igb: Add support for writable pages and build_skb
Subsystems (2)
v3 cover igb: Add support for writable pages and build_skb
This patch set enables support for using the recent changes that allow for unmapping pages without invalidating their contents via DMA_ATTR_SKIP_CPU_SYNC. With this change DMA pages should be writable and as a result we should be able to make use of build_skb which can be used to drop the skb->head memory allocation, header parsing, and memcpy from the receive path which can greatly help to improve performance.
My main concern at this point is that there might be an architecture where I didn't get DMA_ATTR_SKIP_CPU_SYNC implemented that might still need it. For that reason I have also added a ethtool private flag called out as "legacy-rx". If a platform encounters an issue where the Rx can possibly corrupt data it can be enbled by running:
ethtool --set-priv-flags DEVNAME legacy-rx on
The testing matrix for all of these patches is going to be pretty extensive. Basically we want to test these patches on as many platforms and architectures as possible with as many features being toggled as possible including SR-IOV and Jumbo Frames all while receiving traffic.
Within the patches there is also some intialization changes. Specifically I have updated the code paths to defer clearing the rings until we are about to initialize them and give them to hardware. By doing this we are able to avoid having to dirty memory we don't need to which should help to improve suspend/resume times for when we start looking at possibly using the suspend/resume approach for migration of interface in VMs.
v2: Minor fixes to address a few issues found in testing
v3: Fix minor build issues reported by kbuild test robot
---
Alexander Duyck (9):
igb: Add support for DMA_ATTR_WEAK_ORDERING
igb: Use length to determine if descriptor is done
igb: Clear Rx buffer_info in configure instead of clean
igb: Don't bother clearing Tx buffer_info in igb_clean_tx_ring
igb: Limit maximum frame Rx based on MTU
igb: Add support for padding packet
igb: Add support for ethtool private flag to allow use of legacy Rx
igb: Break out Rx buffer page management
igb: Re-add support for build_skb in igb
drivers/net/ethernet/intel/igb/igb.h | 58 +++ drivers/net/ethernet/intel/igb/igb_ethtool.c | 65 +++ drivers/net/ethernet/intel/igb/igb_main.c | 511 ++++++++++++++++---------- drivers/net/ethernet/intel/igb/igb_ptp.c | 3 4 files changed, 435 insertions(+), 202 deletions(-)
--
PATCH v3 1/9 igb: Add support for DMA_ATTR_WEAK_ORDERING
From: Alexander Duyck <[email protected]>
Since we are already using DMA attributes in igb for Rx there is no reason why we can't also apply DMA_ATTR_WEAK_ORDERING which is needed on some platforms to improve performance.
--- drivers/net/ethernet/intel/igb/igb.h | 3 +++ drivers/net/ethernet/intel/igb/igb_main.c | 6 +++--- 2 files changed, 6 insertions(+), 3 deletions(-)
drivers/net/ethernet/intel/igb/igb.h +3 -0
@@ -148,6 +148,9 @@ struct vf_data_storage {/* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IGB_RX_BUFFER_WRITE 16/* Must be power of 2 */ +#define IGB_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) +#define AUTO_ALL_MODES 0#define IGB_EEPROM_APME 0x0400
drivers/net/ethernet/intel/igb/igb_main.c +3 -3
@@ -3963,7 +3963,7 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) buffer_info->dma,PAGE_SIZE ,DMA_FROM_DEVICE , - DMA_ATTR_SKIP_CPU_SYNC); + IGB_RX_DMA_ATTR);__page_frag_cache_drain (buffer_info->page, buffer_info->pagecnt_bias);
@@ -6992,7 +6992,7 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,*/ dma_unmap_page_attrs (rx_ring->dev, rx_buffer->dma,PAGE_SIZE ,DMA_FROM_DEVICE , -DMA_ATTR_SKIP_CPU_SYNC ); +IGB_RX_DMA_ATTR );__page_frag_cache_drain (page, rx_buffer->pagecnt_bias); }
@@ -7252,7 +7252,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,/* map page for use */ dma =dma_map_page_attrs (rx_ring->dev, page,0 ,PAGE_SIZE , -DMA_FROM_DEVICE ,DMA_ATTR_SKIP_CPU_SYNC ); +DMA_FROM_DEVICE ,IGB_RX_DMA_ATTR );/* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use
PATCH v3 2/9 igb: Use length to determine if descriptor is done
In reply to Alexander DuyckFrom: Alexander Duyck <[email protected]>
This change makes it so that we use the length of the packet instead of the DD status bit to determine if a new descriptor is ready to be processed. The obvious advantage is that it cuts down on reads as we don't really even need the DD bit if going from a 0 to a non-zero value on size is enough to inform us that the packet has been completed.
In addition I have updated the code so that we only reset the Rx descriptor length for descriptor zero when resetting a ring instead of having to do a memset with 0 over the entire ring. By doing this we can save some time on initialization.
---
v2: Update ethtool loopback test to use length check instead of DD check
drivers/net/ethernet/intel/igb/igb_ethtool.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 14 ++++++++------ 2 files changed, 9 insertions(+), 7 deletions(-)
drivers/net/ethernet/intel/igb/igb_ethtool.c +1 -1
@@ -1811,7 +1811,7 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring, tx_ntc = tx_ring->next_to_clean; rx_desc =IGB_RX_DESC (rx_ring, rx_ntc); -while (igb_test_staterr (rx_desc,E1000_RXD_STAT_DD )) { +while (rx_desc->wb.upper.length) {/* check Rx buffer */ rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc];
drivers/net/ethernet/intel/igb/igb_main.c +8 -6
@@ -3720,6 +3720,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, struct igb_ring *ring) {struct e1000_hw *hw = &adapter->hw; +union e1000_adv_rx_desc *rx_desc;u64 rdba = ring->dma;int reg_idx = ring->reg_idx;u32 srrctl =0 , rxdctl =0 ;
@@ -3758,6 +3759,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, rxdctl |=IGB_RX_HTHRESH <<8 ; rxdctl |=IGB_RX_WTHRESH <<16 ; +/* initialize Rx descriptor 0 */ + rx_desc =IGB_RX_DESC (ring,0 ); + rx_desc->wb.upper.length =0 ; +/* enable receive descriptor fetching */ rxdctl |=E1000_RXDCTL_QUEUE_ENABLE ;wr32 (E1000_RXDCTL (reg_idx), rxdctl);
@@ -3973,9 +3978,6 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) size =sizeof (struct igb_rx_buffer ) * rx_ring->count;memset (rx_ring->rx_buffer_info,0 , size); -/* Zero out the descriptor ring */ -memset (rx_ring->desc,0 , rx_ring->size); - rx_ring->next_to_alloc =0 ; rx_ring->next_to_clean =0 ; rx_ring->next_to_use =0 ;
@@ -7174,7 +7176,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) rx_desc =IGB_RX_DESC (rx_ring, rx_ring->next_to_clean); -if (!rx_desc->wb.upper.status_error) +if (!rx_desc->wb.upper.length)break ;/* This memory barrier is needed to keep us from reading
@@ -7314,8 +7316,8 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) i -= rx_ring->count; } -/* clear the status bits for the next_to_use descriptor */ - rx_desc->wb.upper.status_error =0 ; +/* clear the length for the next_to_use descriptor */ + rx_desc->wb.upper.length =0 ; cleaned_count--; }while (cleaned_count);
PATCH v3 3/9 igb: Clear Rx buffer_info in configure instead of clean
In reply to Alexander DuyckFrom: Alexander Duyck <[email protected]>
This change makes it so that instead of going through the entire ring on Rx cleanup we only go through the region that was designated to be cleaned up and stop when we reach the region where new allocations should start.
In addition we can avoid having to perform a memset on the Rx buffer_info structures until we are about to start using the ring again. By deferring this we can avoid dirtying the cache any more than we have to which can help to improve the time needed to bring the interface down and then back up again in a reset or suspend/resume cycle.
--- drivers/net/ethernet/intel/igb/igb_main.c | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-)
drivers/net/ethernet/intel/igb/igb_main.c +10 -14
@@ -3435,7 +3435,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) size =sizeof (struct igb_rx_buffer ) * rx_ring->count; - rx_ring->rx_buffer_info =vzalloc (size); + rx_ring->rx_buffer_info =vmalloc (size);if (!rx_ring->rx_buffer_info) goto err;
@@ -3759,6 +3759,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, rxdctl |=IGB_RX_HTHRESH <<8 ; rxdctl |=IGB_RX_WTHRESH <<16 ; +/* initialize rx_buffer_info */ +memset (ring->rx_buffer_info,0 , +sizeof (struct igb_rx_buffer ) * ring->count); +/* initialize Rx descriptor 0 */ rx_desc =IGB_RX_DESC (ring,0 ); rx_desc->wb.upper.length =0 ;
@@ -3937,23 +3941,16 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter)**/ static void igb_clean_rx_ring (struct igb_ring *rx_ring) { -unsigned long size; -u16 i; +u16 i = rx_ring->next_to_clean;if (rx_ring->skb)dev_kfree_skb (rx_ring->skb); rx_ring->skb =NULL ; -if (!rx_ring->rx_buffer_info) -return ; -/* Free all the Rx ring sk_buffs */ -for (i =0 ; i < rx_ring->count; i++) { +while (i != rx_ring->next_to_alloc) {struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i]; -if (!buffer_info->page) -continue ; -/* Invalidate cache lines that may have been written to by * device so that we avoid corrupting memory. */
@@ -3972,12 +3969,11 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring)__page_frag_cache_drain (buffer_info->page, buffer_info->pagecnt_bias); - buffer_info->page =NULL ; + i++; +if (i == rx_ring->count) + i =0 ; } - size =sizeof (struct igb_rx_buffer ) * rx_ring->count; -memset (rx_ring->rx_buffer_info,0 , size); - rx_ring->next_to_alloc =0 ; rx_ring->next_to_clean =0 ; rx_ring->next_to_use =0 ;
PATCH v3 4/9 igb: Don't bother clearing Tx buffer_info in igb_clean_tx_ring
In reply to Alexander DuyckFrom: Alexander Duyck <[email protected]>
In the case of the Tx rings we need to only clear the Tx buffer_info when we are resetting the rings. Ideally we do this when we configure the ring to bring it back up instead of when we are taking it down in order to avoid dirtying pages we don't need to.
In addition we don't need to clear the Tx descriptor ring since we will fully repopulate it when we begin transmitting frames and next_to_watch can be cleared to prevent the ring from being cleaned beyond that point instead of needing to touch anything in the Tx descriptor ring.
Finally with these changes we can avoid having to reset the skb member of the Tx buffer_info structure in the cleanup path since the skb will always be associated with the first buffer which has next_to_watch set.
---
v2: Fixed Tx mapping exception path to reset tx_buffer address
drivers/net/ethernet/intel/igb/igb.h | 1 drivers/net/ethernet/intel/igb/igb_ethtool.c | 11 ++ drivers/net/ethernet/intel/igb/igb_main.c | 120 ++++++++++++++++---------- 3 files changed, 83 insertions(+), 49 deletions(-)
drivers/net/ethernet/intel/igb/igb.h +0 -1
@@ -594,7 +594,6 @@ enum igb_boards {void igb_setup_tctl (struct igb_adapter *);void igb_setup_rctl (struct igb_adapter *);netdev_tx_t igb_xmit_frame_ring (struct sk_buff *,struct igb_ring *); -void igb_unmap_and_free_tx_resource (struct igb_ring *,struct igb_tx_buffer *);void igb_alloc_rx_buffers (struct igb_ring *,u16 );void igb_update_stats (struct igb_adapter *,struct rtnl_link_stats64 *);bool igb_has_link (struct igb_adapter *adapter);
drivers/net/ethernet/intel/igb/igb_ethtool.c +10 -1
@@ -1833,7 +1833,16 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,/* unmap buffer on Tx side */ tx_buffer_info = &tx_ring->tx_buffer_info[tx_ntc]; -igb_unmap_and_free_tx_resource (tx_ring, tx_buffer_info); + +/* Free all the Tx ring sk_buffs */ +dev_kfree_skb_any (tx_buffer_info->skb); + +/* unmap skb header data */ +dma_unmap_single (tx_ring->dev, +dma_unmap_addr (tx_buffer_info, dma), +dma_unmap_len (tx_buffer_info, len), +DMA_TO_DEVICE ); +dma_unmap_len_set (tx_buffer_info, len,0 );/* increment Rx/Tx next to clean counters */ rx_ntc++;
drivers/net/ethernet/intel/igb/igb_main.c +73 -47
173 lines not on this page · raw message
PATCH v3 5/9 igb: Limit maximum frame Rx based on MTU
In reply to Alexander DuyckFrom: Alexander Duyck <[email protected]>
In order to support the use of build_skb going forward it will be necessary to place a maximum limit on the amount of data we can receive when jumbo frames is not enabled. In order to do this I am adding a new upper limit for receive based on the size of a 2K buffer minus padding.
