summaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/intel/ixgbe
Commit message (Collapse)AuthorAgeFilesLines
...
* ixgbe: Update layout of ixgbe_ring structure to improve cache performanceAlexander Duyck2012-03-191-9/+9
| | | | | | | | | | | This change makes it so that only the 2nd cache line in the ring structure should see frequent updates. The advantage to this is that it should reduce the amount of cross CPU cache bouncing since only the 2nd cache line will be changing between most network transactions. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Store Tx flags and protocol information to tx_buffer soonerAlexander Duyck2012-03-193-51/+51
| | | | | | | | | | | This change makes it so that we store the tx_flags and protocol information to the tx_buffer_info structure sooner. This allows us to avoid unnecessary read/write transactions since we are placing the data in the final location earlier. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: always write DMA for single_mapped value with skbAlexander Duyck2012-03-172-118/+153
| | | | | | | | | | | | | | | | | | | | | This change makes it so that we always write the DMA address for the skb itself on the same tx_buffer struct that the skb is written on. This way we don't need the MAPPED_AS_PAGE flag and we always know it will be the first DMA value that we will have to unmap. In addition I have found an issue in which we were leaking a DMA mapping if the value happened to be 0 which is possible on some platforms. In order to resolve that I have updated the transmit path to use the length instead of the DMA mapping in order to determine if a mapping is actually present. One other tweak in this patch is that it only writes the olinfo information on the first descriptor. As it turns out it isn't necessary to write it for anything but the first descriptor so there is no need to carry it forward. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Write gso_segs and bytcount to the ring soonerAlexander Duyck2012-03-172-25/+21
| | | | | | | | | | This change makes it so that gso_segs and bytecount are written to the ring sooner. This helps to simplify the logic for the two since segmentation offloads can now update them within their own function. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Place skb on first buffer_info structure to avoid using stack spaceAlexander Duyck2012-03-173-29/+40
| | | | | | | | | | | | Instead of keeping a local copy of the skb on the stack for as long as long as we do it makes sense to instead just place it on the first tx_buffer structure so that we can save space on the stack and avoid unnecessary read/write operations copying the pointer out of the stack and onto the ring later. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Use packets to track Tx completions instead of a seperate valueAlexander Duyck2012-03-172-5/+1
| | | | | | | | | | A separate value was added to track Tx completions in order to determine if the Tx unit was hung. However we can do the same thing using the number of packets completed without having to add another stat to the Tx ring. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Modify setup of descriptor flags to avoid conditional jumpsAlexander Duyck2012-03-171-17/+17
| | | | | | | | | | | | | | | This change makes it more likely that the descriptor flags setup will use cmov instructions instead of conditional jumps when setting up the flags. The advantage to this is that the code should just flow a bit more smoothly. To do this it is necessary to set the TX_FLAGS_CSUM bit in tx_flags when doing TSO so that we also do the checksum in addition to the segmentation offload. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Make certain that all frames fit minimum size requirementsAlexander Duyck2012-03-171-1/+17
| | | | | | | | | This change makes certain that any packet we attempt to transmit will meet minimum size requirements for the hardware. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: cleanup logic in ixgbe_change_mtuAlexander Duyck2012-03-171-8/+12
| | | | | | | | | | This change is meant to just cleanup the logic in ixgbe_change_mtu since we are making it unnecessarily complex due to a workaround required for 82599 when SR-IOV is enabled. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Replace standard receive path with a page based receiveAlexander Duyck2012-03-173-430/+457
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch replaces the existing Rx hot-path in the ixgbe driver with a new implementation that is based on performing a double buffered receive. The ixgbe driver already had something similar in place for its' packet split path, however in that case we were still receiving the header for the packet into the sk_buff. The big change here is the entire receive path will receive into pages only, and then pull the header out of the page and copy it into the sk_buff data. There are several motivations behind this approach. First, this allows us to avoid several cache misses as we were taking a set of cache misses for allocating the sk_buff and then another set for receiving data into the sk_buff. We are able to avoid these misses on receive now as we allocate the sk_buff when data is available. Second we are able to see a considerable performance gain when an IOMMU is enabled because we are no longer unmapping every buffer on receive. Instead we can delay the unmap until we are unable to use the page, and instead we can simply call sync_single_range on the half of the page that contains new data. Finally we are able to drop a considerable amount of code from the driver as we no longer have to support 2 different receive modes, packet split and one buffer. This allows us to optimize the Rx path further since less branching is required. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Ross Brattain <ross.b.brattain@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Support RX-ALL feature flag.Ben Greear2012-03-171-2/+23
