clean up and streamline probe_kernel_* and friends v3
Subsystems (37)
Hi all,
this series start cleaning up the safe kernel and user memory probing helpers in mm/maccess.c, and then allows architectures to implement the kernel probing without overriding the address space limit and temporarily allowing access to user memory. It then switches x86 over to this new mechanism by reusing the unsafe_* uaccess logic.
This version also switches to the saner copy_{from,to}_kernel_nofault naming suggested by Linus.
I kept the x86 helprs as-is without calling unsage_{get,put}_user as that avoids a number of hard to trace casts, and it will still work with the asm-goto based version easily.
Changes since v2:
- rebased on 5.7-rc6 with the bpf trace format string changes
- rename arch_kernel_read to __get_kernel_nofault and arch_kernel_write to __put_kernel_nofault
- clean up the tracers to only allowd "mixed" reads when the kernel has non-overlapping address spaces
_______________________________________________
linux-um mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 1/20 maccess: unexport probe_kernel_write and probe_user_write
These two functions are not used by any modular code.
--- mm/maccess.c | 2 -- 1 file changed, 2 deletions(-)
mm/maccess.c +0 -2
@@ -121,7 +121,6 @@ long __probe_kernel_write(void *dst, const void *src, size_t size)return ret; } -EXPORT_SYMBOL_GPL (probe_kernel_write);/** * probe_user_write(): safely attempt to write to a user-space location
@@ -148,7 +147,6 @@ long __probe_user_write(void __user *dst, const void *src, size_t size)return ret; } -EXPORT_SYMBOL_GPL (probe_user_write);/** * strncpy_from_unsafe: - Copy a NUL terminated string from unsafe address.
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 2/20 maccess: remove various unused weak aliases
In reply to Christoph Hellwigmaccess tends to define lots of underscore prefixed symbols that then have other weak aliases. But except for two cases they are never actually used, so remove them.
--- include/linux/uaccess.h | 3 --- mm/maccess.c | 19 +++---------------- 2 files changed, 3 insertions(+), 19 deletions(-)
include/linux/uaccess.h +0 -3
@@ -324,7 +324,6 @@ extern long __probe_kernel_read(void *dst, const void *src, size_t size);* happens, handle that and return -EFAULT. */ extern long probe_user_read (void *dst,const void __user *src,size_t size); -extern long __probe_user_read (void *dst,const void __user *src,size_t size);/* * probe_kernel_write(): safely attempt to write to a location
@@ -336,7 +335,6 @@ extern long __probe_user_read(void *dst, const void __user *src, size_t size);* happens, handle that and return -EFAULT. */ extern long notrace probe_kernel_write (void *dst,const void *src,size_t size); -extern long notrace __probe_kernel_write (void *dst,const void *src,size_t size);/* * probe_user_write(): safely attempt to write to a location in user space
@@ -348,7 +346,6 @@ extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size* happens, handle that and return -EFAULT. */ extern long notrace probe_user_write (void __user *dst,const void *src,size_t size); -extern long notrace __probe_user_write (void __user *dst,const void *src,size_t size);extern long strncpy_from_unsafe (char *dst,const void *unsafe_addr,long count); extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr,
mm/maccess.c +3 -16
@@ -79,11 +79,7 @@ EXPORT_SYMBOL_GPL(probe_kernel_read);* 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 probe_user_read (void *dst,const void __user *src,size_t size) {long ret = -EFAULT ;mm_segment_t old_fs =get_fs ();
@@ -106,11 +102,7 @@ EXPORT_SYMBOL_GPL(probe_user_read);* 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 probe_kernel_write (void *dst,const void *src,size_t size) {long ret;mm_segment_t old_fs =get_fs ();
@@ -131,11 +123,7 @@ long __probe_kernel_write(void *dst, const void *src, size_t size)* 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 probe_user_write (void __user *dst,const void *src,size_t size) {long ret = -EFAULT ;mm_segment_t old_fs =get_fs ();
@@ -171,7 +159,6 @@ long __probe_user_write(void __user *dst, const void *src, size_t size)* probing memory on a user address range where strncpy_from_unsafe_user() is * supposed to be used instead. */ -long __weak strncpy_from_unsafe (char *dst,const void *unsafe_addr,long count) __attribute__((alias ("__strncpy_from_unsafe" )));
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 3/20 maccess: remove duplicate kerneldoc comments
In reply to Christoph HellwigMany of the maccess routines have a copy of the kerneldoc comment in the header. Remove it as it is not useful and will get out of sync sooner or later.
--- include/linux/uaccess.h | 38 -------------------------------------- 1 file changed, 38 deletions(-)
include/linux/uaccess.h +0 -38
@@ -301,50 +301,12 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src,return 0 ; } -/* -* probe_kernel_read(): safely attempt to read from a 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. -*/ extern long probe_kernel_read (void *dst,const void *src,size_t size);extern long probe_kernel_read_strict (void *dst,const void *src,size_t size);extern long __probe_kernel_read (void *dst,const void *src,size_t size); - -/* -* probe_user_read(): safely attempt to read from a location in user space -* @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. -*/ extern long probe_user_read (void *dst,const void __user *src,size_t size); -/* -* 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. -*/ extern long notrace probe_kernel_write (void *dst,const void *src,size_t size); - -/* -* probe_user_write(): safely attempt to write to a location in user space -* @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. -*/ extern long notrace probe_user_write (void __user *dst,const void *src,size_t size);extern long strncpy_from_unsafe (char *dst,const void *unsafe_addr,long count);
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 4/20 maccess: clarify kerneldoc comments
In reply to Christoph HellwigAdd proper kerneldoc comments for probe_kernel_read_strict and probe_kernel_read strncpy_from_unsafe_strict and explain the different versus the non-strict version.
--- mm/maccess.c | 61 ++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 43 insertions(+), 18 deletions(-)
mm/maccess.c +43 -18
@@ -31,29 +31,35 @@ probe_write_common(void __user *dst, const void *src, size_t size) }/** -* probe_kernel_read(): safely attempt to read from a kernel-space location +* probe_kernel_read(): safely attempt to read from any 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. +* Same as probe_kernel_read_strict() except that for architectures with +* not fully separated user and kernel address spaces this function also works +* for user address tanges. +* +* DO NOT USE THIS FUNCTION - it is broken on architectures with entirely +* separate kernel and user address spaces, and also a bad idea otherwise. +*/ +long __weak probe_kernel_read (void *dst,const void *src,size_t size) + __attribute__((alias ("__probe_kernel_read" ))); + +/** +* probe_kernel_read_strict(): safely attempt to read from kernel-space +* @dst: pointer to the buffer that shall take the data +* @src: address to read from +* @size: size of the data chunk +* +* Safely read from kernel 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. -* -* 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" ))); -long __weak probe_kernel_read_strict (void *dst,const void *src,size_t size) __attribute__((alias ("__probe_kernel_read" )));
@@ -153,15 +159,34 @@ long probe_user_write(void __user *dst, const void *src, size_t size)* 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. * -* 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. +* Same as strncpy_from_unsafe_strict() except that for architectures with +* not fully separated user and kernel address spaces this function also works +* for user address tanges. +* +* DO NOT USE THIS FUNCTION - it is broken on architectures with entirely +* separate kernel and user address spaces, and also a bad idea otherwise. */ long __weak strncpy_from_unsafe (char *dst,const void *unsafe_addr,long count) __attribute__((alias ("__strncpy_from_unsafe" ))); +/** +* strncpy_from_unsafe_strict: - 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. +*/ long __weak strncpy_from_unsafe_strict (char *dst,const void *unsafe_addr,long count) __attribute__((alias ("__strncpy_from_unsafe" )));
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 5/20 maccess: update the top of file comment
In reply to Christoph HellwigThis file now also contains several helpers for accessing user memory.
--- mm/maccess.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
mm/maccess.c +1 -1
@@ -1,6 +1,6 @@// SPDX-License-Identifier: GPL-2.0-only /* -* Access kernel memory without faulting. +* Access kernel or user memory without faulting. */ #include <linux/export.h> #include <linux/mm.h>
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 6/20 maccess: rename strncpy_from_unsafe_user to strncpy_from_user_nofault
In reply to Christoph HellwigThis matches the naming of strncpy_from_user, and also makes it more clear what the function is supposed to do.
--- include/linux/uaccess.h | 4 ++-- kernel/trace/bpf_trace.c | 4 ++-- kernel/trace/trace_kprobe.c | 2 +- mm/maccess.c | 4 ++-- 4 files changed, 7 insertions(+), 7 deletions(-)
include/linux/uaccess.h +2 -2
@@ -313,8 +313,8 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);extern long strncpy_from_unsafe_strict (char *dst,const void *unsafe_addr,long count);extern long __strncpy_from_unsafe (char *dst,const void *unsafe_addr,long count); -extern long strncpy_from_unsafe_user (char *dst,const void __user *unsafe_addr, -long count); +long strncpy_from_user_nofault (char *dst,const void __user *unsafe_addr, +long count);extern long strnlen_unsafe_user (const void __user *unsafe_addr,long count);/**
kernel/trace/bpf_trace.c +2 -2
@@ -159,7 +159,7 @@ static const struct bpf_func_proto bpf_probe_read_user_proto = { BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size, const void __user *, unsafe_ptr) { -int ret =strncpy_from_unsafe_user (dst, unsafe_ptr, size); +int ret =strncpy_from_user_nofault (dst, unsafe_ptr, size);if (unlikely (ret <0 ))memset (dst,0 , size);
@@ -416,7 +416,7 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, sizeof(buf));break ;case 'u' : -strncpy_from_unsafe_user (buf, +strncpy_from_user_nofault (buf, (__force void __user *)unsafe_ptr,sizeof (buf));break ;
kernel/trace/trace_kprobe.c +1 -1
@@ -1268,7 +1268,7 @@ fetch_store_string_user(unsigned long addr, void *dest, void *base) __dest =get_loc_data (dest, base); - ret =strncpy_from_unsafe_user (__dest, uaddr, maxlen); + ret =strncpy_from_user_nofault (__dest, uaddr, maxlen);if (ret >=0 ) *(u32 *)dest =make_data_loc (ret, __dest - base);
mm/maccess.c +2 -2
@@ -215,7 +215,7 @@ long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count) }/** -* strncpy_from_unsafe_user: - Copy a NUL terminated string from unsafe user +* strncpy_from_user_nofault: - Copy a NUL terminated string from unsafe user * address. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long.
@@ -232,7 +232,7 @@ long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)* 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 strncpy_from_user_nofault (char *dst,const void __user *unsafe_addr,long count) {mm_segment_t old_fs =get_fs ();
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 7/20 maccess: rename strncpy_from_unsafe_strict to strncpy_from_kernel_nofault
In reply to Christoph HellwigThis matches the naming of strncpy_from_user_nofault, and also makes it more clear what the function is supposed to do.
--- arch/x86/mm/maccess.c | 2 +- include/linux/uaccess.h | 4 ++-- kernel/trace/bpf_trace.c | 4 ++-- mm/maccess.c | 6 +++--- 4 files changed, 8 insertions(+), 8 deletions(-)
arch/x86/mm/maccess.c +1 -1
@@ -34,7 +34,7 @@ long probe_kernel_read_strict(void *dst, const void *src, size_t size)return __probe_kernel_read (dst, src, size); } -long strncpy_from_unsafe_strict (char *dst,const void *unsafe_addr,long count) +long strncpy_from_kernel_nofault (char *dst,const void *unsafe_addr,long count) {if (unlikely (invalid_probe_range ((unsigned long )unsafe_addr)))return -EFAULT ;
include/linux/uaccess.h +2 -2
@@ -310,8 +310,8 @@ extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);extern long notrace probe_user_write (void __user *dst,const void *src,size_t size);extern long strncpy_from_unsafe (char *dst,const void *unsafe_addr,long count); -extern long strncpy_from_unsafe_strict (char *dst,const void *unsafe_addr, -long count); +long strncpy_from_kernel_nofault (char *dst,const void *unsafe_addr, +long count);extern long __strncpy_from_unsafe (char *dst,const void *unsafe_addr,long count);long strncpy_from_user_nofault (char *dst,const void __user *unsafe_addr,long count);
kernel/trace/bpf_trace.c +2 -2
@@ -240,7 +240,7 @@ bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr,* is returned that can be used for bpf_perf_event_output() et al. */ ret = compat ?strncpy_from_unsafe (dst, unsafe_ptr, size) : -strncpy_from_unsafe_strict (dst, unsafe_ptr, size); +strncpy_from_kernel_nofault (dst, unsafe_ptr, size);if (unlikely (ret <0 )) out:memset (dst,0 , size);
@@ -412,7 +412,7 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,break ;#endif case 'k' : -strncpy_from_unsafe_strict (buf, unsafe_ptr, +strncpy_from_kernel_nofault (buf, unsafe_ptr,sizeof (buf));break ;case 'u' :
mm/maccess.c +3 -3
@@ -159,7 +159,7 @@ long probe_user_write(void __user *dst, const void *src, size_t size)* 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. * -* Same as strncpy_from_unsafe_strict() except that for architectures with +* Same as strncpy_from_kernel_nofault() except that for architectures with * not fully separated user and kernel address spaces this function also works * for user address tanges. *
@@ -170,7 +170,7 @@ long __weak strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count) __attribute__((alias("__strncpy_from_unsafe")));/** -* strncpy_from_unsafe_strict: - Copy a NUL terminated string from unsafe +* strncpy_from_kernel_nofault: - Copy a NUL terminated string from unsafe * address. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long.
@@ -187,7 +187,7 @@ long __weak strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)* 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 __weak strncpy_from_unsafe_strict (char *dst,const void *unsafe_addr, +long __weak strncpy_from_kernel_nofault (char *dst,const void *unsafe_addr,long count) __attribute__((alias ("__strncpy_from_unsafe" )));
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 8/20 maccess: rename strnlen_unsafe_user to strnlen_user_nofault
In reply to Christoph HellwigThis matches the naming of strnlen_user, and also makes it more clear what the function is supposed to do.
