From: Arnd Bergmann arnd@arndb.de
commit 36903abedfe8d419e90ce349b2b4ce6dc2883e17 upstream.
The __range_not_ok() helper is an x86 (and sparc64) specific interface that does roughly the same thing as __access_ok(), but with different calling conventions.
Change this to use the normal interface in order for consistency as we clean up all access_ok() implementations.
This changes the limit from TASK_SIZE to TASK_SIZE_MAX, which Al points out is the right thing do do here anyway.
The callers have to use __access_ok() instead of the normal access_ok() though, because on x86 that contains a WARN_ON_IN_IRQ() check that cannot be used inside of NMI context while tracing.
The check in copy_code() is not needed any more, because this one is already done by copy_from_user_nmi().
Suggested-by: Al Viro viro@zeniv.linux.org.uk Suggested-by: Christoph Hellwig hch@infradead.org Link: https://lore.kernel.org/lkml/YgsUKcXGR7r4nINj@zeniv-ca.linux.org.uk/ Signed-off-by: Arnd Bergmann arnd@arndb.de Stable-dep-of: d319f344561d ("mm: Fix copy_from_user_nofault().") Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@igalia.com --- arch/x86/events/core.c | 2 +- arch/x86/include/asm/uaccess.h | 10 ++++++---- arch/x86/kernel/dumpstack.c | 6 ------ arch/x86/kernel/stacktrace.c | 2 +- arch/x86/lib/usercopy.c | 2 +- 5 files changed, 9 insertions(+), 13 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 9a77c6062c24..fdf1e2aaa5ed 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2790,7 +2790,7 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re static inline int valid_user_frame(const void __user *fp, unsigned long size) { - return (__range_not_ok(fp, size, TASK_SIZE) == 0); + return __access_ok(fp, size); }
static unsigned long get_segment_base(unsigned int segment) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 3616fd4ba395..66284ac86076 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -16,8 +16,10 @@ * Test whether a block of memory is a valid user space address. * Returns 0 if the range is valid, nonzero otherwise. */ -static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, unsigned long limit) +static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size) { + unsigned long limit = TASK_SIZE_MAX; + /* * If we have used "sizeof()" for the size, * we know it won't overflow the limit (but @@ -35,10 +37,10 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un return unlikely(addr > limit); }
-#define __range_not_ok(addr, size, limit) \ +#define __access_ok(addr, size) \ ({ \ __chk_user_ptr(addr); \ - __chk_range_not_ok((unsigned long __force)(addr), size, limit); \ + !__chk_range_not_ok((unsigned long __force)(addr), size); \ })
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP @@ -69,7 +71,7 @@ static inline bool pagefault_disabled(void); #define access_ok(addr, size) \ ({ \ WARN_ON_IN_IRQ(); \ - likely(!__range_not_ok(addr, size, TASK_SIZE_MAX)); \ + likely(__access_ok(addr, size)); \ })
extern int __get_user_1(void); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 8a8660074284..bf73dbfb2355 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -81,12 +81,6 @@ static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src, /* The user space code from other tasks cannot be accessed. */ if (regs != task_pt_regs(current)) return -EPERM; - /* - * Make sure userspace isn't trying to trick us into dumping kernel - * memory by pointing the userspace instruction pointer at it. - */ - if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX)) - return -EINVAL;
/* * Even if named copy_from_user_nmi() this can be invoked from diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 15b058eefc4e..ee117fcf46ed 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -90,7 +90,7 @@ copy_stack_frame(const struct stack_frame_user __user *fp, { int ret;
- if (__range_not_ok(fp, sizeof(*frame), TASK_SIZE)) + if (!__access_ok(fp, sizeof(*frame))) return 0;
ret = 1; diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c index c3e8a62ca561..ad0139d25401 100644 --- a/arch/x86/lib/usercopy.c +++ b/arch/x86/lib/usercopy.c @@ -32,7 +32,7 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n) { unsigned long ret;
- if (__range_not_ok(from, n, TASK_SIZE)) + if (!__access_ok(from, n)) return n;
if (!nmi_uaccess_okay())
From: Alexei Starovoitov ast@kernel.org
commit d319f344561de23e810515d109c7278919bff7b0 upstream.
There are several issues with copy_from_user_nofault():
- access_ok() is designed for user context only and for that reason it has WARN_ON_IN_IRQ() which triggers when bpf, kprobe, eprobe and perf on ppc are calling it from irq.
- it's missing nmi_uaccess_okay() which is a nop on all architectures except x86 where it's required. The comment in arch/x86/mm/tlb.c explains the details why it's necessary. Calling copy_from_user_nofault() from bpf, [ke]probe without this check is not safe.
- __copy_from_user_inatomic() under CONFIG_HARDENED_USERCOPY is calling check_object_size()->__check_object_size()->check_heap_object()->find_vmap_area()->spin_lock() which is not safe to do from bpf, [ke]probe and perf due to potential deadlock.
Fix all three issues. At the end the copy_from_user_nofault() becomes equivalent to copy_from_user_nmi() from safety point of view with a difference in the return value.
Reported-by: Hsin-Wei Hung hsinweih@uci.edu Signed-off-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Florian Lehner dev@der-flo.net Tested-by: Hsin-Wei Hung hsinweih@uci.edu Tested-by: Florian Lehner dev@der-flo.net Link: https://lore.kernel.org/r/20230410174345.4376-2-dev@der-flo.net Signed-off-by: Alexei Starovoitov ast@kernel.org [cascardo: the test in check_heap_objects did not exist] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@igalia.com --- mm/maccess.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)
diff --git a/mm/maccess.c b/mm/maccess.c index ded4bfaba7f3..02f87fad4336 100644 --- a/mm/maccess.c +++ b/mm/maccess.c @@ -5,6 +5,7 @@ #include <linux/export.h> #include <linux/mm.h> #include <linux/uaccess.h> +#include <asm/tlb.h>
bool __weak copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) @@ -223,11 +224,16 @@ long copy_from_user_nofault(void *dst, const void __user *src, size_t size) long ret = -EFAULT; mm_segment_t old_fs = force_uaccess_begin();
- if (access_ok(src, size)) { - pagefault_disable(); - ret = __copy_from_user_inatomic(dst, src, size); - pagefault_enable(); - } + if (!__access_ok(src, size)) + return ret; + + if (!nmi_uaccess_okay()) + return ret; + + pagefault_disable(); + ret = __copy_from_user_inatomic(dst, src, size); + pagefault_enable(); + force_uaccess_end(old_fs);
if (ret)
linux-stable-mirror@lists.linaro.org
-
Thadeu Lima de Souza Cascardo