Cross Memory Attach v4

PATCH In review Christopher Yeoh 2 participants 3 messages Jul 27, 2011

Subsystems (11)

Memory management x86 VFS PowerPC +7 more subsystems

lore

Share & tools

lore

Christopher Yeoh

author

2011-07-27 03:23 UTC #0 lore raw

PATCH 1/1 Cross Memory Attach v4

Hi Andrew,

Here's an updated version of the Cross Memory Attach patch. Changes since the v3:

- Adds x86_64 specific wire up
- Changes behaviour so process_vm_readv and process_vm_writev return the number of bytes successfully read or written even if an error occurs
- Adds more kernel doc interface comments
- rename of some internal functions (process_vm_rw_check_iovecs, process_vm_rw) so they make more sense.

Still need to do benchmarking to see if the optimisation for small copies using a local on-stack array in process_vm_rw_core is worth it.

Regards,

Chris

Signature · 1 line

[email protected]

arch/powerpc/include/asm/systbl.h +2 -0

index f6736b7..525db4b 100644
@@ -354,3 +354,5 @@ COMPAT_SYS_SPU(clock_adjtime)
 SYSCALL_SPU(syncfs)
 COMPAT_SYS_SPU(sendmmsg)
 SYSCALL_SPU(setns)
+COMPAT_SYS(process_vm_readv)
+COMPAT_SYS(process_vm_writev)

arch/powerpc/include/asm/unistd.h +3 -1

index b8b3f59..d3d1b5e 100644
@@ -373,10 +373,12 @@
 #define __NR_syncfs		348
 #define __NR_sendmmsg		349
 #define __NR_setns		350
+#define __NR_process_vm_readv	351
+#define __NR_process_vm_writev	352
 
 #ifdef __KERNEL__
 
-#define __NR_syscalls		351
+#define __NR_syscalls		353
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls

arch/x86/ia32/ia32entry.S +2 -0

index c1870dd..cde849f 100644
@@ -850,4 +850,6 @@ ia32_sys_call_table:
 	.quad sys_syncfs
 	.quad compat_sys_sendmmsg	/* 345 */
 	.quad sys_setns
+	.quad compat_sys_process_vm_readv
+	.quad compat_sys_process_vm_writev
 ia32_syscall_end:

arch/x86/include/asm/unistd_32.h +3 -1

index 593485b..599c77d 100644
@@ -352,10 +352,12 @@
 #define __NR_syncfs             344
 #define __NR_sendmmsg		345
 #define __NR_setns		346
+#define __NR_process_vm_readv	347
+#define __NR_process_vm_writev	348
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 347
+#define NR_syscalls 349
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR

arch/x86/include/asm/unistd_64.h +4 -0

index 705bf13..1f1d1ef 100644
@@ -681,6 +681,10 @@ __SYSCALL(__NR_syncfs, sys_syncfs)
 __SYSCALL(__NR_sendmmsg, sys_sendmmsg)
 #define __NR_setns				308
 __SYSCALL(__NR_setns, sys_setns)
+#define __NR_process_vm_readv			309
+__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv)
+#define __NR_process_vm_writev			310
+__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR

arch/x86/kernel/syscall_table_32.S +2 -0

index fbb0a04..ca0fe4d 100644
@@ -346,3 +346,5 @@ ENTRY(sys_call_table)
 	.long sys_syncfs
 	.long sys_sendmmsg		/* 345 */
 	.long sys_setns
+	.long sys_process_vm_readv
+	.long sys_process_vm_writev

fs/aio.c +2 -2

index e29ec48..632b235 100644
@@ -1387,13 +1387,13 @@ static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb, bool compat)
 		ret = compat_rw_copy_check_uvector(type,
 				(struct compat_iovec __user *)kiocb->ki_buf,
 				kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec,
-				&kiocb->ki_iovec);
+				&kiocb->ki_iovec, 1);
 	else
 #endif
 		ret = rw_copy_check_uvector(type,
 				(struct iovec __user *)kiocb->ki_buf,
 				kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec,
-				&kiocb->ki_iovec);
+				&kiocb->ki_iovec, 1);
 	if (ret < 0)
 		goto out;

fs/compat.c +4 -3

index 0ea0083..ec53ccc 100644
@@ -550,7 +550,7 @@ out:
 ssize_t compat_rw_copy_check_uvector(int type,
 		const struct compat_iovec __user *uvector, unsigned long nr_segs,
 		unsigned long fast_segs, struct iovec *fast_pointer,
-		struct iovec **ret_pointer)
+		struct iovec **ret_pointer, int check_access)
 {
 	compat_ssize_t tot_len;
 	struct iovec *iov = *ret_pointer = fast_pointer;