--- include/linux/uaccess.h | 2 +- kernel/trace/trace_kprobe.c | 2 +- mm/maccess.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-)
include/linux/uaccess.h +1 -1
@@ -315,7 +315,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr,extern long __strncpy_from_unsafe (char *dst,const void *unsafe_addr,long count);long strncpy_from_user_nofault (char *dst,const void __user *unsafe_addr,long count); -extern long strnlen_unsafe_user (const void __user *unsafe_addr,long count); +long strnlen_user_nofault (const void __user *unsafe_addr,long count);/** * probe_kernel_address(): safely attempt to read from a location
kernel/trace/trace_kprobe.c +1 -1
@@ -1221,7 +1221,7 @@ fetch_store_strlen_user(unsigned long addr) {const void __user *uaddr = (__force const void __user *)addr; -return strnlen_unsafe_user (uaddr,MAX_STRING_SIZE ); +return strnlen_user_nofault (uaddr,MAX_STRING_SIZE ); }/*
mm/maccess.c +2 -2
@@ -258,7 +258,7 @@ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, }/** -* strnlen_unsafe_user: - Get the size of a user string INCLUDING final NUL. +* strnlen_user_nofault: - Get the size of a user string INCLUDING final NUL. * @unsafe_addr: The string to measure. * @count: Maximum count (including NUL) *
@@ -273,7 +273,7 @@ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr,* 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) +long strnlen_user_nofault (const void __user *unsafe_addr,long count) {mm_segment_t old_fs =get_fs ();int ret;
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 9/20 maccess: remove probe_read_common and probe_write_common
In reply to Christoph HellwigEach of the helpers has just two callers, which also different in dealing with kernel or userspace pointers. Just open code the logic in the callers.
--- mm/maccess.c | 63 ++++++++++++++++++++++++---------------------------- 1 file changed, 29 insertions(+), 34 deletions(-)
mm/maccess.c +29 -34
@@ -6,30 +6,6 @@#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 any location * @dst: pointer to the buffer that shall take the data
@@ -69,10 +45,15 @@ long __probe_kernel_read(void *dst, const void *src, size_t size)mm_segment_t old_fs =get_fs ();set_fs (KERNEL_DS ); - ret =probe_read_common (dst, (__force const void __user *)src, size); +pagefault_disable (); + ret =__copy_from_user_inatomic (dst, (__force const void __user *)src, + size); +pagefault_enable ();set_fs (old_fs); -return ret; +if (ret) +return -EFAULT ; +return 0 ; }EXPORT_SYMBOL_GPL (probe_kernel_read);
@@ -91,11 +72,16 @@ long probe_user_read(void *dst, const void __user *src, size_t size)mm_segment_t old_fs =get_fs ();set_fs (USER_DS ); -if (access_ok (src, size)) - ret =probe_read_common (dst, src, size); +if (access_ok (src, size)) { +pagefault_disable (); + ret =__copy_from_user_inatomic (dst, src, size); +pagefault_enable (); + }set_fs (old_fs); -return ret; +if (ret) +return -EFAULT ; +return 0 ; }EXPORT_SYMBOL_GPL (probe_user_read);
@@ -114,10 +100,14 @@ long probe_kernel_write(void *dst, const void *src, size_t size)mm_segment_t old_fs =get_fs ();set_fs (KERNEL_DS ); - ret =probe_write_common ((__force void __user *)dst, src, size); +pagefault_disable (); + ret =__copy_to_user_inatomic ((__force void __user *)dst, src, size); +pagefault_enable ();set_fs (old_fs); -return ret; +if (ret) +return -EFAULT ; +return 0 ; }/**
@@ -135,11 +125,16 @@ long probe_user_write(void __user *dst, const void *src, size_t size)mm_segment_t old_fs =get_fs ();set_fs (USER_DS ); -if (access_ok (dst, size)) - ret =probe_write_common (dst, src, size); +if (access_ok (dst, size)) { +pagefault_disable (); + ret =__copy_to_user_inatomic (dst, src, size); +pagefault_enable (); + }set_fs (old_fs); -return ret; +if (ret) +return -EFAULT ; +return 0 ; }/**
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 10/20 maccess: unify the probe kernel arch hooks
In reply to Christoph HellwigCurrently architectures have to override every routine that probes kernel memory, which includes a pure read and strcpy, both in strict and not strict variants. Just provide a single arch hooks instead to make sure all architectures cover all the cases.
--- arch/parisc/lib/memcpy.c | 13 ++++------- arch/um/kernel/maccess.c | 11 ++++----- arch/x86/mm/maccess.c | 18 ++++----------- include/linux/uaccess.h | 6 +++-- mm/maccess.c | 49 ++++++++++++++++++++++++++++++---------- 5 files changed, 56 insertions(+), 41 deletions(-)
arch/parisc/lib/memcpy.c +5 -8
@@ -57,14 +57,11 @@ void * memcpy(void * dst,const void *src, size_t count)EXPORT_SYMBOL (raw_copy_in_user);EXPORT_SYMBOL (memcpy); -long probe_kernel_read (void *dst,const void *src,size_t size) +bool probe_kernel_read_allowed (void *dst,const void *unsafe_src,size_t size, +bool strict) { -unsigned long addr = (unsigned long )src; - -if (addr <PAGE_SIZE ) -return -EFAULT ; - +if ((unsigned long )unsafe_src <PAGE_SIZE ) +return false;/* check for I/O space F_EXTEND(0xfff00000) access as well? */ - -return __probe_kernel_read (dst, src, size); +return true; }
arch/um/kernel/maccess.c +5 -6
@@ -7,15 +7,14 @@#include <linux/kernel.h> #include <os.h> -long probe_kernel_read (void *dst,const void *src,size_t size) +bool probe_kernel_read_allowed (void *dst,const void *src,size_t size, +bool strict) {void *psrc = (void *)rounddown ((unsigned long )src,PAGE_SIZE );if ((unsigned long )src <PAGE_SIZE || size <=0 ) -return -EFAULT ; - +return false;if (os_mincore (psrc, size + src - psrc) <=0 ) -return -EFAULT ; - -return __probe_kernel_read (dst, src, size); +return false; +return true; }
arch/x86/mm/maccess.c +5 -13
@@ -26,18 +26,10 @@ static __always_inline bool invalid_probe_range(u64 vaddr) }#endif -long probe_kernel_read_strict (void *dst,const void *src,size_t size) +bool probe_kernel_read_allowed (void *dst,const void *unsafe_src,size_t size, +bool strict) { -if (unlikely (invalid_probe_range ((unsigned long )src))) -return -EFAULT ; - -return __probe_kernel_read (dst, src, size); -} - -long strncpy_from_kernel_nofault (char *dst,const void *unsafe_addr,long count) -{ -if (unlikely (invalid_probe_range ((unsigned long )unsafe_addr))) -return -EFAULT ; - -return __strncpy_from_unsafe (dst, unsafe_addr, count); +if (!strict) +return true; +return !invalid_probe_range ((unsigned long )unsafe_src); }
include/linux/uaccess.h +4 -2
@@ -301,9 +301,11 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src,return 0 ; } +bool probe_kernel_read_allowed (void *dst,const void *unsafe_src, +size_t size,bool strict); +extern long probe_kernel_read (void *dst,const void *src,size_t size);extern long probe_kernel_read_strict (void *dst,const void *src,size_t size); -extern long __probe_kernel_read (void *dst,const void *src,size_t size);extern long probe_user_read (void *dst,const void __user *src,size_t size);extern long notrace probe_kernel_write (void *dst,const void *src,size_t size);
@@ -312,7 +314,7 @@ extern long notrace probe_user_write(void __user *dst, const void *src, size_t sextern long strncpy_from_unsafe (char *dst,const void *unsafe_addr,long count);long strncpy_from_kernel_nofault (char *dst,const void *unsafe_addr,long count); -extern long __strncpy_from_unsafe (char *dst,const void *unsafe_addr,long count); +long strncpy_from_user_nofault (char *dst,const void __user *unsafe_addr,long count);long strnlen_user_nofault (const void __user *unsafe_addr,long count);
mm/maccess.c +37 -12
97 lines not on this page · raw message
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 11/20 bpf: factor out a bpf_trace_copy_string helper
In reply to Christoph HellwigSplit out a helper to do the fault free access to the string pointer to get it out of a crazy indentation level.
--- kernel/trace/bpf_trace.c | 42 +++++++++++++++++++++++----------------- 1 file changed, 24 insertions(+), 18 deletions(-)
kernel/trace/bpf_trace.c +24 -18
@@ -321,6 +321,28 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void)return &bpf_probe_write_user_proto; } +static void bpf_trace_copy_string (char *buf,void *unsafe_ptr,char fmt_ptype, +size_t bufsz) +{ +void __user *user_ptr = (__force void __user *)unsafe_ptr; + + buf[0 ] =0 ; + +switch (fmt_ptype) { +case 's' : +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE +strncpy_from_unsafe (buf, unsafe_ptr, bufsz); +break ; +#endif +case 'k' : +strncpy_from_kernel_nofault (buf, unsafe_ptr, bufsz); +break ; +case 'u' : +strncpy_from_user_nofault (buf, user_ptr, bufsz); +break ; + } +} +/* * Only limited trace_printk() conversion specifiers allowed: * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pks %pus %s
@@ -403,24 +425,8 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,break ; } - buf[0 ] =0 ; -switch (fmt_ptype) { -case 's' : -#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE -strncpy_from_unsafe (buf, unsafe_ptr, -sizeof (buf)); -break ; -#endif -case 'k' : -strncpy_from_kernel_nofault (buf, unsafe_ptr, -sizeof (buf)); -break ; -case 'u' : -strncpy_from_user_nofault (buf, - (__force void __user *)unsafe_ptr, -sizeof (buf)); -break ; - } +bpf_trace_copy_string (buf, unsafe_ptr, fmt_ptype, +sizeof (buf)); goto fmt_next; }
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
Re: [PATCH 11/20] bpf: factor out a bpf_trace_copy_string helper
kernel/trace/bpf_trace.c static const struct bpf_func_proto *bpf_get_probe_write_proto(void) · line 339
Quoted 10 lines · Christoph Hellwig
kernel/trace/bpf_trace.c +9
-0+switch (fmt_ptype) { +case 's' : +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE +strncpy_from_unsafe (buf, unsafe_ptr, bufsz); +break ; +#endif +case 'k' : +strncpy_from_kernel_nofault (buf, unsafe_ptr, bufsz); +break ;
That 's' case needs a "fallthrough;" for the overlapping case, methinks. Otherwise you'll get warnings.
Linus
Re: [PATCH 11/20] bpf: factor out a bpf_trace_copy_string helper
Quoted 14 lines · Linus Torvalds
kernel/trace/bpf_trace.c static const struct bpf_func_proto *bpf_get_probe_write_proto(void) · line 339
Quoted 10 lines · Christoph Hellwig
kernel/trace/bpf_trace.c +9
-0+switch (fmt_ptype) { +case 's' : +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE +strncpy_from_unsafe (buf, unsafe_ptr, bufsz); +break ; +#endif +case 'k' : +strncpy_from_kernel_nofault (buf, unsafe_ptr, bufsz); +break ;That 's' case needs a "fallthrough;" for the overlapping case, methinks. Otherwise you'll get warnings.
I don't think we need it as the case of
case 'a': case 'b': do_stuff(); break;
has always been fine even with the fallthough warnings. And the rest of the stuff gets removed by cpp..
Re: [PATCH 11/20] bpf: factor out a bpf_trace_copy_string helper
Quoted 10 lines · Christoph Hellwig
I don't think we need it as the case of
case 'a': case 'b': do_stuff(); break;has always been fine even with the fallthough warnings. And the rest of the stuff gets removed by cpp..
You're right. I read it as a fallthrough because as a human it looks like there's code in there between, but yeah, the compiler won't actually ever see it.
So scratch that objection.
Linus
PATCH 12/20 maccess: remove strncpy_from_unsafe
In reply to Christoph HellwigAll three callers really should try the explicit kernel or user copies. Switch them to try a user copy if the address is smaller than TASK_SIZE and the architecture has non-overlapping address ranges, or a kernel copy otherwise.
--- include/linux/uaccess.h | 1 - kernel/trace/bpf_trace.c | 23 +++++++++++++++------- kernel/trace/trace_kprobe.c | 8 +++++++- mm/maccess.c | 39 +------------------------------------ 4 files changed, 24 insertions(+), 47 deletions(-)
include/linux/uaccess.h +0 -1
@@ -311,7 +311,6 @@ extern long probe_user_read(void *dst, const void __user *src, size_t size);extern long notrace probe_kernel_write (void *dst,const void *src,size_t size);extern long notrace probe_user_write (void __user *dst,const void *src,size_t size); -extern long strncpy_from_unsafe (char *dst,const void *unsafe_addr,long count);long strncpy_from_kernel_nofault (char *dst,const void *unsafe_addr,long count);
kernel/trace/bpf_trace.c +16 -7
@@ -226,12 +226,14 @@ static __always_inline int bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr, const bool compat) { +const void __user *user_ptr = (__force const void __user *)unsafe_ptr;int ret =security_locked_down (LOCKDOWN_BPF_READ );if (unlikely (ret <0 )) - goto out; + goto fail; +/* -* The strncpy_from_unsafe_*() call will likely not fill the entire +* The strncpy_from_*_nofault() calls will likely not fill the entire * buffer, but that's okay in this circumstance as we're probing * arbitrary memory anyway similar to bpf_probe_read_*() and might * as well probe the stack. Thus, memory is explicitly cleared
@@ -239,11 +241,17 @@ bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr,* code altogether don't copy garbage; otherwise length of string * is returned that can be used for bpf_perf_event_output() et al. */ - ret = compat ?strncpy_from_unsafe (dst, unsafe_ptr, size) : -strncpy_from_kernel_nofault (dst, unsafe_ptr, size); +if (IS_ENABLED (CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE ) && + compat && (unsigned long )unsafe_ptr <TASK_SIZE ) + ret =strncpy_from_user_nofault (dst, user_ptr, size); +else + ret =strncpy_from_kernel_nofault (dst, unsafe_ptr, size);if (unlikely (ret <0 )) -out: -memset (dst,0 , size); + goto fail; + +return 0 ; +fail: +memset (dst,0 , size);return ret; }
@@ -331,7 +339,8 @@ static void bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,switch (fmt_ptype) {case 's' :#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE -strncpy_from_unsafe (buf, unsafe_ptr, bufsz); +if (strncpy_from_kernel_nofault (buf, unsafe_ptr, bufsz) ==0 ) +strncpy_from_user_nofault (buf, user_ptr, bufsz);break ;#endif case 'k' :
kernel/trace/trace_kprobe.c +7 -1
@@ -1244,7 +1244,13 @@ fetch_store_string(unsigned long addr, void *dest, void *base)* Try to get string again, since the string can be changed while * probing. */ - ret =strncpy_from_unsafe (__dest, (void *)addr, maxlen); +if (IS_ENABLED (CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE ) && + addr <TASK_SIZE ) { + ret =strncpy_from_user_nofault (__dest, (void __user *)addr, + maxlen); + }else { + ret =strncpy_from_kernel_nofault (__dest, (void *)addr, maxlen); + }if (ret >=0 ) *(u32 *)dest =make_data_loc (ret, __dest - base);
mm/maccess.c +1 -38
@@ -8,8 +8,6 @@static long __probe_kernel_read (void *dst,const void *src,size_t size,bool strict); -static long __strncpy_from_unsafe (char *dst,const void *unsafe_addr, -long count,bool strict);bool __weak probe_kernel_read_allowed (void *dst,const void *unsafe_src,size_t size,bool strict)
@@ -156,35 +154,6 @@ long probe_user_write(void __user *dst, const void *src, size_t size)return 0 ; } -/** -* 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. -* -* Same as strncpy_from_kernel_nofault() except that for architectures with -* not fully separated user and kernel address spaces this function also works -* for user address tanges. -* -* DO NOT USE THIS FUNCTION - it is broken on architectures with entirely -* separate kernel and user address spaces, and also a bad idea otherwise. -*/ -long strncpy_from_unsafe (char *dst,const void *unsafe_addr,long count) -{ -return __strncpy_from_unsafe (dst, unsafe_addr, count, false); -} -/** * strncpy_from_kernel_nofault: - Copy a NUL terminated string from unsafe * address.
