e100/e1000*/igb*/ixgb*: Add missing read memory barrier
authorJeff Kirsher <jeffrey.t.kirsher@intel.com>
Sun, 8 Aug 2010 16:02:31 +0000 (16:02 +0000)
committerGreg Kroah-Hartman <gregkh@suse.de>
Fri, 13 Aug 2010 20:30:49 +0000 (13:30 -0700)
commit 2d0bb1c1f4524befe9f0fcf0d0cd3081a451223f upstream.

Based on patches from Sonny Rao and Milton Miller...

Combined the patches to fix up clean_tx_irq and clean_rx_irq.

The PowerPC architecture does not require loads to independent bytes
to be ordered without adding an explicit barrier.

In ixgbe_clean_rx_irq we load the status bit then load the packet data.
With packet split disabled if these loads go out of order we get a
stale packet, but we will notice the bad sequence numbers and drop it.

The problem occurs with packet split enabled where the TCP/IP header
and data are in different descriptors. If the reads go out of order
we may have data that doesn't match the TCP/IP header. Since we use
hardware checksumming this bad data is never verified and it makes it
all the way to the application.

This bug was found during stress testing and adding this barrier has
been shown to fix it.  The bug can manifest as a data integrity issue
(bad payload data) or as a BUG in skb_pull().

This was a nasty bug to hunt down, if people agree with the fix I think
it's a candidate for stable.

Previously Submitted to e1000-devel only for ixgbe

http://marc.info/?l=e1000-devel&m=126593062701537&w=3

We've now seen this problem hit with other device drivers (e1000e mostly)
So I'm resubmitting with fixes for other Intel Device Drivers with
similar issues.

CC: Milton Miller <miltonm@bga.com>
CC: Anton Blanchard <anton@samba.org>
CC: Sonny Rao <sonnyrao@us.ibm.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
drivers/net/e100.c
drivers/net/e1000/e1000_main.c
drivers/net/e1000e/netdev.c
drivers/net/igb/igb_main.c
drivers/net/igbvf/netdev.c
drivers/net/ixgb/ixgb_main.c
drivers/net/ixgbe/ixgbe_main.c
drivers/net/ixgbevf/ixgbevf_main.c

index b194bad29ace251c2f33bfe5d9845ca571af352a..8e2eab4e7c759c6f1ae82bd3ea8959050c901684 100644 (file)
@@ -1779,6 +1779,7 @@ static int e100_tx_clean(struct nic *nic)
        for (cb = nic->cb_to_clean;
            cb->status & cpu_to_le16(cb_complete);
            cb = nic->cb_to_clean = cb->next) {
+               rmb(); /* read skb after status */
                netif_printk(nic, tx_done, KERN_DEBUG, nic->netdev,
                             "cb[%d]->status = 0x%04X\n",
                             (int)(((void*)cb - (void*)nic->cbs)/sizeof(struct cb)),
@@ -1927,6 +1928,7 @@ static int e100_rx_indicate(struct nic *nic, struct rx *rx,
 
        netif_printk(nic, rx_status, KERN_DEBUG, nic->netdev,
                     "status=0x%04X\n", rfd_status);
+       rmb(); /* read size after status bit */
 
        /* If data isn't ready, nothing to indicate */
        if (unlikely(!(rfd_status & cb_complete))) {
index 68a80893dce1daa492c23f6a7e6e0dd290645046..a2680bfbc7ad57443b89a4636e168542e818f5bf 100644 (file)
@@ -3448,6 +3448,7 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter,
        while ((eop_desc->upper.data & cpu_to_le32(E1000_TXD_STAT_DD)) &&
               (count < tx_ring->count)) {
                bool cleaned = false;
+               rmb();  /* read buffer_info after eop_desc */
                for ( ; !cleaned; count++) {
                        tx_desc = E1000_TX_DESC(*tx_ring, i);
                        buffer_info = &tx_ring->buffer_info[i];
@@ -3637,6 +3638,7 @@ static bool e1000_clean_jumbo_rx_irq(struct e1000_adapter *adapter,
                if (*work_done >= work_to_do)
                        break;
                (*work_done)++;
+               rmb(); /* read descriptor and rx_buffer_info after status DD */
 
                status = rx_desc->status;
                skb = buffer_info->skb;
@@ -3843,6 +3845,7 @@ static bool e1000_clean_rx_irq(struct e1000_adapter *adapter,
                if (*work_done >= work_to_do)
                        break;
                (*work_done)++;
+               rmb(); /* read descriptor and rx_buffer_info after status DD */
 
                status = rx_desc->status;
                skb = buffer_info->skb;
index 79e38dc60a43d9cf807d998834299d745bb261e4..ba246793ea4abdfb16578e37f1d91d426da1ab8f 100644 (file)
@@ -774,6 +774,7 @@ static bool e1000_clean_rx_irq(struct e1000_adapter *adapter,
                if (*work_done >= work_to_do)
                        break;
                (*work_done)++;
+               rmb();  /* read descriptor and rx_buffer_info after status DD */
 
                status = rx_desc->status;
                skb = buffer_info->skb;
@@ -984,6 +985,7 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter)
        while ((eop_desc->upper.data & cpu_to_le32(E1000_TXD_STAT_DD)) &&
               (count < tx_ring->count)) {
                bool cleaned = false;
+               rmb(); /* read buffer_info after eop_desc */
                for (; !cleaned; count++) {
                        tx_desc = E1000_TX_DESC(*tx_ring, i);
                        buffer_info = &tx_ring->buffer_info[i];
@@ -1080,6 +1082,7 @@ static bool e1000_clean_rx_irq_ps(struct e1000_adapter *adapter,
                        break;
                (*work_done)++;
                skb = buffer_info->skb;
+               rmb();  /* read descriptor and rx_buffer_info after status DD */
 
