From: Oak Zeng <oak.zeng@intel.com>
To: dri-devel@lists.freedesktop.org, intel-xe@lists.freedesktop.org
Cc: matthew.brost@intel.com, Thomas.Hellstrom@linux.intel.com,
brian.welty@intel.com, himal.prasad.ghimiray@intel.com,
krishnaiah.bommu@intel.com, niranjana.vishwanathapura@intel.com
Subject: [PATCH 07/23] drm/xe/svm: Add helper for binding hmm range to gpu
Date: Wed, 17 Jan 2024 17:12:07 -0500 [thread overview]
Message-ID: <20240117221223.18540-8-oak.zeng@intel.com> (raw)
In-Reply-To: <20240117221223.18540-1-oak.zeng@intel.com>
Add helper function xe_bind_svm_range to bind a svm range
to gpu. A temporary xe_vma is created locally to re-use
existing page table update functions which are vma-based.
The svm page table update lock design is different from
userptr and bo page table update. A xe_pt_svm_pre_commit
function is introduced for svm range pre-commitment.
A hmm_range pointer is added to xe_vma struct.
v1: Make userptr member to be the last member of xe_vma struct
Signed-off-by: Oak Zeng <oak.zeng@intel.com>
Cc: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@intel.com>
Cc: Brian Welty <brian.welty@intel.com>
---
drivers/gpu/drm/xe/xe_pt.c | 114 +++++++++++++++++++++++++++++--
drivers/gpu/drm/xe/xe_pt.h | 4 ++
drivers/gpu/drm/xe/xe_vm_types.h | 13 +++-
3 files changed, 126 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index de1030a47588..f1e479fa3001 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -17,6 +17,7 @@
#include "xe_trace.h"
#include "xe_ttm_stolen_mgr.h"
#include "xe_vm.h"
+#include "xe_svm.h"
struct xe_pt_dir {
struct xe_pt pt;
@@ -582,8 +583,15 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma,
{
struct xe_device *xe = tile_to_xe(tile);
struct xe_bo *bo = xe_vma_bo(vma);
- bool is_devmem = !xe_vma_is_userptr(vma) && bo &&
- (xe_bo_is_vram(bo) || xe_bo_is_stolen_devmem(bo));
+ /*
+ * FIXME: Right now assume all svm ranges bound to GPU is backed
+ * by device memory. This assumption will change once migration
+ * policy is implemented. A svm range's backing store can be a
+ * mixture of device memory and system memory, page by page based.
+ * We probably need a separate stage_bind function for svm.
+ */
+ bool is_devmem = vma->svm_sg || (!xe_vma_is_userptr(vma) && bo &&
+ (xe_bo_is_vram(bo) || xe_bo_is_stolen_devmem(bo)));
struct xe_res_cursor curs;
struct xe_pt_stage_bind_walk xe_walk = {
.base = {
@@ -617,7 +625,10 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma,
xe_bo_assert_held(bo);
if (!xe_vma_is_null(vma)) {
- if (xe_vma_is_userptr(vma))
+ if (vma->svm_sg)
+ xe_res_first_sg(vma->svm_sg, 0, xe_vma_size(vma),
+ &curs);
+ else if (xe_vma_is_userptr(vma))
xe_res_first_sg(vma->userptr.sg, 0, xe_vma_size(vma),
&curs);
else if (xe_bo_is_vram(bo) || xe_bo_is_stolen(bo))
@@ -1046,6 +1057,28 @@ static int xe_pt_userptr_pre_commit(struct xe_migrate_pt_update *pt_update)
return 0;
}
+static int xe_pt_svm_pre_commit(struct xe_migrate_pt_update *pt_update)
+{
+ struct xe_vma *vma = pt_update->vma;
+ struct hmm_range *range = vma->hmm_range;
+
+ if (mmu_interval_read_retry(range->notifier,
+ range->notifier_seq)) {
+ /*
+ * FIXME: is this really necessary? We didn't update GPU
+ * page table yet...
+ */
+ xe_vm_invalidate_vma(vma);
+ return -EAGAIN;
+ }
+ return 0;
+}
+
+static const struct xe_migrate_pt_update_ops svm_bind_ops = {
+ .populate = xe_vm_populate_pgtable,
+ .pre_commit = xe_pt_svm_pre_commit,
+};
+
static const struct xe_migrate_pt_update_ops bind_ops = {
.populate = xe_vm_populate_pgtable,
.pre_commit = xe_pt_pre_commit,
@@ -1197,7 +1230,8 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
struct xe_vm_pgtable_update entries[XE_VM_MAX_LEVEL * 2 + 1];
struct xe_pt_migrate_pt_update bind_pt_update = {
.base = {
- .ops = xe_vma_is_userptr(vma) ? &userptr_bind_ops : &bind_ops,
+ .ops = vma->svm_sg ? &svm_bind_ops :
+ (xe_vma_is_userptr(vma) ? &userptr_bind_ops : &bind_ops),
.vma = vma,
.tile_id = tile->id,
},
@@ -1651,3 +1685,75 @@ __xe_pt_unbind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queu
return fence;
}
+
+/**
+ * xe_bind_svm_range() - bind an address range to vm
+ *
+ * @vm: the vm to bind this address range
+ * @tile: the tile to bind this address range to
+ * @range: a hmm_range which includes all the information
+ * needed for binding: virtual address range and physical
+ * pfns to back up this virtual address range.
+ * @flags: the binding flags to set in pte
+ *
+ * This is a helper function used by svm sub-system
+ * to bind a svm range to gpu vm. svm sub-system
+ * doesn't have xe_vma, thus helpers such as
+ * __xe_pt_bind_vma can't be used directly. So this
+ * helper is written for svm sub-system to use.
+ *
+ * This is a synchronous function. When this function
+ * returns, either the svm range is bound to GPU, or
+ * error happened.
+ *
+ * Return: 0 for success or error code for failure
+ * If -EAGAIN returns, it means mmu notifier was called (
+ * aka there was concurrent cpu page table update) during
+ * this function, caller has to retry hmm_range_fault
+ */
+int xe_bind_svm_range(struct xe_vm *vm, struct xe_tile *tile,
+ struct hmm_range *range, u64 flags)
+{
+ struct dma_fence *fence = NULL;
+ struct xe_svm *svm = vm->svm;
+ int ret = 0;
+ /*
+ * Create a temp vma to reuse page table helpers such as
+ * __xe_pt_bind_vma
+ */
+ struct xe_vma vma = {
+ .gpuva = {
+ .va = {
+ .addr = range->start,
+ .range = range->end - range->start + 1,
+ },
+ .vm = &vm->gpuvm,
+ .flags = flags,
+ },
+ .tile_mask = 0x1 << tile->id,
+ .hmm_range = range,
+ };
+
+ xe_svm_build_sg(range, &vma.svm_sgt);
+ vma.svm_sg = &vma.svm_sgt;
+
+ mutex_lock(&svm->mutex);
+ if (mmu_interval_read_retry(range->notifier, range->notifier_seq)) {
+ ret = -EAGAIN;
+ goto unlock;
+ }
+ xe_vm_lock(vm, true);
+ fence = __xe_pt_bind_vma(tile, &vma, vm->q[tile->id], NULL, 0, false);
+ xe_vm_unlock(vm);
+
+unlock:
+ mutex_unlock(&svm->mutex);
+ sg_free_table(vma.svm_sg);
+
+ if (IS_ERR(fence))
+ return PTR_ERR(fence);
+
+ dma_fence_wait(fence, false);
+ dma_fence_put(fence);
+ return ret;
+}
diff --git a/drivers/gpu/drm/xe/xe_pt.h b/drivers/gpu/drm/xe/xe_pt.h
index 71a4fbfcff43..775d08707466 100644
--- a/drivers/gpu/drm/xe/xe_pt.h
+++ b/drivers/gpu/drm/xe/xe_pt.h
@@ -17,6 +17,8 @@ struct xe_sync_entry;
struct xe_tile;
struct xe_vm;
struct xe_vma;
+struct xe_svm;
+struct hmm_range;
/* Largest huge pte is currently 1GiB. May become device dependent. */
#define MAX_HUGEPTE_LEVEL 2
@@ -45,4 +47,6 @@ __xe_pt_unbind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queu
bool xe_pt_zap_ptes(struct xe_tile *tile, struct xe_vma *vma);
+int xe_bind_svm_range(struct xe_vm *vm, struct xe_tile *tile,
+ struct hmm_range *range, u64 flags);
#endif
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 037fb7168c63..68c7484b2110 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -21,6 +21,7 @@ struct xe_svm;
struct xe_bo;
struct xe_sync_entry;
struct xe_vm;
+struct hmm_range;
#define TEST_VM_ASYNC_OPS_ERROR
#define FORCE_ASYNC_OP_ERROR BIT(31)
@@ -107,9 +108,19 @@ struct xe_vma {
*/
u16 pat_index;
+ /**
+ * @svm_sgt: a scatter gather table to save svm virtual address range's
+ * pfns
+ */
+ struct sg_table svm_sgt;
+ struct sg_table *svm_sg;
+ /** hmm range of this pt update, used by svm */
+ struct hmm_range *hmm_range;
+
/**
* @userptr: user pointer state, only allocated for VMAs that are
- * user pointers
+ * user pointers. When you add new members to xe_vma struct, userptr
+ * has to be the last member, xe_vma_create assumes this.
*/
struct xe_userptr userptr;
};
--
2.26.3
next prev parent reply other threads:[~2024-01-17 22:02 UTC|newest]
Thread overview: 123+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-17 22:12 [PATCH 00/23] XeKmd basic SVM support Oak Zeng
2024-01-17 22:12 ` [PATCH 01/23] drm/xe/svm: Add SVM document Oak Zeng
2024-01-17 22:12 ` [PATCH 02/23] drm/xe/svm: Add svm key data structures Oak Zeng
2024-01-17 22:12 ` [PATCH 03/23] drm/xe/svm: create xe svm during vm creation Oak Zeng
2024-01-17 22:12 ` [PATCH 04/23] drm/xe/svm: Trace svm creation Oak Zeng
2024-01-17 22:12 ` [PATCH 05/23] drm/xe/svm: add helper to retrieve svm range from address Oak Zeng
2024-01-17 22:12 ` [PATCH 06/23] drm/xe/svm: Introduce a helper to build sg table from hmm range Oak Zeng
2024-04-05 0:39 ` Jason Gunthorpe
2024-04-05 3:33 ` Zeng, Oak
2024-04-05 12:37 ` Jason Gunthorpe
2024-04-05 16:42 ` Zeng, Oak
2024-04-05 18:02 ` Jason Gunthorpe
2024-04-09 16:45 ` Zeng, Oak
2024-04-09 17:24 ` Jason Gunthorpe
2024-04-23 21:17 ` Zeng, Oak
2024-04-24 2:31 ` Matthew Brost
2024-04-24 13:57 ` Jason Gunthorpe
2024-04-24 16:35 ` Matthew Brost
2024-04-24 16:44 ` Jason Gunthorpe
2024-04-24 16:56 ` Matthew Brost
2024-04-24 17:48 ` Jason Gunthorpe
2024-04-24 13:48 ` Jason Gunthorpe
2024-04-24 23:59 ` Zeng, Oak
2024-04-25 1:05 ` Jason Gunthorpe
2024-04-26 9:55 ` Thomas Hellström
2024-04-26 12:00 ` Jason Gunthorpe
2024-04-26 14:49 ` Thomas Hellström
2024-04-26 16:35 ` Jason Gunthorpe
2024-04-29 8:25 ` Thomas Hellström
2024-04-30 17:30 ` Jason Gunthorpe
2024-04-30 18:57 ` Daniel Vetter
2024-05-01 0:09 ` Jason Gunthorpe
2024-05-02 8:04 ` Daniel Vetter
2024-05-02 9:11 ` Thomas Hellström
2024-05-02 12:46 ` Jason Gunthorpe
2024-05-02 15:01 ` Thomas Hellström
2024-05-02 19:25 ` Zeng, Oak
2024-05-03 13:37 ` Jason Gunthorpe
2024-05-03 14:43 ` Zeng, Oak
2024-05-03 16:28 ` Jason Gunthorpe
2024-05-03 20:29 ` Zeng, Oak
2024-05-04 1:03 ` Dave Airlie
2024-05-06 13:04 ` Daniel Vetter
2024-05-06 23:50 ` Matthew Brost
2024-05-07 11:56 ` Jason Gunthorpe
2024-05-06 13:33 ` Jason Gunthorpe
2024-04-09 17:33 ` Matthew Brost
2024-01-17 22:12 ` Oak Zeng [this message]
2024-01-17 22:12 ` [PATCH 08/23] drm/xe/svm: Add helper to invalidate svm range from GPU Oak Zeng
2024-01-17 22:12 ` [PATCH 09/23] drm/xe/svm: Remap and provide memmap backing for GPU vram Oak Zeng
2024-01-17 22:12 ` [PATCH 10/23] drm/xe/svm: Introduce svm migration function Oak Zeng
2024-01-17 22:12 ` [PATCH 11/23] drm/xe/svm: implement functions to allocate and free device memory Oak Zeng
2024-01-17 22:12 ` [PATCH 12/23] drm/xe/svm: Trace buddy block allocation and free Oak Zeng
2024-01-17 22:12 ` [PATCH 13/23] drm/xe/svm: Handle CPU page fault Oak Zeng
2024-01-17 22:12 ` [PATCH 14/23] drm/xe/svm: trace svm range migration Oak Zeng
2024-01-17 22:12 ` [PATCH 15/23] drm/xe/svm: Implement functions to register and unregister mmu notifier Oak Zeng
2024-01-17 22:12 ` [PATCH 16/23] drm/xe/svm: Implement the mmu notifier range invalidate callback Oak Zeng