@@ -204,12 +173,6 @@ long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count)* sets the last byte of @dst buffer to NUL and returns @count. */ long strncpy_from_kernel_nofault (char *dst,const void *unsafe_addr,long count) -{ -return __strncpy_from_unsafe (dst, unsafe_addr, count, true); -} - -static long __strncpy_from_unsafe (char *dst,const void *unsafe_addr, -long count,bool strict) {mm_segment_t old_fs =get_fs ();const void *src = unsafe_addr;
@@ -217,7 +180,7 @@ static long __strncpy_from_unsafe(char *dst, const void *unsafe_addr,if (unlikely (count <=0 ))return 0 ; -if (!probe_kernel_read_allowed (dst, unsafe_addr, count, strict)) +if (!probe_kernel_read_allowed (dst, unsafe_addr, count, true))return -EFAULT ;set_fs (KERNEL_DS );
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
Re: [PATCH 12/20] maccess: remove strncpy_from_unsafe
kernel/trace/bpf_trace.c bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr, · line 248
Quoted 6 lines · Christoph Hellwig
kernel/trace/bpf_trace.c +5
-0+if (IS_ENABLED (CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE ) && + compat && (unsigned long )unsafe_ptr <TASK_SIZE ) + ret =strncpy_from_user_nofault (dst, user_ptr, size); +else + ret =strncpy_from_kernel_nofault (dst, unsafe_ptr, size);
These conditionals are completely illegible.
That's true in the next patch too.
Stop using "IS_ENABLED(config)" to make very complex conditionals.
A clear #ifdef is much better if the alternative is a conditional that is completely impossible to actually understand and needs multiple lines to read.
If you made this a simple helper (called "bpf_strncpy_from_unsafe()" with that "compat" flag, perhaps?), it would be much more legible as
/*
* Big comment goes here about the compat behavior and
* non-overlapping address spaces and ambiguous pointers. */
static long bpf_strncpy_from_legacy(void *dest, const void*unsafe_ptr, long size, bool legacy)
{
#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
if (legacy && addr < TASK_SIZE)
return strncpy_from_user_nofault(dst, (const void __user
*) unsafe_ptr, size);
#endif
return strncpy_from_kernel_nofault(dst, unsafe_ptr, size);
}
and then you'd just use
if (bpf_strncpy_from_unsafe(dst, unsafe_ptr, size, compat) < 0)
memset(dst, 0, size);
and avoid any complicated conditionals, goto's, and make the code much easier to understand thanks to having a big comment about the legacy case.
In fact, separately I'd probably want that "compat" naming to be scrapped entirely in that file.
"compat" generally means something very specific and completely different in the kernel: it's the "I'm a 32-bit binary on a 64-bit kernel" compatibility case.
Here, it's literally "BPF legacy behavior", not that kind of "compat" thing.
But that renaming is separate, although I'd start the ball rolling with that "bpf_strncpy_from_legacy()" helper.
Linus
Re: [PATCH 12/20] maccess: remove strncpy_from_unsafe
Quoted 9 lines · Linus Torvalds
kernel/trace/bpf_trace.c bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr, · line 248
Quoted 6 lines · Christoph Hellwig
kernel/trace/bpf_trace.c +5
-0+if (IS_ENABLED (CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE ) && + compat && (unsigned long )unsafe_ptr <TASK_SIZE ) + ret =strncpy_from_user_nofault (dst, user_ptr, size); +else + ret =strncpy_from_kernel_nofault (dst, unsafe_ptr, size);These conditionals are completely illegible.
I had a lot of folks complaining about things like:
#ifdef CONFIG_FOO if (foo) do_stuff(); else #endif do_something_else();
which I personally don't mind at all, so I switched to this style.
Quoted 12 lines
static long bpf_strncpy_from_legacy(void *dest, const void
*unsafe_ptr, long size, bool legacy)
{
#ifdefCONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
if (legacy && addr <TASK_SIZE)
return strncpy_from_user_nofault(dst, (const void__user
*)unsafe_ptr, size);
#endifreturn strncpy_from_kernel_nofault(dst, unsafe_ptr, size);}
Quoted 8 lines
and then you'd just use
if (
bpf_strncpy_from_unsafe(dst, unsafe_ptr, size, compat)< 0)
memset(dst, 0, size);and avoid any complicated conditionals, goto's, and make the code much easier to understand thanks to having a big comment about the legacy case.
Sure.
Quoted 2 lines
In fact, separately I'd probably want that "compat" naming to be scrapped entirely in that file.
Not my choice.. Maybe Daniel has a recommendation of what to change there, but I'd love to not have to deal with that renaming as well in this series.
Re: [PATCH 12/20] maccess: remove strncpy_from_unsafe
Quoted 11 lines · Christoph Hellwig
I had a lot of folks complaining about things like:
#ifdef CONFIG_FOO if (foo) do_stuff(); else #endif do_something_else();which I personally don't mind at all, so I switched to this style.
Well, I don't particularly like that style either, it is _very_ easy to get wrong when you edit it later (and various indentation checkers tend to be very unhappy about it too).
But that's why I like trying to just make simple helper functions instead.
Yeah, it's often a few more lines of code (if only because of the extra function definition etc), but with good naming and sane arguments those few extra lines can also help make it much more understandable in the process, and it gives you a nice place to add commentary for the really odd cases (comments inside code that then does other things often make things just harder to see).
Linus
PATCH 13/20 maccess: always use strict semantics for probe_kernel_read
In reply to Christoph HellwigExcept for historical confusion in the kprobes/uprobes and bpf tracers, there is no good reason to ever allow user memory accesses from probe_kernel_read. Switch probe_kernel_read to only read from kernel memory itself, and try to read user memory in the tracers only if the address is smaller than TASK_SIZE, and the architecture has non-overlapping address ranges.
--- arch/parisc/lib/memcpy.c | 3 +-- arch/um/kernel/maccess.c | 3 +-- arch/x86/mm/maccess.c | 5 +---- include/linux/uaccess.h | 4 +--- kernel/trace/bpf_trace.c | 18 ++++++++++++----- kernel/trace/trace_kprobe.c | 14 ++++++++++++- mm/maccess.c | 39 ++++++------------------------------- 7 files changed, 36 insertions(+), 50 deletions(-)
arch/parisc/lib/memcpy.c +1 -2
@@ -57,8 +57,7 @@ void * memcpy(void * dst,const void *src, size_t count)EXPORT_SYMBOL (raw_copy_in_user);EXPORT_SYMBOL (memcpy); -bool probe_kernel_read_allowed (void *dst,const void *unsafe_src,size_t size, -bool strict) +bool probe_kernel_read_allowed (void *dst,const void *unsafe_src,size_t size) {if ((unsigned long )unsafe_src <PAGE_SIZE )return false;
arch/um/kernel/maccess.c +1 -2
@@ -7,8 +7,7 @@#include <linux/kernel.h> #include <os.h> -bool probe_kernel_read_allowed (void *dst,const void *src,size_t size, -bool strict) +bool probe_kernel_read_allowed (void *dst,const void *src,size_t size) {void *psrc = (void *)rounddown ((unsigned long )src,PAGE_SIZE );
arch/x86/mm/maccess.c +1 -4
@@ -26,10 +26,7 @@ static __always_inline bool invalid_probe_range(u64 vaddr) }#endif -bool probe_kernel_read_allowed (void *dst,const void *unsafe_src,size_t size, -bool strict) +bool probe_kernel_read_allowed (void *dst,const void *unsafe_src,size_t size) { -if (!strict) -return true;return !invalid_probe_range ((unsigned long )unsafe_src); }
include/linux/uaccess.h +1 -3
@@ -301,11 +301,9 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src,return 0 ; } -bool probe_kernel_read_allowed (void *dst,const void *unsafe_src, -size_t size,bool strict); +bool probe_kernel_read_allowed (void *dst,const void *unsafe_src,size_t size);extern long probe_kernel_read (void *dst,const void *src,size_t size); -extern long probe_kernel_read_strict (void *dst,const void *src,size_t size);extern long probe_user_read (void *dst,const void __user *src,size_t size);extern long notrace probe_kernel_write (void *dst,const void *src,size_t size);
kernel/trace/bpf_trace.c +13 -5
@@ -180,15 +180,23 @@ static __always_inline int bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr, const bool compat) { +const void __user *user_ptr = (__force const void __user *)unsafe_ptr;int ret =security_locked_down (LOCKDOWN_BPF_READ );if (unlikely (ret <0 )) - goto out; - ret = compat ?probe_kernel_read (dst, unsafe_ptr, size) : -probe_kernel_read_strict (dst, unsafe_ptr, size); + goto fail; + +if (IS_ENABLED (CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE ) && + compat && (unsigned long )unsafe_ptr <TASK_SIZE ) + ret =probe_user_read (dst, user_ptr, size); +else + ret =probe_kernel_read (dst, unsafe_ptr, size);if (unlikely (ret <0 )) -out: -memset (dst,0 , size); + goto fail; + +return 0 ; +fail: +memset (dst,0 , size);return ret; }
kernel/trace/trace_kprobe.c +13 -1
@@ -1208,7 +1208,13 @@ fetch_store_strlen(unsigned long addr)u8 c;do { - ret =probe_kernel_read (&c, (u8 *)addr + len,1 ); +if (IS_ENABLED (CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE ) && + (unsigned long )addr <TASK_SIZE ) { + ret =probe_user_read (&c, + (__force u8 __user *)addr + len,1 ); + }else { + ret =probe_kernel_read (&c, (u8 *)addr + len,1 ); + } len++; }while (c && ret ==0 && len <MAX_STRING_SIZE );
@@ -1284,6 +1290,12 @@ fetch_store_string_user(unsigned long addr, void *dest, void *base) static nokprobe_inline intprobe_mem_read (void *dest,void *src,size_t size) { +if (IS_ENABLED (CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE ) && + (unsigned long )src <TASK_SIZE ) { +return probe_user_read (dest, (__force const void __user *)src, + size); + } +return probe_kernel_read (dest, src, size); }
mm/maccess.c +6 -33
@@ -6,36 +6,14 @@#include <linux/mm.h> #include <linux/uaccess.h> -static long __probe_kernel_read (void *dst,const void *src,size_t size, -bool strict); -bool __weak probe_kernel_read_allowed (void *dst,const void *unsafe_src, -size_t size,bool strict) +size_t size) {return true; }/** -* probe_kernel_read(): safely attempt to read from any location -* @dst: pointer to the buffer that shall take the data -* @src: address to read from -* @size: size of the data chunk -* -* Same as probe_kernel_read_strict() except that for architectures with -* not fully separated user and kernel address spaces this function also works -* for user address tanges. -* -* DO NOT USE THIS FUNCTION - it is broken on architectures with entirely -* separate kernel and user address spaces, and also a bad idea otherwise. -*/ -long probe_kernel_read (void *dst,const void *src,size_t size) -{ -return __probe_kernel_read (dst, src, size, false); -} -EXPORT_SYMBOL_GPL (probe_kernel_read); - -/** -* probe_kernel_read_strict(): safely attempt to read from kernel-space +* probe_kernel_read(): safely attempt to read from kernel-space * @dst: pointer to the buffer that shall take the data * @src: address to read from * @size: size of the data chunk
@@ -48,18 +26,12 @@ EXPORT_SYMBOL_GPL(probe_kernel_read);* probe_kernel_read() suitable for use within regions where the caller * already holds mmap_sem, or other locks which nest inside mmap_sem. */ -long probe_kernel_read_strict (void *dst,const void *src,size_t size) -{ -return __probe_kernel_read (dst, src, size, true); -} - -static long __probe_kernel_read (void *dst,const void *src,size_t size, -bool strict) +long probe_kernel_read (void *dst,const void *src,size_t size) {long ret;mm_segment_t old_fs =get_fs (); -if (!probe_kernel_read_allowed (dst, src, size, strict)) +if (!probe_kernel_read_allowed (dst, src, size))return -EFAULT ;set_fs (KERNEL_DS );
@@ -73,6 +45,7 @@ static long __probe_kernel_read(void *dst, const void *src, size_t size,return -EFAULT ;return 0 ; } +EXPORT_SYMBOL_GPL (probe_kernel_read);/** * probe_user_read(): safely attempt to read from a user-space location
@@ -180,7 +153,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)if (unlikely (count <=0 ))return 0 ; -if (!probe_kernel_read_allowed (dst, unsafe_addr, count, true)) +if (!probe_kernel_read_allowed (dst, unsafe_addr, count))return -EFAULT ;set_fs (KERNEL_DS );
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
Re: [PATCH 13/20] maccess: always use strict semantics for probe_kernel_read
Quoted 7 lines · Christoph Hellwig
kernel/trace/bpf_trace.c +6
-0+ +if (IS_ENABLED (CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE ) && + compat && (unsigned long )unsafe_ptr <TASK_SIZE ) + ret =probe_user_read (dst, user_ptr, size); +else + ret =probe_kernel_read (dst, unsafe_ptr, size);
...
Quoted 8 lines
kernel/trace/trace_kprobe.c +7
-1- ret =probe_kernel_read (&c, (u8 *)addr + len,1 ); +if (IS_ENABLED (CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE ) && + (unsigned long )addr <TASK_SIZE ) { + ret =probe_user_read (&c, + (__force u8 __user *)addr + len,1 ); + }else { + ret =probe_kernel_read (&c, (u8 *)addr + len,1 ); + }
...
kernel/trace/trace_kprobe.c fetch_store_string_user(unsigned long addr, void *dest, void *base) · line 1296
Quoted 4 lines
kernel/trace/trace_kprobe.c +4
-0+if (IS_ENABLED (CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE ) && + (unsigned long )src <TASK_SIZE ) { +return probe_user_read (dest, (__force const void __user *)src, + size);
If you can't make the conditional legible and fit on a single line and make it obvious _why_ you have that conditional, just use a helper function.
