OpenCloudOS-Kernel/include/linux/uio.h

295 lines
8.8 KiB
C
Raw Normal View History

/*
* Berkeley style UIO structures - Alan Cox 1994.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef __LINUX_UIO_H
#define __LINUX_UIO_H
#include <linux/kernel.h>
#include <linux/thread_info.h>
#include <crypto/hash.h>
#include <uapi/linux/uio.h>
struct page;
struct pipe_inode_info;
struct kvec {
void *iov_base; /* and that should *never* hold a userland pointer */
size_t iov_len;
};
enum iter_type {
ITER_IOVEC = 0,
ITER_KVEC = 2,
ITER_BVEC = 4,
ITER_PIPE = 8,
ITER_DISCARD = 16,
};
struct iov_iter {
unsigned int type;
size_t iov_offset;
size_t count;
union {
const struct iovec *iov;
const struct kvec *kvec;
const struct bio_vec *bvec;
struct pipe_inode_info *pipe;
};
union {
unsigned long nr_segs;
struct {
int idx;
int start_idx;
};
};
};
static inline enum iter_type iov_iter_type(const struct iov_iter *i)
{
return i->type & ~(READ | WRITE);
}
static inline bool iter_is_iovec(const struct iov_iter *i)
{
return iov_iter_type(i) == ITER_IOVEC;
}
static inline bool iov_iter_is_kvec(const struct iov_iter *i)
{
return iov_iter_type(i) == ITER_KVEC;
}
static inline bool iov_iter_is_bvec(const struct iov_iter *i)
{
return iov_iter_type(i) == ITER_BVEC;
}
static inline bool iov_iter_is_pipe(const struct iov_iter *i)
{
return iov_iter_type(i) == ITER_PIPE;
}
static inline bool iov_iter_is_discard(const struct iov_iter *i)
{
return iov_iter_type(i) == ITER_DISCARD;
}
static inline unsigned char iov_iter_rw(const struct iov_iter *i)
{
return i->type & (READ | WRITE);
}
/*
* Total number of bytes covered by an iovec.
*
* NOTE that it is not safe to use this function until all the iovec's
* segment lengths have been validated. Because the individual lengths can
* overflow a size_t when added together.
*/
static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs)
{
unsigned long seg;
size_t ret = 0;
for (seg = 0; seg < nr_segs; seg++)
ret += iov[seg].iov_len;
return ret;
}
static inline struct iovec iov_iter_iovec(const struct iov_iter *iter)
{
return (struct iovec) {
.iov_base = iter->iov->iov_base + iter->iov_offset,
.iov_len = min(iter->count,
iter->iov->iov_len - iter->iov_offset),
};
}
#define iov_for_each(iov, iter, start) \
if (iov_iter_type(start) == ITER_IOVEC || \
iov_iter_type(start) == ITER_KVEC) \
for (iter = (start); \
(iter).count && \
((iov = iov_iter_iovec(&(iter))), 1); \
iov_iter_advance(&(iter), (iov).iov_len))
size_t iov_iter_copy_from_user_atomic(struct page *page,
struct iov_iter *i, unsigned long offset, size_t bytes);
void iov_iter_advance(struct iov_iter *i, size_t bytes);
void iov_iter_revert(struct iov_iter *i, size_t bytes);
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
size_t iov_iter_single_seg_count(const struct iov_iter *i);
size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i);
size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i);
size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);
bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i);
size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i);
bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i);
static __always_inline __must_check
size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
{
if (unlikely(!check_copy_size(addr, bytes, true)))
return 0;
else
return _copy_to_iter(addr, bytes, i);
}
static __always_inline __must_check
size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
{
if (unlikely(!check_copy_size(addr, bytes, false)))
return 0;
else
return _copy_from_iter(addr, bytes, i);
}
static __always_inline __must_check
bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i)
{
if (unlikely(!check_copy_size(addr, bytes, false)))
return false;
else
return _copy_from_iter_full(addr, bytes, i);
}
static __always_inline __must_check
size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
{
if (unlikely(!check_copy_size(addr, bytes, false)))
return 0;
else
return _copy_from_iter_nocache(addr, bytes, i);
}
static __always_inline __must_check
bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i)
{
if (unlikely(!check_copy_size(addr, bytes, false)))
return false;
else
return _copy_from_iter_full_nocache(addr, bytes, i);
}
