aboutsummaryrefslogtreecommitdiffstats
path: root/Documentation
diff options
context:
space:
mode:
Diffstat (limited to 'Documentation')
-rw-r--r--Documentation/unaligned-memory-access.txt32
1 files changed, 29 insertions, 3 deletions
diff --git a/Documentation/unaligned-memory-access.txt b/Documentation/unaligned-memory-access.txt
index b0472ac5226a..f866c72291bf 100644
--- a/Documentation/unaligned-memory-access.txt
+++ b/Documentation/unaligned-memory-access.txt
@@ -218,9 +218,35 @@ If use of such macros is not convenient, another option is to use memcpy(),
218where the source or destination (or both) are of type u8* or unsigned char*. 218where the source or destination (or both) are of type u8* or unsigned char*.
219Due to the byte-wise nature of this operation, unaligned accesses are avoided. 219Due to the byte-wise nature of this operation, unaligned accesses are avoided.
220 220
221
222Alignment vs. Networking
223========================
224
225On architectures that require aligned loads, networking requires that the IP
226header is aligned on a four-byte boundary to optimise the IP stack. For
227regular ethernet hardware, the constant NET_IP_ALIGN is used. On most
228architectures this constant has the value 2 because the normal ethernet
229header is 14 bytes long, so in order to get proper alignment one needs to
230DMA to an address which can be expressed as 4*n + 2. One notable exception
231here is powerpc which defines NET_IP_ALIGN to 0 because DMA to unaligned
232addresses can be very expensive and dwarf the cost of unaligned loads.
233
234For some ethernet hardware that cannot DMA to unaligned addresses like
2354*n+2 or non-ethernet hardware, this can be a problem, and it is then
236required to copy the incoming frame into an aligned buffer. Because this is
237unnecessary on architectures that can do unaligned accesses, the code can be
238made dependent on CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS like so:
239
240#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
241 skb = original skb
242#else
243 skb = copy skb
244#endif
245
221-- 246--
222Author: Daniel Drake <dsd@gentoo.org> 247Authors: Daniel Drake <dsd@gentoo.org>,
248 Johannes Berg <johannes@sipsolutions.net>
223With help from: Alan Cox, Avuton Olrich, Heikki Orsila, Jan Engelhardt, 249With help from: Alan Cox, Avuton Olrich, Heikki Orsila, Jan Engelhardt,
224Johannes Berg, Kyle McMartin, Kyle Moffett, Randy Dunlap, Robert Hancock, 250Kyle McMartin, Kyle Moffett, Randy Dunlap, Robert Hancock, Uli Kunitz,
225Uli Kunitz, Vadim Lobanov 251Vadim Lobanov
226 252