leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

hmm related patches for 5.8

Browse Source 
This series adds a selftest for hmm_range_fault() and several of the
 DEVICE_PRIVATE migration related actions, and another simplification for
 hmm_range_fault()'s API.
 
 - Simplify hmm_range_fault() with a simpler return code, no
   HMM_PFN_SPECIAL, and no customizable output PFN format
 
 - Add a selftest for hmm_range_fault() and DEVICE_PRIVATE related
   functionality
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEfB7FMLh+8QxL+6i3OG33FX4gmxoFAl7VQr8ACgkQOG33FX4g
 mxrpcg/+O+oZ2p8FDTZi/0BTaU0crUiKwJngmmv78UuvD8nzhOZ0fkhK2lsXn9Uo
 70lYbfDUSX2TbReP7y39VArW0v+Bj7wo9/7AZ+R2o5A0ajC6kccjGdnb7uEc3L6v
 CR+uumRYf/ZNz13cbuRBbYEz477DGnz+3vhBb4FLNTFj9XiNAC61jA1WUI0ep6x3
 lDrkhDatqmdBJ+EqZDMq2+UH+lWbkptQT7hPqgEp6o7FqdnySxRd+rT3hALz5wNP
 fbryfWXM7V1eh7Kxr2mBJJqIkgbdhGLj2yLl1Iz11BbG6u7AT20r23WTvJ7hUCyt
 18574twdltZ81gheqqN7KVYYAo+5seMfP14QdthqzzBMo3pOeLG0JMVqQNisDPgn
 Tf4lWF/GR7ajKxyRbLdvUgRE7pFQ9VMAiP86GoIpBFmSZQQDwcecnoYxg60zsTwR
 yuf60gopfNsSWNmDqKT3td12PQyFQYHYT6ue1eW6Rb9P+yA++tZaGkvGFn7kHeNV
 ZeUqsKEy6a9l6cDrFzNmsCcdNZg/qmw9mKFfa/4RRulU5jlskt/e52NiLaLU2rsr
 0Tot3j5tMufLLorZPprMI3Z/M9ohVAS5DkX6ttcZDs5v0iGQEUOOnq0cXmwlJQ9I
 0CHr2ImjiDr9v2fS+5ixaRNSHfnQWnHxcqq79UZiTjtPW1Daauo=
 =twev
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull hmm updates from Jason Gunthorpe:
 "This series adds a selftest for hmm_range_fault() and several of the
  DEVICE_PRIVATE migration related actions, and another simplification
  for hmm_range_fault()'s API.

   - Simplify hmm_range_fault() with a simpler return code, no
     HMM_PFN_SPECIAL, and no customizable output PFN format

   - Add a selftest for hmm_range_fault() and DEVICE_PRIVATE related
     functionality"

* tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  MAINTAINERS: add HMM selftests
  mm/hmm/test: add selftests for HMM
  mm/hmm/test: add selftest driver for HMM
  mm/hmm: remove the customizable pfn format from hmm_range_fault
  mm/hmm: remove HMM_PFN_SPECIAL
  drm/amdgpu: remove dead code after hmm_range_fault()
  mm/hmm: make hmm_range_fault return 0 or -1
This commit is contained in:
Linus Torvalds 2020-06-02 14:05:27 -07:00
commit cfa3b8068b
18 changed files with 2934 additions and 289 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
Documentation/vm/hmm.rst
View File

@ -161,7 +161,7 @@ device must complete the update before the driver callback returns.
When the device driver wants to populate a range of virtual addresses, it can
use::
long hmm_range_fault(struct hmm_range *range);
int hmm_range_fault(struct hmm_range *range);
It will trigger a page fault on missing or read-only entries if write access is
requested (see below). Page faults use the generic mm page fault code path just
@ -184,10 +184,7 @@ The usage pattern is::
range.notifier = &interval_sub;
range.start = ...;
range.end = ...;
range.pfns = ...;
range.flags = ...;
range.values = ...;
range.pfn_shift = ...;
range.hmm_pfns = ...;
if (!mmget_not_zero(interval_sub->notifier.mm))
return -EFAULT;
@ -229,15 +226,10 @@ The hmm_range struct has 2 fields, default_flags and pfn_flags_mask, that specif
fault or snapshot policy for the whole range instead of having to set them
for each entry in the pfns array.
For instance, if the device flags for range.flags are::
For instance if the device driver wants pages for a range with at least read
permission, it sets::
range.flags[HMM_PFN_VALID] = (1 << 63);
range.flags[HMM_PFN_WRITE] = (1 << 62);
and the device driver wants pages for a range with at least read permission,
it sets::
range->default_flags = (1 << 63);
range->default_flags = HMM_PFN_REQ_FAULT;
range->pfn_flags_mask = 0;
and calls hmm_range_fault() as described above. This will fill fault all pages
@ -246,18 +238,18 @@ in the range with at least read permission.
Now let's say the driver wants to do the same except for one page in the range for
which it wants to have write permission. Now driver set::
range->default_flags = (1 << 63);
range->pfn_flags_mask = (1 << 62);
range->pfns[index_of_write] = (1 << 62);
range->default_flags = HMM_PFN_REQ_FAULT;
range->pfn_flags_mask = HMM_PFN_REQ_WRITE;
range->pfns[index_of_write] = HMM_PFN_REQ_WRITE;
With this, HMM will fault in all pages with at least read (i.e., valid) and for the
address == range->start + (index_of_write << PAGE_SHIFT) it will fault with
write permission i.e., if the CPU pte does not have write permission set then HMM
will call handle_mm_fault().
Note that HMM will populate the pfns array with write permission for any page
that is mapped with CPU write permission no matter what values are set
in default_flags or pfn_flags_mask.
After hmm_range_fault completes the flag bits are set to the current state of
the page tables, ie HMM_PFN_VALID | HMM_PFN_WRITE will be set if the page is
writable.
Represent and manage device memory from core kernel point of view

2
MAINTAINERS
View File

@ -7768,7 +7768,9 @@ L: linux-mm@kvack.org
S: Maintained
F: Documentation/vm/hmm.rst
F: include/linux/hmm*
F: lib/test_hmm*
F: mm/hmm*
F: tools/testing/selftests/vm/*hmm*
HOST AP DRIVER
M: Jouni Malinen <j@w1.fi>

56
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
View File

@ -766,18 +766,6 @@ struct amdgpu_ttm_tt {
};
#ifdef CONFIG_DRM_AMDGPU_USERPTR
/* flags used by HMM internal, not related to CPU/GPU PTE flags */
static const uint64_t hmm_range_flags[HMM_PFN_FLAG_MAX] = {
(1 << 0), /* HMM_PFN_VALID */
(1 << 1), /* HMM_PFN_WRITE */
};
static const uint64_t hmm_range_values[HMM_PFN_VALUE_MAX] = {
0xfffffffffffffffeUL, /* HMM_PFN_ERROR */
0, /* HMM_PFN_NONE */
0xfffffffffffffffcUL /* HMM_PFN_SPECIAL */
};
/**
* amdgpu_ttm_tt_get_user_pages - get device accessible pages that back user
* memory and start HMM tracking CPU page table update
@ -816,18 +804,15 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
goto out;
}
range->notifier = &bo->notifier;
range->flags = hmm_range_flags;
range->values = hmm_range_values;
range->pfn_shift = PAGE_SHIFT;
range->start = bo->notifier.interval_tree.start;
range->end = bo->notifier.interval_tree.last + 1;
range->default_flags = hmm_range_flags[HMM_PFN_VALID];
range->default_flags = HMM_PFN_REQ_FAULT;
if (!amdgpu_ttm_tt_is_readonly(ttm))
range->default_flags |= range->flags[HMM_PFN_WRITE];
range->default_flags |= HMM_PFN_REQ_WRITE;
range->pfns = kvmalloc_array(ttm->num_pages, sizeof(*range->pfns),
GFP_KERNEL);
if (unlikely(!range->pfns)) {
range->hmm_pfns = kvmalloc_array(ttm->num_pages,
sizeof(*range->hmm_pfns), GFP_KERNEL);
if (unlikely(!range->hmm_pfns)) {
r = -ENOMEM;
goto out_free_ranges;
}
@ -852,27 +837,23 @@ retry:
down_read(&mm->mmap_sem);
r = hmm_range_fault(range);
up_read(&mm->mmap_sem);
if (unlikely(r <= 0)) {
if (unlikely(r)) {
/*
* FIXME: This timeout should encompass the retry from
* mmu_interval_read_retry() as well.
*/
if ((r == 0 || r == -EBUSY) && !time_after(jiffies, timeout))
if (r == -EBUSY && !time_after(jiffies, timeout))
goto retry;
goto out_free_pfns;
}
for (i = 0; i < ttm->num_pages; i++) {
/* FIXME: The pages cannot be touched outside the notifier_lock */
pages[i] = hmm_device_entry_to_page(range, range->pfns[i]);
if (unlikely(!pages[i])) {
pr_err("Page fault failed for pfn[%lu] = 0x%llx\n",
i, range->pfns[i]);
r = -ENOMEM;
goto out_free_pfns;
}
}
/*
* Due to default_flags, all pages are HMM_PFN_VALID or
* hmm_range_fault() fails. FIXME: The pages cannot be touched outside
* the notifier_lock, and mmu_interval_read_retry() must be done first.
*/
for (i = 0; i < ttm->num_pages; i++)
pages[i] = hmm_pfn_to_page(range->hmm_pfns[i]);
gtt->range = range;
mmput(mm);
@ -882,7 +863,7 @@ retry:
out_unlock:
up_read(&mm->mmap_sem);
out_free_pfns:
kvfree(range->pfns);
kvfree(range->hmm_pfns);
out_free_ranges:
kfree(range);
out:
@ -907,7 +888,7 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm)
DRM_DEBUG_DRIVER("user_pages_done 0x%llx pages 0x%lx\n",
gtt->userptr, ttm->num_pages);
WARN_ONCE(!gtt->range || !gtt->range->pfns,
WARN_ONCE(!gtt->range || !gtt->range->hmm_pfns,
"No user pages to check\n");
if (gtt->range) {
@ -917,7 +898,7 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm)
*/
r = mmu_interval_read_retry(gtt->range->notifier,
gtt->range->notifier_seq);
kvfree(gtt->range->pfns);
kvfree(gtt->range->hmm_pfns);
kfree(gtt->range);
gtt->range = NULL;
}
@ -1008,8 +989,7 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
for (i = 0; i < ttm->num_pages; i++) {
if (ttm->pages[i] !=
hmm_device_entry_to_page(gtt->range,
gtt->range->pfns[i]))
hmm_pfn_to_page(gtt->range->hmm_pfns[i]))
break;
}

27
drivers/gpu/drm/nouveau/nouveau_dmem.c
View File

@ -85,7 +85,7 @@ static inline struct nouveau_dmem *page_to_dmem(struct page *page)
return container_of(page->pgmap, struct nouveau_dmem, pagemap);
}
static unsigned long nouveau_dmem_page_addr(struct page *page)
unsigned long nouveau_dmem_page_addr(struct page *page)
{
struct nouveau_dmem_chunk *chunk = page->zone_device_data;
unsigned long idx = page_to_pfn(page) - chunk->pfn_first;
@ -671,28 +671,3 @@ out_free_src:
out:
return ret;
}
void
nouveau_dmem_convert_pfn(struct nouveau_drm *drm,
struct hmm_range *range)
{
unsigned long i, npages;
npages = (range->end - range->start) >> PAGE_SHIFT;
for (i = 0; i < npages; ++i) {
struct page *page;
uint64_t addr;
page = hmm_device_entry_to_page(range, range->pfns[i]);
if (page == NULL)
continue;
if (!is_device_private_page(page))
continue;
addr = nouveau_dmem_page_addr(page);
range->pfns[i] &= ((1UL << range->pfn_shift) - 1);
range->pfns[i] |= (addr >> PAGE_SHIFT) << range->pfn_shift;
range->pfns[i] |= NVIF_VMM_PFNMAP_V0_VRAM;
}
}

