| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Tue, 29 Jan 2019 11:54:26 -0500
From: jglisse@...hat.com
To: linux-mm@...ck.org
Cc: linux-kernel@...r.kernel.org,
Jérôme Glisse <jglisse@...hat.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Ralph Campbell <rcampbell@...dia.com>,
John Hubbard <jhubbard@...dia.com>
Subject: [PATCH 08/10] mm/hmm: support hugetlbfs (snap shoting, faulting and DMA mapping)
From: Jérôme Glisse <jglisse@...hat.com>
This adds support for hugetlbfs so that HMM user can map mirror range
of virtual address back by hugetlbfs. Note that now the range allows
user to optimize DMA mapping of such page so that we can map a huge
page as one chunk.
Signed-off-by: Jérôme Glisse <jglisse@...hat.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: Ralph Campbell <rcampbell@...dia.com>
Cc: John Hubbard <jhubbard@...dia.com>
---
include/linux/hmm.h | 29 ++++++++-
mm/hmm.c | 141 +++++++++++++++++++++++++++++++++++++-------
2 files changed, 147 insertions(+), 23 deletions(-)
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index fc3630d0bbfd..b3850297352f 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -181,10 +181,31 @@ 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
+ * Returns: 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
+ * Returns: 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
@@ -438,7 +459,7 @@ void hmm_mirror_unregister(struct hmm_mirror *mirror);
* struct hmm_range range;
* ...
*
- * ret = hmm_range_register(&range, mm, start, end);
+ * ret = hmm_range_register(&range, mm, start, end, page_shift);
* if (ret)
* return ret;
*
@@ -498,7 +519,8 @@ void hmm_mirror_unregister(struct hmm_mirror *mirror);
int hmm_range_register(struct hmm_range *range,
struct mm_struct *mm,
unsigned long start,
- unsigned long end);
+ unsigned long end,
+ unsigned page_shift);
void hmm_range_unregister(struct hmm_range *range);
long hmm_range_snapshot(struct hmm_range *range);
long hmm_range_fault(struct hmm_range *range, bool block);
@@ -538,7 +560,8 @@ static inline int hmm_vma_fault(struct hmm_range *range, bool block)
range->pfn_flags_mask = -1UL;
ret = hmm_range_register(range, range->vma->vm_mm,
- range->start, range->end);
+ range->start, range->end,
+ PAGE_SHIFT);
if (ret)
return (int)ret;
diff --git a/mm/hmm.c b/mm/hmm.c
index 9cd68334a759..8b87e1813313 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -396,11 +396,13 @@ 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;
+ unsigned long i, page_size;
hmm_vma_walk->last = addr;
- i = (addr - range->start) >> PAGE_SHIFT;
- for (; addr < end; addr += PAGE_SIZE, i++) {
+ page_size = 1UL << range->page_shift;
+ i = (addr - range->start) >> range->page_shift;
+
+ for (; addr < end; addr += page_size, i++) {
pfns[i] = range->values[HMM_PFN_NONE];
if (fault || write_fault) {
int ret;
@@ -712,6 +714,69 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
return 0;
}
+static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
+ unsigned long start, unsigned long end,
+ struct mm_walk *walk)
+{
+#ifdef CONFIG_HUGETLB_PAGE
+ unsigned long addr = start, i, pfn, mask, size, pfn_inc;
+ struct hmm_vma_walk *hmm_vma_walk = walk->private;
+ struct hmm_range *range = hmm_vma_walk->range;
+ struct vm_area_struct *vma = walk->vma;
+ struct hstate *h = hstate_vma(vma);
