- Print the CPU number at segfault time. The number printed is not

always accurate (preemption is enabled at that time) but the print string
   contains "likely" and after a lot of back'n'forth on this, this was the
   consensus that was reached. See thread starting at:
   https://lore.kernel.org/r/5d62c1d0-7425-d5bb-ecb5-1dc3b4d7d245@intel.com
 
 - After a *lot* of testing and polishing, finally the clear_user()
   improvements to inline REP; STOSB by default
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEzv7L6UO9uDPlPSfHEsHwGGHeVUoFAmM780YACgkQEsHwGGHe
 VUoVmRAAhTTUYqe81XRAX1Egge1RVwXgZFZQQD54239IveLt80kpg1AFR697z3/G
 GSaL5dy9/LEwyE0r9u7VN1SuY3Bz8LEZLYfurKlGfMGv3mlcUedLSWHQNaNZ4+cx
 nwP1VjrfH80Qwn7l99hOZ7kwCRlUWdsamcMsv6n7Fq0YnM7vW6MgmQGlqCGADQKI
 GGElgn3VaU5pEXF4YtZE0qfy17dgkW+RJD7RlaAtzmKcdKYiKgfX0Mh9bkQ5VVcb
 973peg9GHKHoP0w54LYKNgF/WkYPpBwcNIkJW//aMLGS5ofalliu0W281okAhZ7w
 Sknnx+umoprCAV9ljn/HZbQnseXPXKlZWUxiwfEZD2fcBI6+60HK86zVSEvrYxNs
 COZRhpj/bwvOt5LtNj7dcV6cbbBvJJIEJSNazXHscds2zUh79fidzkjZ/Z0Hbo7D
 sr7SM80STaURGFPTLoD41z4TY3V2GH8JUbWG9+I4fBjmSDyX+tQKKJhH886MRSSW
 ZQ0pY1uhwF8QBMlp3t87pZ2gbdjMr40PSYJGU+Xqsb/khq7xOWnP1CiIkVUHLF2L
 n/hm6VF6ifwFstFhOBc8nTcz7kGqzKvlQssFpf+DAIl/b7mZ3AKHVIJxTpZ1hcis
 BqQdeNcVEcNCRZWFzrG5hCs0b7xtaJrI30RPSMsQP2IcaX+DNyg=
 =xLSS
 -----END PGP SIGNATURE-----

Merge tag 'x86_cpu_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cpu updates from Borislav Petkov:

 - Print the CPU number at segfault time.

   The number printed is not always accurate (preemption is enabled at
   that time) but the print string contains "likely" and after a lot of
   back'n'forth on this, this was the consensus that was reached. See
   thread at [1].

 - After a *lot* of testing and polishing, finally the clear_user()
   improvements to inline REP; STOSB by default

Link: https://lore.kernel.org/r/5d62c1d0-7425-d5bb-ecb5-1dc3b4d7d245@intel.com [1]

* tag 'x86_cpu_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Print likely CPU at segfault time
  x86/clear_user: Make it faster
This commit is contained in:
Linus Torvalds 2022-10-04 09:21:30 -07:00
commit 7db99f01d1
6 changed files with 198 additions and 43 deletions

View File

@ -502,9 +502,6 @@ strncpy_from_user(char *dst, const char __user *src, long count);
extern __must_check long strnlen_user(const char __user *str, long n);
unsigned long __must_check clear_user(void __user *mem, unsigned long len);
unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
#ifdef CONFIG_ARCH_HAS_COPY_MC
unsigned long __must_check
copy_mc_to_kernel(void *to, const void *from, unsigned len);
@ -526,6 +523,8 @@ extern struct movsl_mask {
#define ARCH_HAS_NOCACHE_UACCESS 1
#ifdef CONFIG_X86_32
unsigned long __must_check clear_user(void __user *mem, unsigned long len);
unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
# include <asm/uaccess_32.h>
#else
# include <asm/uaccess_64.h>

View File

@ -79,4 +79,49 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
kasan_check_write(dst, size);
return __copy_user_flushcache(dst, src, size);
}
/*
* Zero Userspace.
*/
__must_check unsigned long
clear_user_original(void __user *addr, unsigned long len);
__must_check unsigned long
clear_user_rep_good(void __user *addr, unsigned long len);
__must_check unsigned long
clear_user_erms(void __user *addr, unsigned long len);
static __always_inline __must_check unsigned long __clear_user(void __user *addr, unsigned long size)
{
might_fault();
stac();
/*
* No memory constraint because it doesn't change any memory gcc
* knows about.
*/
asm volatile(
"1:\n\t"
ALTERNATIVE_3("rep stosb",
"call clear_user_erms", ALT_NOT(X86_FEATURE_FSRM),
"call clear_user_rep_good", ALT_NOT(X86_FEATURE_ERMS),
"call clear_user_original", ALT_NOT(X86_FEATURE_REP_GOOD))
"2:\n"
_ASM_EXTABLE_UA(1b, 2b)
: "+c" (size), "+D" (addr), ASM_CALL_CONSTRAINT
: "a" (0)
/* rep_good clobbers %rdx */
: "rdx");
clac();
return size;
}
static __always_inline unsigned long clear_user(void __user *to, unsigned long n)
{
if (access_ok(to, n))
return __clear_user(to, n);
return n;
}
#endif /* _ASM_X86_UACCESS_64_H */

View File

@ -1,5 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0-only */
#include <linux/linkage.h>
#include <asm/asm.h>
#include <asm/export.h>
/*
@ -50,3 +51,140 @@ SYM_FUNC_START(clear_page_erms)
RET
SYM_FUNC_END(clear_page_erms)
EXPORT_SYMBOL_GPL(clear_page_erms)
/*
* Default clear user-space.
* Input:
* rdi destination
* rcx count
*
* Output:
* rcx: uncleared bytes or 0 if successful.
*/
SYM_FUNC_START(clear_user_original)
/*
* Copy only the lower 32 bits of size as that is enough to handle the rest bytes,
* i.e., no need for a 'q' suffix and thus a REX prefix.
*/
mov %ecx,%eax
shr $3,%rcx
jz .Lrest_bytes
# do the qwords first
.p2align 4
.Lqwords:
movq $0,(%rdi)
lea 8(%rdi),%rdi
dec %rcx
jnz .Lqwords
.Lrest_bytes:
and $7, %eax
jz .Lexit
# now do the rest bytes
.Lbytes:
movb $0,(%rdi)
inc %rdi
dec %eax
jnz .Lbytes
.Lexit:
/*
* %rax still needs to be cleared in the exception case because this function is called
* from inline asm and the compiler expects %rax to be zero when exiting the inline asm,
* in case it might reuse it somewhere.
*/
xor %eax,%eax
RET
.Lqwords_exception:
# convert remaining qwords back into bytes to return to caller
shl $3, %rcx
and $7, %eax
add %rax,%rcx
jmp .Lexit
.Lbytes_exception:
mov %eax,%ecx
jmp .Lexit
_ASM_EXTABLE_UA(.Lqwords, .Lqwords_exception)
_ASM_EXTABLE_UA(.Lbytes, .Lbytes_exception)
SYM_FUNC_END(clear_user_original)
EXPORT_SYMBOL(clear_user_original)
/*
* Alternative clear user-space when CPU feature X86_FEATURE_REP_GOOD is
* present.
* Input:
* rdi destination
* rcx count
*
* Output:
* rcx: uncleared bytes or 0 if successful.
*/
SYM_FUNC_START(clear_user_rep_good)
# call the original thing for less than a cacheline
cmp $64, %rcx
jb clear_user_original
.Lprep:
# copy lower 32-bits for rest bytes
mov %ecx, %edx
shr $3, %rcx
jz .Lrep_good_rest_bytes
.Lrep_good_qwords:
rep stosq
.Lrep_good_rest_bytes:
and $7, %edx
jz .Lrep_good_exit
.Lrep_good_bytes:
mov %edx, %ecx
rep stosb
.Lrep_good_exit:
# see .Lexit comment above
xor %eax, %eax
RET
.Lrep_good_qwords_exception:
# convert remaining qwords back into bytes to return to caller
shl $3, %rcx
and $7, %edx
add %rdx, %rcx
jmp .Lrep_good_exit
_ASM_EXTABLE_UA(.Lrep_good_qwords, .Lrep_good_qwords_exception)
_ASM_EXTABLE_UA(.Lrep_good_bytes, .Lrep_good_exit)
SYM_FUNC_END(clear_user_rep_good)
EXPORT_SYMBOL(clear_user_rep_good)
/*
* Alternative clear user-space when CPU feature X86_FEATURE_ERMS is present.
* Input:
* rdi destination
* rcx count
*
* Output:
* rcx: uncleared bytes or 0 if successful.
*
*/
SYM_FUNC_START(clear_user_erms)
# call the original thing for less than a cacheline
cmp $64, %rcx
jb clear_user_original
.Lerms_bytes:
rep stosb
.Lerms_exit:
xorl %eax,%eax
RET
_ASM_EXTABLE_UA(.Lerms_bytes, .Lerms_exit)
SYM_FUNC_END(clear_user_erms)
EXPORT_SYMBOL(clear_user_erms)