x86, uaccess: introduce copy_from_iter_flushcache for pmem / cache-bypass operations The pmem driver has a need to transfer data with a persistent memory destination and be able to rely on the fact that the destination writes are not cached. It is sufficient for the writes to be flushed to a cpu-store-buffer (non-temporal / "movnt" in x86 terms), as we expect userspace to call fsync() to ensure data-writes have reached a power-fail-safe zone in the platform. The fsync() triggers a REQ_FUA or REQ_FLUSH to the pmem driver which will turn around and fence previous writes with an "sfence". Implement a __copy_from_user_inatomic_flushcache, memcpy_page_flushcache, and memcpy_flushcache, that guarantee that the destination buffer is not dirty in the cpu cache on completion. The new copy_from_iter_flushcache and sub-routines will be used to replace the "pmem api" (include/linux/pmem.h + arch/x86/include/asm/pmem.h). The availability of copy_from_iter_flushcache() and memcpy_flushcache() are gated by the CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE config symbol, and fallback to copy_from_iter_nocache() and plain memcpy() otherwise. This is meant to satisfy the concern from Linus that if a driver wants to do something beyond the normal nocache semantics it should be something private to that driver [1], and Al's concern that anything uaccess related belongs with the rest of the uaccess code [2]. The first consumer of this interface is a new 'copy_from_iter' dax operation so that pmem can inject cache maintenance operations without imposing this overhead on other dax-capable drivers. [1]: https://lists.01.org/pipermail/linux-nvdimm/2017-January/008364.html [2]: https://lists.01.org/pipermail/linux-nvdimm/2017-April/009942.html Cc: <x86@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Matthew Wilcox <mawilcox@microsoft.com> Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2017-05-30 03:22:50 +08:00
#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
/*
* Note, users like pmem that depend on the stricter semantics of
* copy_from_iter_flushcache() than copy_from_iter_nocache() must check for
* IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the
* destination is flushed from the cache on return.
*/
Merge branch 'uaccess-work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs Pull iov_iter hardening from Al Viro: "This is the iov_iter/uaccess/hardening pile. For one thing, it trims the inline part of copy_to_user/copy_from_user to the minimum that *does* need to be inlined - object size checks, basically. For another, it sanitizes the checks for iov_iter primitives. There are 4 groups of checks: access_ok(), might_fault(), object size and KASAN. - access_ok() had been verified by whoever had set the iov_iter up. However, that has happened in a function far away, so proving that there's no path to actual copying bypassing those checks is hard and proving that iov_iter has not been buggered in the meanwhile is also not pleasant. So we want those redone in actual copyin/copyout. - might_fault() is better off consolidated - we know whether it needs to be checked as soon as we enter iov_iter primitive and observe the iov_iter flavour. No need to wait until the copyin/copyout. The call chains are short enough to make sure we won't miss anything - in fact, it's more robust that way, since there are cases where we do e.g. forced fault-in before getting to copyin/copyout. It's not quite what we need to check (in particular, combination of iovec-backed and set_fs(KERNEL_DS) is almost certainly a bug, not a cause to skip checks), but that's for later series. For now let's keep might_fault(). - KASAN checks belong in copyin/copyout - at the same level where other iov_iter flavours would've hit them in memcpy(). - object size checks should apply to *all* iov_iter flavours, not just iovec-backed ones. There are two groups of primitives - one gets the kernel object described as pointer + size (copy_to_iter(), etc.) while another gets it as page + offset + size (copy_page_to_iter(), etc.) For the first group the checks are best done where we actually have a chance to find the object size. In other words, those belong in inline wrappers in uio.h, before calling into iov_iter.c. Same kind as we have for inlined part of copy_to_user(). For the second group there is no object to look at - offset in page is just a number, it bears no type information. So we do them in the common helper called by iov_iter.c primitives of that kind. All it currently does is checking that we are not trying to access outside of the compound page; eventually we might want to add some sanity checks on the page involved. So the things we need in copyin/copyout part of iov_iter.c do not quite match anything in uaccess.h (we want no zeroing, we *do* want access_ok() and KASAN and we want no might_fault() or object size checks done on that level). OTOH, these needs are simple enough to provide a couple of helpers (static in iov_iter.c) doing just what we need..." * 'uaccess-work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: iov_iter: saner checks on copyin/copyout iov_iter: sanity checks for copy to/from page primitives iov_iter/hardening: move object size checks to inlined part copy_{to,from}_user(): consolidate object size checks copy_{from,to}_user(): move kasan checks and might_fault() out-of-line
