From: Christoph Hellwig <hch@lst.de>
To: x86@kernel.org, Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Masami Hiramatsu <mhiramat@kernel.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
Andrew Morton <akpm@linux-foundation.org>
Cc: linux-parisc@vger.kernel.org, linux-um@lists.infradead.org,
netdev@vger.kernel.org, bpf@vger.kernel.org, linux-mm@kvack.org,
linux-kernel@vger.kernel.org
Subject: [PATCH 12/18] maccess: always use strict semantics for probe_kernel_read
Date: Wed, 13 May 2020 18:00:32 +0200 [thread overview]
Message-ID: <20200513160038.2482415-13-hch@lst.de> (raw)
In-Reply-To: <20200513160038.2482415-1-hch@lst.de>
Except 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. Make the tracers fall back to a probe_user_read
if the probe_kernel_read falls to keep the core API clean.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
---
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 | 20 +++++++++++++------
kernel/trace/trace_kprobe.c | 11 ++++++++++-
mm/maccess.c | 39 ++++++-------------------------------
7 files changed, 34 insertions(+), 51 deletions(-)
diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c
index 5ef648bd33119..9fe662b3b5604 100644
--- a/arch/parisc/lib/memcpy.c
+++ b/arch/parisc/lib/memcpy.c
@@ -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;
diff --git a/arch/um/kernel/maccess.c b/arch/um/kernel/maccess.c
index 90a1bec923158..734f3d7e57c0f 100644
--- a/arch/um/kernel/maccess.c
+++ b/arch/um/kernel/maccess.c
@@ -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);
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
index 5c323ab187b27..a1bd81677aa72 100644
--- a/arch/x86/mm/maccess.c
+++ b/arch/x86/mm/maccess.c
@@ -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);
}
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 28944a14e0534..78e0ff8641559 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -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);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0d849acc9de38..5dea4169a8323 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -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);
- if (unlikely(ret < 0))
-out:
- memset(dst, 0, size);
+ goto fail;
+
+ ret = probe_kernel_read(dst, unsafe_ptr, size);
+ if (unlikely(ret < 0)) {
+ if (compat)
+ ret = probe_user_read(dst, user_ptr, size);
+ if (unlikely(ret < 0))
+ goto fail;
+ }
+
+ return 0;
+fail:
+ memset(dst, 0, size);
return ret;
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 8c456e30933d3..7725146369731 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1209,6 +1209,9 @@ fetch_store_strlen(unsigned long addr)
do {
ret = probe_kernel_read(&c, (u8 *)addr + len, 1);
+ if (ret)
+ ret = probe_user_read(&c,
+ (__force u8 __user *)addr + len, 1);
len++;
} while (c && ret == 0 && len < MAX_STRING_SIZE);
@@ -1281,7 +1284,13 @@ fetch_store_string_user(unsigned long addr, void *dest, void *base)
static nokprobe_inline int
probe_mem_read(void *dest, void *src, size_t size)
{
- return probe_kernel_read(dest, src, size);
+ const void __user *user_ptr = (__force const void __user *)src;
+ int ret;
+
+ ret = probe_kernel_read(dest, src, size);
+ if (ret)
+ ret = probe_user_read(dest, user_ptr, size);
+ return ret;
}
static nokprobe_inline int
diff --git a/mm/maccess.c b/mm/maccess.c
index 3d85e48013e6b..05c44d490b4e3 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -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);