@@ -597,7 +597,8 @@ ssize_t compat_rw_copy_check_uvector(int type,
 		}
 		if (len < 0)	/* size_t not fitting in compat_ssize_t .. */
 			goto out;
-		if (!access_ok(vrfy_dir(type), compat_ptr(buf), len)) {
+		if (check_access &&
+		    !access_ok(vrfy_dir(type), compat_ptr(buf), len)) {
 			ret = -EFAULT;
 			goto out;
 		}

@@ -1111,7 +1112,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 		goto out;
 
 	tot_len = compat_rw_copy_check_uvector(type, uvector, nr_segs,
-					       UIO_FASTIOV, iovstack, &iov);
+					       UIO_FASTIOV, iovstack, &iov, 1);
 	if (tot_len == 0) {
 		ret = 0;
 		goto out;

fs/read_write.c +5 -3

index 5520f8a..b905826 100644
@@ -575,7 +575,8 @@ ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov,
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			      unsigned long nr_segs, unsigned long fast_segs,
 			      struct iovec *fast_pointer,
-			      struct iovec **ret_pointer)
+			      struct iovec **ret_pointer,
+			      int check_access)
 {
 	unsigned long seg;
 	ssize_t ret;

@@ -631,7 +632,8 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			ret = -EINVAL;
 			goto out;
 		}
-		if (unlikely(!access_ok(vrfy_dir(type), buf, len))) {
+		if (check_access
+		    && unlikely(!access_ok(vrfy_dir(type), buf, len))) {
 			ret = -EFAULT;
 			goto out;
 		}

@@ -663,7 +665,7 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	}
 
 	ret = rw_copy_check_uvector(type, uvector, nr_segs,
-			ARRAY_SIZE(iovstack), iovstack, &iov);
+				    ARRAY_SIZE(iovstack), iovstack, &iov, 1);
 	if (ret <= 0)
 		goto out;

include/linux/compat.h +2 -1

index 846bb17..1cc917a 100644
@@ -557,7 +557,8 @@ extern ssize_t compat_rw_copy_check_uvector(int type,
 		const struct compat_iovec __user *uvector,
 		unsigned long nr_segs,
 		unsigned long fast_segs, struct iovec *fast_pointer,
-		struct iovec **ret_pointer);
+		struct iovec **ret_pointer,
+		int check_access);
 
 extern void __user *compat_alloc_user_space(unsigned long len);

include/linux/fs.h +4 -3

index b5b9792..d97ffab 100644
@@ -1608,9 +1608,10 @@ struct inode_operations {
 struct seq_file;
 
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
-				unsigned long nr_segs, unsigned long fast_segs,
-				struct iovec *fast_pointer,
-				struct iovec **ret_pointer);
+			      unsigned long nr_segs, unsigned long fast_segs,
+			      struct iovec *fast_pointer,
+			      struct iovec **ret_pointer,
+			      int check_access);
 
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);

include/linux/syscalls.h +13 -0

index 8c03b98..0dc0809 100644
@@ -847,4 +847,17 @@ asmlinkage long sys_open_by_handle_at(int mountdirfd,
 				      struct file_handle __user *handle,
 				      int flags);
 asmlinkage long sys_setns(int fd, int nstype);
+asmlinkage long sys_process_vm_readv(pid_t pid,
+				     const struct iovec __user *lvec,
+				     unsigned long liovcnt,
+				     const struct iovec __user *rvec,
+				     unsigned long riovcnt,
+				     unsigned long flags);
+asmlinkage long sys_process_vm_writev(pid_t pid,
+				      const struct iovec __user *lvec,
+				      unsigned long liovcnt,
+				      const struct iovec __user *rvec,
+				      unsigned long riovcnt,
+				      unsigned long flags);
+
 #endif

kernel/sys_ni.c +4 -0

index 62cbc88..7a34e9f 100644
@@ -146,6 +146,10 @@ cond_syscall(sys_io_submit);
 cond_syscall(sys_io_cancel);
 cond_syscall(sys_io_getevents);
 cond_syscall(sys_syslog);
+cond_syscall(sys_process_vm_readv);
+cond_syscall(sys_process_vm_writev);
+cond_syscall(compat_sys_process_vm_readv);
+cond_syscall(compat_sys_process_vm_writev);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);

