The patch titled aio: fix the compat vectored operations has been added to the -mm tree. Its filename is aio-fix-the-compat-vectored-operations.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find out what to do about this The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ Subject: aio: fix the compat vectored operations From: Jeff Moyer <jmoyer@xxxxxxxxxx> The aio compat code was not converting the struct iovecs from 32bit to 64bit pointers, causing either EINVAL to be returned from io_getevents, or EFAULT as the result of the I/O. This patch passes a compat flag to io_submit to signal that pointer conversion is necessary for a given iocb array. A variant of this was tested by Michael Tokarev. I have also updated the libaio test harness to exercise this code path with good success. Further, I grabbed a copy of ltp and ran the testcases/kernel/syscall/readv and writev tests there (compiled with -m32 on my 64bit system). All seems happy, but extra eyes on this would be welcome. Signed-off-by: Jeff Moyer <jmoyer@xxxxxxxxxx> Reported-by: Michael Tokarev <mjt@xxxxxxxxxx> Cc: Zach Brown <zach.brown@xxxxxxxxxx> Cc: <stable@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- fs/aio.c | 63 ++++++++++++++++++++++++++---------------- fs/compat.c | 2 - include/linux/aio.h | 5 +++ 3 files changed, 45 insertions(+), 25 deletions(-) diff -puN fs/aio.c~aio-fix-the-compat-vectored-operations fs/aio.c --- a/fs/aio.c~aio-fix-the-compat-vectored-operations +++ a/fs/aio.c @@ -36,6 +36,7 @@ #include <linux/blkdev.h> #include <linux/mempool.h> #include <linux/hash.h> +#include <linux/compat.h> #include <asm/kmap_types.h> #include <asm/uaccess.h> @@ -1384,13 +1385,20 @@ static ssize_t aio_fsync(struct kiocb *i return ret; } -static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb) +static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb, bool compat) { ssize_t ret; - ret = rw_copy_check_uvector(type, (struct iovec __user *)kiocb->ki_buf, - kiocb->ki_nbytes, 1, - &kiocb->ki_inline_vec, &kiocb->ki_iovec); + if (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); + else + ret = rw_copy_check_uvector(type, + (struct iovec __user *)kiocb->ki_buf, + kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec, + &kiocb->ki_iovec); if (ret < 0) goto out; @@ -1420,7 +1428,7 @@ static ssize_t aio_setup_single_vector(s * Performs the initial checks and aio retry method * setup for the kiocb at the time of io submission. */ -static ssize_t aio_setup_iocb(struct kiocb *kiocb) +static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat) { struct file *file = kiocb->ki_filp; ssize_t ret = 0; @@ -1469,7 +1477,7 @@ static ssize_t aio_setup_iocb(struct kio ret = security_file_permission(file, MAY_READ); if (unlikely(ret)) break; - ret = aio_setup_vectored_rw(READ, kiocb); + ret = aio_setup_vectored_rw(READ, kiocb, compat); if (ret) break; ret = -EINVAL; @@ -1483,7 +1491,7 @@ static ssize_t aio_setup_iocb(struct kio ret = security_file_permission(file, MAY_WRITE); if (unlikely(ret)) break; - ret = aio_setup_vectored_rw(WRITE, kiocb); + ret = aio_setup_vectored_rw(WRITE, kiocb, compat); if (ret) break; ret = -EINVAL; @@ -1548,7 +1556,8 @@ static void aio_batch_free(struct hlist_ } static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, - struct iocb *iocb, struct hlist_head *batch_hash) + struct iocb *iocb, struct hlist_head *batch_hash, + bool compat) { struct kiocb *req; struct file *file; @@ -1609,7 +1618,7 @@ static int io_submit_one(struct kioctx * req->ki_left = req->ki_nbytes = iocb->aio_nbytes; req->ki_opcode = iocb->aio_lio_opcode; - ret = aio_setup_iocb(req); + ret = aio_setup_iocb(req, compat); if (ret) goto out_put_req; @@ -1637,20 +1646,8 @@ out_put_req: return ret; } -/* sys_io_submit: - * Queue