2017-07-08 11:39:20 +08:00
size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i);
x86, uaccess: introduce copy_from_iter_flushcache for pmem / cache-bypass operations The pmem driver has a need to transfer data with a persistent memory destination and be able to rely on the fact that the destination writes are not cached. It is sufficient for the writes to be flushed to a cpu-store-buffer (non-temporal / "movnt" in x86 terms), as we expect userspace to call fsync() to ensure data-writes have reached a power-fail-safe zone in the platform. The fsync() triggers a REQ_FUA or REQ_FLUSH to the pmem driver which will turn around and fence previous writes with an "sfence". Implement a __copy_from_user_inatomic_flushcache, memcpy_page_flushcache, and memcpy_flushcache, that guarantee that the destination buffer is not dirty in the cpu cache on completion. The new copy_from_iter_flushcache and sub-routines will be used to replace the "pmem api" (include/linux/pmem.h + arch/x86/include/asm/pmem.h). The availability of copy_from_iter_flushcache() and memcpy_flushcache() are gated by the CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE config symbol, and fallback to copy_from_iter_nocache() and plain memcpy() otherwise. This is meant to satisfy the concern from Linus that if a driver wants to do something beyond the normal nocache semantics it should be something private to that driver [1], and Al's concern that anything uaccess related belongs with the rest of the uaccess code [2]. The first consumer of this interface is a new 'copy_from_iter' dax operation so that pmem can inject cache maintenance operations without imposing this overhead on other dax-capable drivers. [1]: https://lists.01.org/pipermail/linux-nvdimm/2017-January/008364.html [2]: https://lists.01.org/pipermail/linux-nvdimm/2017-April/009942.html Cc: <x86@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Matthew Wilcox <mawilcox@microsoft.com> Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2017-05-30 03:22:50 +08:00
#else
Merge branch 'uaccess-work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs Pull iov_iter hardening from Al Viro: "This is the iov_iter/uaccess/hardening pile. For one thing, it trims the inline part of copy_to_user/copy_from_user to the minimum that *does* need to be inlined - object size checks, basically. For another, it sanitizes the checks for iov_iter primitives. There are 4 groups of checks: access_ok(), might_fault(), object size and KASAN. - access_ok() had been verified by whoever had set the iov_iter up. However, that has happened in a function far away, so proving that there's no path to actual copying bypassing those checks is hard and proving that iov_iter has not been buggered in the meanwhile is also not pleasant. So we want those redone in actual copyin/copyout. - might_fault() is better off consolidated - we know whether it needs to be checked as soon as we enter iov_iter primitive and observe the iov_iter flavour. No need to wait until the copyin/copyout. The call chains are short enough to make sure we won't miss anything - in fact, it's more robust that way, since there are cases where we do e.g. forced fault-in before getting to copyin/copyout. It's not quite what we need to check (in particular, combination of iovec-backed and set_fs(KERNEL_DS) is almost certainly a bug, not a cause to skip checks), but that's for later series. For now let's keep might_fault(). - KASAN checks belong in copyin/copyout - at the same level where other iov_iter flavours would've hit them in memcpy(). - object size checks should apply to *all* iov_iter flavours, not just iovec-backed ones. There are two groups of primitives - one gets the kernel object described as pointer + size (copy_to_iter(), etc.) while another gets it as page + offset + size (copy_page_to_iter(), etc.) For the first group the checks are best done where we actually have a chance to find the object size. In other words, those belong in inline wrappers in uio.h, before calling into iov_iter.c. Same kind as we have for inlined part of copy_to_user(). For the second group there is no object to look at - offset in page is just a number, it bears no type information. So we do them in the common helper called by iov_iter.c primitives of that kind. All it currently does is checking that we are not trying to access outside of the compound page; eventually we might want to add some sanity checks on the page involved. So the things we need in copyin/copyout part of iov_iter.c do not quite match anything in uaccess.h (we want no zeroing, we *do* want access_ok() and KASAN and we want no might_fault() or object size checks done on that level). OTOH, these needs are simple enough to provide a couple of helpers (static in iov_iter.c) doing just what we need..." * 'uaccess-work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: iov_iter: saner checks on copyin/copyout iov_iter: sanity checks for copy to/from page primitives iov_iter/hardening: move object size checks to inlined part copy_{to,from}_user(): consolidate object size checks copy_{from,to}_user(): move kasan checks and might_fault() out-of-line
