linux_dsm_epyc7002/arch/x86/mm/pkeys.c
Dave Hansen 76de993727 x86/pkeys: Allow configuration of init_pkru
As discussed in the previous patch, there is a reliability
benefit to allowing an init value for the Protection Keys Rights
User register (PKRU) which differs from what the XSAVE hardware
provides.

But, having PKRU be 0 (its init value) provides some nonzero
amount of optimization potential to the hardware.  It can, for
instance, skip writes to the XSAVE buffer when it knows that PKRU
is in its init state.

The cost of losing this optimization is approximately 100 cycles
per context switch for a workload which lightly using XSAVE
state (something not using AVX much).  The overhead comes from a
combinaation of actually manipulating PKRU and the overhead of
pullin in an extra cacheline.

This overhead is not huge, but it's also not something that I
think we should unconditionally inflict on everyone.  So, make it
configurable both at boot-time and from debugfs.

Changes to the debugfs value affect all processes created after
the write to debugfs.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: linux-arch@vger.kernel.org
Cc: Dave Hansen <dave@sr71.net>
Cc: mgorman@techsingularity.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/20160729163023.407672D2@viggo.jf.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2016-09-09 13:02:28 +02:00

228 lines
6.5 KiB
C

/*
* Intel Memory Protection Keys management
* Copyright (c) 2015, Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
* version 2, as published by the Free Software Foundation.
*
* This program is distributed in the hope it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
* more details.
*/
#include <linux/debugfs.h> /* debugfs_create_u32() */
#include <linux/mm_types.h> /* mm_struct, vma, etc... */
#include <linux/pkeys.h> /* PKEY_* */
#include <uapi/asm-generic/mman-common.h>
#include <asm/cpufeature.h> /* boot_cpu_has, ... */
#include <asm/mmu_context.h> /* vma_pkey() */
#include <asm/fpu/internal.h> /* fpregs_active() */
int __execute_only_pkey(struct mm_struct *mm)
{
bool need_to_set_mm_pkey = false;
int execute_only_pkey = mm->context.execute_only_pkey;
int ret;
/* Do we need to assign a pkey for mm's execute-only maps? */
if (execute_only_pkey == -1) {
/* Go allocate one to use, which might fail */
execute_only_pkey = mm_pkey_alloc(mm);
if (execute_only_pkey < 0)
return -1;
need_to_set_mm_pkey = true;
}
/*
* We do not want to go through the relatively costly
* dance to set PKRU if we do not need to. Check it
* first and assume that if the execute-only pkey is
* write-disabled that we do not have to set it
* ourselves. We need preempt off so that nobody
* can make fpregs inactive.
*/
preempt_disable();
if (!need_to_set_mm_pkey &&
fpregs_active() &&
!__pkru_allows_read(read_pkru(), execute_only_pkey)) {
preempt_enable();
return execute_only_pkey;
}
preempt_enable();
/*
* Set up PKRU so that it denies access for everything
* other than execution.
*/
ret = arch_set_user_pkey_access(current, execute_only_pkey,
PKEY_DISABLE_ACCESS);
/*
* If the PKRU-set operation failed somehow, just return
* 0 and effectively disable execute-only support.
*/
if (ret) {
mm_set_pkey_free(mm, execute_only_pkey);
return -1;
}
/* We got one, store it and use it from here on out */
if (need_to_set_mm_pkey)
mm->context.execute_only_pkey = execute_only_pkey;
return execute_only_pkey;
}
static inline bool vma_is_pkey_exec_only(struct vm_area_struct *vma)
{
/* Do this check first since the vm_flags should be hot */
if ((vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) != VM_EXEC)
return false;
if (vma_pkey(vma) != vma->vm_mm->context.execute_only_pkey)
return false;
return true;