3
drivers/gpu/drm/nouveau/nouveau_dmem.h
View File

@ -37,9 +37,8 @@ int nouveau_dmem_migrate_vma(struct nouveau_drm *drm,
struct vm_area_struct *vma,
unsigned long start,
unsigned long end);
unsigned long nouveau_dmem_page_addr(struct page *page);
void nouveau_dmem_convert_pfn(struct nouveau_drm *drm,
struct hmm_range *range);
#else /* IS_ENABLED(CONFIG_DRM_NOUVEAU_SVM) */
static inline void nouveau_dmem_init(struct nouveau_drm *drm) {}
static inline void nouveau_dmem_fini(struct nouveau_drm *drm) {}

94
drivers/gpu/drm/nouveau/nouveau_svm.c
View File

@ -369,19 +369,6 @@ out_free:
return ret;
}
static const u64
nouveau_svm_pfn_flags[HMM_PFN_FLAG_MAX] = {
[HMM_PFN_VALID ] = NVIF_VMM_PFNMAP_V0_V,
[HMM_PFN_WRITE ] = NVIF_VMM_PFNMAP_V0_W,
};
static const u64
nouveau_svm_pfn_values[HMM_PFN_VALUE_MAX] = {
[HMM_PFN_ERROR ] = ~NVIF_VMM_PFNMAP_V0_V,
[HMM_PFN_NONE ] = NVIF_VMM_PFNMAP_V0_NONE,
[HMM_PFN_SPECIAL] = ~NVIF_VMM_PFNMAP_V0_V,
};
/* Issue fault replay for GPU to retry accesses that faulted previously. */
static void
nouveau_svm_fault_replay(struct nouveau_svm *svm)
@ -519,9 +506,45 @@ static const struct mmu_interval_notifier_ops nouveau_svm_mni_ops = {
.invalidate = nouveau_svm_range_invalidate,
};
static void nouveau_hmm_convert_pfn(struct nouveau_drm *drm,
struct hmm_range *range, u64 *ioctl_addr)
{
unsigned long i, npages;
/*
* The ioctl_addr prepared here is passed through nvif_object_ioctl()
* to an eventual DMA map in something like gp100_vmm_pgt_pfn()
*
* This is all just encoding the internal hmm representation into a
* different nouveau internal representation.
*/
npages = (range->end - range->start) >> PAGE_SHIFT;
for (i = 0; i < npages; ++i) {
struct page *page;
if (!(range->hmm_pfns[i] & HMM_PFN_VALID)) {
ioctl_addr[i] = 0;
continue;
}
page = hmm_pfn_to_page(range->hmm_pfns[i]);
if (is_device_private_page(page))
ioctl_addr[i] = nouveau_dmem_page_addr(page) |
NVIF_VMM_PFNMAP_V0_V |
NVIF_VMM_PFNMAP_V0_VRAM;
else
ioctl_addr[i] = page_to_phys(page) |
NVIF_VMM_PFNMAP_V0_V |
NVIF_VMM_PFNMAP_V0_HOST;
if (range->hmm_pfns[i] & HMM_PFN_WRITE)
ioctl_addr[i] |= NVIF_VMM_PFNMAP_V0_W;
}
}
static int nouveau_range_fault(struct nouveau_svmm *svmm,
struct nouveau_drm *drm, void *data, u32 size,
u64 *pfns, struct svm_notifier *notifier)
unsigned long hmm_pfns[], u64 *ioctl_addr,
struct svm_notifier *notifier)
{
unsigned long timeout =
jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
@ -530,26 +553,27 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
.notifier = &notifier->notifier,
.start = notifier->notifier.interval_tree.start,
.end = notifier->notifier.interval_tree.last + 1,
.pfns = pfns,
.flags = nouveau_svm_pfn_flags,
.values = nouveau_svm_pfn_values,
.pfn_shift = NVIF_VMM_PFNMAP_V0_ADDR_SHIFT,
.pfn_flags_mask = HMM_PFN_REQ_FAULT | HMM_PFN_REQ_WRITE,
.hmm_pfns = hmm_pfns,
};
struct mm_struct *mm = notifier->notifier.mm;
long ret;
int ret;
while (true) {
if (time_after(jiffies, timeout))
return -EBUSY;
range.notifier_seq = mmu_interval_read_begin(range.notifier);
range.default_flags = 0;
range.pfn_flags_mask = -1UL;
down_read(&mm->mmap_sem);
ret = hmm_range_fault(&range);
up_read(&mm->mmap_sem);
if (ret <= 0) {
if (ret == 0 || ret == -EBUSY)
if (ret) {
/*
* FIXME: the input PFN_REQ flags are destroyed on
* -EBUSY, we need to regenerate them, also for the
* other continue below
*/
if (ret == -EBUSY)
continue;
return ret;
}
@ -563,7 +587,7 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
break;
}
nouveau_dmem_convert_pfn(drm, &range);
nouveau_hmm_convert_pfn(drm, &range, ioctl_addr);
svmm->vmm->vmm.object.client->super = true;
ret = nvif_object_ioctl(&svmm->vmm->vmm.object, data, size, NULL);
@ -590,6 +614,7 @@ nouveau_svm_fault(struct nvif_notify *notify)
} i;
u64 phys[16];
} args;
unsigned long hmm_pfns[ARRAY_SIZE(args.phys)];
struct vm_area_struct *vma;
u64 inst, start, limit;
int fi, fn, pi, fill;
@ -705,12 +730,17 @@ nouveau_svm_fault(struct nvif_notify *notify)
* access flags.
*XXX: atomic?
*/
if (buffer->fault[fn]->access != 0 /* READ. */ &&
buffer->fault[fn]->access != 3 /* PREFETCH. */) {
args.phys[pi++] = NVIF_VMM_PFNMAP_V0_V |
NVIF_VMM_PFNMAP_V0_W;
} else {
args.phys[pi++] = NVIF_VMM_PFNMAP_V0_V;
switch (buffer->fault[fn]->access) {
case 0: /* READ. */
hmm_pfns[pi++] = HMM_PFN_REQ_FAULT;
break;
case 3: /* PREFETCH. */
hmm_pfns[pi++] = 0;
break;
default:
hmm_pfns[pi++] = HMM_PFN_REQ_FAULT |
HMM_PFN_REQ_WRITE;
break;
}
args.i.p.size = pi << PAGE_SHIFT;
@ -738,7 +768,7 @@ nouveau_svm_fault(struct nvif_notify *notify)
fill = (buffer->fault[fn ]->addr -
buffer->fault[fn - 1]->addr) >> PAGE_SHIFT;
while (--fill)
args.phys[pi++] = NVIF_VMM_PFNMAP_V0_NONE;
hmm_pfns[pi++] = 0;
}
SVMM_DBG(svmm, "wndw %016llx-%016llx covering %d fault(s)",
@ -754,7 +784,7 @@ nouveau_svm_fault(struct nvif_notify *notify)
ret = nouveau_range_fault(
svmm, svm->drm, &args,
sizeof(args.i) + pi * sizeof(args.phys[0]),
args.phys, &notifier);
hmm_pfns, args.phys, &notifier);
mmu_interval_notifier_remove(&notifier.notifier);
}
mmput(mm);