Either for just the conditional itself, or for the whole operation. And at least for the bpf case, since you want the whole operation for that error handling and clearing of the result buffer anyway, I suspect it would be cleaner to have that kind of "bpf_copy_legacy_nofault()" function or whatever.
(And see previous email why I dislike that "compat" naming in the bpf case)
Linus
Masami Hiramatsu
maintainerRe: [PATCH 13/20] maccess: always use strict semantics for probe_kernel_read
In reply to Christoph HellwigQuoted 8 lines · On Tue, 19 May 2020 15:44:42 +0200 Christoph Hellwig <[email protected]> wrote:
kernel/trace/trace_kprobe.c +0
-0@@ -1208,7 +1208,13 @@ fetch_store_strlen(unsigned long addr)u8 c; do {
kernel/trace/trace_kprobe.c fetch_store_strlen(unsigned long addr) · line 1219
Quoted 10 lines
kernel/trace/trace_kprobe.c +7
-1- ret =probe_kernel_read (&c, (u8 *)addr + len,1 ); +if (IS_ENABLED (CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE ) && + (unsigned long )addr <TASK_SIZE ) { + ret =probe_user_read (&c, + (__force u8 __user *)addr + len,1 ); + }else { + ret =probe_kernel_read (&c, (u8 *)addr + len,1 ); + } len++; }while (c && ret ==0 && len <MAX_STRING_SIZE );
To avoid redundant check in the loop, we can use strnlen_user_nofault() out of the loop. Something like below.
...
u8 c;
if (IS_ENABLED(CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE) &&
(unsigned long)addr < TASK_SIZE) {
return strnlen_user_nofault((__force u8 __user *)addr, MAX_STRING_SIZE);
do {
ret = probe_kernel_read(&c, (u8 *)addr + len, 1);
len++;
} while (c && ret == 0 && len < MAX_STRING_SIZE);...
This must work because we must not have a string that continues across kernel space and user space.
Thank you,
Signature · 1 line
Masami Hiramatsu <[email protected]>
Re: [PATCH 13/20] maccess: always use strict semantics for probe_kernel_read
Quoted 5 lines · Masami Hiramatsu
Quoted 5 lines
kernel/trace/trace_kprobe.c +4
-1- ret =probe_kernel_read (&c, (u8 *)addr + len,1 ); +if (IS_ENABLED (CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE ) && + (unsigned long )addr <TASK_SIZE ) { + ret =probe_user_read (&c, + (__force u8 __user *)addr + len,1 );
Quoted 8 lines
kernel/trace/trace_kprobe.c fetch_store_strlen(unsigned long addr) · line 1219
Quoted 5 lines
kernel/trace/trace_kprobe.c +3
-0+ }else { + ret =probe_kernel_read (&c, (u8 *)addr + len,1 ); + } len++; }while (c && ret ==0 && len <MAX_STRING_SIZE );To avoid redundant check in the loop, we can use
strnlen_user_nofault()out of the loop. Something like below.
Yes, I've done something very similar in response to Linus' comment (just using an ifdef instead).
PATCH 14/20 maccess: move user access routines together
In reply to Christoph HellwigMove kernel access vs user access routines together to ease upcoming ifdefs.
--- mm/maccess.c | 110 +++++++++++++++++++++++++-------------------------- 1 file changed, 55 insertions(+), 55 deletions(-)
mm/maccess.c +55 -55
@@ -47,34 +47,6 @@ long probe_kernel_read(void *dst, const void *src, size_t size) }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 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)) { -pagefault_disable (); - ret =__copy_from_user_inatomic (dst, src, size); -pagefault_enable (); - } -set_fs (old_fs); - -if (ret) -return -EFAULT ; -return 0 ; -} -EXPORT_SYMBOL_GPL (probe_user_read); -/** * probe_kernel_write(): safely attempt to write to a location * @dst: address to write to
@@ -100,33 +72,6 @@ long probe_kernel_write(void *dst, const void *src, size_t size)return 0 ; } -/** -* 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 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)) { -pagefault_disable (); - ret =__copy_to_user_inatomic (dst, src, size); -pagefault_enable (); - } -set_fs (old_fs); - -if (ret) -return -EFAULT ; -return 0 ; -} -/** * strncpy_from_kernel_nofault: - Copy a NUL terminated string from unsafe * address.
@@ -170,6 +115,61 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)return ret ? -EFAULT : src - unsafe_addr; } +/** +* 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 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)) { +pagefault_disable (); + ret =__copy_from_user_inatomic (dst, src, size); +pagefault_enable (); + } +set_fs (old_fs); + +if (ret) +return -EFAULT ; +return 0 ; +} +EXPORT_SYMBOL_GPL (probe_user_read); + +/** +* 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 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)) { +pagefault_disable (); + ret =__copy_to_user_inatomic (dst, src, size); +pagefault_enable (); + } +set_fs (old_fs); + +if (ret) +return -EFAULT ; +return 0 ; +} +/** * strncpy_from_user_nofault: - Copy a NUL terminated string from unsafe user * address.
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 15/20 maccess: allow architectures to provide kernel probing directly
In reply to Christoph HellwigProvide alternative versions of probe_kernel_read, probe_kernel_write and strncpy_from_kernel_unsafe that don't need set_fs magic, but instead use arch hooks that are modelled after unsafe_{get,put}_user to access kernel memory in an exception safe way.
--- mm/maccess.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 76 insertions(+)
mm/maccess.c +76 -0
@@ -12,6 +12,81 @@ bool __weak probe_kernel_read_allowed(void *dst, const void *unsafe_src,return true; } +#ifdef HAVE_GET_KERNEL_NOFAULT + +#define probe_kernel_read_loop (dst, src, len, type, err_label) \ + while (len >= sizeof(type)) { \ + __get_kernel_nofault(dst, src, type, err_label); \ + dst += sizeof(type); \ + src += sizeof(type); \ + len -= sizeof(type); \ + } + +long probe_kernel_read (void *dst,const void *src,size_t size) +{ +if (!probe_kernel_read_allowed (dst, src, size)) +return -EFAULT ; + +pagefault_disable (); +probe_kernel_read_loop (dst, src, size, u64, Efault); +probe_kernel_read_loop (dst, src, size, u32, Efault); +probe_kernel_read_loop (dst, src, size, u16, Efault); +probe_kernel_read_loop (dst, src, size, u8, Efault); +pagefault_enable (); +return 0 ; +Efault: +pagefault_enable (); +return -EFAULT ; +} +EXPORT_SYMBOL_GPL (probe_kernel_read); + +#define probe_kernel_write_loop (dst, src, len, type, err_label) \ + while (len >= sizeof(type)) { \ + __put_kernel_nofault(dst, src, type, err_label); \ + dst += sizeof(type); \ + src += sizeof(type); \ + len -= sizeof(type); \ + } + +long probe_kernel_write (void *dst,const void *src,size_t size) +{ +pagefault_disable (); +probe_kernel_write_loop (dst, src, size, u64, Efault); +probe_kernel_write_loop (dst, src, size, u32, Efault); +probe_kernel_write_loop (dst, src, size, u16, Efault); +probe_kernel_write_loop (dst, src, size, u8, Efault); +pagefault_enable (); +return 0 ; +Efault: +pagefault_enable (); +return -EFAULT ; +} + +long strncpy_from_kernel_nofault (char *dst,const void *unsafe_addr,long count) +{ +const void *src = unsafe_addr; + +if (unlikely (count <=0 )) +return 0 ; +if (!probe_kernel_read_allowed (dst, unsafe_addr, count)) +return -EFAULT ; + +pagefault_disable (); +do { +__get_kernel_nofault (dst, src, u8, Efault); + dst++; + src++; + }while (dst[-1 ] && src - unsafe_addr < count); +pagefault_enable (); + + dst[-1 ] ='\0' ; +return src - unsafe_addr; +Efault: +pagefault_enable (); + dst[-1 ] ='\0' ; +return -EFAULT ; +} +#else /* HAVE_GET_KERNEL_NOFAULT */ /** * probe_kernel_read(): safely attempt to read from kernel-space * @dst: pointer to the buffer that shall take the data
@@ -114,6 +189,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count) return ret ? -EFAULT : src - unsafe_addr; } +#endif /* HAVE_GET_KERNEL_NOFAULT */ /** * probe_user_read(): safely attempt to read from a user-space location
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 16/20 x86: use non-set_fs based maccess routines
In reply to Christoph HellwigProvide arch_kernel_read and arch_kernel_write routines to implement the maccess routines without messing with set_fs and without stac/clac that opens up access to user space.
--- arch/x86/include/asm/uaccess.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)
arch/x86/include/asm/uaccess.h +16 -0
@@ -523,5 +523,21 @@ do { \unsafe_copy_loop (__ucu_dst, __ucu_src, __ucu_len, u8, label); \ } while (0) +#define HAVE_GET_KERNEL_NOFAULT + +#define __get_kernel_nofault (dst, src, type, err_label) \ +do { \ + int __kr_err; \ + \ + __get_user_size(*((type *)dst), (__force type __user *)src, \ + sizeof(type), __kr_err); \ + if (unlikely(__kr_err)) \ + goto err_label; \ +} while (0) + +#define __put_kernel_nofault (dst, src, type, err_label) \ + __put_user_size(*((type *)(src)), (__force type __user *)(dst), \ + sizeof(type), err_label) +#endif /* _ASM_X86_UACCESS_H */
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 17/20 maccess: rename probe_kernel_{read,write} to copy_{from,to}_kernel_nofault
In reply to Christoph HellwigBetter describe what these functions do.
--- arch/arm/kernel/ftrace.c | 3 +- arch/arm/kernel/kgdb.c | 2 +- arch/arm64/kernel/insn.c | 4 +-- arch/csky/kernel/ftrace.c | 5 ++-- arch/ia64/kernel/ftrace.c | 6 ++-- arch/mips/kernel/kprobes.c | 6 ++-- arch/nds32/kernel/ftrace.c | 5 ++-- arch/parisc/kernel/ftrace.c | 2 +- arch/parisc/kernel/kgdb.c | 4 +-- arch/parisc/lib/memcpy.c | 3 +- arch/powerpc/kernel/module_64.c | 5 ++-- arch/powerpc/kernel/trace/ftrace.c | 24 +++++++-------- arch/powerpc/perf/core-book3s.c | 3 +- arch/riscv/kernel/ftrace.c | 3 +- arch/riscv/kernel/patch.c | 4 +-- arch/s390/kernel/ftrace.c | 4 +-- arch/sh/kernel/ftrace.c | 6 ++-- arch/um/kernel/maccess.c | 2 +- arch/x86/include/asm/ptrace.h | 4 +-- arch/x86/kernel/dumpstack.c | 2 +- arch/x86/kernel/ftrace.c | 8 ++--- arch/x86/kernel/kgdb.c | 6 ++-- arch/x86/kernel/kprobes/core.c | 5 ++-- arch/x86/kernel/kprobes/opt.c | 2 +- arch/x86/kernel/traps.c | 3 +- arch/x86/mm/fault.c | 2 +- arch/x86/mm/init_32.c | 2 +- arch/x86/mm/maccess.c | 3 +- arch/x86/xen/enlighten_pv.c | 2 +- drivers/char/mem.c | 2 +- drivers/dio/dio.c | 6 ++-- drivers/input/serio/hp_sdc.c | 2 +- drivers/misc/kgdbts.c | 6 ++-- drivers/video/fbdev/hpfb.c | 2 +- fs/proc/kcore.c | 3 +- include/linux/uaccess.h | 14 +++++---- kernel/debug/debug_core.c | 6 ++-- kernel/debug/gdbstub.c | 6 ++-- kernel/debug/kdb/kdb_main.c | 3 +- kernel/debug/kdb/kdb_support.c | 7 +++-- kernel/kthread.c | 2 +- kernel/trace/bpf_trace.c | 2 +- kernel/trace/trace_kprobe.c | 4 +-- kernel/workqueue.c | 10 +++---- mm/maccess.c | 48 +++++++++++++++--------------- mm/rodata_test.c | 2 +- mm/slub.c | 2 +- 47 files changed, 137 insertions(+), 120 deletions(-)
arch/arm/kernel/ftrace.c +2 -1
@@ -84,7 +84,8 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old, old =__opcode_to_mem_arm (old);if (validate) { -if (probe_kernel_read (&replaced, (void *)pc,MCOUNT_INSN_SIZE )) +if (copy_from_kernel_nofault (&replaced, (void *)pc, +MCOUNT_INSN_SIZE ))return -EFAULT ;if (replaced != old)
arch/arm/kernel/kgdb.c +1 -1
@@ -236,7 +236,7 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)/* patch_text() only supports int-sized breakpoints */ BUILD_BUG_ON (sizeof (int ) !=BREAK_INSTR_SIZE ); - err =probe_kernel_read (bpt->saved_instr, (char *)bpt->bpt_addr, + err =copy_from_kernel_nofault (bpt->saved_instr, (char *)bpt->bpt_addr,BREAK_INSTR_SIZE );if (err)return err;
arch/arm64/kernel/insn.c +2 -2
@@ -123,7 +123,7 @@ int __kprobes aarch64_insn_read(void *addr, u32 *insnp)int ret;__le32 val; - ret =probe_kernel_read (&val, addr,AARCH64_INSN_SIZE ); + ret =copy_from_kernel_nofault (&val, addr,AARCH64_INSN_SIZE );if (!ret) *insnp =le32_to_cpu (val);
@@ -139,7 +139,7 @@ static int __kprobes __aarch64_insn_write(void *addr, __le32 insn)raw_spin_lock_irqsave (&patch_lock, flags); waddr =patch_map (addr,FIX_TEXT_POKE0 ); - ret =probe_kernel_write (waddr, &insn,AARCH64_INSN_SIZE ); + ret =copy_to_kernel_nofault (waddr, &insn,AARCH64_INSN_SIZE );patch_unmap (FIX_TEXT_POKE0 );raw_spin_unlock_irqrestore (&patch_lock, flags);
arch/csky/kernel/ftrace.c +3 -2
@@ -72,7 +72,8 @@ static int ftrace_check_current_nop(unsigned long hook)uint16_t olds[7 ];unsigned long hook_pos = hook -2 ; -if (probe_kernel_read ((void *)olds, (void *)hook_pos,sizeof (nops))) +if (copy_from_kernel_nofault ((void *)olds, (void *)hook_pos, +sizeof (nops)))return -EFAULT ;if (memcmp ((void *)nops, (void *)olds,sizeof (nops))) {
@@ -97,7 +98,7 @@ static int ftrace_modify_code(unsigned long hook, unsigned long target,make_jbsr (target, hook, call, nolr); - ret =probe_kernel_write ((void *)hook_pos, enable ? call : nops, + ret =copy_to_kernel_nofault ((void *)hook_pos, enable ? call : nops,sizeof (nops));if (ret)return -EPERM ;
arch/ia64/kernel/ftrace.c +3 -3
@@ -108,7 +108,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, goto skip_check;/* read the text we want to modify */ -if (probe_kernel_read (replaced, (void *)ip,MCOUNT_INSN_SIZE )) +if (copy_from_kernel_nofault (replaced, (void *)ip,MCOUNT_INSN_SIZE ))return -EFAULT ;/* Make sure it is what we expect it to be */
@@ -117,7 +117,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, skip_check:/* replace the text with the new text */ -if (probe_kernel_write (((void *)ip), new_code,MCOUNT_INSN_SIZE )) +if (copy_to_kernel_nofault (((void *)ip), new_code,MCOUNT_INSN_SIZE ))return -EPERM ;flush_icache_range (ip, ip +MCOUNT_INSN_SIZE );
