linux/arch/riscv/include/asm/uaccess.h

409 lines
11 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2012 Regents of the University of California
*
* This file was copied from include/asm-generic/uaccess.h
*/
#ifndef _ASM_RISCV_UACCESS_H
#define _ASM_RISCV_UACCESS_H
#include <asm/pgtable.h> /* for TASK_SIZE */
#define _ASM_EXTABLE(from, to) \
" .pushsection __ex_table, \"a\"\n" \
" .balign " RISCV_SZPTR " \n" \
" " RISCV_PTR "(" #from "), (" #to ")\n" \
" .popsection\n"
/*
* User space memory access functions
*/
#ifdef CONFIG_MMU
#include <linux/errno.h>
#include <linux/compiler.h>
#include <linux/thread_info.h>
#include <asm/byteorder.h>
#include <asm/extable.h>
#include <asm/asm.h>
#define __enable_user_access() \
__asm__ __volatile__ ("csrs sstatus, %0" : : "r" (SR_SUM) : "memory")
#define __disable_user_access() \
__asm__ __volatile__ ("csrc sstatus, %0" : : "r" (SR_SUM) : "memory")
/**
* access_ok: - Checks if a user space pointer is valid
* @addr: User space pointer to start of block to check
* @size: Size of block to check
*
* Context: User context only. This function may sleep.
*
* Checks if a pointer to a block of memory in user space is valid.
*
* Returns true (nonzero) if the memory block may be valid, false (zero)
* if it is definitely invalid.
*
* Note that, depending on architecture, this function probably just
* checks that the pointer is in the user space range - after calling
* this function, memory access functions may still return -EFAULT.
*/
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 05:57:57 +03:00
#define access_ok(addr, size) ({ \
__chk_user_ptr(addr); \
likely(__access_ok((unsigned long __force)(addr), (size))); \
})
/*
* Ensure that the range [addr, addr+size) is within the process's
* address space
*/
static inline int __access_ok(unsigned long addr, unsigned long size)
{
return size <= TASK_SIZE && addr <= TASK_SIZE - size;
}
/*
* The exception table consists of pairs of addresses: the first is the
* address of an instruction that is allowed to fault, and the second is
* the address at which the program should continue. No registers are
* modified, so it is entirely up to the continuation code to figure out
* what to do.
*
* All the routines below use bits of fixup code that are out of line
* with the main instruction path. This means when everything is well,
* we don't even have to jump over them. Further, they do not intrude
* on our cache or tlb entries.
*/
#define __LSW 0
#define __MSW 1
/*
* The "__xxx" versions of the user access functions do not verify the address
* space - it must have been done previously with a separate "access_ok()"
* call.
*/
#define __get_user_asm(insn, x, ptr, err) \
do { \
uintptr_t __tmp; \
__typeof__(x) __x; \
__asm__ __volatile__ ( \
"1:\n" \
" " insn " %1, %3\n" \
"2:\n" \
" .section .fixup,\"ax\"\n" \
" .balign 4\n" \
"3:\n" \
" li %0, %4\n" \
" li %1, 0\n" \
" jump 2b, %2\n" \
" .previous\n" \
_ASM_EXTABLE(1b, 3b) \
: "+r" (err), "=&r" (__x), "=r" (__tmp) \
: "m" (*(ptr)), "i" (-EFAULT)); \
(x) = __x; \
} while (0)
#ifdef CONFIG_64BIT
#define __get_user_8(x, ptr, err) \
__get_user_asm("ld", x, ptr, err)
#else /* !CONFIG_64BIT */
#define __get_user_8(x, ptr, err) \
do { \
u32 __user *__ptr = (u32 __user *)(ptr); \
u32 __lo, __hi; \
uintptr_t __tmp; \
__asm__ __volatile__ ( \
"1:\n" \
" lw %1, %4\n" \
"2:\n" \
" lw %2, %5\n" \
"3:\n" \
" .section .fixup,\"ax\"\n" \
" .balign 4\n" \
"4:\n" \
" li %0, %6\n" \
" li %1, 0\n" \
" li %2, 0\n" \
" jump 3b, %3\n" \
" .previous\n" \
_ASM_EXTABLE(1b, 4b) \
_ASM_EXTABLE(2b, 4b) \
: "+r" (err), "=&r" (__lo), "=r" (__hi), \
"=r" (__tmp) \
: "m" (__ptr[__LSW]), "m" (__ptr[__MSW]), \
"i" (-EFAULT)); \
(x) = (__typeof__(x))((__typeof__((x)-(x)))( \
(((u64)__hi << 32) | __lo))); \
} while (0)
#endif /* CONFIG_64BIT */
#define __get_user_nocheck(x, __gu_ptr, __gu_err) \
do { \
switch (sizeof(*__gu_ptr)) { \
case 1: \
__get_user_asm("lb", (x), __gu_ptr, __gu_err); \
break; \
case 2: \
__get_user_asm("lh", (x), __gu_ptr, __gu_err); \
break; \
case 4: \
__get_user_asm("lw", (x), __gu_ptr, __gu_err); \
break; \
case 8: \
__get_user_8((x), __gu_ptr, __gu_err); \
break; \
default: \
BUILD_BUG(); \
} \
} while (0)
/**
* __get_user: - Get a simple variable from user space, with less checking.
