| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <a186d9c79aa12ed072eb11bbd20ae5c49eddb700.1310339688.git.mirq-linux@rere.qmqm.pl>
Date: Mon, 11 Jul 2011 02:52:46 +0200 (CEST)
From: Michał Mirosław <mirq-linux@...e.qmqm.pl>
To: netdev@...r.kernel.org
Subject: [PATCH v2 02/46] net: wrap common patterns of rx handler code
Introduce dev_skb_finish_rx_dma() and dev_skb_finish_rx_dma_refill() ---
two common patterns for rx handling as seen in various network drivers
that implement rx_copybreak idea (copying smaller packets, passing larger
ones in original skb).
The common pattern (as implemented in dev_skb_finish_rx_dma()) is:
if (packet len < threshold)
allocate new, smaller skb
sync DMA buffer to cpu
copy packet's data
give DMA buffer back to device
pass new skb
reuse buffer in rx ring
else (or if skb alloc for copy failed)
unmap DMA buffer
pass skb
remove buffer from rx ring
[refill rx ring later]
This scheme is modified by some drivers to immediately refill rx slot before
passing original rx skb up the stack. Those drivers have also a problem that
they drop packets from the head of the queue when that allocation fails. This
forces unnecessary retransmits and can deadlock if the device is used for
swapping over network. To mark this case, dev_skb_finish_rx_dma_refill()
implementing it, is marked as deprecated to encourage driver maintainers to
look into the matter.
Those functions are called from rx handler hot path and have a lot of arguments,
and so are inlined. This should allow compiler to better optimize the code with
calling code.
v2:
- remove unnecessary dma_sync_single_for_device()
[See: DMA-API.txt, part. Id, DMA_FROM_DEVICE description]
- check dma_mapping_error() in dev_skb_finish_rx_dma_refill()
- handle RX_OFFSET (padding inserted by hardware before packet's data)
Signed-off-by: Michał Mirosław <mirq-linux@...e.qmqm.pl>
---
include/linux/skbuff.h | 142 ++++++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 142 insertions(+), 0 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c873897..bf51006 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -29,6 +29,7 @@
#include <linux/rcupdate.h>
#include <linux/dmaengine.h>
#include <linux/hrtimer.h>
+#include <linux/dma-mapping.h>
/* Don't change this without changing skb_csum_unnecessary! */
#define CHECKSUM_NONE 0
@@ -2310,5 +2311,146 @@ static inline void skb_checksum_none_assert(struct sk_buff *skb)
bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off);
+/**
+ * __dev_skb_finish_rx_dma - finish skb after DMA'd RX
+ * @skb: skb to finish
+ * @len: packet data length
+ * @copybreak: maximum packet size to copy
+ * @rx_offset: count of bytes prepended to packet's data by hardware
+ * @dma_dev: device used for DMA
+ * @dma_buf: DMA mapping address
+ * @dma_len: DMA mapping length
+ *
+ * This function finishes DMA mapping (sync for copied, unmap otherwise) for
+ * a packet and copies it to new skb if its size is at or below @copybreak
+ * threshold.
+ *
+ * Returns new skb or NULL if the copy wasn't made.
+ */
+static inline struct sk_buff *__dev_skb_finish_rx_dma(struct sk_buff *skb,
+ unsigned int len, unsigned int copybreak, unsigned int rx_offset,
+ struct device *dma_dev, dma_addr_t dma_buf, size_t dma_len)
+{
+ if (len < copybreak) {
+ struct sk_buff *skb2 = netdev_alloc_skb_ip_align(skb->dev, len);
+ if (likely(skb2)) {
+ dma_sync_single_for_cpu(dma_dev, dma_buf,
+ len + rx_offset, DMA_FROM_DEVICE);
+ skb_copy_to_linear_data(skb2, skb->data, len);
+ return skb2;
+ }
+ }
+
+ /* else or copy failed */
+
+ dma_unmap_single(dma_dev, dma_buf, dma_len, DMA_FROM_DEVICE);
+ return NULL;
+}
+
+/**
+ * dev_skb_finish_rx_dma - finish skb after DMA'd RX
+ * @pskb: pointer to variable holding skb to finish
+ * @len: packet data length
+ * @copybreak: maximum packet size to copy
+ * @rx_offset: count of bytes prepended to packet's data by hardware
+ * @dma_dev: device used for DMA
+ * @dma_buf: DMA mapping address
+ * @dma_len: DMA mapping length
+ *
+ * This function finishes DMA mapping (sync for copied, unmap otherwise) for
+ * a packet and copies it to new skb if its size is at or below @copybreak
+ * threshold. Like __dev_skb_finish_rx_dma().
