* [PATCH 1/4] mm: fix device-dax pud write-faults triggered by get_user_pages()
2017-11-11 0:44 [PATCH 0/4] fix device-dax pud crash and fixup {pte,pmd,pud}_write Dan Williams
@ 2017-11-11 0:44 ` Dan Williams
2017-11-11 0:44 ` [PATCH 2/4] mm: replace pud_write with pud_access_permitted in fault + gup paths Dan Williams
` (2 subsequent siblings)
3 siblings, 0 replies; 5+ messages in thread
From: Dan Williams @ 2017-11-11 0:44 UTC (permalink / raw)
To: akpm
Cc: linux-nvdimm, linux-kernel, stable, linux-mm, Dave Hansen,
Kirill A. Shutemov
Currently only get_user_pages_fast() can safely handle the writable gup
case due to its use of pud_access_permitted() to check whether the pud
entry is writable. In the gup slow path pud_write() is used instead of
pud_access_permitted() and to date it has been unimplemented, just calls
BUG_ON().
kernel BUG at ./include/linux/hugetlb.h:244!
[..]
RIP: 0010:follow_devmap_pud+0x482/0x490
[..]
Call Trace:
follow_page_mask+0x28c/0x6e0
__get_user_pages+0xe4/0x6c0
get_user_pages_unlocked+0x130/0x1b0
get_user_pages_fast+0x89/0xb0
iov_iter_get_pages_alloc+0x114/0x4a0
nfs_direct_read_schedule_iovec+0xd2/0x350
? nfs_start_io_direct+0x63/0x70
nfs_file_direct_read+0x1e0/0x250
nfs_file_read+0x90/0xc0
For now this just implements a simple check for the _PAGE_RW bit similar
to pmd_write. However, this implies that the gup-slow-path check is
missing the extra checks that the gup-fast-path performs with
pud_access_permitted. Later patches will align all checks to use the
'access_permitted' helper if the architecture provides it. Note that the
generic 'access_permitted' helper fallback is the simple _PAGE_RW check
on architectures that do not define the 'access_permitted' helper(s).
Cc: <stable@vger.kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Fixes: a00cc7d9dd93 ("mm, x86: add support for PUD-sized transparent hugepages")
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
arch/x86/include/asm/pgtable.h | 6 ++++++
include/asm-generic/pgtable.h | 9 +++++++++
include/linux/hugetlb.h | 8 --------
3 files changed, 15 insertions(+), 8 deletions(-)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index f735c3016325..5c396724fd0d 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1093,6 +1093,12 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
}
+#define __HAVE_ARCH_PUD_WRITE
+static inline int pud_write(pud_t pud)
+{
+ return pud_flags(pud) & _PAGE_RW;
+}
+
/*
* clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
*
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 757dc6ffc7ba..bd738624bd16 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -812,6 +812,15 @@ static inline int pmd_write(pmd_t pmd)
return 0;
}
#endif /* __HAVE_ARCH_PMD_WRITE */
+
+#ifndef __HAVE_ARCH_PUD_WRITE
+static inline int pud_write(pud_t pud)
+{
+ BUG();
+ return 0;
+}
+#endif /* __HAVE_ARCH_PUD_WRITE */
+
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index fbf5b31d47ee..82a25880714a 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -239,14 +239,6 @@ static inline int pgd_write(pgd_t pgd)
}
#endif
-#ifndef pud_write
-static inline int pud_write(pud_t pud)
-{
- BUG();
- return 0;
-}
-#endif
-
#define HUGETLB_ANON_FILE "anon_hugepage"
enum {
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 5+ messages in thread* [PATCH 2/4] mm: replace pud_write with pud_access_permitted in fault + gup paths
2017-11-11 0:44 [PATCH 0/4] fix device-dax pud crash and fixup {pte,pmd,pud}_write Dan Williams
2017-11-11 0:44 ` [PATCH 1/4] mm: fix device-dax pud write-faults triggered by get_user_pages() Dan Williams
@ 2017-11-11 0:44 ` Dan Williams
2017-11-11 0:44 ` [PATCH 3/4] mm: replace pmd_write with pmd_access_permitted " Dan Williams
2017-11-11 0:44 ` [PATCH 4/4] mm: replace pte_write with pte_access_permitted " Dan Williams
3 siblings, 0 replies; 5+ messages in thread
From: Dan Williams @ 2017-11-11 0:44 UTC (permalink / raw)
To: akpm
Cc: linux-nvdimm, linux-kernel, linux-mm, Dave Hansen,
David S. Miller, Kirill A. Shutemov
The 'access_permitted' helper is used in the gup-fast path and goes
beyond the simple _PAGE_RW check to also:
* validate that the mapping is writable from a protection keys
standpoint
* validate that the pte has _PAGE_USER set since all fault paths where
pud_write is must be referencing user-memory.