}
/*
* This is only called for *plain* mprotect calls.
*/
int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey)
{
/*
* Is this an mprotect_pkey() call? If so, never
* override the value that came from the user.
*/
if (pkey != -1)
return pkey;
/*
* Look for a protection-key-drive execute-only mapping
* which is now being given permissions that are not
* execute-only. Move it back to the default pkey.
*/
if (vma_is_pkey_exec_only(vma) &&
(prot & (PROT_READ|PROT_WRITE))) {
return 0;
}
/*
* The mapping is execute-only. Go try to get the
* execute-only protection key. If we fail to do that,
* fall through as if we do not have execute-only
* support.
*/
if (prot == PROT_EXEC) {
pkey = execute_only_pkey(vma->vm_mm);
if (pkey > 0)
return pkey;
}
/*
* This is a vanilla, non-pkey mprotect (or we failed to
* setup execute-only), inherit the pkey from the VMA we
* are working on.
*/
return vma_pkey(vma);
}
#define PKRU_AD_KEY(pkey) (PKRU_AD_BIT << ((pkey) * PKRU_BITS_PER_PKEY))
/*
* Make the default PKRU value (at execve() time) as restrictive
* as possible. This ensures that any threads clone()'d early
* in the process's lifetime will not accidentally get access
* to data which is pkey-protected later on.
*/
u32 init_pkru_value = PKRU_AD_KEY( 1) | PKRU_AD_KEY( 2) | PKRU_AD_KEY( 3) |
PKRU_AD_KEY( 4) | PKRU_AD_KEY( 5) | PKRU_AD_KEY( 6) |
PKRU_AD_KEY( 7) | PKRU_AD_KEY( 8) | PKRU_AD_KEY( 9) |
PKRU_AD_KEY(10) | PKRU_AD_KEY(11) | PKRU_AD_KEY(12) |
PKRU_AD_KEY(13) | PKRU_AD_KEY(14) | PKRU_AD_KEY(15);
/*
* Called from the FPU code when creating a fresh set of FPU
* registers. This is called from a very specific context where
* we know the FPU regstiers are safe for use and we can use PKRU
* directly. The fact that PKRU is only available when we are
* using eagerfpu mode makes this possible.
*/
void copy_init_pkru_to_fpregs(void)
{
u32 init_pkru_value_snapshot = READ_ONCE(init_pkru_value);
/*
* Any write to PKRU takes it out of the XSAVE 'init
* state' which increases context switch cost. Avoid
* writing 0 when PKRU was already 0.
*/
if (!init_pkru_value_snapshot && !read_pkru())
return;
/*
* Override the PKRU state that came from 'init_fpstate'
* with the baseline from the process.
*/
write_pkru(init_pkru_value_snapshot);
}
static ssize_t init_pkru_read_file(struct file *file, char __user *user_buf,
size_t count, loff_t *ppos)
{
char buf[32];
unsigned int len;
len = sprintf(buf, "0x%x\n", init_pkru_value);
return simple_read_from_buffer(user_buf, count, ppos, buf, len);
}
static ssize_t init_pkru_write_file(struct file *file,
const char __user *user_buf, size_t count, loff_t *ppos)
{
char buf[32];
ssize_t len;
u32 new_init_pkru;
len = min(count, sizeof(buf) - 1);
if (copy_from_user(buf, user_buf, len))
return -EFAULT;
/* Make the buffer a valid string that we can not overrun */
buf[len] = '\0';
if (kstrtouint(buf, 0, &new_init_pkru))
return -EINVAL;
/*
* Don't allow insane settings that will blow the system
* up immediately if someone attempts to disable access
* or writes to pkey 0.
*/
if (new_init_pkru & (PKRU_AD_BIT|PKRU_WD_BIT))
return -EINVAL;
WRITE_ONCE(init_pkru_value, new_init_pkru);
return count;
}
static const struct file_operations fops_init_pkru = {
.read = init_pkru_read_file,
.write = init_pkru_write_file,
.llseek = default_llseek,
};
static int __init create_init_pkru_value(void)
{
debugfs_create_file("init_pkru", S_IRUSR | S_IWUSR,
arch_debugfs_dir, NULL, &fops_init_pkru);
return 0;
}
late_initcall(create_init_pkru_value);
static __init int setup_init_pkru(char *opt)
{
u32 new_init_pkru;
if (kstrtouint(opt, 0, &new_init_pkru))
return 1;
WRITE_ONCE(init_pkru_value, new_init_pkru);
return 1;
}
__setup("init_pkru=", setup_init_pkru);