提交 0f657262 编写于 作者: L Linus Torvalds

Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm updates from Ingo Molnar:
 "Various x86 low level modifications:

   - preparatory work to support virtually mapped kernel stacks (Andy
     Lutomirski)

   - support for 64-bit __get_user() on 32-bit kernels (Benjamin
     LaHaise)

   - (involved) workaround for Knights Landing CPU erratum (Dave Hansen)

   - MPX enhancements (Dave Hansen)

   - mremap() extension to allow remapping of the special VDSO vma, for
     purposes of user level context save/restore (Dmitry Safonov)

   - hweight and entry code cleanups (Borislav Petkov)

   - bitops code generation optimizations and cleanups with modern GCC
     (H. Peter Anvin)

   - syscall entry code optimizations (Paolo Bonzini)"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (43 commits)
  x86/mm/cpa: Add missing comment in populate_pdg()
  x86/mm/cpa: Fix populate_pgd(): Stop trying to deallocate failed PUDs
  x86/syscalls: Add compat_sys_preadv64v2/compat_sys_pwritev64v2
  x86/smp: Remove unnecessary initialization of thread_info::cpu
  x86/smp: Remove stack_smp_processor_id()
  x86/uaccess: Move thread_info::addr_limit to thread_struct
  x86/dumpstack: Rename thread_struct::sig_on_uaccess_error to sig_on_uaccess_err
  x86/uaccess: Move thread_info::uaccess_err and thread_info::sig_on_uaccess_err to thread_struct
  x86/dumpstack: When OOPSing, rewind the stack before do_exit()
  x86/mm/64: In vmalloc_fault(), use CR3 instead of current->active_mm
  x86/dumpstack/64: Handle faults when printing the "Stack: " part of an OOPS
  x86/dumpstack: Try harder to get a call trace on stack overflow
  x86/mm: Remove kernel_unmap_pages_in_pgd() and efi_cleanup_page_tables()
  x86/mm/cpa: In populate_pgd(), don't set the PGD entry until it's populated
  x86/mm/hotplug: Don't remove PGD entries in remove_pagetable()
  x86/mm: Use pte_none() to test for empty PTE
  x86/mm: Disallow running with 32-bit PTEs to work around erratum
  x86/mm: Ignore A/D bits in pte/pmd/pud_none()
  x86/mm: Move swap offset/type up in PTE to work around erratum
  x86/entry: Inline enter_from_user_mode()
  ...
......@@ -294,11 +294,6 @@ config X86_32_LAZY_GS
def_bool y
depends on X86_32 && !CC_STACKPROTECTOR
config ARCH_HWEIGHT_CFLAGS
string
default "-fcall-saved-ecx -fcall-saved-edx" if X86_32
default "-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11" if X86_64
config ARCH_SUPPORTS_UPROBES
def_bool y
......
......@@ -16,14 +16,16 @@
#define BOOT_BITOPS_H
#define _LINUX_BITOPS_H /* Inhibit inclusion of <linux/bitops.h> */
static inline int constant_test_bit(int nr, const void *addr)
#include <linux/types.h>
static inline bool constant_test_bit(int nr, const void *addr)
{
const u32 *p = (const u32 *)addr;
return ((1UL << (nr & 31)) & (p[nr >> 5])) != 0;
}
static inline int variable_test_bit(int nr, const void *addr)
static inline bool variable_test_bit(int nr, const void *addr)
{
u8 v;
bool v;
const u32 *p = (const u32 *)addr;
asm("btl %2,%1; setc %0" : "=qm" (v) : "m" (*p), "Ir" (nr));
......
......@@ -24,6 +24,7 @@
#include <linux/types.h>
#include <linux/edd.h>
#include <asm/setup.h>
#include <asm/asm.h>
#include "bitops.h"
#include "ctype.h"
#include "cpuflags.h"
......@@ -176,18 +177,18 @@ static inline void wrgs32(u32 v, addr_t addr)
}
/* Note: these only return true/false, not a signed return value! */
static inline int memcmp_fs(const void *s1, addr_t s2, size_t len)
static inline bool memcmp_fs(const void *s1, addr_t s2, size_t len)
{
u8 diff;
asm volatile("fs; repe; cmpsb; setnz %0"
: "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
bool diff;
asm volatile("fs; repe; cmpsb" CC_SET(nz)
: CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
return diff;
}
static inline int memcmp_gs(const void *s1, addr_t s2, size_t len)
static inline bool memcmp_gs(const void *s1, addr_t s2, size_t len)
{
u8 diff;
asm volatile("gs; repe; cmpsb; setnz %0"
: "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
bool diff;
asm volatile("gs; repe; cmpsb" CC_SET(nz)
: CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
return diff;
}
......@@ -294,6 +295,7 @@ static inline int cmdline_find_option_bool(const char *option)
/* cpu.c, cpucheck.c */
int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr);
int check_knl_erratum(void);
int validate_cpu(void);
/* early_serial_console.c */
......
......@@ -93,6 +93,8 @@ int validate_cpu(void)
show_cap_strs(err_flags);
putchar('\n');
return -1;
} else if (check_knl_erratum()) {
return -1;
} else {
return 0;
}
......
......@@ -24,6 +24,7 @@
# include "boot.h"
#endif
#include <linux/types.h>
#include <asm/intel-family.h>
#include <asm/processor-flags.h>
#include <asm/required-features.h>
#include <asm/msr-index.h>
......@@ -175,6 +176,8 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
puts("WARNING: PAE disabled. Use parameter 'forcepae' to enable at your own risk!\n");
}
}
if (!err)
err = check_knl_erratum();
if (err_flags_ptr)
*err_flags_ptr = err ? err_flags : NULL;
......@@ -185,3 +188,33 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
return (cpu.level < req_level || err) ? -1 : 0;
}
int check_knl_erratum(void)
{
/*
* First check for the affected model/family:
*/
if (!is_intel() ||
cpu.family != 6 ||
cpu.model != INTEL_FAM6_XEON_PHI_KNL)
return 0;
/*
* This erratum affects the Accessed/Dirty bits, and can
* cause stray bits to be set in !Present PTEs. We have
* enough bits in our 64-bit PTEs (which we have on real
* 64-bit mode or PAE) to avoid using these troublesome
* bits. But, we do not have enough space in our 32-bit
* PTEs. So, refuse to run on 32-bit non-PAE kernels.
*/
if (IS_ENABLED(CONFIG_X86_64) || IS_ENABLED(CONFIG_X86_PAE))
return 0;
puts("This 32-bit kernel can not run on this Xeon Phi x200\n"
"processor due to a processor erratum. Use a 64-bit\n"
"kernel, or enable PAE in this 32-bit kernel.\n\n");
return -1;
}
......@@ -102,6 +102,7 @@ void get_cpuflags(void)
cpuid(0x1, &tfms, &ignored, &cpu.flags[4],
&cpu.flags[0]);
cpu.level = (tfms >> 8) & 15;
cpu.family = cpu.level;
cpu.model = (tfms >> 4) & 15;
if (cpu.level >= 6)
cpu.model += ((tfms >> 16) & 0xf) << 4;
......
......@@ -6,6 +6,7 @@
struct cpu_features {
int level; /* Family, or 64 for x86-64 */
int family; /* Family, always */
int model;
u32 flags[NCAPINTS];
};
......
......@@ -17,7 +17,7 @@
int memcmp(const void *s1, const void *s2, size_t len)
{
u8 diff;
bool diff;
asm("repe; cmpsb; setnz %0"
: "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
return diff;
......
......@@ -40,10 +40,10 @@ static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs)
#ifdef CONFIG_CONTEXT_TRACKING
/* Called on entry from user mode with IRQs off. */
__visible void enter_from_user_mode(void)
__visible inline void enter_from_user_mode(void)
{
CT_WARN_ON(ct_state() != CONTEXT_USER);
user_exit();
user_exit_irqoff();
}
#else
static inline void enter_from_user_mode(void) {}
......@@ -274,7 +274,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
ti->status &= ~TS_COMPAT;
#endif
user_enter();
user_enter_irqoff();
}
#define SYSCALL_EXIT_WORK_FLAGS \
......
......@@ -1153,3 +1153,14 @@ ENTRY(async_page_fault)
jmp error_code
END(async_page_fault)
#endif
ENTRY(rewind_stack_do_exit)
/* Prevent any naive code from trying to unwind to our caller. */
xorl %ebp, %ebp
movl PER_CPU_VAR(cpu_current_top_of_stack), %esi
leal -TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp
call do_exit
1: jmp 1b
END(rewind_stack_do_exit)
......@@ -1423,3 +1423,14 @@ ENTRY(ignore_sysret)
mov $-ENOSYS, %eax
sysret
END(ignore_sysret)
ENTRY(rewind_stack_do_exit)
/* Prevent any naive code from trying to unwind to our caller. */
xorl %ebp, %ebp
movq PER_CPU_VAR(cpu_current_top_of_stack), %rax
leaq -TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%rax), %rsp
call do_exit
1: jmp 1b
END(rewind_stack_do_exit)
......@@ -374,5 +374,5 @@
543 x32 io_setup compat_sys_io_setup
544 x32 io_submit compat_sys_io_submit
545 x32 execveat compat_sys_execveat/ptregs
534 x32 preadv2 compat_sys_preadv2
535 x32 pwritev2 compat_sys_pwritev2
546 x32 preadv2 compat_sys_preadv64v2
547 x32 pwritev2 compat_sys_pwritev64v2
......@@ -33,7 +33,7 @@
.endif
call \func
jmp restore
jmp .L_restore
_ASM_NOKPROBE(\name)
.endm
......@@ -54,7 +54,7 @@
#if defined(CONFIG_TRACE_IRQFLAGS) \
|| defined(CONFIG_DEBUG_LOCK_ALLOC) \
|| defined(CONFIG_PREEMPT)
restore:
.L_restore:
popq %r11
popq %r10
popq %r9
......@@ -66,5 +66,5 @@ restore:
popq %rdi
popq %rbp
ret
_ASM_NOKPROBE(restore)
_ASM_NOKPROBE(.L_restore)
#endif
......@@ -134,7 +134,7 @@ VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
override obj-dirs = $(dir $(obj)) $(obj)/vdso32/
targets += vdso32/vdso32.lds
targets += vdso32/note.o vdso32/vclock_gettime.o vdso32/system_call.o
targets += vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o
targets += vdso32/vclock_gettime.o
KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS)) -DBUILD_VDSO
......@@ -156,7 +156,8 @@ $(obj)/vdso32.so.dbg: FORCE \
$(obj)/vdso32/vdso32.lds \
$(obj)/vdso32/vclock_gettime.o \
$(obj)/vdso32/note.o \
$(obj)/vdso32/system_call.o
$(obj)/vdso32/system_call.o \
$(obj)/vdso32/sigreturn.o
$(call if_changed,vdso)
#
......
/*
* Common code for the sigreturn entry points in vDSO images.
* So far this code is the same for both int80 and sysenter versions.
* This file is #include'd by int80.S et al to define them first thing.
* The kernel assumes that the addresses of these routines are constant
* for all vDSO implementations.
*/
#include <linux/linkage.h>
#include <asm/unistd_32.h>
#include <asm/asm-offsets.h>
......
......@@ -2,16 +2,11 @@
* AT_SYSINFO entry point
*/
#include <linux/linkage.h>
#include <asm/dwarf2.h>
#include <asm/cpufeatures.h>
#include <asm/alternative-asm.h>
/*
* First get the common code for the sigreturn entry points.
* This must come first.
*/
#include "sigreturn.S"
.text
.globl __kernel_vsyscall
.type __kernel_vsyscall,@function
......
......@@ -12,6 +12,7 @@
#include <linux/random.h>
#include <linux/elf.h>
#include <linux/cpu.h>
#include <linux/ptrace.h>
#include <asm/pvclock.h>
#include <asm/vgtod.h>
#include <asm/proto.h>
......@@ -97,10 +98,40 @@ static int vdso_fault(const struct vm_special_mapping *sm,
return 0;
}
static const struct vm_special_mapping text_mapping = {
.name = "[vdso]",
.fault = vdso_fault,
};
static void vdso_fix_landing(const struct vdso_image *image,
struct vm_area_struct *new_vma)
{
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
if (in_ia32_syscall() && image == &vdso_image_32) {
struct pt_regs *regs = current_pt_regs();
unsigned long vdso_land = image->sym_int80_landing_pad;
unsigned long old_land_addr = vdso_land +
(unsigned long)current->mm->context.vdso;
/* Fixing userspace landing - look at do_fast_syscall_32 */
if (regs->ip == old_land_addr)
regs->ip = new_vma->vm_start + vdso_land;
}
#endif
}
static int vdso_mremap(const struct vm_special_mapping *sm,
struct vm_area_struct *new_vma)
{
unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
const struct vdso_image *image = current->mm->context.vdso_image;
if (image->size != new_size)
return -EINVAL;
if (WARN_ON_ONCE(current->mm != new_vma->vm_mm))
return -EFAULT;
vdso_fix_landing(image, new_vma);
current->mm->context.vdso = (void __user *)new_vma->vm_start;
return 0;
}
static int vvar_fault(const struct vm_special_mapping *sm,
struct vm_area_struct *vma, struct vm_fault *vmf)
......@@ -151,6 +182,12 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
struct vm_area_struct *vma;
unsigned long addr, text_start;
int ret = 0;
static const struct vm_special_mapping vdso_mapping = {
.name = "[vdso]",
.fault = vdso_fault,
.mremap = vdso_mremap,
};
static const struct vm_special_mapping vvar_mapping = {
.name = "[vvar]",
.fault = vvar_fault,
......@@ -185,7 +222,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
image->size,
VM_READ|VM_EXEC|
VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
&text_mapping);
&vdso_mapping);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
......
