linux_dsm_epyc7002/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c

369 lines
9.4 KiB
C
Raw Normal View History

/*
* Copyright 2008 Advanced Micro Devices, Inc.
* Copyright 2008 Red Hat Inc.
* Copyright 2009 Jerome Glisse.
*
* 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 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 COPYRIGHT HOLDER(S) OR AUTHOR(S) 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.
*
* Authors: Dave Airlie
* Alex Deucher
* Jerome Glisse
* Christian König
*/
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <drm/drmP.h>
#include <drm/amdgpu_drm.h>
#include "amdgpu.h"
#include "atom.h"
#define AMDGPU_IB_TEST_TIMEOUT msecs_to_jiffies(1000)
/*
* IB
* IBs (Indirect Buffers) and areas of GPU accessible memory where
* commands are stored. You can put a pointer to the IB in the
* command ring and the hw will fetch the commands from the IB
* and execute them. Generally userspace acceleration drivers
* produce command buffers which are send to the kernel and
* put in IBs for execution by the requested ring.
*/
static int amdgpu_debugfs_sa_init(struct amdgpu_device *adev);
/**
* amdgpu_ib_get - request an IB (Indirect Buffer)
*
* @ring: ring index the IB is associated with
* @size: requested IB size
* @ib: IB object returned
*
* Request an IB (all asics). IBs are allocated using the
* suballocator.
* Returns 0 on success, error on failure.
*/
int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
unsigned size, struct amdgpu_ib *ib)
{
int r;
if (size) {
r = amdgpu_sa_bo_new(&adev->ring_tmp_bo,
&ib->sa_bo, size, 256);
if (r) {
dev_err(adev->dev, "failed to get a new IB (%d)\n", r);
return r;
}
ib->ptr = amdgpu_sa_bo_cpu_addr(ib->sa_bo);
if (!vm)
ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo);
}
return 0;
}
/**
* amdgpu_ib_free - free an IB (Indirect Buffer)
*
* @adev: amdgpu_device pointer
* @ib: IB object to free
* @f: the fence SA bo need wait on for the ib alloation
*
* Free an IB (all asics).
*/
void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib,
dma-buf: Rename struct fence to dma_fence I plan to usurp the short name of struct fence for a core kernel struct, and so I need to rename the specialised fence/timeline for DMA operations to make room. A consensus was reached in https://lists.freedesktop.org/archives/dri-devel/2016-July/113083.html that making clear this fence applies to DMA operations was a good thing. Since then the patch has grown a bit as usage increases, so hopefully it remains a good thing! (v2...: rebase, rerun spatch) v3: Compile on msm, spotted a manual fixup that I broke. v4: Try again for msm, sorry Daniel coccinelle script: @@ @@ - struct fence + struct dma_fence @@ @@ - struct fence_ops + struct dma_fence_ops @@ @@ - struct fence_cb + struct dma_fence_cb @@ @@ - struct fence_array + struct dma_fence_array @@ @@ - enum fence_flag_bits + enum dma_fence_flag_bits @@ @@ ( - fence_init + dma_fence_init | - fence_release + dma_fence_release | - fence_free + dma_fence_free | - fence_get + dma_fence_get | - fence_get_rcu + dma_fence_get_rcu | - fence_put + dma_fence_put | - fence_signal + dma_fence_signal | - fence_signal_locked + dma_fence_signal_locked | - fence_default_wait + dma_fence_default_wait | - fence_add_callback + dma_fence_add_callback | - fence_remove_callback + dma_fence_remove_callback | - fence_enable_sw_signaling + dma_fence_enable_sw_signaling | - fence_is_signaled_locked + dma_fence_is_signaled_locked | - fence_is_signaled + dma_fence_is_signaled | - fence_is_later + dma_fence_is_later | - fence_later + dma_fence_later | - fence_wait_timeout + dma_fence_wait_timeout | - fence_wait_any_timeout + dma_fence_wait_any_timeout | - fence_wait + dma_fence_wait | - fence_context_alloc + dma_fence_context_alloc | - fence_array_create + dma_fence_array_create | - to_fence_array + to_dma_fence_array | - fence_is_array + dma_fence_is_array | - trace_fence_emit + trace_dma_fence_emit | - FENCE_TRACE + DMA_FENCE_TRACE | - FENCE_WARN + DMA_FENCE_WARN | - FENCE_ERR + DMA_FENCE_ERR ) ( ... ) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk> Acked-by: Sumit Semwal <sumit.semwal@linaro.org> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20161025120045.28839-1-chris@chris-wilson.co.uk
2016-10-25 19:00:45 +07:00
struct dma_fence *f)
{
amdgpu_sa_bo_free(adev, &ib->sa_bo, f);
}
/**
* amdgpu_ib_schedule - schedule an IB (Indirect Buffer) on the ring
*
* @adev: amdgpu_device pointer
* @num_ibs: number of IBs to schedule
* @ibs: IB objects to schedule
* @f: fence created during this submission
*
* Schedule an IB on the associated ring (all asics).
