Hi Jérôme, Ben, Felix and Jason,
below is a series against the hmm tree which cleans up various minor
bits and allows HMM_MIRROR to be built on all architectures.
Diffstat:
11 files changed, 94 insertions(+), 210 deletions(-)
A git tree is also available at:
git://git.infradead.org/users/hch/misc.git hmm-cleanups.2
Gitweb:
http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/hmm-cleanups.2
Changes since v1:
- fix the cover letter subject
- improve various patch descriptions
- use svmm->mm in nouveau_range_fault
- inverse the hmask field when using it
- select HMM_MIRROR instead of making it a user visible option
We'll need the nouveau_svmm structure to improve the function soon.
For now this allows using the svmm->mm reference to unlock the
mmap_sem, and thus the same dereference chain that the caller uses
to lock and unlock it.
Signed-off-by: Christoph Hellwig <[email protected]>
---
drivers/gpu/drm/nouveau/nouveau_svm.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index a74530b5a523..98072fd48cf7 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -485,23 +485,23 @@ nouveau_range_done(struct hmm_range *range)
}
static int
-nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range)
+nouveau_range_fault(struct nouveau_svmm *svmm, struct hmm_range *range)
{
long ret;
range->default_flags = 0;
range->pfn_flags_mask = -1UL;
- ret = hmm_range_register(range, mirror,
+ ret = hmm_range_register(range, &svmm->mirror,
range->start, range->end,
PAGE_SHIFT);
if (ret) {
- up_read(&range->hmm->mm->mmap_sem);
+ up_read(&svmm->mm->mmap_sem);
return (int)ret;
}
if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) {
- up_read(&range->hmm->mm->mmap_sem);
+ up_read(&svmm->mm->mmap_sem);
return -EBUSY;
}
@@ -509,7 +509,7 @@ nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range)
if (ret <= 0) {
if (ret == 0)
ret = -EBUSY;
- up_read(&range->hmm->mm->mmap_sem);
+ up_read(&svmm->mm->mmap_sem);
hmm_range_unregister(range);
return ret;
}
@@ -689,7 +689,7 @@ nouveau_svm_fault(struct nvif_notify *notify)
range.values = nouveau_svm_pfn_values;
range.pfn_shift = NVIF_VMM_PFNMAP_V0_ADDR_SHIFT;
again:
- ret = nouveau_range_fault(&svmm->mirror, &range);
+ ret = nouveau_range_fault(svmm, &range);
if (ret == 0) {
mutex_lock(&svmm->mutex);
if (!nouveau_range_done(&range)) {
--
2.20.1
All users pass PAGE_SIZE here, and if we wanted to support single
entries for huge pages we should really just add a HMM_FAULT_HUGEPAGE
flag instead that uses the huge page size instead of having the
caller calculate that size once, just for the hmm code to verify it.
Signed-off-by: Christoph Hellwig <[email protected]>
Acked-by: Felix Kuehling <[email protected]>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 1 -
drivers/gpu/drm/nouveau/nouveau_svm.c | 1 -
include/linux/hmm.h | 22 -------------
mm/hmm.c | 42 ++++++-------------------
4 files changed, 9 insertions(+), 57 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 71d6e7087b0b..8bf79288c4e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -818,7 +818,6 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
0 : range->flags[HMM_PFN_WRITE];
range->pfn_flags_mask = 0;
range->pfns = pfns;
- range->page_shift = PAGE_SHIFT;
range->start = start;
range->end = start + ttm->num_pages * PAGE_SIZE;
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index 41fad4719ac6..668d4bd0c118 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -680,7 +680,6 @@ nouveau_svm_fault(struct nvif_notify *notify)
args.i.p.addr + args.i.p.size, fn - fi);
/* Have HMM fault pages within the fault window to the GPU. */
- range.page_shift = PAGE_SHIFT;
range.start = args.i.p.addr;
range.end = args.i.p.addr + args.i.p.size;
range.pfns = args.phys;
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index c5b51376b453..51e18fbb8953 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -158,7 +158,6 @@ enum hmm_pfn_value_e {
* @values: pfn value for some special case (none, special, error, ...)