+ uint64_t orig_pfn, cpu_flags;
+ bool fault, write_fault;
+ spinlock_t *ptl;
+ pte_t entry;
+ int ret = 0;
+
+ size = 1UL << huge_page_shift(h);
+ mask = size - 1;
+ if (range->page_shift != PAGE_SHIFT) {
+ /* Make sure we are looking at 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;
+ }
+
+
+ ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte);
+ entry = huge_ptep_get(pte);
+
+ i = (start - range->start) >> range->page_shift;
+ orig_pfn = range->pfns[i];
+ range->pfns[i] = range->values[HMM_PFN_NONE];
+ cpu_flags = pte_to_hmm_pfn_flags(range, entry);
+ fault = write_fault = false;
+ hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
+ &fault, &write_fault);
+ if (fault || write_fault) {
+ ret = -ENOENT;
+ goto unlock;
+ }
+
+ pfn = pte_pfn(entry) + (start & mask);
+ for (; addr < end; addr += size, i++, pfn += pfn_inc)
+ range->pfns[i] = hmm_pfn_from_pfn(range, pfn) | cpu_flags;
+ hmm_vma_walk->last = end;
+
+unlock:
+ spin_unlock(ptl);
+
+ if (ret == -ENOENT)
+ return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
+
+ return ret;
+#else /* CONFIG_HUGETLB_PAGE */
+ return -EINVAL;
+#endif
+}
+
static void hmm_pfns_clear(struct hmm_range *range,
uint64_t *pfns,
unsigned long addr,
@@ -735,6 +800,7 @@ static void hmm_pfns_special(struct hmm_range *range)
* @mm: the mm struct for the range of virtual address
* @start: start virtual address (inclusive)
* @end: end virtual address (exclusive)
+ * @page_shift: expect page shift for the range
* Returns 0 on success, -EFAULT if the address space is no longer valid
*
* Track updates to the CPU page table see include/linux/hmm.h
@@ -742,15 +808,22 @@ static void hmm_pfns_special(struct hmm_range *range)
int hmm_range_register(struct hmm_range *range,
struct mm_struct *mm,
unsigned long start,
- unsigned long end)
+ unsigned long end,
+ unsigned page_shift)
{
- range->start = start & PAGE_MASK;
- range->end = end & PAGE_MASK;
+ unsigned long mask = ((1UL << page_shift) - 1UL);
+
range->valid = false;
range->hmm = NULL;
- if (range->start >= range->end)
+ if ((start & mask) || (end & mask))
return -EINVAL;
+ if (start >= end)
+ return -EINVAL;
+
+ range->page_shift = page_shift;
+ range->start = start;
+ range->end = end;
range->hmm = hmm_register(mm);
if (!range->hmm)
@@ -818,6 +891,7 @@ EXPORT_SYMBOL(hmm_range_unregister);
*/
long hmm_range_snapshot(struct hmm_range *range)
{
+ const unsigned long device_vma = VM_IO | VM_PFNMAP | VM_MIXEDMAP;
unsigned long start = range->start, end;
struct hmm_vma_walk hmm_vma_walk;
struct hmm *hmm = range->hmm;
@@ -834,15 +908,26 @@ long hmm_range_snapshot(struct hmm_range *range)
return -EAGAIN;
vma = find_vma(hmm->mm, start);
- if (vma == NULL || (vma->vm_flags & VM_SPECIAL))
+ if (vma == NULL || (vma->vm_flags & device_vma))
return -EFAULT;
- /* FIXME support hugetlb fs/dax */
- if (is_vm_hugetlb_page(vma) || vma_is_dax(vma)) {
+ /* FIXME support dax */
+ if (vma_is_dax(vma)) {
hmm_pfns_special(range);
return -EINVAL;
}
+ if (is_vm_hugetlb_page(vma)) {
+ struct hstate *h = hstate_vma(vma);
+
+ if (huge_page_shift(h) != 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
@@ -868,6 +953,7 @@ long hmm_range_snapshot(struct hmm_range *range)
mm_walk.hugetlb_entry = NULL;
mm_walk.pmd_entry = hmm_vma_walk_pmd;
mm_walk.pte_hole = hmm_vma_walk_hole;
+ mm_walk.hugetlb_entry = hmm_vma_walk_hugetlb_entry;