* Returns 0 on success, error on failure.
*
* On SI, there are two parallel engines fed from the primary ring,
* the CE (Constant Engine) and the DE (Drawing Engine). Since
* resource descriptors have moved to memory, the CE allows you to
* prime the caches while the DE is updating register state so that
* the resource descriptors will be already in cache when the draw is
* processed. To accomplish this, the userspace driver submits two
* IBs, one for the CE and one for the DE. If there is a CE IB (called
* a CONST_IB), it will be put on the ring prior to the DE IB. Prior
* to SI there was just a DE IB.
*/
int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
struct amdgpu_ib *ibs, struct amdgpu_job *job,
struct dma_fence **f)
{
struct amdgpu_device *adev = ring->adev;
struct amdgpu_ib *ib = &ibs[0];
bool skip_preamble, need_ctx_switch;
unsigned patch_offset = ~0;
struct amdgpu_vm *vm;
uint64_t fence_ctx;
uint32_t status = 0, alloc_size;
unsigned i;
int r = 0;
if (num_ibs == 0)
return -EINVAL;
/* ring tests don't use a job */
if (job) {
vm = job->vm;
fence_ctx = job->fence_ctx;
} else {
vm = NULL;
fence_ctx = 0;
}
if (!ring->ready) {
dev_err(adev->dev, "couldn't schedule ib on ring <%s>\n", ring->name);
return -EINVAL;
}
if (vm && !job->vm_id) {
dev_err(adev->dev, "VM IB without ID\n");
return -EINVAL;
}
alloc_size = ring->funcs->emit_frame_size + num_ibs *
ring->funcs->emit_ib_size;
r = amdgpu_ring_alloc(ring, alloc_size);
if (r) {
dev_err(adev->dev, "scheduling IB failed (%d).\n", r);
return r;
}
if (vm) {
r = amdgpu_vm_flush(ring, job);
if (r) {
amdgpu_ring_undo(ring);
return r;
}
}
drm/amdgpu:changes in gfx DMAframe scheme (v2) 1) Adapt to vulkan: Now use double SWITCH BUFFER to replace the 128 nops w/a, because when vulkan introduced, umd can insert 7 ~ 16 IBs per submit which makes 256 DW size cannot hold the whole DMAframe (if we still insert those 128 nops), CP team suggests use double SWITCH_BUFFERs, instead of tricky 128 NOPs w/a. 2) To fix the CE VM fault issue when MCBP introduced: Need one more COND_EXEC wrapping IB part (original one us for VM switch part). this change can fix vm fault issue caused by below scenario without this change: >CE passed original COND_EXEC (no MCBP issued this moment), proceed as normal. >DE catch up to this COND_EXEC, but this time MCBP issued, thus DE treats all following packages as NOP. The following VM switch packages now looks just as NOP to DE, so DE dosen't do VM flush at all. >Now CE proceeds to the first IBc, and triggers VM fault, because DE didn't do VM flush for this DMAframe. 3) change estimated alloc size for gfx9. with new DMAframe scheme, we need modify emit_frame_size for gfx9 4) No need to insert 128 nops after gfx8 vm flush anymore because there was double SWITCH_BUFFER append to vm flush, and for gfx7 we already use double SWITCH_BUFFER following after vm_flush so no change needed for it. 5) Change emit_frame_size for gfx8 v2: squash in BUG removal from Monk Signed-off-by: Monk Liu <Monk.Liu@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2017-03-15 11:18:57 +07:00
if (ring->funcs->init_cond_exec)
patch_offset = amdgpu_ring_init_cond_exec(ring);
if (ring->funcs->emit_hdp_flush
#ifdef CONFIG_X86_64
&& !(adev->flags & AMD_IS_APU)
#endif
)
amdgpu_ring_emit_hdp_flush(ring);
skip_preamble = ring->current_ctx == fence_ctx;
need_ctx_switch = ring->current_ctx != fence_ctx;
if (job && ring->funcs->emit_cntxcntl) {
if (need_ctx_switch)
status |= AMDGPU_HAVE_CTX_SWITCH;
status |= job->preamble_status;
if (vm)
status |= AMDGPU_VM_DOMAIN;
amdgpu_ring_emit_cntxcntl(ring, status);
}
for (i = 0; i < num_ibs; ++i) {
ib = &ibs[i];
/* drop preamble IBs if we don't have a context switch */