* @default_flags: default flags for the range (write, read, ... see hmm doc)
* @pfn_flags_mask: allows to mask pfn flags so that only default_flags matter
- * @page_shift: device virtual address shift value (should be >= PAGE_SHIFT)
* @pfn_shifts: pfn shift value (should be <= PAGE_SHIFT)
* @valid: pfns array did not change since it has been fill by an HMM function
*/
@@ -172,31 +171,10 @@ struct hmm_range {
const uint64_t *values;
uint64_t default_flags;
uint64_t pfn_flags_mask;
- uint8_t page_shift;
uint8_t pfn_shift;
bool valid;
};
-/*
- * hmm_range_page_shift() - return the page shift for the range
- * @range: range being queried
- * Return: page shift (page size = 1 << page shift) for the range
- */
-static inline unsigned hmm_range_page_shift(const struct hmm_range *range)
-{
- return range->page_shift;
-}
-
-/*
- * hmm_range_page_size() - return the page size for the range
- * @range: range being queried
- * Return: page size for the range in bytes
- */
-static inline unsigned long hmm_range_page_size(const struct hmm_range *range)
-{
- return 1UL << hmm_range_page_shift(range);
-}
-
/*
* hmm_range_wait_until_valid() - wait for range to be valid
* @range: range affected by invalidation to wait on
diff --git a/mm/hmm.c b/mm/hmm.c
index 926735a3aef9..f26d6abc4ed2 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -344,13 +344,12 @@ static int hmm_vma_walk_hole_(unsigned long addr, unsigned long end,
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
uint64_t *pfns = range->pfns;
- unsigned long i, page_size;
+ unsigned long i;
hmm_vma_walk->last = addr;
- page_size = hmm_range_page_size(range);
- i = (addr - range->start) >> range->page_shift;
+ i = (addr - range->start) >> PAGE_SHIFT;
- for (; addr < end; addr += page_size, i++) {
+ for (; addr < end; addr += PAGE_SIZE, i++) {
pfns[i] = range->values[HMM_PFN_NONE];
if (fault || write_fault) {
int ret;
@@ -772,7 +771,7 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
struct mm_walk *walk)
{
#ifdef CONFIG_HUGETLB_PAGE
- unsigned long addr = start, i, pfn, mask, size, pfn_inc;
+ unsigned long addr = start, i, pfn, mask;
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
struct vm_area_struct *vma = walk->vma;
@@ -783,24 +782,12 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
pte_t entry;
int ret = 0;
- size = huge_page_size(h);
- mask = size - 1;
- if (range->page_shift != PAGE_SHIFT) {
- /* Make sure we are looking at a full page. */
- if (start & mask)
- return -EINVAL;
- if (end < (start + size))
- return -EINVAL;
- pfn_inc = size >> PAGE_SHIFT;
- } else {
- pfn_inc = 1;
- size = PAGE_SIZE;
- }
+ mask = huge_page_size(h) - 1;
ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte);
entry = huge_ptep_get(pte);
- i = (start - range->start) >> range->page_shift;
+ i = (start - range->start) >> PAGE_SHIFT;
orig_pfn = range->pfns[i];
range->pfns[i] = range->values[HMM_PFN_NONE];
cpu_flags = pte_to_hmm_pfn_flags(range, entry);
@@ -812,8 +799,8 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
goto unlock;
}
- pfn = pte_pfn(entry) + ((start & mask) >> range->page_shift);
- for (; addr < end; addr += size, i++, pfn += pfn_inc)
+ pfn = pte_pfn(entry) + ((start & mask) >> PAGE_SHIFT);
+ for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
range->pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
cpu_flags;
hmm_vma_walk->last = end;
@@ -850,14 +837,13 @@ static void hmm_pfns_clear(struct hmm_range *range,
*/
int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror)
{
- unsigned long mask = ((1UL << range->page_shift) - 1UL);
struct hmm *hmm = mirror->hmm;
unsigned long flags;
range->valid = false;
range->hmm = NULL;
- if ((range->start & mask) || (range->end & mask))
+ if ((range->start & (PAGE_SIZE - 1)) || (range->end & (PAGE_SIZE - 1)))
return -EINVAL;
if (range->start >= range->end)
return -EINVAL;
@@ -964,16 +950,6 @@ long hmm_range_fault(struct hmm_range *range, unsigned int flags)
if (vma == NULL || (vma->vm_flags & device_vma))
return -EFAULT;
- if (is_vm_hugetlb_page(vma)) {
- if (huge_page_shift(hstate_vma(vma)) !=
- range->page_shift &&
- range->page_shift != PAGE_SHIFT)
- return -EINVAL;
- } else {
- if (range->page_shift != PAGE_SHIFT)
- return -EINVAL;
- }
-
if (!(vma->vm_flags & VM_READ)) {
/*
* If vma do not allow read access, then assume that it
--
2.20.1
On Tue, Aug 06, 2019 at 07:05:41PM +0300, Christoph Hellwig wrote:
> We'll need the nouveau_svmm structure to improve the function soon.
