From 3859a271a003aba01e45b85c9d8b355eb7bf25f9 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 28 Oct 2016 01:22:25 -0700 Subject: randstruct: Mark various structs for randomization This marks many critical kernel structures for randomization. These are structures that have been targeted in the past in security exploits, or contain functions pointers, pointers to function pointer tables, lists, workqueues, ref-counters, credentials, permissions, or are otherwise sensitive. This initial list was extracted from Brad Spengler/PaX Team's code in the last public patch of grsecurity/PaX based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. Left out of this list is task_struct, which requires special handling and will be covered in a subsequent patch. Signed-off-by: Kees Cook --- include/linux/fs.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 803e5a9b2654..8f28143486c4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -275,7 +275,7 @@ struct kiocb { void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); void *private; int ki_flags; -}; +} __randomize_layout; static inline bool is_sync_kiocb(struct kiocb *kiocb) { @@ -392,7 +392,7 @@ struct address_space { gfp_t gfp_mask; /* implicit gfp mask for allocations */ struct list_head private_list; /* ditto */ void *private_data; /* ditto */ -} __attribute__((aligned(sizeof(long)))); +} __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit @@ -435,7 +435,7 @@ struct block_device { int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; -}; +} __randomize_layout; /* * Radix-tree tags, for tagging dirty and writeback pages within the pagecache @@ -653,7 +653,7 @@ struct inode { #endif void *i_private; /* fs or device private pointer */ -}; +} __randomize_layout; static inline unsigned int i_blocksize(const struct inode *node) { @@ -868,7 +868,8 @@ struct file { struct list_head f_tfile_llink; #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; -} __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ +} __randomize_layout + __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; @@ -1005,7 +1006,7 @@ struct file_lock { int state; /* state of grant or error if -ve */ } afs; } fl_u; -}; +} __randomize_layout; struct file_lock_context { spinlock_t flc_lock; @@ -1404,7 +1405,7 @@ struct super_block { spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ -}; +} __randomize_layout; /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can @@ -1690,7 +1691,7 @@ struct file_operations { u64); ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *, u64); -}; +} __randomize_layout; struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); -- cgit v1.2.3-55-g7522 From 0cc3b0ec23ce4c69e1e890ed2b8d2fa932b14aad Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 27 Aug 2017 12:12:25 -0700 Subject: Clarify (and fix) MAX_LFS_FILESIZE macros We have a MAX_LFS_FILESIZE macro that is meant to be filled in by filesystems (and other IO targets) that know they are 64-bit clean and don't have any 32-bit limits in their IO path. It turns out that our 32-bit value for that limit was bogus. On 32-bit, the VM layer is limited by the page cache to only 32-bit index values, but our logic for that was confusing and actually wrong. We used to define that value to (((loff_t)PAGE_SIZE << (BITS_PER_LONG-1))-1) which is actually odd in several ways: it limits the index to 31 bits, and then it limits files so that they can't have data in that last byte of a page that has the highest 31-bit index (ie page index 0x7fffffff). Neither of those limitations make sense. The index is actually the full 32 bit unsigned value, and we can use that whole full page. So the maximum size of the file would logically be "PAGE_SIZE << BITS_PER_LONG". However, we do wan tto avoid the maximum index, because we have code that iterates over the page indexes, and we don't want that code to overflow. So the maximum size of a file on a 32-bit host should actually be one page less than the full 32-bit index. So the actual limit is ULONG_MAX << PAGE_SHIFT. That means that we will not actually be using the page of that last index (ULONG_MAX), but we can grow a file up to that limit. The wrong value of MAX_LFS_FILESIZE actually caused problems for Doug Nazar, who was still using a 32-bit host, but with a 9.7TB 2 x RAID5 volume. It turns out that our old MAX_LFS_FILESIZE was 8TiB (well, one byte less), but the actual true VM limit is one page less than 16TiB. This was invisible until commit c2a9737f45e2 ("vfs,mm: fix a dead loop in truncate_inode_pages_range()"), which started applying that MAX_LFS_FILESIZE limit to block devices too. NOTE! On 64-bit, the page index isn't a limiter at all, and the limit is actually just the offset type itself (loff_t), which is signed. But for clarity, on 64-bit, just use the maximum signed value, and don't make people have to count the number of 'f' characters in the hex constant. So just use LLONG_MAX for the 64-bit case. That was what the value had been before too, just written out as a hex constant. Fixes: c2a9737f45e2 ("vfs,mm: fix a dead loop in truncate_inode_pages_range()") Reported-and-tested-by: Doug Nazar Cc: Andreas Dilger Cc: Mark Fasheh Cc: Joel Becker Cc: Dave Kleikamp Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6e1fd5d21248..cbfe127bccf8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -907,9 +907,9 @@ static inline struct file *get_file(struct file *f) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 -#define MAX_LFS_FILESIZE (((loff_t)PAGE_SIZE << (BITS_PER_LONG-1))-1) +#define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 -#define MAX_LFS_FILESIZE ((loff_t)0x7fffffffffffffffLL) +#define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif #define FL_POSIX 1 -- cgit v1.2.3-55-g7522