the nr iocbs pointed to by iocbpp for processing. Returns - * the number of iocbs queued. May return -EINVAL if the aio_context - * specified by ctx_id is invalid, if nr is < 0, if the iocb at - * *iocbpp[0] is not properly initialized, if the operation specified - * is invalid for the file descriptor in the iocb. May fail with - * -EFAULT if any of the data structures point to invalid data. May - * fail with -EBADF if the file descriptor specified in the first - * iocb is invalid. May fail with -EAGAIN if insufficient resources - * are available to queue any iocbs. Will return 0 if nr is 0. Will - * fail with -ENOSYS if not implemented. - */ -SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr, - struct iocb __user * __user *, iocbpp) +long do_io_submit(aio_context_t ctx_id, long nr, + struct iocb __user *__user * iocbpp, bool compat) { struct kioctx *ctx; long ret = 0; @@ -1687,7 +1684,7 @@ SYSCALL_DEFINE3(io_submit, aio_context_t break; } - ret = io_submit_one(ctx, user_iocb, &tmp, batch_hash); + ret = io_submit_one(ctx, user_iocb, &tmp, batch_hash, compat); if (ret) break; } @@ -1697,6 +1694,24 @@ SYSCALL_DEFINE3(io_submit, aio_context_t return i ? i : ret; } +/* sys_io_submit: + * Queue the nr iocbs pointed to by iocbpp for processing. Returns + * the number of iocbs queued. May return -EINVAL if the aio_context + * specified by ctx_id is invalid, if nr is < 0, if the iocb at + * *iocbpp[0] is not properly initialized, if the operation specified + * is invalid for the file descriptor in the iocb. May fail with + * -EFAULT if any of the data structures point to invalid data. May + * fail with -EBADF if the file descriptor specified in the first + * iocb is invalid. May fail with -EAGAIN if insufficient resources + * are available to queue any iocbs. Will return 0 if nr is 0. Will + * fail with -ENOSYS if not implemented. + */ +SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr, + struct iocb __user * __user *, iocbpp) +{ + return do_io_submit(ctx_id, nr, iocbpp, 0); +} + /* lookup_kiocb * Finds a given iocb for cancellation. */ diff -puN fs/compat.c~aio-fix-the-compat-vectored-operations fs/compat.c --- a/fs/compat.c~aio-fix-the-compat-vectored-operations +++ a/fs/compat.c @@ -673,7 +673,7 @@ compat_sys_io_submit(aio_context_t ctx_i iocb64 = compat_alloc_user_space(nr * sizeof(*iocb64)); ret = copy_iocb(nr, iocb, iocb64); if (!ret) - ret = sys_io_submit(ctx_id, nr, iocb64); + ret = do_io_submit(ctx_id, nr, iocb64, 1); return ret; } diff -puN include/linux/aio.h~aio-fix-the-compat-vectored-operations include/linux/aio.h --- a/include/linux/aio.h~aio-fix-the-compat-vectored-operations +++ a/include/linux/aio.h @@ -212,6 +212,8 @@ extern void kick_iocb(struct kiocb *iocb extern int aio_complete(struct kiocb *iocb, long res, long res2); struct mm_struct; extern void exit_aio(struct mm_struct *mm); +extern long do_io_submit(aio_context_t ctx_id, long nr, + struct iocb __user *__user * iocbpp, bool compat); #else static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; } static inline int aio_put_req(struct kiocb *iocb) { return 0; } @@ -219,6 +221,9 @@ static inline void kick_iocb(struct kioc static inline int aio_complete(struct kiocb *iocb, long res, long res2) { return 0; } struct mm_struct; static inline void exit_aio(struct mm_struct *mm) { } +static inline long do_io_submit(aio_context_t ctx_id, long nr, + struct iocb __user * __user * iocbpp, + bool compat) { } #endif /* CONFIG_AIO */ static inline struct kiocb *list_kiocb(struct list_head *h) _ Patches currently in -mm which might be from jmoyer@xxxxxxxxxx are compat-factor-out-compat_rw_copy_check_uvector-from-compat_do_readv_writev.patch aio-fix-the-compat-vectored-operations.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html