| 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: <20120917003630.124045394@decadent.org.uk>
Date: Mon, 17 Sep 2012 01:36:53 +0100
From: Ben Hutchings <ben@...adent.org.uk>
To: linux-kernel@...r.kernel.org, stable@...r.kernel.org
Cc: torvalds@...ux-foundation.org, akpm@...ux-foundation.org,
alan@...rguk.ukuu.org.uk, Bruce Allan <bruce.w.allan@...el.com>,
Ben Hutchings <bhutchings@...arflare.com>,
Aaron Brown <aaron.f.brown@...el.com>,
Jeff Kirsher <jeffrey.t.kirsher@...el.com>,
"David S. Miller" <davem@...emloft.net>
Subject: [ 028/135] e1000e: DoS while TSO enabled caused by link partner with small MSS
3.2-stable review patch. If anyone has any objections, please let me know.
I was able to test the backported fix myself, having found the bug in the
first place.
------------------
From: Bruce Allan <bruce.w.allan@...el.com>
commit d821a4c4d11ad160925dab2bb009b8444beff484 upstream.
With a low enough MSS on the link partner and TSO enabled locally, the
networking stack can periodically send a very large (e.g. 64KB) TCP
message for which the driver will attempt to use more Tx descriptors than
are available by default in the Tx ring. This is due to a workaround in
the code that imposes a limit of only 4 MSS-sized segments per descriptor
which appears to be a carry-over from the older e1000 driver and may be
applicable only to some older PCI or PCIx parts which are not supported in
e1000e. When the driver gets a message that is too large to fit across the
configured number of Tx descriptors, it stops the upper stack from queueing
any more and gets stuck in this state. After a timeout, the upper stack
assumes the adapter is hung and calls the driver to reset it.
Remove the unnecessary limitation of using up to only 4 MSS-sized segments
per Tx descriptor, and put in a hard failure test to catch when attempting
to check for message sizes larger than would fit in the whole Tx ring.
Refactor the remaining logic that limits the size of data per Tx descriptor
from a seemingly arbitrary 8KB to a limit based on the dynamic size of the
Tx packet buffer as described in the hardware specification.
Also, fix the logic in the check for space in the Tx ring for the next
largest possible packet after the current one has been successfully queued
for transmit, and use the appropriate defines for default ring sizes in
e1000_probe instead of magic values.
This issue goes back to the introduction of e1000e in 2.6.24 when it was
split off from e1000.
Reported-by: Ben Hutchings <bhutchings@...arflare.com>
Signed-off-by: Bruce Allan <bruce.w.allan@...el.com>
Tested-by: Aaron Brown <aaron.f.brown@...el.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@...el.com>
Signed-off-by: David S. Miller <davem@...emloft.net>
[bwh: Backported to 3.2:
- Adjust context
- Adjust for use of net_device vs e1000_ring parameter]
Signed-off-by: Ben Hutchings <ben@...adent.org.uk>
---
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -302,6 +302,7 @@ struct e1000_adapter {
*/
struct e1000_ring *tx_ring /* One per active queue */
____cacheline_aligned_in_smp;
+ u32 tx_fifo_limit;
struct napi_struct napi;
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -3386,6 +3386,15 @@ void e1000e_reset(struct e1000_adapter *
}
/*
+ * Alignment of Tx data is on an arbitrary byte boundary with the
+ * maximum size per Tx descriptor limited only to the transmit
+ * allocation of the packet buffer minus 96 bytes with an upper
+ * limit of 24KB due to receive synchronization limitations.
+ */
+ adapter->tx_fifo_limit = min_t(u32, ((er32(PBA) >> 16) << 10) - 96,
+ 24 << 10);
+
+ /*
* Disable Adaptive Interrupt Moderation if 2 full packets cannot
* fit in receive buffer and early-receive not supported.