......@@ -96,7 +96,7 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size)
{
/*
* XXX: if access_ok, get_user, and put_user handled
* sig_on_uaccess_error, this could go away.
* sig_on_uaccess_err, this could go away.
*/
if (!access_ok(VERIFY_WRITE, (void __user *)ptr, size)) {
......@@ -125,7 +125,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
struct task_struct *tsk;
unsigned long caller;
int vsyscall_nr, syscall_nr, tmp;
int prev_sig_on_uaccess_error;
int prev_sig_on_uaccess_err;
long ret;
/*
......@@ -221,8 +221,8 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
* With a real vsyscall, page faults cause SIGSEGV. We want to
* preserve that behavior to make writing exploits harder.
*/
prev_sig_on_uaccess_error = current_thread_info()->sig_on_uaccess_error;
current_thread_info()->sig_on_uaccess_error = 1;
prev_sig_on_uaccess_err = current->thread.sig_on_uaccess_err;
current->thread.sig_on_uaccess_err = 1;
ret = -EFAULT;
switch (vsyscall_nr) {
......@@ -243,7 +243,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
break;
}
current_thread_info()->sig_on_uaccess_error = prev_sig_on_uaccess_error;
current->thread.sig_on_uaccess_err = prev_sig_on_uaccess_err;
check_fault:
if (ret == -EFAULT) {
......
......@@ -45,11 +45,11 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
: "memory", "cc");
}
static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in,
u32 ecx_in, u32 *eax)
static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
u32 ecx_in, u32 *eax)
{
int cx, dx, si;
u8 error;
bool error;
/*
* N.B. We do NOT need a cld after the BIOS call
......
......@@ -4,8 +4,8 @@
#include <asm/cpufeatures.h>
#ifdef CONFIG_64BIT
/* popcnt %edi, %eax -- redundant REX prefix for alignment */
#define POPCNT32 ".byte 0xf3,0x40,0x0f,0xb8,0xc7"
/* popcnt %edi, %eax */
#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc7"
/* popcnt %rdi, %rax */
#define POPCNT64 ".byte 0xf3,0x48,0x0f,0xb8,0xc7"
#define REG_IN "D"
......@@ -17,19 +17,15 @@
#define REG_OUT "a"
#endif
/*
* __sw_hweightXX are called from within the alternatives below
* and callee-clobbered registers need to be taken care of. See
* ARCH_HWEIGHT_CFLAGS in <arch/x86/Kconfig> for the respective
* compiler switches.
*/
#define __HAVE_ARCH_SW_HWEIGHT
static __always_inline unsigned int __arch_hweight32(unsigned int w)
{
unsigned int res = 0;
unsigned int res;
asm (ALTERNATIVE("call __sw_hweight32", POPCNT32, X86_FEATURE_POPCNT)
: "="REG_OUT (res)
: REG_IN (w));
: "="REG_OUT (res)
: REG_IN (w));
return res;
}
......@@ -53,11 +49,11 @@ static inline unsigned long __arch_hweight64(__u64 w)
#else
static __always_inline unsigned long __arch_hweight64(__u64 w)
{
unsigned long res = 0;
unsigned long res;
asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT)
: "="REG_OUT (res)
: REG_IN (w));
: "="REG_OUT (res)
: REG_IN (w));
return res;
}
......
......@@ -25,8 +25,6 @@
#include <asm/processor.h>
#include <asm/cpufeature.h>
#include <asm/alternative.h>
#include <asm/nops.h>
#define RDRAND_RETRY_LOOPS 10
......@@ -40,97 +38,91 @@
# define RDSEED_LONG RDSEED_INT
#endif
#ifdef CONFIG_ARCH_RANDOM
/* Unconditional execution of RDRAND and RDSEED */
/* Instead of arch_get_random_long() when alternatives haven't run. */
static inline int rdrand_long(unsigned long *v)
static inline bool rdrand_long(unsigned long *v)
{
int ok;
asm volatile("1: " RDRAND_LONG "\n\t"
"jc 2f\n\t"
"decl %0\n\t"
"jnz 1b\n\t"
"2:"
: "=r" (ok), "=a" (*v)
: "0" (RDRAND_RETRY_LOOPS));
return ok;
bool ok;
unsigned int retry = RDRAND_RETRY_LOOPS;
do {
asm volatile(RDRAND_LONG "\n\t"
CC_SET(c)
: CC_OUT(c) (ok), "=a" (*v));
if (ok)
return true;
} while (--retry);
return false;
}
static inline bool rdrand_int(unsigned int *v)
{
bool ok;
unsigned int retry = RDRAND_RETRY_LOOPS;
do {
asm volatile(RDRAND_INT "\n\t"
CC_SET(c)
: CC_OUT(c) (ok), "=a" (*v));
if (ok)
return true;
} while (--retry);
return false;
}
/* A single attempt at RDSEED */
static inline bool rdseed_long(unsigned long *v)
{
unsigned char ok;
bool ok;
asm volatile(RDSEED_LONG "\n\t"
"setc %0"
: "=qm" (ok), "=a" (*v));
CC_SET(c)
: CC_OUT(c) (ok), "=a" (*v));
return ok;
}
#define GET_RANDOM(name, type, rdrand, nop) \
static inline int name(type *v) \
{ \
int ok; \
alternative_io("movl $0, %0\n\t" \
nop, \
"\n1: " rdrand "\n\t" \
"jc 2f\n\t" \
"decl %0\n\t" \
"jnz 1b\n\t" \
"2:", \
X86_FEATURE_RDRAND, \
ASM_OUTPUT2("=r" (ok), "=a" (*v)), \
"0" (RDRAND_RETRY_LOOPS)); \
return ok; \
}
#define GET_SEED(name, type, rdseed, nop) \
static inline int name(type *v) \
{ \
unsigned char ok; \
alternative_io("movb $0, %0\n\t" \
nop, \
rdseed "\n\t" \
"setc %0", \
X86_FEATURE_RDSEED, \
ASM_OUTPUT2("=q" (ok), "=a" (*v))); \
return ok; \
static inline bool rdseed_int(unsigned int *v)
{
bool ok;
asm volatile(RDSEED_INT "\n\t"
CC_SET(c)
: CC_OUT(c) (ok), "=a" (*v));
return ok;
}
#ifdef CONFIG_X86_64
GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP5);
GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP4);
GET_SEED(arch_get_random_seed_long, unsigned long, RDSEED_LONG, ASM_NOP5);
GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4);
#else
GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP3);
GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP3);
GET_SEED(arch_get_random_seed_long, unsigned long, RDSEED_LONG, ASM_NOP4);
GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4);
#endif /* CONFIG_X86_64 */
/* Conditional execution based on CPU type */
#define arch_has_random() static_cpu_has(X86_FEATURE_RDRAND)
#define arch_has_random_seed() static_cpu_has(X86_FEATURE_RDSEED)
#else
/*
* These are the generic interfaces; they must not be declared if the
* stubs in <linux/random.h> are to be invoked,
* i.e. CONFIG_ARCH_RANDOM is not defined.
*/
#ifdef CONFIG_ARCH_RANDOM
static inline int rdrand_long(unsigned long *v)
static inline bool arch_get_random_long(unsigned long *v)
{
return 0;
return arch_has_random() ? rdrand_long(v) : false;
}
static inline bool rdseed_long(unsigned long *v)
static inline bool arch_get_random_int(unsigned int *v)
{
return 0;
return arch_has_random() ? rdrand_int(v) : false;
}
#endif /* CONFIG_ARCH_RANDOM */
static inline bool arch_get_random_seed_long(unsigned long *v)
{
return arch_has_random_seed() ? rdseed_long(v) : false;
}
static inline bool arch_get_random_seed_int(unsigned int *v)
{
return arch_has_random_seed() ? rdseed_int(v) : false;
}
extern void x86_init_rdrand(struct cpuinfo_x86 *c);
#else /* !CONFIG_ARCH_RANDOM */
static inline void x86_init_rdrand(struct cpuinfo_x86 *c) { }
#endif /* !CONFIG_ARCH_RANDOM */
#endif /* ASM_X86_ARCHRANDOM_H */
......@@ -42,6 +42,18 @@
#define _ASM_SI __ASM_REG(si)
#define _ASM_DI __ASM_REG(di)
/*
* Macros to generate condition code outputs from inline assembly,
* The output operand must be type "bool".
*/
#ifdef __GCC_ASM_FLAG_OUTPUTS__
# define CC_SET(c) "\n\t/* output condition code " #c "*/\n"
# define CC_OUT(c) "=@cc" #c
#else
# define CC_SET(c) "\n\tset" #c " %[_cc_" #c "]\n"
# define CC_OUT(c) [_cc_ ## c] "=qm"
#endif
/* Exception table entry */
#ifdef __ASSEMBLY__
# define _ASM_EXTABLE_HANDLE(from, to, handler) \
......
......@@ -75,9 +75,9 @@ static __always_inline void atomic_sub(int i, atomic_t *v)
* true if the result is zero, or false for all
* other cases.
*/
static __always_inline int atomic_sub_and_test(int i, atomic_t *v)
static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e");
GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
}
/**
......@@ -112,9 +112,9 @@ static __always_inline void atomic_dec(atomic_t *v)
* returns true if the result is 0, or false for all other
* cases.
*/
static __always_inline int atomic_dec_and_test(atomic_t *v)
static __always_inline bool atomic_dec_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
}
/**
......@@ -125,9 +125,9 @@ static __always_inline int atomic_dec_and_test(atomic_t *v)
* and returns true if the result is zero, or false for all
* other cases.
*/
static __always_inline int atomic_inc_and_test(atomic_t *v)
static __always_inline bool atomic_inc_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
}
/**
......@@ -139,9 +139,9 @@ static __always_inline int atomic_inc_and_test(atomic_t *v)
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
static __always_inline int atomic_add_negative(int i, atomic_t *v)
static __always_inline bool atomic_add_negative(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s");
GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
}
/**
......
......@@ -70,9 +70,9 @@ static inline void atomic64_sub(long i, atomic64_t *v)
* true if the result is zero, or false for all
* other cases.
*/
static inline int atomic64_sub_and_test(long i, atomic64_t *v)
static inline bool atomic64_sub_and_test(long i, atomic64_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", "e");
GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
}
/**
......@@ -109,9 +109,9 @@ static __always_inline void atomic64_dec(atomic64_t *v)
* returns true if the result is 0, or false for all other
* cases.
*/
static inline int atomic64_dec_and_test(atomic64_t *v)
static inline bool atomic64_dec_and_test(atomic64_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", "e");
GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
}
/**
......@@ -122,9 +122,9 @@ static inline int atomic64_dec_and_test(atomic64_t *v)
* and returns true if the result is zero, or false for all
* other cases.
*/
static inline int atomic64_inc_and_test(atomic64_t *v)
static inline bool atomic64_inc_and_test(atomic64_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", "e");
GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
}
/**
......@@ -136,9 +136,9 @@ static inline int atomic64_inc_and_test(atomic64_t *v)
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
static inline int atomic64_add_negative(long i, atomic64_t *v)
static inline bool atomic64_add_negative(long i, atomic64_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", "s");
GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
}
/**
......@@ -190,7 +190,7 @@ static inline long atomic64_xchg(atomic64_t *v, long new)
* Atomically adds @a to @v, so long as it was not @u.
* Returns the old value of @v.
*/
static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
{
long c, old;
c = atomic64_read(v);
......
......@@ -201,9 +201,9 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
static __always_inline int test_and_set_bit(long nr, volatile unsigned long *addr)
static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", "c");
GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", c);
}
/**
......@@ -213,7 +213,7 @@ static __always_inline int test_and_set_bit(long nr, volatile unsigned long *add
*
* This is the same as test_and_set_bit on x86.
*/
static __always_inline int
static __always_inline bool
test_and_set_bit_lock(long nr, volatile unsigned long *addr)
{
return test_and_set_bit(nr, addr);
......@@ -228,13 +228,13 @@ test_and_set_bit_lock(long nr, volatile unsigned long *addr)
* If two examples of this operation race, one can appear to succeed
* but actually fail. You must protect multiple accesses with a lock.
*/
static __always_inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
bool oldbit;
asm("bts %2,%1\n\t"
"sbb %0,%0"
: "=r" (oldbit), ADDR
CC_SET(c)
: CC_OUT(c) (oldbit), ADDR
: "Ir" (nr));
return oldbit;
}
......@@ -247,9 +247,9 @@ static __always_inline int __test_and_set_bit(long nr, volatile unsigned long *a
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
static __always_inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", "c");
GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", c);
}
/**
......@@ -268,25 +268,25 @@ static __always_inline int test_and_clear_bit(long nr, volatile unsigned long *a
* accessed from a hypervisor on the same CPU if running in a VM: don't change
* this without also updating arch/x86/kernel/kvm.c
*/
static __always_inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
bool oldbit;
asm volatile("btr %2,%1\n\t"
"sbb %0,%0"
: "=r" (oldbit), ADDR
CC_SET(c)
: CC_OUT(c) (oldbit), ADDR
: "Ir" (nr));
return oldbit;
}
/* WARNING: non atomic and it can be reordered! */
static __always_inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
static __always_inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
bool oldbit;
asm volatile("btc %2,%1\n\t"
"sbb %0,%0"
: "=r" (oldbit), ADDR
CC_SET(c)
: CC_OUT(c) (oldbit), ADDR
: "Ir" (nr) : "memory");
return oldbit;
......@@ -300,24 +300,24 @@ static __always_inline int __test_and_change_bit(long nr, volatile unsigned long
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
static __always_inline int test_and_change_bit(long nr, volatile unsigned long *addr)
static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", "c");
GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", c);
}
static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr)
static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
{
return ((1UL << (nr & (BITS_PER_LONG-1))) &
(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
}
static __always_inline int variable_test_bit(long nr, volatile const unsigned long *addr)
static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
{
int oldbit;
bool oldbit;
asm volatile("bt %2,%1\n\t"
"sbb %0,%0"
: "=r" (oldbit)
CC_SET(c)
: CC_OUT(c) (oldbit)
: "m" (*(unsigned long *)addr), "Ir" (nr));
return oldbit;
......@@ -329,7 +329,7 @@ static __always_inline int variable_test_bit(long nr, volatile const unsigned lo
* @nr: bit number to test
* @addr: Address to start counting from
*/
static int test_bit(int nr, const volatile unsigned long *addr);
static bool test_bit(int nr, const volatile unsigned long *addr);
#endif
#define test_bit(nr, addr) \
......
......@@ -2,8 +2,7 @@
#define _ASM_X86_CHECKSUM_32_H
#include <linux/in6.h>
#include <asm/uaccess.h>
#include <linux/uaccess.h>
/*
* computes the checksum of a memory block at buff, length len,
......
......@@ -40,6 +40,7 @@ typedef s32 compat_long_t;
typedef s64 __attribute__((aligned(4))) compat_s64;
typedef u32 compat_uint_t;
typedef u32 compat_ulong_t;
typedef u32 compat_u32;
typedef u64 __attribute__((aligned(4))) compat_u64;
typedef u32 compat_uptr_t;
......@@ -181,6 +182,16 @@ typedef struct compat_siginfo {
/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
struct {
unsigned int _addr; /* faulting insn/memory ref. */
short int _addr_lsb; /* Valid LSB of the reported address. */
union {
/* used when si_code=SEGV_BNDERR */
struct {
compat_uptr_t _lower;
compat_uptr_t _upper;
} _addr_bnd;
/* used when si_code=SEGV_PKUERR */
compat_u32 _pkey;
};
} _sigfault;
/* SIGPOLL */
......
......@@ -17,7 +17,6 @@ static inline void prefill_possible_map(void) {}
#define cpu_physical_id(cpu) boot_cpu_physical_apicid
#define safe_smp_processor_id() 0
#define stack_smp_processor_id() 0
#endif /* CONFIG_SMP */
......
......@@ -124,7 +124,6 @@ extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
extern void efi_sync_low_kernel_mappings(void);
extern int __init efi_alloc_page_tables(void);
extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
extern void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
extern void __init old_map_region(efi_memory_desc_t *md);
extern void __init runtime_code_page_mkexec(void);
extern void __init efi_runtime_update_mappings(void);
......
......@@ -50,9 +50,9 @@ static inline void local_sub(long i, local_t *l)
* true if the result is zero, or false for all
* other cases.
*/
static inline int local_sub_and_test(long i, local_t *l)
static inline bool local_sub_and_test(long i, local_t *l)
{
GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, "er", i, "%0", "e");
GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, "er", i, "%0", e);
}
/**
......@@ -63,9 +63,9 @@ static inline int local_sub_and_test(long i, local_t *l)
* returns true if the result is 0, or false for all other
* cases.
*/
static inline int local_dec_and_test(local_t *l)
static inline bool local_dec_and_test(local_t *l)
{
GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", "e");
GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", e);
}
/**
......@@ -76,9 +76,9 @@ static inline int local_dec_and_test(local_t *l)
* and returns true if the result is zero, or false for all
* other cases.
*/
static inline int local_inc_and_test(local_t *l)
static inline bool local_inc_and_test(local_t *l)
{
GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", "e");
GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", e);
}
/**
......@@ -90,9 +90,9 @@ static inline int local_inc_and_test(local_t *l)
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
static inline int local_add_negative(long i, local_t *l)
static inline bool local_add_negative(long i, local_t *l)
{
GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, "er", i, "%0", "s");
GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, "er", i, "%0", s);
}
/**
......
......@@ -510,14 +510,15 @@ do { \
/* This is not atomic against other CPUs -- CPU preemption needs to be off */
#define x86_test_and_clear_bit_percpu(bit, var) \
({ \
int old__; \
asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0" \
: "=r" (old__), "+m" (var) \
bool old__; \
asm volatile("btr %2,"__percpu_arg(1)"\n\t" \
CC_SET(c) \
: CC_OUT(c) (old__), "+m" (var) \
: "dIr" (bit)); \
old__; \
})
static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr,
const unsigned long __percpu *addr)
{
unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG;
......@@ -529,14 +530,14 @@ static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
#endif
}
static inline int x86_this_cpu_variable_test_bit(int nr,
static inline bool x86_this_cpu_variable_test_bit(int nr,
const unsigned long __percpu *addr)
{
int oldbit;
bool oldbit;
asm volatile("bt "__percpu_arg(2)",%1\n\t"
"sbb %0,%0"
: "=r" (oldbit)
CC_SET(c)
: CC_OUT(c) (oldbit)
: "m" (*(unsigned long *)addr), "Ir" (nr));
return oldbit;
......
......@@ -480,7 +480,7 @@ pte_t *populate_extra_pte(unsigned long vaddr);
static inline int pte_none(pte_t pte)
{
return !pte.pte;
return !(pte.pte & ~(_PAGE_KNL_ERRATUM_MASK));
}
#define __HAVE_ARCH_PTE_SAME
......@@ -552,7 +552,8 @@ static inline int pmd_none(pmd_t pmd)
{
/* Only check low word on 32-bit platforms, since it might be
out of sync with upper half. */
return (unsigned long)native_pmd_val(pmd) == 0;
unsigned long val = native_pmd_val(pmd);
return (val & ~_PAGE_KNL_ERRATUM_MASK) == 0;
}
static inline unsigned long pmd_page_vaddr(pmd_t pmd)
......@@ -616,7 +617,7 @@ static inline unsigned long pages_to_mb(unsigned long npg)
#if CONFIG_PGTABLE_LEVELS > 2
static inline int pud_none(pud_t pud)
{
return native_pud_val(pud) == 0;
return (native_pud_val(pud) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0;
}
static inline int pud_present(pud_t pud)
......@@ -694,6 +695,12 @@ static inline int pgd_bad(pgd_t pgd)
static inline int pgd_none(pgd_t pgd)
{
/*
* There is no need to do a workaround for the KNL stray
* A/D bit erratum here. PGDs only point to page tables
* except on 32-bit non-PAE which is not supported on
* KNL.
*/
return !native_pgd_val(pgd);
}
#endif /* CONFIG_PGTABLE_LEVELS > 3 */
......
......@@ -140,18 +140,32 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
#define pte_unmap(pte) ((void)(pte))/* NOP */
/* Encode and de-code a swap entry */
/*
* Encode and de-code a swap entry
*
* | ... | 11| 10| 9|8|7|6|5| 4| 3|2|1|0| <- bit number
* | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U|W|P| <- bit names
* | OFFSET (14->63) | TYPE (10-13) |0|X|X|X| X| X|X|X|0| <- swp entry
*
* G (8) is aliased and used as a PROT_NONE indicator for
* !present ptes. We need to start storing swap entries above
* there. We also need to avoid using A and D because of an
* erratum where they can be incorrectly set by hardware on
* non-present PTEs.
*/
#define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
#define SWP_TYPE_BITS 5
#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
/* Place the offset above the type: */
#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS + 1)
#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
#define __swp_type(x) (((x).val >> (_PAGE_BIT_PRESENT + 1)) \
#define __swp_type(x) (((x).val >> (SWP_TYPE_FIRST_BIT)) \
& ((1U << SWP_TYPE_BITS) - 1))
#define __swp_offset(x) ((x).val >> SWP_OFFSET_SHIFT)
#define __swp_offset(x) ((x).val >> SWP_OFFSET_FIRST_BIT)
#define __swp_entry(type, offset) ((swp_entry_t) { \
((type) << (_PAGE_BIT_PRESENT + 1)) \
| ((offset) << SWP_OFFSET_SHIFT) })
((type) << (SWP_TYPE_FIRST_BIT)) \
| ((offset) << SWP_OFFSET_FIRST_BIT) })
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) })
#define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val })
......
......@@ -70,6 +70,12 @@
_PAGE_PKEY_BIT2 | \
_PAGE_PKEY_BIT3)
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
#define _PAGE_KNL_ERRATUM_MASK (_PAGE_DIRTY | _PAGE_ACCESSED)
#else
#define _PAGE_KNL_ERRATUM_MASK 0
#endif
#ifdef CONFIG_KMEMCHECK
#define _PAGE_HIDDEN (_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN)
#else
......@@ -475,8 +481,6 @@ extern pmd_t *lookup_pmd_address(unsigned long address);
extern phys_addr_t slow_virt_to_phys(void *__address);
extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
unsigned numpages, unsigned long page_flags);
void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
unsigned numpages);
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_X86_PGTABLE_DEFS_H */
......@@ -81,7 +81,7 @@ static __always_inline void __preempt_count_sub(int val)
*/
static __always_inline bool __preempt_count_dec_and_test(void)
{
GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");
GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), e);
}
/*
......
......@@ -371,6 +371,10 @@ extern unsigned int xstate_size;
struct perf_event;
typedef struct {
unsigned long seg;
} mm_segment_t;
struct thread_struct {
/* Cached TLS descriptors: */
struct desc_struct tls_array[GDT_ENTRY_TLS_ENTRIES];
......@@ -419,6 +423,11 @@ struct thread_struct {
/* Max allowed port in the bitmap, in bytes: */
unsigned io_bitmap_max;
mm_segment_t addr_limit;
unsigned int sig_on_uaccess_err:1;
unsigned int uaccess_err:1; /* uaccess failed */
/* Floating point and extended processor state */
struct fpu fpu;
/*
......@@ -490,11 +499,6 @@ static inline void load_sp0(struct tss_struct *tss,
#define set_iopl_mask native_set_iopl_mask
#endif /* CONFIG_PARAVIRT */
typedef struct {
unsigned long seg;
} mm_segment_t;
/* Free all resources held by a thread. */
extern void release_thread(struct task_struct *);
......@@ -716,6 +720,7 @@ static inline void spin_lock_prefetch(const void *x)
.sp0 = TOP_OF_INIT_STACK, \
.sysenter_cs = __KERNEL_CS, \
.io_bitmap_ptr = NULL, \
.addr_limit = KERNEL_DS, \
}
extern unsigned long thread_saved_pc(struct task_struct *tsk);
......@@ -765,8 +770,9 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
#define STACK_TOP TASK_SIZE
#define STACK_TOP_MAX TASK_SIZE_MAX
#define INIT_THREAD { \
.sp0 = TOP_OF_INIT_STACK \
#define INIT_THREAD { \
.sp0 = TOP_OF_INIT_STACK, \
.addr_limit = KERNEL_DS, \
}
/*
......
#ifndef _ASM_X86_RMWcc
#define _ASM_X86_RMWcc
#ifdef CC_HAVE_ASM_GOTO
#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO)
/* Use asm goto */
#define __GEN_RMWcc(fullop, var, cc, ...) \
do { \
asm_volatile_goto (fullop "; j" cc " %l[cc_label]" \
asm_volatile_goto (fullop "; j" #cc " %l[cc_label]" \
: : "m" (var), ## __VA_ARGS__ \
: "memory" : cc_label); \
return 0; \
......@@ -19,15 +21,17 @@ cc_label: \
#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \
__GEN_RMWcc(op " %1, " arg0, var, cc, vcon (val))
#else /* !CC_HAVE_ASM_GOTO */
#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
/* Use flags output or a set instruction */
#define __GEN_RMWcc(fullop, var, cc, ...) \
do { \
char c; \
asm volatile (fullop "; set" cc " %1" \
: "+m" (var), "=qm" (c) \
bool c; \
asm volatile (fullop ";" CC_SET(cc) \
: "+m" (var), CC_OUT(cc) (c) \
: __VA_ARGS__ : "memory"); \
return c != 0; \
return c; \
} while (0)
#define GEN_UNARY_RMWcc(op, var, arg0, cc) \
......@@ -36,6 +40,6 @@ do { \
#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \
__GEN_RMWcc(op " %2, " arg0, var, cc, vcon (val))
#endif /* CC_HAVE_ASM_GOTO */
#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
#endif /* _ASM_X86_RMWcc */
......@@ -77,7 +77,7 @@ static inline void __down_read(struct rw_semaphore *sem)
/*
* trylock for reading -- returns 1 if successful, 0 if contention
*/
static inline int __down_read_trylock(struct rw_semaphore *sem)
static inline bool __down_read_trylock(struct rw_semaphore *sem)
{
long result, tmp;
asm volatile("# beginning __down_read_trylock\n\t"
......@@ -93,7 +93,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
: "+m" (sem->count), "=&a" (result), "=&r" (tmp)
: "i" (RWSEM_ACTIVE_READ_BIAS)
: "memory", "cc");
return result >= 0 ? 1 : 0;
return result >= 0;
}
/*
......@@ -134,9 +134,10 @@ static inline int __down_write_killable(struct rw_semaphore *sem)
/*
* trylock for writing -- returns 1 if successful, 0 if contention
*/
static inline int __down_write_trylock(struct rw_semaphore *sem)
static inline bool __down_write_trylock(struct rw_semaphore *sem)
{
long result, tmp;
bool result;
long tmp0, tmp1;
asm volatile("# beginning __down_write_trylock\n\t"
" mov %0,%1\n\t"
"1:\n\t"
......@@ -144,14 +145,14 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
/* was the active mask 0 before? */
" jnz 2f\n\t"
" mov %1,%2\n\t"
" add %3,%2\n\t"
" add %4,%2\n\t"
LOCK_PREFIX " cmpxchg %2,%0\n\t"
" jnz 1b\n\t"
"2:\n\t"
" sete %b1\n\t"
" movzbl %b1, %k1\n\t"
CC_SET(e)
"# ending __down_write_trylock\n\t"
: "+m" (sem->count), "=&a" (result), "=&r" (tmp)
: "+m" (sem->count), "=&a" (tmp0), "=&r" (tmp1),
CC_OUT(e) (result)
: "er" (RWSEM_ACTIVE_WRITE_BIAS)
: "memory", "cc");
return result;
......
......@@ -81,9 +81,9 @@ static inline int __const_sigismember(sigset_t *set, int _sig)
static inline int __gen_sigismember(sigset_t *set, int _sig)
{
int ret;
asm("btl %2,%1\n\tsbbl %0,%0"
: "=r"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
unsigned char ret;
asm("btl %2,%1\n\tsetc %0"
: "=qm"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
return ret;
}
......
......@@ -172,12 +172,6 @@ extern int safe_smp_processor_id(void);
#elif defined(CONFIG_X86_64_SMP)
#define raw_smp_processor_id() (this_cpu_read(cpu_number))
#define stack_smp_processor_id() \
({ \
struct thread_info *ti; \
__asm__("andq %%rsp,%0; ":"=r" (ti) : "0" (CURRENT_MASK)); \
ti->cpu; \
})
#define safe_smp_processor_id() smp_processor_id()
#endif
......
......@@ -79,10 +79,10 @@ static inline void sync_change_bit(long nr, volatile unsigned long *addr)
*/
static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
unsigned char oldbit;
asm volatile("lock; bts %2,%1\n\tsbbl %0,%0"
: "=r" (oldbit), "+m" (ADDR)
asm volatile("lock; bts %2,%1\n\tsetc %0"
: "=qm" (oldbit), "+m" (ADDR)
: "Ir" (nr) : "memory");
return oldbit;
}
......@@ -97,10 +97,10 @@ static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
*/
static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
unsigned char oldbit;
asm volatile("lock; btr %2,%1\n\tsbbl %0,%0"
: "=r" (oldbit), "+m" (ADDR)
asm volatile("lock; btr %2,%1\n\tsetc %0"
: "=qm" (oldbit), "+m" (ADDR)
: "Ir" (nr) : "memory");
return oldbit;
}
......@@ -115,10 +115,10 @@ static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
*/
static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
unsigned char oldbit;
asm volatile("lock; btc %2,%1\n\tsbbl %0,%0"
: "=r" (oldbit), "+m" (ADDR)
asm volatile("lock; btc %2,%1\n\tsetc %0"
: "=qm" (oldbit), "+m" (ADDR)
: "Ir" (nr) : "memory");
return oldbit;
}
......
......@@ -57,9 +57,6 @@ struct thread_info {
__u32 flags; /* low level flags */
__u32 status; /* thread synchronous flags */
__u32 cpu; /* current CPU */
mm_segment_t addr_limit;
unsigned int sig_on_uaccess_error:1;
unsigned int uaccess_err:1; /* uaccess failed */
};
#define INIT_THREAD_INFO(tsk) \
......@@ -67,7 +64,6 @@ struct thread_info {
.task = &tsk, \
.flags = 0, \
.cpu = 0, \
.addr_limit = KERNEL_DS, \
}
#define init_thread_info (init_thread_union.thread_info)
......@@ -186,11 +182,6 @@ static inline unsigned long current_stack_pointer(void)
# define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
#endif
/* Load thread_info address into "reg" */
#define GET_THREAD_INFO(reg) \
_ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \
_ASM_SUB $(THREAD_SIZE),reg ;
/*
* ASM operand which evaluates to a 'thread_info' address of
* the current task, if it is known that "reg" is exactly "off"
......
......@@ -29,12 +29,12 @@
#define USER_DS MAKE_MM_SEG(TASK_SIZE_MAX)
#define get_ds() (KERNEL_DS)
#define get_fs() (current_thread_info()->addr_limit)
#define set_fs(x) (current_thread_info()->addr_limit = (x))
#define get_fs() (current->thread.addr_limit)
#define set_fs(x) (current->thread.addr_limit = (x))
#define segment_eq(a, b) ((a).seg == (b).seg)
#define user_addr_max() (current_thread_info()->addr_limit.seg)
#define user_addr_max() (current->thread.addr_limit.seg)
#define __addr_ok(addr) \
((unsigned long __force)(addr) < user_addr_max())
......@@ -342,7 +342,26 @@ do { \
} while (0)
#ifdef CONFIG_X86_32
#define __get_user_asm_u64(x, ptr, retval, errret) (x) = __get_user_bad()
#define __get_user_asm_u64(x, ptr, retval, errret) \
({ \
__typeof__(ptr) __ptr = (ptr); \
asm volatile(ASM_STAC "\n" \
"1: movl %2,%%eax\n" \
"2: movl %3,%%edx\n" \
"3: " ASM_CLAC "\n" \
".section .fixup,\"ax\"\n" \
"4: mov %4,%0\n" \
" xorl %%eax,%%eax\n" \
" xorl %%edx,%%edx\n" \
" jmp 3b\n" \
".previous\n" \
_ASM_EXTABLE(1b, 4b) \
_ASM_EXTABLE(2b, 4b) \
: "=r" (retval), "=A"(x) \
: "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1), \
"i" (errret), "0" (retval)); \
})
#define __get_user_asm_ex_u64(x, ptr) (x) = __get_user_bad()
#else
#define __get_user_asm_u64(x, ptr, retval, errret) \
......@@ -429,7 +448,7 @@ do { \
#define __get_user_nocheck(x, ptr, size) \
({ \
int __gu_err; \
unsigned long __gu_val; \
__inttype(*(ptr)) __gu_val; \
__uaccess_begin(); \
__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \
__uaccess_end(); \
......@@ -468,13 +487,13 @@ struct __large_struct { unsigned long buf[100]; };
* uaccess_try and catch
*/
#define uaccess_try do { \
current_thread_info()->uaccess_err = 0; \
current->thread.uaccess_err = 0; \
__uaccess_begin(); \
barrier();
#define uaccess_catch(err) \
__uaccess_end(); \
(err) |= (current_thread_info()->uaccess_err ? -EFAULT : 0); \
(err) |= (current->thread.uaccess_err ? -EFAULT : 0); \
} while (0)
/**
......
......@@ -26,6 +26,8 @@
# define __ARCH_WANT_COMPAT_SYS_GETDENTS64
# define __ARCH_WANT_COMPAT_SYS_PREADV64
# define __ARCH_WANT_COMPAT_SYS_PWRITEV64
# define __ARCH_WANT_COMPAT_SYS_PREADV64V2
# define __ARCH_WANT_COMPAT_SYS_PWRITEV64V2
# endif
......
......@@ -31,7 +31,9 @@ void common(void) {
BLANK();
OFFSET(TI_flags, thread_info, flags);
OFFSET(TI_status, thread_info, status);
OFFSET(TI_addr_limit, thread_info, addr_limit);
BLANK();
OFFSET(TASK_addr_limit, task_struct, thread.addr_limit);
BLANK();
OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
......
......@@ -1452,7 +1452,7 @@ void cpu_init(void)
struct task_struct *me;
struct tss_struct *t;
unsigned long v;
int cpu = stack_smp_processor_id();
int cpu = raw_smp_processor_id();
int i;
wait_for_master_cpu(cpu);
......
......@@ -39,9 +39,9 @@ __setup("nordrand", x86_rdrand_setup);
*/
#define SANITY_CHECK_LOOPS 8
#ifdef CONFIG_ARCH_RANDOM
void x86_init_rdrand(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_ARCH_RANDOM
unsigned long tmp;
int i;
......@@ -55,5 +55,5 @@ void x86_init_rdrand(struct cpuinfo_x86 *c)
return;
}
}
#endif
}
#endif
......@@ -87,7 +87,7 @@ static inline int valid_stack_ptr(struct task_struct *task,
else
return 0;
}
return p > t && p < t + THREAD_SIZE - size;
return p >= t && p < t + THREAD_SIZE - size;
}
unsigned long
......@@ -98,6 +98,14 @@ print_context_stack(struct task_struct *task,
{
struct stack_frame *frame = (struct stack_frame *)bp;
/*
* If we overflowed the stack into a guard page, jump back to the
* bottom of the usable stack.
*/
if ((unsigned long)task_stack_page(task) - (unsigned long)stack <
PAGE_SIZE)
stack = (unsigned long *)task_stack_page(task);
while (valid_stack_ptr(task, stack, sizeof(*stack), end)) {
unsigned long addr;
......@@ -226,6 +234,8 @@ unsigned long oops_begin(void)
EXPORT_SYMBOL_GPL(oops_begin);
NOKPROBE_SYMBOL(oops_begin);
void __noreturn rewind_stack_do_exit(int signr);
void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
{
if (regs && kexec_should_crash(current))
......@@ -247,7 +257,13 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
panic("Fatal exception in interrupt");
if (panic_on_oops)
panic("Fatal exception");
do_exit(signr);
/*
* We're not going to return, but we might be on an IST stack or
* have very little stack space left. Rewind the stack and kill
* the task.
*/
rewind_stack_do_exit(signr);
}
NOKPROBE_SYMBOL(oops_end);
......
......@@ -272,6 +272,8 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
stack = sp;
for (i = 0; i < kstack_depth_to_print; i++) {
unsigned long word;
if (stack >= irq_stack && stack <= irq_stack_end) {
if (stack == irq_stack_end) {
stack = (unsigned long *) (irq_stack_end[-1]);
......@@ -281,12 +283,18 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
if (kstack_end(stack))
break;
}
if (probe_kernel_address(stack, word))
break;
if ((i % STACKSLOTS_PER_LINE) == 0) {
if (i != 0)
pr_cont("\n");
printk("%s %016lx", log_lvl, *stack++);
printk("%s %016lx", log_lvl, word);
} else
pr_cont(" %016lx", *stack++);
pr_cont(" %016lx", word);
stack++;
touch_nmi_watchdog();
}
preempt_enable();
......
......@@ -42,3 +42,5 @@ EXPORT_SYMBOL(empty_zero_page);
EXPORT_SYMBOL(___preempt_schedule);
EXPORT_SYMBOL(___preempt_schedule_notrace);
#endif
EXPORT_SYMBOL(__sw_hweight32);
#include <linux/compat.h>
#include <linux/uaccess.h>
/*
* The compat_siginfo_t structure and handing code is very easy
* to break in several ways. It must always be updated when new
* updates are made to the main siginfo_t, and
* copy_siginfo_to_user32() must be updated when the
* (arch-independent) copy_siginfo_to_user() is updated.
*
* It is also easy to put a new member in the compat_siginfo_t
* which has implicit alignment which can move internal structure
* alignment around breaking the ABI. This can happen if you,
* for instance, put a plain 64-bit value in there.
*/
static inline void signal_compat_build_tests(void)
{
int _sifields_offset = offsetof(compat_siginfo_t, _sifields);
/*
* If adding a new si_code, there is probably new data in
* the siginfo. Make sure folks bumping the si_code
* limits also have to look at this code. Make sure any
* new fields are handled in copy_siginfo_to_user32()!
*/
BUILD_BUG_ON(NSIGILL != 8);
BUILD_BUG_ON(NSIGFPE != 8);
BUILD_BUG_ON(NSIGSEGV != 4);
BUILD_BUG_ON(NSIGBUS != 5);
BUILD_BUG_ON(NSIGTRAP != 4);
BUILD_BUG_ON(NSIGCHLD != 6);
BUILD_BUG_ON(NSIGSYS != 1);
/* This is part of the ABI and can never change in size: */
BUILD_BUG_ON(sizeof(compat_siginfo_t) != 128);
/*
* The offsets of all the (unioned) si_fields are fixed
* in the ABI, of course. Make sure none of them ever
* move and are always at the beginning:
*/
BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields) != 3 * sizeof(int));
#define CHECK_CSI_OFFSET(name) BUILD_BUG_ON(_sifields_offset != offsetof(compat_siginfo_t, _sifields.name))
/*
* Ensure that the size of each si_field never changes.
* If it does, it is a sign that the
* copy_siginfo_to_user32() code below needs to updated
* along with the size in the CHECK_SI_SIZE().
*
* We repeat this check for both the generic and compat
* siginfos.
*
* Note: it is OK for these to grow as long as the whole
* structure stays within the padding size (checked
* above).
*/
#define CHECK_CSI_SIZE(name, size) BUILD_BUG_ON(size != sizeof(((compat_siginfo_t *)0)->_sifields.name))
#define CHECK_SI_SIZE(name, size) BUILD_BUG_ON(size != sizeof(((siginfo_t *)0)->_sifields.name))
CHECK_CSI_OFFSET(_kill);
CHECK_CSI_SIZE (_kill, 2*sizeof(int));
CHECK_SI_SIZE (_kill, 2*sizeof(int));
CHECK_CSI_OFFSET(_timer);
CHECK_CSI_SIZE (_timer, 5*sizeof(int));
CHECK_SI_SIZE (_timer, 6*sizeof(int));
CHECK_CSI_OFFSET(_rt);
CHECK_CSI_SIZE (_rt, 3*sizeof(int));
CHECK_SI_SIZE (_rt, 4*sizeof(int));
CHECK_CSI_OFFSET(_sigchld);
CHECK_CSI_SIZE (_sigchld, 5*sizeof(int));
CHECK_SI_SIZE (_sigchld, 8*sizeof(int));
CHECK_CSI_OFFSET(_sigchld_x32);
CHECK_CSI_SIZE (_sigchld_x32, 7*sizeof(int));
/* no _sigchld_x32 in the generic siginfo_t */
CHECK_CSI_OFFSET(_sigfault);
CHECK_CSI_SIZE (_sigfault, 4*sizeof(int));
CHECK_SI_SIZE (_sigfault, 8*sizeof(int));
CHECK_CSI_OFFSET(_sigpoll);
CHECK_CSI_SIZE (_sigpoll, 2*sizeof(int));
CHECK_SI_SIZE (_sigpoll, 4*sizeof(int));
CHECK_CSI_OFFSET(_sigsys);
CHECK_CSI_SIZE (_sigsys, 3*sizeof(int));
CHECK_SI_SIZE (_sigsys, 4*sizeof(int));
/* any new si_fields should be added here */
}
int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
{
int err = 0;
bool ia32 = test_thread_flag(TIF_IA32);
signal_compat_build_tests();
if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
return -EFAULT;
......@@ -32,6 +125,21 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
&to->_sifields._pad[0]);
switch (from->si_code >> 16) {
case __SI_FAULT >> 16:
if (from->si_signo == SIGBUS &&
(from->si_code == BUS_MCEERR_AR ||
from->si_code == BUS_MCEERR_AO))
put_user_ex(from->si_addr_lsb, &to->si_addr_lsb);
if (from->si_signo == SIGSEGV) {
if (from->si_code == SEGV_BNDERR) {
compat_uptr_t lower = (unsigned long)&to->si_lower;
compat_uptr_t upper = (unsigned long)&to->si_upper;
put_user_ex(lower, &to->si_lower);
put_user_ex(upper, &to->si_upper);
}
if (from->si_code == SEGV_PKUERR)
put_user_ex(from->si_pkey, &to->si_pkey);
}
break;
case __SI_SYS >> 16:
put_user_ex(from->si_syscall, &to->si_syscall);
......
......@@ -1292,7 +1292,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
cpumask_copy(cpu_callin_mask, cpumask_of(0));
mb();
current_thread_info()->cpu = 0; /* needed? */
for_each_possible_cpu(i) {
zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
......
......@@ -440,10 +440,7 @@ static inline unsigned long get_vflags(struct kernel_vm86_regs *regs)
static inline int is_revectored(int nr, struct revectored_struct *bitmap)
{
__asm__ __volatile__("btl %2,%1\n\tsbbl %0,%0"
:"=r" (nr)
:"m" (*bitmap), "r" (nr));
return nr;
return test_bit(nr, bitmap->__map);
}
#define val_byte(val, n) (((__u8 *)&val)[n])
......
......@@ -44,6 +44,9 @@ EXPORT_SYMBOL(clear_page);
EXPORT_SYMBOL(csum_partial);
EXPORT_SYMBOL(__sw_hweight32);
EXPORT_SYMBOL(__sw_hweight64);
/*
* Export string functions. We normally rely on gcc builtin for most of these,
* but gcc sometimes decides not to inline them.
......
......@@ -25,7 +25,7 @@ lib-y += memcpy_$(BITS).o
lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o
obj-y += msr.o msr-reg.o msr-reg-export.o
obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
ifeq ($(CONFIG_X86_32),y)
obj-y += atomic64_32.o
......
......@@ -17,11 +17,11 @@
/* Standard copy_to_user with segment limit checking */
ENTRY(_copy_to_user)
GET_THREAD_INFO(%rax)
mov PER_CPU_VAR(current_task), %rax
movq %rdi,%rcx
addq %rdx,%rcx
jc bad_to_user
cmpq TI_addr_limit(%rax),%rcx
cmpq TASK_addr_limit(%rax),%rcx
ja bad_to_user
ALTERNATIVE_2 "jmp copy_user_generic_unrolled", \
"jmp copy_user_generic_string", \
......@@ -32,11 +32,11 @@ ENDPROC(_copy_to_user)
/* Standard copy_from_user with segment limit checking */
ENTRY(_copy_from_user)
GET_THREAD_INFO(%rax)
mov PER_CPU_VAR(current_task), %rax
movq %rsi,%rcx
addq %rdx,%rcx
jc bad_from_user
cmpq TI_addr_limit(%rax),%rcx
cmpq TASK_addr_limit(%rax),%rcx
ja bad_from_user
ALTERNATIVE_2 "jmp copy_user_generic_unrolled", \
"jmp copy_user_generic_string", \
......
......@@ -6,6 +6,7 @@
*/
#include <asm/checksum.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <asm/smap.h>
/**
......
......@@ -35,8 +35,8 @@
.text
ENTRY(__get_user_1)
GET_THREAD_INFO(%_ASM_DX)
cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
mov PER_CPU_VAR(current_task), %_ASM_DX
cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
jae bad_get_user
ASM_STAC
1: movzbl (%_ASM_AX),%edx
......@@ -48,8 +48,8 @@ ENDPROC(__get_user_1)
ENTRY(__get_user_2)
add $1,%_ASM_AX
jc bad_get_user
GET_THREAD_INFO(%_ASM_DX)
cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
mov PER_CPU_VAR(current_task), %_ASM_DX
cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
jae bad_get_user
ASM_STAC
2: movzwl -1(%_ASM_AX),%edx
......@@ -61,8 +61,8 @@ ENDPROC(__get_user_2)
ENTRY(__get_user_4)
add $3,%_ASM_AX
jc bad_get_user
GET_THREAD_INFO(%_ASM_DX)
cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
mov PER_CPU_VAR(current_task), %_ASM_DX
cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
jae bad_get_user
ASM_STAC
3: movl -3(%_ASM_AX),%edx
......@@ -75,8 +75,8 @@ ENTRY(__get_user_8)
#ifdef CONFIG_X86_64
add $7,%_ASM_AX
jc bad_get_user
GET_THREAD_INFO(%_ASM_DX)
cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
mov PER_CPU_VAR(current_task), %_ASM_DX
cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
jae bad_get_user
ASM_STAC
4: movq -7(%_ASM_AX),%rdx
......@@ -86,8 +86,8 @@ ENTRY(__get_user_8)
#else
add $7,%_ASM_AX
jc bad_get_user_8
GET_THREAD_INFO(%_ASM_DX)
cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
mov PER_CPU_VAR(current_task), %_ASM_DX
cmp TASK_addr_limit(%_ASM_DX),%_ASM_AX
jae bad_get_user_8
ASM_STAC
4: movl -7(%_ASM_AX),%edx
......
#include <linux/linkage.h>
#include <asm/asm.h>
/*
* unsigned int __sw_hweight32(unsigned int w)
* %rdi: w
*/
ENTRY(__sw_hweight32)
#ifdef CONFIG_X86_64
movl %edi, %eax # w
#endif
__ASM_SIZE(push,) %__ASM_REG(dx)
movl %eax, %edx # w -> t
shrl %edx # t >>= 1
andl $0x55555555, %edx # t &= 0x55555555
subl %edx, %eax # w -= t
movl %eax, %edx # w -> t
shrl $2, %eax # w_tmp >>= 2
andl $0x33333333, %edx # t &= 0x33333333
andl $0x33333333, %eax # w_tmp &= 0x33333333
addl %edx, %eax # w = w_tmp + t
movl %eax, %edx # w -> t
shrl $4, %edx # t >>= 4
addl %edx, %eax # w_tmp += t
andl $0x0f0f0f0f, %eax # w_tmp &= 0x0f0f0f0f
imull $0x01010101, %eax, %eax # w_tmp *= 0x01010101
shrl $24, %eax # w = w_tmp >> 24
__ASM_SIZE(pop,) %__ASM_REG(dx)
ret
ENDPROC(__sw_hweight32)
ENTRY(__sw_hweight64)
#ifdef CONFIG_X86_64
pushq %rdx
movq %rdi, %rdx # w -> t
movabsq $0x5555555555555555, %rax
shrq %rdx # t >>= 1
andq %rdx, %rax # t &= 0x5555555555555555
movabsq $0x3333333333333333, %rdx
subq %rax, %rdi # w -= t
movq %rdi, %rax # w -> t
shrq $2, %rdi # w_tmp >>= 2
andq %rdx, %rax # t &= 0x3333333333333333
andq %rdi, %rdx # w_tmp &= 0x3333333333333333
addq %rdx, %rax # w = w_tmp + t
movq %rax, %rdx # w -> t
shrq $4, %rdx # t >>= 4
addq %rdx, %rax # w_tmp += t
movabsq $0x0f0f0f0f0f0f0f0f, %rdx
andq %rdx, %rax # w_tmp &= 0x0f0f0f0f0f0f0f0f
movabsq $0x0101010101010101, %rdx
imulq %rdx, %rax # w_tmp *= 0x0101010101010101
shrq $56, %rax # w = w_tmp >> 56
popq %rdx
ret
#else /* CONFIG_X86_32 */
/* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */
pushl %ecx
call __sw_hweight32
movl %eax, %ecx # stash away result
movl %edx, %eax # second part of input
call __sw_hweight32
addl %ecx, %eax # result
popl %ecx
ret
#endif
ENDPROC(__sw_hweight64)
......@@ -29,14 +29,14 @@
* as they get called from within inline assembly.
*/
#define ENTER GET_THREAD_INFO(%_ASM_BX)
#define ENTER mov PER_CPU_VAR(current_task), %_ASM_BX
#define EXIT ASM_CLAC ; \
ret
.text
ENTRY(__put_user_1)
ENTER
cmp TI_addr_limit(%_ASM_BX),%_ASM_CX
cmp TASK_addr_limit(%_ASM_BX),%_ASM_CX
jae bad_put_user
ASM_STAC
1: movb %al,(%_ASM_CX)
......@@ -46,7 +46,7 @@ ENDPROC(__put_user_1)
ENTRY(__put_user_2)
ENTER
mov TI_addr_limit(%_ASM_BX),%_ASM_BX
mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
sub $1,%_ASM_BX
cmp %_ASM_BX,%_ASM_CX
jae bad_put_user
......@@ -58,7 +58,7 @@ ENDPROC(__put_user_2)
ENTRY(__put_user_4)
ENTER
mov TI_addr_limit(%_ASM_BX),%_ASM_BX
mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
sub $3,%_ASM_BX
cmp %_ASM_BX,%_ASM_CX
jae bad_put_user
......@@ -70,7 +70,7 @@ ENDPROC(__put_user_4)
ENTRY(__put_user_8)
ENTER
mov TI_addr_limit(%_ASM_BX),%_ASM_BX
mov TASK_addr_limit(%_ASM_BX),%_ASM_BX
sub $7,%_ASM_BX
cmp %_ASM_BX,%_ASM_CX
jae bad_put_user
......
......@@ -6,7 +6,7 @@
* Copyright 2002 Andi Kleen <ak@suse.de>
*/
#include <linux/module.h>
#include <asm/uaccess.h>
#include <linux/uaccess.h>
/*
* Zero Userspace
......
......@@ -37,7 +37,7 @@ bool ex_handler_ext(const struct exception_table_entry *fixup,
struct pt_regs *regs, int trapnr)
{
/* Special hack for uaccess_err */
current_thread_info()->uaccess_err = 1;
current->thread.uaccess_err = 1;
regs->ip = ex_fixup_addr(fixup);
return true;
}
......
......@@ -439,7 +439,7 @@ static noinline int vmalloc_fault(unsigned long address)
* happen within a race in page table update. In the later
* case just flush:
*/
pgd = pgd_offset(current->active_mm, address);
pgd = (pgd_t *)__va(read_cr3()) + pgd_index(address);
pgd_ref = pgd_offset_k(address);
if (pgd_none(*pgd_ref))
return -1;
......@@ -737,7 +737,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
* In this case we need to make sure we're not recursively
* faulting through the emulate_vsyscall() logic.
*/
if (current_thread_info()->sig_on_uaccess_error && signal) {
if (current->thread.sig_on_uaccess_err && signal) {
tsk->thread.trap_nr = X86_TRAP_PF;
tsk->thread.error_code = error_code | PF_USER;
tsk->thread.cr2 = address;
......
......@@ -354,7 +354,7 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
* pagetable pages as RO. So assume someone who pre-setup
* these mappings are more intelligent.
*/
if (pte_val(*pte)) {
if (!pte_none(*pte)) {
if (!after_bootmem)
pages++;
continue;
......@@ -396,7 +396,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
continue;
}
if (pmd_val(*pmd)) {
if (!pmd_none(*pmd)) {
if (!pmd_large(*pmd)) {
spin_lock(&init_mm.page_table_lock);
pte = (pte_t *)pmd_page_vaddr(*pmd);
......@@ -470,7 +470,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
continue;
}
if (pud_val(*pud)) {
if (!pud_none(*pud)) {
if (!pud_large(*pud)) {
pmd = pmd_offset(pud, 0);
last_map_addr = phys_pmd_init(pmd, addr, end,
......@@ -673,7 +673,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
for (i = 0; i < PTRS_PER_PTE; i++) {
pte = pte_start + i;
if (pte_val(*pte))
if (!pte_none(*pte))
return;
}
......@@ -691,7 +691,7 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
for (i = 0; i < PTRS_PER_PMD; i++) {
pmd = pmd_start + i;
if (pmd_val(*pmd))
if (!pmd_none(*pmd))
return;
}
......@@ -702,27 +702,6 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
spin_unlock(&init_mm.page_table_lock);
}
/* Return true if pgd is changed, otherwise return false. */
static bool __meminit free_pud_table(pud_t *pud_start, pgd_t *pgd)
{
pud_t *pud;
int i;
for (i = 0; i < PTRS_PER_PUD; i++) {
pud = pud_start + i;
if (pud_val(*pud))
return false;
}
/* free a pud table */
free_pagetable(pgd_page(*pgd), 0);
spin_lock(&init_mm.page_table_lock);
pgd_clear(pgd);
spin_unlock(&init_mm.page_table_lock);
return true;
}
static void __meminit
remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
bool direct)
......@@ -913,7 +892,6 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct)
unsigned long addr;
pgd_t *pgd;
pud_t *pud;
bool pgd_changed = false;
for (addr = start; addr < end; addr = next) {
next = pgd_addr_end(addr, end);
......@@ -924,13 +902,8 @@ remove_pagetable(unsigned long start, unsigned long end, bool direct)
pud = (pud_t *)pgd_page_vaddr(*pgd);
remove_pud_table(pud, addr, next, direct);
if (free_pud_table(pud, pgd))
pgd_changed = true;
}
if (pgd_changed)
sync_global_pgds(start, end - 1, 1);
flush_tlb_all();
}
......
......@@ -746,18 +746,6 @@ static bool try_to_free_pmd_page(pmd_t *pmd)
return true;
}
static bool try_to_free_pud_page(pud_t *pud)
{
int i;
for (i = 0; i < PTRS_PER_PUD; i++)
if (!pud_none(pud[i]))
return false;
free_page((unsigned long)pud);
return true;
}
static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
{
pte_t *pte = pte_offset_kernel(pmd, start);
......@@ -871,16 +859,6 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
*/
}
static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end)
{
pgd_t *pgd_entry = root + pgd_index(addr);
unmap_pud_range(pgd_entry, addr, end);
if (try_to_free_pud_page((pud_t *)pgd_page_vaddr(*pgd_entry)))
pgd_clear(pgd_entry);
}
static int alloc_pte_page(pmd_t *pmd)
{
pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
......@@ -1113,7 +1091,12 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
ret = populate_pud(cpa, addr, pgd_entry, pgprot);
if (ret < 0) {
unmap_pgd_range(cpa->pgd, addr,
/*
* Leave the PUD page in place in case some other CPU or thread
* already found it, but remove any useless entries we just
* added to it.
*/
unmap_pud_range(pgd_entry, addr,
addr + (cpa->numpages << PAGE_SHIFT));
return ret;
}
......@@ -1185,7 +1168,7 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
return __cpa_process_fault(cpa, address, primary);
old_pte = *kpte;
if (!pte_val(old_pte))
if (pte_none(old_pte))
return __cpa_process_fault(cpa, address, primary);
if (level == PG_LEVEL_4K) {
......@@ -1991,12 +1974,6 @@ int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
return retval;
}
void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
unsigned numpages)
{
unmap_pgd_range(root, address, address + (numpages << PAGE_SHIFT));
}
/*
* The testcases use internal knowledge of the implementation that shouldn't
* be exposed to the rest of the kernel. Include these directly here.
......
......@@ -755,11 +755,8 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
return 1;
while (cursor < to) {
if (!devmem_is_allowed(pfn)) {
pr_info("x86/PAT: Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n",
current->comm, from, to - 1);
if (!devmem_is_allowed(pfn))
return 0;
}
cursor += PAGE_SIZE;
pfn++;
}
......
......@@ -47,7 +47,7 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
return;
}
pte = pte_offset_kernel(pmd, vaddr);
if (pte_val(pteval))
if (!pte_none(pteval))
set_pte_at(&init_mm, vaddr, pte, pteval);
else
pte_clear(&init_mm, vaddr, pte);
......
......@@ -963,8 +963,6 @@ static void __init __efi_enter_virtual_mode(void)
* EFI mixed mode we need all of memory to be accessible when
* we pass parameters to the EFI runtime services in the
* thunking code.
*
* efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift);
*/
free_pages((unsigned long)new_memmap, pg_shift);
......
......@@ -49,9 +49,6 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
{
return 0;
}
void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
{
}
void __init efi_map_region(efi_memory_desc_t *md)
{
......
......@@ -285,11 +285,6 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
return 0;
}
void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
{
kernel_unmap_pages_in_pgd(efi_pgd, pa_memmap, num_pages);
}
static void __init __map_region(efi_memory_desc_t *md, u64 va)
{
unsigned long flags = _PAGE_RW;
......
......@@ -521,9 +521,7 @@ static void set_aliased_prot(void *v, pgprot_t prot)
preempt_disable();
pagefault_disable(); /* Avoid warnings due to being atomic. */
__get_user(dummy, (unsigned char __user __force *)v);
pagefault_enable();
probe_kernel_read(&dummy, v, 1);
if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
BUG();
......
......@@ -66,12 +66,8 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
u64 cursor = from;
while (cursor < to) {
if (!devmem_is_allowed(pfn)) {
printk(KERN_INFO
"Program %s tried to access /dev/mem between %Lx->%Lx.\n",
current->comm, from, to);
if (!devmem_is_allowed(pfn))
return 0;
}
cursor += PAGE_SIZE;
pfn++;
}
......
......@@ -21,7 +21,7 @@
#include <linux/isapnp.h>
#include <linux/proc_fs.h>
#include <linux/init.h>
#include <asm/uaccess.h>
#include <linux/uaccess.h>
extern struct pnp_protocol isapnp_protocol;
......
......@@ -1168,6 +1168,15 @@ COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
return do_compat_preadv64(fd, vec, vlen, pos, 0);
}
#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2
COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd,
const struct compat_iovec __user *,vec,
unsigned long, vlen, loff_t, pos, int, flags)
{
return do_compat_preadv64(fd, vec, vlen, pos, flags);
}
#endif
COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
compat_ulong_t, vlen, u32, pos_low, u32, pos_high,
......@@ -1265,6 +1274,15 @@ COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
return do_compat_pwritev64(fd, vec, vlen, pos, 0);
}
#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2
COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd,
const struct compat_iovec __user *,vec,
unsigned long, vlen, loff_t, pos, int, flags)
{
return do_compat_pwritev64(fd, vec, vlen, pos, flags);
}
#endif
COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
compat_ulong_t, vlen, u32, pos_low, u32, pos_high, int, flags)
......
......@@ -31,6 +31,19 @@ static inline void user_exit(void)
context_tracking_exit(CONTEXT_USER);
}
/* Called with interrupts disabled. */
static inline void user_enter_irqoff(void)
{
if (context_tracking_is_enabled())
__context_tracking_enter(CONTEXT_USER);
}
static inline void user_exit_irqoff(void)
{
if (context_tracking_is_enabled())
__context_tracking_exit(CONTEXT_USER);
}
static inline enum ctx_state exception_enter(void)
{
enum ctx_state prev_ctx;
......@@ -69,6 +82,8 @@ static inline enum ctx_state ct_state(void)
#else
static inline void user_enter(void) { }
static inline void user_exit(void) { }
static inline void user_enter_irqoff(void) { }
static inline void user_exit_irqoff(void) { }
static inline enum ctx_state exception_enter(void) { return 0; }
static inline void exception_exit(enum ctx_state prev_ctx) { }
static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; }
......
......@@ -594,6 +594,9 @@ struct vm_special_mapping {
int (*fault)(const struct vm_special_mapping *sm,
struct vm_area_struct *vma,
struct vm_fault *vmf);
int (*mremap)(const struct vm_special_mapping *sm,
struct vm_area_struct *new_vma);
};
enum tlb_flush_reason {
......
......@@ -95,27 +95,27 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
#ifdef CONFIG_ARCH_RANDOM
# include <asm/archrandom.h>
#else
static inline int arch_get_random_long(unsigned long *v)
static inline bool arch_get_random_long(unsigned long *v)
{
return 0;
}
static inline int arch_get_random_int(unsigned int *v)
static inline bool arch_get_random_int(unsigned int *v)
{
return 0;
}
static inline int arch_has_random(void)
static inline bool arch_has_random(void)
{
return 0;
}
static inline int arch_get_random_seed_long(unsigned long *v)
static inline bool arch_get_random_seed_long(unsigned long *v)
{
return 0;
}
static inline int arch_get_random_seed_int(unsigned int *v)
static inline bool arch_get_random_seed_int(unsigned int *v)
{
return 0;
}
static inline int arch_has_random_seed(void)
static inline bool arch_has_random_seed(void)
{
return 0;
}
......
......@@ -15,9 +15,6 @@ KCOV_INSTRUMENT_rbtree.o := n
KCOV_INSTRUMENT_list_debug.o := n
KCOV_INSTRUMENT_debugobjects.o := n
KCOV_INSTRUMENT_dynamic_debug.o := n
# Kernel does not boot if we instrument this file as it uses custom calling
# convention (see CONFIG_ARCH_HWEIGHT_CFLAGS).
KCOV_INSTRUMENT_hweight.o := n
lib-y := ctype.o string.o vsprintf.o cmdline.o \
rbtree.o radix-tree.o dump_stack.o timerqueue.o\
......@@ -74,8 +71,6 @@ obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o
obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o
obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o
GCOV_PROFILE_hweight.o := n
CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS))
obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
obj-$(CONFIG_BTREE) += btree.o
......
......@@ -14,9 +14,9 @@
#include <linux/bug.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/uaccess.h>
#include <asm/page.h>
#include <asm/uaccess.h>
/*
* bitmaps provide an array of bits, implemented using an an
......
......@@ -9,6 +9,7 @@
* The Hamming Weight of a number is the total number of bits set in it.
*/
#ifndef __HAVE_ARCH_SW_HWEIGHT
unsigned int __sw_hweight32(unsigned int w)
{
#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
......@@ -25,6 +26,7 @@ unsigned int __sw_hweight32(unsigned int w)
#endif
}
EXPORT_SYMBOL(__sw_hweight32);
#endif
unsigned int __sw_hweight16(unsigned int w)
{
......@@ -43,6 +45,7 @@ unsigned int __sw_hweight8(unsigned int w)
}
EXPORT_SYMBOL(__sw_hweight8);
#ifndef __HAVE_ARCH_SW_HWEIGHT
unsigned long __sw_hweight64(__u64 w)
{
#if BITS_PER_LONG == 32
......@@ -65,3 +68,4 @@ unsigned long __sw_hweight64(__u64 w)
#endif
}
EXPORT_SYMBOL(__sw_hweight64);
#endif
......@@ -2943,9 +2943,19 @@ static const char *special_mapping_name(struct vm_area_struct *vma)
return ((struct vm_special_mapping *)vma->vm_private_data)->name;
}
static int special_mapping_mremap(struct vm_area_struct *new_vma)
{
struct vm_special_mapping *sm = new_vma->vm_private_data;
if (sm->mremap)
return sm->mremap(sm, new_vma);
return 0;
}
static const struct vm_operations_struct special_mapping_vmops = {
.close = special_mapping_close,
.fault = special_mapping_fault,
.mremap = special_mapping_mremap,
.name = special_mapping_name,
};
......
......@@ -4,8 +4,8 @@ include ../lib.mk
.PHONY: all all_32 all_64 warn_32bit_failure clean
TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall \
check_initial_reg_state sigreturn ldt_gdt iopl
TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \
check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test
TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
test_FCMOV test_FCOMI test_FISTTP \
vdso_restorer
......
#ifndef _MPX_DEBUG_H
#define _MPX_DEBUG_H
#ifndef DEBUG_LEVEL
#define DEBUG_LEVEL 0
#endif
#define dprintf_level(level, args...) do { if(level <= DEBUG_LEVEL) printf(args); } while(0)
#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)
#define dprintf5(args...) dprintf_level(5, args)
#endif /* _MPX_DEBUG_H */
/*
* Written by Dave Hansen <dave.hansen@intel.com>
*/
#include <stdlib.h>
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <errno.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
#include <sys/mman.h>
#include <string.h>
#include <fcntl.h>
#include "mpx-debug.h"
#include "mpx-mm.h"
#include "mpx-hw.h"
unsigned long bounds_dir_global;
#define mpx_dig_abort() __mpx_dig_abort(__FILE__, __func__, __LINE__)
static void inline __mpx_dig_abort(const char *file, const char *func, int line)
{
fprintf(stderr, "MPX dig abort @ %s::%d in %s()\n", file, line, func);
printf("MPX dig abort @ %s::%d in %s()\n", file, line, func);
abort();
}
/*
* run like this (BDIR finds the probably bounds directory):
*
* BDIR="$(cat /proc/$pid/smaps | grep -B1 2097152 \
* | head -1 | awk -F- '{print $1}')";
* ./mpx-dig $pid 0x$BDIR
*
* NOTE:
* assumes that the only 2097152-kb VMA is the bounds dir
*/
long nr_incore(void *ptr, unsigned long size_bytes)
{
int i;
long ret = 0;
long vec_len = size_bytes / PAGE_SIZE;
unsigned char *vec = malloc(vec_len);
int incore_ret;
if (!vec)
mpx_dig_abort();
incore_ret = mincore(ptr, size_bytes, vec);
if (incore_ret) {
printf("mincore ret: %d\n", incore_ret);
perror("mincore");
mpx_dig_abort();
}
for (i = 0; i < vec_len; i++)
ret += vec[i];
free(vec);
return ret;
}
int open_proc(int pid, char *file)
{
static char buf[100];
int fd;
snprintf(&buf[0], sizeof(buf), "/proc/%d/%s", pid, file);
fd = open(&buf[0], O_RDONLY);
if (fd < 0)
perror(buf);
return fd;
}
struct vaddr_range {
unsigned long start;
unsigned long end;
};
struct vaddr_range *ranges;
int nr_ranges_allocated;
int nr_ranges_populated;
int last_range = -1;
int __pid_load_vaddrs(int pid)
{
int ret = 0;
int proc_maps_fd = open_proc(pid, "maps");
char linebuf[10000];
unsigned long start;
unsigned long end;
char rest[1000];
FILE *f = fdopen(proc_maps_fd, "r");
if (!f)
mpx_dig_abort();
nr_ranges_populated = 0;
while (!feof(f)) {
char *readret = fgets(linebuf, sizeof(linebuf), f);
int parsed;
if (readret == NULL) {
if (feof(f))
break;
mpx_dig_abort();
}
parsed = sscanf(linebuf, "%lx-%lx%s", &start, &end, rest);
if (parsed != 3)
mpx_dig_abort();
dprintf4("result[%d]: %lx-%lx<->%s\n", parsed, start, end, rest);
if (nr_ranges_populated >= nr_ranges_allocated) {
ret = -E2BIG;
break;
}
ranges[nr_ranges_populated].start = start;
ranges[nr_ranges_populated].end = end;
nr_ranges_populated++;
}
last_range = -1;
fclose(f);
close(proc_maps_fd);
return ret;
}
int pid_load_vaddrs(int pid)
{
int ret;
dprintf2("%s(%d)\n", __func__, pid);
if (!ranges) {
nr_ranges_allocated = 4;
ranges = malloc(nr_ranges_allocated * sizeof(ranges[0]));
dprintf2("%s(%d) allocated %d ranges @ %p\n", __func__, pid,
nr_ranges_allocated, ranges);
assert(ranges != NULL);
}
do {
ret = __pid_load_vaddrs(pid);
if (!ret)
break;
if (ret == -E2BIG) {
dprintf2("%s(%d) need to realloc\n", __func__, pid);
nr_ranges_allocated *= 2;
ranges = realloc(ranges,
nr_ranges_allocated * sizeof(ranges[0]));
dprintf2("%s(%d) allocated %d ranges @ %p\n", __func__,
pid, nr_ranges_allocated, ranges);
assert(ranges != NULL);
dprintf1("reallocating to hold %d ranges\n", nr_ranges_allocated);
}
} while (1);
dprintf2("%s(%d) done\n", __func__, pid);
return ret;
}
static inline int vaddr_in_range(unsigned long vaddr, struct vaddr_range *r)
{
if (vaddr < r->start)
return 0;
if (vaddr >= r->end)
return 0;
return 1;
}
static inline int vaddr_mapped_by_range(unsigned long vaddr)
{
int i;
if (last_range > 0 && vaddr_in_range(vaddr, &ranges[last_range]))
return 1;
for (i = 0; i < nr_ranges_populated; i++) {
struct vaddr_range *r = &ranges[i];
if (vaddr_in_range(vaddr, r))
continue;
last_range = i;
return 1;
}
return 0;
}
const int bt_entry_size_bytes = sizeof(unsigned long) * 4;
void *read_bounds_table_into_buf(unsigned long table_vaddr)
{
#ifdef MPX_DIG_STANDALONE
static char bt_buf[MPX_BOUNDS_TABLE_SIZE_BYTES];
off_t seek_ret = lseek(fd, table_vaddr, SEEK_SET);
if (seek_ret != table_vaddr)
mpx_dig_abort();
int read_ret = read(fd, &bt_buf, sizeof(bt_buf));
if (read_ret != sizeof(bt_buf))
mpx_dig_abort();
return &bt_buf;
#else
return (void *)table_vaddr;
#endif
}
int dump_table(unsigned long table_vaddr, unsigned long base_controlled_vaddr,
unsigned long bde_vaddr)
{
unsigned long offset_inside_bt;
int nr_entries = 0;
int do_abort = 0;
char *bt_buf;
dprintf3("%s() base_controlled_vaddr: 0x%012lx bde_vaddr: 0x%012lx\n",
__func__, base_controlled_vaddr, bde_vaddr);
bt_buf = read_bounds_table_into_buf(table_vaddr);
dprintf4("%s() read done\n", __func__);
for (offset_inside_bt = 0;
offset_inside_bt < MPX_BOUNDS_TABLE_SIZE_BYTES;
offset_inside_bt += bt_entry_size_bytes) {
unsigned long bt_entry_index;
unsigned long bt_entry_controls;
unsigned long this_bt_entry_for_vaddr;
unsigned long *bt_entry_buf;
int i;
dprintf4("%s() offset_inside_bt: 0x%lx of 0x%llx\n", __func__,
offset_inside_bt, MPX_BOUNDS_TABLE_SIZE_BYTES);
bt_entry_buf = (void *)&bt_buf[offset_inside_bt];
if (!bt_buf) {
printf("null bt_buf\n");
mpx_dig_abort();
}
if (!bt_entry_buf) {
printf("null bt_entry_buf\n");
mpx_dig_abort();
}
dprintf4("%s() reading *bt_entry_buf @ %p\n", __func__,
bt_entry_buf);
if (!bt_entry_buf[0] &&
!bt_entry_buf[1] &&
!bt_entry_buf[2] &&
!bt_entry_buf[3])
continue;
nr_entries++;
bt_entry_index = offset_inside_bt/bt_entry_size_bytes;
bt_entry_controls = sizeof(void *);
this_bt_entry_for_vaddr =
base_controlled_vaddr + bt_entry_index*bt_entry_controls;
/*
* We sign extend vaddr bits 48->63 which effectively
* creates a hole in the virtual address space.
* This calculation corrects for the hole.
*/
if (this_bt_entry_for_vaddr > 0x00007fffffffffffUL)
this_bt_entry_for_vaddr |= 0xffff800000000000;
if (!vaddr_mapped_by_range(this_bt_entry_for_vaddr)) {
printf("bt_entry_buf: %p\n", bt_entry_buf);
printf("there is a bte for %lx but no mapping\n",
this_bt_entry_for_vaddr);
printf(" bde vaddr: %016lx\n", bde_vaddr);
printf("base_controlled_vaddr: %016lx\n", base_controlled_vaddr);
printf(" table_vaddr: %016lx\n", table_vaddr);
printf(" entry vaddr: %016lx @ offset %lx\n",
table_vaddr + offset_inside_bt, offset_inside_bt);
do_abort = 1;
mpx_dig_abort();
}
if (DEBUG_LEVEL < 4)
continue;
printf("table entry[%lx]: ", offset_inside_bt);
for (i = 0; i < bt_entry_size_bytes; i += sizeof(unsigned long))
printf("0x%016lx ", bt_entry_buf[i]);
printf("\n");
}
if (do_abort)
mpx_dig_abort();
dprintf4("%s() done\n", __func__);
return nr_entries;
}
int search_bd_buf(char *buf, int len_bytes, unsigned long bd_offset_bytes,
int *nr_populated_bdes)
{
unsigned long i;
int total_entries = 0;
dprintf3("%s(%p, %x, %lx, ...) buf end: %p\n", __func__, buf,
len_bytes, bd_offset_bytes, buf + len_bytes);
for (i = 0; i < len_bytes; i += sizeof(unsigned long)) {
unsigned long bd_index = (bd_offset_bytes + i) / sizeof(unsigned long);
unsigned long *bounds_dir_entry_ptr = (unsigned long *)&buf[i];
unsigned long bounds_dir_entry;
unsigned long bd_for_vaddr;
unsigned long bt_start;
unsigned long bt_tail;
int nr_entries;
dprintf4("%s() loop i: %ld bounds_dir_entry_ptr: %p\n", __func__, i,
bounds_dir_entry_ptr);
bounds_dir_entry = *bounds_dir_entry_ptr;
if (!bounds_dir_entry) {
dprintf4("no bounds dir at index 0x%lx / 0x%lx "
"start at offset:%lx %lx\n", bd_index, bd_index,
bd_offset_bytes, i);
continue;
}
dprintf3("found bounds_dir_entry: 0x%lx @ "
"index 0x%lx buf ptr: %p\n", bounds_dir_entry, i,
&buf[i]);
/* mask off the enable bit: */
bounds_dir_entry &= ~0x1;
(*nr_populated_bdes)++;
dprintf4("nr_populated_bdes: %p\n", nr_populated_bdes);
dprintf4("*nr_populated_bdes: %d\n", *nr_populated_bdes);
bt_start = bounds_dir_entry;
bt_tail = bounds_dir_entry + MPX_BOUNDS_TABLE_SIZE_BYTES - 1;
if (!vaddr_mapped_by_range(bt_start)) {
printf("bounds directory 0x%lx points to nowhere\n",
bounds_dir_entry);
mpx_dig_abort();
}
if (!vaddr_mapped_by_range(bt_tail)) {
printf("bounds directory end 0x%lx points to nowhere\n",
bt_tail);
mpx_dig_abort();
}
/*
* Each bounds directory entry controls 1MB of virtual address
* space. This variable is the virtual address in the process
* of the beginning of the area controlled by this bounds_dir.