--- drivers/net/ethernet/intel/igb/igb.h | 10 +++++++++- drivers/net/ethernet/intel/igb/igb_main.c | 16 ++++++++++++---- 2 files changed, 21 insertions(+), 5 deletions(-)
drivers/net/ethernet/intel/igb/igb.h +9 -1
@@ -143,8 +143,17 @@ struct vf_data_storage {#define IGB_RXBUFFER_256 256#define IGB_RXBUFFER_2048 2048#define IGB_RX_HDR_LEN IGB_RXBUFFER_256 +#define IGB_TS_HDR_LEN 16#define IGB_RX_BUFSZ IGB_RXBUFFER_2048 +#define IGB_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#if (PAGE_SIZE <8192 ) +#define IGB_MAX_FRAME_BUILD_SKB \ + (SKB_WITH_OVERHEAD(IGB_RXBUFFER_2048) - IGB_SKB_PAD - IGB_TS_HDR_LEN) +#else +#define IGB_MAX_FRAME_BUILD_SKB (IGB_RXBUFFER_2048 - IGB_TS_HDR_LEN) +#endif +/* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IGB_RX_BUFFER_WRITE 16/* Must be power of 2 */
@@ -561,7 +570,6 @@ struct igb_adapter {#define IGB_DMCTLX_DCFLUSH_DIS 0x80000000/* Disable DMA Coal Flush */ #define IGB_82576_TSYNC_SHIFT 19 -#define IGB_TS_HDR_LEN 16enum e1000_state_t { __IGB_TESTING, __IGB_RESETTING,
drivers/net/ethernet/intel/igb/igb_main.c +12 -4
@@ -4250,7 +4250,7 @@ static void igb_set_rx_mode(struct net_device *netdev)struct igb_adapter *adapter =netdev_priv (netdev);struct e1000_hw *hw = &adapter->hw;unsigned int vfn = adapter->vfs_allocated_count; -u32 rctl =0 , vmolr =0 ; +u32 rctl =0 , vmolr =0 , rlpml =MAX_JUMBO_FRAME_SIZE ;int count;/* Check for Promiscuous and All Multicast modes */
@@ -4322,12 +4322,20 @@ static void igb_set_rx_mode(struct net_device *netdev) vmolr |=rd32 (E1000_VMOLR (vfn)) & ~(E1000_VMOLR_ROPE |E1000_VMOLR_MPME |E1000_VMOLR_ROMPE ); -/* enable Rx jumbo frames, no need for restriction */ +/* enable Rx jumbo frames, restrict as needed to support build_skb */ vmolr &= ~E1000_VMOLR_RLPML_MASK ; - vmolr |=MAX_JUMBO_FRAME_SIZE |E1000_VMOLR_LPE ; +#if (PAGE_SIZE <8192 ) +if (adapter->max_frame_size <=IGB_MAX_FRAME_BUILD_SKB ) { +if (!adapter->vfs_allocated_count) + rlpml =IGB_MAX_FRAME_BUILD_SKB ; + vmolr |=IGB_MAX_FRAME_BUILD_SKB ; + } else +#endif + vmolr |=MAX_JUMBO_FRAME_SIZE ; + vmolr |=E1000_VMOLR_LPE ;wr32 (E1000_VMOLR (vfn), vmolr); -wr32 (E1000_RLPML ,MAX_JUMBO_FRAME_SIZE ); +wr32 (E1000_RLPML , rlpml);igb_restore_vf_multicasts (adapter); }
PATCH v3 6/9 igb: Add support for padding packet
In reply to Alexander DuyckFrom: Alexander Duyck <[email protected]>
With the size of the frame limited we can now write to an offset within the buffer instead of having to write at the very start of the buffer. The advantage to this is that it allows us to leave padding room for things like supporting XDP in the future.
One side effect of this patch is that we can end up using a larger buffer if jumbo frames is enabled. The impact shouldn't be too great, but it could hurt small packet performance for UDP workloads if jumbo frames is enabled as the truesize of frames will be larger.
---
v3: Fixed "unsigned char *" / "void *" mismatch on pointer arithmetic
drivers/net/ethernet/intel/igb/igb.h | 44 ++++++++++++- drivers/net/ethernet/intel/igb/igb_ethtool.c | 4 + drivers/net/ethernet/intel/igb/igb_main.c | 91 +++++++++++++++++++------- drivers/net/ethernet/intel/igb/igb_ptp.c | 3 - 4 files changed, 110 insertions(+), 32 deletions(-)
drivers/net/ethernet/intel/igb/igb.h +42 -2
@@ -142,9 +142,9 @@ struct vf_data_storage {/* Supported Rx Buffer Sizes */ #define IGB_RXBUFFER_256 256#define IGB_RXBUFFER_2048 2048 +#define IGB_RXBUFFER_3072 3072#define IGB_RX_HDR_LEN IGB_RXBUFFER_256#define IGB_TS_HDR_LEN 16 -#define IGB_RX_BUFSZ IGB_RXBUFFER_2048#define IGB_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)#if (PAGE_SIZE <8192 )
@@ -313,12 +313,51 @@ struct igb_q_vector { };enum e1000_ring_flags_t { +IGB_RING_FLAG_RX_3K_BUFFER , +IGB_RING_FLAG_RX_BUILD_SKB_ENABLED ,IGB_RING_FLAG_RX_SCTP_CSUM ,IGB_RING_FLAG_RX_LB_VLAN_BSWAP ,IGB_RING_FLAG_TX_CTX_IDX ,IGB_RING_FLAG_TX_DETECT_HANG }; +#define ring_uses_build_skb (ring) \ + test_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) +#define set_ring_build_skb_enabled (ring) \ + set_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) +#define clear_ring_build_skb_enabled (ring) \ + clear_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) + +#define ring_uses_large_buffer (ring) \ + test_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define set_ring_uses_large_buffer (ring) \ + set_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define clear_ring_uses_large_buffer (ring) \ + clear_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) + +static inline unsigned int igb_rx_bufsz (struct igb_ring *ring) +{ +#if (PAGE_SIZE <8192 ) +if (ring_uses_large_buffer (ring)) +return IGB_RXBUFFER_3072 ; + +if (ring_uses_build_skb (ring)) +return IGB_MAX_FRAME_BUILD_SKB +IGB_TS_HDR_LEN ; +#endif +return IGB_RXBUFFER_2048 ; +} + +static inline unsigned int igb_rx_pg_order (struct igb_ring *ring) +{ +#if (PAGE_SIZE <8192 ) +if (ring_uses_large_buffer (ring)) +return 1 ; +#endif +return 0 ; +} + +#define igb_rx_pg_size (_ring) (PAGE_SIZE << igb_rx_pg_order(_ring)) +#define IGB_TXD_DCMD (E1000_ADVTXD_DCMD_EOP | E1000_ADVTXD_DCMD_RS)#define IGB_RX_DESC (R , i) \
@@ -557,6 +596,7 @@ struct igb_adapter {#define IGB_FLAG_HAS_MSIX BIT(13)#define IGB_FLAG_EEE BIT(14)#define IGB_FLAG_VLAN_PROMISC BIT(15) +#define IGB_FLAG_RX_LEGACY BIT(16)/* Media Auto Sense */ #define IGB_MAS_ENABLE_0 0X0001
@@ -614,7 +654,7 @@ enum igb_boards {void igb_ptp_suspend (struct igb_adapter *adapter);void igb_ptp_rx_hang (struct igb_adapter *adapter);void igb_ptp_rx_rgtstamp (struct igb_q_vector *q_vector,struct sk_buff *skb); -void igb_ptp_rx_pktstamp (struct igb_q_vector *q_vector,unsigned char *va, +void igb_ptp_rx_pktstamp (struct igb_q_vector *q_vector,void *va,struct sk_buff *skb);int igb_ptp_set_ts_config (struct net_device *netdev,struct ifreq *ifr);int igb_ptp_get_ts_config (struct net_device *netdev,struct ifreq *ifr);
drivers/net/ethernet/intel/igb/igb_ethtool.c +2 -2
@@ -1818,7 +1818,7 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,/* sync Rx buffer for CPU read */ dma_sync_single_for_cpu (rx_ring->dev, rx_buffer_info->dma, -IGB_RX_BUFSZ , + size,DMA_FROM_DEVICE );/* verify contents of skb */
@@ -1828,7 +1828,7 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,/* sync Rx buffer for device write */ dma_sync_single_for_device (rx_ring->dev, rx_buffer_info->dma, -IGB_RX_BUFSZ , + size,DMA_FROM_DEVICE );/* unmap buffer on Tx side */
drivers/net/ethernet/intel/igb/igb_main.c +65 -26
219 lines not on this page · raw message
drivers/net/ethernet/intel/igb/igb_ptp.c +1 -2
@@ -764,8 +764,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)* incoming frame. The value is stored in little endian format starting on * byte 8. **/ -void igb_ptp_rx_pktstamp (struct igb_q_vector *q_vector, -unsigned char *va, +void igb_ptp_rx_pktstamp (struct igb_q_vector *q_vector,void *va,struct sk_buff *skb) {__le64 *regval = (__le64 *)va;
Brown
PATCH v3 6/9 igb: Add support for padding packet
Quoted 23 lines
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at lists.osuosl.org] On Behalf Of Alexander Duyck
Sent: Monday, January 23, 2017 8:59 AM
To: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetFrom: Alexander Duyck <[email protected]>
With the size of the frame limited we can now write to an offset within the buffer instead of having to write at the very start of the buffer. The advantage to this is that it allows us to leave padding room for things like supporting XDP in the future.
One side effect of this patch is that we can end up using a larger buffer if jumbo frames is enabled. The impact shouldn't be too great, but it could hurt small packet performance for UDP workloads if jumbo frames is enabled as the truesize of frames will be larger.
Signed-off-by Alexander Duyck <[email protected]>---
Quoted 8 lines
v3: Fixed "unsigned char *" / "void *" mismatch on pointer arithmetic
drivers/net/ethernet/intel/igb/igb.h | 44 ++++++++++++- drivers/net/ethernet/intel/igb/igb_ethtool.c | 4 + drivers/net/ethernet/intel/igb/igb_main.c | 91 +++++++++++++++++++-- ----- drivers/net/ethernet/intel/igb/igb_ptp.c | 3 - 4 files changed, 110 insertions(+), 32 deletions(-)
I am having one (and only one) system dump on me when running netperf_stress (multiple netperf sessions of varying sizes running in looped cycles.) The system itself is an older SuperMicro system with a pair of 82575EB LOMs. It's a rather dated system but I managed to locate another box of more or less the same era with 82575EB LOMs and am NOT seeing the dump there. I stripped off the other patches from this series and the problem does not appear with the first 5, but with this one on I get the system to crash. Usually it freezes or restarts, sometimes it just locks up the consoles. When it repeats or restarts it captures the trace to /var/log/messages so I was able to grab this trace from there:
------------------------------------------------------------------------------------------------
Feb 2 15:08:00 u1485 xinetd[1866]: START: netperf pid=5528 from=::ffff:190.1.4.85 Feb 2 15:08:02 u1485 kernel: swap_free: Bad swap offset entry 1c995c1d195b8 Feb 2 15:08:02 u1485 kernel: BUG: Bad page map in process sleep pte:72657074656e0066 pmd:7be3b067 Feb 2 15:08:02 u1485 kernel: addr:00007fdfedc00000 vm_flags:00000070 anon_vma: (null) mapping:ffff880079436cc0 index:1ba Feb 2 15:08:02 u1485 kernel: file:libc-2.12.so fault:ext4_filemap_fault [ext4] mmap:ext4_file_mmap [ext4] readpage:ext4_readpage [ext4] Feb 2 15:08:02 u1485 kernel: CPU: 5 PID: 5526 Comm: sleep Tainted: G E 4.10.0-rc4_next-queue_regress #18 Feb 2 15:08:02 u1485 kernel: Hardware name: Supermicro X7DW3/X7DWN+, BIOS 1.2c 11/19/2010 Feb 2 15:08:02 u1485 kernel: Call Trace: Feb 2 15:08:02 u1485 kernel: dump_stack+0x51/0x78 Feb 2 15:08:02 u1485 kernel: ? ext4_bh_unmapped+0x20/0x20 [ext4] Feb 2 15:08:02 u1485 kernel: ? ext4_file_open+0x220/0x220 [ext4] Feb 2 15:08:02 u1485 kernel: print_bad_pte+0x1cd/0x280 Feb 2 15:08:02 u1485 kernel: zap_pte_range+0x5ab/0x640 Feb 2 15:08:02 u1485 kernel: ? pte_alloc_one_map+0x1c3/0x250 Feb 2 15:08:02 u1485 kernel: unmap_page_range+0x1f8/0x300 Feb 2 15:08:02 u1485 kernel: unmap_single_vma+0x60/0xe0 Feb 2 15:08:02 u1485 kernel: unmap_vmas+0x4b/0xa0 Feb 2 15:08:02 u1485 kernel: exit_mmap+0xbb/0x140 Feb 2 15:08:02 u1485 kernel: mmput+0x77/0x170 Feb 2 15:08:02 u1485 kernel: ? mm_release+0x57/0x140 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: exit_mm+0x140/0x1d0 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: ? exit_signals+0x150/0x170 Feb 2 15:08:02 u1485 kernel: do_exit+0x12e/0x490 Feb 2 15:08:02 u1485 kernel: ? handle_mm_fault+0x87/0x190 Feb 2 15:08:02 u1485 kernel: ? filp_close+0x65/0x90 Feb 2 15:08:02 u1485 kernel: do_group_exit+0x4e/0xc0 Feb 2 15:08:02 u1485 kernel: SyS_exit_group+0x17/0x20 Feb 2 15:08:02 u1485 kernel: entry_SYSCALL_64_fastpath+0x13/0x94 Feb 2 15:08:02 u1485 kernel: RIP: 0033:0x7fdfedaf2df8 Feb 2 15:08:02 u1485 kernel: RSP: 002b:00007ffe94402408 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7 Feb 2 15:08:02 u1485 kernel: RAX: ffffffffffffffda RBX: 00000000fbad2084 RCX: 00007fdfedaf2df8 Feb 2 15:08:02 u1485 kernel: RDX: 0000000000000000 RSI: 000000000000003c RDI: 0000000000000000 Feb 2 15:08:02 u1485 kernel: RBP: 00007fdfeddd47a0 R08: 00000000000000e7 R09: ffffffffffffffa8 Feb 2 15:08:02 u1485 kernel: R10: 0000000000000004 R11: 0000000000000246 R12: 0000000000000000 Feb 2 15:08:02 u1485 kernel: R13: 00007ffe94402468 R14: 0000000000000001 R15: 00007ffe94402460 Feb 2 15:08:02 u1485 kernel: Disabling lock debugging due to kernel taint Feb 2 15:08:02 u1485 kernel: swap_free: Bad swap offset