mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-23 07:38:25 +07:00
e8c24d3a23
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>
45 lines
953 B
C
45 lines
953 B
C
#ifndef _ASM_X86_MMU_H
|
|
#define _ASM_X86_MMU_H
|
|
|
|
#include <linux/spinlock.h>
|
|
#include <linux/mutex.h>
|
|
|
|
/*
|
|
* The x86 doesn't have a mmu context, but
|
|
* we put the segment information here.
|
|
*/
|
|
typedef struct {
|
|
#ifdef CONFIG_MODIFY_LDT_SYSCALL
|
|
struct ldt_struct *ldt;
|
|
#endif
|
|
|
|
#ifdef CONFIG_X86_64
|
|
/* True if mm supports a task running in 32 bit compatibility mode. */
|
|
unsigned short ia32_compat;
|
|
#endif
|
|
|
|
struct mutex lock;
|
|
void __user *vdso; /* vdso base address */
|
|
const struct vdso_image *vdso_image; /* vdso image in use */
|
|
|
|
atomic_t perf_rdpmc_allowed; /* nonzero if rdpmc is allowed */
|
|
#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
|
|
} mm_context_t;
|
|
|
|
#ifdef CONFIG_SMP
|
|
void leave_mm(int cpu);
|
|
#else
|
|
static inline void leave_mm(int cpu)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#endif /* _ASM_X86_MMU_H */
|