@@ -129,7 +129,7 @@ static int ftrace_make_nop_check(struct dyn_ftrace *rec, unsigned long addr)unsigned char __attribute__((aligned (8 ))) replaced[MCOUNT_INSN_SIZE ];unsigned long ip = rec->ip; -if (probe_kernel_read (replaced, (void *)ip,MCOUNT_INSN_SIZE )) +if (copy_from_kernel_nofault (replaced, (void *)ip,MCOUNT_INSN_SIZE ))return -EFAULT ;if (rec->flags &FTRACE_FL_CONVERTED ) {struct ftrace_call_insn *call_insn, *tmp_call;
arch/mips/kernel/kprobes.c +3 -3
@@ -86,9 +86,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) goto out; } -if ((probe_kernel_read (&prev_insn, p->addr -1 , -sizeof (mips_instruction)) ==0 ) && -insn_has_delayslot (prev_insn)) { +if (copy_from_kernel_nofault (&prev_insn, p->addr -1 , +sizeof (mips_instruction)) ==0 && +insn_has_delayslot (prev_insn)) {pr_notice ("Kprobes for branch delayslot are not supported\n" ); ret = -EINVAL ; goto out;
arch/nds32/kernel/ftrace.c +3 -2
@@ -131,13 +131,14 @@ static int __ftrace_modify_code(unsigned long pc, unsigned long *old_insn,unsigned long orig_insn[3 ];if (validate) { -if (probe_kernel_read (orig_insn, (void *)pc,MCOUNT_INSN_SIZE )) +if (copy_from_kernel_nofault (orig_insn, (void *)pc, +MCOUNT_INSN_SIZE ))return -EFAULT ;if (memcmp (orig_insn, old_insn,MCOUNT_INSN_SIZE ))return -EINVAL ; } -if (probe_kernel_write ((void *)pc, new_insn,MCOUNT_INSN_SIZE )) +if (copy_to_kernel_nofault ((void *)pc, new_insn,MCOUNT_INSN_SIZE ))return -EPERM ;return 0 ;
arch/parisc/kernel/ftrace.c +1 -1
@@ -172,7 +172,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) ip = (void *)(rec->ip +4 - size); - ret =probe_kernel_read (insn, ip, size); + ret =copy_from_kernel_nofault (insn, ip, size);if (ret)return ret;
arch/parisc/kernel/kgdb.c +2 -2
@@ -154,8 +154,8 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)int kgdb_arch_set_breakpoint (struct kgdb_bkpt *bpt) { -int ret =probe_kernel_read (bpt->saved_instr, (char *)bpt->bpt_addr, -BREAK_INSTR_SIZE ); +int ret =copy_from_kernel_nofault (bpt->saved_instr, + (char *)bpt->bpt_addr,BREAK_INSTR_SIZE );if (ret)return ret;
arch/parisc/lib/memcpy.c +2 -1
@@ -57,7 +57,8 @@ void * memcpy(void * dst,const void *src, size_t count)EXPORT_SYMBOL (raw_copy_in_user);EXPORT_SYMBOL (memcpy); -bool probe_kernel_read_allowed (void *dst,const void *unsafe_src,size_t size) +bool copy_from_kernel_nofault_allowed (void *dst,const void *unsafe_src, +size_t size) {if ((unsigned long )unsafe_src <PAGE_SIZE )return false;
arch/powerpc/kernel/module_64.c +3 -2
@@ -159,7 +159,7 @@ int module_trampoline_target(struct module *mod, unsigned long addr, stub = (struct ppc64_stub_entry *)addr; -if (probe_kernel_read (&magic, &stub->magic,sizeof (magic))) { +if (copy_from_kernel_nofault (&magic, &stub->magic,sizeof (magic))) {pr_err ("%s: fault reading magic for stub %lx for %s\n" , __func__, addr, mod->name);return -EFAULT ; }
@@ -169,7 +169,8 @@ int module_trampoline_target(struct module *mod, unsigned long addr,return -EFAULT ; } -if (probe_kernel_read (&funcdata, &stub->funcdata,sizeof (funcdata))) { +if (copy_from_kernel_nofault (&funcdata, &stub->funcdata, +sizeof (funcdata))) {pr_err ("%s: fault reading funcdata for stub %lx for %s\n" , __func__, addr, mod->name);return -EFAULT ; }
arch/powerpc/kernel/trace/ftrace.c +12 -12
@@ -67,7 +67,7 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)*/ /* read the text we want to modify */ -if (probe_kernel_read (&replaced, (void *)ip,MCOUNT_INSN_SIZE )) +if (copy_from_kernel_nofault (&replaced, (void *)ip,MCOUNT_INSN_SIZE ))return -EFAULT ;/* Make sure it is what we expect it to be */
@@ -128,7 +128,7 @@ __ftrace_make_nop(struct module *mod,unsigned int op, pop;/* read where this goes */ -if (probe_kernel_read (&op, (void *)ip,sizeof (int ))) { +if (copy_from_kernel_nofault (&op, (void *)ip,sizeof (int ))) {pr_err ("Fetching opcode failed.\n" );return -EFAULT ; }
@@ -162,7 +162,7 @@ __ftrace_make_nop(struct module *mod,/* When using -mkernel_profile there is no load to jump over */ pop =PPC_INST_NOP ; -if (probe_kernel_read (&op, (void *)(ip -4 ),4 )) { +if (copy_from_kernel_nofault (&op, (void *)(ip -4 ),4 )) {pr_err ("Fetching instruction at %lx failed.\n" , ip -4 );return -EFAULT ; }
@@ -193,7 +193,7 @@ __ftrace_make_nop(struct module *mod,* Check what is in the next instruction. We can see ld r2,40(r1), but * on first pass after boot we will see mflr r0. */ -if (probe_kernel_read (&op, (void *)(ip+4 ),MCOUNT_INSN_SIZE )) { +if (copy_from_kernel_nofault (&op, (void *)(ip+4 ),MCOUNT_INSN_SIZE )) {pr_err ("Fetching op failed.\n" );return -EFAULT ; }
@@ -222,7 +222,7 @@ __ftrace_make_nop(struct module *mod,unsigned long ip = rec->ip;unsigned long tramp; -if (probe_kernel_read (&op, (void *)ip,MCOUNT_INSN_SIZE )) +if (copy_from_kernel_nofault (&op, (void *)ip,MCOUNT_INSN_SIZE ))return -EFAULT ;/* Make sure that that this is still a 24bit jump */
@@ -245,7 +245,7 @@ __ftrace_make_nop(struct module *mod,pr_devel ("ip:%lx jumps to %lx" , ip, tramp);/* Find where the trampoline jumps to */ -if (probe_kernel_read (jmp, (void *)tramp,sizeof (jmp))) { +if (copy_from_kernel_nofault (jmp, (void *)tramp,sizeof (jmp))) {pr_err ("Failed to read %lx\n" , tramp);return -EFAULT ; }
@@ -341,7 +341,7 @@ static int setup_mcount_compiler_tramp(unsigned long tramp)return -1 ;/* New trampoline -- read where this goes */ -if (probe_kernel_read (&op, (void *)tramp,sizeof (int ))) { +if (copy_from_kernel_nofault (&op, (void *)tramp,sizeof (int ))) {pr_debug ("Fetching opcode failed.\n" );return -1 ; }
@@ -391,7 +391,7 @@ static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr)unsigned int op;/* Read where this goes */ -if (probe_kernel_read (&op, (void *)ip,sizeof (int ))) { +if (copy_from_kernel_nofault (&op, (void *)ip,sizeof (int ))) {pr_err ("Fetching opcode failed.\n" );return -EFAULT ; }
@@ -516,7 +516,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)struct module *mod = rec->arch.mod;/* read where this goes */ -if (probe_kernel_read (op, ip,sizeof (op))) +if (copy_from_kernel_nofault (op, ip,sizeof (op)))return -EFAULT ;if (!expected_nop_sequence (ip, op[0 ], op[1 ])) {
@@ -578,7 +578,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)unsigned long ip = rec->ip;/* read where this goes */ -if (probe_kernel_read (&op, (void *)ip,MCOUNT_INSN_SIZE )) +if (copy_from_kernel_nofault (&op, (void *)ip,MCOUNT_INSN_SIZE ))return -EFAULT ;/* It should be pointing to a nop */
@@ -634,7 +634,7 @@ static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr) }/* Make sure we have a nop */ -if (probe_kernel_read (&op, ip,sizeof (op))) { +if (copy_from_kernel_nofault (&op, ip,sizeof (op))) {pr_err ("Unable to read ftrace location %p\n" , ip);return -EFAULT ; }
@@ -712,7 +712,7 @@ __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, }/* read where this goes */ -if (probe_kernel_read (&op, (void *)ip,sizeof (int ))) { +if (copy_from_kernel_nofault (&op, (void *)ip,sizeof (int ))) {pr_err ("Fetching opcode failed.\n" );return -EFAULT ; }
arch/powerpc/perf/core-book3s.c +2 -1
@@ -418,7 +418,8 @@ static __u64 power_pmu_bhrb_to(u64 addr)__u64 target;if (is_kernel_addr (addr)) { -if (probe_kernel_read (&instr, (void *)addr,sizeof (instr))) +if (copy_from_kernel_nofault (&instr, (void *)addr, +sizeof (instr)))return 0 ;return branch_target (&instr);
arch/riscv/kernel/ftrace.c +2 -1
@@ -25,7 +25,8 @@ static int ftrace_check_current_call(unsigned long hook_pos,* Read the text we want to modify; * return must be -EFAULT on read error */ -if (probe_kernel_read (replaced, (void *)hook_pos,MCOUNT_INSN_SIZE )) +if (copy_from_kernel_nofault (replaced, (void *)hook_pos, +MCOUNT_INSN_SIZE ))return -EFAULT ;/*
arch/riscv/kernel/patch.c +2 -2
@@ -57,7 +57,7 @@ static int __kprobes riscv_insn_write(void *addr, const void *insn, size_t len) waddr =patch_map (addr,FIX_TEXT_POKE0 ); - ret =probe_kernel_write (waddr, insn, len); + ret =copy_to_kernel_nofault (waddr, insn, len);patch_unmap (FIX_TEXT_POKE0 );
@@ -71,7 +71,7 @@ static int __kprobes riscv_insn_write(void *addr, const void *insn, size_t len)#else static int __kprobes riscv_insn_write (void *addr,const void *insn,size_t len) { -return probe_kernel_write (addr, insn, len); +return copy_to_kernel_nofault (addr, insn, len); }#endif /* CONFIG_MMU */
arch/s390/kernel/ftrace.c +2 -2
@@ -99,7 +99,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, {struct ftrace_insn orig, new, old; -if (probe_kernel_read (&old, (void *) rec->ip,sizeof (old))) +if (copy_from_kernel_nofault (&old, (void *) rec->ip,sizeof (old)))return -EFAULT ;if (addr ==MCOUNT_ADDR ) {/* Initial code replacement */
@@ -121,7 +121,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) {struct ftrace_insn orig, new, old; -if (probe_kernel_read (&old, (void *) rec->ip,sizeof (old))) +if (copy_from_kernel_nofault (&old, (void *) rec->ip,sizeof (old)))return -EFAULT ;/* Replace nop with an ftrace call. */ ftrace_generate_nop_insn (&orig);
arch/sh/kernel/ftrace.c +3 -3
@@ -119,7 +119,7 @@ static void ftrace_mod_code(void)* But if one were to fail, then they all should, and if one were * to succeed, then they all should. */ - mod_code_status =probe_kernel_write (mod_code_ip, mod_code_newcode, + mod_code_status =copy_to_kernel_nofault (mod_code_ip, mod_code_newcode,MCOUNT_INSN_SIZE );/* if we fail, then kill any new writers */
@@ -203,7 +203,7 @@ static int ftrace_modify_code(unsigned long ip, unsigned char *old_code,*/ /* read the text we want to modify */ -if (probe_kernel_read (replaced, (void *)ip,MCOUNT_INSN_SIZE )) +if (copy_from_kernel_nofault (replaced, (void *)ip,MCOUNT_INSN_SIZE ))return -EFAULT ;/* Make sure it is what we expect it to be */
@@ -268,7 +268,7 @@ static int ftrace_mod(unsigned long ip, unsigned long old_addr, {unsigned char code[MCOUNT_INSN_SIZE ]; -if (probe_kernel_read (code, (void *)ip,MCOUNT_INSN_SIZE )) +if (copy_from_kernel_nofault (code, (void *)ip,MCOUNT_INSN_SIZE ))return -EFAULT ;if (old_addr !=__raw_readl ((unsigned long *)code))
arch/um/kernel/maccess.c +1 -1
@@ -7,7 +7,7 @@#include <linux/kernel.h> #include <os.h> -bool probe_kernel_read_allowed (void *dst,const void *src,size_t size) +bool copy_from_kernel_nofault_allowed (void *dst,const void *src,size_t size) {void *psrc = (void *)rounddown ((unsigned long )src,PAGE_SIZE );
arch/x86/include/asm/ptrace.h +2 -2
@@ -278,7 +278,7 @@ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs }/* To avoid include hell, we can't include uaccess.h */ -extern long probe_kernel_read (void *dst,const void *src,size_t size); +extern long copy_from_kernel_nofault (void *dst,const void *src,size_t size);/** * regs_get_kernel_stack_nth() - get Nth entry of the stack
@@ -298,7 +298,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, addr =regs_get_kernel_stack_nth_addr (regs, n);if (addr) { - ret =probe_kernel_read (&val, addr,sizeof (val)); + ret =copy_from_kernel_nofault (&val, addr,sizeof (val));if (!ret)return val; }
arch/x86/kernel/dumpstack.c +1 -1
@@ -106,7 +106,7 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) bad_ip =user_mode (regs) &&__chk_range_not_ok (prologue,OPCODE_BUFSIZE ,TASK_SIZE_MAX ); -if (bad_ip ||probe_kernel_read (opcodes, (u8 *)prologue, +if (bad_ip ||copy_from_kernel_nofault (opcodes, (u8 *)prologue,OPCODE_BUFSIZE )) {printk ("%sCode: Bad RIP value.\n" , loglvl); }else {
arch/x86/kernel/ftrace.c +4 -4
@@ -86,7 +86,7 @@ static int ftrace_verify_code(unsigned long ip, const char *old_code)* sure what we read is what we expected it to be before modifying it. */ /* read the text we want to modify */ -if (probe_kernel_read (cur_code, (void *)ip,MCOUNT_INSN_SIZE )) { +if (copy_from_kernel_nofault (cur_code, (void *)ip,MCOUNT_INSN_SIZE )) {WARN_ON (1 );return -EFAULT ; }
@@ -354,7 +354,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) npages =DIV_ROUND_UP (*tramp_size,PAGE_SIZE );/* Copy ftrace_caller onto the trampoline memory */ - ret =probe_kernel_read (trampoline, (void *)start_offset, size); + ret =copy_from_kernel_nofault (trampoline, (void *)start_offset, size);if (WARN_ON (ret <0 )) goto fail;
@@ -362,7 +362,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)/* The trampoline ends with ret(q) */ retq = (unsigned long )ftrace_stub; - ret =probe_kernel_read (ip, (void *)retq,RET_SIZE ); + ret =copy_from_kernel_nofault (ip, (void *)retq,RET_SIZE );if (WARN_ON (ret <0 )) goto fail;
@@ -498,7 +498,7 @@ static void *addr_from_call(void *ptr)union text_poke_insn call;int ret; - ret =probe_kernel_read (&call, ptr,CALL_INSN_SIZE ); + ret =copy_from_kernel_nofault (&call, ptr,CALL_INSN_SIZE );if (WARN_ON_ONCE (ret <0 ))return NULL ;
arch/x86/kernel/kgdb.c +3 -3
@@ -732,11 +732,11 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)int err; bpt->type =BP_BREAKPOINT ; - err =probe_kernel_read (bpt->saved_instr, (char *)bpt->bpt_addr, + err =copy_from_kernel_nofault (bpt->saved_instr, (char *)bpt->bpt_addr,BREAK_INSTR_SIZE );if (err)return err; - err =probe_kernel_write ((char *)bpt->bpt_addr, + err =copy_to_kernel_nofault ((char *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,BREAK_INSTR_SIZE );if (!err)return err;