> For now this allows using the svmm->mm reference to unlock the
> mmap_sem, and thus the same dereference chain that the caller uses
> to lock and unlock it.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> ---
> drivers/gpu/drm/nouveau/nouveau_svm.c | 12 ++++++------
> 1 file changed, 6 insertions(+), 6 deletions(-)
Reviewed-by: Jason Gunthorpe <[email protected]>
Jason
On Tue, Aug 06, 2019 at 07:05:38PM +0300, Christoph Hellwig wrote:
>
> Hi Jérôme, Ben, Felix and Jason,
>
> below is a series against the hmm tree which cleans up various minor
> bits and allows HMM_MIRROR to be built on all architectures.
>
> Diffstat:
>
> 11 files changed, 94 insertions(+), 210 deletions(-)
>
> A git tree is also available at:
>
> git://git.infradead.org/users/hch/misc.git hmm-cleanups.2
>
> Gitweb:
>
> http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/hmm-cleanups.2
>
> Changes since v1:
> - fix the cover letter subject
> - improve various patch descriptions
> - use svmm->mm in nouveau_range_fault
> - inverse the hmask field when using it
> - select HMM_MIRROR instead of making it a user visible option
I think it is straightforward enough to move into -next, so applied to
the hmm.git lets get some more reviewed-bys/tested-by though.
For now I dropped 'remove the pgmap field from struct hmm_vma_walk'
just to hear the followup and 'amdgpu: remove
CONFIG_DRM_AMDGPU_USERPTR' until the AMD team Acks
Thanks,
Jason
On Tue, Aug 06, 2019 at 07:05:45PM +0300, Christoph Hellwig wrote:
> All users pass PAGE_SIZE here, and if we wanted to support single
> entries for huge pages we should really just add a HMM_FAULT_HUGEPAGE
> flag instead that uses the huge page size instead of having the
> caller calculate that size once, just for the hmm code to verify it.
>
> Signed-off-by: Christoph Hellwig <[email protected]>
> Acked-by: Felix Kuehling <[email protected]>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 1 -
> drivers/gpu/drm/nouveau/nouveau_svm.c | 1 -
> include/linux/hmm.h | 22 -------------
> mm/hmm.c | 42 ++++++-------------------
> 4 files changed, 9 insertions(+), 57 deletions(-)
Having looked at ODP more closley this doesn't seem to match what it
needs anyhow. It can keep using its checking algorithm
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> index 71d6e7087b0b..8bf79288c4e2 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
> @@ -818,7 +818,6 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
> 0 : range->flags[HMM_PFN_WRITE];
> range->pfn_flags_mask = 0;
> range->pfns = pfns;
> - range->page_shift = PAGE_SHIFT;
> range->start = start;
> range->end = start + ttm->num_pages * PAGE_SIZE;
>
> diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
> index 41fad4719ac6..668d4bd0c118 100644
> --- a/drivers/gpu/drm/nouveau/nouveau_svm.c
> +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
> @@ -680,7 +680,6 @@ nouveau_svm_fault(struct nvif_notify *notify)
> args.i.p.addr + args.i.p.size, fn - fi);
>
> /* Have HMM fault pages within the fault window to the GPU. */
> - range.page_shift = PAGE_SHIFT;
> range.start = args.i.p.addr;
> range.end = args.i.p.addr + args.i.p.size;
> range.pfns = args.phys;
> diff --git a/include/linux/hmm.h b/include/linux/hmm.h
> index c5b51376b453..51e18fbb8953 100644
> --- a/include/linux/hmm.h
> +++ b/include/linux/hmm.h
> @@ -158,7 +158,6 @@ enum hmm_pfn_value_e {
> * @values: pfn value for some special case (none, special, error, ...)