111
include/linux/hmm.h
View File

@ -19,51 +19,47 @@
#include <linux/mmu_notifier.h>
/*
* hmm_pfn_flag_e - HMM flag enums
* On output:
* 0 - The page is faultable and a future call with
* HMM_PFN_REQ_FAULT could succeed.
* HMM_PFN_VALID - the pfn field points to a valid PFN. This PFN is at
* least readable. If dev_private_owner is !NULL then this could
* point at a DEVICE_PRIVATE page.
* HMM_PFN_WRITE - if the page memory can be written to (requires HMM_PFN_VALID)
* HMM_PFN_ERROR - accessing the pfn is impossible and the device should
* fail. ie poisoned memory, special pages, no vma, etc
*
* Flags:
* HMM_PFN_VALID: pfn is valid. It has, at least, read permission.
* HMM_PFN_WRITE: CPU page table has write permission set
*
* The driver provides a flags array for mapping page protections to device
* PTE bits. If the driver valid bit for an entry is bit 3,
* i.e., (entry & (1 << 3)), then the driver must provide
* an array in hmm_range.flags with hmm_range.flags[HMM_PFN_VALID] == 1 << 3.
* Same logic apply to all flags. This is the same idea as vm_page_prot in vma
* except that this is per device driver rather than per architecture.
* On input:
* 0 - Return the current state of the page, do not fault it.
* HMM_PFN_REQ_FAULT - The output must have HMM_PFN_VALID or hmm_range_fault()
* will fail
* HMM_PFN_REQ_WRITE - The output must have HMM_PFN_WRITE or hmm_range_fault()
* will fail. Must be combined with HMM_PFN_REQ_FAULT.
*/
enum hmm_pfn_flag_e {
HMM_PFN_VALID = 0,
HMM_PFN_WRITE,
HMM_PFN_FLAG_MAX
enum hmm_pfn_flags {
/* Output flags */
HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1),
HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2),
HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3),
/* Input flags */
HMM_PFN_REQ_FAULT = HMM_PFN_VALID,
HMM_PFN_REQ_WRITE = HMM_PFN_WRITE,
HMM_PFN_FLAGS = HMM_PFN_VALID | HMM_PFN_WRITE | HMM_PFN_ERROR,
};
/*
* hmm_pfn_value_e - HMM pfn special value
* hmm_pfn_to_page() - return struct page pointed to by a device entry
*
* Flags:
* HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory
* HMM_PFN_NONE: corresponding CPU page table entry is pte_none()
* HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the
* result of vmf_insert_pfn() or vm_insert_page(). Therefore, it should not
* be mirrored by a device, because the entry will never have HMM_PFN_VALID
* set and the pfn value is undefined.
*
* Driver provides values for none entry, error entry, and special entry.
* Driver can alias (i.e., use same value) error and special, but
* it should not alias none with error or special.
*
* HMM pfn value returned by hmm_vma_get_pfns() or hmm_vma_fault() will be:
* hmm_range.values[HMM_PFN_ERROR] if CPU page table entry is poisonous,
* hmm_range.values[HMM_PFN_NONE] if there is no CPU page table entry,
* hmm_range.values[HMM_PFN_SPECIAL] if CPU page table entry is a special one
* This must be called under the caller 'user_lock' after a successful
* mmu_interval_read_begin(). The caller must have tested for HMM_PFN_VALID
* already.
*/
enum hmm_pfn_value_e {
HMM_PFN_ERROR,
HMM_PFN_NONE,
HMM_PFN_SPECIAL,
HMM_PFN_VALUE_MAX
};
static inline struct page *hmm_pfn_to_page(unsigned long hmm_pfn)
{
return pfn_to_page(hmm_pfn & ~HMM_PFN_FLAGS);
}
/*
* struct hmm_range - track invalidation lock on virtual address range
@ -72,12 +68,9 @@ enum hmm_pfn_value_e {
* @notifier_seq: result of mmu_interval_read_begin()
* @start: range virtual start address (inclusive)
* @end: range virtual end address (exclusive)
* @pfns: array of pfns (big enough for the range)
* @flags: pfn flags to match device driver page table
* @values: pfn value for some special case (none, special, error, ...)
* @hmm_pfns: array of pfns (big enough for the range)
* @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
* @pfn_shift: pfn shift value (should be <= PAGE_SHIFT)
* @dev_private_owner: owner of device private pages
*/
struct hmm_range {
@ -85,42 +78,16 @@ struct hmm_range {
unsigned long notifier_seq;
unsigned long start;
unsigned long end;
uint64_t *pfns;
const uint64_t *flags;
const uint64_t *values;
uint64_t default_flags;
uint64_t pfn_flags_mask;
uint8_t pfn_shift;
unsigned long *hmm_pfns;
unsigned long default_flags;
unsigned long pfn_flags_mask;
void *dev_private_owner;
};
/*
* hmm_device_entry_to_page() - return struct page pointed to by a device entry
* @range: range use to decode device entry value
* @entry: device entry value to get corresponding struct page from
* Return: struct page pointer if entry is a valid, NULL otherwise
*
* If the device entry is valid (ie valid flag set) then return the struct page
* matching the entry value. Otherwise return NULL.
*/
static inline struct page *hmm_device_entry_to_page(const struct hmm_range *range,
uint64_t entry)
{
if (entry == range->values[HMM_PFN_NONE])
return NULL;
if (entry == range->values[HMM_PFN_ERROR])
return NULL;
if (entry == range->values[HMM_PFN_SPECIAL])
return NULL;
if (!(entry & range->flags[HMM_PFN_VALID]))
return NULL;
return pfn_to_page(entry >> range->pfn_shift);
}
/*
* Please see Documentation/vm/hmm.rst for how to use the range API.
*/
long hmm_range_fault(struct hmm_range *range);
int hmm_range_fault(struct hmm_range *range);
/*
* HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range