entry 1c995c1d195b8 Feb 2 15:08:02 u1485 kernel: BUG: Bad page map in process sleep pte:72657074656e0066 pmd:7be3b067 Feb 2 15:08:02 u1485 kernel: addr:00007fdfedc01000 vm_flags:00000070 anon_vma: (null) mapping:ffff880079436cc0 index:1bb Feb 2 15:08:02 u1485 kernel: file:libc-2.12.so fault:ext4_filemap_fault [ext4] mmap:ext4_file_mmap [ext4] readpage:ext4_readpage [ext4] Feb 2 15:08:02 u1485 kernel: CPU: 5 PID: 5526 Comm: sleep Tainted: G B E 4.10.0-rc4_next-queue_regress #18 Feb 2 15:08:02 u1485 kernel: Hardware name: Supermicro X7DW3/X7DWN+, BIOS 1.2c 11/19/2010 Feb 2 15:08:02 u1485 kernel: Call Trace: Feb 2 15:08:02 u1485 kernel: dump_stack+0x51/0x78 Feb 2 15:08:02 u1485 kernel: ? ext4_bh_unmapped+0x20/0x20 [ext4] Feb 2 15:08:02 u1485 kernel: ? ext4_file_open+0x220/0x220 [ext4] Feb 2 15:08:02 u1485 kernel: print_bad_pte+0x1cd/0x280 Feb 2 15:08:02 u1485 kernel: zap_pte_range+0x5ab/0x640 Feb 2 15:08:02 u1485 kernel: ? pte_alloc_one_map+0x1c3/0x250 Feb 2 15:08:02 u1485 kernel: unmap_page_range+0x1f8/0x300 Feb 2 15:08:02 u1485 kernel: unmap_single_vma+0x60/0xe0 Feb 2 15:08:02 u1485 kernel: unmap_vmas+0x4b/0xa0 Feb 2 15:08:02 u1485 kernel: exit_mmap+0xbb/0x140 Feb 2 15:08:02 u1485 kernel: mmput+0x77/0x170 Feb 2 15:08:02 u1485 kernel: ? mm_release+0x57/0x140 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: exit_mm+0x140/0x1d0 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: ? exit_signals+0x150/0x170 Feb 2 15:08:02 u1485 kernel: do_exit+0x12e/0x490 Feb 2 15:08:02 u1485 kernel: ? handle_mm_fault+0x87/0x190 Feb 2 15:08:02 u1485 kernel: ? filp_close+0x65/0x90 Feb 2 15:08:02 u1485 kernel: do_group_exit+0x4e/0xc0 Feb 2 15:08:02 u1485 kernel: SyS_exit_group+0x17/0x20 Feb 2 15:08:02 u1485 kernel: entry_SYSCALL_64_fastpath+0x13/0x94 Feb 2 15:08:02 u1485 kernel: RIP: 0033:0x7fdfedaf2df8 Feb 2 15:08:02 u1485 kernel: RSP: 002b:00007ffe94402408 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7 Feb 2 15:08:02 u1485 kernel: RAX: ffffffffffffffda RBX: 00000000fbad2084 RCX: 00007fdfedaf2df8 Feb 2 15:08:02 u1485 kernel: RDX: 0000000000000000 RSI: 000000000000003c RDI: 0000000000000000 Feb 2 15:08:02 u1485 kernel: RBP: 00007fdfeddd47a0 R08: 00000000000000e7 R09: ffffffffffffffa8 Feb 2 15:08:02 u1485 kernel: R10: 0000000000000004 R11: 0000000000000246 R12: 0000000000000000 Feb 2 15:08:02 u1485 kernel: R13: 00007ffe94402468 R14: 0000000000000001 R15: 00007ffe94402460 Feb 2 15:08:02 u1485 kernel: swap_free: Bad swap offset entry 1c995c1d195b8 Feb 2 15:08:02 u1485 kernel: BUG: Bad page map in process sleep pte:72657074656e0066 pmd:7be3b067 Feb 2 15:08:02 u1485 kernel: addr:00007fdfedc02000 vm_flags:00000070 anon_vma: (null) mapping:ffff880079436cc0 index:1bc Feb 2 15:08:02 u1485 kernel: file:libc-2.12.so fault:ext4_filemap_fault [ext4] mmap:ext4_file_mmap [ext4] readpage:ext4_readpage [ext4] Feb 2 15:08:02 u1485 kernel: CPU: 5 PID: 5526 Comm: sleep Tainted: G B E 4.10.0-rc4_next-queue_regress #18 Feb 2 15:08:02 u1485 kernel: Hardware name: Supermicro X7DW3/X7DWN+, BIOS 1.2c 11/19/2010
...
------------------------------------------------------------------------------------------------
This call trace pattern repeated 7 ot 8 times and then the system either rebooted on its own or simply locked up.
I am not entirely convinced it is not my hardware as I cannot reproduce the issue on any other system. This one is very low on disk space and I have been meaning to rebuild it on a larger partition, preferably newer and larger drive for some time. Given it calls out a bad swap offset at the beginning of the bug / call trace text I suppose I could be running into issues with an overly full disk (though that seems a bit unlikely being different partitions and all.) I will go ahead and rebuild this system granting new, larger freshly formatted partitions and see if the problem goes away.
PATCH v3 6/9 igb: Add support for padding packet
Quoted 114 lines · Aaron F
Quoted 23 lines
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at lists.osuosl.org] On Behalf Of Alexander Duyck
Sent: Monday, January 23, 2017 8:59 AM
To: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetFrom: Alexander Duyck <[email protected]>
With the size of the frame limited we can now write to an offset within the buffer instead of having to write at the very start of the buffer. The advantage to this is that it allows us to leave padding room for things like supporting XDP in the future.
One side effect of this patch is that we can end up using a larger buffer if jumbo frames is enabled. The impact shouldn't be too great, but it could hurt small packet performance for UDP workloads if jumbo frames is enabled as the truesize of frames will be larger.
Signed-off-by Alexander Duyck <[email protected]>---
Quoted 8 lines
v3: Fixed "unsigned char *" / "void *" mismatch on pointer arithmetic
drivers/net/ethernet/intel/igb/igb.h | 44 ++++++++++++- drivers/net/ethernet/intel/igb/igb_ethtool.c | 4 + drivers/net/ethernet/intel/igb/igb_main.c | 91 +++++++++++++++++++-- ----- drivers/net/ethernet/intel/igb/igb_ptp.c | 3 - 4 files changed, 110 insertions(+), 32 deletions(-)I am having one (and only one) system dump on me when running
netperf_stress(multiple netperf sessions of varying sizes running in looped cycles.) The system itself is an older SuperMicro system with a pair of 82575EB LOMs. It's a rather dated system but I managed to locate another box of more or less the same era with 82575EB LOMs and am NOT seeing the dump there. I stripped off the other patches from this series and the problem does not appear with the first 5, but with this one on I get the system to crash. Usually it freezes or restarts, sometimes it just locks up the consoles. When it repeats or restarts it captures the trace to/var/log/messagesso I was able to grab this trace from there:
------------------------------------------------------------------------------------------------Feb 2 15:08:00 u1485 xinetd[1866]: START: netperf pid=5528 from=::ffff:190.1.4.85 Feb 2 15:08:02 u1485 kernel: swap_free: Bad swap offset entry 1c995c1d195b8 Feb 2 15:08:02 u1485 kernel: BUG: Bad page map in process sleep pte:72657074656e0066 pmd:7be3b067 Feb 2 15:08:02 u1485 kernel: addr:00007fdfedc00000 vm_flags:00000070 anon_vma: (null) mapping:ffff880079436cc0 index:1ba Feb 2 15:08:02 u1485 kernel: file:libc-2.12.so fault:ext4_filemap_fault [ext4] mmap:ext4_file_mmap [ext4] readpage:ext4_readpage [ext4] Feb 2 15:08:02 u1485 kernel: CPU: 5 PID: 5526 Comm: sleep Tainted: G E 4.10.0-rc4_next-queue_regress #18 Feb 2 15:08:02 u1485 kernel: Hardware name: Supermicro X7DW3/X7DWN+, BIOS 1.2c 11/19/2010 Feb 2 15:08:02 u1485 kernel: Call Trace: Feb 2 15:08:02 u1485 kernel: dump_stack+0x51/0x78 Feb 2 15:08:02 u1485 kernel: ? ext4_bh_unmapped+0x20/0x20 [ext4] Feb 2 15:08:02 u1485 kernel: ? ext4_file_open+0x220/0x220 [ext4] Feb 2 15:08:02 u1485 kernel: print_bad_pte+0x1cd/0x280 Feb 2 15:08:02 u1485 kernel: zap_pte_range+0x5ab/0x640 Feb 2 15:08:02 u1485 kernel: ? pte_alloc_one_map+0x1c3/0x250 Feb 2 15:08:02 u1485 kernel: unmap_page_range+0x1f8/0x300 Feb 2 15:08:02 u1485 kernel: unmap_single_vma+0x60/0xe0 Feb 2 15:08:02 u1485 kernel: unmap_vmas+0x4b/0xa0 Feb 2 15:08:02 u1485 kernel: exit_mmap+0xbb/0x140 Feb 2 15:08:02 u1485 kernel: mmput+0x77/0x170 Feb 2 15:08:02 u1485 kernel: ? mm_release+0x57/0x140 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: exit_mm+0x140/0x1d0 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: ? exit_signals+0x150/0x170 Feb 2 15:08:02 u1485 kernel: do_exit+0x12e/0x490 Feb 2 15:08:02 u1485 kernel: ? handle_mm_fault+0x87/0x190 Feb 2 15:08:02 u1485 kernel: ? filp_close+0x65/0x90 Feb 2 15:08:02 u1485 kernel: do_group_exit+0x4e/0xc0 Feb 2 15:08:02 u1485 kernel: SyS_exit_group+0x17/0x20 Feb 2 15:08:02 u1485 kernel: entry_SYSCALL_64_fastpath+0x13/0x94 Feb 2 15:08:02 u1485 kernel: RIP: 0033:0x7fdfedaf2df8 Feb 2 15:08:02 u1485 kernel: RSP: 002b:00007ffe94402408 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7 Feb 2 15:08:02 u1485 kernel: RAX: ffffffffffffffda RBX: 00000000fbad2084 RCX: 00007fdfedaf2df8 Feb 2 15:08:02 u1485 kernel: RDX: 0000000000000000 RSI: 000000000000003c RDI: 0000000000000000 Feb 2 15:08:02 u1485 kernel: RBP: 00007fdfeddd47a0 R08: 00000000000000e7 R09: ffffffffffffffa8 Feb 2 15:08:02 u1485 kernel: R10: 0000000000000004 R11: 0000000000000246 R12: 0000000000000000 Feb 2 15:08:02 u1485 kernel: R13: 00007ffe94402468 R14: 0000000000000001 R15: 00007ffe94402460 Feb 2 15:08:02 u1485 kernel: Disabling lock debugging due to kernel taint Feb 2 15:08:02 u1485 kernel: swap_free: Bad swap offset entry 1c995c1d195b8 Feb 2 15:08:02 u1485 kernel: BUG: Bad page map in process sleep pte:72657074656e0066 pmd:7be3b067 Feb 2 15:08:02 u1485 kernel: addr:00007fdfedc01000 vm_flags:00000070 anon_vma: (null) mapping:ffff880079436cc0 index:1bb Feb 2 15:08:02 u1485 kernel: file:libc-2.12.so fault:ext4_filemap_fault [ext4] mmap:ext4_file_mmap [ext4] readpage:ext4_readpage [ext4] Feb 2 15:08:02 u1485 kernel: CPU: 5 PID: 5526 Comm: sleep Tainted: G B E 4.10.0-rc4_next-queue_regress #18 Feb 2 15:08:02 u1485 kernel: Hardware name: Supermicro X7DW3/X7DWN+, BIOS 1.2c 11/19/2010 Feb 2 15:08:02 u1485 kernel: Call Trace: Feb 2 15:08:02 u1485 kernel: dump_stack+0x51/0x78 Feb 2 15:08:02 u1485 kernel: ? ext4_bh_unmapped+0x20/0x20 [ext4] Feb 2 15:08:02 u1485 kernel: ? ext4_file_open+0x220/0x220 [ext4] Feb 2 15:08:02 u1485 kernel: print_bad_pte+0x1cd/0x280 Feb 2 15:08:02 u1485 kernel: zap_pte_range+0x5ab/0x640 Feb 2 15:08:02 u1485 kernel: ? pte_alloc_one_map+0x1c3/0x250 Feb 2 15:08:02 u1485 kernel: unmap_page_range+0x1f8/0x300 Feb 2 15:08:02 u1485 kernel: unmap_single_vma+0x60/0xe0 Feb 2 15:08:02 u1485 kernel: unmap_vmas+0x4b/0xa0 Feb 2 15:08:02 u1485 kernel: exit_mmap+0xbb/0x140 Feb 2 15:08:02 u1485 kernel: mmput+0x77/0x170 Feb 2 15:08:02 u1485 kernel: ? mm_release+0x57/0x140 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: exit_mm+0x140/0x1d0 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: ? exit_signals+0x150/0x170 Feb 2 15:08:02 u1485 kernel: do_exit+0x12e/0x490 Feb 2 15:08:02 u1485 kernel: ? handle_mm_fault+0x87/0x190 Feb 2 15:08:02 u1485 kernel: ? filp_close+0x65/0x90 Feb 2 15:08:02 u1485 kernel: do_group_exit+0x4e/0xc0 Feb 2 15:08:02 u1485 kernel: SyS_exit_group+0x17/0x20 Feb 2 15:08:02 u1485 kernel: entry_SYSCALL_64_fastpath+0x13/0x94 Feb 2 15:08:02 u1485 kernel: RIP: 0033:0x7fdfedaf2df8 Feb 2 15:08:02 u1485 kernel: RSP: 002b:00007ffe94402408 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7 Feb 2 15:08:02 u1485 kernel: RAX: ffffffffffffffda RBX: 00000000fbad2084 RCX: 00007fdfedaf2df8 Feb 2 15:08:02 u1485 kernel: RDX: 0000000000000000 RSI: 000000000000003c RDI: 0000000000000000 Feb 2 15:08:02 u1485 kernel: RBP: 00007fdfeddd47a0 R08: 00000000000000e7 R09: ffffffffffffffa8 Feb 2 15:08:02 u1485 kernel: R10: 0000000000000004 R11: 0000000000000246 R12: 0000000000000000 Feb 2 15:08:02 u1485 kernel: R13: 00007ffe94402468 R14: 0000000000000001 R15: 00007ffe94402460 Feb 2 15:08:02 u1485 kernel: swap_free: Bad swap offset entry 1c995c1d195b8 Feb 2 15:08:02 u1485 kernel: BUG: Bad page map in process sleep pte:72657074656e0066 pmd:7be3b067 Feb 2 15:08:02 u1485 kernel: addr:00007fdfedc02000 vm_flags:00000070 anon_vma: (null) mapping:ffff880079436cc0 index:1bc Feb 2 15:08:02 u1485 kernel: file:libc-2.12.so fault:ext4_filemap_fault [ext4] mmap:ext4_file_mmap [ext4] readpage:ext4_readpage [ext4] Feb 2 15:08:02 u1485 kernel: CPU: 5 PID: 5526 Comm: sleep Tainted: G B E 4.10.0-rc4_next-queue_regress #18 Feb 2 15:08:02 u1485 kernel: Hardware name: Supermicro X7DW3/X7DWN+, BIOS 1.2c 11/19/2010
Quoted 5 lines
...