mm/Makefile +2 -1

index 836e416..50ec00e 100644
@@ -5,7 +5,8 @@
 mmu-y			:= nommu.o
 mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
-			   vmalloc.o pagewalk.o pgtable-generic.o
+			   vmalloc.o pagewalk.o pgtable-generic.o \
+			   process_vm_access.o
 
 obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   maccess.o page_alloc.o page-writeback.o \

mm/process_vm_access.c new file +482 -0

482 lines not on this page · raw message

security/keys/compat.c +1 -1

index 338b510..4c48e13 100644
@@ -38,7 +38,7 @@ long compat_keyctl_instantiate_key_iov(
 
 	ret = compat_rw_copy_check_uvector(WRITE, _payload_iov, ioc,
 					   ARRAY_SIZE(iovstack),
-					   iovstack, &iov);
+					   iovstack, &iov, 1);
 	if (ret < 0)
 		return ret;
 	if (ret == 0)

security/keys/keyctl.c +1 -1

index eca5191..0b3f5d7 100644
@@ -1065,7 +1065,7 @@ long keyctl_instantiate_key_iov(key_serial_t id,
 		goto no_payload;
 
 	ret = rw_copy_check_uvector(WRITE, _payload_iov, ioc,
-				    ARRAY_SIZE(iovstack), iovstack, &iov);
+				    ARRAY_SIZE(iovstack), iovstack, &iov, 1);
 	if (ret < 0)
 		return ret;
 	if (ret == 0)

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

Randy Dunlap

2011-07-27 04:55 UTC #1 lore raw

Quoted 13 lines · On Wed, 27 Jul 2011 12:53:42 +0930 Christopher Yeoh wrote:

Hi Andrew,
Here's an updated version of the Cross Memory Attach patch. Changes since the v3:
- Adds x86_64 specific wire up
- Changes behaviour so process_vm_readv and process_vm_writev return the number of bytes successfully read or written even if an error occurs
- Adds more kernel doc interface comments
- rename of some internal functions (process_vm_rw_check_iovecs, process_vm_rw) so they make more sense.

Quoted 2 lines

Still need to do benchmarking to see if the optimisation for small copies using a local on-stack array in process_vm_rw_core is worth it.

It's nice to include a diffstat so that people can get a quick patch summary and see what files are touched.

Quoted 1 line

diffstat -w 70 -p 1 cma-v4.patch

 arch/powerpc/include/asm/systbl.h  |    2 
 arch/powerpc/include/asm/unistd.h  |    4 
 arch/x86/ia32/ia32entry.S          |    2 
 arch/x86/include/asm/unistd_32.h   |    4 
 arch/x86/include/asm/unistd_64.h   |    4 
 arch/x86/kernel/syscall_table_32.S |    2 
 fs/aio.c                           |    4 
 fs/compat.c                        |    7 
 fs/read_write.c                    |    8 
 include/linux/compat.h             |    3 
 include/linux/fs.h                 |    7 
 include/linux/syscalls.h           |   13 
 kernel/sys_ni.c                    |    4 
 mm/Makefile                        |    3 
 mm/process_vm_access.c             |  482 +++++++++++++++++++++++++++
 security/keys/compat.c             |    2 
 security/keys/keyctl.c             |    2 
 17 files changed, 536 insertions(+), 17 deletions(-)

mm/process_vm_access.c line 4

Quoted 10 lines

mm/process_vm_access.c new file +4 -0

new file mode 100644
index 0000000..a0e3cfb
@@ -0,0 +1,482 @@
+/*
+ *  linux/mm/process_vm_access.c
+ *
+ *  Copyright (C) 2010-2011 Christopher Yeoh <[email protected]>, IBM Corp.

Any license for this file? maybe GPL?

Quoted 5 lines

mm/process_vm_access.c new file +5 -0

+ */
+
+#include <linux/mm.h>
+#include <linux/uio.h>
+#include <linux/sched.h>

mm/process_vm_access.c line 19

Quoted 10 lines

mm/process_vm_access.c new file +10 -0

+#include <linux/highmem.h>
+#include <linux/ptrace.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+
+#ifdef CONFIG_COMPAT
+#include <linux/compat.h>
+#endif
+
+/*

Any problem with using
/**
so that these are proper kernel-doc notation? (for all [4] functions here that have such notation)