*/
@@ -4647,13 +4656,9 @@ static bool e1000_tx_csum(struct e1000_a
return 1;
}
-#define E1000_MAX_PER_TXD 8192
-#define E1000_MAX_TXD_PWR 12
-
static int e1000_tx_map(struct e1000_adapter *adapter,
struct sk_buff *skb, unsigned int first,
- unsigned int max_per_txd, unsigned int nr_frags,
- unsigned int mss)
+ unsigned int max_per_txd, unsigned int nr_frags)
{
struct e1000_ring *tx_ring = adapter->tx_ring;
struct pci_dev *pdev = adapter->pdev;
@@ -4882,20 +4887,19 @@ static int e1000_maybe_stop_tx(struct ne
{
struct e1000_adapter *adapter = netdev_priv(netdev);
+ BUG_ON(size > adapter->tx_ring->count);
+
if (e1000_desc_unused(adapter->tx_ring) >= size)
return 0;
return __e1000_maybe_stop_tx(netdev, size);
}
-#define TXD_USE_COUNT(S, X) (((S) >> (X)) + 1 )
static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
struct net_device *netdev)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_ring *tx_ring = adapter->tx_ring;
unsigned int first;
- unsigned int max_per_txd = E1000_MAX_PER_TXD;
- unsigned int max_txd_pwr = E1000_MAX_TXD_PWR;
unsigned int tx_flags = 0;
unsigned int len = skb_headlen(skb);
unsigned int nr_frags;
@@ -4915,18 +4919,8 @@ static netdev_tx_t e1000_xmit_frame(stru
}
mss = skb_shinfo(skb)->gso_size;
- /*
- * The controller does a simple calculation to
- * make sure there is enough room in the FIFO before
- * initiating the DMA for each buffer. The calc is:
- * 4 = ceil(buffer len/mss). To make sure we don't
- * overrun the FIFO, adjust the max buffer len if mss
- * drops.
- */
if (mss) {
u8 hdr_len;
- max_per_txd = min(mss << 2, max_per_txd);
- max_txd_pwr = fls(max_per_txd) - 1;
/*
* TSO Workaround for 82571/2/3 Controllers -- if skb->data
@@ -4956,12 +4950,12 @@ static netdev_tx_t e1000_xmit_frame(stru
count++;
count++;
- count += TXD_USE_COUNT(len, max_txd_pwr);
+ count += DIV_ROUND_UP(len, adapter->tx_fifo_limit);
nr_frags = skb_shinfo(skb)->nr_frags;
for (f = 0; f < nr_frags; f++)
- count += TXD_USE_COUNT(skb_frag_size(&skb_shinfo(skb)->frags[f]),
- max_txd_pwr);
+ count += DIV_ROUND_UP(skb_frag_size(&skb_shinfo(skb)->frags[f]),
+ adapter->tx_fifo_limit);
if (adapter->hw.mac.tx_pkt_filtering)
e1000_transfer_dhcp_info(adapter, skb);
@@ -5000,12 +4994,15 @@ static netdev_tx_t e1000_xmit_frame(stru
tx_flags |= E1000_TX_FLAGS_IPV4;
/* if count is 0 then mapping error has occurred */
- count = e1000_tx_map(adapter, skb, first, max_per_txd, nr_frags, mss);
+ count = e1000_tx_map(adapter, skb, first, adapter->tx_fifo_limit,
+ nr_frags);
if (count) {
e1000_tx_queue(adapter, tx_flags, count);
/* Make sure there is space in the ring for the next send. */
- e1000_maybe_stop_tx(netdev, MAX_SKB_FRAGS + 2);
-
+ e1000_maybe_stop_tx(netdev,
+ (MAX_SKB_FRAGS *
+ DIV_ROUND_UP(PAGE_SIZE,
+ adapter->tx_fifo_limit) + 2));
} else {
dev_kfree_skb_any(skb);
tx_ring->buffer_info[first].time_stamp = 0;
@@ -6150,8 +6147,8 @@ static int __devinit e1000_probe(struct
adapter->hw.phy.autoneg_advertised = 0x2f;
/* ring size defaults */
- adapter->rx_ring->count = 256;
- adapter->tx_ring->count = 256;
+ adapter->rx_ring->count = E1000_DEFAULT_RXD;
+ adapter->tx_ring->count = E1000_DEFAULT_TXD;
/*
* Initial Wake on LAN setting - If APM wake is enabled in
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists