2008-10-23 05:26:29 +00:00
|
|
|
#ifndef _ASM_X86_MMU_H
|
|
|
|
|
#define _ASM_X86_MMU_H
|
2007-10-20 06:56:59 +00:00
|
|
|
|
|
|
|
|
#include <linux/spinlock.h>
|
|
|
|
|
#include <linux/mutex.h>
|
2017-06-29 15:53:15 +00:00
|
|
|
#include <linux/atomic.h>
|
2007-10-20 06:56:59 +00:00
|
|
|
|
|
|
|
|
/*
|
2017-06-29 15:53:15 +00:00
|
|
|
* x86 has arch-specific MMU state beyond what lives in mm_struct.
|
2007-10-20 06:56:59 +00:00
|
|
|
*/
|
2008-03-23 08:02:44 +00:00
|
|
|
typedef struct {
|
2017-06-29 15:53:15 +00:00
|
|
|
/*
|
|
|
|
|
* ctx_id uniquely identifies this mm_struct. A ctx_id will never
|
|
|
|
|
* be reused, and zero is not a valid ctx_id.
|
|
|
|
|
*/
|
|
|
|
|
u64 ctx_id;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Any code that needs to do any sort of TLB flushing for this
|
|
|
|
|
* mm will first make its changes to the page tables, then
|
|
|
|
|
* increment tlb_gen, then flush. This lets the low-level
|
|
|
|
|
* flushing code keep track of what needs flushing.
|
|
|
|
|
*
|
|
|
|
|
* This is not used on Xen PV.
|
|
|
|
|
*/
|
|
|
|
|
atomic64_t tlb_gen;
|
|
|
|
|
|
2015-07-30 21:31:34 +00:00
|
|
|
#ifdef CONFIG_MODIFY_LDT_SYSCALL
|
2015-07-30 21:31:32 +00:00
|
|
|
struct ldt_struct *ldt;
|
2015-07-30 21:31:34 +00:00
|
|
|
#endif
|
2011-03-13 19:49:13 +00:00
|
|
|
|
|
|
|
|
#ifdef CONFIG_X86_64
|
|
|
|
|
/* True if mm supports a task running in 32 bit compatibility mode. */
|
|
|
|
|
unsigned short ia32_compat;
|
|
|
|
|
#endif
|
|
|
|
|
|
2011-05-24 13:49:59 +00:00
|
|
|
struct mutex lock;
|
2015-12-30 04:12:21 +00:00
|
|
|
void __user *vdso; /* vdso base address */
|
|
|
|
|
const struct vdso_image *vdso_image; /* vdso image in use */
|
2014-10-24 22:58:12 +00:00
|
|
|
|
|
|
|
|
atomic_t perf_rdpmc_allowed; /* nonzero if rdpmc is allowed */
|
x86/pkeys: Allocation/free syscalls
This patch adds two new system calls:
int pkey_alloc(unsigned long flags, unsigned long init_access_rights)
int pkey_free(int pkey);
These implement an "allocator" for the protection keys
themselves, which can be thought of as analogous to the allocator
that the kernel has for file descriptors. The kernel tracks
which numbers are in use, and only allows operations on keys that
are valid. A key which was not obtained by pkey_alloc() may not,
for instance, be passed to pkey_mprotect().
These system calls are also very important given the kernel's use
of pkeys to implement execute-only support. These help ensure
that userspace can never assume that it has control of a key
unless it first asks the kernel. The kernel does not promise to
preserve PKRU (right register) contents except for allocated
pkeys.
The 'init_access_rights' argument to pkey_alloc() specifies the
rights that will be established for the returned pkey. For
instance:
pkey = pkey_alloc(flags, PKEY_DENY_WRITE);
will allocate 'pkey', but also sets the bits in PKRU[1] such that
writing to 'pkey' is already denied.
The kernel does not prevent pkey_free() from successfully freeing
in-use pkeys (those still assigned to a memory range by
pkey_mprotect()). It would be expensive to implement the checks
for this, so we instead say, "Just don't do it" since sane
software will never do it anyway.
Any piece of userspace calling pkey_alloc() needs to be prepared
for it to fail. Why? pkey_alloc() returns the same error code
(ENOSPC) when there are no pkeys and when pkeys are unsupported.
They can be unsupported for a whole host of reasons, so apps must
be prepared for this. Also, libraries or LD_PRELOADs might steal
keys before an application gets access to them.
This allocation mechanism could be implemented in userspace.
Even if we did it in userspace, we would still need additional
user/kernel interfaces to tell userspace which keys are being
used by the kernel internally (such as for execute-only
mappings). Having the kernel provide this facility completely
removes the need for these additional interfaces, or having an
implementation of this in userspace at all.
Note that we have to make changes to all of the architectures
that do not use mman-common.h because we use the new
PKEY_DENY_ACCESS/WRITE macros in arch-independent code.
1. PKRU is the Protection Key Rights User register. It is a
usermode-accessible register that controls whether writes
and/or access to each individual pkey is allowed or denied.
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: linux-arch@vger.kernel.org
Cc: Dave Hansen <dave@sr71.net>
Cc: arnd@arndb.de
Cc: linux-api@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: luto@kernel.org
Cc: akpm@linux-foundation.org
Cc: torvalds@linux-foundation.org
Link: http://lkml.kernel.org/r/20160729163015.444FE75F@viggo.jf.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-07-29 16:30:15 +00:00
|
|
|
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
|
|
|
|
|
/*
|
|
|
|
|
* One bit per protection key says whether userspace can
|
|
|
|
|
* use it or not. protected by mmap_sem.
|
|
|
|
|
*/
|
|
|
|
|
u16 pkey_allocation_map;
|
|
|
|
|
s16 execute_only_pkey;
|
|
|
|
|
#endif
|
2016-12-16 12:40:55 +00:00
|
|
|
#ifdef CONFIG_X86_INTEL_MPX
|
|
|
|
|
/* address of the bounds directory */
|
|
|
|
|
void __user *bd_addr;
|
|
|
|
|
#endif
|
2007-10-20 06:56:59 +00:00
|
|
|
} mm_context_t;
|
|
|
|
|
|
2017-06-29 15:53:15 +00:00
|
|
|
#define INIT_MM_CONTEXT(mm) \
|
|
|
|
|
.context = { \
|
|
|
|
|
.ctx_id = 1, \
|
|
|
|
|
}
|
|
|
|
|
|
2008-01-30 12:32:01 +00:00
|
|
|
void leave_mm(int cpu);
|
|
|
|
|
|
2008-10-23 05:26:29 +00:00
|
|
|
#endif /* _ASM_X86_MMU_H */
|