+ *
+ * Returns the skb - old or copied. *pskb is cleared if the skb wasn't copied.
+ */
+static inline struct sk_buff *dev_skb_finish_rx_dma(struct sk_buff **pskb,
+ unsigned int len, unsigned int copybreak, unsigned int rx_offset,
+ struct device *dma_dev, dma_addr_t dma_buf, size_t dma_len)
+{
+ struct sk_buff *skb2;
+
+ skb2 = __dev_skb_finish_rx_dma(*pskb, len, copybreak, rx_offset,
+ dma_dev, dma_buf, dma_len);
+
+ if (!skb2) {
+ /* not copied */
+ skb2 = *pskb;
+ *pskb = NULL;
+ }
+
+ skb_put(skb2, len);
+ return skb2;
+}
+
+/**
+ * dev_skb_finish_rx_dma_refill - finish skb after DMA'd RX and refill the slot
+ * @pskb: pointer to variable holding skb to finish
+ * @len: packet data length
+ * @copybreak: maximum packet size to copy
+ * @ip_align: new skb's alignment offset
+ * @rx_offset: count of bytes prepended by HW before packet's data
+ * @dma_dev: device used for DMA
+ * @dma_buf: DMA mapping address
+ * @dma_len: DMA mapping length
+ * @dma_align: required DMA buffer alignment for new skbs
+ *
+ * This function finishes DMA mapping (sync for copied, unmap otherwise) for
+ * a packet and copies it to new skb if its size is at or below @copybreak
+ * threshold. Like __dev_skb_finish_rx_dma().
+ *
+ * *pskb is filled with new mapped skb if the skb wasn't copied.
+ * Returns the skb - old or copied, or NULL if refill failed.
+ *
+ * NOTE:
+ * This will effectively drop the packet in case of memory pressure. This
+ * might not be wanted when swapping over network. It's better to throttle
+ * the receiver queue (refill later) as the packet might be needed to
+ * reclaim some memory.
+ */
+static inline __deprecated struct sk_buff *dev_skb_finish_rx_dma_refill(
+ struct sk_buff **pskb, unsigned int len, unsigned int copybreak,
+ unsigned int ip_align, unsigned int rx_offset,
+ struct device *dma_dev, dma_addr_t *dma_buf, size_t dma_len,
+ size_t dma_align)
+{
+ struct sk_buff *skb;
+
+ skb = __dev_skb_finish_rx_dma(*pskb, len, copybreak, rx_offset,
+ dma_dev, *dma_buf, dma_len);
+
+ if (!skb) {
+ /* not copied */
+ skb = *pskb;
+ /* netdev_alloc_skb_ip_align() */
+ *pskb = __netdev_alloc_skb_aligned(skb->dev, dma_len + ip_align,
+ dma_align, GFP_ATOMIC);
+ if (likely(*pskb))
+ skb_reserve(*pskb, ip_align + rx_offset);
+ else {
+ /* no memory - drop packet */
+ *pskb = skb;
+ skb = NULL;
+ }
+
+ *dma_buf = dma_map_single(dma_dev, (*pskb)->data - rx_offset,
+ dma_len, DMA_FROM_DEVICE);
+ if (dma_mapping_error(dma_dev, *dma_buf)) {
+ BUG_ON(!skb); /* caller can't handle this case */
+ kfree_skb(*pskb);
+ *pskb = skb;
+ skb = NULL;
+ *dma_buf = dma_map_single(dma_dev,
+ (*pskb)->data - rx_offset, dma_len,
+ DMA_FROM_DEVICE);
+ BUG_ON(dma_mapping_error(dma_dev, *dma_buf));
+ }
+ }
+
+ if (likely(skb))
+ skb_put(skb, len);
+
+ return skb;
+}
+
#endif /* __KERNEL__ */
#endif /* _LINUX_SKBUFF_H */
--
1.7.5.4
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists