From c30ddcece3a0a86853862a7d92678a79525ca1fb Mon Sep 17 00:00:00 2001
From: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Date: Thu, 13 Apr 2023 16:22:52 +0200
Subject: drm/amdgpu: Add a max ibs per submission limit.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
And ensure each ring supports that many submissions. This makes
sure that we don't get surprises after the submission has been
scheduled where the ring allocation actually gets rejected.
My calculations on the existing limits:
COMPUTE v10: 128
COMPUTE v11: 128
COMPUTE v6: 157
COMPUTE v7: 133
COMPUTE v8: 130
COMPUTE v9: 125
GFX v10: 208
GFX v11: 213
GFX v6: 154 (doubling this in the previous patch)
GFX v7: 226
GFX v8: 213
GFX v9: 208
GFX v9 (SW): 208
SDMA CIK: 87
SDMA SI: 97
SDMA v2.4: 74
SDMA v3.0: 74
SDMA v4.0: 72
SDMA v5.0: 51
SDMA v6.0: 52
UVD ENC v6.0: 98
UVD ENC v7.0: 92
UVD v3.1: 124
UVD v4.2: 124
UVD v5.0: 83
UVD v6.0 (VM): 55
UVD v7.0: 51
VCE v2.0: 126
VCE v3.0 (VM): 98
VCE v4.0: 93
VCN DEC v1.0: 49
VCN DEC v2.0: 51
VCN DEC v3.0: 51
VCN ENC v1.0: 58
VCN ENC v2.0: 93
VCN ENC v3.0: 93
VCN ENC v4.0: 93
VCN JPEG v1.0: 17
VCN JPEG v2.0: 16
VCN JPEG v2.5: 17
VCN JPEG v3.0: 17
VCN JPEG v4.0: 17
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2498
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 3 +++
1 file changed, 3 insertions(+)
(limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c')
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 08eced097bd8..d8b3c9198d33 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -112,6 +112,9 @@ static int amdgpu_cs_p1_ib(struct amdgpu_cs_parser *p,
if (r < 0)
return r;
+ if (num_ibs[r] >= amdgpu_ring_max_ibs(chunk_ib->ip_type))
+ return -EINVAL;
+
++(num_ibs[r]);
p->gang_leader_idx = r;
return 0;
--
cgit v1.2.3
From 87c2213e85bd81e4a9a4d0880c256568794ae388 Mon Sep 17 00:00:00 2001
From: hackyzh002 <hackyzh002@gmail.com>
Date: Wed, 19 Apr 2023 20:22:33 +0800
Subject: drm/amdgpu: Fix integer overflow in amdgpu_cs_pass1
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The type of size is unsigned int, if size is 0x40000000, there will
be an integer overflow, size will be zero after size *= sizeof(uint32_t),
will cause uninitialized memory to be referenced later.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: hackyzh002 <hackyzh002@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c')
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index d8b3c9198d33..a8ec5ff41fc0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -195,7 +195,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p,
uint64_t *chunk_array_user;
uint64_t *chunk_array;
uint32_t uf_offset = 0;
- unsigned int size;
+ size_t size;
int ret;
int i;
--
cgit v1.2.3
From ac9287055ff16a092416c76a19006764e4c6a978 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 9 Mar 2023 15:40:48 -0500
Subject: drm/amdgpu: add gfx shadow CS IOCTL support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Add support for submitting the shadow update packet
when submitting an IB. Needed for MCBP on GFX11.
v2: update API for CSA (Alex)
v3: fix ordering; SET_Q_PREEMPTION_MODE most come before COND_EXEC
Add missing check for AMDGPU_CHUNK_ID_CP_GFX_SHADOW in
amdgpu_cs_pass1()
Only initialize shadow on first use
(Alex)
v4: Pass parameters rather than job to new ring callback (Alex)
v5: squash in change to call SET_Q_PREEMPTION_MODE/COND_EXEC
before RELEASE_MEM to complete the UMDs use of the shadow (Alex)
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 26 ++++++++++++++++++++++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 29 ++++++++++++++++++++++++++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_job.h | 6 ++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 3 +++
4 files changed, 63 insertions(+), 1 deletion(-)
(limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c')
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index a8ec5ff41fc0..c3b3287dc29e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -288,6 +288,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p,
case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES:
case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT:
case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL:
+ case AMDGPU_CHUNK_ID_CP_GFX_SHADOW:
break;
default:
@@ -578,6 +579,26 @@ static int amdgpu_cs_p2_syncobj_timeline_signal(struct amdgpu_cs_parser *p,
return 0;
}
+static int amdgpu_cs_p2_shadow(struct amdgpu_cs_parser *p,
+ struct amdgpu_cs_chunk *chunk)
+{
+ struct drm_amdgpu_cs_chunk_cp_gfx_shadow *shadow = chunk->kdata;
+ int i;
+
+ if (shadow->flags & ~AMDGPU_CS_CHUNK_CP_GFX_SHADOW_FLAGS_INIT_SHADOW)
+ return -EINVAL;
+
+ for (i = 0; i < p->gang_size; ++i) {
+ p->jobs[i]->shadow_va = shadow->shadow_va;
+ p->jobs[i]->csa_va = shadow->csa_va;
+ p->jobs[i]->gds_va = shadow->gds_va;
+ p->jobs[i]->init_shadow =
+ shadow->flags & AMDGPU_CS_CHUNK_CP_GFX_SHADOW_FLAGS_INIT_SHADOW;
+ }
+
+ return 0;
+}
+
static int amdgpu_cs_pass2(struct amdgpu_cs_parser *p)
{
unsigned int ce_preempt = 0, de_preempt = 0;
@@ -620,6 +641,11 @@ static int amdgpu_cs_pass2(struct amdgpu_cs_parser *p)
if (r)
return r;
break;
+ case AMDGPU_CHUNK_ID_CP_GFX_SHADOW:
+ r = amdgpu_cs_p2_shadow(p, chunk);
+ if (r)
+ return r;
+ break;
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index ef96ff2f4272..aebc0e5bddc6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -136,7 +136,9 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
uint64_t fence_ctx;
uint32_t status = 0, alloc_size;
unsigned fence_flags = 0;
- bool secure;
+ bool secure, init_shadow;
+ u64 shadow_va, csa_va, gds_va;
+ int vmid = AMDGPU_JOB_GET_VMID(job);
unsigned i;
int r = 0;
@@ -150,9 +152,17 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
vm = job->vm;
fence_ctx = job->base.s_fence ?
job->base.s_fence->scheduled.context : 0;
+ shadow_va = job->shadow_va;
+ csa_va = job->csa_va;
+ gds_va = job->gds_va;
+ init_shadow = job->init_shadow;
} else {
vm = NULL;
fence_ctx = 0;
+ shadow_va = 0;
+ csa_va = 0;
+ gds_va = 0;
+ init_shadow = false;
}
if (!ring->sched.ready && !ring->is_mes_queue) {
@@ -212,6 +222,11 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
}
amdgpu_ring_ib_begin(ring);
+
+ if (job && ring->funcs->emit_gfx_shadow)
+ amdgpu_ring_emit_gfx_shadow(ring, shadow_va, csa_va, gds_va,
+ init_shadow, vmid);
+
if (job && ring->funcs->init_cond_exec)
patch_offset = amdgpu_ring_init_cond_exec(ring);
@@ -263,6 +278,18 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
fence_flags | AMDGPU_FENCE_FLAG_64BIT);
}
+ if (ring->funcs->emit_gfx_shadow) {
+ amdgpu_ring_emit_gfx_shadow(ring, 0, 0, 0, false, 0);
+
+ if (ring->funcs->init_cond_exec) {
+ unsigned ce_offset = ~0;
+
+ ce_offset = amdgpu_ring_init_cond_exec(ring);
+ if (ce_offset != ~0 && ring->funcs->patch_cond_exec)
+ amdgpu_ring_patch_cond_exec(ring, ce_offset);
+ }
+ }
+
r = amdgpu_fence_emit(ring, f, job, fence_flags);
if (r) {
dev_err(adev->dev, "failed to emit fence (%d)\n", r);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index 52f2e313ea17..3f9804f956c9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -67,6 +67,12 @@ struct amdgpu_job {
uint64_t uf_addr;
uint64_t uf_sequence;
+ /* virtual addresses for shadow/GDS/CSA */
+ uint64_t shadow_va;
+ uint64_t csa_va;
+ uint64_t gds_va;
+ bool init_shadow;
+
/* job_run_counter >= 1 means a resubmit job */
uint32_t job_run_counter;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 8eca6532ed19..2aa6cc1c4212 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -212,6 +212,8 @@ struct amdgpu_ring_funcs {
void (*end_use)(struct amdgpu_ring *ring);
void (*emit_switch_buffer) (struct amdgpu_ring *ring);
void (*emit_cntxcntl) (struct amdgpu_ring *ring, uint32_t flags);
+ void (*emit_gfx_shadow)(struct amdgpu_ring *ring, u64 shadow_va, u64 csa_va,
+ u64 gds_va, bool init_shadow, int vmid);
void (*emit_rreg)(struct amdgpu_ring *ring, uint32_t reg,
uint32_t reg_val_offs);
void (*emit_wreg)(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
@@ -309,6 +311,7 @@ struct amdgpu_ring {
#define amdgpu_ring_emit_hdp_flush(r) (r)->funcs->emit_hdp_flush((r))
#define amdgpu_ring_emit_switch_buffer(r) (r)->funcs->emit_switch_buffer((r))
#define amdgpu_ring_emit_cntxcntl(r, d) (r)->funcs->emit_cntxcntl((r), (d))
+#define amdgpu_ring_emit_gfx_shadow(r, s, c, g, i, v) ((r)->funcs->emit_gfx_shadow((r), (s), (c), (g), (i), (v)))
#define amdgpu_ring_emit_rreg(r, d, o) (r)->funcs->emit_rreg((r), (d), (o))
#define amdgpu_ring_emit_wreg(r, d, v) (r)->funcs->emit_wreg((r), (d), (v))
#define amdgpu_ring_emit_reg_wait(r, d, v, m) (r)->funcs->emit_reg_wait((r), (d), (v), (m))
--
cgit v1.2.3
From 9e690184586bfb88efa176cdf912414f6c53519c Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Wed, 3 May 2023 14:10:20 +0530
Subject: drm/amd/amdgpu: Fix errors & warnings in amdgpu _bios, _cs, _dma_buf,
_fence.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The following checkpatch errors & warning is removed.
ERROR: else should follow close brace '}'
ERROR: trailing statements should be on next line
WARNING: Prefer 'unsigned int' to bare use of 'unsigned'
WARNING: Possible repeated word: 'Fences'
WARNING: Missing a blank line after declarations
WARNING: braces {} are not necessary for single statement blocks
WARNING: Comparisons should place the constant on the right side of the test
WARNING: printk() should include KERN_<LEVEL> facility level
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c | 16 +++++++---------
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 16 ++++++++--------
drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 14 ++++++++------
4 files changed, 24 insertions(+), 24 deletions(-)
(limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c')
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
index 30c28a69e847..b582b83c4984 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
@@ -104,9 +104,8 @@ static bool igp_read_bios_from_vram(struct amdgpu_device *adev)
adev->bios = NULL;
vram_base = pci_resource_start(adev->pdev, 0);
bios = ioremap_wc(vram_base, size);
- if (!bios) {
+ if (!bios)
return false;
- }
adev->bios = kmalloc(size, GFP_KERNEL);
if (!adev->bios) {
@@ -133,9 +132,8 @@ bool amdgpu_read_bios(struct amdgpu_device *adev)
adev->bios = NULL;
/* XXX: some cards may return 0 for rom size? ddx has a workaround */
bios = pci_map_rom(adev->pdev, &size);
- if (!bios) {
+ if (!bios)
return false;
- }
adev->bios = kzalloc(size, GFP_KERNEL);
if (adev->bios == NULL) {
@@ -168,9 +166,9 @@ static bool amdgpu_read_bios_from_rom(struct amdgpu_device *adev)
header[AMD_VBIOS_SIGNATURE_END] = 0;
if ((!AMD_IS_VALID_VBIOS(header)) ||
- 0 != memcmp((char *)&header[AMD_VBIOS_SIGNATURE_OFFSET],
- AMD_VBIOS_SIGNATURE,
- strlen(AMD_VBIOS_SIGNATURE)))
+ memcmp((char *)&header[AMD_VBIOS_SIGNATURE_OFFSET],
+ AMD_VBIOS_SIGNATURE,
+ strlen(AMD_VBIOS_SIGNATURE)) != 0)
return false;