2024-01-17 22:12 ` [PATCH 17/23] drm/xe/svm: clean up svm range during process exit Oak Zeng
2024-01-17 22:12 ` [PATCH 18/23] drm/xe/svm: Move a few structures to xe_gt.h Oak Zeng
2024-01-17 22:12 ` [PATCH 19/23] drm/xe/svm: migrate svm range to vram Oak Zeng
2024-01-17 22:12 ` [PATCH 20/23] drm/xe/svm: Populate svm range Oak Zeng
2024-01-17 22:12 ` [PATCH 21/23] drm/xe/svm: GPU page fault support Oak Zeng
2024-01-23 2:06 ` Welty, Brian
2024-01-23 3:09 ` Zeng, Oak
2024-01-23 3:21 ` Making drm_gpuvm work across gpu devices Zeng, Oak
2024-01-23 11:13 ` Christian König
2024-01-23 19:37 ` Zeng, Oak
2024-01-23 20:17 ` Felix Kuehling
2024-01-25 1:39 ` Zeng, Oak
2024-01-23 23:56 ` Danilo Krummrich
2024-01-24 3:57 ` Zeng, Oak
2024-01-24 4:14 ` Zeng, Oak
2024-01-24 6:48 ` Christian König
2024-01-25 22:13 ` Danilo Krummrich
2024-01-24 8:33 ` Christian König
2024-01-25 1:17 ` Zeng, Oak
2024-01-25 1:25 ` David Airlie
2024-01-25 5:25 ` Zeng, Oak
2024-01-26 10:09 ` Christian König
2024-01-26 20:13 ` Zeng, Oak
2024-01-29 10:10 ` Christian König
2024-01-29 20:09 ` Zeng, Oak
2024-01-25 11:00 ` 回复:Making " 周春明(日月)
2024-01-25 17:00 ` Zeng, Oak
2024-01-25 17:15 ` Making " Felix Kuehling
2024-01-25 18:37 ` Zeng, Oak
2024-01-26 13:23 ` Christian König
2024-01-25 16:42 ` Zeng, Oak
2024-01-25 18:32 ` Daniel Vetter
2024-01-25 21:02 ` Zeng, Oak
2024-01-26 8:21 ` Thomas Hellström
2024-01-26 12:52 ` Christian König
2024-01-27 2:21 ` Zeng, Oak
2024-01-29 10:19 ` Christian König
2024-01-30 0:21 ` Zeng, Oak
2024-01-30 8:39 ` Christian König
2024-01-30 22:29 ` Zeng, Oak
2024-01-30 23:12 ` David Airlie
2024-01-31 9:15 ` Daniel Vetter
2024-01-31 20:17 ` Zeng, Oak
2024-01-31 20:59 ` Zeng, Oak
2024-02-01 8:52 ` Christian König
2024-02-29 18:22 ` Zeng, Oak
2024-03-08 4:43 ` Zeng, Oak
2024-03-08 10:07 ` Christian König
2024-01-30 8:43 ` Thomas Hellström
2024-01-29 15:03 ` Felix Kuehling
2024-01-29 15:33 ` Christian König
2024-01-29 16:24 ` Felix Kuehling
2024-01-29 16:28 ` Christian König
2024-01-29 17:52 ` Felix Kuehling
2024-01-29 19:03 ` Christian König
2024-01-29 20:24 ` Felix Kuehling
2024-02-23 20:12 ` Zeng, Oak
2024-02-27 6:54 ` Christian König
2024-02-27 15:58 ` Zeng, Oak
2024-02-28 19:51 ` Zeng, Oak
2024-02-29 9:41 ` Christian König
2024-02-29 16:05 ` Zeng, Oak
2024-02-29 17:12 ` Thomas Hellström
2024-03-01 7:01 ` Christian König
2024-01-17 22:12 ` [PATCH 22/23] drm/xe/svm: Add DRM_XE_SVM kernel config entry Oak Zeng
2024-01-17 22:12 ` [PATCH 23/23] drm/xe/svm: Add svm memory hints interface Oak Zeng
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240117221223.18540-8-oak.zeng@intel.com \
--to=oak.zeng@intel.com \
--cc=Thomas.Hellstrom@linux.intel.com \
--cc=brian.welty@intel.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=himal.prasad.ghimiray@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=krishnaiah.bommu@intel.com \
--cc=matthew.brost@intel.com \
--cc=niranjana.vishwanathapura@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).