2017-07-08 11:39:20 +08:00
#define _copy_from_iter_flushcache _copy_from_iter_nocache
#endif
#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE
size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i);
#else
#define _copy_to_iter_mcsafe _copy_to_iter
#endif
Merge branch 'uaccess-work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs Pull iov_iter hardening from Al Viro: "This is the iov_iter/uaccess/hardening pile. For one thing, it trims the inline part of copy_to_user/copy_from_user to the minimum that *does* need to be inlined - object size checks, basically. For another, it sanitizes the checks for iov_iter primitives. There are 4 groups of checks: access_ok(), might_fault(), object size and KASAN. - access_ok() had been verified by whoever had set the iov_iter up. However, that has happened in a function far away, so proving that there's no path to actual copying bypassing those checks is hard and proving that iov_iter has not been buggered in the meanwhile is also not pleasant. So we want those redone in actual copyin/copyout. - might_fault() is better off consolidated - we know whether it needs to be checked as soon as we enter iov_iter primitive and observe the iov_iter flavour. No need to wait until the copyin/copyout. The call chains are short enough to make sure we won't miss anything - in fact, it's more robust that way, since there are cases where we do e.g. forced fault-in before getting to copyin/copyout. It's not quite what we need to check (in particular, combination of iovec-backed and set_fs(KERNEL_DS) is almost certainly a bug, not a cause to skip checks), but that's for later series. For now let's keep might_fault(). - KASAN checks belong in copyin/copyout - at the same level where other iov_iter flavours would've hit them in memcpy(). - object size checks should apply to *all* iov_iter flavours, not just iovec-backed ones. There are two groups of primitives - one gets the kernel object described as pointer + size (copy_to_iter(), etc.) while another gets it as page + offset + size (copy_page_to_iter(), etc.) For the first group the checks are best done where we actually have a chance to find the object size. In other words, those belong in inline wrappers in uio.h, before calling into iov_iter.c. Same kind as we have for inlined part of copy_to_user(). For the second group there is no object to look at - offset in page is just a number, it bears no type information. So we do them in the common helper called by iov_iter.c primitives of that kind. All it currently does is checking that we are not trying to access outside of the compound page; eventually we might want to add some sanity checks on the page involved. So the things we need in copyin/copyout part of iov_iter.c do not quite match anything in uaccess.h (we want no zeroing, we *do* want access_ok() and KASAN and we want no might_fault() or object size checks done on that level). OTOH, these needs are simple enough to provide a couple of helpers (static in iov_iter.c) doing just what we need..." * 'uaccess-work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: iov_iter: saner checks on copyin/copyout iov_iter: sanity checks for copy to/from page primitives iov_iter/hardening: move object size checks to inlined part copy_{to,from}_user(): consolidate object size checks copy_{from,to}_user(): move kasan checks and might_fault() out-of-line
2017-07-08 11:39:20 +08:00
static __always_inline __must_check
size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
