The patch titled
Subject: nouveau/svm: implement atomic SVM access
has been removed from the -mm tree. Its filename was
nouveau-svm-implement-atomic-svm-access.patch
This patch was dropped because an updated version will be merged
------------------------------------------------------
From: Alistair Popple <apopple@xxxxxxxxxx>
Subject: nouveau/svm: implement atomic SVM access
Some NVIDIA GPUs do not support direct atomic access to system memory via
PCIe. Instead this must be emulated by granting the GPU exclusive access
to the memory. This is achieved by replacing CPU page table entries with
special swap entries that fault on userspace access.
The driver then grants the GPU permission to update the page undergoing
atomic access via the GPU page tables. When CPU access to the page is
required a CPU fault is raised which calls into the device driver via MMU
notifiers to revoke the atomic access. The original page table entries
are then restored allowing CPU access to proceed.
Link: https://lkml.kernel.org/r/20210524132725.12697-11-apopple@xxxxxxxxxx
Signed-off-by: Alistair Popple <apopple@xxxxxxxxxx>
Reviewed-by: Ben Skeggs <bskeggs@xxxxxxxxxx>
Cc: Balbir Singh <bsingharora@xxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxxxx>
Cc: Jerome Glisse <jglisse@xxxxxxxxxx>
Cc: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Ralph Campbell <rcampbell@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/nouveau/include/nvif/if000c.h | 1
drivers/gpu/drm/nouveau/nouveau_svm.c | 126 ++++++++++-
drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h | 1
drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c | 6
4 files changed, 123 insertions(+), 11 deletions(-)
--- a/drivers/gpu/drm/nouveau/include/nvif/if000c.h~nouveau-svm-implement-atomic-svm-access
+++ a/drivers/gpu/drm/nouveau/include/nvif/if000c.h
@@ -77,6 +77,7 @@ struct nvif_vmm_pfnmap_v0 {
#define NVIF_VMM_PFNMAP_V0_APER 0x00000000000000f0ULL
#define NVIF_VMM_PFNMAP_V0_HOST 0x0000000000000000ULL
#define NVIF_VMM_PFNMAP_V0_VRAM 0x0000000000000010ULL
+#define NVIF_VMM_PFNMAP_V0_A 0x0000000000000004ULL
#define NVIF_VMM_PFNMAP_V0_W 0x0000000000000002ULL
#define NVIF_VMM_PFNMAP_V0_V 0x0000000000000001ULL
#define NVIF_VMM_PFNMAP_V0_NONE 0x0000000000000000ULL
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c~nouveau-svm-implement-atomic-svm-access
+++ a/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -35,6 +35,7 @@
#include <linux/sched/mm.h>
#include <linux/sort.h>
#include <linux/hmm.h>
+#include <linux/rmap.h>
struct nouveau_svm {
struct nouveau_drm *drm;
@@ -67,6 +68,11 @@ struct nouveau_svm {
} buffer[1];
};
+#define FAULT_ACCESS_READ 0
+#define FAULT_ACCESS_WRITE 1
+#define FAULT_ACCESS_ATOMIC 2
+#define FAULT_ACCESS_PREFETCH 3
+
#define SVM_DBG(s,f,a...) NV_DEBUG((s)->drm, "svm: "f"\n", ##a)
#define SVM_ERR(s,f,a...) NV_WARN((s)->drm, "svm: "f"\n", ##a)
@@ -412,6 +418,24 @@ nouveau_svm_fault_cancel_fault(struct no
}
static int
+nouveau_svm_fault_priority(u8 fault)
+{
+ switch (fault) {
+ case FAULT_ACCESS_PREFETCH:
+ return 0;
+ case FAULT_ACCESS_READ:
+ return 1;
+ case FAULT_ACCESS_WRITE:
+ return 2;
+ case FAULT_ACCESS_ATOMIC:
+ return 3;
+ default:
+ WARN_ON_ONCE(1);
+ return -1;
+ }
+}
+
+static int
nouveau_svm_fault_cmp(const void *a, const void *b)
{
const struct nouveau_svm_fault *fa = *(struct nouveau_svm_fault **)a;
@@ -421,9 +445,8 @@ nouveau_svm_fault_cmp(const void *a, con
return ret;
if ((ret = (s64)fa->addr - fb->addr))
return ret;
- /*XXX: atomic? */
- return (fa->access == 0 || fa->access == 3) -
- (fb->access == 0 || fb->access == 3);
+ return nouveau_svm_fault_priority(fa->access) -
+ nouveau_svm_fault_priority(fb->access);
}
static void
@@ -487,6 +510,10 @@ static bool nouveau_svm_range_invalidate
struct svm_notifier *sn =
container_of(mni, struct svm_notifier, notifier);
+ if (range->event == MMU_NOTIFY_EXCLUSIVE &&
+ range->owner == sn->svmm->vmm->cli->drm->dev)
+ return true;
+
/*
* serializes the update to mni->invalidate_seq done by caller and
* prevents invalidation of the PTE from progressing while HW is being
@@ -555,6 +582,71 @@ static void nouveau_hmm_convert_pfn(stru
args->p.phys[0] |= NVIF_VMM_PFNMAP_V0_W;
}
+static int nouveau_atomic_range_fault(struct nouveau_svmm *svmm,
+ struct nouveau_drm *drm,
+ struct nouveau_pfnmap_args *args, u32 size,
+ struct svm_notifier *notifier)
+{
+ unsigned long timeout =
+ jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
+ struct mm_struct *mm = svmm->notifier.mm;
+ struct page *page;
+ unsigned long start = args->p.addr;
+ unsigned long notifier_seq;
+ int ret = 0;
+
+ ret = mmu_interval_notifier_insert(¬ifier->notifier, mm,
+ args->p.addr, args->p.size,
+ &nouveau_svm_mni_ops);
+ if (ret)
+ return ret;
+
+ while (true) {
+ if (time_after(jiffies, timeout)) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ notifier_seq = mmu_interval_read_begin(¬ifier->notifier);
+ mmap_read_lock(mm);
+ make_device_exclusive_range(mm, start, start + PAGE_SIZE,
+ &page, drm->dev);
+ mmap_read_unlock(mm);
+ if (!page) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ mutex_lock(&svmm->mutex);
+ if (!mmu_interval_read_retry(¬ifier->notifier,
+ notifier_seq))
+ break;
+ mutex_unlock(&svmm->mutex);
+ }
+
+ /* Map the page on the GPU. */
+ args->p.page = 12;
+ args->p.size = PAGE_SIZE;
+ args->p.addr = start;
+ args->p.phys[0] = page_to_phys(page) |
+ NVIF_VMM_PFNMAP_V0_V |
+ NVIF_VMM_PFNMAP_V0_W |
+ NVIF_VMM_PFNMAP_V0_A |
+ NVIF_VMM_PFNMAP_V0_HOST;
+
+ svmm->vmm->vmm.object.client->super = true;
+ ret = nvif_object_ioctl(&svmm->vmm->vmm.object, args, size, NULL);
+ svmm->vmm->vmm.object.client->super = false;
+ mutex_unlock(&svmm->mutex);
+
+ unlock_page(page);
+ put_page(page);
+
+out:
+ mmu_interval_notifier_remove(¬ifier->notifier);
+ return ret;
+}
+
static int nouveau_range_fault(struct nouveau_svmm *svmm,
struct nouveau_drm *drm,
struct nouveau_pfnmap_args *args, u32 size,
@@ -637,7 +729,7 @@ nouveau_svm_fault(struct nvif_notify *no
unsigned long hmm_flags;
u64 inst, start, limit;
int fi, fn;
- int replay = 0, ret;
+ int replay = 0, atomic = 0, ret;
/* Parse available fault buffer entries into a cache, and update
* the GET pointer so HW can reuse the entries.
@@ -718,12 +810,14 @@ nouveau_svm_fault(struct nvif_notify *no
/*
* Determine required permissions based on GPU fault
* access flags.
- * XXX: atomic?