*/
bd_for_vaddr = bd_index * (1UL<<20);
nr_entries = dump_table(bounds_dir_entry, bd_for_vaddr,
bounds_dir_global+bd_offset_bytes+i);
total_entries += nr_entries;
dprintf5("dir entry[%4ld @ %p]: 0x%lx %6d entries "
"total this buf: %7d bd_for_vaddrs: 0x%lx -> 0x%lx\n",
bd_index, buf+i,
bounds_dir_entry, nr_entries, total_entries,
bd_for_vaddr, bd_for_vaddr + (1UL<<20));
}
dprintf3("%s(%p, %x, %lx, ...) done\n", __func__, buf, len_bytes,
bd_offset_bytes);
return total_entries;
}
int proc_pid_mem_fd = -1;
void *fill_bounds_dir_buf_other(long byte_offset_inside_bounds_dir,
long buffer_size_bytes, void *buffer)
{
unsigned long seekto = bounds_dir_global + byte_offset_inside_bounds_dir;
int read_ret;
off_t seek_ret = lseek(proc_pid_mem_fd, seekto, SEEK_SET);
if (seek_ret != seekto)
mpx_dig_abort();
read_ret = read(proc_pid_mem_fd, buffer, buffer_size_bytes);
/* there shouldn't practically be short reads of /proc/$pid/mem */
if (read_ret != buffer_size_bytes)
mpx_dig_abort();
return buffer;
}
void *fill_bounds_dir_buf_self(long byte_offset_inside_bounds_dir,
long buffer_size_bytes, void *buffer)
{
unsigned char vec[buffer_size_bytes / PAGE_SIZE];
char *dig_bounds_dir_ptr =
(void *)(bounds_dir_global + byte_offset_inside_bounds_dir);
/*
* use mincore() to quickly find the areas of the bounds directory
* that have memory and thus will be worth scanning.
*/
int incore_ret;
int incore = 0;
int i;
dprintf4("%s() dig_bounds_dir_ptr: %p\n", __func__, dig_bounds_dir_ptr);
incore_ret = mincore(dig_bounds_dir_ptr, buffer_size_bytes, &vec[0]);
if (incore_ret) {
printf("mincore ret: %d\n", incore_ret);
perror("mincore");
mpx_dig_abort();
}
for (i = 0; i < sizeof(vec); i++)
incore += vec[i];
dprintf4("%s() total incore: %d\n", __func__, incore);
if (!incore)
return NULL;
dprintf3("%s() total incore: %d\n", __func__, incore);
return dig_bounds_dir_ptr;
}
int inspect_pid(int pid)
{
static int dig_nr;
long offset_inside_bounds_dir;
char bounds_dir_buf[sizeof(unsigned long) * (1UL << 15)];
char *dig_bounds_dir_ptr;
int total_entries = 0;
int nr_populated_bdes = 0;
int inspect_self;
if (getpid() == pid) {
dprintf4("inspecting self\n");
inspect_self = 1;
} else {
dprintf4("inspecting pid %d\n", pid);
mpx_dig_abort();
}
for (offset_inside_bounds_dir = 0;
offset_inside_bounds_dir < MPX_BOUNDS_TABLE_SIZE_BYTES;
offset_inside_bounds_dir += sizeof(bounds_dir_buf)) {
static int bufs_skipped;
int this_entries;
if (inspect_self) {
dig_bounds_dir_ptr =
fill_bounds_dir_buf_self(offset_inside_bounds_dir,
sizeof(bounds_dir_buf),
&bounds_dir_buf[0]);
} else {
dig_bounds_dir_ptr =
fill_bounds_dir_buf_other(offset_inside_bounds_dir,
sizeof(bounds_dir_buf),
&bounds_dir_buf[0]);
}
if (!dig_bounds_dir_ptr) {
bufs_skipped++;
continue;
}
this_entries = search_bd_buf(dig_bounds_dir_ptr,
sizeof(bounds_dir_buf),
offset_inside_bounds_dir,
&nr_populated_bdes);
total_entries += this_entries;
}
printf("mpx dig (%3d) complete, SUCCESS (%8d / %4d)\n", ++dig_nr,
total_entries, nr_populated_bdes);
return total_entries + nr_populated_bdes;
}
#ifdef MPX_DIG_REMOTE
int main(int argc, char **argv)
{
int err;
char *c;
unsigned long bounds_dir_entry;
int pid;
printf("mpx-dig starting...\n");
err = sscanf(argv[1], "%d", &pid);
printf("parsing: '%s', err: %d\n", argv[1], err);
if (err != 1)
mpx_dig_abort();
err = sscanf(argv[2], "%lx", &bounds_dir_global);
printf("parsing: '%s': %d\n", argv[2], err);
if (err != 1)
mpx_dig_abort();
proc_pid_mem_fd = open_proc(pid, "mem");
if (proc_pid_mem_fd < 0)
mpx_dig_abort();
inspect_pid(pid);
return 0;
}
#endif
long inspect_me(struct mpx_bounds_dir *bounds_dir)
{
int pid = getpid();
pid_load_vaddrs(pid);
bounds_dir_global = (unsigned long)bounds_dir;
dprintf4("enter %s() bounds dir: %p\n", __func__, bounds_dir);
return inspect_pid(pid);
}
#ifndef _MPX_HW_H
#define _MPX_HW_H
#include <assert.h>
/* Describe the MPX Hardware Layout in here */
#define NR_MPX_BOUNDS_REGISTERS 4
#ifdef __i386__
#define MPX_BOUNDS_TABLE_ENTRY_SIZE_BYTES 16 /* 4 * 32-bits */
#define MPX_BOUNDS_TABLE_SIZE_BYTES (1ULL << 14) /* 16k */
#define MPX_BOUNDS_DIR_ENTRY_SIZE_BYTES 4
#define MPX_BOUNDS_DIR_SIZE_BYTES (1ULL << 22) /* 4MB */
#define MPX_BOUNDS_TABLE_BOTTOM_BIT 2
#define MPX_BOUNDS_TABLE_TOP_BIT 11
#define MPX_BOUNDS_DIR_BOTTOM_BIT 12
#define MPX_BOUNDS_DIR_TOP_BIT 31
#else
/*
* Linear Address of "pointer" (LAp)
* 0 -> 2: ignored
* 3 -> 19: index in to bounds table
* 20 -> 47: index in to bounds directory
* 48 -> 63: ignored
*/
#define MPX_BOUNDS_TABLE_ENTRY_SIZE_BYTES 32
#define MPX_BOUNDS_TABLE_SIZE_BYTES (1ULL << 22) /* 4MB */
#define MPX_BOUNDS_DIR_ENTRY_SIZE_BYTES 8
#define MPX_BOUNDS_DIR_SIZE_BYTES (1ULL << 31) /* 2GB */
#define MPX_BOUNDS_TABLE_BOTTOM_BIT 3
#define MPX_BOUNDS_TABLE_TOP_BIT 19
#define MPX_BOUNDS_DIR_BOTTOM_BIT 20
#define MPX_BOUNDS_DIR_TOP_BIT 47
#endif
#define MPX_BOUNDS_DIR_NR_ENTRIES \
(MPX_BOUNDS_DIR_SIZE_BYTES/MPX_BOUNDS_DIR_ENTRY_SIZE_BYTES)
#define MPX_BOUNDS_TABLE_NR_ENTRIES \
(MPX_BOUNDS_TABLE_SIZE_BYTES/MPX_BOUNDS_TABLE_ENTRY_SIZE_BYTES)
#define MPX_BOUNDS_TABLE_ENTRY_VALID_BIT 0x1
struct mpx_bd_entry {
union {
char x[MPX_BOUNDS_DIR_ENTRY_SIZE_BYTES];
void *contents[1];
};
} __attribute__((packed));
struct mpx_bt_entry {
union {
char x[MPX_BOUNDS_TABLE_ENTRY_SIZE_BYTES];
unsigned long contents[1];
};
} __attribute__((packed));
struct mpx_bounds_dir {
struct mpx_bd_entry entries[MPX_BOUNDS_DIR_NR_ENTRIES];
} __attribute__((packed));
struct mpx_bounds_table {
struct mpx_bt_entry entries[MPX_BOUNDS_TABLE_NR_ENTRIES];
} __attribute__((packed));
static inline unsigned long GET_BITS(unsigned long val, int bottombit, int topbit)
{
int total_nr_bits = topbit - bottombit;
unsigned long mask = (1UL << total_nr_bits)-1;
return (val >> bottombit) & mask;
}
static inline unsigned long __vaddr_bounds_table_index(void *vaddr)
{
return GET_BITS((unsigned long)vaddr, MPX_BOUNDS_TABLE_BOTTOM_BIT,
MPX_BOUNDS_TABLE_TOP_BIT);
}
static inline unsigned long __vaddr_bounds_directory_index(void *vaddr)
{
return GET_BITS((unsigned long)vaddr, MPX_BOUNDS_DIR_BOTTOM_BIT,
MPX_BOUNDS_DIR_TOP_BIT);
}
static inline struct mpx_bd_entry *mpx_vaddr_to_bd_entry(void *vaddr,
struct mpx_bounds_dir *bounds_dir)
{
unsigned long index = __vaddr_bounds_directory_index(vaddr);
return &bounds_dir->entries[index];
}
static inline int bd_entry_valid(struct mpx_bd_entry *bounds_dir_entry)
{
unsigned long __bd_entry = (unsigned long)bounds_dir_entry->contents;
return (__bd_entry & MPX_BOUNDS_TABLE_ENTRY_VALID_BIT);
}
static inline struct mpx_bounds_table *
__bd_entry_to_bounds_table(struct mpx_bd_entry *bounds_dir_entry)
{
unsigned long __bd_entry = (unsigned long)bounds_dir_entry->contents;
assert(__bd_entry & MPX_BOUNDS_TABLE_ENTRY_VALID_BIT);
__bd_entry &= ~MPX_BOUNDS_TABLE_ENTRY_VALID_BIT;
return (struct mpx_bounds_table *)__bd_entry;
}
static inline struct mpx_bt_entry *
mpx_vaddr_to_bt_entry(void *vaddr, struct mpx_bounds_dir *bounds_dir)
{
struct mpx_bd_entry *bde = mpx_vaddr_to_bd_entry(vaddr, bounds_dir);
struct mpx_bounds_table *bt = __bd_entry_to_bounds_table(bde);
unsigned long index = __vaddr_bounds_table_index(vaddr);
return &bt->entries[index];
}
#endif /* _MPX_HW_H */
此差异已折叠。
#ifndef _MPX_MM_H
#define _MPX_MM_H
#define PAGE_SIZE 4096
#define MB (1UL<<20)
extern long nr_incore(void *ptr, unsigned long size_bytes);
#endif /* _MPX_MM_H */
/*
* 32-bit test to check vDSO mremap.
*
* Copyright (c) 2016 Dmitry Safonov
* Suggested-by: Andrew Lutomirski
*
* 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.
*/
/*
* Can be built statically:
* gcc -Os -Wall -static -m32 test_mremap_vdso.c
*/
#define _GNU_SOURCE
#include <stdio.h>
#include <errno.h>
#include <unistd.h>
#include <string.h>
#include <sys/mman.h>
#include <sys/auxv.h>
#include <sys/syscall.h>
#include <sys/wait.h>
#define PAGE_SIZE 4096
static int try_to_remap(void *vdso_addr, unsigned long size)
{
void *dest_addr, *new_addr;
/* Searching for memory location where to remap */
dest_addr = mmap(0, size, PROT_NONE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
if (dest_addr == MAP_FAILED) {
printf("[WARN]\tmmap failed (%d): %m\n", errno);
return 0;
}
printf("[NOTE]\tMoving vDSO: [%p, %#lx] -> [%p, %#lx]\n",
vdso_addr, (unsigned long)vdso_addr + size,
dest_addr, (unsigned long)dest_addr + size);
fflush(stdout);
new_addr = mremap(vdso_addr, size, size,
MREMAP_FIXED|MREMAP_MAYMOVE, dest_addr);
if ((unsigned long)new_addr == (unsigned long)-1) {
munmap(dest_addr, size);
if (errno == EINVAL) {
printf("[NOTE]\tvDSO partial move failed, will try with bigger size\n");
return -1; /* Retry with larger */
}
printf("[FAIL]\tmremap failed (%d): %m\n", errno);
return 1;
}
return 0;
}
int main(int argc, char **argv, char **envp)
{
pid_t child;
child = fork();
if (child == -1) {
printf("[WARN]\tfailed to fork (%d): %m\n", errno);
return 1;
}
if (child == 0) {
unsigned long vdso_size = PAGE_SIZE;
unsigned long auxval;
int ret = -1;
auxval = getauxval(AT_SYSINFO_EHDR);
printf("\tAT_SYSINFO_EHDR is %#lx\n", auxval);
if (!auxval || auxval == -ENOENT) {
printf("[WARN]\tgetauxval failed\n");
return 0;
}
/* Simpler than parsing ELF header */
while (ret < 0) {
ret = try_to_remap((void *)auxval, vdso_size);
vdso_size += PAGE_SIZE;
}
/* Glibc is likely to explode now - exit with raw syscall */
asm volatile ("int $0x80" : : "a" (__NR_exit), "b" (!!ret));
} else {
int status;
if (waitpid(child, &status, 0) != child ||
!WIFEXITED(status)) {
printf("[FAIL]\tmremap() of the vDSO does not work on this kernel!\n");
return 1;
} else if (WEXITSTATUS(status) != 0) {
printf("[FAIL]\tChild failed with %d\n",
WEXITSTATUS(status));
return 1;
}
printf("[OK]\n");
}
return 0;
}
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册