x86, uaccess: introduce copy_from_iter_flushcache for pmem / cache-bypass operations The pmem driver has a need to transfer data with a persistent memory destination and be able to rely on the fact that the destination writes are not cached. It is sufficient for the writes to be flushed to a cpu-store-buffer (non-temporal / "movnt" in x86 terms), as we expect userspace to call fsync() to ensure data-writes have reached a power-fail-safe zone in the platform. The fsync() triggers a REQ_FUA or REQ_FLUSH to the pmem driver which will turn around and fence previous writes with an "sfence". Implement a __copy_from_user_inatomic_flushcache, memcpy_page_flushcache, and memcpy_flushcache, that guarantee that the destination buffer is not dirty in the cpu cache on completion. The new copy_from_iter_flushcache and sub-routines will be used to replace the "pmem api" (include/linux/pmem.h + arch/x86/include/asm/pmem.h). The availability of copy_from_iter_flushcache() and memcpy_flushcache() are gated by the CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE config symbol, and fallback to copy_from_iter_nocache() and plain memcpy() otherwise. This is meant to satisfy the concern from Linus that if a driver wants to do something beyond the normal nocache semantics it should be something private to that driver [1], and Al's concern that anything uaccess related belongs with the rest of the uaccess code [2]. The first consumer of this interface is a new 'copy_from_iter' dax operation so that pmem can inject cache maintenance operations without imposing this overhead on other dax-capable drivers. [1]: https://lists.01.org/pipermail/linux-nvdimm/2017-January/008364.html [2]: https://lists.01.org/pipermail/linux-nvdimm/2017-April/009942.html Cc: <x86@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Matthew Wilcox <mawilcox@microsoft.com> Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2017-05-30 03:22:50 +08:00
{
Merge branch 'uaccess-work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs Pull iov_iter hardening from Al Viro: "This is the iov_iter/uaccess/hardening pile. For one thing, it trims the inline part of copy_to_user/copy_from_user to the minimum that *does* need to be inlined - object size checks, basically. For another, it sanitizes the checks for iov_iter primitives. There are 4 groups of checks: access_ok(), might_fault(), object size and KASAN. - access_ok() had been verified by whoever had set the iov_iter up. However, that has happened in a function far away, so proving that there's no path to actual copying bypassing those checks is hard and proving that iov_iter has not been buggered in the meanwhile is also not pleasant. So we want those redone in actual copyin/copyout. - might_fault() is better off consolidated - we know whether it needs to be checked as soon as we enter iov_iter primitive and observe the iov_iter flavour. No need to wait until the copyin/copyout. The call chains are short enough to make sure we won't miss anything - in fact, it's more robust that way, since there are cases where we do e.g. forced fault-in before getting to copyin/copyout. It's not quite what we need to check (in particular, combination of iovec-backed and set_fs(KERNEL_DS) is almost certainly a bug, not a cause to skip checks), but that's for later series. For now let's keep might_fault(). - KASAN checks belong in copyin/copyout - at the same level where other iov_iter flavours would've hit them in memcpy(). - object size checks should apply to *all* iov_iter flavours, not just iovec-backed ones. There are two groups of primitives - one gets the kernel object described as pointer + size (copy_to_iter(), etc.) while another gets it as page + offset + size (copy_page_to_iter(), etc.) For the first group the checks are best done where we actually have a chance to find the object size. In other words, those belong in inline wrappers in uio.h, before calling into iov_iter.c. Same kind as we have for inlined part of copy_to_user(). For the second group there is no object to look at - offset in page is just a number, it bears no type information. So we do them in the common helper called by iov_iter.c primitives of that kind. All it currently does is checking that we are not trying to access outside of the compound page; eventually we might want to add some sanity checks on the page involved. So the things we need in copyin/copyout part of iov_iter.c do not quite match anything in uaccess.h (we want no zeroing, we *do* want access_ok() and KASAN and we want no might_fault() or object size checks done on that level). OTOH, these needs are simple enough to provide a couple of helpers (static in iov_iter.c) doing just what we need..." * 'uaccess-work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: iov_iter: saner checks on copyin/copyout iov_iter: sanity checks for copy to/from page primitives iov_iter/hardening: move object size checks to inlined part copy_{to,from}_user(): consolidate object size checks copy_{from,to}_user(): move kasan checks and might_fault() out-of-line
2017-07-08 11:39:20 +08:00
if (unlikely(!check_copy_size(addr, bytes, false)))
return 0;
