kernel_optimize_test/mm/maccess.c

279 lines
7.9 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Access kernel memory without faulting.
*/
#include <linux/export.h>
#include <linux/mm.h>
#include <linux/uaccess.h>
static __always_inline long
probe_read_common(void *dst, const void __user *src, size_t size)
{
long ret;
pagefault_disable();
ret = __copy_from_user_inatomic(dst, src, size);
pagefault_enable();
return ret ? -EFAULT : 0;
}
static __always_inline long
probe_write_common(void __user *dst, const void *src, size_t size)
{
long ret;
pagefault_disable();
ret = __copy_to_user_inatomic(dst, src, size);
pagefault_enable();
return ret ? -EFAULT : 0;
}
/**
* probe_kernel_read(): safely attempt to read from a kernel-space location
* @dst: pointer to the buffer that shall take the data
* @src: address to read from
* @size: size of the data chunk
*
* Safely read from address @src to the buffer at @dst. If a kernel fault
* happens, handle that and return -EFAULT.
*
* We ensure that the copy_from_user is executed in atomic context so that
* do_page_fault() doesn't attempt to take mmap_sem. This makes
* probe_kernel_read() suitable for use within regions where the caller
* already holds mmap_sem, or other locks which nest inside mmap_sem.
uaccess: Add strict non-pagefault kernel-space read function Add two new probe_kernel_read_strict() and strncpy_from_unsafe_strict() helpers which by default alias to the __probe_kernel_read() and the __strncpy_from_unsafe(), respectively, but can be overridden by archs which have non-overlapping address ranges for kernel space and user space in order to bail out with -EFAULT when attempting to probe user memory including non-canonical user access addresses [0]: 4-level page tables: user-space mem: 0x0000000000000000 - 0x00007fffffffffff non-canonical: 0x0000800000000000 - 0xffff7fffffffffff 5-level page tables: user-space mem: 0x0000000000000000 - 0x00ffffffffffffff non-canonical: 0x0100000000000000 - 0xfeffffffffffffff The idea is that these helpers are complementary to the probe_user_read() and strncpy_from_unsafe_user() which probe user-only memory. Both added helpers here do the same, but for kernel-only addresses. Both set of helpers are going to be used for BPF tracing. They also explicitly avoid throwing the splat for non-canonical user addresses from 00c42373d397 ("x86-64: add warning for non-canonical user access address dereferences"). For compat, the current probe_kernel_read() and strncpy_from_unsafe() are left as-is. [0] Documentation/x86/x86_64/mm.txt Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: x86@kernel.org Link: https://lore.kernel.org/bpf/eefeefd769aa5a013531f491a71f0936779e916b.1572649915.git.daniel@iogearbox.net
2019-11-02 07:17:57 +08:00
*
* probe_kernel_read_strict() is the same as probe_kernel_read() except for
* the case where architectures have non-overlapping user and kernel address
* ranges: probe_kernel_read_strict() will additionally return -EFAULT for
* probing memory on a user address range where probe_user_read() is supposed
* to be used instead.
*/
long __weak probe_kernel_read(void *dst, const void *src, size_t size)
__attribute__((alias("__probe_kernel_read")));
uaccess: Add strict non-pagefault kernel-space read function Add two new probe_kernel_read_strict() and strncpy_from_unsafe_strict() helpers which by default alias to the __probe_kernel_read() and the __strncpy_from_unsafe(), respectively, but can be overridden by archs which have non-overlapping address ranges for kernel space and user space in order to bail out with -EFAULT when attempting to probe user memory including non-canonical user access addresses [0]: 4-level page tables: user-space mem: 0x0000000000000000 - 0x00007fffffffffff non-canonical: 0x0000800000000000 - 0xffff7fffffffffff 5-level page tables: user-space mem: 0x0000000000000000 - 0x00ffffffffffffff non-canonical: 0x0100000000000000 - 0xfeffffffffffffff The idea is that these helpers are complementary to the probe_user_read() and strncpy_from_unsafe_user() which probe user-only memory. Both added helpers here do the same, but for kernel-only addresses. Both set of helpers are going to be used for BPF tracing. They also explicitly avoid throwing the splat for non-canonical user addresses from 00c42373d397 ("x86-64: add warning for non-canonical user access address dereferences"). For compat, the current probe_kernel_read() and strncpy_from_unsafe() are left as-is. [0] Documentation/x86/x86_64/mm.txt Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: x86@kernel.org Link: https://lore.kernel.org/bpf/eefeefd769aa5a013531f491a71f0936779e916b.1572649915.git.daniel@iogearbox.net
2019-11-02 07:17:57 +08:00
long __weak probe_kernel_read_strict(void *dst, const void *src, size_t size)
__attribute__((alias("__probe_kernel_read")));
long __probe_kernel_read(void *dst, const void *src, size_t size)
{
long ret;
mm_segment_t old_fs = get_fs();
set_fs(KERNEL_DS);
ret = probe_read_common(dst, (__force const void __user *)src, size);
set_fs(old_fs);
return ret;
}
EXPORT_SYMBOL_GPL(probe_kernel_read);
/**
* probe_user_read(): safely attempt to read from a user-space location
* @dst: pointer to the buffer that shall take the data
* @src: address to read from. This must be a user address.