@@ -768,7 +768,7 @@ int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)return 0 ; knl_write: -return probe_kernel_write ((char *)bpt->bpt_addr, +return copy_to_kernel_nofault ((char *)bpt->bpt_addr, (char *)bpt->saved_instr,BREAK_INSTR_SIZE ); }
arch/x86/kernel/kprobes/core.c +3 -2
@@ -243,7 +243,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)* Fortunately, we know that the original code is the ideal 5-byte * long NOP. */ -if (probe_kernel_read (buf, (void *)addr, +if (copy_from_kernel_nofault (buf, (void *)addr,MAX_INSN_SIZE *sizeof (kprobe_opcode_t)))return 0UL ;
@@ -346,7 +346,8 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)return 0 ;/* This can access kernel text if given address is not recovered */ -if (probe_kernel_read (dest, (void *)recovered_insn,MAX_INSN_SIZE )) +if (copy_from_kernel_nofault (dest, (void *)recovered_insn, +MAX_INSN_SIZE ))return 0 ;kernel_insn_init (insn, dest,MAX_INSN_SIZE );
arch/x86/kernel/kprobes/opt.c +1 -1
@@ -56,7 +56,7 @@ unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr)* overwritten by jump destination address. In this case, original * bytes must be recovered from op->optinsn.copied_insn buffer. */ -if (probe_kernel_read (buf, (void *)addr, +if (copy_from_kernel_nofault (buf, (void *)addr,MAX_INSN_SIZE *sizeof (kprobe_opcode_t)))return 0UL ;
arch/x86/kernel/traps.c +2 -1
@@ -483,7 +483,8 @@ static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs,u8 insn_buf[MAX_INSN_SIZE ];struct insn insn; -if (probe_kernel_read (insn_buf, (void *)regs->ip,MAX_INSN_SIZE )) +if (copy_from_kernel_nofault (insn_buf, (void *)regs->ip, +MAX_INSN_SIZE ))return GP_NO_HINT ;kernel_insn_init (&insn, insn_buf,MAX_INSN_SIZE );
arch/x86/mm/fault.c +1 -1
@@ -590,7 +590,7 @@ static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index)return ; } -if (probe_kernel_read (&desc, (void *)(gdt->address + offset), +if (copy_from_kernel_nofault (&desc, (void *)(gdt->address + offset),sizeof (struct ldttss_desc ))) {pr_alert ("%s: 0x%hx -- GDT entry is not readable\n" , name, index);
arch/x86/mm/init_32.c +1 -1
@@ -758,7 +758,7 @@ static void __init test_wp_bit(void)__set_fixmap (FIX_WP_TEST ,__pa_symbol (empty_zero_page),PAGE_KERNEL_RO ); -if (probe_kernel_write ((char *)fix_to_virt (FIX_WP_TEST ), &z,1 )) { +if (copy_to_kernel_nofault ((char *)fix_to_virt (FIX_WP_TEST ), &z,1 )) {clear_fixmap (FIX_WP_TEST );printk (KERN_CONT "Ok.\n" );return ;
arch/x86/mm/maccess.c +2 -1
@@ -26,7 +26,8 @@ static __always_inline bool invalid_probe_range(u64 vaddr) }#endif -bool probe_kernel_read_allowed (void *dst,const void *unsafe_src,size_t size) +bool copy_from_kernel_nofault_allowed (void *dst,const void *unsafe_src, +size_t size) {return !invalid_probe_range ((unsigned long )unsafe_src); }
arch/x86/xen/enlighten_pv.c +1 -1
@@ -387,7 +387,7 @@ static void set_aliased_prot(void *v, pgprot_t prot)preempt_disable (); -probe_kernel_read (&dummy, v,1 ); +copy_from_kernel_nofault (&dummy, v,1 );if (HYPERVISOR_update_va_mapping ((unsigned long )v, pte,0 ))BUG ();
drivers/char/mem.c +1 -1
@@ -167,7 +167,7 @@ static ssize_t read_mem(struct file *file, char __user *buf,if (!ptr) goto failed; - probe =probe_kernel_read (bounce, ptr, sz); + probe =copy_from_kernel_nofault (bounce, ptr, sz);unxlate_dev_mem_ptr (p, ptr);if (probe) goto failed;
drivers/dio/dio.c +4 -2
@@ -135,7 +135,8 @@ int __init dio_find(int deviceid)else va =ioremap (pa,PAGE_SIZE ); -if (probe_kernel_read (&i, (unsigned char *)va +DIO_IDOFF ,1 )) { +if (copy_from_kernel_nofault (&i, + (unsigned char *)va +DIO_IDOFF ,1 )) {if (scode >=DIOII_SCBASE )iounmap (va);continue ;/* no board present at that select code */
@@ -208,7 +209,8 @@ static int __init dio_init(void)else va =ioremap (pa,PAGE_SIZE ); -if (probe_kernel_read (&i, (unsigned char *)va +DIO_IDOFF ,1 )) { +if (copy_from_kernel_nofault (&i, + (unsigned char *)va +DIO_IDOFF ,1 )) {if (scode >=DIOII_SCBASE )iounmap (va);continue ;/* no board present at that select code */
drivers/input/serio/hp_sdc.c +1 -1
@@ -1021,7 +1021,7 @@ static int __init hp_sdc_register(void) hp_sdc.base_io = (unsigned long )0xf0428000 ; hp_sdc.data_io = (unsigned long ) hp_sdc.base_io +1 ; hp_sdc.status_io = (unsigned long ) hp_sdc.base_io +3 ; -if (!probe_kernel_read (&i, (unsigned char *)hp_sdc.data_io,1 )) +if (!copy_from_kernel_nofault (&i, (unsigned char *)hp_sdc.data_io,1 )) hp_sdc.dev = (void *)1 ; hp_sdc.dev_err =hp_sdc_init ();#endif
drivers/misc/kgdbts.c +3 -3
@@ -828,7 +828,7 @@ static void run_plant_and_detach_test(int is_early)char before[BREAK_INSTR_SIZE ];char after[BREAK_INSTR_SIZE ]; -probe_kernel_read (before, (char *)kgdbts_break_test, +copy_from_kernel_nofault (before, (char *)kgdbts_break_test,BREAK_INSTR_SIZE );init_simple_test (); ts.tst = plant_and_detach_test;
@@ -836,8 +836,8 @@ static void run_plant_and_detach_test(int is_early)/* Activate test with initial breakpoint */ if (!is_early)kgdb_breakpoint (); -probe_kernel_read (after, (char *)kgdbts_break_test, -BREAK_INSTR_SIZE ); +copy_from_kernel_nofault (after, (char *)kgdbts_break_test, +BREAK_INSTR_SIZE );if (memcmp (before, after,BREAK_INSTR_SIZE )) {printk (KERN_CRIT "kgdbts: ERROR kgdb corrupted memory\n" );panic ("kgdb memory corruption" );
drivers/video/fbdev/hpfb.c +1 -1
@@ -402,7 +402,7 @@ int __init hpfb_init(void)if (err)return err; - err =probe_kernel_read (&i, (unsigned char *)INTFBVADDR +DIO_IDOFF ,1 ); + err =copy_from_kernel_nofault (&i, (unsigned char *)INTFBVADDR +DIO_IDOFF ,1 );if (!err && (i ==DIO_ID_FBUFFER ) &&topcat_sid_ok (sid =DIO_SECID (INTFBVADDR ))) {if (!request_mem_region (INTFBPADDR ,DIO_DEVSIZE ,"Internal Topcat" ))
fs/proc/kcore.c +2 -1
@@ -512,7 +512,8 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)* Using bounce buffer to bypass the * hardened user copy kernel text checks. */ -if (probe_kernel_read (buf, (void *) start, tsz)) { +if (copy_from_kernel_nofault (buf, (void *)start, + tsz)) {if (clear_user (buffer, tsz)) { ret = -EFAULT ; goto out;
include/linux/uaccess.h +8 -6
@@ -301,13 +301,15 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src,return 0 ; } -bool probe_kernel_read_allowed (void *dst,const void *unsafe_src,size_t size); +bool copy_from_kernel_nofault_allowed (void *dst,const void *unsafe_src, +size_t size); -extern long probe_kernel_read (void *dst,const void *src,size_t size); -extern long probe_user_read (void *dst,const void __user *src,size_t size); +long copy_from_kernel_nofault (void *dst,const void *src,size_t size); +long notrace copy_to_kernel_nofault (void *dst,const void *src,size_t size); -extern long notrace probe_kernel_write (void *dst,const void *src,size_t size); -extern long notrace probe_user_write (void __user *dst,const void *src,size_t size); +extern long probe_user_read (void *dst,const void __user *src,size_t size); +extern long notrace probe_user_write (void __user *dst,const void *src, +size_t size);long strncpy_from_kernel_nofault (char *dst,const void *unsafe_addr,long count);
@@ -324,7 +326,7 @@ long strnlen_user_nofault(const void __user *unsafe_addr, long count);* Returns 0 on success, or -EFAULT. */ #define probe_kernel_address (addr, retval) \ - probe_kernel_read(&retval, addr, sizeof(retval)) + copy_from_kernel_nofault(&retval, addr, sizeof(retval))#ifndef user_access_begin#define user_access_begin (ptr,len) access_ok(ptr, len)
kernel/debug/debug_core.c +3 -3
@@ -171,18 +171,18 @@ int __weak kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) {int err; - err =probe_kernel_read (bpt->saved_instr, (char *)bpt->bpt_addr, + err =copy_from_kernel_nofault (bpt->saved_instr, (char *)bpt->bpt_addr,BREAK_INSTR_SIZE );if (err)return err; - err =probe_kernel_write ((char *)bpt->bpt_addr, + err =copy_to_kernel_nofault ((char *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,BREAK_INSTR_SIZE );return err; }int __weak kgdb_arch_remove_breakpoint (struct kgdb_bkpt *bpt) { -return probe_kernel_write ((char *)bpt->bpt_addr, +return copy_to_kernel_nofault ((char *)bpt->bpt_addr, (char *)bpt->saved_instr,BREAK_INSTR_SIZE ); }
kernel/debug/gdbstub.c +3 -3
@@ -247,7 +247,7 @@ char *kgdb_mem2hex(char *mem, char *buf, int count)*/ tmp = buf + count; - err =probe_kernel_read (tmp, mem, count); + err =copy_from_kernel_nofault (tmp, mem, count);if (err)return NULL ;while (count >0 ) {
@@ -283,7 +283,7 @@ int kgdb_hex2mem(char *buf, char *mem, int count) *tmp_raw |=hex_to_bin (*tmp_hex--) <<4 ; } -return probe_kernel_write (mem, tmp_raw, count); +return copy_to_kernel_nofault (mem, tmp_raw, count); }/*
@@ -335,7 +335,7 @@ static int kgdb_ebin2mem(char *buf, char *mem, int count) size++; } -return probe_kernel_write (mem, c, size); +return copy_to_kernel_nofault (mem, c, size); }#if DBG_MAX_REG_NUM >0
kernel/debug/kdb/kdb_main.c +2 -1
@@ -2325,7 +2325,8 @@ void kdb_ps1(const struct task_struct *p)int cpu;unsigned long tmp; -if (!p ||probe_kernel_read (&tmp, (char *)p,sizeof (unsigned long ))) +if (!p || +copy_from_kernel_nofault (&tmp, (char *)p,sizeof (unsigned long )))return ; cpu =kdb_process_cpu (p);
kernel/debug/kdb/kdb_support.c +4 -3
@@ -325,7 +325,7 @@ char *kdb_strdup(const char *str, gfp_t type)*/ int kdb_getarea_size (void *res,unsigned long addr,size_t size) { -int ret =probe_kernel_read ((char *)res, (char *)addr, size); +int ret =copy_from_kernel_nofault ((char *)res, (char *)addr, size);if (ret) {if (!KDB_STATE (SUPPRESS )) {kdb_printf ("kdb_getarea: Bad address 0x%lx\n" , addr);
@@ -350,7 +350,7 @@ int kdb_getarea_size(void *res, unsigned long addr, size_t size)*/ int kdb_putarea_size (unsigned long addr,void *res,size_t size) { -int ret =probe_kernel_read ((char *)addr, (char *)res, size); +int ret =copy_from_kernel_nofault ((char *)addr, (char *)res, size);if (ret) {if (!KDB_STATE (SUPPRESS )) {kdb_printf ("kdb_putarea: Bad address 0x%lx\n" , addr);
@@ -624,7 +624,8 @@ char kdb_task_state_char (const struct task_struct *p)char state;unsigned long tmp; -if (!p ||probe_kernel_read (&tmp, (char *)p,sizeof (unsigned long ))) +if (!p || +copy_from_kernel_nofault (&tmp, (char *)p,sizeof (unsigned long )))return 'E' ; cpu =kdb_process_cpu (p);
kernel/kthread.c +1 -1
@@ -179,7 +179,7 @@ void *kthread_probe_data(struct task_struct *task)struct kthread *kthread =to_kthread (task);void *data =NULL ; -probe_kernel_read (&data, &kthread->data,sizeof (data)); +copy_from_kernel_nofault (&data, &kthread->data,sizeof (data));return data; }
kernel/trace/bpf_trace.c +1 -1
@@ -190,7 +190,7 @@ bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr, compat && (unsigned long)unsafe_ptr < TASK_SIZE) ret =probe_user_read (dst, user_ptr, size); else - ret =probe_kernel_read (dst, unsafe_ptr, size); + ret =copy_from_kernel_nofault (dst, unsafe_ptr, size);if (unlikely (ret <0 )) goto fail;
kernel/trace/trace_kprobe.c +2 -2
@@ -1213,7 +1213,7 @@ fetch_store_strlen(unsigned long addr) ret =probe_user_read (&c, (__force u8 __user *)addr + len,1 ); }else { - ret =probe_kernel_read (&c, (u8 *)addr + len,1 ); + ret =copy_from_kernel_nofault (&c, (u8 *)addr + len,1 ); } len++; }while (c && ret ==0 && len <MAX_STRING_SIZE );
@@ -1296,7 +1296,7 @@ probe_mem_read(void *dest, void *src, size_t size) size); } -return probe_kernel_read (dest, src, size); +return copy_from_kernel_nofault (dest, src, size); }static nokprobe_inline int
kernel/workqueue.c +5 -5
@@ -4627,11 +4627,11 @@ void print_worker_info(const char *log_lvl, struct task_struct *task)* Carefully copy the associated workqueue's workfn, name and desc. * Keep the original last '\0' in case the original is garbage. */ -probe_kernel_read (&fn, &worker->current_func,sizeof (fn)); -probe_kernel_read (&pwq, &worker->current_pwq,sizeof (pwq)); -probe_kernel_read (&wq, &pwq->wq,sizeof (wq)); -probe_kernel_read (name, wq->name,sizeof (name) -1 ); -probe_kernel_read (desc, worker->desc,sizeof (desc) -1 ); +copy_from_kernel_nofault (&fn, &worker->current_func,sizeof (fn)); +copy_from_kernel_nofault (&pwq, &worker->current_pwq,sizeof (pwq)); +copy_from_kernel_nofault (&wq, &pwq->wq,sizeof (wq)); +copy_from_kernel_nofault (name, wq->name,sizeof (name) -1 ); +copy_from_kernel_nofault (desc, worker->desc,sizeof (desc) -1 );if (fn || name[0 ] || desc[0 ]) {printk ("%sWorkqueue: %s %ps" , log_lvl, name, fn);
mm/maccess.c +24 -24
129 lines not on this page · raw message
mm/rodata_test.c +1 -1
@@ -25,7 +25,7 @@ void rodata_test(void) }/* test 2: write to the variable; this should fault */ -if (!probe_kernel_write ((void *)&rodata_test_data, +if (!copy_to_kernel_nofault ((void *)&rodata_test_data, (void *)&zero,sizeof (zero))) {pr_err ("test data was not read only\n" );return ;
mm/slub.c +1 -1
@@ -292,7 +292,7 @@ static inline void *get_freepointer_safe(struct kmem_cache *s, void *object)return get_freepointer (s, object); freepointer_addr = (unsigned long )object + s->offset; -probe_kernel_read (&p, (void **)freepointer_addr,sizeof (p)); +copy_from_kernel_nofault (&p, (void **)freepointer_addr,sizeof (p));return freelist_ptr (s, p, freepointer_addr); }
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 18/20 maccess: rename probe_user_{read,write} to copy_{from,to}_user_nofault
In reply to Christoph HellwigBetter describe what these functions do.