if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) &&
skip_preamble &&
!(status & AMDGPU_PREAMBLE_IB_PRESENT_FIRST) &&
!amdgpu_sriov_vf(adev)) /* for SRIOV preemption, Preamble CE ib must be inserted anyway */
continue;
amdgpu_ring_emit_ib(ring, ib, job ? job->vm_id : 0,
need_ctx_switch);
need_ctx_switch = false;
}
if (ring->funcs->emit_hdp_invalidate
#ifdef CONFIG_X86_64
&& !(adev->flags & AMD_IS_APU)
#endif
)
amdgpu_ring_emit_hdp_invalidate(ring);
r = amdgpu_fence_emit(ring, f);
if (r) {
dev_err(adev->dev, "failed to emit fence (%d)\n", r);
if (job && job->vm_id)
amdgpu_vm_reset_id(adev, job->vm_id);
amdgpu_ring_undo(ring);
return r;
}
if (ring->funcs->insert_end)
ring->funcs->insert_end(ring);
/* wrap the last IB with fence */
if (job && job->uf_addr) {
amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
AMDGPU_FENCE_FLAG_64BIT);
}
if (patch_offset != ~0 && ring->funcs->patch_cond_exec)
amdgpu_ring_patch_cond_exec(ring, patch_offset);
ring->current_ctx = fence_ctx;
if (vm && ring->funcs->emit_switch_buffer)
amdgpu_ring_emit_switch_buffer(ring);
amdgpu_ring_commit(ring);
return 0;
}
/**
* amdgpu_ib_pool_init - Init the IB (Indirect Buffer) pool
*
* @adev: amdgpu_device pointer
*
* Initialize the suballocator to manage a pool of memory
* for use as IBs (all asics).
* Returns 0 on success, error on failure.
*/
int amdgpu_ib_pool_init(struct amdgpu_device *adev)
{
int r;
if (adev->ib_pool_ready) {
return 0;
}
r = amdgpu_sa_bo_manager_init(adev, &adev->ring_tmp_bo,
AMDGPU_IB_POOL_SIZE*64*1024,
AMDGPU_GPU_PAGE_SIZE,
AMDGPU_GEM_DOMAIN_GTT);
if (r) {
return r;
}
r = amdgpu_sa_bo_manager_start(adev, &adev->ring_tmp_bo);
if (r) {
return r;
}
adev->ib_pool_ready = true;
if (amdgpu_debugfs_sa_init(adev)) {
dev_err(adev->dev, "failed to register debugfs file for SA\n");
}
return 0;
}
/**
* amdgpu_ib_pool_fini - Free the IB (Indirect Buffer) pool
*
* @adev: amdgpu_device pointer
*
* Tear down the suballocator managing the pool of memory
* for use as IBs (all asics).
*/
void amdgpu_ib_pool_fini(struct amdgpu_device *adev)
{
if (adev->ib_pool_ready) {
amdgpu_sa_bo_manager_suspend(adev, &adev->ring_tmp_bo);
amdgpu_sa_bo_manager_fini(adev, &adev->ring_tmp_bo);
adev->ib_pool_ready = false;
}
}
/**
* amdgpu_ib_ring_tests - test IBs on the rings
*
* @adev: amdgpu_device pointer
*
* Test an IB (Indirect Buffer) on each ring.
* If the test fails, disable the ring.
* Returns 0 on success, error if the primary GFX ring
* IB test fails.
*/
int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
{
unsigned i;
int r, ret = 0;
for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
struct amdgpu_ring *ring = adev->rings[i];
if (!ring || !ring->ready)
continue;
r = amdgpu_ring_test_ib(ring, AMDGPU_IB_TEST_TIMEOUT);
if (r) {
ring->ready = false;
if (ring == &adev->gfx.gfx_ring[0]) {
/* oh, oh, that's really bad */
DRM_ERROR("amdgpu: failed testing IB on GFX ring (%d).\n", r);
adev->accel_working = false;
return r;
} else {
/* still not good, but we can live with it */
DRM_ERROR("amdgpu: failed testing IB on ring %d (%d).\n", i, r);
ret = r;
}
}
}
return ret;
}
/*
* Debugfs info
*/
#if defined(CONFIG_DEBUG_FS)
static int amdgpu_debugfs_sa_info(struct seq_file *m, void *data)
{
struct drm_info_node *node = (struct drm_info_node *) m->private;
struct drm_device *dev = node->minor->dev;
struct amdgpu_device *adev = dev->dev_private;
amdgpu_sa_bo_dump_debug_info(&adev->ring_tmp_bo, m);
return 0;
}
static const struct drm_info_list amdgpu_debugfs_sa_list[] = {
{"amdgpu_sa_info", &amdgpu_debugfs_sa_info, 0, NULL},
};
#endif
static int amdgpu_debugfs_sa_init(struct amdgpu_device *adev)
{
#if defined(CONFIG_DEBUG_FS)
return amdgpu_debugfs_add_files(adev, amdgpu_debugfs_sa_list, 1);
#else
return 0;
#endif
}