linux-yocto/tools/testing/selftests/mm/pkey-helpers.h
Linus Torvalds 70f43ea3a3 Updates for x86 memory management:
- Make LAM enablement safe vs. kernel threads using a process mm
    temporarily as switching back to the process would not update CR3 and
    therefore not enable LAM causing faults in user space when using tagged
    pointers. Cure it by synchronizing LAM enablement via IPIs to all CPUs
    which use the related mm.
 
  - Cure a LAM harmless inconsistency between CR3 and the state during
    context switch. It's both confusing and prone to lead to real bugs
 
  - Handle alt stack handling for threads which run with a non-zero
    protection key. The non-zero key prevents the kernel to access the
    alternate stack. Cure it by temporarily enabling all protection keys for
    the alternate stack setup/restore operations.
 
  - Provide a EFI config table identity mapping for kexec kernel to prevent
    kexec fails because the new kernel cannot access the config table array
 
  - Use GB pages only when a full GB is mapped in the identity map as
    otherwise the CPU can speculate into reserved areas after the end of
    memory which causes malfunction on UV systems.
 
  - Remove the noisy and pointless SRAT table dump during boot
 
  - Use is_ioremap_addr() for iounmap() address range checks instead of
    high_memory. is_ioremap_addr() is more precise.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEQp8+kY+LLUocC4bMphj1TA10mKEFAmbpPpYTHHRnbHhAbGlu
 dXRyb25peC5kZQAKCRCmGPVMDXSYoYddD/9HeH5/rpWS3JU4ZVC+huY28uJuwAFW
 ER48zniRbmuz8y+dZZ6K8uvqoWB+ro+yNjA9Jhm9nHUzhs7kE5O8+bmkUi6HXViW
 6zS6PW95+u80dmSGy1Gna0SU3158OyBf2X61SySJABLLek7WwrR7jakkgrDBVtL5
 ILKS/dUwIrUPoVlszCh9uE0Kj6gdFquooE06sif5EIibnhSgSXfr2EbGj0Qq/YYf
 FYfpggSSVpTXFSkZSB2VCEqK66jaGUfKzZ6v1DkSioChUCsky2OO6zD9pk0dMixO
 a/0XvRUo3OhiXZbj1tPUtxaEBgJdigpsxke7xQSVxSl+DNNuapiybpgAzFM5Xh+m
 yFcP66nIpJcHE10vjVR3jSUlTSb2zk+v9d1Ujj10G1h8RHLTfsTCRHgzs7P0/nkE
 NJleWstYVRV5rFpPLoY0ryQmjW/PzYokkaqWKI12Lhxg4ojijZso3pS8WfOsk1/B
 081tOZERWeGnJEOOJwwYE1wt0Qq8th4S9b2/fz3vk2fsEHIf42s4fKQwy1CxKopb
 PyIrgnZyWx6ueX9QaIGIzGV1GsY4FKMgFJVOyVb0D0stMnr1ty2m3993eNs/nCXy
 +rHPMwFteLcwiWp/C3hq5IQd7uEvmRt/mYJ5hdvCj5wCIkXI3JtgsXfLSVs3Ln4f
 R6HvZehYmbJoNQ==
 =VZcR
 -----END PGP SIGNATURE-----

Merge tag 'x86-mm-2024-09-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 memory management updates from Thomas Gleixner:

 - Make LAM enablement safe vs. kernel threads using a process mm
   temporarily as switching back to the process would not update CR3 and
   therefore not enable LAM causing faults in user space when using
   tagged pointers. Cure it by synchronizing LAM enablement via IPIs to
   all CPUs which use the related mm.

 - Cure a LAM harmless inconsistency between CR3 and the state during
   context switch. It's both confusing and prone to lead to real bugs

 - Handle alt stack handling for threads which run with a non-zero
   protection key. The non-zero key prevents the kernel to access the
   alternate stack. Cure it by temporarily enabling all protection keys
   for the alternate stack setup/restore operations.

 - Provide a EFI config table identity mapping for kexec kernel to
   prevent kexec fails because the new kernel cannot access the config
   table array

 - Use GB pages only when a full GB is mapped in the identity map as
   otherwise the CPU can speculate into reserved areas after the end of
   memory which causes malfunction on UV systems.