Quoted 21 lines

mm/process_vm_access.c new file +21 -0

+ * process_vm_rw_pages - read/write pages from task specified
+ * @task: task to read/write from
+ * @mm: mm for task
+ * @process_pages: struct pages area that can store at least
+ *  nr_pages_to_copy struct page pointers
+ * @pa: address of page in task to start copying from/to
+ * @start_offset: offset in page to start copying from/to
+ * @len: number of bytes to copy
+ * @lvec: iovec array specifying where to copy to/from
+ * @lvec_cnt: number of elements in iovec array
+ * @lvec_current: index in iovec array we are up to
+ * @lvec_offset: offset in bytes from current iovec iov_base we are up to
+ * @vm_write: 0 means copy from, 1 means copy to
+ * @nr_pages_to_copy: number of pages to copy
+ * @bytes_copied: returns number of bytes successfully copied
+ * Returns 0 on success, error code otherwise
+ */
+static int process_vm_rw_pages(struct task_struct *task,
+			       struct mm_struct *mm,
+			       struct page **process_pages,
+			       unsigned long pa,

mm/process_vm_access.c line 50

Quoted 10 lines

mm/process_vm_access.c new file +10 -0

+			       unsigned long start_offset,
+			       unsigned long len,
+			       const struct iovec *lvec,
+			       unsigned long lvec_cnt,
+			       unsigned long *lvec_current,
+			       size_t *lvec_offset,
+			       int vm_write,
+			       unsigned int nr_pages_to_copy,
+			       ssize_t *bytes_copied)
+{

---
~Randy
*** Remember to use Documentation/SubmitChecklist when testing your code *** --
To unsubscribe from this list: send the line "unsubscribe linux-man" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html

Christopher Yeoh

author

2011-07-27 14:49 UTC #2 lore raw

Re: [PATCH] Cross Memory Attach v4 (patch updated)

Quoted 15 lines · On Tue, 26 Jul 2011 21:55:54 -0700 Randy Dunlap <[email protected]> wrote:

Quoted 13 lines · On Wed, 27 Jul 2011 12:53:42 +0930 Christopher Yeoh wrote:
Hi Andrew,
Here's an updated version of the Cross Memory Attach patch. Changes since the v3:
- Adds x86_64 specific wire up
- Changes behaviour so process_vm_readv and process_vm_writev return the number of bytes successfully read or written even if an error occurs
- Adds more kernel doc interface comments
- rename of some internal functions (process_vm_rw_check_iovecs, process_vm_rw) so they make more sense.

Quoted 7 lines

Quoted 3 lines
Still need to do benchmarking to see if the optimisation for small copies using a local on-stack array in process_vm_rw_core is worth it.
It's nice to include a diffstat so that people can get a quick patch summary and see what files are touched.

Thanks. Updated patch below. Only changes are:
- Adds licence message
- Fixed kernel-doc comment format

Signed-off-by Chris Yeoh <[email protected]>

---
 arch/powerpc/include/asm/systbl.h  |    2 
 arch/powerpc/include/asm/unistd.h  |    4 
 arch/x86/ia32/ia32entry.S          |    2 
 arch/x86/include/asm/unistd_32.h   |    4 
 arch/x86/include/asm/unistd_64.h   |    4 
 arch/x86/kernel/syscall_table_32.S |    2 
 fs/aio.c                           |    4 
 fs/compat.c                        |    7 
 fs/read_write.c                    |    8 
 include/linux/compat.h             |    3 
 include/linux/fs.h                 |    7 
 include/linux/syscalls.h           |   13 
 kernel/sys_ni.c                    |    4 
 mm/Makefile                        |    3 
 mm/process_vm_access.c             |  487 +++++++++++++++++++++++++++++++++++++
 security/keys/compat.c             |    2 
 security/keys/keyctl.c             |    2 
 17 files changed, 541 insertions(+), 17 deletions(-)

arch/powerpc/include/asm/systbl.h +2 -0

index f6736b7..525db4b 100644
@@ -354,3 +354,5 @@ COMPAT_SYS_SPU(clock_adjtime)
 SYSCALL_SPU(syncfs)
 COMPAT_SYS_SPU(sendmmsg)
 SYSCALL_SPU(setns)
+COMPAT_SYS(process_vm_readv)
+COMPAT_SYS(process_vm_writev)

arch/powerpc/include/asm/unistd.h +3 -1

index b8b3f59..d3d1b5e 100644
@@ -373,10 +373,12 @@
 #define __NR_syncfs		348
 #define __NR_sendmmsg		349
 #define __NR_setns		350
+#define __NR_process_vm_readv	351
+#define __NR_process_vm_writev	352
 