13
lib/Kconfig.debug
View File

@ -2218,6 +2218,19 @@ config TEST_MEMINIT
If unsure, say N.
config TEST_HMM
tristate "Test HMM (Heterogeneous Memory Management)"
depends on TRANSPARENT_HUGEPAGE
depends on DEVICE_PRIVATE
select HMM_MIRROR
select MMU_NOTIFIER
help
This is a pseudo device driver solely for testing HMM.
Say M here if you want to build the HMM test module.
Doing so will allow you to run tools/testing/selftest/vm/hmm-tests.
If unsure, say N.
endif # RUNTIME_TESTING_MENU
config MEMTEST

1
lib/Makefile
View File

@ -92,6 +92,7 @@ obj-$(CONFIG_TEST_STACKINIT) += test_stackinit.o
obj-$(CONFIG_TEST_BLACKHOLE_DEV) += test_blackhole_dev.o
obj-$(CONFIG_TEST_MEMINIT) += test_meminit.o
obj-$(CONFIG_TEST_LOCKUP) += test_lockup.o
obj-$(CONFIG_TEST_HMM) += test_hmm.o
obj-$(CONFIG_TEST_LIVEPATCH) += livepatch/

1164
lib/test_hmm.c Normal file
View File

File diff suppressed because it is too large Load Diff

59
lib/test_hmm_uapi.h Normal file
View File

@ -0,0 +1,59 @@
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/*
* This is a module to test the HMM (Heterogeneous Memory Management) API
* of the kernel. It allows a userspace program to expose its entire address
* space through the HMM test module device file.
*/
#ifndef _LIB_TEST_HMM_UAPI_H
#define _LIB_TEST_HMM_UAPI_H
#include <linux/types.h>
#include <linux/ioctl.h>
/*
* Structure to pass to the HMM test driver to mimic a device accessing
* system memory and ZONE_DEVICE private memory through device page tables.
*
* @addr: (in) user address the device will read/write
* @ptr: (in) user address where device data is copied to/from
* @npages: (in) number of pages to read/write
* @cpages: (out) number of pages copied
* @faults: (out) number of device page faults seen
*/
struct hmm_dmirror_cmd {
__u64 addr;
__u64 ptr;
__u64 npages;
__u64 cpages;
__u64 faults;
};
/* Expose the address space of the calling process through hmm device file */
#define HMM_DMIRROR_READ _IOWR('H', 0x00, struct hmm_dmirror_cmd)
#define HMM_DMIRROR_WRITE _IOWR('H', 0x01, struct hmm_dmirror_cmd)
#define HMM_DMIRROR_MIGRATE _IOWR('H', 0x02, struct hmm_dmirror_cmd)
#define HMM_DMIRROR_SNAPSHOT _IOWR('H', 0x03, struct hmm_dmirror_cmd)
/*
* Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT.
* HMM_DMIRROR_PROT_ERROR: no valid mirror PTE for this page
* HMM_DMIRROR_PROT_NONE: unpopulated PTE or PTE with no access
* HMM_DMIRROR_PROT_READ: read-only PTE
* HMM_DMIRROR_PROT_WRITE: read/write PTE
* HMM_DMIRROR_PROT_ZERO: special read-only zero page
* HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL: Migrated device private page on the
* device the ioctl() is made
* HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE: Migrated device private page on some
* other device
*/
enum {
HMM_DMIRROR_PROT_ERROR = 0xFF,
HMM_DMIRROR_PROT_NONE = 0x00,
HMM_DMIRROR_PROT_READ = 0x01,
HMM_DMIRROR_PROT_WRITE = 0x02,
HMM_DMIRROR_PROT_ZERO = 0x10,
HMM_DMIRROR_PROT_DEV_PRIVATE_LOCAL = 0x20,
HMM_DMIRROR_PROT_DEV_PRIVATE_REMOTE = 0x30,
};
#endif /* _LIB_TEST_HMM_UAPI_H */