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
* Context: User context only. This function may sleep.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
* data types like structures or arrays.
*
* @ptr must have pointer-to-simple-variable type, and the result of
* dereferencing @ptr must be assignable to @x without a cast.
*
* Caller must check the pointer with access_ok() before calling this
* function.
*
* Returns zero on success, or -EFAULT on error.
* On error, the variable @x is set to zero.
*/
#define __get_user(x, ptr) \
({ \
const __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
long __gu_err = 0; \
\
__chk_user_ptr(__gu_ptr); \
\
__enable_user_access(); \
__get_user_nocheck(x, __gu_ptr, __gu_err); \
__disable_user_access(); \
\
__gu_err; \
})
/**
* get_user: - Get a simple variable from user space.
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
* Context: User context only. This function may sleep.
*
* This macro copies a single simple variable from user space to kernel
* space. It supports simple types like char and int, but not larger
* data types like structures or arrays.
*
* @ptr must have pointer-to-simple-variable type, and the result of
* dereferencing @ptr must be assignable to @x without a cast.
*
* Returns zero on success, or -EFAULT on error.
* On error, the variable @x is set to zero.
*/
#define get_user(x, ptr) \
({ \
const __typeof__(*(ptr)) __user *__p = (ptr); \
might_fault(); \
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 05:57:57 +03:00
access_ok(__p, sizeof(*__p)) ? \
__get_user((x), __p) : \
((x) = 0, -EFAULT); \
})
#define __put_user_asm(insn, x, ptr, err) \
do { \
uintptr_t __tmp; \
__typeof__(*(ptr)) __x = x; \
__asm__ __volatile__ ( \
"1:\n" \
" " insn " %z3, %2\n" \
"2:\n" \
" .section .fixup,\"ax\"\n" \
" .balign 4\n" \
"3:\n" \
" li %0, %4\n" \
" jump 2b, %1\n" \
" .previous\n" \
_ASM_EXTABLE(1b, 3b) \
: "+r" (err), "=r" (__tmp), "=m" (*(ptr)) \
: "rJ" (__x), "i" (-EFAULT)); \
} while (0)
#ifdef CONFIG_64BIT
#define __put_user_8(x, ptr, err) \
__put_user_asm("sd", x, ptr, err)
#else /* !CONFIG_64BIT */
#define __put_user_8(x, ptr, err) \
do { \
u32 __user *__ptr = (u32 __user *)(ptr); \
u64 __x = (__typeof__((x)-(x)))(x); \
uintptr_t __tmp; \
__asm__ __volatile__ ( \
"1:\n" \
" sw %z4, %2\n" \
"2:\n" \
" sw %z5, %3\n" \
"3:\n" \
" .section .fixup,\"ax\"\n" \
" .balign 4\n" \
"4:\n" \
" li %0, %6\n" \
" jump 3b, %1\n" \
" .previous\n" \
_ASM_EXTABLE(1b, 4b) \
_ASM_EXTABLE(2b, 4b) \
: "+r" (err), "=r" (__tmp), \
"=m" (__ptr[__LSW]), \
"=m" (__ptr[__MSW]) \
: "rJ" (__x), "rJ" (__x >> 32), "i" (-EFAULT)); \
} while (0)
#endif /* CONFIG_64BIT */
#define __put_user_nocheck(x, __gu_ptr, __pu_err) \
do { \
switch (sizeof(*__gu_ptr)) { \
case 1: \
__put_user_asm("sb", (x), __gu_ptr, __pu_err); \
break; \
case 2: \
__put_user_asm("sh", (x), __gu_ptr, __pu_err); \
break; \
case 4: \
__put_user_asm("sw", (x), __gu_ptr, __pu_err); \
break; \
case 8: \
__put_user_8((x), __gu_ptr, __pu_err); \
break; \
default: \
BUILD_BUG(); \
} \
} while (0)
/**
* __put_user: - Write a simple value into user space, with less checking.
