bpf, events: fix offset in skb copy handler

This patch fixes the __output_custom() routine we currently use with
bpf_skb_copy(). I missed that when len is larger than the size of the
current handle, we can issue multiple invocations of copy_func, and
__output_custom() advances destination but also source buffer by the
written amount of bytes. When we have __output_custom(), this is actually
wrong since in that case the source buffer points to a non-linear object,
in our case an skb, which the copy_func helper is supposed to walk.
Therefore, since this is non-linear we thus need to pass the offset into
the helper, so that copy_func can use it for extracting the data from
the source object.

Therefore, adjust the callback signatures properly and pass offset
into the skb_header_pointer() invoked from bpf_skb_copy() callback. The
__DEFINE_OUTPUT_COPY_BODY() is adjusted to accommodate for two things:
i) to pass in whether we should advance source buffer or not; this is
a compile-time constant condition, ii) to pass in the offset for
__output_custom(), which we do with help of __VA_ARGS__, so everything
can stay inlined as is currently. Both changes allow for adapting the
__output_* fast-path helpers w/o extra overhead.

Fixes: 555c8a8623a3 ("bpf: avoid stack copy and use skb ctx for event output")
Fixes: 7e3f977edd0b ("perf, events: add non-linear data support for raw records")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 10 insertions, 5 deletions

diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 2417eb5512cd..486fd78eb8d5 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -123,18 +123,19 @@ static inline unsigned long perf_aux_size(struct ring_buffer *rb)
 	return rb->aux_nr_pages << PAGE_SHIFT;
 }
 
-#define __DEFINE_OUTPUT_COPY_BODY(memcpy_func)				\
+#define __DEFINE_OUTPUT_COPY_BODY(advance_buf, memcpy_func, ...)	\
 {									\
 	unsigned long size, written;					\
 									\
 	do {								\
 		size    = min(handle->size, len);			\
-		written = memcpy_func(handle->addr, buf, size);		\
+		written = memcpy_func(__VA_ARGS__);			\
 		written = size - written;				\
 									\
 		len -= written;						\
 		handle->addr += written;				\
-		buf += written;						\
+		if (advance_buf)					\
+			buf += written;					\
 		handle->size -= written;				\
 		if (!handle->size) {					\
 			struct ring_buffer *rb = handle->rb;		\
@@ -153,12 +154,16 @@ static inline unsigned long perf_aux_size(struct ring_buffer *rb)
 static inline unsigned long						\
 func_name(struct perf_output_handle *handle,				\
 	  const void *buf, unsigned long len)				\
-__DEFINE_OUTPUT_COPY_BODY(memcpy_func)
+__DEFINE_OUTPUT_COPY_BODY(true, memcpy_func, handle->addr, buf, size)
 
 static inline unsigned long
 __output_custom(struct perf_output_handle *handle, perf_copy_f copy_func,
 		const void *buf, unsigned long len)
-__DEFINE_OUTPUT_COPY_BODY(copy_func)
+{
+	unsigned long orig_len = len;
+	__DEFINE_OUTPUT_COPY_BODY(false, copy_func, handle->addr, buf,
+				  orig_len - len, size)
+}
 
 static inline unsigned long
 memcpy_common(void *dst, const void *src, unsigned long n)