185
mm/hmm.c
View File

@ -37,28 +37,13 @@ enum {
HMM_NEED_ALL_BITS = HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT,
};
/*
* hmm_device_entry_from_pfn() - create a valid device entry value from pfn
* @range: range use to encode HMM pfn value
* @pfn: pfn value for which to create the device entry
* Return: valid device entry for the pfn
*/
static uint64_t hmm_device_entry_from_pfn(const struct hmm_range *range,
unsigned long pfn)
{
return (pfn << range->pfn_shift) | range->flags[HMM_PFN_VALID];
}
static int hmm_pfns_fill(unsigned long addr, unsigned long end,
struct hmm_range *range, enum hmm_pfn_value_e value)
struct hmm_range *range, unsigned long cpu_flags)
{
uint64_t *pfns = range->pfns;
unsigned long i;
unsigned long i = (addr - range->start) >> PAGE_SHIFT;
i = (addr - range->start) >> PAGE_SHIFT;
for (; addr < end; addr += PAGE_SIZE, i++)
pfns[i] = range->values[value];
range->hmm_pfns[i] = cpu_flags;
return 0;
}
@ -96,7 +81,8 @@ static int hmm_vma_fault(unsigned long addr, unsigned long end,
}
static unsigned int hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
uint64_t pfns, uint64_t cpu_flags)
unsigned long pfn_req_flags,
unsigned long cpu_flags)
{
struct hmm_range *range = hmm_vma_walk->range;
@ -110,27 +96,28 @@ static unsigned int hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
* waste to have the user pre-fill the pfn arrays with a default
* flags value.
*/
pfns = (pfns & range->pfn_flags_mask) | range->default_flags;
pfn_req_flags &= range->pfn_flags_mask;
pfn_req_flags |= range->default_flags;
/* We aren't ask to do anything ... */
if (!(pfns & range->flags[HMM_PFN_VALID]))
if (!(pfn_req_flags & HMM_PFN_REQ_FAULT))
return 0;
/* Need to write fault ? */
if ((pfns & range->flags[HMM_PFN_WRITE]) &&
!(cpu_flags & range->flags[HMM_PFN_WRITE]))
if ((pfn_req_flags & HMM_PFN_REQ_WRITE) &&
!(cpu_flags & HMM_PFN_WRITE))
return HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT;
/* If CPU page table is not valid then we need to fault */
if (!(cpu_flags & range->flags[HMM_PFN_VALID]))
if (!(cpu_flags & HMM_PFN_VALID))
return HMM_NEED_FAULT;
return 0;
}
static unsigned int
hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
const uint64_t *pfns, unsigned long npages,
uint64_t cpu_flags)
const unsigned long hmm_pfns[], unsigned long npages,
unsigned long cpu_flags)
{
struct hmm_range *range = hmm_vma_walk->range;
unsigned int required_fault = 0;
@ -142,12 +129,12 @@ hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
* hmm_pte_need_fault() will always return 0.
*/
if (!((range->default_flags | range->pfn_flags_mask) &
range->flags[HMM_PFN_VALID]))
HMM_PFN_REQ_FAULT))
return 0;
for (i = 0; i < npages; ++i) {
required_fault |=
hmm_pte_need_fault(hmm_vma_walk, pfns[i], cpu_flags);
required_fault |= hmm_pte_need_fault(hmm_vma_walk, hmm_pfns[i],
cpu_flags);
if (required_fault == HMM_NEED_ALL_BITS)
return required_fault;
}
@ -161,12 +148,13 @@ static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
struct hmm_range *range = hmm_vma_walk->range;
unsigned int required_fault;
unsigned long i, npages;
uint64_t *pfns;
unsigned long *hmm_pfns;
i = (addr - range->start) >> PAGE_SHIFT;
npages = (end - addr) >> PAGE_SHIFT;
pfns = &range->pfns[i];
required_fault = hmm_range_need_fault(hmm_vma_walk, pfns, npages, 0);
hmm_pfns = &range->hmm_pfns[i];
required_fault =
hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0);
if (!walk->vma) {
if (required_fault)
return -EFAULT;
@ -174,46 +162,44 @@ static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
}
if (required_fault)
return hmm_vma_fault(addr, end, required_fault, walk);
hmm_vma_walk->last = addr;
return hmm_pfns_fill(addr, end, range, HMM_PFN_NONE);
return hmm_pfns_fill(addr, end, range, 0);
}
static inline uint64_t pmd_to_hmm_pfn_flags(struct hmm_range *range, pmd_t pmd)
static inline unsigned long pmd_to_hmm_pfn_flags(struct hmm_range *range,
pmd_t pmd)
{
if (pmd_protnone(pmd))
return 0;
return pmd_write(pmd) ? range->flags[HMM_PFN_VALID] |
range->flags[HMM_PFN_WRITE] :
range->flags[HMM_PFN_VALID];
return pmd_write(pmd) ? (HMM_PFN_VALID | HMM_PFN_WRITE) : HMM_PFN_VALID;
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
unsigned long end, uint64_t *pfns, pmd_t pmd)
unsigned long end, unsigned long hmm_pfns[],
pmd_t pmd)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
unsigned long pfn, npages, i;
unsigned int required_fault;
uint64_t cpu_flags;
unsigned long cpu_flags;
npages = (end - addr) >> PAGE_SHIFT;
cpu_flags = pmd_to_hmm_pfn_flags(range, pmd);
required_fault =
hmm_range_need_fault(hmm_vma_walk, pfns, npages, cpu_flags);
hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, cpu_flags);
if (required_fault)
return hmm_vma_fault(addr, end, required_fault, walk);
pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags;
hmm_vma_walk->last = end;
hmm_pfns[i] = pfn | cpu_flags;
return 0;
}
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
/* stub to allow the code below to compile */
int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
unsigned long end, uint64_t *pfns, pmd_t pmd);
unsigned long end, unsigned long hmm_pfns[], pmd_t pmd);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static inline bool hmm_is_device_private_entry(struct hmm_range *range,
@ -224,31 +210,31 @@ static inline bool hmm_is_device_private_entry(struct hmm_range *range,
range->dev_private_owner;
}
static inline uint64_t pte_to_hmm_pfn_flags(struct hmm_range *range, pte_t pte)
static inline unsigned long pte_to_hmm_pfn_flags(struct hmm_range *range,
pte_t pte)
{
if (pte_none(pte) || !pte_present(pte) || pte_protnone(pte))
return 0;
return pte_write(pte) ? range->flags[HMM_PFN_VALID] |
range->flags[HMM_PFN_WRITE] :
range->flags[HMM_PFN_VALID];
return pte_write(pte) ? (HMM_PFN_VALID | HMM_PFN_WRITE) : HMM_PFN_VALID;
}
static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
unsigned long end, pmd_t *pmdp, pte_t *ptep,
uint64_t *pfn)
unsigned long *hmm_pfn)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
unsigned int required_fault;
uint64_t cpu_flags;
unsigned long cpu_flags;
pte_t pte = *ptep;
uint64_t orig_pfn = *pfn;
uint64_t pfn_req_flags = *hmm_pfn;
if (pte_none(pte)) {
required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0);
required_fault =
hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0);
if (required_fault)
goto fault;
*pfn = range->values[HMM_PFN_NONE];
*hmm_pfn = 0;
return 0;
}
@ -260,17 +246,18 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
* the PFN even if not present.
*/
if (hmm_is_device_private_entry(range, entry)) {
*pfn = hmm_device_entry_from_pfn(range,
device_private_entry_to_pfn(entry));
*pfn |= range->flags[HMM_PFN_VALID];
cpu_flags = HMM_PFN_VALID;
if (is_write_device_private_entry(entry))
*pfn |= range->flags[HMM_PFN_WRITE];
cpu_flags |= HMM_PFN_WRITE;
*hmm_pfn = device_private_entry_to_pfn(entry) |
cpu_flags;
return 0;
}
required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0);
required_fault =
hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0);
if (!required_fault) {
*pfn = range->values[HMM_PFN_NONE];
