[PATCH v7 01/12] Add get_user_pages() variant that fails if major fault is required.
From: Gleb Natapov g...@redhat.com
This patch add get_user_pages() variant that only succeeds if getting
a reference to a page doesn't require major fault.
Reviewed-by: Rik van Riel r...@redhat.com
Signed-off-by: Gleb Natapov g...@redhat.com
---
fs/ncpfs/mmap.c|2 ++
include/linux/mm.h |5 +
mm/filemap.c |3 +++
mm/memory.c| 31 ---
mm/shmem.c |8 +++-
5 files changed, 45 insertions(+), 4 deletions(-)
diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c
index 56f5b3a..b9c4f36 100644
--- a/fs/ncpfs/mmap.c
+++ b/fs/ncpfs/mmap.c
@@ -39,6 +39,8 @@ static int ncp_file_mmap_fault(struct vm_area_struct *area,
int bufsize;
int pos; /* XXX: loff_t ? */
+ if (vmf-flags FAULT_FLAG_MINOR)
+ return VM_FAULT_MAJOR | VM_FAULT_ERROR;
/*
* ncpfs has nothing against high pages as long
* as recvmsg and memset works on it
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 74949fb..da32900 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -144,6 +144,7 @@ extern pgprot_t protection_map[16];
#define FAULT_FLAG_WRITE 0x01/* Fault was a write access */
#define FAULT_FLAG_NONLINEAR 0x02/* Fault was via a nonlinear mapping */
#define FAULT_FLAG_MKWRITE 0x04/* Fault was mkwrite of existing pte */
+#define FAULT_FLAG_MINOR 0x08/* Do only minor fault */
/*
* This interface is used by x86 PAT code to identify a pfn mapping that is
@@ -848,6 +849,9 @@ extern int access_process_vm(struct task_struct *tsk,
unsigned long addr, void *
int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, int nr_pages, int write, int force,
struct page **pages, struct vm_area_struct **vmas);
+int get_user_pages_noio(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, int nr_pages, int write, int force,
+ struct page **pages, struct vm_area_struct **vmas);
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages);
struct page *get_dump_page(unsigned long addr);
@@ -1394,6 +1398,7 @@ struct page *follow_page(struct vm_area_struct *,
unsigned long address,
#define FOLL_GET 0x04/* do get_page on page */
#define FOLL_DUMP 0x08/* give error on hole if it would be zero */
#define FOLL_FORCE 0x10/* get_user_pages read/write w/o permission */
+#define FOLL_MINOR 0x20/* do only minor page faults */
typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
diff --git a/mm/filemap.c b/mm/filemap.c
index 3d4df44..ef28b6d 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1548,6 +1548,9 @@ int filemap_fault(struct vm_area_struct *vma, struct
vm_fault *vmf)
goto no_cached_page;
}
} else {
+ if (vmf-flags FAULT_FLAG_MINOR)
+ return VM_FAULT_MAJOR | VM_FAULT_ERROR;
+
/* No page in the page cache at all */
do_sync_mmap_readahead(vma, ra, file, offset);
count_vm_event(PGMAJFAULT);
diff --git a/mm/memory.c b/mm/memory.c
index 0e18b4d..b221458 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1441,10 +1441,13 @@ int __get_user_pages(struct task_struct *tsk, struct
mm_struct *mm,
cond_resched();
while (!(page = follow_page(vma, start, foll_flags))) {
int ret;
+ unsigned int fault_fl =
+ ((foll_flags FOLL_WRITE) ?
+ FAULT_FLAG_WRITE : 0) |
+ ((foll_flags FOLL_MINOR) ?
+ FAULT_FLAG_MINOR : 0);
- ret = handle_mm_fault(mm, vma, start,
- (foll_flags FOLL_WRITE) ?
- FAULT_FLAG_WRITE : 0);
+ ret = handle_mm_fault(mm, vma, start, fault_fl);
if (ret VM_FAULT_ERROR) {
if (ret VM_FAULT_OOM)
@@ -1452,6 +1455,8 @@ int __get_user_pages(struct task_struct *tsk, struct
mm_struct *mm,
if (ret
(VM_FAULT_HWPOISON|VM_FAULT_SIGBUS))
return i ? i : -EFAULT;
+ else if (ret VM_FAULT_MAJOR)
+ return i ? i : -EFAULT;
BUG();
}
if (ret VM_FAULT_MAJOR)
@@ -1562,6 +1567,23 @@ int get_user_pages(struct
[PATCH v7 01/12] Add get_user_pages() variant that fails if major fault is required.