 - Remove the noisy and pointless SRAT table dump during boot

 - Use is_ioremap_addr() for iounmap() address range checks instead of
   high_memory. is_ioremap_addr() is more precise.

* tag 'x86-mm-2024-09-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/ioremap: Improve iounmap() address range checks
  x86/mm: Remove duplicate check from build_cr3()
  x86/mm: Remove unused NX related declarations
  x86/mm: Remove unused CR3_HW_ASID_BITS
  x86/mm: Don't print out SRAT table information
  x86/mm/ident_map: Use gbpages only where full GB page should be mapped.
  x86/kexec: Add EFI config table identity mapping for kexec kernel
  selftests/mm: Add new testcases for pkeys
  x86/pkeys: Restore altstack access in sigreturn()
  x86/pkeys: Update PKRU to enable all pkeys before XSAVE
  x86/pkeys: Add helper functions to update PKRU on the sigframe
  x86/pkeys: Add PKRU as a parameter in signal handling functions
  x86/mm: Cleanup prctl_enable_tagged_addr() nr_bits error checking
  x86/mm: Fix LAM inconsistency during context switch
  x86/mm: Use IPIs to synchronize LAM enablement
2024-09-17 15:03:01 +02:00

246 lines
5.7 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _PKEYS_HELPER_H
#define _PKEYS_HELPER_H
#define _GNU_SOURCE
#include <string.h>
#include <stdarg.h>
#include <stdio.h>
#include <stdint.h>
#include <stdbool.h>
#include <signal.h>
#include <assert.h>
#include <stdlib.h>
#include <ucontext.h>
#include <sys/mman.h>
#include "../kselftest.h"
/* Define some kernel-like types */
#define u8 __u8
#define u16 __u16
#define u32 __u32
#define u64 __u64
#define PTR_ERR_ENOTSUP ((void *)-ENOTSUP)
#ifndef DEBUG_LEVEL
#define DEBUG_LEVEL 0
#endif
#define DPRINT_IN_SIGNAL_BUF_SIZE 4096
extern int dprint_in_signal;
extern char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];
extern int test_nr;
extern int iteration_nr;
#ifdef __GNUC__
__printf(1, 2)
#endif
static inline void sigsafe_printf(const char *format, ...)
{
va_list ap;
if (!dprint_in_signal) {
va_start(ap, format);
vprintf(format, ap);
va_end(ap);
} else {
int ret;
/*
* No printf() functions are signal-safe.
* They deadlock easily. Write the format
* string to get some output, even if
* incomplete.
*/
ret = write(1, format, strlen(format));
if (ret < 0)
exit(1);
}
}
#define dprintf_level(level, args...) do { \
if (level <= DEBUG_LEVEL) \
sigsafe_printf(args); \
} while (0)
#define dprintf0(args...) dprintf_level(0, args)
#define dprintf1(args...) dprintf_level(1, args)
#define dprintf2(args...) dprintf_level(2, args)
#define dprintf3(args...) dprintf_level(3, args)
#define dprintf4(args...) dprintf_level(4, args)
extern void abort_hooks(void);
#define pkey_assert(condition) do { \
if (!(condition)) { \
dprintf0("assert() at %s::%d test_nr: %d iteration: %d\n", \
__FILE__, __LINE__, \
test_nr, iteration_nr); \
dprintf0("errno at assert: %d", errno); \
abort_hooks(); \
exit(__LINE__); \
} \
} while (0)
#define barrier() __asm__ __volatile__("": : :"memory")
#ifndef noinline
# define noinline __attribute__((noinline))
#endif
noinline int read_ptr(int *ptr)
{
/* Keep GCC from optimizing this away somehow */
barrier();
return *ptr;
}
void expected_pkey_fault(int pkey);
int sys_pkey_alloc(unsigned long flags, unsigned long init_val);
int sys_pkey_free(unsigned long pkey);
int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
unsigned long pkey);