                /* in the packet split case this is header only */
                prefetch(skb->data - NET_IP_ALIGN);
@@ -1279,6 +1282,7 @@ static bool e1000_clean_jumbo_rx_irq(struct e1000_adapter *adapter,
                if (*work_done >= work_to_do)
                        break;
                (*work_done)++;
+               rmb();  /* read descriptor and rx_buffer_info after status DD */
 
                status = rx_desc->status;
                skb = buffer_info->skb;
index df2a6d7c23afb3cfbe9012a36f8fc64f012cefaa..c9cb9c444442002649a0704c6cfc79270ebdcee8 100644 (file)
@@ -5344,6 +5344,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
 
        while ((eop_desc->wb.status & cpu_to_le32(E1000_TXD_STAT_DD)) &&
               (count < tx_ring->count)) {
+               rmb();  /* read buffer_info after eop_desc status */
                for (cleaned = false; !cleaned; count++) {
                        tx_desc = E1000_TX_DESC_ADV(*tx_ring, i);
                        buffer_info = &tx_ring->buffer_info[i];
@@ -5549,6 +5550,7 @@ static bool igb_clean_rx_irq_adv(struct igb_q_vector *q_vector,
                if (*work_done >= budget)
                        break;
                (*work_done)++;
+               rmb(); /* read descriptor and rx_buffer_info after status DD */
 
                skb = buffer_info->skb;
                prefetch(skb->data - NET_IP_ALIGN);
index 5e2b2a8c56c6f81ade223d30f9e3bf0705ed3f6e..57b5fee4ca8dec08f6eb74c65a7ea3e7e83c4b62 100644 (file)
@@ -248,6 +248,7 @@ static bool igbvf_clean_rx_irq(struct igbvf_adapter *adapter,
                if (*work_done >= work_to_do)
                        break;
                (*work_done)++;
+               rmb(); /* read descriptor and rx_buffer_info after status DD */
 
                buffer_info = &rx_ring->buffer_info[i];
 
@@ -780,6 +781,7 @@ static bool igbvf_clean_tx_irq(struct igbvf_ring *tx_ring)
 
        while ((eop_desc->wb.status & cpu_to_le32(E1000_TXD_STAT_DD)) &&
               (count < tx_ring->count)) {
+               rmb();  /* read buffer_info after eop_desc status */
                for (cleaned = false; !cleaned; count++) {
                        tx_desc = IGBVF_TX_DESC_ADV(*tx_ring, i);
                        buffer_info = &tx_ring->buffer_info[i];
index c6b75c83100c91b782221bf3e7ae6f813ef43da5..45fc89b9ba643d0e8f28edc8664cba4d89ae964a 100644 (file)
@@ -1816,6 +1816,7 @@ ixgb_clean_tx_irq(struct ixgb_adapter *adapter)
 
        while (eop_desc->status & IXGB_TX_DESC_STATUS_DD) {
 
+               rmb(); /* read buffer_info after eop_desc */
                for (cleaned = false; !cleaned; ) {
                        tx_desc = IXGB_TX_DESC(*tx_ring, i);
                        buffer_info = &tx_ring->buffer_info[i];
@@ -1976,6 +1977,7 @@ ixgb_clean_rx_irq(struct ixgb_adapter *adapter, int *work_done, int work_to_do)
                        break;
 
                (*work_done)++;
+               rmb();  /* read descriptor and rx_buffer_info after status DD */
                status = rx_desc->status;
                skb = buffer_info->skb;
                buffer_info->skb = NULL;
index 74d9b6df3029f3c67e9e85ff5a95a14c5ef6ff0b..649c8678d3437da604331fcea57fca8d5d7a63c5 100644 (file)
@@ -748,6 +748,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
        while ((eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)) &&
               (count < tx_ring->work_limit)) {
                bool cleaned = false;
+               rmb(); /* read buffer_info after eop_desc */
                for ( ; !cleaned; count++) {
                        struct sk_buff *skb;
                        tx_desc = IXGBE_TX_DESC_ADV(*tx_ring, i);
index a16cff7e54a3ec8daea5f499ca40834c5adb3111..3ea59f1199512cfb4bb9cadec3720971c1c888f7 100644 (file)
@@ -231,6 +231,7 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_adapter *adapter,
        while ((eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)) &&
               (count < tx_ring->work_limit)) {
                bool cleaned = false;
+               rmb(); /* read buffer_info after eop_desc */
                for ( ; !cleaned; count++) {
                        struct sk_buff *skb;
                        tx_desc = IXGBE_TX_DESC_ADV(*tx_ring, i);
@@ -518,6 +519,7 @@ static bool ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
                        break;
                (*work_done)++;
 
+               rmb(); /* read descriptor and rx_buffer_info after status DD */
                if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
                        hdr_info = le16_to_cpu(ixgbevf_get_hdr_info(rx_desc));
                        len = (hdr_info & IXGBE_RXDADV_HDRBUFLEN_MASK) >>