*/
switch (buffer->fault[fi]->access) {
case 0: /* READ. */
hmm_flags = HMM_PFN_REQ_FAULT;
break;
+ case 2: /* ATOMIC. */
+ atomic = true;
+ break;
case 3: /* PREFETCH. */
hmm_flags = 0;
break;
@@ -739,8 +833,14 @@ nouveau_svm_fault(struct nvif_notify *no
}
notifier.svmm = svmm;
- ret = nouveau_range_fault(svmm, svm->drm, &args.i,
- sizeof(args), hmm_flags, ¬ifier);
+ if (atomic)
+ ret = nouveau_atomic_range_fault(svmm, svm->drm,
+ &args.i, sizeof(args),
+ ¬ifier);
+ else
+ ret = nouveau_range_fault(svmm, svm->drm, &args.i,
+ sizeof(args), hmm_flags,
+ ¬ifier);
mmput(mm);
limit = args.i.p.addr + args.i.p.size;
@@ -756,11 +856,15 @@ nouveau_svm_fault(struct nvif_notify *no
*/
if (buffer->fault[fn]->svmm != svmm ||
buffer->fault[fn]->addr >= limit ||
- (buffer->fault[fi]->access == 0 /* READ. */ &&
+ (buffer->fault[fi]->access == FAULT_ACCESS_READ &&
!(args.phys[0] & NVIF_VMM_PFNMAP_V0_V)) ||
- (buffer->fault[fi]->access != 0 /* READ. */ &&
- buffer->fault[fi]->access != 3 /* PREFETCH. */ &&
- !(args.phys[0] & NVIF_VMM_PFNMAP_V0_W)))
+ (buffer->fault[fi]->access != FAULT_ACCESS_READ &&
+ buffer->fault[fi]->access != FAULT_ACCESS_PREFETCH &&
+ !(args.phys[0] & NVIF_VMM_PFNMAP_V0_W)) ||
+ (buffer->fault[fi]->access != FAULT_ACCESS_READ &&
+ buffer->fault[fi]->access != FAULT_ACCESS_WRITE &&
+ buffer->fault[fi]->access != FAULT_ACCESS_PREFETCH &&
+ !(args.phys[0] & NVIF_VMM_PFNMAP_V0_A)))
break;
}
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c~nouveau-svm-implement-atomic-svm-access
+++ a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c
@@ -88,6 +88,9 @@ gp100_vmm_pgt_pfn(struct nvkm_vmm *vmm,
if (!(*map->pfn & NVKM_VMM_PFN_W))
data |= BIT_ULL(6); /* RO. */
+ if (!(*map->pfn & NVKM_VMM_PFN_A))
+ data |= BIT_ULL(7); /* Atomic disable. */
+
if (!(*map->pfn & NVKM_VMM_PFN_VRAM)) {
addr = *map->pfn >> NVKM_VMM_PFN_ADDR_SHIFT;
addr = dma_map_page(dev, pfn_to_page(addr), 0,
@@ -322,6 +325,9 @@ gp100_vmm_pd0_pfn(struct nvkm_vmm *vmm,
if (!(*map->pfn & NVKM_VMM_PFN_W))
data |= BIT_ULL(6); /* RO. */
+ if (!(*map->pfn & NVKM_VMM_PFN_A))
+ data |= BIT_ULL(7); /* Atomic disable. */
+
if (!(*map->pfn & NVKM_VMM_PFN_VRAM)) {
addr = *map->pfn >> NVKM_VMM_PFN_ADDR_SHIFT;
addr = dma_map_page(dev, pfn_to_page(addr), 0,
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h~nouveau-svm-implement-atomic-svm-access
+++ a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h
@@ -178,6 +178,7 @@ void nvkm_vmm_unmap_region(struct nvkm_v
#define NVKM_VMM_PFN_APER 0x00000000000000f0ULL
#define NVKM_VMM_PFN_HOST 0x0000000000000000ULL
#define NVKM_VMM_PFN_VRAM 0x0000000000000010ULL
+#define NVKM_VMM_PFN_A 0x0000000000000004ULL
#define NVKM_VMM_PFN_W 0x0000000000000002ULL
#define NVKM_VMM_PFN_V 0x0000000000000001ULL
#define NVKM_VMM_PFN_NONE 0x0000000000000000ULL
_
Patches currently in -mm which might be from apopple@xxxxxxxxxx are