 #ifdef __KERNEL__
 
-#define __NR_syscalls		351
+#define __NR_syscalls		353
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls

arch/x86/ia32/ia32entry.S +2 -0

index c1870dd..cde849f 100644
@@ -850,4 +850,6 @@ ia32_sys_call_table:
 	.quad sys_syncfs
 	.quad compat_sys_sendmmsg	/* 345 */
 	.quad sys_setns
+	.quad compat_sys_process_vm_readv
+	.quad compat_sys_process_vm_writev
 ia32_syscall_end:

arch/x86/include/asm/unistd_32.h +3 -1

index 593485b..599c77d 100644
@@ -352,10 +352,12 @@
 #define __NR_syncfs             344
 #define __NR_sendmmsg		345
 #define __NR_setns		346
+#define __NR_process_vm_readv	347
+#define __NR_process_vm_writev	348
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 347
+#define NR_syscalls 349
 
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR

arch/x86/include/asm/unistd_64.h +4 -0

index 705bf13..1f1d1ef 100644
@@ -681,6 +681,10 @@ __SYSCALL(__NR_syncfs, sys_syncfs)
 __SYSCALL(__NR_sendmmsg, sys_sendmmsg)
 #define __NR_setns				308
 __SYSCALL(__NR_setns, sys_setns)
+#define __NR_process_vm_readv			309
+__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv)
+#define __NR_process_vm_writev			310
+__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev)
 
 #ifndef __NO_STUBS
 #define __ARCH_WANT_OLD_READDIR

arch/x86/kernel/syscall_table_32.S +2 -0

index fbb0a04..ca0fe4d 100644
@@ -346,3 +346,5 @@ ENTRY(sys_call_table)
 	.long sys_syncfs
 	.long sys_sendmmsg		/* 345 */
 	.long sys_setns
+	.long sys_process_vm_readv
+	.long sys_process_vm_writev

fs/aio.c +2 -2

index e29ec48..632b235 100644
@@ -1387,13 +1387,13 @@ static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb, bool compat)
 		ret = compat_rw_copy_check_uvector(type,
 				(struct compat_iovec __user *)kiocb->ki_buf,
 				kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec,
-				&kiocb->ki_iovec);
+				&kiocb->ki_iovec, 1);
 	else
 #endif
 		ret = rw_copy_check_uvector(type,
 				(struct iovec __user *)kiocb->ki_buf,
 				kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec,
-				&kiocb->ki_iovec);
+				&kiocb->ki_iovec, 1);
 	if (ret < 0)
 		goto out;

fs/compat.c +4 -3

index 0ea0083..ec53ccc 100644
@@ -550,7 +550,7 @@ out:
 ssize_t compat_rw_copy_check_uvector(int type,
 		const struct compat_iovec __user *uvector, unsigned long nr_segs,
 		unsigned long fast_segs, struct iovec *fast_pointer,
-		struct iovec **ret_pointer)
+		struct iovec **ret_pointer, int check_access)
 {
 	compat_ssize_t tot_len;
 	struct iovec *iov = *ret_pointer = fast_pointer;

@@ -597,7 +597,8 @@ ssize_t compat_rw_copy_check_uvector(int type,
 		}
 		if (len < 0)	/* size_t not fitting in compat_ssize_t .. */
 			goto out;
-		if (!access_ok(vrfy_dir(type), compat_ptr(buf), len)) {
+		if (check_access &&
+		    !access_ok(vrfy_dir(type), compat_ptr(buf), len)) {
 			ret = -EFAULT;
 			goto out;
 		}

@@ -1111,7 +1112,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 		goto out;
 
 	tot_len = compat_rw_copy_check_uvector(type, uvector, nr_segs,
-					       UIO_FASTIOV, iovstack, &iov);
+					       UIO_FASTIOV, iovstack, &iov, 1);
 	if (tot_len == 0) {
 		ret = 0;
 		goto out;

fs/read_write.c +5 -3

index 5520f8a..b905826 100644
@@ -575,7 +575,8 @@ ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov,
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			      unsigned long nr_segs, unsigned long fast_segs,
 			      struct iovec *fast_pointer,
-			      struct iovec **ret_pointer)
+			      struct iovec **ret_pointer,
+			      int check_access)
 {
 	unsigned long seg;
 	ssize_t ret;

@@ -631,7 +632,8 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			ret = -EINVAL;
 			goto out;
 		}
-		if (unlikely(!access_ok(vrfy_dir(type), buf, len))) {
+		if (check_access
+		    && unlikely(!access_ok(vrfy_dir(type), buf, len))) {
 			ret = -EFAULT;
 			goto out;
 		}

@@ -663,7 +665,7 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	}
 
 	ret = rw_copy_check_uvector(type, uvector, nr_segs,
-			ARRAY_SIZE(iovstack), iovstack, &iov);
+				    ARRAY_SIZE(iovstack), iovstack, &iov, 1);
 	if (ret <= 0)
 		goto out;

include/linux/compat.h +2 -1

index 846bb17..1cc917a 100644
@@ -557,7 +557,8 @@ extern ssize_t compat_rw_copy_check_uvector(int type,
 		const struct compat_iovec __user *uvector,
 		unsigned long nr_segs,
 		unsigned long fast_segs, struct iovec *fast_pointer,
-		struct iovec **ret_pointer);
+		struct iovec **ret_pointer,
+		int check_access);
 
 extern void __user *compat_alloc_user_space(unsigned long len);

include/linux/fs.h +4 -3

index b5b9792..d97ffab 100644
@@ -1608,9 +1608,10 @@ struct inode_operations {
 struct seq_file;
 
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
-				unsigned long nr_segs, unsigned long fast_segs,
-				struct iovec *fast_pointer,
-				struct iovec **ret_pointer);
+			      unsigned long nr_segs, unsigned long fast_segs,
+			      struct iovec *fast_pointer,
+			      struct iovec **ret_pointer,
+			      int check_access);
 
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);

include/linux/syscalls.h +13 -0

index 8c03b98..0dc0809 100644
@@ -847,4 +847,17 @@ asmlinkage long sys_open_by_handle_at(int mountdirfd,
 				      struct file_handle __user *handle,
 				      int flags);
 asmlinkage long sys_setns(int fd, int nstype);
+asmlinkage long sys_process_vm_readv(pid_t pid,
+				     const struct iovec __user *lvec,
+				     unsigned long liovcnt,
+				     const struct iovec __user *rvec,
+				     unsigned long riovcnt,
+				     unsigned long flags);
+asmlinkage long sys_process_vm_writev(pid_t pid,
+				      const struct iovec __user *lvec,
+				      unsigned long liovcnt,
+				      const struct iovec __user *rvec,
+				      unsigned long riovcnt,
+				      unsigned long flags);
+
 #endif

kernel/sys_ni.c +4 -0

index 62cbc88..7a34e9f 100644
@@ -146,6 +146,10 @@ cond_syscall(sys_io_submit);
 cond_syscall(sys_io_cancel);
 cond_syscall(sys_io_getevents);
 cond_syscall(sys_syslog);
+cond_syscall(sys_process_vm_readv);
+cond_syscall(sys_process_vm_writev);
+cond_syscall(compat_sys_process_vm_readv);
+cond_syscall(compat_sys_process_vm_writev);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);

mm/Makefile +2 -1

index 836e416..50ec00e 100644
@@ -5,7 +5,8 @@
 mmu-y			:= nommu.o
 mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
-			   vmalloc.o pagewalk.o pgtable-generic.o
+			   vmalloc.o pagewalk.o pgtable-generic.o \
+			   process_vm_access.o
 
 obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   maccess.o page_alloc.o page-writeback.o \

mm/process_vm_access.c new file +487 -0

487 lines not on this page · raw message

security/keys/compat.c +1 -1

index 338b510..4c48e13 100644
@@ -38,7 +38,7 @@ long compat_keyctl_instantiate_key_iov(
 
 	ret = compat_rw_copy_check_uvector(WRITE, _payload_iov, ioc,
 					   ARRAY_SIZE(iovstack),
-					   iovstack, &iov);
+					   iovstack, &iov, 1);
 	if (ret < 0)
 		return ret;
 	if (ret == 0)

security/keys/keyctl.c +1 -1

index eca5191..0b3f5d7 100644
@@ -1065,7 +1065,7 @@ long keyctl_instantiate_key_iov(key_serial_t id,
 		goto no_payload;
 
 	ret = rw_copy_check_uvector(WRITE, _payload_iov, ioc,
-				    ARRAY_SIZE(iovstack), iovstack, &iov);
+				    ARRAY_SIZE(iovstack), iovstack, &iov, 1);
 	if (ret < 0)
 		return ret;
 	if (ret == 0)

Signature · 8 lines

[email protected]

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to [email protected].  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>