View File

@ -14,46 +14,6 @@
* Zero Userspace
*/
unsigned long __clear_user(void __user *addr, unsigned long size)
{
long __d0;
might_fault();
/* no memory constraint because it doesn't change any memory gcc knows
about */
stac();
asm volatile(
" testq %[size8],%[size8]\n"
" jz 4f\n"
" .align 16\n"
"0: movq $0,(%[dst])\n"
" addq $8,%[dst]\n"
" decl %%ecx ; jnz 0b\n"
"4: movq %[size1],%%rcx\n"
" testl %%ecx,%%ecx\n"
" jz 2f\n"
"1: movb $0,(%[dst])\n"
" incq %[dst]\n"
" decl %%ecx ; jnz 1b\n"
"2:\n"
_ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN8, %[size1])
_ASM_EXTABLE_UA(1b, 2b)
: [size8] "=&c"(size), [dst] "=&D" (__d0)
: [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr));
clac();
return size;
}
EXPORT_SYMBOL(__clear_user);
unsigned long clear_user(void __user *to, unsigned long n)
{
if (access_ok(to, n))
return __clear_user(to, n);
return n;
}
EXPORT_SYMBOL(clear_user);
#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
/**
* clean_cache_range - write back a cache range with CLWB

View File

@ -769,6 +769,8 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
unsigned long address, struct task_struct *tsk)
{
const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG;
/* This is a racy snapshot, but it's better than nothing. */
int cpu = raw_smp_processor_id();
if (!unhandled_signal(tsk, SIGSEGV))
return;
@ -782,6 +784,14 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code,
print_vma_addr(KERN_CONT " in ", regs->ip);
/*
* Dump the likely CPU where the fatal segfault happened.
* This can help identify faulty hardware.
*/
printk(KERN_CONT " likely on CPU %d (core %d, socket %d)", cpu,
topology_core_id(cpu), topology_physical_package_id(cpu));
printk(KERN_CONT "\n");
show_opcodes(regs, loglvl);

View File

@ -1073,6 +1073,9 @@ static const char *uaccess_safe_builtin[] = {
"copy_mc_fragile_handle_tail",
"copy_mc_enhanced_fast_string",
"ftrace_likely_update", /* CONFIG_TRACE_BRANCH_PROFILING */
"clear_user_erms",
"clear_user_rep_good",
"clear_user_original",
NULL
};