--- arch/powerpc/kernel/process.c | 3 ++- arch/powerpc/kvm/book3s_64_mmu_radix.c | 4 ++-- arch/powerpc/mm/fault.c | 2 +- arch/powerpc/oprofile/backtrace.c | 6 ++++-- arch/powerpc/perf/callchain_32.c | 2 +- arch/powerpc/perf/callchain_64.c | 2 +- arch/powerpc/perf/core-book3s.c | 3 ++- arch/powerpc/sysdev/fsl_pci.c | 4 ++-- include/linux/uaccess.h | 4 ++-- kernel/trace/bpf_trace.c | 6 +++--- kernel/trace/trace_kprobe.c | 8 ++++---- mm/maccess.c | 10 +++++----- 12 files changed, 29 insertions(+), 25 deletions(-)
arch/powerpc/kernel/process.c +2 -1
@@ -1294,7 +1294,8 @@ void show_user_instructions(struct pt_regs *regs)for (i =0 ; i <8 && n; i++, n--, pc +=sizeof (int )) {int instr; -if (probe_user_read (&instr, (void __user *)pc,sizeof (instr))) { +if (copy_from_user_nofault (&instr, (void __user *)pc, +sizeof (instr))) {seq_buf_printf (&s,"XXXXXXXX " );continue ; }
arch/powerpc/kvm/book3s_64_mmu_radix.c +2 -2
@@ -64,9 +64,9 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,isync ();if (is_load) - ret =probe_user_read (to, (const void __user *)from, n); + ret =copy_from_user_nofault (to, (const void __user *)from, n);else - ret =probe_user_write ((void __user *)to, from, n); + ret =copy_to_user_nofault ((void __user *)to, from, n);/* switch the pid first to avoid running host with unallocated pid */ if (quadrant ==1 && pid != old_pid)
arch/powerpc/mm/fault.c +1 -1
@@ -280,7 +280,7 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, access_ok(nip, sizeof(*nip))) {unsigned int inst; -if (!probe_user_read (&inst, nip,sizeof (inst))) +if (!copy_from_user_nofault (&inst, nip,sizeof (inst)))return !store_updates_sp (inst); *must_retry = true; }
arch/powerpc/oprofile/backtrace.c +4 -2
@@ -33,7 +33,8 @@ static unsigned int user_getsp32(unsigned int sp, int is_first)* which means that we've done all that we can do from * interrupt context. */ -if (probe_user_read (stack_frame, (void __user *)p,sizeof (stack_frame))) +if (copy_from_user_nofault (stack_frame, (void __user *)p, +sizeof (stack_frame)))return 0 ;if (!is_first)
@@ -51,7 +52,8 @@ static unsigned long user_getsp64(unsigned long sp, int is_first) {unsigned long stack_frame[3 ]; -if (probe_user_read (stack_frame, (void __user *)sp,sizeof (stack_frame))) +if (copy_from_user_nofault (stack_frame, (void __user *)sp, +sizeof (stack_frame)))return 0 ;if (!is_first)
arch/powerpc/perf/callchain_32.c +1 -1
@@ -45,7 +45,7 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret) ((unsigned long)ptr & 3))return -EFAULT ; - rc =probe_user_read (ret, ptr,sizeof (*ret)); + rc =copy_from_user_nofault (ret, ptr,sizeof (*ret));if (IS_ENABLED (CONFIG_PPC64 ) && rc)return read_user_stack_slow (ptr, ret,4 );
arch/powerpc/perf/callchain_64.c +1 -1
@@ -71,7 +71,7 @@ static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret) ((unsigned long)ptr & 7))return -EFAULT ; -if (!probe_user_read (ret, ptr,sizeof (*ret))) +if (!copy_from_user_nofault (ret, ptr,sizeof (*ret)))return 0 ;return read_user_stack_slow (ptr, ret,8 );
arch/powerpc/perf/core-book3s.c +2 -1
@@ -426,7 +426,8 @@ static __u64 power_pmu_bhrb_to(u64 addr) }/* Userspace: need copy instruction here then translate it */ -if (probe_user_read (&instr, (unsigned int __user *)addr,sizeof (instr))) +if (copy_from_user_nofault (&instr, (unsigned int __user *)addr, +sizeof (instr)))return 0 ; target =branch_target (&instr);
arch/powerpc/sysdev/fsl_pci.c +2 -2
@@ -1066,8 +1066,8 @@ int fsl_pci_mcheck_exception(struct pt_regs *regs)if (is_in_pci_mem_space (addr)) {if (user_mode (regs)) - ret =probe_user_read (&inst, (void __user *)regs->nip, -sizeof (inst)); + ret =copy_from_user_nofault (&inst, + (void __user *)regs->nip,sizeof (inst));else ret =probe_kernel_address ((void *)regs->nip, inst);
include/linux/uaccess.h +2 -2
@@ -307,8 +307,8 @@ bool copy_from_kernel_nofault_allowed(void *dst, const void *unsafe_src,long copy_from_kernel_nofault (void *dst,const void *src,size_t size);long notrace copy_to_kernel_nofault (void *dst,const void *src,size_t size); -extern long probe_user_read (void *dst,const void __user *src,size_t size); -extern long notrace probe_user_write (void __user *dst,const void *src, +long copy_from_user_nofault (void *dst,const void __user *src,size_t size); +long notrace copy_to_user_nofault (void __user *dst,const void *src,size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr,
kernel/trace/bpf_trace.c +3 -3
@@ -139,7 +139,7 @@ static const struct bpf_func_proto bpf_override_return_proto = { BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size, const void __user *, unsafe_ptr) { -int ret =probe_user_read (dst, unsafe_ptr, size); +int ret =copy_from_user_nofault (dst, unsafe_ptr, size);if (unlikely (ret <0 ))memset (dst,0 , size);
@@ -188,7 +188,7 @@ bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr,if (IS_ENABLED (CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE ) && compat && (unsigned long )unsafe_ptr <TASK_SIZE ) - ret =probe_user_read (dst, user_ptr, size); + ret =copy_from_user_nofault (dst, user_ptr, size);else ret =copy_from_kernel_nofault (dst, unsafe_ptr, size);if (unlikely (ret <0 ))
@@ -317,7 +317,7 @@ BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src,if (unlikely (!nmi_uaccess_okay ()))return -EPERM ; -return probe_user_write (unsafe_ptr, src, size); +return copy_to_user_nofault (unsafe_ptr, src, size); }static const struct bpf_func_proto bpf_probe_write_user_proto = {
kernel/trace/trace_kprobe.c +4 -4
@@ -1210,7 +1210,7 @@ fetch_store_strlen(unsigned long addr) do { if (IS_ENABLED(CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE) && (unsigned long)addr < TASK_SIZE) { - ret = probe_user_read(&c, + ret = copy_from_user_nofault(&c, (__force u8 __user *)addr + len, 1); } else { ret = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1);
@@ -1292,8 +1292,8 @@ probe_mem_read(void *dest, void *src, size_t size) {if (IS_ENABLED (CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE ) && (unsigned long )src <TASK_SIZE ) { -return probe_user_read (dest, (__force const void __user *)src, - size); +return copy_from_user_nofault (dest, + (__force const void __user *)src, size); }return copy_from_kernel_nofault (dest, src, size);
@@ -1304,7 +1304,7 @@ probe_mem_read_user(void *dest, void *src, size_t size) {const void __user *uaddr = (__force const void __user *)src; -return probe_user_read (dest, uaddr, size); +return copy_from_user_nofault (dest, uaddr, size); }/* Note that we don't verify it, since the code does not come from user space */
mm/maccess.c +5 -5
@@ -192,7 +192,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)#endif /* HAVE_GET_KERNEL_NOFAULT */ /** -* probe_user_read(): safely attempt to read from a user-space location +* copy_from_user_nofault(): 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
@@ -200,7 +200,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)* Safely read from user address @src to the buffer at @dst. If a kernel fault * happens, handle that and return -EFAULT. */ -long probe_user_read (void *dst,const void __user *src,size_t size) +long copy_from_user_nofault (void *dst,const void __user *src,size_t size) {long ret = -EFAULT ;mm_segment_t old_fs =get_fs ();
@@ -217,10 +217,10 @@ long probe_user_read(void *dst, const void __user *src, size_t size)return -EFAULT ;return 0 ; } -EXPORT_SYMBOL_GPL (probe_user_read); +EXPORT_SYMBOL_GPL (copy_from_user_nofault);/** -* probe_user_write(): safely attempt to write to a user-space location +* copy_to_user_nofault(): 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
@@ -228,7 +228,7 @@ EXPORT_SYMBOL_GPL(probe_user_read);* Safely write to address @dst from the buffer at @src. If a kernel fault * happens, handle that and return -EFAULT. */ -long probe_user_write (void __user *dst,const void *src,size_t size) +long copy_to_user_nofault (void __user *dst,const void *src,size_t size) {long ret = -EFAULT ;mm_segment_t old_fs =get_fs ();
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 19/20 maccess: rename probe_kernel_address to get_kernel_nofault
In reply to Christoph HellwigBetter describe what this helper does, and match the naming of copy_from_kernel_nofault.