* @size: size of the data chunk
*
* Safely read from user address @src to the buffer at @dst. If a kernel fault
* happens, handle that and return -EFAULT.
*/
long __weak probe_user_read(void *dst, const void __user *src, size_t size)
__attribute__((alias("__probe_user_read")));
long __probe_user_read(void *dst, const void __user *src, size_t size)
{
long ret = -EFAULT;
mm_segment_t old_fs = get_fs();
set_fs(USER_DS);
if (access_ok(src, size))
ret = probe_read_common(dst, src, size);
set_fs(old_fs);
return ret;
}
EXPORT_SYMBOL_GPL(probe_user_read);
/**
* probe_kernel_write(): safely attempt to write to a location
* @dst: address to write to
* @src: pointer to the data that shall be written
* @size: size of the data chunk
*
* Safely write to address @dst from the buffer at @src. If a kernel fault
* happens, handle that and return -EFAULT.
*/
long __weak probe_kernel_write(void *dst, const void *src, size_t size)
__attribute__((alias("__probe_kernel_write")));
long __probe_kernel_write(void *dst, const void *src, size_t size)
{
long ret;
mm_segment_t old_fs = get_fs();
set_fs(KERNEL_DS);
ret = probe_write_common((__force void __user *)dst, src, size);
set_fs(old_fs);
return ret;
}
EXPORT_SYMBOL_GPL(probe_kernel_write);
/**
* probe_user_write(): safely attempt to write to a user-space location
* @dst: address to write to
* @src: pointer to the data that shall be written
* @size: size of the data chunk
*
* Safely write to address @dst from the buffer at @src. If a kernel fault
* happens, handle that and return -EFAULT.
*/
long __weak probe_user_write(void __user *dst, const void *src, size_t size)
__attribute__((alias("__probe_user_write")));
long __probe_user_write(void __user *dst, const void *src, size_t size)
{
long ret = -EFAULT;
mm_segment_t old_fs = get_fs();
set_fs(USER_DS);
if (access_ok(dst, size))
ret = probe_write_common(dst, src, size);
set_fs(old_fs);
return ret;
}
EXPORT_SYMBOL_GPL(probe_user_write);
/**
* strncpy_from_unsafe: - Copy a NUL terminated string from unsafe address.
* @dst: Destination address, in kernel space. This buffer must be at
* least @count bytes long.
* @unsafe_addr: Unsafe address.
* @count: Maximum number of bytes to copy, including the trailing NUL.
*
* Copies a NUL-terminated string from unsafe address to kernel buffer.
*
* On success, returns the length of the string INCLUDING the trailing NUL.
*
* If access fails, returns -EFAULT (some data may have been copied
* and the trailing NUL added).
*
* If @count is smaller than the length of the string, copies @count-1 bytes,
* sets the last byte of @dst buffer to NUL and returns @count.
uaccess: Add strict non-pagefault kernel-space read function Add two new probe_kernel_read_strict() and strncpy_from_unsafe_strict() helpers which by default alias to the __probe_kernel_read() and the __strncpy_from_unsafe(), respectively, but can be overridden by archs which have non-overlapping address ranges for kernel space and user space in order to bail out with -EFAULT when attempting to probe user memory including non-canonical user access addresses [0]: 4-level page tables: user-space mem: 0x0000000000000000 - 0x00007fffffffffff non-canonical: 0x0000800000000000 - 0xffff7fffffffffff 5-level page tables: user-space mem: 0x0000000000000000 - 0x00ffffffffffffff non-canonical: 0x0100000000000000 - 0xfeffffffffffffff The idea is that these helpers are complementary to the probe_user_read() and strncpy_from_unsafe_user() which probe user-only memory. Both added helpers here do the same, but for kernel-only addresses. Both set of helpers are going to be used for BPF tracing. They also explicitly avoid throwing the splat for non-canonical user addresses from 00c42373d397 ("x86-64: add warning for non-canonical user access address dereferences"). For compat, the current probe_kernel_read() and strncpy_from_unsafe() are left as-is. [0] Documentation/x86/x86_64/mm.txt Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: x86@kernel.org Link: https://lore.kernel.org/bpf/eefeefd769aa5a013531f491a71f0936779e916b.1572649915.git.daniel@iogearbox.net
2019-11-02 07:17:57 +08:00
*
* strncpy_from_unsafe_strict() is the same as strncpy_from_unsafe() except
* for the case where architectures have non-overlapping user and kernel address
* ranges: strncpy_from_unsafe_strict() will additionally return -EFAULT for
* probing memory on a user address range where strncpy_from_unsafe_user() is
* supposed to be used instead.