--
2.26.2
next prev parent reply other threads:[~2020-05-13 16:02 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-13 16:00 clean up and streamline probe_kernel_* and friends v2 Christoph Hellwig
2020-05-13 16:00 ` [PATCH 01/18] maccess: unexport probe_kernel_write and probe_user_write Christoph Hellwig
2020-05-13 16:00 ` [PATCH 02/18] maccess: remove various unused weak aliases Christoph Hellwig
2020-05-13 16:00 ` [PATCH 03/18] maccess: remove duplicate kerneldoc comments Christoph Hellwig
2020-05-13 16:00 ` [PATCH 04/18] maccess: clarify " Christoph Hellwig
2020-05-13 16:00 ` [PATCH 05/18] maccess: update the top of file comment Christoph Hellwig
2020-05-13 16:00 ` [PATCH 06/18] maccess: rename strncpy_from_unsafe_user to strncpy_from_user_nofault Christoph Hellwig
2020-05-13 16:00 ` [PATCH 07/18] maccess: rename strncpy_from_unsafe_strict to strncpy_from_kernel_nofault Christoph Hellwig
2020-05-13 16:00 ` [PATCH 08/18] maccess: rename strnlen_unsafe_user to strnlen_user_nofault Christoph Hellwig
2020-05-13 16:00 ` [PATCH 09/18] maccess: remove probe_read_common and probe_write_common Christoph Hellwig
2020-05-13 16:00 ` [PATCH 10/18] maccess: unify the probe kernel arch hooks Christoph Hellwig
2020-05-14 1:13 ` Masami Hiramatsu
2020-05-19 5:46 ` Christoph Hellwig
2020-05-13 16:00 ` [PATCH 11/18] maccess: remove strncpy_from_unsafe Christoph Hellwig
2020-05-13 19:11 ` Linus Torvalds
2020-05-13 19:28 ` Christoph Hellwig
2020-05-13 22:36 ` Daniel Borkmann
2020-05-13 23:03 ` Linus Torvalds
2020-05-13 23:24 ` Daniel Borkmann
2020-05-13 23:20 ` Masami Hiramatsu
2020-05-13 23:59 ` Linus Torvalds
2020-05-14 1:00 ` Masami Hiramatsu
2020-05-14 2:43 ` Linus Torvalds
2020-05-14 9:44 ` Masami Hiramatsu
2020-05-14 10:27 ` Daniel Borkmann
2020-05-13 23:28 ` Al Viro
2020-05-13 23:58 ` Daniel Borkmann
2020-05-14 10:01 ` David Laight
2020-05-14 10:21 ` Daniel Borkmann
2020-05-13 16:00 ` Christoph Hellwig [this message]
2020-05-13 16:00 ` [PATCH 13/18] maccess: move user access routines together Christoph Hellwig
2020-05-13 16:00 ` [PATCH 14/18] maccess: allow architectures to provide kernel probing directly Christoph Hellwig
2020-05-13 19:36 ` Linus Torvalds
2020-05-13 19:40 ` Christoph Hellwig
2020-05-13 19:48 ` Linus Torvalds
2020-05-13 19:54 ` Christoph Hellwig
2020-05-16 3:42 ` Masami Hiramatsu
2020-05-18 15:09 ` Christoph Hellwig
2020-05-13 16:00 ` [PATCH 15/18] x86: use non-set_fs based maccess routines Christoph Hellwig
2020-05-13 16:00 ` [PATCH 16/18] maccess: rename probe_kernel_{read,write} to copy_{from,to}_kernel_nofault Christoph Hellwig
2020-05-13 16:00 ` [PATCH 17/18] maccess: rename probe_user_{read,write} to copy_{from,to}_user_nofault Christoph Hellwig
2020-05-13 16:00 ` [PATCH 18/18] maccess: rename probe_kernel_address to get_kernel_nofault Christoph Hellwig
2020-05-13 19:37 ` clean up and streamline probe_kernel_* and friends v2 Linus Torvalds
2020-05-13 23:04 ` Daniel Borkmann
2020-05-13 23:20 ` Linus Torvalds
2020-05-19 5:50 ` Christoph Hellwig
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200513160038.2482415-13-hch@lst.de \
--to=hch@lst.de \
--cc=akpm@linux-foundation.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-parisc@vger.kernel.org \
--cc=linux-um@lists.infradead.org \
--cc=mhiramat@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=torvalds@linux-foundation.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).