------------------------------------------------------------------------------------------------
This call trace pattern repeated 7 ot 8 times and then the system either rebooted on its own or simply locked up.I am not entirely convinced it is not my hardware as I cannot reproduce the issue on any other system. This one is very low on disk space and I have been meaning to rebuild it on a larger partition, preferably newer and larger drive for some time. Given it calls out a bad swap offset at the beginning of the bug / call trace text I suppose I could be running into issues with an overly full disk (though that seems a bit unlikely being different partitions and all.) I will go ahead and rebuild this system granting new, larger freshly formatted partitions and see if the problem goes away.
Well one thing you might try doing is running "ethtool --set-priv-flags <ethX> legacy-rx on" and seeing if you have the same problem or not. Turning on legacy Rx with this patch applied should only have the effect of adding padding to the front of the frame and will help to eliminate some of the code as being potentially responsible for this.
I'll look through this patch several times today and try to see if I can find anything that might be causing the issue.
- Alex
Brown
PATCH v3 6/9 igb: Add support for padding packet
Quoted 185 lines
From: Alexander Duyck [mailto:alexander.duyck at gmail.com]
Sent: Friday, February 3, 2017 9:58 AM
To: Brown, Aaron F <[email protected]>
Cc: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: Re: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetQuoted 1 line · Aaron F
Quoted 1 line
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at lists.osuosl.org]
On
Quoted 5 lines
Quoted 5 lines
Behalf Of Alexander Duyck
Sent: Monday, January 23, 2017 8:59 AM
To: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support forpadding
Quoted 5 lines
Quoted 5 lines
packet
From: Alexander Duyck <[email protected]>
With the size of the frame limited we can now write to an offset within
the
Quoted 7 lines
Quoted 7 lines
buffer instead of having to write at the very start of the buffer. The advantage to this is that it allows us to leave padding room for things like supporting XDP in the future.
One side effect of this patch is that we can end up using a larger buffer if jumbo frames is enabled. The impact shouldn't be too great, but it could hurt small packet performance for UDP workloads if jumbo frames
is
Quoted 10 lines
Quoted 10 lines
enabled as the truesize of frames will be larger.
Signed-off-by Alexander Duyck <[email protected]>---
v3: Fixed "unsigned char *" / "void *" mismatch on pointer arithmetic
drivers/net/ethernet/intel/igb/igb.h | 44 ++++++++++++- drivers/net/ethernet/intel/igb/igb_ethtool.c | 4 + drivers/net/ethernet/intel/igb/igb_main.c | 91+++++++++++++++++++--
Quoted 5 lines
Quoted 3 lines
-----
drivers/net/ethernet/intel/igb/igb_ptp.c | 3 - 4 files changed, 110 insertions(+), 32 deletions(-)I am having one (and only one) system dump on me when running
netperf_stress(multiple netperf sessions of varying sizes running in looped cycles.) The system itself is an older SuperMicro system with a pair of 82575EB LOMs. It's a rather dated system but I managed to locate another box of more or less the same era with 82575EB LOMs and am NOT seeing the dump there. I stripped off the other patches from this series and the problem does not appear with the first 5, but with this one on I get the system to crash. Usually it freezes or restarts, sometimes it just locks up the consoles. When it repeats or restarts it captures the trace to/var/log/messagesso I was able to grab this trace from there:Quoted 1 line
-------------------------------------------------------------------------------------------
-----
Quoted 1 line
Feb 2 15:08:00 u1485 xinetd[1866]: START: netperf pid=5528from=::ffff:190.1.4.85
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: swap_free: Bad swap offset entry
1c995c1d195b8Quoted 1 line
Feb 2 15:08:02 u1485 kernel: BUG: Bad page map in process sleeppte:72657074656e0066 pmd:7be3b067
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: addr:00007fdfedc00000 vm_flags:00000070
anon_vma: (null) mapping:ffff880079436cc0 index:1baQuoted 1 line
Feb 2 15:08:02 u1485 kernel: file:libc-2.12.so fault:ext4_filemap_fault[ext4] mmap:ext4_file_mmap [ext4] readpage:ext4_readpage [ext4]
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: CPU: 5 PID: 5526 Comm: sleep Tainted: GE 4.10.0-rc4_next-queue_regress #18
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: Hardware name: SupermicroX7DW3/X7DWN+, BIOS 1.2c 11/19/2010
Quoted 17 lines
Feb 2 15:08:02 u1485 kernel: Call Trace: Feb 2 15:08:02 u1485 kernel: dump_stack+0x51/0x78 Feb 2 15:08:02 u1485 kernel: ? ext4_bh_unmapped+0x20/0x20 [ext4] Feb 2 15:08:02 u1485 kernel: ? ext4_file_open+0x220/0x220 [ext4] Feb 2 15:08:02 u1485 kernel: print_bad_pte+0x1cd/0x280 Feb 2 15:08:02 u1485 kernel: zap_pte_range+0x5ab/0x640 Feb 2 15:08:02 u1485 kernel: ? pte_alloc_one_map+0x1c3/0x250 Feb 2 15:08:02 u1485 kernel: unmap_page_range+0x1f8/0x300 Feb 2 15:08:02 u1485 kernel: unmap_single_vma+0x60/0xe0 Feb 2 15:08:02 u1485 kernel: unmap_vmas+0x4b/0xa0 Feb 2 15:08:02 u1485 kernel: exit_mmap+0xbb/0x140 Feb 2 15:08:02 u1485 kernel: mmput+0x77/0x170 Feb 2 15:08:02 u1485 kernel: ? mm_release+0x57/0x140 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: exit_mm+0x140/0x1d0 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: ? exit_signals+0x150/0x170Quoted 8 lines
Feb 2 15:08:02 u1485 kernel: do_exit+0x12e/0x490 Feb 2 15:08:02 u1485 kernel: ? handle_mm_fault+0x87/0x190 Feb 2 15:08:02 u1485 kernel: ? filp_close+0x65/0x90 Feb 2 15:08:02 u1485 kernel: do_group_exit+0x4e/0xc0 Feb 2 15:08:02 u1485 kernel: SyS_exit_group+0x17/0x20 Feb 2 15:08:02 u1485 kernel: entry_SYSCALL_64_fastpath+0x13/0x94 Feb 2 15:08:02 u1485 kernel: RIP: 0033:0x7fdfedaf2df8 Feb 2 15:08:02 u1485 kernel: RSP: 002b:00007ffe94402408 EFLAGS:00000246
ORIG_RAX:00000000000000e7Quoted 1 line
Feb 2 15:08:02 u1485 kernel: RAX: ffffffffffffffda RBX: 00000000fbad2084RCX:
00007fdfedaf2df8Quoted 1 line
Feb 2 15:08:02 u1485 kernel: RDX: 0000000000000000 RSI:
000000000000003cRDI: 0000000000000000Quoted 1 line
Feb 2 15:08:02 u1485 kernel: RBP: 00007fdfeddd47a0 R08:
00000000000000e7R09:ffffffffffffffa8Quoted 1 line
Feb 2 15:08:02 u1485 kernel: R10: 0000000000000004 R11:0000000000000246 R12: 0000000000000000
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: R13: 00007ffe94402468 R14: 0000000000000001R15:
00007ffe94402460Quoted 2 lines
Feb 2 15:08:02 u1485 kernel: Disabling lock debugging due to kernel taint Feb 2 15:08:02 u1485 kernel: swap_free: Bad swap offset entry
1c995c1d195b8Quoted 1 line
Feb 2 15:08:02 u1485 kernel: BUG: Bad page map in process sleeppte:72657074656e0066 pmd:7be3b067
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: addr:00007fdfedc01000 vm_flags:00000070
anon_vma: (null) mapping:ffff880079436cc0 index:1bbQuoted 1 line
Feb 2 15:08:02 u1485 kernel: file:libc-2.12.so fault:ext4_filemap_fault[ext4] mmap:ext4_file_mmap [ext4] readpage:ext4_readpage [ext4]
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: CPU: 5 PID: 5526 Comm: sleep Tainted: G BE 4.10.0-rc4_next-queue_regress #18
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: Hardware name: SupermicroX7DW3/X7DWN+, BIOS 1.2c 11/19/2010
Quoted 17 lines
Feb 2 15:08:02 u1485 kernel: Call Trace: Feb 2 15:08:02 u1485 kernel: dump_stack+0x51/0x78 Feb 2 15:08:02 u1485 kernel: ? ext4_bh_unmapped+0x20/0x20 [ext4] Feb 2 15:08:02 u1485 kernel: ? ext4_file_open+0x220/0x220 [ext4] Feb 2 15:08:02 u1485 kernel: print_bad_pte+0x1cd/0x280 Feb 2 15:08:02 u1485 kernel: zap_pte_range+0x5ab/0x640 Feb 2 15:08:02 u1485 kernel: ? pte_alloc_one_map+0x1c3/0x250 Feb 2 15:08:02 u1485 kernel: unmap_page_range+0x1f8/0x300 Feb 2 15:08:02 u1485 kernel: unmap_single_vma+0x60/0xe0 Feb 2 15:08:02 u1485 kernel: unmap_vmas+0x4b/0xa0 Feb 2 15:08:02 u1485 kernel: exit_mmap+0xbb/0x140 Feb 2 15:08:02 u1485 kernel: mmput+0x77/0x170 Feb 2 15:08:02 u1485 kernel: ? mm_release+0x57/0x140 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: exit_mm+0x140/0x1d0 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: ? exit_signals+0x150/0x170Quoted 8 lines
Feb 2 15:08:02 u1485 kernel: do_exit+0x12e/0x490 Feb 2 15:08:02 u1485 kernel: ? handle_mm_fault+0x87/0x190 Feb 2 15:08:02 u1485 kernel: ? filp_close+0x65/0x90 Feb 2 15:08:02 u1485 kernel: do_group_exit+0x4e/0xc0 Feb 2 15:08:02 u1485 kernel: SyS_exit_group+0x17/0x20 Feb 2 15:08:02 u1485 kernel: entry_SYSCALL_64_fastpath+0x13/0x94 Feb 2 15:08:02 u1485 kernel: RIP: 0033:0x7fdfedaf2df8 Feb 2 15:08:02 u1485 kernel: RSP: 002b:00007ffe94402408 EFLAGS:00000246
ORIG_RAX:00000000000000e7Quoted 1 line
Feb 2 15:08:02 u1485 kernel: RAX: ffffffffffffffda RBX: 00000000fbad2084RCX:
00007fdfedaf2df8Quoted 1 line
Feb 2 15:08:02 u1485 kernel: RDX: 0000000000000000 RSI:
000000000000003cRDI: 0000000000000000Quoted 1 line
Feb 2 15:08:02 u1485 kernel: RBP: 00007fdfeddd47a0 R08:
00000000000000e7R09:ffffffffffffffa8Quoted 1 line
Feb 2 15:08:02 u1485 kernel: R10: 0000000000000004 R11:0000000000000246 R12: 0000000000000000
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: R13: 00007ffe94402468 R14: 0000000000000001R15:
00007ffe94402460Quoted 1 line
Feb 2 15:08:02 u1485 kernel: swap_free: Bad swap offset entry
1c995c1d195b8Quoted 1 line
Feb 2 15:08:02 u1485 kernel: BUG: Bad page map in process sleeppte:72657074656e0066 pmd:7be3b067
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: addr:00007fdfedc02000 vm_flags:00000070
anon_vma: (null) mapping:ffff880079436cc0 index:1bcQuoted 1 line
Feb 2 15:08:02 u1485 kernel: file:libc-2.12.so fault:ext4_filemap_fault[ext4] mmap:ext4_file_mmap [ext4] readpage:ext4_readpage [ext4]
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: CPU: 5 PID: 5526 Comm: sleep Tainted: G BE 4.10.0-rc4_next-queue_regress #18
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: Hardware name: SupermicroX7DW3/X7DWN+, BIOS 1.2c 11/19/2010
Quoted 2 lines
...