--- arch/arm/kernel/traps.c | 2 +- arch/arm/mm/alignment.c | 4 ++-- arch/arm64/kernel/traps.c | 2 +- arch/ia64/include/asm/sections.h | 2 +- arch/parisc/kernel/process.c | 2 +- arch/powerpc/include/asm/sections.h | 2 +- arch/powerpc/kernel/kgdb.c | 2 +- arch/powerpc/kernel/process.c | 2 +- arch/powerpc/sysdev/fsl_pci.c | 2 +- arch/riscv/kernel/traps.c | 4 ++-- arch/s390/mm/fault.c | 2 +- arch/sh/kernel/traps.c | 2 +- arch/x86/kernel/probe_roms.c | 20 ++++++++++---------- arch/x86/kernel/traps.c | 2 +- arch/x86/mm/fault.c | 6 +++--- arch/x86/pci/pcbios.c | 2 +- include/linux/uaccess.h | 4 ++-- lib/test_lockup.c | 6 +++--- 18 files changed, 34 insertions(+), 34 deletions(-)
arch/arm/kernel/traps.c +1 -1
@@ -391,7 +391,7 @@ int is_valid_bugaddr(unsigned long pc)u32 insn =__opcode_to_mem_arm (BUG_INSTR_VALUE );#endif -if (probe_kernel_address ((unsigned *)pc, bkpt)) +if (get_kernel_nofault ((unsigned *)pc, bkpt))return 0 ;return bkpt == insn;
arch/arm/mm/alignment.c +2 -2
@@ -774,7 +774,7 @@ static int alignment_get_arm(struct pt_regs *regs, u32 *ip, u32 *inst)if (user_mode (regs)) fault =get_user (instr, ip);else - fault =probe_kernel_address (ip, instr); + fault =get_kernel_nofault (ip, instr); *inst =__mem_to_opcode_arm (instr);
@@ -789,7 +789,7 @@ static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst)if (user_mode (regs)) fault =get_user (instr, ip);else - fault =probe_kernel_address (ip, instr); + fault =get_kernel_nofault (ip, instr); *inst =__mem_to_opcode_thumb16 (instr);
arch/arm64/kernel/traps.c +1 -1
@@ -315,7 +315,7 @@ static int call_undef_hook(struct pt_regs *regs)if (!user_mode (regs)) {__le32 instr_le; -if (probe_kernel_address ((__force __le32 *)pc, instr_le)) +if (get_kernel_nofault ((__force __le32 *)pc, instr_le)) goto exit; instr =le32_to_cpu (instr_le); }else if (compat_thumb_mode (regs)) {
arch/ia64/include/asm/sections.h +1 -1
@@ -35,7 +35,7 @@ static inline void *dereference_function_descriptor(void *ptr)struct fdesc *desc = ptr;void *p; -if (!probe_kernel_address (&desc->ip, p)) +if (!get_kernel_nofault (&desc->ip, p)) ptr = p;return ptr; }
arch/parisc/kernel/process.c +1 -1
@@ -293,7 +293,7 @@ void *dereference_function_descriptor(void *ptr)Elf64_Fdesc *desc = ptr;void *p; -if (!probe_kernel_address (&desc->addr, p)) +if (!get_kernel_nofault (&desc->addr, p)) ptr = p;return ptr; }
arch/powerpc/include/asm/sections.h +1 -1
@@ -85,7 +85,7 @@ static inline void *dereference_function_descriptor(void *ptr)struct ppc64_opd_entry *desc = ptr;void *p; -if (!probe_kernel_address (&desc->funcaddr, p)) +if (!get_kernel_nofault (&desc->funcaddr, p)) ptr = p;return ptr; }
arch/powerpc/kernel/kgdb.c +1 -1
@@ -420,7 +420,7 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)unsigned int instr;unsigned int *addr = (unsigned int *)bpt->bpt_addr; - err =probe_kernel_address (addr, instr); + err =get_kernel_nofault (addr, instr);if (err)return err;
arch/powerpc/kernel/process.c +1 -1
@@ -1260,7 +1260,7 @@ static void show_instructions(struct pt_regs *regs)#endif if (!__kernel_text_address (pc) || -probe_kernel_address ((const void *)pc, instr)) { +get_kernel_nofault ((const void *)pc, instr)) {pr_cont ("XXXXXXXX " ); }else {if (regs->nip == pc)
arch/powerpc/sysdev/fsl_pci.c +1 -1
@@ -1069,7 +1069,7 @@ int fsl_pci_mcheck_exception(struct pt_regs *regs) ret =copy_from_user_nofault (&inst, (void __user *)regs->nip,sizeof (inst)); else - ret =probe_kernel_address ((void *)regs->nip, inst); + ret =get_kernel_nofault ((void *)regs->nip, inst);if (!ret &&mcheck_handle_load (regs, inst)) { regs->nip +=4 ;
arch/riscv/kernel/traps.c +2 -2
@@ -137,7 +137,7 @@ static inline unsigned long get_break_insn_length(unsigned long pc) {bug_insn_t insn; -if (probe_kernel_address ((bug_insn_t *)pc, insn)) +if (get_kernel_nofault ((bug_insn_t *)pc, insn))return 0 ;return GET_INSN_LENGTH (insn);
@@ -160,7 +160,7 @@ int is_valid_bugaddr(unsigned long pc)if (pc <VMALLOC_START )return 0 ; -if (probe_kernel_address ((bug_insn_t *)pc, insn)) +if (get_kernel_nofault ((bug_insn_t *)pc, insn))return 0 ;if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32)return (insn == __BUG_INSN_32);
arch/s390/mm/fault.c +1 -1
@@ -106,7 +106,7 @@ static int bad_address(void *p) {unsigned long dummy; -return probe_kernel_address ((unsigned long *)p, dummy); +return get_kernel_nofault ((unsigned long *)p, dummy); }static void dump_pagetable (unsigned long asce,unsigned long address)
arch/sh/kernel/traps.c +1 -1
@@ -118,7 +118,7 @@ int is_valid_bugaddr(unsigned long addr)if (addr <PAGE_OFFSET )return 0 ; -if (probe_kernel_address ((insn_size_t *)addr, opcode)) +if (get_kernel_nofault ((insn_size_t *)addr, opcode))return 0 ;if (opcode ==TRAPA_BUG_OPCODE )return 1 ;
arch/x86/kernel/probe_roms.c +10 -10
@@ -99,7 +99,7 @@ static bool probe_list(struct pci_dev *pdev, unsigned short vendor,unsigned short device; do { - if (probe_kernel_address(rom_list, device) != 0) + if (get_kernel_nofault(rom_list, device) != 0) device = 0; if (device && match_id(pdev, vendor, device))
@@ -125,13 +125,13 @@ static struct resource *find_oprom(struct pci_dev *pdev)break ; rom =isa_bus_to_virt (res->start); -if (probe_kernel_address (rom +0x18 , offset) !=0 ) +if (get_kernel_nofault (rom +0x18 , offset) !=0 )continue ; -if (probe_kernel_address (rom + offset +0x4 , vendor) !=0 ) +if (get_kernel_nofault (rom + offset +0x4 , vendor) !=0 )continue ; -if (probe_kernel_address (rom + offset +0x6 , device) !=0 ) +if (get_kernel_nofault (rom + offset +0x6 , device) !=0 )continue ;if (match_id (pdev, vendor, device)) {
@@ -139,8 +139,8 @@ static struct resource *find_oprom(struct pci_dev *pdev)break ; } -if (probe_kernel_address (rom + offset +0x8 , list) ==0 && -probe_kernel_address (rom + offset +0xc , rev) ==0 && +if (get_kernel_nofault (rom + offset +0x8 , list) ==0 && +get_kernel_nofault (rom + offset +0xc , rev) ==0 && rev >=3 && list &&probe_list (pdev, vendor, rom + offset + list)) { oprom = res;
@@ -183,14 +183,14 @@ static int __init romsignature(const unsigned char *rom)const unsigned short *const ptr = (const unsigned short *)rom;unsigned short sig; -return probe_kernel_address (ptr, sig) ==0 && sig ==ROMSIGNATURE ; +return get_kernel_nofault (ptr, sig) ==0 && sig ==ROMSIGNATURE ; }static int __init romchecksum (const unsigned char *rom,unsigned long length) {unsigned char sum, c; -for (sum =0 ; length &&probe_kernel_address (rom++, c) ==0 ; length--) +for (sum =0 ; length &&get_kernel_nofault (rom++, c) ==0 ; length--) sum += c;return !length && !sum; }
@@ -211,7 +211,7 @@ void __init probe_roms(void) video_rom_resource.start = start; -if (probe_kernel_address (rom +2 , c) !=0 ) +if (get_kernel_nofault (rom +2 , c) !=0 )continue ;/* 0 < length <= 0x7f * 512, historically */
@@ -249,7 +249,7 @@ void __init probe_roms(void)if (!romsignature (rom))continue ; -if (probe_kernel_address (rom +2 , c) !=0 ) +if (get_kernel_nofault (rom +2 , c) !=0 )continue ;/* 0 < length <= 0x7f * 512, historically */
arch/x86/kernel/traps.c +1 -1
@@ -161,7 +161,7 @@ int is_valid_bugaddr(unsigned long addr)if (addr <TASK_SIZE_MAX )return 0 ; -if (probe_kernel_address ((unsigned short *)addr, ud)) +if (get_kernel_nofault ((unsigned short *)addr, ud))return 0 ;return ud ==INSN_UD0 || ud ==INSN_UD2 ;
arch/x86/mm/fault.c +3 -3
@@ -98,7 +98,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,return !instr_lo || (instr_lo>>1 ) ==1 ;case 0x00 :/* Prefetch instruction is 0x0F0D or 0x0F18 */ -if (probe_kernel_address (instr, opcode)) +if (get_kernel_nofault (instr, opcode))return 0 ; *prefetch = (instr_lo == 0xF) &&
@@ -132,7 +132,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)while (instr < max_instr) {unsigned char opcode; -if (probe_kernel_address (instr, opcode)) +if (get_kernel_nofault (instr, opcode))break ; instr++;
@@ -441,7 +441,7 @@ static int bad_address(void *p) {unsigned long dummy; -return probe_kernel_address ((unsigned long *)p, dummy); +return get_kernel_nofault ((unsigned long *)p, dummy); }static void dump_pagetable (unsigned long address)
arch/x86/pci/pcbios.c +1 -1
@@ -302,7 +302,7 @@ static const struct pci_raw_ops *__init pci_find_bios(void) check <= (union bios32 *)__va (0xffff0 ); ++check) {long sig; -if (probe_kernel_address (&check->fields.signature, sig)) +if (get_kernel_nofault (&check->fields.signature, sig))continue ;if (check->fields.signature !=BIOS32_SIGNATURE )
include/linux/uaccess.h +2 -2
@@ -319,13 +319,13 @@ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr,long strnlen_user_nofault (const void __user *unsafe_addr,long count);/** -* probe_kernel_address(): safely attempt to read from a location +* get_kernel_nofault(): safely attempt to read from a location * @addr: address to read from * @retval: read into this variable * * Returns 0 on success, or -EFAULT. */ -#define probe_kernel_address (addr, retval) \ +#define get_kernel_nofault (addr, retval) \ copy_from_kernel_nofault(&retval, addr, sizeof(retval))#ifndef user_access_begin
lib/test_lockup.c +3 -3
@@ -419,8 +419,8 @@ static bool test_kernel_ptr(unsigned long addr, int size)/* should be at least readable kernel address */ if (access_ok (ptr,1 ) ||access_ok (ptr + size -1 ,1 ) || -probe_kernel_address (ptr, buf) || -probe_kernel_address (ptr + size -1 , buf)) { +get_kernel_nofault (ptr, buf) || +get_kernel_nofault (ptr + size -1 , buf)) {pr_err ("invalid kernel ptr: %#lx\n" , addr);return true; }
@@ -437,7 +437,7 @@ static bool __maybe_unused test_magic(unsigned long addr, int offset,if (!addr)return false; -if (probe_kernel_address (ptr, magic) || magic != expected) { +if (get_kernel_nofault (ptr, magic) || magic != expected) {pr_err ("invalid magic at %#lx + %#x = %#x, expected %#x\n" , addr, offset, magic, expected);return true;
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
PATCH 20/20 maccess: return -ERANGE when copy_from_kernel_nofault_allowed fails
In reply to Christoph HellwigAllow the callers to distinguish a real unmapped address vs a range that can't be probed.
--- mm/maccess.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
mm/maccess.c +4 -4
@@ -25,7 +25,7 @@ bool __weak copy_from_kernel_nofault_allowed(void *dst, const void *unsafe_src,long copy_from_kernel_nofault (void *dst,const void *src,size_t size) {if (!copy_from_kernel_nofault_allowed (dst, src, size)) -return -EFAULT ; +return -ERANGE ;pagefault_disable ();copy_from_kernel_nofault_loop (dst, src, size, u64, Efault);
@@ -69,7 +69,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)if (unlikely (count <=0 ))return 0 ;if (!copy_from_kernel_nofault_allowed (dst, unsafe_addr, count)) -return -EFAULT ; +return -ERANGE ;pagefault_disable (); do {
@@ -107,7 +107,7 @@ long copy_from_kernel_nofault(void *dst, const void *src, size_t size)mm_segment_t old_fs =get_fs ();if (!copy_from_kernel_nofault_allowed (dst, src, size)) -return -EFAULT ; +return -ERANGE ;set_fs (KERNEL_DS );pagefault_disable ();
@@ -174,7 +174,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)if (unlikely (count <=0 ))return 0 ;if (!copy_from_kernel_nofault_allowed (dst, unsafe_addr, count)) -return -EFAULT ; +return -ERANGE ;set_fs (KERNEL_DS );pagefault_disable ();
Signature · 7 lines
2.26.2 _______________________________________________ linux-um mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-um
Re: [PATCH 20/20] maccess: return -ERANGE when copy_from_kernel_nofault_allowed fails
Quoted 5 lines · On Tue, 19 May 2020 15:44:49 +0200 Christoph Hellwig <[email protected]> wrote:
Allow the callers to distinguish a real unmapped address vs a range that can't be probed.
Suggested-by Masami Hiramatsu <[email protected]>Signed-off-by Christoph Hellwig <[email protected]>
Hi Christoph,
Can you also update the kerneldoc comment too?
Other than that, this looks good to me.
Thank you!
Quoted 47 lines
--- mm/maccess.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)mm/maccess.c +4
-4@@ -25,7 +25,7 @@ bool __weak copy_from_kernel_nofault_allowed(void *dst, const void *unsafe_src,long copy_from_kernel_nofault (void *dst,const void *src,size_t size) {if (!copy_from_kernel_nofault_allowed (dst, src, size)) -return -EFAULT ; +return -ERANGE ;pagefault_disable ();copy_from_kernel_nofault_loop (dst, src, size, u64, Efault);@@ -69,7 +69,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)if (unlikely (count <=0 ))return 0 ;if (!copy_from_kernel_nofault_allowed (dst, unsafe_addr, count)) -return -EFAULT ; +return -ERANGE ;pagefault_disable (); do {@@ -107,7 +107,7 @@ long copy_from_kernel_nofault(void *dst, const void *src, size_t size)mm_segment_t old_fs =get_fs ();if (!copy_from_kernel_nofault_allowed (dst, src, size)) -return -EFAULT ; +return -ERANGE ;set_fs (KERNEL_DS );pagefault_disable ();@@ -174,7 +174,7 @@ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count)if (unlikely (count <=0 ))return 0 ;if (!copy_from_kernel_nofault_allowed (dst, unsafe_addr, count)) -return -EFAULT ; +return -ERANGE ;set_fs (KERNEL_DS );pagefault_disable ();Signature · 1 line
2.26.2
Signature · 1 line
Masami Hiramatsu <[email protected]>
Re: [PATCH 20/20] maccess: return -ERANGE when copy_from_kernel_nofault_allowed fails
Quoted 1 line · Masami Hiramatsu
Can you also update the kerneldoc comment too?
Sure, done.
Quoted 2 lines · Christoph Hellwig
- rebased on 5.7-rc6 with the bpf trace format string changes
Other than the critique about illegible conditionals in the result when doing that bpf/trace conversion, I like it.
Linus