From 60622d68227d6d71fdfba5fb39f7f3d44cdd8815 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 3 May 2018 17:06:21 -0700 Subject: x86/asm/memcpy_mcsafe: Return bytes remaining Machine check safe memory copies are currently deployed in the pmem driver whenever reading from persistent memory media, so that -EIO is returned rather than triggering a kernel panic. While this protects most pmem accesses, it is not complete in the filesystem-dax case. When filesystem-dax is enabled reads may bypass the block layer and the driver via dax_iomap_actor() and its usage of copy_to_iter(). In preparation for creating a copy_to_iter() variant that can handle machine checks, teach memcpy_mcsafe() to return the number of bytes remaining rather than -EFAULT when an exception occurs. Co-developed-by: Tony Luck Signed-off-by: Dan Williams Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tony Luck Cc: hch@lst.de Cc: linux-fsdevel@vger.kernel.org Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/152539238119.31796.14318473522414462886.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Ingo Molnar --- include/linux/string.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index dd39a690c841..4a5a0eb7df51 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -147,8 +147,8 @@ extern int memcmp(const void *,const void *,__kernel_size_t); extern void * memchr(const void *,int,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMCPY_MCSAFE -static inline __must_check int memcpy_mcsafe(void *dst, const void *src, - size_t cnt) +static inline __must_check unsigned long memcpy_mcsafe(void *dst, + const void *src, size_t cnt) { memcpy(dst, src, cnt); return 0; -- cgit v1.2.2 From 8780356ef630aa577fd4daa49e49b79674711fae Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 3 May 2018 17:06:31 -0700 Subject: x86/asm/memcpy_mcsafe: Define copy_to_iter_mcsafe() Use the updated memcpy_mcsafe() implementation to define copy_user_mcsafe() and copy_to_iter_mcsafe(). The most significant difference from typical copy_to_iter() is that the ITER_KVEC and ITER_BVEC iterator types can fail to complete a full transfer. Signed-off-by: Dan Williams Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tony Luck Cc: hch@lst.de Cc: linux-fsdevel@vger.kernel.org Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/152539239150.31796.9189779163576449784.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Ingo Molnar --- include/linux/uio.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index e67e12adb136..f5766e853a77 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -154,6 +154,12 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #define _copy_from_iter_flushcache _copy_from_iter_nocache #endif +#ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE +size_t _copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i); +#else +#define _copy_to_iter_mcsafe _copy_to_iter +#endif + static __always_inline __must_check size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { @@ -163,6 +169,15 @@ size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) return _copy_from_iter_flushcache(addr, bytes, i); } +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, false))) + 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); -- cgit v1.2.2 From 522239b445a2de988edb81672963708a6aaf9046 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 22 May 2018 23:17:03 -0700 Subject: uio, lib: Fix CONFIG_ARCH_HAS_UACCESS_MCSAFE compilation Add a common Kconfig CONFIG_ARCH_HAS_UACCESS_MCSAFE that archs can optionally select, and fixup the declaration of _copy_to_iter_mcsafe(). Fixes: 8780356ef630 ("x86/asm/memcpy_mcsafe: Define copy_to_iter_mcsafe()") Signed-off-by: Dan Williams --- include/linux/uio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index f5766e853a77..409c845d4cd3 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -155,7 +155,7 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #endif #ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE -size_t _copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i); +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 -- cgit v1.2.2 From b3a9a0c36e1f7b9e2e6cf965c2bb973624f2b3b9 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 2 May 2018 06:46:33 -0700 Subject: dax: Introduce a ->copy_to_iter dax operation Similar to the ->copy_from_iter() operation, a platform may want to deploy an architecture or device specific routine for handling reads from a dax_device like /dev/pmemX. On x86 this routine will point to a machine check safe version of copy_to_iter(). For now, add the plumbing to device-mapper and the dax core. Cc: Ross Zwisler Cc: Mike Snitzer Cc: Christoph Hellwig Signed-off-by: Dan Williams --- include/linux/dax.h | 5 +++++ include/linux/device-mapper.h | 5 +++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index f9eb22ad341e..a43b396fb336 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -20,6 +20,9 @@ struct dax_operations { /* copy_from_iter: required operation for fs-dax direct-i/o */ size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t, struct iov_iter *); + /* copy_to_iter: required operation for fs-dax direct-i/o */ + size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t, + struct iov_iter *); }; extern struct attribute_group dax_attribute_group; @@ -118,6 +121,8 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); +size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, + size_t bytes, struct iov_iter *i); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 31fef7c34185..6fb0808e87c8 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -133,7 +133,7 @@ typedef int (*dm_busy_fn) (struct dm_target *ti); */ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); -typedef size_t (*dm_dax_copy_from_iter_fn)(struct dm_target *ti, pgoff_t pgoff, +typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); #define PAGE_SECTORS (PAGE_SIZE / 512) @@ -184,7 +184,8 @@ struct target_type { dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; dm_dax_direct_access_fn direct_access; - dm_dax_copy_from_iter_fn dax_copy_from_iter; + dm_dax_copy_iter_fn dax_copy_from_iter; + dm_dax_copy_iter_fn dax_copy_to_iter; /* For internal device-mapper use. */ struct list_head list; -- cgit v1.2.2