------------------------------------------------------------------------------------------------
Quoted 1 line
This call trace pattern repeated 7 ot 8 times and then the system either
rebooted on its own or simply locked up.
Quoted 2 lines
I am not entirely convinced it is not my hardware as I cannot reproduce the
issue on any other system. This one is very low on disk space and I have been meaning to rebuild it on a larger partition, preferably newer and larger drive for some time. Given it calls out a bad swap offset at the beginning of the bug / call trace text I suppose I could be running into issues with an overly full disk (though that seems a bit unlikely being different partitions and all.) I will go ahead and rebuild this system granting new, larger freshly formatted partitions and see if the problem goes away.
Quoted 6 lines
Well one thing you might try doing is running "ethtool --set-priv-flags <ethX> legacy-rx on" and seeing if you have the same problem or not. Turning on legacy Rx with this patch applied should only have the effect of adding padding to the front of the frame and will help to eliminate some of the code as being potentially responsible for this.
Well, I had wiped the old system before I got this message, but after rebuilding I still get a dump from running the same netperf_stress test. The trace has changed to a GPF and if I turn on legacy RX as you suggested netperf_stress continues to run fine and I do NOT get the dump. Here is a copy of the latest dump I got when running netperf_stress (and with legacy RX off.):
---------------------------------------------------------------
Feb 3 16:23:14 u1485 xinetd[2096]: START: netperf pid=4207 from=::ffff:190.2.4.85 Feb 3 16:23:15 u1485 xinetd[2096]: START: netperf pid=4237 from=::ffff:190.2.4.85 Feb 3 16:23:20 u1485 kernel: general protection fault: 0000 [#1] SMP Feb 3 16:23:20 u1485 kernel: Modules linked in: igb e100 ip6table_filter ip6_tables ebtable_nat ebtables nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT nf_reject_ipv4 xt_CHECKSUM iptable_mangle iptable_filter ip_tables bridge stp llc nfsd lockd grace nfs_acl auth_rpcgss sunrpc autofs4 ipv6 crc_ccitt dm_mirror dm_region_hash dm_log vhost_net macvtap macvlan vhost tun uinput iTCO_wdt iTCO_vendor_support mii sg joydev serio_raw i2c_i801 lpc_ich mfd_core dca ptp pps_core shpchp i5400_edac edac_core i5k_amb dm_mod(E) ext4(E) mbcache(E) jbd2(E) sd_mod(E) sr_mod(E) cdrom(E) pata_acpi(E) ata_generic(E) ata_piix(E) radeon(E) ttm(E) drm_kms_helper(E) drm(E) fb_sys_fops(E) sysimgblt(E) sysfillrect(E) syscopyarea(E) i2c_algo_bit(E) i2c_core(E) [last unloaded: e100] Feb 3 16:23:20 u1485 kernel: CPU: 7 PID: 77 Comm: kworker/7:1 Tainted: G E 4.10.0-rc4_next_dev_8b48872+ #1 Feb 3 16:23:20 u1485 kernel: Hardware name: Supermicro X7DW3/X7DWN+, BIOS 1.2c 11/19/2010 Feb 3 16:23:20 u1485 kernel: Workqueue: events_long gc_worker [nf_conntrack] Feb 3 16:23:20 u1485 kernel: task: ffff88007c608980 task.stack: ffffc900005bc000 Feb 3 16:23:20 u1485 kernel: RIP: 0010:gc_worker+0x94/0x1e0 [nf_conntrack] Feb 3 16:23:20 u1485 kernel: RSP: 0018:ffffc900005bfc20 EFLAGS: 00010246 Feb 3 16:23:20 u1485 kernel: RAX: 72657074656e0066 RBX: ffffffffa0290aa0 RCX: 000000000001b118 Feb 3 16:23:20 u1485 kernel: RDX: ffffc900005bfc40 RSI: 000000010003d572 RDI: ffff88006d0ad000 Feb 3 16:23:20 u1485 kernel: RBP: ffffc900005bfca0 R08: ffffc900005bfab0 R09: ffffc900005bfa90 Feb 3 16:23:20 u1485 kernel: R10: 0000000000000a0c R11: 0000000000000001 R12: 0000000000000eb9 Feb 3 16:23:20 u1485 kernel: R13: 0000000000000000 R14: 0000000000000003 R15: fffffffffffffff0 Feb 3 16:23:20 u1485 kernel: FS: 0000000000000000(0000) GS:ffff88007fdc0000(0000) knlGS:0000000000000000 Feb 3 16:23:20 u1485 kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 Feb 3 16:23:20 u1485 kernel: CR2: 00007f6c3623d000 CR3: 0000000069ef3000 CR4: 00000000000006e0 Feb 3 16:23:20 u1485 kernel: Call Trace: Feb 3 16:23:20 u1485 kernel: ? trace_event_raw_event_workqueue_execute_start+0x66/0xa0 Feb 3 16:23:20 u1485 kernel: process_one_work+0x19e/0x500 Feb 3 16:23:20 u1485 kernel: ? schedule+0x3a/0xa0 Feb 3 16:23:20 u1485 kernel: worker_thread+0x186/0x530 Feb 3 16:23:20 u1485 kernel: ? default_wake_function+0x12/0x20 Feb 3 16:23:20 u1485 kernel: ? maybe_create_worker+0x110/0x110 Feb 3 16:23:20 u1485 kernel: ? schedule+0x3a/0xa0 Feb 3 16:23:20 u1485 kernel: ? maybe_create_worker+0x110/0x110 Feb 3 16:23:20 u1485 kernel: kthread+0x103/0x140 Feb 3 16:23:20 u1485 kernel: ? __kthread_init_worker+0x40/0x40 Feb 3 16:23:20 u1485 kernel: ret_from_fork+0x29/0x40 Feb 3 16:23:20 u1485 kernel: Code: 75 da 41 39 f4 0f 82 f7 00 00 00 31 c0 45 31 e4 48 8d 04 01 48 8b 00 a8 01 48 89 45 b0 74 0c eb 61 48 8b 00 a8 01 48 89 02 75 57 <0f> b6 48 37 41 83 c6 01 48 8d 34 cd 00 00 00 00 48 c1 e1 06 48 Feb 3 16:23:20 u1485 kernel: RIP: gc_worker+0x94/0x1e0 [nf_conntrack] RSP: ffffc900005bfc20 Feb 3 16:23:20 u1485 kernel: ---[ end trace e0cac6f2424f4578 ]--- Feb 3 16:23:24 u1485 xinetd[2096]: EXIT: netperf status=0 pid=4207 duration=10(sec) Feb 3 16:23:25 u1485 xinetd[2096]: EXIT: netperf status=0 pid=4237 duration=10(sec)
---------------------------------------------------------------
In this case the system rebooted continued to run but rebooted itself shortly afterwards. An earlier instance it seemed to lock up.
Quoted 5 lines
I'll look through this patch several times today and try to see if I can find anything that might be causing the issue.
- Alex
PATCH v3 6/9 igb: Add support for padding packet
Quoted 185 lines · Aaron F
Quoted 185 lines
From: Alexander Duyck [mailto:alexander.duyck at gmail.com]
Sent: Friday, February 3, 2017 9:58 AM
To: Brown, Aaron F <[email protected]>
Cc: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: Re: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetQuoted 1 line · Aaron F
Quoted 1 line
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at lists.osuosl.org]
On
Quoted 5 lines
Quoted 5 lines
Behalf Of Alexander Duyck
Sent: Monday, January 23, 2017 8:59 AM
To: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support forpadding
Quoted 5 lines
Quoted 5 lines
packet
From: Alexander Duyck <[email protected]>
With the size of the frame limited we can now write to an offset within
the
Quoted 7 lines
Quoted 7 lines
buffer instead of having to write at the very start of the buffer. The advantage to this is that it allows us to leave padding room for things like supporting XDP in the future.
One side effect of this patch is that we can end up using a larger buffer if jumbo frames is enabled. The impact shouldn't be too great, but it could hurt small packet performance for UDP workloads if jumbo frames
is
Quoted 10 lines
Quoted 10 lines
enabled as the truesize of frames will be larger.
Signed-off-by Alexander Duyck <[email protected]>---
v3: Fixed "unsigned char *" / "void *" mismatch on pointer arithmetic
drivers/net/ethernet/intel/igb/igb.h | 44 ++++++++++++- drivers/net/ethernet/intel/igb/igb_ethtool.c | 4 + drivers/net/ethernet/intel/igb/igb_main.c | 91+++++++++++++++++++--
Quoted 5 lines
Quoted 3 lines
-----
drivers/net/ethernet/intel/igb/igb_ptp.c | 3 - 4 files changed, 110 insertions(+), 32 deletions(-)I am having one (and only one) system dump on me when running
netperf_stress(multiple netperf sessions of varying sizes running in looped cycles.) The system itself is an older SuperMicro system with a pair of 82575EB LOMs. It's a rather dated system but I managed to locate another box of more or less the same era with 82575EB LOMs and am NOT seeing the dump there. I stripped off the other patches from this series and the problem does not appear with the first 5, but with this one on I get the system to crash. Usually it freezes or restarts, sometimes it just locks up the consoles. When it repeats or restarts it captures the trace to/var/log/messagesso I was able to grab this trace from there:Quoted 1 line
-------------------------------------------------------------------------------------------
-----
Quoted 1 line
Feb 2 15:08:00 u1485 xinetd[1866]: START: netperf pid=5528from=::ffff:190.1.4.85
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: swap_free: Bad swap offset entry
1c995c1d195b8Quoted 1 line
Feb 2 15:08:02 u1485 kernel: BUG: Bad page map in process sleeppte:72657074656e0066 pmd:7be3b067
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: addr:00007fdfedc00000 vm_flags:00000070
anon_vma: (null) mapping:ffff880079436cc0 index:1baQuoted 1 line
Feb 2 15:08:02 u1485 kernel: file:libc-2.12.so fault:ext4_filemap_fault[ext4] mmap:ext4_file_mmap [ext4] readpage:ext4_readpage [ext4]
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: CPU: 5 PID: 5526 Comm: sleep Tainted: GE 4.10.0-rc4_next-queue_regress #18
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: Hardware name: SupermicroX7DW3/X7DWN+, BIOS 1.2c 11/19/2010
Quoted 17 lines
Feb 2 15:08:02 u1485 kernel: Call Trace: Feb 2 15:08:02 u1485 kernel: dump_stack+0x51/0x78 Feb 2 15:08:02 u1485 kernel: ? ext4_bh_unmapped+0x20/0x20 [ext4] Feb 2 15:08:02 u1485 kernel: ? ext4_file_open+0x220/0x220 [ext4] Feb 2 15:08:02 u1485 kernel: print_bad_pte+0x1cd/0x280 Feb 2 15:08:02 u1485 kernel: zap_pte_range+0x5ab/0x640 Feb 2 15:08:02 u1485 kernel: ? pte_alloc_one_map+0x1c3/0x250 Feb 2 15:08:02 u1485 kernel: unmap_page_range+0x1f8/0x300 Feb 2 15:08:02 u1485 kernel: unmap_single_vma+0x60/0xe0 Feb 2 15:08:02 u1485 kernel: unmap_vmas+0x4b/0xa0 Feb 2 15:08:02 u1485 kernel: exit_mmap+0xbb/0x140 Feb 2 15:08:02 u1485 kernel: mmput+0x77/0x170 Feb 2 15:08:02 u1485 kernel: ? mm_release+0x57/0x140 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: exit_mm+0x140/0x1d0 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: ? exit_signals+0x150/0x170Quoted 8 lines
Feb 2 15:08:02 u1485 kernel: do_exit+0x12e/0x490 Feb 2 15:08:02 u1485 kernel: ? handle_mm_fault+0x87/0x190 Feb 2 15:08:02 u1485 kernel: ? filp_close+0x65/0x90 Feb 2 15:08:02 u1485 kernel: do_group_exit+0x4e/0xc0 Feb 2 15:08:02 u1485 kernel: SyS_exit_group+0x17/0x20 Feb 2 15:08:02 u1485 kernel: entry_SYSCALL_64_fastpath+0x13/0x94 Feb 2 15:08:02 u1485 kernel: RIP: 0033:0x7fdfedaf2df8 Feb 2 15:08:02 u1485 kernel: RSP: 002b:00007ffe94402408 EFLAGS:00000246
ORIG_RAX:00000000000000e7Quoted 1 line
Feb 2 15:08:02 u1485 kernel: RAX: ffffffffffffffda RBX: 00000000fbad2084RCX:
00007fdfedaf2df8Quoted 1 line
Feb 2 15:08:02 u1485 kernel: RDX: 0000000000000000 RSI:
000000000000003cRDI: 0000000000000000Quoted 1 line
Feb 2 15:08:02 u1485 kernel: RBP: 00007fdfeddd47a0 R08:
00000000000000e7R09:ffffffffffffffa8Quoted 1 line
Feb 2 15:08:02 u1485 kernel: R10: 0000000000000004 R11:0000000000000246 R12: 0000000000000000
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: R13: 00007ffe94402468 R14: 0000000000000001R15:
00007ffe94402460Quoted 2 lines
Feb 2 15:08:02 u1485 kernel: Disabling lock debugging due to kernel taint Feb 2 15:08:02 u1485 kernel: swap_free: Bad swap offset entry
1c995c1d195b8Quoted 1 line
Feb 2 15:08:02 u1485 kernel: BUG: Bad page map in process sleeppte:72657074656e0066 pmd:7be3b067
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: addr:00007fdfedc01000 vm_flags:00000070
anon_vma: (null) mapping:ffff880079436cc0 index:1bbQuoted 1 line
Feb 2 15:08:02 u1485 kernel: file:libc-2.12.so fault:ext4_filemap_fault[ext4] mmap:ext4_file_mmap [ext4] readpage:ext4_readpage [ext4]
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: CPU: 5 PID: 5526 Comm: sleep Tainted: G BE 4.10.0-rc4_next-queue_regress #18
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: Hardware name: SupermicroX7DW3/X7DWN+, BIOS 1.2c 11/19/2010
Quoted 17 lines
Feb 2 15:08:02 u1485 kernel: Call Trace: Feb 2 15:08:02 u1485 kernel: dump_stack+0x51/0x78 Feb 2 15:08:02 u1485 kernel: ? ext4_bh_unmapped+0x20/0x20 [ext4] Feb 2 15:08:02 u1485 kernel: ? ext4_file_open+0x220/0x220 [ext4] Feb 2 15:08:02 u1485 kernel: print_bad_pte+0x1cd/0x280 Feb 2 15:08:02 u1485 kernel: zap_pte_range+0x5ab/0x640 Feb 2 15:08:02 u1485 kernel: ? pte_alloc_one_map+0x1c3/0x250 Feb 2 15:08:02 u1485 kernel: unmap_page_range+0x1f8/0x300 Feb 2 15:08:02 u1485 kernel: unmap_single_vma+0x60/0xe0 Feb 2 15:08:02 u1485 kernel: unmap_vmas+0x4b/0xa0 Feb 2 15:08:02 u1485 kernel: exit_mmap+0xbb/0x140 Feb 2 15:08:02 u1485 kernel: mmput+0x77/0x170 Feb 2 15:08:02 u1485 kernel: ? mm_release+0x57/0x140 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: exit_mm+0x140/0x1d0 Feb 2 15:08:02 u1485 kernel: ? down_read+0x16/0x40 Feb 2 15:08:02 u1485 kernel: ? exit_signals+0x150/0x170Quoted 8 lines
Feb 2 15:08:02 u1485 kernel: do_exit+0x12e/0x490 Feb 2 15:08:02 u1485 kernel: ? handle_mm_fault+0x87/0x190 Feb 2 15:08:02 u1485 kernel: ? filp_close+0x65/0x90 Feb 2 15:08:02 u1485 kernel: do_group_exit+0x4e/0xc0 Feb 2 15:08:02 u1485 kernel: SyS_exit_group+0x17/0x20 Feb 2 15:08:02 u1485 kernel: entry_SYSCALL_64_fastpath+0x13/0x94 Feb 2 15:08:02 u1485 kernel: RIP: 0033:0x7fdfedaf2df8 Feb 2 15:08:02 u1485 kernel: RSP: 002b:00007ffe94402408 EFLAGS:00000246
ORIG_RAX:00000000000000e7Quoted 1 line
Feb 2 15:08:02 u1485 kernel: RAX: ffffffffffffffda RBX: 00000000fbad2084RCX:
00007fdfedaf2df8Quoted 1 line
Feb 2 15:08:02 u1485 kernel: RDX: 0000000000000000 RSI:
000000000000003cRDI: 0000000000000000Quoted 1 line
Feb 2 15:08:02 u1485 kernel: RBP: 00007fdfeddd47a0 R08:
00000000000000e7R09:ffffffffffffffa8Quoted 1 line
Feb 2 15:08:02 u1485 kernel: R10: 0000000000000004 R11:0000000000000246 R12: 0000000000000000
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: R13: 00007ffe94402468 R14: 0000000000000001R15:
00007ffe94402460Quoted 1 line
Feb 2 15:08:02 u1485 kernel: swap_free: Bad swap offset entry
1c995c1d195b8Quoted 1 line
Feb 2 15:08:02 u1485 kernel: BUG: Bad page map in process sleeppte:72657074656e0066 pmd:7be3b067
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: addr:00007fdfedc02000 vm_flags:00000070
anon_vma: (null) mapping:ffff880079436cc0 index:1bcQuoted 1 line
Feb 2 15:08:02 u1485 kernel: file:libc-2.12.so fault:ext4_filemap_fault[ext4] mmap:ext4_file_mmap [ext4] readpage:ext4_readpage [ext4]
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: CPU: 5 PID: 5526 Comm: sleep Tainted: G BE 4.10.0-rc4_next-queue_regress #18
Quoted 1 line
Feb 2 15:08:02 u1485 kernel: Hardware name: SupermicroX7DW3/X7DWN+, BIOS 1.2c 11/19/2010
Quoted 2 lines
...
------------------------------------------------------------------------------------------------
Quoted 1 line
This call trace pattern repeated 7 ot 8 times and then the system either
rebooted on its own or simply locked up.
Quoted 2 lines
I am not entirely convinced it is not my hardware as I cannot reproduce the
issue on any other system. This one is very low on disk space and I have been meaning to rebuild it on a larger partition, preferably newer and larger drive for some time. Given it calls out a bad swap offset at the beginning of the bug / call trace text I suppose I could be running into issues with an overly full disk (though that seems a bit unlikely being different partitions and all.) I will go ahead and rebuild this system granting new, larger freshly formatted partitions and see if the problem goes away.
Quoted 8 lines
Quoted 6 lines
Well one thing you might try doing is running "ethtool --set-priv-flags <ethX> legacy-rx on" and seeing if you have the same problem or not. Turning on legacy Rx with this patch applied should only have the effect of adding padding to the front of the frame and will help to eliminate some of the code as being potentially responsible for this.
Well, I had wiped the old system before I got this message, but after rebuilding I still get a dump from running the same
netperf_stresstest. The trace has changed to a GPF and if I turn on legacy RX as you suggestednetperf_stresscontinues to run fine and I do NOT get the dump. Here is a copy of the latest dump I got when runningnetperf_stress(and with legacy RX off.):
Okay so that gives me a bit to go on. If I am not mistaken that system has support for VTd, do you have that enabled in your kernel or is it disabled?
What I did is break the patch up into smaller steps. If possible try the v4 set and if you still see the issue I would recommend trying a bisection between patches 6 and 10 to see at which point the issue starts to occur. My theory is it will either be patch 7 or patch 10. The others shouldn't have an impact but it doesn't hurt to verify it.
If nothing else I can probably come by the lab on Tuesday to take a look in person and do some further debugging.
Thanks.
- Alex
Brown
PATCH v3 6/9 igb: Add support for padding packet
Quoted 53 lines
-----Original Message-----
From: Alexander Duyck [mailto:alexander.duyck at gmail.com]
Sent: Sunday, February 5, 2017 8:45 PM
To: Brown, Aaron F <[email protected]>
Cc: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: Re: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetQuoted 9 lines · Aaron F
Quoted 9 lines
From: Alexander Duyck [mailto:alexander.duyck at gmail.com]
Sent: Friday, February 3, 2017 9:58 AM
To: Brown, Aaron F <[email protected]>
Cc: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: Re: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetOn Thu, Feb 2, 2017 at 8:01 PM, Brown, Aaron F
Quoted 2 lines
Quoted 2 lines
Quoted 1 line · wrote:
Quoted 1 line
From: Intel-wired-lan [mailto:intel-wired-lan-
bounces at lists.osuosl.org]
Quoted 12 lines
Quoted 12 lines
On
Quoted 5 lines
Quoted 5 lines
Behalf Of Alexander Duyck
Sent: Monday, January 23, 2017 8:59 AM
To: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support forpadding
Quoted 5 lines
Quoted 5 lines
packet
From: Alexander Duyck <[email protected]>
With the size of the frame limited we can now write to an offset within
Quoted 8 lines
Quoted 8 lines
the
Quoted 7 lines
Quoted 7 lines
buffer instead of having to write at the very start of the buffer. The advantage to this is that it allows us to leave padding room for things like supporting XDP in the future.
One side effect of this patch is that we can end up using a larger buffer if jumbo frames is enabled. The impact shouldn't be too great, but it could hurt small packet performance for UDP workloads if jumbo
frames
Quoted 6 lines
Quoted 6 lines
is
Quoted 5 lines
Quoted 5 lines
enabled as the truesize of frames will be larger.
Signed-off-by Alexander Duyck <[email protected]>---
<snip>
Quoted 15 lines
Quoted 9 lines
Quoted 7 lines
Well one thing you might try doing is running "ethtool --set-priv-flags <ethX> legacy-rx on" and seeing if you have the same problem or not. Turning on legacy Rx with this patch applied should only have the effect of adding padding to the front of the frame and will help to eliminate some of the code as being potentially responsible for this.
Well, I had wiped the old system before I got this message, but after
rebuilding I still get a dump from running the same
netperf_stresstest. The trace has changed to a GPF and if I turn on legacy RX as you suggestednetperf_stresscontinues to run fine and I do NOT get the dump. Here is a copy of the latest dump I got when runningnetperf_stress(and with legacy RX off.):
Quoted 3 lines
Okay so that gives me a bit to go on. If I am not mistaken that system has support for VTd, do you have that enabled in your kernel or is it disabled?
Yes, the system is supposed to be capable of VTd, it was disable in BIOS and kernel when I was running into this last week. I enabled in BIOS and added the intel_iommu=on line to the boot stanza and am still seeing the dump when I run it.
Quoted 6 lines
What I did is break the patch up into smaller steps. If possible try the v4 set and if you still see the issue I would recommend trying a bisection between patches 6 and 10 to see at which point the issue starts to occur. My theory is it will either be patch 7 or patch 10. The others shouldn't have an impact but it doesn't hurt to verify it.
Will do...
Quoted 7 lines
If nothing else I can probably come by the lab on Tuesday to take a look in person and do some further debugging.
Thanks.
- Alex
Brown
PATCH v3 6/9 igb: Add support for padding packet
In reply to Alexander DuyckQuoted 82 lines
-----Original Message-----
From: Brown, Aaron F
Sent: Monday, February 6, 2017 3:21 PM
To: 'Alexander Duyck' <[email protected]>
Cc: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: RE: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetQuoted 20 lines
-----Original Message-----
From: Alexander Duyck [mailto:alexander.duyck at gmail.com]
Sent: Sunday, February 5, 2017 8:45 PM
To: Brown, Aaron F <[email protected]>
Cc: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: Re: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetQuoted 8 lines · Aaron F
Quoted 8 lines
From: Alexander Duyck [mailto:alexander.duyck at gmail.com]
Sent: Friday, February 3, 2017 9:58 AM
To: Brown, Aaron F <[email protected]>
Cc: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: Re: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetQuoted 17 lines
Quoted 1 line
Quoted 1 line
On Thu, Feb 2, 2017 at 8:01 PM, Brown, Aaron F
Quoted 2 lines
Quoted 2 lines
Quoted 1 line · wrote:
Quoted 1 line
From: Intel-wired-lan [mailto:intel-wired-lan-
bounces at lists.osuosl.org]
Quoted 12 lines
Quoted 12 lines
On
Quoted 5 lines
Quoted 5 lines
Behalf Of Alexander Duyck
Sent: Monday, January 23, 2017 8:59 AM
To: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support forpadding
Quoted 5 lines
Quoted 5 lines
packet
From: Alexander Duyck <[email protected]>
With the size of the frame limited we can now write to an offset
within
Quoted 6 lines
Quoted 6 lines
Quoted 6 lines
the
Quoted 5 lines
Quoted 5 lines
buffer instead of having to write at the very start of the buffer. The advantage to this is that it allows us to leave padding room for things like supporting XDP in the future.
One side effect of this patch is that we can end up using a larger
buffer
Quoted 9 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
if jumbo frames is enabled. The impact shouldn't be too great, but it could hurt small packet performance for UDP workloads if jumbo
frames
Quoted 6 lines
Quoted 6 lines
is
Quoted 5 lines
Quoted 5 lines
enabled as the truesize of frames will be larger.
Signed-off-by Alexander Duyck <[email protected]>---
<snip>
Quoted 10 lines
Quoted 9 lines
Quoted 7 lines
Well one thing you might try doing is running "ethtool --set-priv-flags <ethX> legacy-rx on" and seeing if you have the same problem or not. Turning on legacy Rx with this patch applied should only have the effect of adding padding to the front of the frame and will help to eliminate some of the code as being potentially responsible for this.
Well, I had wiped the old system before I got this message, but after
rebuilding I still get a dump from running the same
netperf_stresstest.The
Quoted 5 lines
trace has changed to a GPF and if I turn on legacy RX as you suggested
netperf_stresscontinues to run fine and I do NOT get the dump. Here is a copy of the latest dump I got when runningnetperf_stress(and with legacy RX off.):
Quoted 8 lines
Quoted 3 lines
Okay so that gives me a bit to go on. If I am not mistaken that system has support for VTd, do you have that enabled in your kernel or is it disabled?
Yes, the system is supposed to be capable of VTd, it was disable in BIOS and kernel when I was running into this last week. I enabled in BIOS and added the intel_iommu=on line to the boot stanza and am still seeing the dump when I run it.
Looks like I spoke to soon about VTd truly being enabled. It was enabled in BIOS and the stanza set, but INTEL_IOMMU was not set in the kernel's .config file. I've fixed that now, rebuilt, rebooted, and now the system is running the netperf_stress continually without a crash for far longer than it had earlier. However, I am still getting a message in the log, every few seconds I will see the following splatted to dmesg:
--------------------------------------------------------------------------------------------------------
DMAR: DRHD: handling fault status reg 2
DMAR: [DMA Write] Request device [08:00.1] fault addr ff9f1000 [fault reason 05] PTE Write access is not set
--------------------------------------------------------------------------------------------------------
The called out device, 08:00.1, is the slot for the NIC that is engaged in the netperf_stress test.
So, still a problem, but changed and not as drastic.
Quoted 16 lines
Quoted 6 lines
What I did is break the patch up into smaller steps. If possible try the v4 set and if you still see the issue I would recommend trying a bisection between patches 6 and 10 to see at which point the issue starts to occur. My theory is it will either be patch 7 or patch 10. The others shouldn't have an impact but it doesn't hurt to verify it.
Will do...
