summaryrefslogtreecommitdiffstats
path: root/tools/include
diff options
context:
space:
mode:
authorDaniel Borkmann <daniel@iogearbox.net>2019-11-02 00:17:59 +0100
committerAlexei Starovoitov <ast@kernel.org>2019-11-02 12:39:12 -0700
commit6ae08ae3dea2cfa03dd3665a3c8475c2d429ef47 (patch)
tree7d89f1cc7074ea3cec0e35ab80490f653894dc72 /tools/include
parenteb1b66887472eaa7342305b7890ae510dd9d1a79 (diff)
downloadlinux-6ae08ae3dea2cfa03dd3665a3c8475c2d429ef47.tar.gz
linux-6ae08ae3dea2cfa03dd3665a3c8475c2d429ef47.tar.bz2
linux-6ae08ae3dea2cfa03dd3665a3c8475c2d429ef47.zip
bpf: Add probe_read_{user, kernel} and probe_read_{user, kernel}_str helpers
The current bpf_probe_read() and bpf_probe_read_str() helpers are broken in that they assume they can be used for probing memory access for kernel space addresses /as well as/ user space addresses. However, plain use of probe_kernel_read() for both cases will attempt to always access kernel space address space given access is performed under KERNEL_DS and some archs in-fact have overlapping address spaces where a kernel pointer and user pointer would have the /same/ address value and therefore accessing application memory via bpf_probe_read{,_str}() would read garbage values. Lets fix BPF side by making use of recently added 3d7081822f7f ("uaccess: Add non-pagefault user-space read functions"). Unfortunately, the only way to fix this status quo is to add dedicated bpf_probe_read_{user,kernel}() and bpf_probe_read_{user,kernel}_str() helpers. The bpf_probe_read{,_str}() helpers are kept as-is to retain their current behavior. The two *_user() variants attempt the access always under USER_DS set, the two *_kernel() variants will -EFAULT when accessing user memory if the underlying architecture has non-overlapping address ranges, also avoiding throwing the kernel warning via 00c42373d397 ("x86-64: add warning for non-canonical user access address dereferences"). Fixes: a5e8c07059d0 ("bpf: add bpf_probe_read_str helper") Fixes: 2541517c32be ("tracing, perf: Implement BPF programs attached to kprobes") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/796ee46e948bc808d54891a1108435f8652c6ca4.1572649915.git.daniel@iogearbox.net
Diffstat (limited to 'tools/include')
-rw-r--r--tools/include/uapi/linux/bpf.h122
1 files changed, 82 insertions, 40 deletions
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index a6bf19dabaab..df6809a76404 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -563,10 +563,13 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read(void *dst, u32 size, const void *src)
+ * int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr)
* Description
* For tracing programs, safely attempt to read *size* bytes from
- * address *src* and store the data in *dst*.
+ * kernel space address *unsafe_ptr* and store the data in *dst*.
+ *
+ * Generally, use bpf_probe_read_user() or bpf_probe_read_kernel()
+ * instead.
* Return
* 0 on success, or a negative error in case of failure.
*
@@ -1428,45 +1431,14 @@ union bpf_attr {
* Return
* 0 on success, or a negative error in case of failure.
*
- * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr)
+ * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr)
* Description
- * Copy a NUL terminated string from an unsafe address
- * *unsafe_ptr* to *dst*. The *size* should include the
- * terminating NUL byte. In case the string length is smaller than
- * *size*, the target is not padded with further NUL bytes. If the
- * string length is larger than *size*, just *size*-1 bytes are
- * copied and the last byte is set to NUL.
- *
- * On success, the length of the copied string is returned. This
- * makes this helper useful in tracing programs for reading
- * strings, and more importantly to get its length at runtime. See
- * the following snippet:
- *
- * ::
- *
- * SEC("kprobe/sys_open")
- * void bpf_sys_open(struct pt_regs *ctx)
- * {
- * char buf[PATHLEN]; // PATHLEN is defined to 256
- * int res = bpf_probe_read_str(buf, sizeof(buf),
- * ctx->di);
- *
- * // Consume buf, for example push it to
- * // userspace via bpf_perf_event_output(); we
- * // can use res (the string length) as event
- * // size, after checking its boundaries.
- * }
- *
- * In comparison, using **bpf_probe_read()** helper here instead
- * to read the string would require to estimate the length at
- * compile time, and would often result in copying more memory
- * than necessary.
+ * Copy a NUL terminated string from an unsafe kernel address
+ * *unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for
+ * more details.
*
- * Another useful use case is when parsing individual process
- * arguments or individual environment variables navigating
- * *current*\ **->mm->arg_start** and *current*\
- * **->mm->env_start**: using this helper and the return value,
- * one can quickly iterate at the right offset of the memory area.
+ * Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str()
+ * instead.
* Return
* On success, the strictly positive length of the string,
* including the trailing NUL character. On error, a negative
@@ -2777,6 +2749,72 @@ union bpf_attr {
* restricted to raw_tracepoint bpf programs.
* Return
* 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Safely attempt to read *size* bytes from user space address
+ * *unsafe_ptr* and store the data in *dst*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Safely attempt to read *size* bytes from kernel space address
+ * *unsafe_ptr* and store the data in *dst*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Copy a NUL terminated string from an unsafe user address
+ * *unsafe_ptr* to *dst*. The *size* should include the
+ * terminating NUL byte. In case the string length is smaller than
+ * *size*, the target is not padded with further NUL bytes. If the
+ * string length is larger than *size*, just *size*-1 bytes are
+ * copied and the last byte is set to NUL.
+ *
+ * On success, the length of the copied string is returned. This
+ * makes this helper useful in tracing programs for reading
+ * strings, and more importantly to get its length at runtime. See
+ * the following snippet:
+ *
+ * ::
+ *
+ * SEC("kprobe/sys_open")
+ * void bpf_sys_open(struct pt_regs *ctx)
+ * {
+ * char buf[PATHLEN]; // PATHLEN is defined to 256
+ * int res = bpf_probe_read_user_str(buf, sizeof(buf),
+ * ctx->di);
+ *
+ * // Consume buf, for example push it to
+ * // userspace via bpf_perf_event_output(); we
+ * // can use res (the string length) as event
+ * // size, after checking its boundaries.
+ * }
+ *
+ * In comparison, using **bpf_probe_read_user()** helper here
+ * instead to read the string would require to estimate the length
+ * at compile time, and would often result in copying more memory
+ * than necessary.
+ *
+ * Another useful use case is when parsing individual process
+ * arguments or individual environment variables navigating
+ * *current*\ **->mm->arg_start** and *current*\
+ * **->mm->env_start**: using this helper and the return value,
+ * one can quickly iterate at the right offset of the memory area.
+ * Return
+ * On success, the strictly positive length of the string,
+ * including the trailing NUL character. On error, a negative
+ * value.
+ *
+ * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr)
+ * Description
+ * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr*
+ * to *dst*. Same semantics as with bpf_probe_read_user_str() apply.
+ * Return
+ * On success, the strictly positive length of the string, including
+ * the trailing NUL character. On error, a negative value.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -2890,7 +2928,11 @@ union bpf_attr {
FN(sk_storage_delete), \
FN(send_signal), \
FN(tcp_gen_syncookie), \
- FN(skb_output),
+ FN(skb_output), \
+ FN(probe_read_user), \
+ FN(probe_read_kernel), \
+ FN(probe_read_user_str), \
+ FN(probe_read_kernel_str),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call