs++ = XY_SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (10 - 2);
+ *cs++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | PAGE_SIZE;
+ *cs++ = 0;
+ *cs++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE / 4;
+ *cs++ = CHUNK_SZ; /* dst offset */
+ *cs++ = instance;
+ *cs++ = 0;
+ *cs++ = PAGE_SIZE;
+ *cs++ = 0; /* src offset */
+ *cs++ = instance;
+ } else {
+ GEM_BUG_ON(instance);
+ *cs++ = SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (6 - 2);
+ *cs++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | PAGE_SIZE;
+ *cs++ = size >> PAGE_SHIFT << 16 | PAGE_SIZE;
+ *cs++ = CHUNK_SZ; /* dst offset */
+ *cs++ = PAGE_SIZE;
+ *cs++ = 0; /* src offset */
+ }
+
+ intel_ring_advance(rq, cs);
+ return 0;
+}
+
+int
+intel_context_migrate_copy(struct intel_context *ce,
+ struct dma_fence *await,
+ struct scatterlist *src,
+ enum i915_cache_level src_cache_level,
+ bool src_is_lmem,
+ struct scatterlist *dst,
+ enum i915_cache_level dst_cache_level,
+ bool dst_is_lmem,
+ struct i915_request **out)
+{
+ struct sgt_dma it_src = sg_sgt(src), it_dst = sg_sgt(dst);
+ struct i915_request *rq;
+ int err;
+
+ *out = NULL;
+
+ /* GEM_BUG_ON(ce->vm != migrate_vm); */
+
+ GEM_BUG_ON(ce->ring->size < SZ_64K);
+
+ do {
+ int len;
+
+ rq = i915_request_create(ce);
+ if (IS_ERR(rq)) {
+ err = PTR_ERR(rq);
+ goto out_ce;
+ }
+
+ if (await) {
+ err = i915_request_await_dma_fence(rq, await);
+ if (err)
+ goto out_rq;
+
+ if (rq->engine->emit_init_breadcrumb) {
+ err = rq->engine->emit_init_breadcrumb(rq);
+ if (err)
+ goto out_rq;
+ }
+
+ await = NULL;
+ }
+
+ /* The PTE updates + copy must not be interrupted. */
+ err = emit_no_arbitration(rq);
+ if (err)
+ goto out_rq;
+
+ len = emit_pte(rq, &it_src, src_cache_level, src_is_lmem, 0,
+ CHUNK_SZ);
+ if (len <= 0) {
+ err = len;
+ goto out_rq;
+ }
+
+ err = emit_pte(rq, &it_dst, dst_cache_level, dst_is_lmem,
+ CHUNK_SZ, len);
+ if (err < 0)
+ goto out_rq;
+ if (err < len) {
+ err = -EINVAL;
+ goto out_rq;
+ }
+
+ err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
+ if (err)
+ goto out_rq;
+
+ err = emit_copy(rq, len);
+
+ /* Arbitration is re-enabled between requests. */
+out_rq:
+ if (*out)
+ i915_request_put(*out);
+ *out = i915_request_get(rq);
+ i915_request_add(rq);
+ if (err || !it_src.sg || !sg_dma_len(it_src.sg))
+ break;
+
+ cond_resched();
+ } while (1);
+
+out_ce:
+ return err;
+}
+
+int intel_migrate_copy(struct intel_migrate *m,
+ struct i915_gem_ww_ctx *ww,
+ struct dma_fence *await,
+ struct scatterlist *src,
+ enum i915_cache_level src_cache_level,
+ bool src_is_lmem,
+ struct scatterlist *dst,
+ enum i915_cache_level dst_cache_level,
+ bool dst_is_lmem,
+ struct i915_request **out)
+{
+ struct intel_context *ce;
+ int err;
+
+ *out = NULL;
+ if (!m->context)
+ return -ENODEV;
+
+ ce = intel_migrate_create_context(m);
+ if (IS_ERR(ce))
+ ce = intel_context_get(m->context);
+ GEM_BUG_ON(IS_ERR(ce));
+
+ err = intel_context_pin_ww(ce, ww);
+ if (err)