/* valid vbios, go on */
@@ -264,7 +262,7 @@ static int amdgpu_atrm_call(acpi_handle atrm_handle, uint8_t *bios,
status = acpi_evaluate_object(atrm_handle, NULL, &atrm_arg, &buffer);
if (ACPI_FAILURE(status)) {
- printk("failed to evaluate ATRM got %s\n", acpi_format_exception(status));
+ DRM_ERROR("failed to evaluate ATRM got %s\n", acpi_format_exception(status));
return -ENODEV;
}
@@ -363,7 +361,7 @@ static bool amdgpu_acpi_vfct_bios(struct amdgpu_device *adev)
struct acpi_table_header *hdr;
acpi_size tbl_size;
UEFI_ACPI_VFCT *vfct;
- unsigned offset;
+ unsigned int offset;
if (!ACPI_SUCCESS(acpi_get_table("VFCT", 1, &hdr)))
return false;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index c3b3287dc29e..5270089aee16 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -397,7 +397,7 @@ static int amdgpu_cs_p2_dependencies(struct amdgpu_cs_parser *p,
{
struct drm_amdgpu_cs_chunk_dep *deps = chunk->kdata;
struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
- unsigned num_deps;
+ unsigned int num_deps;
int i, r;
num_deps = chunk->length_dw * 4 /
@@ -468,7 +468,7 @@ static int amdgpu_cs_p2_syncobj_in(struct amdgpu_cs_parser *p,
struct amdgpu_cs_chunk *chunk)
{
struct drm_amdgpu_cs_chunk_sem *deps = chunk->kdata;
- unsigned num_deps;
+ unsigned int num_deps;
int i, r;
num_deps = chunk->length_dw * 4 /
@@ -486,7 +486,7 @@ static int amdgpu_cs_p2_syncobj_timeline_wait(struct amdgpu_cs_parser *p,
struct amdgpu_cs_chunk *chunk)
{
struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps = chunk->kdata;
- unsigned num_deps;
+ unsigned int num_deps;
int i, r;
num_deps = chunk->length_dw * 4 /
@@ -506,7 +506,7 @@ static int amdgpu_cs_p2_syncobj_out(struct amdgpu_cs_parser *p,
struct amdgpu_cs_chunk *chunk)
{
struct drm_amdgpu_cs_chunk_sem *deps = chunk->kdata;
- unsigned num_deps;
+ unsigned int num_deps;
int i;
num_deps = chunk->length_dw * 4 /
@@ -540,7 +540,7 @@ static int amdgpu_cs_p2_syncobj_timeline_signal(struct amdgpu_cs_parser *p,
struct amdgpu_cs_chunk *chunk)
{
struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps = chunk->kdata;
- unsigned num_deps;
+ unsigned int num_deps;
int i;
num_deps = chunk->length_dw * 4 /
@@ -758,6 +758,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev,
if (used_vis_vram < total_vis_vram) {
u64 free_vis_vram = total_vis_vram - used_vis_vram;
+
adev->mm_stats.accum_us_vis = min(adev->mm_stats.accum_us_vis +
increment_us, us_upper_bound);
@@ -1076,9 +1077,8 @@ static int amdgpu_cs_patch_ibs(struct amdgpu_cs_parser *p,
/* the IB should be reserved at this point */
r = amdgpu_bo_kmap(aobj, (void **)&kptr);
- if (r) {
+ if (r)
return r;
- }
kptr += va_start - (m->start * AMDGPU_GPU_PAGE_SIZE);
@@ -1392,7 +1392,7 @@ error_cleanup:
/* Cleanup the parser structure */
static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser)
{
- unsigned i;
+ unsigned int i;
amdgpu_sync_free(&parser->sync);
for (i = 0; i < parser->num_post_deps; i++) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 0c001bb8fc2b..6dceaf40625b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -149,7 +149,7 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach,
if (!bo->tbo.pin_count) {
/* move buffer into GTT or VRAM */
struct ttm_operation_ctx ctx = { false, false };
- unsigned domains = AMDGPU_GEM_DOMAIN_GTT;
+ unsigned int domains = AMDGPU_GEM_DOMAIN_GTT;
if (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM &&
attach->peer2peer) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index f52d0ba91a77..1994eafd3e71 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -42,7 +42,6 @@
#include "amdgpu_reset.h"
/*
- * Fences
* Fences mark an event in the GPUs pipeline and are used
* for GPU/CPU synchronization. When the fence is written,
* it is expected that all buffers associated with that fence
@@ -140,7 +139,7 @@ static u32 amdgpu_fence_read(struct amdgpu_ring *ring)
* Returns 0 on success, -ENOMEM on failure.