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
* Context: User context only. This function may sleep.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
* data types like structures or arrays.
*
* @ptr must have pointer-to-simple-variable type, and @x must be assignable
riscv: evaluate put_user() arg before enabling user access The <asm/uaccess.h> header has a problem with put_user(a, ptr) if the 'a' is not a simple variable, such as a function. This can lead to the compiler producing code as so: 1: enable_user_access() 2: evaluate 'a' into register 'r' 3: put 'r' to 'ptr' 4: disable_user_acess() The issue is that 'a' is now being evaluated with the user memory protections disabled. So we try and force the evaulation by assigning 'x' to __val at the start, and hoping the compiler barriers in enable_user_access() do the job of ordering step 2 before step 1. This has shown up in a bug where 'a' sleeps and thus schedules out and loses the SR_SUM flag. This isn't sufficient to fully fix, but should reduce the window of opportunity. The first instance of this we found is in scheudle_tail() where the code does: $ less -N kernel/sched/core.c 4263 if (current->set_child_tid) 4264 put_user(task_pid_vnr(current), current->set_child_tid); Here, the task_pid_vnr(current) is called within the block that has enabled the user memory access. This can be made worse with KASAN which makes task_pid_vnr() a rather large call with plenty of opportunity to sleep. Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk> Reported-by: syzbot+e74b94fe601ab9552d69@syzkaller.appspotmail.com Suggested-by: Arnd Bergman <arnd@arndb.de> -- Changes since v1: - fixed formatting and updated the patch description with more info Changes since v2: - fixed commenting on __put_user() (schwab@linux-m68k.org) Change since v3: - fixed RFC in patch title. Should be ready to merge. Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
2021-03-29 12:57:49 +03:00
* to the result of dereferencing @ptr. The value of @x is copied to avoid
* re-ordering where @x is evaluated inside the block that enables user-space
* access (thus bypassing user space protection if @x is a function).
*
* Caller must check the pointer with access_ok() before calling this
* function.
*
* Returns zero on success, or -EFAULT on error.
*/
#define __put_user(x, ptr) \
({ \
__typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
riscv: evaluate put_user() arg before enabling user access The <asm/uaccess.h> header has a problem with put_user(a, ptr) if the 'a' is not a simple variable, such as a function. This can lead to the compiler producing code as so: 1: enable_user_access() 2: evaluate 'a' into register 'r' 3: put 'r' to 'ptr' 4: disable_user_acess() The issue is that 'a' is now being evaluated with the user memory protections disabled. So we try and force the evaulation by assigning 'x' to __val at the start, and hoping the compiler barriers in enable_user_access() do the job of ordering step 2 before step 1. This has shown up in a bug where 'a' sleeps and thus schedules out and loses the SR_SUM flag. This isn't sufficient to fully fix, but should reduce the window of opportunity. The first instance of this we found is in scheudle_tail() where the code does: $ less -N kernel/sched/core.c 4263 if (current->set_child_tid) 4264 put_user(task_pid_vnr(current), current->set_child_tid); Here, the task_pid_vnr(current) is called within the block that has enabled the user memory access. This can be made worse with KASAN which makes task_pid_vnr() a rather large call with plenty of opportunity to sleep. Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk> Reported-by: syzbot+e74b94fe601ab9552d69@syzkaller.appspotmail.com Suggested-by: Arnd Bergman <arnd@arndb.de> -- Changes since v1: - fixed formatting and updated the patch description with more info Changes since v2: - fixed commenting on __put_user() (schwab@linux-m68k.org) Change since v3: - fixed RFC in patch title. Should be ready to merge. Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
2021-03-29 12:57:49 +03:00
__typeof__(*__gu_ptr) __val = (x); \
long __pu_err = 0; \
\
__chk_user_ptr(__gu_ptr); \
\
__enable_user_access(); \
riscv: evaluate put_user() arg before enabling user access The <asm/uaccess.h> header has a problem with put_user(a, ptr) if the 'a' is not a simple variable, such as a function. This can lead to the compiler producing code as so: 1: enable_user_access() 2: evaluate 'a' into register 'r' 3: put 'r' to 'ptr' 4: disable_user_acess() The issue is that 'a' is now being evaluated with the user memory protections disabled. So we try and force the evaulation by assigning 'x' to __val at the start, and hoping the compiler barriers in enable_user_access() do the job of ordering step 2 before step 1. This has shown up in a bug where 'a' sleeps and thus schedules out and loses the SR_SUM flag. This isn't sufficient to fully fix, but should reduce the window of opportunity. The first instance of this we found is in scheudle_tail() where the code does: $ less -N kernel/sched/core.c 4263 if (current->set_child_tid) 4264 put_user(task_pid_vnr(current), current->set_child_tid); Here, the task_pid_vnr(current) is called within the block that has enabled the user memory access. This can be made worse with KASAN which makes task_pid_vnr() a rather large call with plenty of opportunity to sleep. Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk> Reported-by: syzbot+e74b94fe601ab9552d69@syzkaller.appspotmail.com Suggested-by: Arnd Bergman <arnd@arndb.de> -- Changes since v1: - fixed formatting and updated the patch description with more info Changes since v2: - fixed commenting on __put_user() (schwab@linux-m68k.org) Change since v3: - fixed RFC in patch title. Should be ready to merge. Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>
2021-03-29 12:57:49 +03:00
__put_user_nocheck(__val, __gu_ptr, __pu_err); \
__disable_user_access(); \
\
__pu_err; \
})
/**
* put_user: - Write a simple value into user space.