+ goto out;
+
+ err = intel_context_migrate_copy(ce, await,
+ src, src_cache_level, src_is_lmem,
+ dst, dst_cache_level, dst_is_lmem,
+ out);
+
+ intel_context_unpin(ce);
+out:
+ intel_context_put(ce);
+ return err;
+}
+
+void intel_migrate_fini(struct intel_migrate *m)
+{
+ struct intel_context *ce;
+
+ ce = fetch_and_zero(&m->context);
+ if (!ce)
+ return;
+
+ intel_engine_destroy_pinned_context(ce);
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_migrate.c"
+#endif
new file mode 100644
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __INTEL_MIGRATE__
+#define __INTEL_MIGRATE__
+
+#include "intel_migrate_types.h"
+
+struct dma_fence;
+struct i915_request;
+struct i915_gem_ww_ctx;
+struct intel_gt;
+struct scatterlist;
+enum i915_cache_level;
+
+int intel_migrate_init(struct intel_migrate *m, struct intel_gt *gt);
+
+struct intel_context *intel_migrate_create_context(struct intel_migrate *m);
+
+int intel_migrate_copy(struct intel_migrate *m,
+ struct i915_gem_ww_ctx *ww,
+ struct dma_fence *await,
+ struct scatterlist *src,
+ enum i915_cache_level src_cache_level,
+ bool src_is_lmem,
+ struct scatterlist *dst,
+ enum i915_cache_level dst_cache_level,
+ bool dst_is_lmem,
+ struct i915_request **out);
+
+int intel_context_migrate_copy(struct intel_context *ce,
+ struct dma_fence *await,
+ struct scatterlist *src,
+ enum i915_cache_level src_cache_level,
+ bool src_is_lmem,
+ struct scatterlist *dst,
+ enum i915_cache_level dst_cache_level,
+ bool dst_is_lmem,
+ struct i915_request **out);
+
+void intel_migrate_fini(struct intel_migrate *m);
+
+#endif /* __INTEL_MIGRATE__ */
new file mode 100644
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __INTEL_MIGRATE_TYPES__
+#define __INTEL_MIGRATE_TYPES__
+
+struct intel_context;
+
+struct intel_migrate {
+ struct intel_context *context;
+};
+
+#endif /* __INTEL_MIGRATE_TYPES__ */
@@ -49,6 +49,7 @@ static inline void intel_ring_advance(struct i915_request *rq, u32 *cs)
* intel_ring_begin()).
*/
GEM_BUG_ON((rq->ring->vaddr + rq->ring->emit) != cs);
+ GEM_BUG_ON(!IS_ALIGNED(rq->ring->emit, 8)); /* RING_TAIL qword align */
}
static inline u32 intel_ring_wrap(const struct intel_ring *ring, u32 pos)
new file mode 100644
@@ -0,0 +1,291 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include "selftests/i915_random.h"
+
+static const unsigned int sizes[] = {
+ SZ_4K,
+ SZ_64K,
+ SZ_2M,
+ CHUNK_SZ - SZ_4K,
+ CHUNK_SZ,
+ CHUNK_SZ + SZ_4K,
+ SZ_64M,
+};
+
+static struct drm_i915_gem_object *
+create_lmem_or_internal(struct drm_i915_private *i915, size_t size)
+{
+ if (HAS_LMEM(i915)) {
+ struct drm_i915_gem_object *obj;
+
+ obj = i915_gem_object_create_lmem(i915, size, 0);
+ if (!IS_ERR(obj))
+ return obj;
+ }
+
+ return i915_gem_object_create_internal(i915, size);
+}
+
+static int copy(struct intel_migrate *migrate,
+ int (*fn)(struct intel_migrate *migrate,
+ struct i915_gem_ww_ctx *ww,
+ struct drm_i915_gem_object *src,
+ struct drm_i915_gem_object *dst,
+ struct i915_request **out),