Quoted 7 lines
If nothing else I can probably come by the lab on Tuesday to take a look in person and do some further debugging.
Thanks.
- Alex
PATCH v3 6/9 igb: Add support for padding packet
Quoted 97 lines · Aaron F
Quoted 82 lines
-----Original Message-----
From: Brown, Aaron F
Sent: Monday, February 6, 2017 3:21 PM
To: 'Alexander Duyck' <[email protected]>
Cc: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: RE: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetQuoted 20 lines
-----Original Message-----
From: Alexander Duyck [mailto:alexander.duyck at gmail.com]
Sent: Sunday, February 5, 2017 8:45 PM
To: Brown, Aaron F <[email protected]>
Cc: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: Re: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetQuoted 8 lines · Aaron F
Quoted 8 lines
From: Alexander Duyck [mailto:alexander.duyck at gmail.com]
Sent: Friday, February 3, 2017 9:58 AM
To: Brown, Aaron F <[email protected]>
Cc: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: Re: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetQuoted 17 lines
Quoted 1 line
Quoted 1 line
On Thu, Feb 2, 2017 at 8:01 PM, Brown, Aaron F
Quoted 2 lines
Quoted 2 lines
Quoted 1 line · wrote:
Quoted 1 line
From: Intel-wired-lan [mailto:intel-wired-lan-
bounces at lists.osuosl.org]
Quoted 12 lines
Quoted 12 lines
On
Quoted 5 lines
Quoted 5 lines
Behalf Of Alexander Duyck
Sent: Monday, January 23, 2017 8:59 AM
To: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support forpadding
Quoted 5 lines
Quoted 5 lines
packet
From: Alexander Duyck <[email protected]>
With the size of the frame limited we can now write to an offset
within
Quoted 6 lines
Quoted 6 lines
Quoted 6 lines
the
Quoted 5 lines
Quoted 5 lines
buffer instead of having to write at the very start of the buffer. The advantage to this is that it allows us to leave padding room for things like supporting XDP in the future.
One side effect of this patch is that we can end up using a larger
buffer
Quoted 9 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
if jumbo frames is enabled. The impact shouldn't be too great, but it could hurt small packet performance for UDP workloads if jumbo
frames
Quoted 6 lines
Quoted 6 lines
is
Quoted 5 lines
Quoted 5 lines
enabled as the truesize of frames will be larger.
Signed-off-by Alexander Duyck <[email protected]>---
<snip>
Quoted 10 lines
Quoted 9 lines
Quoted 7 lines
Well one thing you might try doing is running "ethtool --set-priv-flags <ethX> legacy-rx on" and seeing if you have the same problem or not. Turning on legacy Rx with this patch applied should only have the effect of adding padding to the front of the frame and will help to eliminate some of the code as being potentially responsible for this.
Well, I had wiped the old system before I got this message, but after
rebuilding I still get a dump from running the same
netperf_stresstest.The
Quoted 5 lines
trace has changed to a GPF and if I turn on legacy RX as you suggested
netperf_stresscontinues to run fine and I do NOT get the dump. Here is a copy of the latest dump I got when runningnetperf_stress(and with legacy RX off.):Quoted 8 lines
Quoted 3 lines
Okay so that gives me a bit to go on. If I am not mistaken that system has support for VTd, do you have that enabled in your kernel or is it disabled?
Yes, the system is supposed to be capable of VTd, it was disable in BIOS and kernel when I was running into this last week. I enabled in BIOS and added the intel_iommu=on line to the boot stanza and am still seeing the dump when I run it.
Looks like I spoke to soon about VTd truly being enabled. It was enabled in BIOS and the stanza set, but
INTEL_IOMMUwas not set in the kernel's .config file. I've fixed that now, rebuilt, rebooted, and now the system is running thenetperf_stresscontinually without a crash for far longer than it had earlier. However, I am still getting a message in the log, every few seconds I will see the following splatted to dmesg:
--------------------------------------------------------------------------------------------------------
DMAR: DRHD: handling fault status reg 2
DMAR: [DMA Write] Request device [08:00.1] fault addrff9f1000[fault reason 05] PTE Write access is not set
--------------------------------------------------------------------------------------------------------
Quoted 3 lines
The called out device, 08:00.1, is the slot for the NIC that is engaged in the
netperf_stresstest.So, still a problem, but changed and not as drastic.
Okay, so that gives me more to go on. It looks like we are attempting to write to pages that we don't have access to. I suspect we are somehow writing a 2K buffer even though we are only supposed to be using 1514 bytes and overflowing the end of the page.
Can you send me an ethregs dump for the port? I'm curious what the configuration for the registers is.
Thanks.
- Alex
PATCH v3 6/9 igb: Add support for padding packet
Quoted 107 lines · Alexander Duyck
Quoted 97 lines · Aaron F
Quoted 82 lines
-----Original Message-----
From: Brown, Aaron F
Sent: Monday, February 6, 2017 3:21 PM
To: 'Alexander Duyck' <[email protected]>
Cc: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: RE: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetQuoted 20 lines
-----Original Message-----
From: Alexander Duyck [mailto:alexander.duyck at gmail.com]
Sent: Sunday, February 5, 2017 8:45 PM
To: Brown, Aaron F <[email protected]>
Cc: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: Re: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetQuoted 8 lines · Aaron F
Quoted 8 lines
From: Alexander Duyck [mailto:alexander.duyck at gmail.com]
Sent: Friday, February 3, 2017 9:58 AM
To: Brown, Aaron F <[email protected]>
Cc: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: Re: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support for padding packetQuoted 17 lines
Quoted 1 line
Quoted 1 line
On Thu, Feb 2, 2017 at 8:01 PM, Brown, Aaron F
Quoted 2 lines
Quoted 2 lines
Quoted 1 line · wrote:
Quoted 1 line
From: Intel-wired-lan [mailto:intel-wired-lan-
bounces at lists.osuosl.org]
Quoted 12 lines
Quoted 12 lines
On
Quoted 5 lines
Quoted 5 lines
Behalf Of Alexander Duyck
Sent: Monday, January 23, 2017 8:59 AM
To: intel-wired-lan at lists.osuosl.org; Kirsher, Jeffrey T <[email protected]>
Subject: [Intel-wired-lan] [next PATCH v3 6/9] igb: Add support forpadding
Quoted 5 lines
Quoted 5 lines
packet
From: Alexander Duyck <[email protected]>
With the size of the frame limited we can now write to an offset
within
Quoted 6 lines
Quoted 6 lines
Quoted 6 lines
the
Quoted 5 lines
Quoted 5 lines
buffer instead of having to write at the very start of the buffer. The advantage to this is that it allows us to leave padding room for things like supporting XDP in the future.
One side effect of this patch is that we can end up using a larger
buffer
Quoted 9 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
if jumbo frames is enabled. The impact shouldn't be too great, but it could hurt small packet performance for UDP workloads if jumbo
frames
Quoted 6 lines
Quoted 6 lines
is
Quoted 5 lines
Quoted 5 lines
enabled as the truesize of frames will be larger.
Signed-off-by Alexander Duyck <[email protected]>---
<snip>
Quoted 10 lines
Quoted 9 lines
Quoted 7 lines
Well one thing you might try doing is running "ethtool --set-priv-flags <ethX> legacy-rx on" and seeing if you have the same problem or not. Turning on legacy Rx with this patch applied should only have the effect of adding padding to the front of the frame and will help to eliminate some of the code as being potentially responsible for this.
Well, I had wiped the old system before I got this message, but after
rebuilding I still get a dump from running the same
netperf_stresstest.The
Quoted 5 lines
trace has changed to a GPF and if I turn on legacy RX as you suggested
netperf_stresscontinues to run fine and I do NOT get the dump. Here is a copy of the latest dump I got when runningnetperf_stress(and with legacy RX off.):Quoted 8 lines
Quoted 3 lines
Okay so that gives me a bit to go on. If I am not mistaken that system has support for VTd, do you have that enabled in your kernel or is it disabled?
Yes, the system is supposed to be capable of VTd, it was disable in BIOS and kernel when I was running into this last week. I enabled in BIOS and added the intel_iommu=on line to the boot stanza and am still seeing the dump when I run it.
Looks like I spoke to soon about VTd truly being enabled. It was enabled in BIOS and the stanza set, but
INTEL_IOMMUwas not set in the kernel's .config file. I've fixed that now, rebuilt, rebooted, and now the system is running thenetperf_stresscontinually without a crash for far longer than it had earlier. However, I am still getting a message in the log, every few seconds I will see the following splatted to dmesg:
--------------------------------------------------------------------------------------------------------
DMAR: DRHD: handling fault status reg 2
DMAR: [DMA Write] Request device [08:00.1] fault addrff9f1000[fault reason 05] PTE Write access is not set
--------------------------------------------------------------------------------------------------------Quoted 3 lines
The called out device, 08:00.1, is the slot for the NIC that is engaged in the
netperf_stresstest.So, still a problem, but changed and not as drastic.
Okay, so that gives me more to go on. It looks like we are attempting to write to pages that we don't have access to. I suspect we are somehow writing a 2K buffer even though we are only supposed to be using 1514 bytes and overflowing the end of the page.
Quoted 6 lines
Can you send me an ethregs dump for the port? I'm curious what the configuration for the registers is.
Thanks.
- Alex
Never mind. I think I found the bug. We weren't locking down RLPML on 82575, i210, or i211. I made the mistake of not noticing an if statement that was calling return in igb_set_rx_mode.
I should have a new version out shortly with a fix for the issue.
PATCH v3 7/9 igb: Add support for ethtool private flag to allow use of legacy Rx
In reply to Alexander DuyckFrom: Alexander Duyck <[email protected]>
Since there are potential drawbacks to the new Rx allocation approach I thought it best to add a "chicken bit" so that we can turn the feature off if in the event that a problem is found.
It also provides a means of validating the legacy Rx path in the event that we are forced to fall back. At some point in the future when we are convinced we don't need it anymore we might be able to drop the legacy-rx flag.
--- drivers/net/ethernet/intel/igb/igb_ethtool.c | 48 ++++++++++++++++++++++++++ 1 file changed, 48 insertions(+)
drivers/net/ethernet/intel/igb/igb_ethtool.c +48 -0
@@ -144,6 +144,13 @@ enum igb_diagnostics_results { };#define IGB_TEST_LEN (sizeof(igb_gstrings_test) / ETH_GSTRING_LEN) +static const char igb_priv_flags_strings[][ETH_GSTRING_LEN ] = { +#define IGB_PRIV_FLAGS_LEGACY_RX BIT(0) +"legacy-rx" , +}; + +#define IGB_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igb_priv_flags_strings) +static int igb_get_settings (struct net_device *netdev,struct ethtool_cmd *ecmd) {struct igb_adapter *adapter =netdev_priv (netdev);
@@ -852,6 +859,8 @@ static void igb_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->fw_version));strlcpy (drvinfo->bus_info,pci_name (adapter->pdev),sizeof (drvinfo->bus_info)); + + drvinfo->n_priv_flags =IGB_PRIV_FLAGS_STR_LEN ; } static void igb_get_ringparam(struct net_device *netdev,
@@ -2280,6 +2289,8 @@ static int igb_get_sset_count(struct net_device *netdev, int sset)return IGB_STATS_LEN ;case ETH_SS_TEST :return IGB_TEST_LEN ; +case ETH_SS_PRIV_FLAGS : +return IGB_PRIV_FLAGS_STR_LEN ;default :return -ENOTSUPP ; }
@@ -2385,6 +2396,10 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) }/* BUG_ON(p - data != IGB_STATS_LEN * ETH_GSTRING_LEN); */ break ; +case ETH_SS_PRIV_FLAGS : +memcpy (data, igb_priv_flags_strings, +IGB_PRIV_FLAGS_STR_LEN *ETH_GSTRING_LEN ); +break ; } }
@@ -3397,6 +3412,37 @@ static int igb_set_channels(struct net_device *netdev,return 0 ; } +static u32 igb_get_priv_flags (struct net_device *netdev) +{ +struct igb_adapter *adapter =netdev_priv (netdev); +u32 priv_flags =0 ; + +if (adapter->flags &IGB_FLAG_RX_LEGACY ) + priv_flags |=IGB_PRIV_FLAGS_LEGACY_RX ; + +return priv_flags; +} + +static int igb_set_priv_flags (struct net_device *netdev,u32 priv_flags) +{ +struct igb_adapter *adapter =netdev_priv (netdev); +unsigned int flags = adapter->flags; + + flags &= ~IGB_FLAG_RX_LEGACY ; +if (priv_flags &IGB_PRIV_FLAGS_LEGACY_RX ) + flags |=IGB_FLAG_RX_LEGACY ; + +if (flags != adapter->flags) { + adapter->flags = flags; + +/* reset interface to repopulate queues */ +if (netif_running (netdev)) +igb_reinit_locked (adapter); + } + +return 0 ; +} +static const struct ethtool_ops igb_ethtool_ops = { .get_settings = igb_get_settings, .set_settings = igb_set_settings,
@@ -3435,6 +3481,8 @@ static int igb_set_channels(struct net_device *netdev, .set_rxfh = igb_set_rxfh, .get_channels = igb_get_channels, .set_channels = igb_set_channels, + .get_priv_flags = igb_get_priv_flags, + .set_priv_flags = igb_set_priv_flags, .begin = igb_ethtool_begin, .complete = igb_ethtool_complete, };
PATCH v3 8/9 igb: Break out Rx buffer page management
In reply to Alexander DuyckFrom: Alexander Duyck <[email protected]>
At this point we have 2 to 3 paths that can be taken depending on what Rx modes are enabled. In order to better support that and improve the maintainability I am breaking out the common bits from those paths and making them into their own functions.