*hmm_pfn = 0;
return 0;
}
@ -290,7 +277,8 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
}
cpu_flags = pte_to_hmm_pfn_flags(range, pte);
required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags);
required_fault =
hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags);
if (required_fault)
goto fault;
@ -299,15 +287,15 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
* fall through and treat it like a normal page.
*/
if (pte_special(pte) && !is_zero_pfn(pte_pfn(pte))) {
if (hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0)) {
if (hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0)) {
pte_unmap(ptep);
return -EFAULT;
}
*pfn = range->values[HMM_PFN_SPECIAL];
*hmm_pfn = HMM_PFN_ERROR;
return 0;
}
*pfn = hmm_device_entry_from_pfn(range, pte_pfn(pte)) | cpu_flags;
*hmm_pfn = pte_pfn(pte) | cpu_flags;
return 0;
fault:
@ -323,7 +311,8 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
uint64_t *pfns = &range->pfns[(start - range->start) >> PAGE_SHIFT];
unsigned long *hmm_pfns =
&range->hmm_pfns[(start - range->start) >> PAGE_SHIFT];
unsigned long npages = (end - start) >> PAGE_SHIFT;
unsigned long addr = start;
pte_t *ptep;
@ -335,16 +324,16 @@ again:
return hmm_vma_walk_hole(start, end, -1, walk);
if (thp_migration_supported() && is_pmd_migration_entry(pmd)) {
if (hmm_range_need_fault(hmm_vma_walk, pfns, npages, 0)) {
if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0)) {
hmm_vma_walk->last = addr;
pmd_migration_entry_wait(walk->mm, pmdp);
return -EBUSY;
}
return hmm_pfns_fill(start, end, range, HMM_PFN_NONE);
return hmm_pfns_fill(start, end, range, 0);
}
if (!pmd_present(pmd)) {
if (hmm_range_need_fault(hmm_vma_walk, pfns, npages, 0))
if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0))
return -EFAULT;
return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
}
@ -364,7 +353,7 @@ again:
if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd))
goto again;
return hmm_vma_handle_pmd(walk, addr, end, pfns, pmd);
return hmm_vma_handle_pmd(walk, addr, end, hmm_pfns, pmd);
}
/*
@ -374,37 +363,33 @@ again:
* recover.
*/
if (pmd_bad(pmd)) {
if (hmm_range_need_fault(hmm_vma_walk, pfns, npages, 0))
if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0))
return -EFAULT;
return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
}
ptep = pte_offset_map(pmdp, addr);
for (; addr < end; addr += PAGE_SIZE, ptep++, pfns++) {
for (; addr < end; addr += PAGE_SIZE, ptep++, hmm_pfns++) {
int r;
r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, pfns);
r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, hmm_pfns);
if (r) {
/* hmm_vma_handle_pte() did pte_unmap() */
hmm_vma_walk->last = addr;
return r;
}
}
pte_unmap(ptep - 1);
hmm_vma_walk->last = addr;
return 0;
}
#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && \
defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
static inline uint64_t pud_to_hmm_pfn_flags(struct hmm_range *range, pud_t pud)
static inline unsigned long pud_to_hmm_pfn_flags(struct hmm_range *range,
pud_t pud)
{
if (!pud_present(pud))
return 0;
return pud_write(pud) ? range->flags[HMM_PFN_VALID] |
range->flags[HMM_PFN_WRITE] :
range->flags[HMM_PFN_VALID];
return pud_write(pud) ? (HMM_PFN_VALID | HMM_PFN_WRITE) : HMM_PFN_VALID;
}
static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
@ -432,7 +417,8 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
if (pud_huge(pud) && pud_devmap(pud)) {
unsigned long i, npages, pfn;
unsigned int required_fault;
uint64_t *pfns, cpu_flags;
unsigned long *hmm_pfns;
unsigned long cpu_flags;
if (!pud_present(pud)) {
spin_unlock(ptl);
@ -441,10 +427,10 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
i = (addr - range->start) >> PAGE_SHIFT;
npages = (end - addr) >> PAGE_SHIFT;
pfns = &range->pfns[i];
hmm_pfns = &range->hmm_pfns[i];
cpu_flags = pud_to_hmm_pfn_flags(range, pud);
required_fault = hmm_range_need_fault(hmm_vma_walk, pfns,
required_fault = hmm_range_need_fault(hmm_vma_walk, hmm_pfns,
npages, cpu_flags);
if (required_fault) {
spin_unlock(ptl);
@ -453,9 +439,7 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
for (i = 0; i < npages; ++i, ++pfn)
pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
cpu_flags;
hmm_vma_walk->last = end;
hmm_pfns[i] = pfn | cpu_flags;
goto out_unlock;
}
@ -479,8 +463,9 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
struct vm_area_struct *vma = walk->vma;
uint64_t orig_pfn, cpu_flags;
unsigned int required_fault;
unsigned long pfn_req_flags;
unsigned long cpu_flags;
spinlock_t *ptl;
pte_t entry;
@ -488,9 +473,10 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
entry = huge_ptep_get(pte);
i = (start - range->start) >> PAGE_SHIFT;
orig_pfn = range->pfns[i];
pfn_req_flags = range->hmm_pfns[i];
cpu_flags = pte_to_hmm_pfn_flags(range, entry);
required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags);
required_fault =
hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags);
if (required_fault) {
spin_unlock(ptl);
return hmm_vma_fault(addr, end, required_fault, walk);
@ -498,9 +484,8 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
pfn = pte_pfn(entry) + ((start & ~hmask) >> 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;
range->hmm_pfns[i] = pfn | cpu_flags;
spin_unlock(ptl);
return 0;
}
@ -531,13 +516,12 @@ static int hmm_vma_walk_test(unsigned long start, unsigned long end,
* failure.
*/
if (hmm_range_need_fault(hmm_vma_walk,
range->pfns +
range->hmm_pfns +
((start - range->start) >> PAGE_SHIFT),
(end - start) >> PAGE_SHIFT, 0))
return -EFAULT;
hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
hmm_vma_walk->last = end;
/* Skip this vma and continue processing the next vma. */
return 1;
@ -555,9 +539,7 @@ static const struct mm_walk_ops hmm_walk_ops = {
* hmm_range_fault - try to fault some address in a virtual address range
* @range: argument structure
*
* Return: the number of valid pages in range->pfns[] (from range start
* address), which may be zero. On error one of the following status codes
* can be returned:
* Returns 0 on success or one of the following error codes:
*
* -EINVAL: Invalid arguments or mm or virtual address is in an invalid vma
* (e.g., device file vma).
@ -572,7 +554,7 @@ static const struct mm_walk_ops hmm_walk_ops = {
* This is similar to get_user_pages(), except that it can read the page tables
* without mutating them (ie causing faults).
*/
long hmm_range_fault(struct hmm_range *range)
int hmm_range_fault(struct hmm_range *range)
{
struct hmm_vma_walk hmm_vma_walk = {
.range = range,
@ -590,10 +572,13 @@ long hmm_range_fault(struct hmm_range *range)
return -EBUSY;
ret = walk_page_range(mm, hmm_vma_walk.last, range->end,
&hmm_walk_ops, &hmm_vma_walk);
/*
* When -EBUSY is returned the loop restarts with
* hmm_vma_walk.last set to an address that has not been stored
* in pfns. All entries < last in the pfn array are set to their
* output, and all >= are still at their input values.
*/
} while (ret == -EBUSY);
if (ret)
return ret;
return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
return ret;
}
EXPORT_SYMBOL(hmm_range_fault);