+ u32 sz, struct rnd_state *prng)
+{
+ struct drm_i915_private *i915 = migrate->context->engine->i915;
+ struct drm_i915_gem_object *src, *dst;
+ struct i915_request *rq;
+ struct i915_gem_ww_ctx ww;
+ u32 *vaddr;
+ int err = 0;
+ int i;
+
+ src = create_lmem_or_internal(i915, sz);
+ if (IS_ERR(src))
+ return 0;
+
+ dst = i915_gem_object_create_internal(i915, sz);
+ if (IS_ERR(dst))
+ goto err_free_src;
+
+ for_i915_gem_ww(&ww, err, true) {
+ err = i915_gem_object_lock(src, &ww);
+ if (err)
+ continue;
+
+ err = i915_gem_object_lock(dst, &ww);
+ if (err)
+ continue;
+
+ vaddr = i915_gem_object_pin_map(src, I915_MAP_WC);
+ if (IS_ERR(vaddr)) {
+ err = PTR_ERR(vaddr);
+ continue;
+ }
+
+ for (i = 0; i < sz / sizeof(u32); i++)
+ vaddr[i] = i;
+ i915_gem_object_flush_map(src);
+
+ vaddr = i915_gem_object_pin_map(dst, I915_MAP_WC);
+ if (IS_ERR(vaddr)) {
+ err = PTR_ERR(vaddr);
+ goto unpin_src;
+ }
+
+ for (i = 0; i < sz / sizeof(u32); i++)
+ vaddr[i] = ~i;
+ i915_gem_object_flush_map(dst);
+
+ err = fn(migrate, &ww, src, dst, &rq);
+ if (!err)
+ continue;
+
+ if (err != -EDEADLK && err != -EINTR && err != -ERESTARTSYS)
+ pr_err("%ps failed, size: %u\n", fn, sz);
+ if (rq) {
+ i915_request_wait(rq, 0, HZ);
+ i915_request_put(rq);
+ }
+ i915_gem_object_unpin_map(dst);
+unpin_src:
+ i915_gem_object_unpin_map(src);
+ }
+ if (err)
+ goto err_out;
+
+ if (rq) {
+ if (i915_request_wait(rq, 0, HZ) < 0) {
+ pr_err("%ps timed out, size: %u\n", fn, sz);
+ err = -ETIME;
+ }
+ i915_request_put(rq);
+ }
+
+ for (i = 0; !err && i < sz / PAGE_SIZE; i++) {
+ int x = i * 1024 + i915_prandom_u32_max_state(1024, prng);
+
+ if (vaddr[x] != x) {
+ pr_err("%ps failed, size: %u, offset: %zu\n",
+ fn, sz, x * sizeof(u32));
+ igt_hexdump(vaddr + i * 1024, 4096);
+ err = -EINVAL;
+ }
+ }
+
+ i915_gem_object_unpin_map(dst);
+ i915_gem_object_unpin_map(src);
+
+err_out:
+ i915_gem_object_put(dst);
+err_free_src:
+ i915_gem_object_put(src);
+
+ return err;
+}
+
+static int __migrate_copy(struct intel_migrate *migrate,
+ struct i915_gem_ww_ctx *ww,
+ struct drm_i915_gem_object *src,
+ struct drm_i915_gem_object *dst,
+ struct i915_request **out)
+{
+ return intel_migrate_copy(migrate, ww, NULL,
+ src->mm.pages->sgl, src->cache_level,
+ i915_gem_object_is_lmem(src),
+ dst->mm.pages->sgl, dst->cache_level,
+ i915_gem_object_is_lmem(dst),
+ out);
+}
+
+static int __global_copy(struct intel_migrate *migrate,
+ struct i915_gem_ww_ctx *ww,
+ struct drm_i915_gem_object *src,
+ struct drm_i915_gem_object *dst,
+ struct i915_request **out)
+{
+ return intel_context_migrate_copy(migrate->context, NULL,
+ src->mm.pages->sgl, src->cache_level,
+ i915_gem_object_is_lmem(src),
+ dst->mm.pages->sgl, dst->cache_level,
+ i915_gem_object_is_lmem(dst),
+ out);
+}
+
+static int
+migrate_copy(struct intel_migrate *migrate, u32 sz, struct rnd_state *prng)
+{
+ return copy(migrate, __migrate_copy, sz, prng);
+}
+
+static int
+global_copy(struct intel_migrate *migrate, u32 sz, struct rnd_state *prng)