*/
int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amdgpu_job *job,
- unsigned flags)
+ unsigned int flags)
{
struct amdgpu_device *adev = ring->adev;
struct dma_fence *fence;
@@ -174,11 +173,11 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd
adev->fence_context + ring->idx, seq);
/* Against remove in amdgpu_job_{free, free_cb} */
dma_fence_get(fence);
- }
- else
+ } else {
dma_fence_init(fence, &amdgpu_fence_ops,
&ring->fence_drv.lock,
adev->fence_context + ring->idx, seq);
+ }
}
amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
@@ -396,7 +395,7 @@ signed long amdgpu_fence_wait_polling(struct amdgpu_ring *ring,
* Returns the number of emitted fences on the ring. Used by the
* dynpm code to ring track activity.
*/
-unsigned amdgpu_fence_count_emitted(struct amdgpu_ring *ring)
+unsigned int amdgpu_fence_count_emitted(struct amdgpu_ring *ring)
{
uint64_t emitted;
@@ -475,7 +474,7 @@ void amdgpu_fence_update_start_timestamp(struct amdgpu_ring *ring, uint32_t seq,
*/
int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
struct amdgpu_irq_src *irq_src,
- unsigned irq_type)
+ unsigned int irq_type)
{
struct amdgpu_device *adev = ring->adev;
uint64_t index;
@@ -653,6 +652,7 @@ void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev)
for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
struct amdgpu_ring *ring = adev->rings[i];
+
if (!ring || !ring->fence_drv.initialized)
continue;
@@ -840,6 +840,7 @@ static int amdgpu_debugfs_fence_info_show(struct seq_file *m, void *unused)
for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
struct amdgpu_ring *ring = adev->rings[i];
+
if (!ring || !ring->fence_drv.initialized)
continue;
@@ -913,6 +914,7 @@ static void amdgpu_debugfs_reset_work(struct work_struct *work)
reset_work);
struct amdgpu_reset_context reset_context;
+
memset(&reset_context, 0, sizeof(reset_context));
reset_context.method = AMD_RESET_METHOD_NONE;
--
cgit v1.2.3
From 967a66396e4668ef314e06a0391e67aa1cf6d058 Mon Sep 17 00:00:00 2001
From: Guchun Chen <guchun.chen@amd.com>
Date: Wed, 26 Apr 2023 09:46:54 +0800
Subject: drm/amdgpu: drop redundant sched job cleanup when cs is aborted
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Once command submission failed due to userptr invalidation in
amdgpu_cs_submit, legacy code will perform cleanup of scheduler
job. However, it's not needed at all, as former commit has integrated
job cleanup stuff into amdgpu_job_free. Otherwise, because of double
free, a NULL pointer dereference will occur in such scenario.
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2457
Fixes: f7d66fb2ea43 ("drm/amdgpu: cleanup scheduler job initialization v2")
Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 13 +++----------
1 file changed, 3 insertions(+), 10 deletions(-)
(limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c')
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 5270089aee16..6e1d331af01f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1305,7 +1305,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
r = drm_sched_job_add_dependency(&leader->base, fence);
if (r) {
dma_fence_put(fence);
- goto error_cleanup;
+ return r;
}
}
@@ -1332,7 +1332,8 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
}
if (r) {
r = -EAGAIN;
- goto error_unlock;
+ mutex_unlock(&p->adev->notifier_lock);
+ return r;
}
p->fence = dma_fence_get(&leader->base.s_fence->finished);
@@ -1379,14 +1380,6 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
mutex_unlock(&p->adev->notifier_lock);
mutex_unlock(&p->bo_list->bo_list_mutex);
return 0;
-
-error_unlock:
- mutex_unlock(&p->adev->notifier_lock);
-
-error_cleanup:
- for (i = 0; i < p->gang_size; ++i)
- drm_sched_job_cleanup(&p->jobs[i]->base);
- return r;
}
/* Cleanup the parser structure */
--
cgit v1.2.3