*/
uaccess: Add strict non-pagefault kernel-space read function Add two new probe_kernel_read_strict() and strncpy_from_unsafe_strict() helpers which by default alias to the __probe_kernel_read() and the __strncpy_from_unsafe(), respectively, but can be overridden by archs which have non-overlapping address ranges for kernel space and user space in order to bail out with -EFAULT when attempting to probe user memory including non-canonical user access addresses [0]: 4-level page tables: user-space mem: 0x0000000000000000 - 0x00007fffffffffff non-canonical: 0x0000800000000000 - 0xffff7fffffffffff 5-level page tables: user-space mem: 0x0000000000000000 - 0x00ffffffffffffff non-canonical: 0x0100000000000000 - 0xfeffffffffffffff The idea is that these helpers are complementary to the probe_user_read() and strncpy_from_unsafe_user() which probe user-only memory. Both added helpers here do the same, but for kernel-only addresses. Both set of helpers are going to be used for BPF tracing. They also explicitly avoid throwing the splat for non-canonical user addresses from 00c42373d397 ("x86-64: add warning for non-canonical user access address dereferences"). For compat, the current probe_kernel_read() and strncpy_from_unsafe() are left as-is. [0] Documentation/x86/x86_64/mm.txt Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: x86@kernel.org Link: https://lore.kernel.org/bpf/eefeefd769aa5a013531f491a71f0936779e916b.1572649915.git.daniel@iogearbox.net
2019-11-02 07:17:57 +08:00
long __weak strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
__attribute__((alias("__strncpy_from_unsafe")));
long __weak strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr,
long count)
__attribute__((alias("__strncpy_from_unsafe")));
long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)
{
mm_segment_t old_fs = get_fs();
const void *src = unsafe_addr;
long ret;
if (unlikely(count <= 0))
return 0;
set_fs(KERNEL_DS);
pagefault_disable();
do {
ret = __get_user(*dst++, (const char __user __force *)src++);
} while (dst[-1] && ret == 0 && src - unsafe_addr < count);
dst[-1] = '\0';
pagefault_enable();
set_fs(old_fs);
return ret ? -EFAULT : src - unsafe_addr;
}
/**
* strncpy_from_unsafe_user: - Copy a NUL terminated string from unsafe user
* address.
* @dst: Destination address, in kernel space. This buffer must be at
* least @count bytes long.
* @unsafe_addr: Unsafe user address.
* @count: Maximum number of bytes to copy, including the trailing NUL.
*
* Copies a NUL-terminated string from unsafe user address to kernel buffer.
*
* On success, returns the length of the string INCLUDING the trailing NUL.
*
* If access fails, returns -EFAULT (some data may have been copied
* and the trailing NUL added).
*
* If @count is smaller than the length of the string, copies @count-1 bytes,
* sets the last byte of @dst buffer to NUL and returns @count.
*/
long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr,
long count)
{
mm_segment_t old_fs = get_fs();
long ret;
if (unlikely(count <= 0))
return 0;
set_fs(USER_DS);
pagefault_disable();
ret = strncpy_from_user(dst, unsafe_addr, count);
pagefault_enable();
set_fs(old_fs);
if (ret >= count) {
ret = count;
dst[ret - 1] = '\0';
} else if (ret > 0) {
ret++;
}
return ret;
}
/**
* strnlen_unsafe_user: - Get the size of a user string INCLUDING final NUL.
* @unsafe_addr: The string to measure.
* @count: Maximum count (including NUL)
*
* Get the size of a NUL-terminated string in user space without pagefault.
*
* Returns the size of the string INCLUDING the terminating NUL.
*
* If the string is too long, returns a number larger than @count. User
* has to check the return value against "> count".
* On exception (or invalid count), returns 0.
*
* Unlike strnlen_user, this can be used from IRQ handler etc. because
* it disables pagefaults.
*/
long strnlen_unsafe_user(const void __user *unsafe_addr, long count)
{
mm_segment_t old_fs = get_fs();
int ret;
set_fs(USER_DS);
pagefault_disable();
ret = strnlen_user(unsafe_addr, count);
pagefault_enable();
set_fs(old_fs);
return ret;
}