> * @default_flags: default flags for the range (write, read, ... see hmm doc)
> * @pfn_flags_mask: allows to mask pfn flags so that only default_flags matter
> - * @page_shift: device virtual address shift value (should be >= PAGE_SHIFT)
> * @pfn_shifts: pfn shift value (should be <= PAGE_SHIFT)
> * @valid: pfns array did not change since it has been fill by an HMM function
> */
> @@ -172,31 +171,10 @@ struct hmm_range {
> const uint64_t *values;
> uint64_t default_flags;
> uint64_t pfn_flags_mask;
> - uint8_t page_shift;
> uint8_t pfn_shift;
> bool valid;
> };
>
> -/*
> - * hmm_range_page_shift() - return the page shift for the range
> - * @range: range being queried
> - * Return: page shift (page size = 1 << page shift) for the range
> - */
> -static inline unsigned hmm_range_page_shift(const struct hmm_range *range)
> -{
> - return range->page_shift;
> -}
> -
> -/*
> - * hmm_range_page_size() - return the page size for the range
> - * @range: range being queried
> - * Return: page size for the range in bytes
> - */
> -static inline unsigned long hmm_range_page_size(const struct hmm_range *range)
> -{
> - return 1UL << hmm_range_page_shift(range);
> -}
> -
> /*
> * hmm_range_wait_until_valid() - wait for range to be valid
> * @range: range affected by invalidation to wait on
> diff --git a/mm/hmm.c b/mm/hmm.c
> index 926735a3aef9..f26d6abc4ed2 100644
> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -344,13 +344,12 @@ static int hmm_vma_walk_hole_(unsigned long addr, unsigned long end,
> struct hmm_vma_walk *hmm_vma_walk = walk->private;
> struct hmm_range *range = hmm_vma_walk->range;
> uint64_t *pfns = range->pfns;
> - unsigned long i, page_size;
> + unsigned long i;
>
> hmm_vma_walk->last = addr;
> - page_size = hmm_range_page_size(range);
> - i = (addr - range->start) >> range->page_shift;
> + i = (addr - range->start) >> PAGE_SHIFT;
>
> - for (; addr < end; addr += page_size, i++) {
> + for (; addr < end; addr += PAGE_SIZE, i++) {
> pfns[i] = range->values[HMM_PFN_NONE];
> if (fault || write_fault) {
> int ret;
> @@ -772,7 +771,7 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
> struct mm_walk *walk)
> {
> #ifdef CONFIG_HUGETLB_PAGE
> - unsigned long addr = start, i, pfn, mask, size, pfn_inc;
> + unsigned long addr = start, i, pfn, mask;
> struct hmm_vma_walk *hmm_vma_walk = walk->private;
> struct hmm_range *range = hmm_vma_walk->range;
> struct vm_area_struct *vma = walk->vma;
> @@ -783,24 +782,12 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
> pte_t entry;
> int ret = 0;
>
> - size = huge_page_size(h);
> - mask = size - 1;
> - if (range->page_shift != PAGE_SHIFT) {
> - /* Make sure we are looking at a full page. */
> - if (start & mask)
> - return -EINVAL;
> - if (end < (start + size))
> - return -EINVAL;
> - pfn_inc = size >> PAGE_SHIFT;
> - } else {
> - pfn_inc = 1;
> - size = PAGE_SIZE;
> - }
> + mask = huge_page_size(h) - 1;
>
> ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte);
> entry = huge_ptep_get(pte);
>
> - i = (start - range->start) >> range->page_shift;
> + i = (start - range->start) >> PAGE_SHIFT;
> orig_pfn = range->pfns[i];
> range->pfns[i] = range->values[HMM_PFN_NONE];
> cpu_flags = pte_to_hmm_pfn_flags(range, entry);
> @@ -812,8 +799,8 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
> goto unlock;
> }
>
> - pfn = pte_pfn(entry) + ((start & mask) >> range->page_shift);
> - for (; addr < end; addr += size, i++, pfn += pfn_inc)
> + pfn = pte_pfn(entry) + ((start & mask) >> PAGE_SHIFT);
> + for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
> range->pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
> cpu_flags;
> hmm_vma_walk->last = end;
> @@ -850,14 +837,13 @@ static void hmm_pfns_clear(struct hmm_range *range,
> */
> int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror)
> {
> - unsigned long mask = ((1UL << range->page_shift) - 1UL);
> struct hmm *hmm = mirror->hmm;
> unsigned long flags;
>
> range->valid = false;
> range->hmm = NULL;
>
> - if ((range->start & mask) || (range->end & mask))
> + if ((range->start & (PAGE_SIZE - 1)) || (range->end & (PAGE_SIZE - 1)))
> return -EINVAL;
PAGE_SIZE-1 == PAGE_MASK ? If yes I can fix it
Reviewed-by: Jason Gunthorpe <[email protected]>
Jason