Merge branch 'uaccess-work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs Pull iov_iter hardening from Al Viro: "This is the iov_iter/uaccess/hardening pile. For one thing, it trims the inline part of copy_to_user/copy_from_user to the minimum that *does* need to be inlined - object size checks, basically. For another, it sanitizes the checks for iov_iter primitives. There are 4 groups of checks: access_ok(), might_fault(), object size and KASAN. - access_ok() had been verified by whoever had set the iov_iter up. However, that has happened in a function far away, so proving that there's no path to actual copying bypassing those checks is hard and proving that iov_iter has not been buggered in the meanwhile is also not pleasant. So we want those redone in actual copyin/copyout. - might_fault() is better off consolidated - we know whether it needs to be checked as soon as we enter iov_iter primitive and observe the iov_iter flavour. No need to wait until the copyin/copyout. The call chains are short enough to make sure we won't miss anything - in fact, it's more robust that way, since there are cases where we do e.g. forced fault-in before getting to copyin/copyout. It's not quite what we need to check (in particular, combination of iovec-backed and set_fs(KERNEL_DS) is almost certainly a bug, not a cause to skip checks), but that's for later series. For now let's keep might_fault(). - KASAN checks belong in copyin/copyout - at the same level where other iov_iter flavours would've hit them in memcpy(). - object size checks should apply to *all* iov_iter flavours, not just iovec-backed ones. There are two groups of primitives - one gets the kernel object described as pointer + size (copy_to_iter(), etc.) while another gets it as page + offset + size (copy_page_to_iter(), etc.) For the first group the checks are best done where we actually have a chance to find the object size. In other words, those belong in inline wrappers in uio.h, before calling into iov_iter.c. Same kind as we have for inlined part of copy_to_user(). For the second group there is no object to look at - offset in page is just a number, it bears no type information. So we do them in the common helper called by iov_iter.c primitives of that kind. All it currently does is checking that we are not trying to access outside of the compound page; eventually we might want to add some sanity checks on the page involved. So the things we need in copyin/copyout part of iov_iter.c do not quite match anything in uaccess.h (we want no zeroing, we *do* want access_ok() and KASAN and we want no might_fault() or object size checks done on that level). OTOH, these needs are simple enough to provide a couple of helpers (static in iov_iter.c) doing just what we need..." * 'uaccess-work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: iov_iter: saner checks on copyin/copyout iov_iter: sanity checks for copy to/from page primitives iov_iter/hardening: move object size checks to inlined part copy_{to,from}_user(): consolidate object size checks copy_{from,to}_user(): move kasan checks and might_fault() out-of-line
2017-07-08 11:39:20 +08:00
else
return _copy_from_iter_flushcache(addr, bytes, i);
x86, uaccess: introduce copy_from_iter_flushcache for pmem / cache-bypass operations The pmem driver has a need to transfer data with a persistent memory destination and be able to rely on the fact that the destination writes are not cached. It is sufficient for the writes to be flushed to a cpu-store-buffer (non-temporal / "movnt" in x86 terms), as we expect userspace to call fsync() to ensure data-writes have reached a power-fail-safe zone in the platform. The fsync() triggers a REQ_FUA or REQ_FLUSH to the pmem driver which will turn around and fence previous writes with an "sfence". Implement a __copy_from_user_inatomic_flushcache, memcpy_page_flushcache, and memcpy_flushcache, that guarantee that the destination buffer is not dirty in the cpu cache on completion. The new copy_from_iter_flushcache and sub-routines will be used to replace the "pmem api" (include/linux/pmem.h + arch/x86/include/asm/pmem.h). The availability of copy_from_iter_flushcache() and memcpy_flushcache() are gated by the CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE config symbol, and fallback to copy_from_iter_nocache() and plain memcpy() otherwise. This is meant to satisfy the concern from Linus that if a driver wants to do something beyond the normal nocache semantics it should be something private to that driver [1], and Al's concern that anything uaccess related belongs with the rest of the uaccess code [2]. The first consumer of this interface is a new 'copy_from_iter' dax operation so that pmem can inject cache maintenance operations without imposing this overhead on other dax-capable drivers. [1]: https://lists.01.org/pipermail/linux-nvdimm/2017-January/008364.html [2]: https://lists.01.org/pipermail/linux-nvdimm/2017-April/009942.html Cc: <x86@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Matthew Wilcox <mawilcox@microsoft.com> Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2017-05-30 03:22:50 +08:00