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
* Context: User context only. This function may sleep.
*
* This macro copies a single simple value from kernel space to user
* space. It supports simple types like char and int, but not larger
* data types like structures or arrays.
*
* @ptr must have pointer-to-simple-variable type, and @x must be assignable
* to the result of dereferencing @ptr.
*
* Returns zero on success, or -EFAULT on error.
*/
#define put_user(x, ptr) \
({ \
__typeof__(*(ptr)) __user *__p = (ptr); \
might_fault(); \
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 05:57:57 +03:00
access_ok(__p, sizeof(*__p)) ? \
__put_user((x), __p) : \
-EFAULT; \
})
unsigned long __must_check __asm_copy_to_user(void __user *to,
const void *from, unsigned long n);
unsigned long __must_check __asm_copy_from_user(void *to,
const void __user *from, unsigned long n);
static inline unsigned long
raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
return __asm_copy_from_user(to, from, n);
}
static inline unsigned long
raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
return __asm_copy_to_user(to, from, n);
}
extern long strncpy_from_user(char *dest, const char __user *src, long count);
extern long __must_check strnlen_user(const char __user *str, long n);
extern
unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
static inline
unsigned long __must_check clear_user(void __user *to, unsigned long n)
{
might_fault();
Remove 'type' argument from access_ok() function Nobody has actually used the type (VERIFY_READ vs VERIFY_WRITE) argument of the user address range verification function since we got rid of the old racy i386-only code to walk page tables by hand. It existed because the original 80386 would not honor the write protect bit when in kernel mode, so you had to do COW by hand before doing any user access. But we haven't supported that in a long time, and these days the 'type' argument is a purely historical artifact. A discussion about extending 'user_access_begin()' to do the range checking resulted this patch, because there is no way we're going to move the old VERIFY_xyz interface to that model. And it's best done at the end of the merge window when I've done most of my merges, so let's just get this done once and for all. This patch was mostly done with a sed-script, with manual fix-ups for the cases that weren't of the trivial 'access_ok(VERIFY_xyz' form. There were a couple of notable cases: - csky still had the old "verify_area()" name as an alias. - the iter_iov code had magical hardcoded knowledge of the actual values of VERIFY_{READ,WRITE} (not that they mattered, since nothing really used it) - microblaze used the type argument for a debug printout but other than those oddities this should be a total no-op patch. I tried to fix up all architectures, did fairly extensive grepping for access_ok() uses, and the changes are trivial, but I may have missed something. Any missed conversion should be trivially fixable, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 05:57:57 +03:00
return access_ok(to, n) ?
__clear_user(to, n) : n;
}
#define HAVE_GET_KERNEL_NOFAULT
#define __get_kernel_nofault(dst, src, type, err_label) \
do { \
long __kr_err; \
\
__get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \
if (unlikely(__kr_err)) \
goto err_label; \
} while (0)
#define __put_kernel_nofault(dst, src, type, err_label) \
do { \
long __kr_err; \
\
__put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \
if (unlikely(__kr_err)) \
goto err_label; \
} while (0)
#else /* CONFIG_MMU */
#include <asm-generic/uaccess.h>
#endif /* CONFIG_MMU */
#endif /* _ASM_RISCV_UACCESS_H */