1
tools/testing/selftests/vm/.gitignore vendored
View File

@ -17,3 +17,4 @@ gup_benchmark
va_128TBswitch
map_fixed_noreplace
write_to_hugetlbfs
hmm-tests

3
tools/testing/selftests/vm/Makefile
View File

@ -7,6 +7,7 @@ CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
LDLIBS = -lrt
TEST_GEN_FILES = compaction_test
TEST_GEN_FILES += gup_benchmark
TEST_GEN_FILES += hmm-tests
TEST_GEN_FILES += hugepage-mmap
TEST_GEN_FILES += hugepage-shm
TEST_GEN_FILES += map_hugetlb
@ -33,6 +34,8 @@ TEST_FILES := test_vmalloc.sh
KSFT_KHDR_INSTALL := 1
include ../lib.mk
$(OUTPUT)/hmm-tests: LDLIBS += -lhugetlbfs -lpthread
$(OUTPUT)/userfaultfd: LDLIBS += -lpthread
$(OUTPUT)/mlock-random-test: LDLIBS += -lcap

2
tools/testing/selftests/vm/config
View File

@ -1,3 +1,5 @@
CONFIG_SYSVIPC=y
CONFIG_USERFAULTFD=y
CONFIG_TEST_VMALLOC=m
CONFIG_DEVICE_PRIVATE=y
CONFIG_TEST_HMM=m

1359
tools/testing/selftests/vm/hmm-tests.c Normal file
View File

File diff suppressed because it is too large Load Diff

16
tools/testing/selftests/vm/run_vmtests
View File

@ -307,4 +307,20 @@ else
echo "[FAIL]"
exitcode=1
fi
echo "running HMM smoke test"
echo "------------------------------------"
./test_hmm.sh smoke
ret_val=$?
if [ $ret_val -eq 0 ]; then
echo "[PASS]"
elif [ $ret_val -eq $ksft_skip ]; then
echo "[SKIP]"
exitcode=$ksft_skip
else
echo "[FAIL]"
exitcode=1
fi
exit $exitcode

97
tools/testing/selftests/vm/test_hmm.sh Executable file
View File

@ -0,0 +1,97 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
#
# Copyright (C) 2018 Uladzislau Rezki (Sony) <urezki@gmail.com>
#
# This is a test script for the kernel test driver to analyse vmalloc
# allocator. Therefore it is just a kernel module loader. You can specify
# and pass different parameters in order to:
# a) analyse performance of vmalloc allocations;
# b) stressing and stability check of vmalloc subsystem.
TEST_NAME="test_hmm"
DRIVER="test_hmm"
# 1 if fails
exitcode=1
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
check_test_requirements()
{
uid=$(id -u)
if [ $uid -ne 0 ]; then
echo "$0: Must be run as root"
exit $ksft_skip
fi
if ! which modprobe > /dev/null 2>&1; then
echo "$0: You need modprobe installed"
exit $ksft_skip
fi
if ! modinfo $DRIVER > /dev/null 2>&1; then
echo "$0: You must have the following enabled in your kernel:"
echo "CONFIG_TEST_HMM=m"
exit $ksft_skip
fi
}
load_driver()
{
modprobe $DRIVER > /dev/null 2>&1
if [ $? == 0 ]; then
major=$(awk "\$2==\"HMM_DMIRROR\" {print \$1}" /proc/devices)
mknod /dev/hmm_dmirror0 c $major 0
mknod /dev/hmm_dmirror1 c $major 1
fi
}
unload_driver()
{
modprobe -r $DRIVER > /dev/null 2>&1
rm -f /dev/hmm_dmirror?
}
run_smoke()
{
echo "Running smoke test. Note, this test provides basic coverage."
load_driver
$(dirname "${BASH_SOURCE[0]}")/hmm-tests
unload_driver
}
usage()
{
echo -n "Usage: $0"
echo
echo "Example usage:"
echo
echo "# Shows help message"
echo "./${TEST_NAME}.sh"
echo
echo "# Smoke testing"
echo "./${TEST_NAME}.sh smoke"
echo
exit 0
}
function run_test()
{
if [ $# -eq 0 ]; then
usage
else
if [ "$1" = "smoke" ]; then
run_smoke
else
usage
fi
fi
}
check_test_requirements
run_test $@
exit 0