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
arch/sparc/mm/gup.c | 2 +-
mm/huge_memory.c | 2 +-
mm/memory.c | 2 +-
3 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index 5335ba3c850e..5ae2d0a01a70 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -114,7 +114,7 @@ static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr,
if (!(pud_val(pud) & _PAGE_VALID))
return 0;
- if (write && !pud_write(pud))
+ if (!pud_access_permitted(pud, write))
return 0;
refs = 0;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1981ed697dab..1e4e11275856 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1022,7 +1022,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
assert_spin_locked(pud_lockptr(mm, pud));
- if (flags & FOLL_WRITE && !pud_write(*pud))
+ if (!pud_access_permitted(*pud, flags & FOLL_WRITE))
return NULL;
if (pud_present(*pud) && pud_devmap(*pud))
diff --git a/mm/memory.c b/mm/memory.c
index a728bed16c20..64f86beadcca 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3987,7 +3987,7 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
/* NUMA case for anonymous PUDs would go here */
- if (dirty && !pud_write(orig_pud)) {
+ if (dirty && !pud_access_permitted(orig_pud, WRITE)) {
ret = wp_huge_pud(&vmf, orig_pud);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 5+ messages in thread* [PATCH 3/4] mm: replace pmd_write with pmd_access_permitted in fault + gup paths
2017-11-11 0:44 [PATCH 0/4] fix device-dax pud crash and fixup {pte,pmd,pud}_write Dan Williams
2017-11-11 0:44 ` [PATCH 1/4] mm: fix device-dax pud write-faults triggered by get_user_pages() Dan Williams
2017-11-11 0:44 ` [PATCH 2/4] mm: replace pud_write with pud_access_permitted in fault + gup paths Dan Williams
@ 2017-11-11 0:44 ` Dan Williams
2017-11-11 0:44 ` [PATCH 4/4] mm: replace pte_write with pte_access_permitted " Dan Williams
3 siblings, 0 replies; 5+ messages in thread
From: Dan Williams @ 2017-11-11 0:44 UTC (permalink / raw)
To: akpm
Cc: linux-nvdimm, linux-kernel, linux-mm, Dave Hansen,
Jérôme Glisse, Kirill A. Shutemov
The 'access_permitted' helper is used in the gup-fast path and goes
beyond the simple _PAGE_RW check to also:
* validate that the mapping is writable from a protection keys
standpoint
* validate that the pte has _PAGE_USER set since all fault paths where
pmd_write is must be referencing user-memory.
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: "JA(C)rA'me Glisse" <jglisse@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
arch/sparc/mm/gup.c | 2 +-
fs/dax.c | 3 ++-
mm/hmm.c | 4 ++--
mm/huge_memory.c | 4 ++--
mm/memory.c | 2 +-
5 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
index 5ae2d0a01a70..33c0f8bb0f33 100644
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -75,7 +75,7 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
if (!(pmd_val(pmd) & _PAGE_VALID))
return 0;
- if (write && !pmd_write(pmd))
+ if (!pmd_access_permitted(pmd, write))
return 0;
refs = 0;
diff --git a/fs/dax.c b/fs/dax.c
index f001d8c72a06..3cc40eebbb9e 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -620,7 +620,8 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
if (pfn != pmd_pfn(*pmdp))
goto unlock_pmd;
- if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp))
+ if (!pmd_dirty(*pmdp)
+ && !pmd_access_permitted(*pmdp, WRITE))
goto unlock_pmd;
flush_cache_page(vma, address, pfn);
diff --git a/mm/hmm.c b/mm/hmm.c
index a88a847bccba..cbdd47bf6a48 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -391,11 +391,11 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
if (pmd_protnone(pmd))
return hmm_vma_walk_clear(start, end, walk);
- if (write_fault && !pmd_write(pmd))
+ if (!pmd_access_permitted(pmd, write_fault))
return hmm_vma_walk_clear(start, end, walk);
pfn = pmd_pfn(pmd) + pte_index(addr);
- flag |= pmd_write(pmd) ? HMM_PFN_WRITE : 0;
+ flag |= pmd_access_permitted(pmd, WRITE) ? HMM_PFN_WRITE : 0;
for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