This patch add get_user_pages() variant that only succeeds if getting
a reference to a page doesn't require major fault.
Reviewed-by: Rik van Riel r...@redhat.com
Signed-off-by: Gleb Natapov g...@redhat.com
---
fs/ncpfs/mmap.c|2 ++
include/linux/mm.h |5 +
mm/filemap.c |3 +++
mm/memory.c| 31 ---
mm/shmem.c |8 +++-
5 files changed, 45 insertions(+), 4 deletions(-)
diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c
index 56f5b3a..b9c4f36 100644
--- a/fs/ncpfs/mmap.c
+++ b/fs/ncpfs/mmap.c
@@ -39,6 +39,8 @@ static int ncp_file_mmap_fault(struct vm_area_struct *area,
int bufsize;
int pos; /* XXX: loff_t ? */
+ if (vmf-flags FAULT_FLAG_MINOR)
+ return VM_FAULT_MAJOR | VM_FAULT_ERROR;
/*
* ncpfs has nothing against high pages as long
* as recvmsg and memset works on it
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 74949fb..da32900 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -144,6 +144,7 @@ extern pgprot_t protection_map[16];
#define FAULT_FLAG_WRITE 0x01/* Fault was a write access */
#define FAULT_FLAG_NONLINEAR 0x02/* Fault was via a nonlinear mapping */
#define FAULT_FLAG_MKWRITE 0x04/* Fault was mkwrite of existing pte */
+#define FAULT_FLAG_MINOR 0x08/* Do only minor fault */
/*
* This interface is used by x86 PAT code to identify a pfn mapping that is
@@ -848,6 +849,9 @@ extern int access_process_vm(struct task_struct *tsk,
unsigned long addr, void *
int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
unsigned long start, int nr_pages, int write, int force,
struct page **pages, struct vm_area_struct **vmas);
+int get_user_pages_noio(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long start, int nr_pages, int write, int force,
+ struct page **pages, struct vm_area_struct **vmas);
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages);
struct page *get_dump_page(unsigned long addr);
@@ -1394,6 +1398,7 @@ struct page *follow_page(struct vm_area_struct *,
unsigned long address,
#define FOLL_GET 0x04/* do get_page on page */
#define FOLL_DUMP 0x08/* give error on hole if it would be zero */
#define FOLL_FORCE 0x10/* get_user_pages read/write w/o permission */
+#define FOLL_MINOR 0x20/* do only minor page faults */
typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
diff --git a/mm/filemap.c b/mm/filemap.c
index 3d4df44..ef28b6d 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1548,6 +1548,9 @@ int filemap_fault(struct vm_area_struct *vma, struct
vm_fault *vmf)
goto no_cached_page;
}
} else {
+ if (vmf-flags FAULT_FLAG_MINOR)
+ return VM_FAULT_MAJOR | VM_FAULT_ERROR;
+
/* No page in the page cache at all */
do_sync_mmap_readahead(vma, ra, file, offset);
count_vm_event(PGMAJFAULT);
diff --git a/mm/memory.c b/mm/memory.c
index 0e18b4d..b221458 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1441,10 +1441,13 @@ int __get_user_pages(struct task_struct *tsk, struct
mm_struct *mm,
cond_resched();
while (!(page = follow_page(vma, start, foll_flags))) {
int ret;
+ unsigned int fault_fl =
+ ((foll_flags FOLL_WRITE) ?
+ FAULT_FLAG_WRITE : 0) |
+ ((foll_flags FOLL_MINOR) ?
+ FAULT_FLAG_MINOR : 0);
- ret = handle_mm_fault(mm, vma, start,
- (foll_flags FOLL_WRITE) ?
- FAULT_FLAG_WRITE : 0);
+ ret = handle_mm_fault(mm, vma, start, fault_fl);
if (ret VM_FAULT_ERROR) {
if (ret VM_FAULT_OOM)
@@ -1452,6 +1455,8 @@ int __get_user_pages(struct task_struct *tsk, struct
mm_struct *mm,
if (ret
(VM_FAULT_HWPOISON|VM_FAULT_SIGBUS))
return i ? i : -EFAULT;
+ else if (ret VM_FAULT_MAJOR)
+ return i ? i : -EFAULT;
BUG();
}
if (ret VM_FAULT_MAJOR)
@@ -1562,6 +1567,23 @@ int get_user_pages(struct task_struct *tsk, struct
mm_struct
