mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-30 09:26:45 +07:00
40e041a2c8
If two processes share a common memory region, they usually want some
guarantees to allow safe access. This often includes:
- one side cannot overwrite data while the other reads it
- one side cannot shrink the buffer while the other accesses it
- one side cannot grow the buffer beyond previously set boundaries
If there is a trust-relationship between both parties, there is no need
for policy enforcement. However, if there's no trust relationship (eg.,
for general-purpose IPC) sharing memory-regions is highly fragile and
often not possible without local copies. Look at the following two
use-cases:
1) A graphics client wants to share its rendering-buffer with a
graphics-server. The memory-region is allocated by the client for
read/write access and a second FD is passed to the server. While
scanning out from the memory region, the server has no guarantee that
the client doesn't shrink the buffer at any time, requiring rather
cumbersome SIGBUS handling.
2) A process wants to perform an RPC on another process. To avoid huge
bandwidth consumption, zero-copy is preferred. After a message is
assembled in-memory and a FD is passed to the remote side, both sides
want to be sure that neither modifies this shared copy, anymore. The
source may have put sensible data into the message without a separate
copy and the target may want to parse the message inline, to avoid a
local copy.
While SIGBUS handling, POSIX mandatory locking and MAP_DENYWRITE provide
ways to achieve most of this, the first one is unproportionally ugly to
use in libraries and the latter two are broken/racy or even disabled due
to denial of service attacks.
This patch introduces the concept of SEALING. If you seal a file, a
specific set of operations is blocked on that file forever. Unlike locks,
seals can only be set, never removed. Hence, once you verified a specific
set of seals is set, you're guaranteed that no-one can perform the blocked
operations on this file, anymore.
An initial set of SEALS is introduced by this patch:
- SHRINK: If SEAL_SHRINK is set, the file in question cannot be reduced
in size. This affects ftruncate() and open(O_TRUNC).
- GROW: If SEAL_GROW is set, the file in question cannot be increased
in size. This affects ftruncate(), fallocate() and write().
- WRITE: If SEAL_WRITE is set, no write operations (besides resizing)
are possible. This affects fallocate(PUNCH_HOLE), mmap() and
write().
- SEAL: If SEAL_SEAL is set, no further seals can be added to a file.
This basically prevents the F_ADD_SEAL operation on a file and
can be set to prevent others from adding further seals that you
don't want.
The described use-cases can easily use these seals to provide safe use
without any trust-relationship:
1) The graphics server can verify that a passed file-descriptor has
SEAL_SHRINK set. This allows safe scanout, while the client is
allowed to increase buffer size for window-resizing on-the-fly.
Concurrent writes are explicitly allowed.
2) For general-purpose IPC, both processes can verify that SEAL_SHRINK,
SEAL_GROW and SEAL_WRITE are set. This guarantees that neither
process can modify the data while the other side parses it.
Furthermore, it guarantees that even with writable FDs passed to the
peer, it cannot increase the size to hit memory-limits of the source
process (in case the file-storage is accounted to the source).
The new API is an extension to fcntl(), adding two new commands:
F_GET_SEALS: Return a bitset describing the seals on the file. This
can be called on any FD if the underlying file supports
sealing.
F_ADD_SEALS: Change the seals of a given file. This requires WRITE
access to the file and F_SEAL_SEAL may not already be set.
Furthermore, the underlying file must support sealing and
there may not be any existing shared mapping of that file.
Otherwise, EBADF/EPERM is returned.
The given seals are _added_ to the existing set of seals
on the file. You cannot remove seals again.
The fcntl() handler is currently specific to shmem and disabled on all
files. A file needs to explicitly support sealing for this interface to
work. A separate syscall is added in a follow-up, which creates files that
support sealing. There is no intention to support this on other
file-systems. Semantics are unclear for non-volatile files and we lack any
use-case right now. Therefore, the implementation is specific to shmem.
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Ryan Lortie <desrt@desrt.ca>
Cc: Lennart Poettering <lennart@poettering.net>
Cc: Daniel Mack <zonque@gmail.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
86 lines
2.8 KiB
C
86 lines
2.8 KiB
C
#ifndef __SHMEM_FS_H
|
|
#define __SHMEM_FS_H
|
|
|
|
#include <linux/file.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/mempolicy.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/percpu_counter.h>
|
|
#include <linux/xattr.h>
|
|
|
|
/* inode in-kernel data */
|
|
|
|
struct shmem_inode_info {
|
|
spinlock_t lock;
|
|
unsigned int seals; /* shmem seals */
|
|
unsigned long flags;
|
|
unsigned long alloced; /* data pages alloced to file */
|
|
union {
|
|
unsigned long swapped; /* subtotal assigned to swap */
|
|
char *symlink; /* unswappable short symlink */
|
|
};
|
|
struct shared_policy policy; /* NUMA memory alloc policy */
|
|
struct list_head swaplist; /* chain of maybes on swap */
|
|
struct simple_xattrs xattrs; /* list of xattrs */
|
|
struct inode vfs_inode;
|
|
};
|
|
|
|
struct shmem_sb_info {
|
|
unsigned long max_blocks; /* How many blocks are allowed */
|
|
struct percpu_counter used_blocks; /* How many are allocated */
|
|
unsigned long max_inodes; /* How many inodes are allowed */
|
|
unsigned long free_inodes; /* How many are left for allocation */
|
|
spinlock_t stat_lock; /* Serialize shmem_sb_info changes */
|
|
kuid_t uid; /* Mount uid for root directory */
|
|
kgid_t gid; /* Mount gid for root directory */
|
|
umode_t mode; /* Mount mode for root directory */
|
|
struct mempolicy *mpol; /* default memory policy for mappings */
|
|
};
|
|
|
|
static inline struct shmem_inode_info *SHMEM_I(struct inode *inode)
|
|
{
|
|
return container_of(inode, struct shmem_inode_info, vfs_inode);
|
|
}
|
|
|
|
/*
|
|
* Functions in mm/shmem.c called directly from elsewhere:
|
|
*/
|
|
extern int shmem_init(void);
|
|
extern int shmem_fill_super(struct super_block *sb, void *data, int silent);
|
|
extern struct file *shmem_file_setup(const char *name,
|
|
loff_t size, unsigned long flags);
|
|
extern struct file *shmem_kernel_file_setup(const char *name, loff_t size,
|
|
unsigned long flags);
|
|
extern int shmem_zero_setup(struct vm_area_struct *);
|
|
extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
|
|
extern bool shmem_mapping(struct address_space *mapping);
|
|
extern void shmem_unlock_mapping(struct address_space *mapping);
|
|
extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
|
|
pgoff_t index, gfp_t gfp_mask);
|
|
extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end);
|
|
extern int shmem_unuse(swp_entry_t entry, struct page *page);
|
|
|
|
static inline struct page *shmem_read_mapping_page(
|
|
struct address_space *mapping, pgoff_t index)
|
|
{
|
|
return shmem_read_mapping_page_gfp(mapping, index,
|
|
mapping_gfp_mask(mapping));
|
|
}
|
|
|
|
#ifdef CONFIG_TMPFS
|
|
|
|
extern int shmem_add_seals(struct file *file, unsigned int seals);
|
|
extern int shmem_get_seals(struct file *file);
|
|
extern long shmem_fcntl(struct file *file, unsigned int cmd, unsigned long arg);
|
|
|
|
#else
|
|
|
|
static inline long shmem_fcntl(struct file *f, unsigned int c, unsigned long a)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
|
|
#endif
|
|
|
|
#endif
|