void record_pkey_malloc(void *ptr, long size, int prot);
#if defined(__i386__) || defined(__x86_64__) /* arch */
#include "pkey-x86.h"
#elif defined(__powerpc64__) /* arch */
#include "pkey-powerpc.h"
#elif defined(__aarch64__) /* arch */
#include "pkey-arm64.h"
#else /* arch */
#error Architecture not supported
#endif /* arch */
#ifndef PKEY_MASK
#define PKEY_MASK (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE)
#endif
#ifndef set_pkey_bits
static inline u64 set_pkey_bits(u64 reg, int pkey, u64 flags)
{
u32 shift = pkey_bit_position(pkey);
/* mask out bits from pkey in old value */
reg &= ~((u64)PKEY_MASK << shift);
/* OR in new bits for pkey */
reg |= (flags & PKEY_MASK) << shift;
return reg;
}
#endif
#ifndef get_pkey_bits
static inline u64 get_pkey_bits(u64 reg, int pkey)
{
u32 shift = pkey_bit_position(pkey);
/*
* shift down the relevant bits to the lowest two, then
* mask off all the other higher bits
*/
return ((reg >> shift) & PKEY_MASK);
}
#endif
extern u64 shadow_pkey_reg;
static inline u64 _read_pkey_reg(int line)
{
u64 pkey_reg = __read_pkey_reg();
dprintf4("read_pkey_reg(line=%d) pkey_reg: %016llx"
" shadow: %016llx\n",
line, pkey_reg, shadow_pkey_reg);
assert(pkey_reg == shadow_pkey_reg);
return pkey_reg;
}
#define read_pkey_reg() _read_pkey_reg(__LINE__)
static inline void write_pkey_reg(u64 pkey_reg)
{
dprintf4("%s() changing %016llx to %016llx\n", __func__,
__read_pkey_reg(), pkey_reg);
/* will do the shadow check for us: */
read_pkey_reg();
__write_pkey_reg(pkey_reg);
shadow_pkey_reg = pkey_reg;
dprintf4("%s(%016llx) pkey_reg: %016llx\n", __func__,
pkey_reg, __read_pkey_reg());
}
/*
* These are technically racy. since something could
* change PKEY register between the read and the write.
*/
static inline void __pkey_access_allow(int pkey, int do_allow)
{
u64 pkey_reg = read_pkey_reg();
int bit = pkey * 2;
if (do_allow)
pkey_reg &= (1<<bit);
else
pkey_reg |= (1<<bit);
dprintf4("pkey_reg now: %016llx\n", read_pkey_reg());
write_pkey_reg(pkey_reg);
}
static inline void __pkey_write_allow(int pkey, int do_allow_write)
{
u64 pkey_reg = read_pkey_reg();
int bit = pkey * 2 + 1;
if (do_allow_write)
pkey_reg &= (1<<bit);
else
pkey_reg |= (1<<bit);
write_pkey_reg(pkey_reg);
dprintf4("pkey_reg now: %016llx\n", read_pkey_reg());
}
#define ALIGN_UP(x, align_to) (((x) + ((align_to)-1)) & ~((align_to)-1))
#define ALIGN_DOWN(x, align_to) ((x) & ~((align_to)-1))
#define ALIGN_PTR_UP(p, ptr_align_to) \
((typeof(p))ALIGN_UP((unsigned long)(p), ptr_align_to))
#define ALIGN_PTR_DOWN(p, ptr_align_to) \
((typeof(p))ALIGN_DOWN((unsigned long)(p), ptr_align_to))
#define __stringify_1(x...) #x
#define __stringify(x...) __stringify_1(x)
static inline u32 *siginfo_get_pkey_ptr(siginfo_t *si)
{
#ifdef si_pkey
return &si->si_pkey;
#else
return (u32 *)(((u8 *)si) + si_pkey_offset);
#endif
}
static inline int kernel_has_pkeys(void)
{
/* try allocating a key and see if it succeeds */
int ret = sys_pkey_alloc(0, 0);
if (ret <= 0) {
return 0;
}
sys_pkey_free(ret);
return 1;
}
static inline int is_pkeys_supported(void)
{
/* check if the cpu supports pkeys */
if (!cpu_has_pkeys()) {
dprintf1("SKIP: %s: no CPU support\n", __func__);
return 0;
}
/* check if the kernel supports pkeys */
if (!kernel_has_pkeys()) {
dprintf1("SKIP: %s: no kernel support\n", __func__);
return 0;
}
return 1;
}
#endif /* _PKEYS_HELPER_H */