walk_page_range(start, end, &mm_walk);
start = end;
@@ -909,6 +995,7 @@ EXPORT_SYMBOL(hmm_range_snapshot);
*/
long hmm_range_fault(struct hmm_range *range, bool block)
{
+ const unsigned long device_vma = VM_IO | VM_PFNMAP | VM_MIXEDMAP;
unsigned long start = range->start, end;
struct hmm_vma_walk hmm_vma_walk;
struct hmm *hmm = range->hmm;
@@ -928,15 +1015,26 @@ long hmm_range_fault(struct hmm_range *range, bool block)
}
vma = find_vma(hmm->mm, start);
- if (vma == NULL || (vma->vm_flags & VM_SPECIAL))
+ if (vma == NULL || (vma->vm_flags & device_vma))
return -EFAULT;
- /* FIXME support hugetlb fs/dax */
- if (is_vm_hugetlb_page(vma) || vma_is_dax(vma)) {
+ /* FIXME support dax */
+ if (vma_is_dax(vma)) {
hmm_pfns_special(range);
return -EINVAL;
}
+ if (is_vm_hugetlb_page(vma)) {
+ struct hstate *h = hstate_vma(vma);
+
+ if (huge_page_shift(h) != 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
@@ -963,6 +1061,7 @@ long hmm_range_fault(struct hmm_range *range, bool block)
mm_walk.hugetlb_entry = NULL;
mm_walk.pmd_entry = hmm_vma_walk_pmd;
mm_walk.pte_hole = hmm_vma_walk_hole;
+ mm_walk.hugetlb_entry = hmm_vma_walk_hugetlb_entry;
do {
ret = walk_page_range(start, end, &mm_walk);
@@ -1003,14 +1102,15 @@ long hmm_range_dma_map(struct hmm_range *range,
dma_addr_t *daddrs,
bool block)
{
- unsigned long i, npages, mapped;
+ unsigned long i, npages, mapped, page_size;
long ret;
ret = hmm_range_fault(range, block);
if (ret <= 0)
return ret ? ret : -EBUSY;
- npages = (range->end - range->start) >> PAGE_SHIFT;
+ page_size = hmm_range_page_size(range);
+ npages = (range->end - range->start) >> range->page_shift;
for (i = 0, mapped = 0; i < npages; ++i) {
enum dma_data_direction dir = DMA_FROM_DEVICE;
struct page *page;
@@ -1039,7 +1139,7 @@ long hmm_range_dma_map(struct hmm_range *range,
if (range->pfns[i] & range->values[HMM_PFN_WRITE])
dir = DMA_BIDIRECTIONAL;
- daddrs[i] = dma_map_page(device, page, 0, PAGE_SIZE, dir);
+ daddrs[i] = dma_map_page(device, page, 0, page_size, dir);
if (dma_mapping_error(device, daddrs[i])) {
ret = -EFAULT;
goto unmap;
@@ -1066,7 +1166,7 @@ long hmm_range_dma_map(struct hmm_range *range,
if (range->pfns[i] & range->values[HMM_PFN_WRITE])
dir = DMA_BIDIRECTIONAL;
- dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir);
+ dma_unmap_page(device, daddrs[i], page_size, dir);
mapped--;
}
@@ -1094,7 +1194,7 @@ long hmm_range_dma_unmap(struct hmm_range *range,
dma_addr_t *daddrs,
bool dirty)
{
- unsigned long i, npages;
+ unsigned long i, npages, page_size;
long cpages = 0;
/* Sanity check. */
@@ -1105,7 +1205,8 @@ long hmm_range_dma_unmap(struct hmm_range *range,
if (!range->pfns)
return -EINVAL;
- npages = (range->end - range->start) >> PAGE_SHIFT;
+ page_size = hmm_range_page_size(range);
+ npages = (range->end - range->start) >> range->page_shift;
for (i = 0; i < npages; ++i) {
enum dma_data_direction dir = DMA_FROM_DEVICE;
struct page *page;
@@ -1127,7 +1228,7 @@ long hmm_range_dma_unmap(struct hmm_range *range,
}
/* Unmap and clear pfns/dma address */
- dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir);
+ dma_unmap_page(device, daddrs[i], page_size, dir);
range->pfns[i] = range->values[HMM_PFN_NONE];
/* FIXME see comments in hmm_vma_dma_map() */
daddrs[i] = 0;
--
2.17.2
Powered by blists - more mailing lists