+{
+ return copy(migrate, __global_copy, sz, prng);
+}
+
+static int live_migrate_copy(void *arg)
+{
+ struct intel_migrate *migrate = arg;
+ struct drm_i915_private *i915 = migrate->context->engine->i915;
+ I915_RND_STATE(prng);
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(sizes); i++) {
+ int err;
+
+ err = migrate_copy(migrate, sizes[i], &prng);
+ if (err == 0)
+ err = global_copy(migrate, sizes[i], &prng);
+ i915_gem_drain_freed_objects(i915);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+struct threaded_migrate {
+ struct intel_migrate *migrate;
+ struct task_struct *tsk;
+ struct rnd_state prng;
+};
+
+static int threaded_migrate(struct intel_migrate *migrate,
+ int (*fn)(void *arg),
+ unsigned int flags)
+{
+ const unsigned int n_cpus = num_online_cpus() + 1;
+ struct threaded_migrate *thread;
+ I915_RND_STATE(prng);
+ unsigned int i;
+ int err = 0;
+
+ thread = kcalloc(n_cpus, sizeof(*thread), GFP_KERNEL);
+ if (!thread)
+ return 0;
+
+ for (i = 0; i < n_cpus; ++i) {
+ struct task_struct *tsk;
+
+ thread[i].migrate = migrate;
+ thread[i].prng =
+ I915_RND_STATE_INITIALIZER(prandom_u32_state(&prng));
+
+ tsk = kthread_run(fn, &thread[i], "igt-%d", i);
+ if (IS_ERR(tsk)) {
+ err = PTR_ERR(tsk);
+ break;
+ }
+
+ get_task_struct(tsk);
+ thread[i].tsk = tsk;
+ }
+
+ msleep(10); /* start all threads before we kthread_stop() */
+
+ for (i = 0; i < n_cpus; ++i) {
+ struct task_struct *tsk = thread[i].tsk;
+ int status;
+
+ if (IS_ERR_OR_NULL(tsk))
+ continue;
+
+ status = kthread_stop(tsk);
+ if (status && !err)
+ err = status;
+
+ put_task_struct(tsk);
+ }
+
+ kfree(thread);
+ return err;
+}
+
+static int __thread_migrate_copy(void *arg)
+{
+ struct threaded_migrate *tm = arg;
+
+ return migrate_copy(tm->migrate, 2 * CHUNK_SZ, &tm->prng);
+}
+
+static int thread_migrate_copy(void *arg)
+{
+ return threaded_migrate(arg, __thread_migrate_copy, 0);
+}
+
+static int __thread_global_copy(void *arg)
+{
+ struct threaded_migrate *tm = arg;
+
+ return global_copy(tm->migrate, 2 * CHUNK_SZ, &tm->prng);
+}
+
+static int thread_global_copy(void *arg)
+{
+ return threaded_migrate(arg, __thread_global_copy, 0);
+}
+
+int intel_migrate_live_selftests(struct drm_i915_private *i915)
+{
+ static const struct i915_subtest tests[] = {
+ SUBTEST(live_migrate_copy),
+ SUBTEST(thread_migrate_copy),
+ SUBTEST(thread_global_copy),
+ };
+ struct intel_migrate m;
+ int err;
+
+ if (intel_migrate_init(&m, &i915->gt))
+ return 0;
+
+ err = i915_subtests(tests, &m);
+ intel_migrate_fini(&m);
+
+ return err;
+}
@@ -26,6 +26,7 @@ selftest(gt_mocs, intel_mocs_live_selftests)
selftest(gt_pm, intel_gt_pm_live_selftests)
selftest(gt_heartbeat, intel_heartbeat_live_selftests)
selftest(requests, i915_request_live_selftests)
+selftest(migrate, intel_migrate_live_selftests)
selftest(active, i915_active_live_selftests)
selftest(objects, i915_gem_object_live_selftests)
selftest(mman, i915_gem_mman_live_selftests)