---
v3: Rebase patch on v3 changes to fix pointer arithmetic mismatch
drivers/net/ethernet/intel/igb/igb_main.c | 237 +++++++++++++++-------------- 1 file changed, 123 insertions(+), 114 deletions(-)
drivers/net/ethernet/intel/igb/igb_main.c +123 -114
@@ -6883,8 +6883,14 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring, nta++; rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta :0 ; -/* transfer page from old buffer to new buffer */ - *new_buff = *old_buff; +/* Transfer page from old buffer to new buffer. +* Move each member individually to avoid possible store +* forwarding stalls. +*/ + new_buff->dma = old_buff->dma; + new_buff->page = old_buff->page; + new_buff->page_offset = old_buff->page_offset; + new_buff->pagecnt_bias = old_buff->pagecnt_bias; }static inline bool igb_page_is_reserved (struct page *page)
@@ -6892,11 +6898,10 @@ static inline bool igb_page_is_reserved(struct page *page)return (page_to_nid (page) !=numa_mem_id ()) ||page_is_pfmemalloc (page); } -static bool igb_can_reuse_rx_page (struct igb_rx_buffer *rx_buffer, -struct page *page, -const unsigned int truesize) +static bool igb_can_reuse_rx_page (struct igb_rx_buffer *rx_buffer) { -unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--; +unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; +struct page *page = rx_buffer->page;/* avoid re-using remote pages */ if (unlikely (igb_page_is_reserved (page)))
@@ -6904,14 +6909,9 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,#if (PAGE_SIZE <8192 )/* if we are only owner of page we can reuse it */ -if (unlikely (page_ref_count (page) != pagecnt_bias)) +if (unlikely ((page_ref_count (page) - pagecnt_bias) >1 ))return false; - -/* flip page offset to other buffer */ - rx_buffer->page_offset ^= truesize;#else -/* move offset up to the next cache line */ - rx_buffer->page_offset += truesize;#define IGB_LAST_OFFSET \ (SKB_WITH_OVERHEAD(PAGE_SIZE) - IGB_RXBUFFER_2048)
@@ -6923,7 +6923,7 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,* the pagecnt_bias and page count so that we fully restock the * number of references the driver holds. */ -if (unlikely (pagecnt_bias ==1 )) { +if (unlikely (!pagecnt_bias)) {page_ref_add (page,USHRT_MAX ); rx_buffer->pagecnt_bias =USHRT_MAX ; }
@@ -6935,26 +6935,16 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,* igb_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: buffer containing page to add -* @rx_desc: descriptor containing length of buffer written by hardware * @skb: sk_buff to place the data into +* @size: size of buffer to be added * * This function will add the data contained in rx_buffer->page to the skb. -* This is done either through a direct copy if the data in the buffer is -* less than the skb header size, otherwise it will just attach the page as -* a frag to the skb. -* -* The function will then update the page offset if necessary and return -* true if the buffer can be reused by the adapter. **/ -static bool igb_add_rx_frag (struct igb_ring *rx_ring, +static void igb_add_rx_frag (struct igb_ring *rx_ring,struct igb_rx_buffer *rx_buffer, -unsigned int size, -union e1000_adv_rx_desc *rx_desc, -struct sk_buff *skb) +struct sk_buff *skb, +unsigned int size) { -struct page *page = rx_buffer->page; -void *va =page_address (page) + rx_buffer->page_offset; -unsigned int pull_len;#if (PAGE_SIZE <8192 )unsigned int truesize =igb_rx_pg_size (rx_ring) /2 ;#else
@@ -6962,9 +6952,39 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, SKB_DATA_ALIGN(IGB_SKB_PAD + size) :SKB_DATA_ALIGN (size);#endif +skb_add_rx_frag (skb,skb_shinfo (skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); +#if (PAGE_SIZE <8192 ) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} + +static struct sk_buff *igb_construct_skb (struct igb_ring *rx_ring, +struct igb_rx_buffer *rx_buffer, +union e1000_adv_rx_desc *rx_desc, +unsigned int size) +{ +void *va =page_address (rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE <8192 ) +unsigned int truesize =igb_rx_pg_size (rx_ring) /2 ; +#else +unsigned int truesize =SKB_DATA_ALIGN (size); +#endif +unsigned int headlen; +struct sk_buff *skb; -if (unlikely (skb_is_nonlinear (skb))) - goto add_tail_frag; +/* prefetch first cache line of first page */ +prefetch (va); +#if L1_CACHE_BYTES <128 +prefetch (va +L1_CACHE_BYTES ); +#endif + +/* allocate a skb to store the frags */ + skb =napi_alloc_skb (&rx_ring->q_vector->napi,IGB_RX_HDR_LEN ); +if (unlikely (!skb)) +return NULL ;if (unlikely (igb_test_staterr (rx_desc,E1000_RXDADV_STAT_TSIP ))) {igb_ptp_rx_pktstamp (rx_ring->q_vector, va, skb);
@@ -6972,95 +6992,31 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, size -=IGB_TS_HDR_LEN ; } -if (likely (size <=IGB_RX_HDR_LEN )) { -memcpy (__skb_put (skb, size), va,ALIGN (size,sizeof (long ))); - -/* page is not reserved, we can reuse buffer as-is */ -if (likely (!igb_page_is_reserved (page))) -return true; - -/* this page cannot be reused so discard it */ -return false; - } - -/* we need the header to contain the greater of either ETH_HLEN or -* 60 bytes if the skb->len is less than 60 for skb_pad. -*/ - pull_len =eth_get_headlen (va,IGB_RX_HDR_LEN ); +/* Determine available headroom for copy */ + headlen = size; +if (headlen >IGB_RX_HDR_LEN ) + headlen =eth_get_headlen (va,IGB_RX_HDR_LEN ); +else + headlen = size;/* align pull length to size of long to optimize memcpy performance */ -memcpy (__skb_put (skb, pull_len), va,ALIGN (pull_len,sizeof (long ))); +memcpy (__skb_put (skb, headlen), va,ALIGN (headlen,sizeof (long )));/* update all of the pointers */ - va += pull_len; - size -= pull_len; - -add_tail_frag: -skb_add_rx_frag (skb,skb_shinfo (skb)->nr_frags, page, - va -page_address (page), size, truesize); - -return igb_can_reuse_rx_page (rx_buffer, page, truesize); -} - -static struct sk_buff *igb_fetch_rx_buffer (struct igb_ring *rx_ring, -union e1000_adv_rx_desc *rx_desc, -struct sk_buff *skb) -{ -unsigned int size =le16_to_cpu (rx_desc->wb.upper.length); -struct igb_rx_buffer *rx_buffer; -struct page *page; - - rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; - page = rx_buffer->page; -prefetchw (page); - -/* we are reusing so sync this buffer for CPU use */ -dma_sync_single_range_for_cpu (rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - size, -DMA_FROM_DEVICE ); - -if (likely (!skb)) { -void *va =page_address (page) + rx_buffer->page_offset; - -/* prefetch first cache line of first page */ -prefetch (va); -#if L1_CACHE_BYTES <128 -prefetch (va +L1_CACHE_BYTES ); + size -= headlen; +if (size) { +skb_add_rx_frag (skb,0 , rx_buffer->page, + (va + headlen) -page_address (rx_buffer->page), + size, truesize); +#if (PAGE_SIZE <8192 ) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize;#endif - -/* allocate a skb to store the frags */ - skb =napi_alloc_skb (&rx_ring->q_vector->napi,IGB_RX_HDR_LEN ); -if (unlikely (!skb)) { - rx_ring->rx_stats.alloc_failed++; -return NULL ; - } - -/* we will be copying header into skb->data in -* pskb_may_pull so it is in our interest to prefetch -* it now to avoid a possible cache miss -*/ -prefetchw (skb->data); - } - -/* pull page into skb */ -if (igb_add_rx_frag (rx_ring, rx_buffer, size, rx_desc, skb)) { -/* hand second half of page back to the ring */ -igb_reuse_rx_page (rx_ring, rx_buffer); }else { -/* We are not reusing the buffer so unmap it and free -* any references we are holding to it -*/ -dma_unmap_page_attrs (rx_ring->dev, rx_buffer->dma, -igb_rx_pg_size (rx_ring),DMA_FROM_DEVICE , -IGB_RX_DMA_ATTR ); -__page_frag_cache_drain (page, rx_buffer->pagecnt_bias); + rx_buffer->pagecnt_bias++; } -/* clear contents of rx_buffer */ - rx_buffer->page =NULL ; -return skb; }
@@ -7218,6 +7174,47 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring, skb->protocol =eth_type_trans (skb, rx_ring->netdev); } +static struct igb_rx_buffer *igb_get_rx_buffer (struct igb_ring *rx_ring, +const unsigned int size) +{ +struct igb_rx_buffer *rx_buffer; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; +prefetchw (rx_buffer->page); + +/* we are reusing so sync this buffer for CPU use */ +dma_sync_single_range_for_cpu (rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, +DMA_FROM_DEVICE ); + + rx_buffer->pagecnt_bias--; + +return rx_buffer; +} + +static void igb_put_rx_buffer (struct igb_ring *rx_ring, +struct igb_rx_buffer *rx_buffer) +{ +if (igb_can_reuse_rx_page (rx_buffer)) { +/* hand second half of page back to the ring */ +igb_reuse_rx_page (rx_ring, rx_buffer); + }else { +/* We are not reusing the buffer so unmap it and free +* any references we are holding to it +*/ +dma_unmap_page_attrs (rx_ring->dev, rx_buffer->dma, +igb_rx_pg_size (rx_ring),DMA_FROM_DEVICE , +IGB_RX_DMA_ATTR ); +__page_frag_cache_drain (rx_buffer->page, + rx_buffer->pagecnt_bias); + } + +/* clear contents of rx_buffer */ + rx_buffer->page =NULL ; +} +static int igb_clean_rx_irq (struct igb_q_vector *q_vector,const int budget) {struct igb_ring *rx_ring = q_vector->rx.ring;
@@ -7227,6 +7224,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)while (likely (total_packets < budget)) {union e1000_adv_rx_desc *rx_desc; +struct igb_rx_buffer *rx_buffer; +unsigned int size;/* return some buffers to hardware, one@a time is too slow */ if (cleaned_count >=IGB_RX_BUFFER_WRITE ) {
@@ -7235,8 +7234,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) } rx_desc =IGB_RX_DESC (rx_ring, rx_ring->next_to_clean); - -if (!rx_desc->wb.upper.length) + size =le16_to_cpu (rx_desc->wb.upper.length); +if (!size)break ;/* This memory barrier is needed to keep us from reading
@@ -7245,13 +7244,23 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)*/ dma_rmb (); + rx_buffer =igb_get_rx_buffer (rx_ring, size); +/* retrieve a buffer from the ring */ - skb =igb_fetch_rx_buffer (rx_ring, rx_desc, skb); +if (skb) +igb_add_rx_frag (rx_ring, rx_buffer, skb, size); +else + skb =igb_construct_skb (rx_ring, rx_buffer, + rx_desc, size);/* exit if we failed to retrieve a buffer */ -if (!skb) +if (!skb) { + rx_ring->rx_stats.alloc_failed++; + rx_buffer->pagecnt_bias++;break ; + } +igb_put_rx_buffer (rx_ring, rx_buffer); cleaned_count++;/* fetch next buffer in frame if non-eop */
PATCH v3 9/9 igb: Re-add support for build_skb in igb
In reply to Alexander DuyckFrom: Alexander Duyck <[email protected]>
This reverts commit f9d40f6a9921 ("igb: Revert support for build_skb in igb") and adds a few changes to update it to work with the latest version of igb. We are now able to revert the removal of this due to the fact that with the recent changes to the page count and the use of DMA_ATTR_SKIP_CPU_SYNC we can make the pages writable so we should not be invalidating the additional data added when we call build_skb.
--- drivers/net/ethernet/intel/igb/igb_main.c | 47 +++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+)
drivers/net/ethernet/intel/igb/igb_main.c +47 -0
@@ -7020,6 +7020,51 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,return skb; } +static struct sk_buff *igb_build_skb (struct igb_ring *rx_ring, +struct igb_rx_buffer *rx_buffer, +union e1000_adv_rx_desc *rx_desc, +unsigned int size) +{ +void *va =page_address (rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE <8192 ) +unsigned int truesize =igb_rx_pg_size (rx_ring) /2 ; +#else +unsigned int truesize =SKB_DATA_ALIGN (sizeof (struct skb_shared_info )) + +SKB_DATA_ALIGN (IGB_SKB_PAD + size); +#endif +struct sk_buff *skb; + +/* prefetch first cache line of first page */ +prefetch (va); +#if L1_CACHE_BYTES <128 +prefetch (va +L1_CACHE_BYTES ); +#endif + +/* build an skb to around the page buffer */ + skb =build_skb (va -IGB_SKB_PAD , truesize); +if (unlikely (!skb)) +return NULL ; + +/* update pointers within the skb to store the data */ +skb_reserve (skb,IGB_SKB_PAD ); +__skb_put (skb, size); + +/* pull timestamp out of packet data */ +if (igb_test_staterr (rx_desc,E1000_RXDADV_STAT_TSIP )) { +igb_ptp_rx_pktstamp (rx_ring->q_vector, skb->data, skb); +__skb_pull (skb,IGB_TS_HDR_LEN ); + } + +/* update buffer offset */ +#if (PAGE_SIZE <8192 ) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + +return skb; +} +static inline void igb_rx_checksum (struct igb_ring *ring,union e1000_adv_rx_desc *rx_desc,struct sk_buff *skb)
@@ -7249,6 +7294,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)/* retrieve a buffer from the ring */ if (skb)igb_add_rx_frag (rx_ring, rx_buffer, skb, size); +else if (ring_uses_build_skb (rx_ring)) + skb =igb_build_skb (rx_ring, rx_buffer, rx_desc, size);else skb =igb_construct_skb (rx_ring, rx_buffer, rx_desc, size);