}
Merge branch 'uaccess-work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs Pull iov_iter hardening from Al Viro: "This is the iov_iter/uaccess/hardening pile. For one thing, it trims the inline part of copy_to_user/copy_from_user to the minimum that *does* need to be inlined - object size checks, basically. For another, it sanitizes the checks for iov_iter primitives. There are 4 groups of checks: access_ok(), might_fault(), object size and KASAN. - access_ok() had been verified by whoever had set the iov_iter up. However, that has happened in a function far away, so proving that there's no path to actual copying bypassing those checks is hard and proving that iov_iter has not been buggered in the meanwhile is also not pleasant. So we want those redone in actual copyin/copyout. - might_fault() is better off consolidated - we know whether it needs to be checked as soon as we enter iov_iter primitive and observe the iov_iter flavour. No need to wait until the copyin/copyout. The call chains are short enough to make sure we won't miss anything - in fact, it's more robust that way, since there are cases where we do e.g. forced fault-in before getting to copyin/copyout. It's not quite what we need to check (in particular, combination of iovec-backed and set_fs(KERNEL_DS) is almost certainly a bug, not a cause to skip checks), but that's for later series. For now let's keep might_fault(). - KASAN checks belong in copyin/copyout - at the same level where other iov_iter flavours would've hit them in memcpy(). - object size checks should apply to *all* iov_iter flavours, not just iovec-backed ones. There are two groups of primitives - one gets the kernel object described as pointer + size (copy_to_iter(), etc.) while another gets it as page + offset + size (copy_page_to_iter(), etc.) For the first group the checks are best done where we actually have a chance to find the object size. In other words, those belong in inline wrappers in uio.h, before calling into iov_iter.c. Same kind as we have for inlined part of copy_to_user(). For the second group there is no object to look at - offset in page is just a number, it bears no type information. So we do them in the common helper called by iov_iter.c primitives of that kind. All it currently does is checking that we are not trying to access outside of the compound page; eventually we might want to add some sanity checks on the page involved. So the things we need in copyin/copyout part of iov_iter.c do not quite match anything in uaccess.h (we want no zeroing, we *do* want access_ok() and KASAN and we want no might_fault() or object size checks done on that level). OTOH, these needs are simple enough to provide a couple of helpers (static in iov_iter.c) doing just what we need..." * 'uaccess-work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: iov_iter: saner checks on copyin/copyout iov_iter: sanity checks for copy to/from page primitives iov_iter/hardening: move object size checks to inlined part copy_{to,from}_user(): consolidate object size checks copy_{from,to}_user(): move kasan checks and might_fault() out-of-line
2017-07-08 11:39:20 +08:00
static __always_inline __must_check
size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i)
{
if (unlikely(!check_copy_size(addr, bytes, true)))
return 0;
else
return _copy_to_iter_mcsafe(addr, bytes, i);
}
size_t iov_iter_zero(size_t bytes, struct iov_iter *);
unsigned long iov_iter_alignment(const struct iov_iter *i);
unsigned long iov_iter_gap_alignment(const struct iov_iter *i);
void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov,
unsigned long nr_segs, size_t count);
void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec,
unsigned long nr_segs, size_t count);
void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec,
unsigned long nr_segs, size_t count);
void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe,
size_t count);
void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count);
ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
size_t maxsize, unsigned maxpages, size_t *start);
ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages,
size_t maxsize, size_t *start);
int iov_iter_npages(const struct iov_iter *i, int maxpages);
const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags);
static inline size_t iov_iter_count(const struct iov_iter *i)
{
return i->count;
}
/*
* Cap the iov_iter by given limit; note that the second argument is
* *not* the new size - it's upper limit for such. Passing it a value
* greater than the amount of data in iov_iter is fine - it'll just do
* nothing in that case.