pfns[i] = hmm_pfn_t_from_pfn(pfn) | flag;
return 0;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1e4e11275856..411ba3ba45f8 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -875,7 +875,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
*/
WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set");
- if (flags & FOLL_WRITE && !pmd_write(*pmd))
+ if (!pmd_access_permitted(*pmd, flags & FOLL_WRITE))
return NULL;
if (pmd_present(*pmd) && pmd_devmap(*pmd))
@@ -1379,7 +1379,7 @@ int do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
*/
static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
{
- return pmd_write(pmd) ||
+ return pmd_access_permitted(pmd, WRITE) ||
((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
}
diff --git a/mm/memory.c b/mm/memory.c
index 64f86beadcca..157fd4320bb3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4020,7 +4020,7 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
if (pmd_protnone(orig_pmd) && vma_is_accessible(vma))
return do_huge_pmd_numa_page(&vmf, orig_pmd);
- if (dirty && !pmd_write(orig_pmd)) {
+ if (dirty && !pmd_access_permitted(orig_pmd, WRITE)) {
ret = wp_huge_pmd(&vmf, orig_pmd);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 5+ messages in thread* [PATCH 4/4] mm: replace pte_write with pte_access_permitted in fault + gup paths
2017-11-11 0:44 [PATCH 0/4] fix device-dax pud crash and fixup {pte,pmd,pud}_write Dan Williams
` (2 preceding siblings ...)
2017-11-11 0:44 ` [PATCH 3/4] mm: replace pmd_write with pmd_access_permitted " Dan Williams
@ 2017-11-11 0:44 ` Dan Williams
3 siblings, 0 replies; 5+ messages in thread
From: Dan Williams @ 2017-11-11 0:44 UTC (permalink / raw)
To: akpm
Cc: linux-nvdimm, linux-kernel, linux-mm, Dave Hansen,
Jérôme Glisse, Kirill A. Shutemov
The 'access_permitted' helper is used in the gup-fast path and goes
beyond the simple _PAGE_RW check to also:
* validate that the mapping is writable from a protection keys
standpoint
* validate that the pte has _PAGE_USER set since all fault paths where
pte_write is must be referencing user-memory.
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: "JA(C)rA'me Glisse" <jglisse@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
mm/gup.c | 2 +-
mm/hmm.c | 4 ++--
mm/memory.c | 4 ++--
3 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/mm/gup.c b/mm/gup.c
index b2b4d4263768..bb6542c47b08 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -66,7 +66,7 @@ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
*/
static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
{
- return pte_write(pte) ||
+ return pte_access_permitted(pte, WRITE) ||
((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
}
diff --git a/mm/hmm.c b/mm/hmm.c
index cbdd47bf6a48..3d2e49fd851a 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -456,11 +456,11 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
continue;
}
- if (write_fault && !pte_write(pte))
+ if (!pte_access_permitted(pte, write_fault))
goto fault;
pfns[i] = hmm_pfn_t_from_pfn(pte_pfn(pte)) | flag;
- pfns[i] |= pte_write(pte) ? HMM_PFN_WRITE : 0;
+ pfns[i] |= pte_access_permitted(pte, WRITE) ? HMM_PFN_WRITE : 0;
continue;
fault:
diff --git a/mm/memory.c b/mm/memory.c
index 157fd4320bb3..a8cbc2c3e3c9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3922,7 +3922,7 @@ static int handle_pte_fault(struct vm_fault *vmf)
if (unlikely(!pte_same(*vmf->pte, entry)))
goto unlock;
if (vmf->flags & FAULT_FLAG_WRITE) {
- if (!pte_write(entry))
+ if (!pte_access_permitted(entry, WRITE))
return do_wp_page(vmf);
entry = pte_mkdirty(entry);
}
@@ -4308,7 +4308,7 @@ int follow_phys(struct vm_area_struct *vma,
goto out;
pte = *ptep;
- if ((flags & FOLL_WRITE) && !pte_write(pte))
+ if (!pte_access_permitted(pte, flags & FOLL_WRITE))
goto unlock;
*prot = pgprot_val(pte_pgprot(pte));
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply [flat|nested] 5+ messages in thread