*/
static inline void iov_iter_truncate(struct iov_iter *i, u64 count)
{
/*
* count doesn't have to fit in size_t - comparison extends both
* operands to u64 here and any value that would be truncated by
* conversion in assignement is by definition greater than all
* values of size_t, including old i->count.
*/
if (i->count > count)
i->count = count;
}
/*
* reexpand a previously truncated iterator; count must be no more than how much
* we had shrunk it.
*/
static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
{
i->count = count;
}
size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump, struct iov_iter *i);
size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
struct iov_iter *i);
saner iov_iter initialization primitives iovec-backed iov_iter instances are assumed to satisfy several properties: * no more than UIO_MAXIOV elements in iovec array * total size of all ranges is no more than MAX_RW_COUNT * all ranges pass access_ok(). The problem is, invariants of data structures should be established in the primitives creating those data structures, not in the code using those primitives. And iov_iter_init() violates that principle. For a while we managed to get away with that, but once the use of iov_iter started to spread, it didn't take long for shit to hit the fan - missed check in sys_sendto() had introduced a roothole. We _do_ have primitives for importing and validating iovecs (both native and compat ones) and those primitives are almost always followed by shoving the resulting iovec into iov_iter. Life would be considerably simpler (and safer) if we combined those primitives with initializing iov_iter. That gives us two new primitives - import_iovec() and compat_import_iovec(). Calling conventions: iovec = iov_array; err = import_iovec(direction, uvec, nr_segs, ARRAY_SIZE(iov_array), &iovec, &iter); imports user vector into kernel space (into iov_array if it fits, allocated if it doesn't fit or if iovec was NULL), validates it and sets iter up to refer to it. On success 0 is returned and allocated kernel copy (or NULL if the array had fit into caller-supplied one) is returned via iovec. On failure all allocations are undone and -E... is returned. If the total size of ranges exceeds MAX_RW_COUNT, the excess is silently truncated. compat_import_iovec() expects uvec to be a pointer to user array of compat_iovec; otherwise it's identical to import_iovec(). Finally, import_single_range() sets iov_iter backed by single-element iovec covering a user-supplied range - err = import_single_range(direction, address, size, iovec, &iter); does validation and sets iter up. Again, size in excess of MAX_RW_COUNT gets silently truncated. Next commits will be switching the things up to use of those and reducing the amount of iov_iter_init() instances. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-03-22 05:45:43 +08:00
int import_iovec(int type, const struct iovec __user * uvector,
unsigned nr_segs, unsigned fast_segs,
struct iovec **iov, struct iov_iter *i);
#ifdef CONFIG_COMPAT
struct compat_iovec;
int compat_import_iovec(int type, const struct compat_iovec __user * uvector,
unsigned nr_segs, unsigned fast_segs,
struct iovec **iov, struct iov_iter *i);
#endif
int import_single_range(int type, void __user *buf, size_t len,
struct iovec *iov, struct iov_iter *i);
int iov_iter_for_each_range(struct iov_iter *i, size_t bytes,
int (*f)(struct kvec *vec, void *context),
void *context);
#endif