| | | | | | | | | | | This allows the NIC to receive all frames available, including those with bad FCS, ethernet control frames, and more. Tested by sending frames with bad FCS. Signed-off-by: Ben Greear <greearb@candelatech.com> Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Support sending custom Ethernet FCS.Ben Greear2012-03-171-0/+3
| | | | | | | | | Including bad FCS, used generate frames with bad FCS to test other system's handling of RX of bad packets. Signed-off-by: Ben Greear <greearb@candelatech.com> Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: dcb: use DCB config values for FCoE traffic class on openJohn Fastabend2012-03-141-1/+3
| | | | | | | | | | | | | | Disabling and enabling DCB can cause FCoE hardware initialization to occur on the incorrect traffic class when the up2tc mapping has not yet been reconfigured. Fix this by using the DCB configuration maps that are correct and will be pushed at mqprio after DCB driver setup completes successfully. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Tested-by: Marcus Dennis <marcusx.e.dennis@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Fix race condition where RX buffer could become corrupted.Atita Shirwaikar2012-03-146-24/+84
| | | | | | | | | | | | | | | There was a race condition in the reset path where the RX buffer could become corrupted during Fdir configuration.This is due to a HW bug.The fix right now is to lock the buffer while we do the fdir configuration.Since we were using similar workaround for another bug, I moved the existing code to a function and reused it.HW team also recommended that IXGBE_MAX_SECRX_POLL value be changed from 30 to 40.The erratum for this bug will be published in the next release 82599 Spec Update Signed-off-by: Atita Shirwaikar <atita.shirwaikar@intel.com> Acked-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: use typed min/max functions where possibleJesse Brandeburg2012-03-142-8/+8
| | | | | | | | using the form min((int)var, ver)) is replaced by min_t(int, ...) Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: fix obvious return value bug.Don Skidmore2012-03-141-1/+2
| | | | | | | | | This is clearly a typeo where we are not checking the return value from get_link_capabilities but should. This patch corrects that. Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Replace eitr_low and eitr_high with static values in ixgbe_update_itrAlexander Duyck2012-03-142-17/+8
| | | | | | | | | | | There isn't much point in using variables to store the values of eitr_low and eitr_high since they are not user changeable. As such I am replacing them with the constants 10 and 20 in order to avoid any confusion on what the values actually are. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Do not disable read relaxed ordering when DCA is enabledAlexander Duyck2012-03-144-42/+49
| | | | | | | | | | | | | | | A previous fix had gone though and disabled relaxed ordering for Rx descriptor read fetching. This was not necessary as this functions correctly and has no ill effects on the system. In addition several of the defines used for the DCA control registers were incorrect in that they indicated descriptor effects when they actually had an impact on either data or header write back. As such I have update these to correctly reflect either DATA or HEAD. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Simplify logic for ethtool loopback frame creation and testingAlexander Duyck2012-03-121-31/+32
| | | | | | | | | | | | | | | | | | | | | This change makes it a bit easier to do the loopback frame creating and testing. Previously we were doing an and to drop the last bit, and then dividing the frame_size by 2 in order to get locations for frame bytes and testing. Instead we can simplify it by just shifting the register one bit to the right and using that for the frame offsets. This change also replaces all instances of rx_buffer_info with just rx_buffer since that is closer to the name of the actual structure being used and can save a few extra characters. In addition I have updated the logic for cleaning up a test frame so that we pass an rx_buffer instead of the sk_buff. The main motivation behind this is changes that will replace the sk_buff with just a page in the future. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Add iterator for cycling through rings on a q_vectorAlexander Duyck2012-03-122-8/+12
| | | | | | | | | | Since there are multiple spots where we have to cycle through all of the rings on a q_vector it makes sense to just add a function for iterating through all of them. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Allocate rings as part of the q_vectorAlexander Duyck2012-03-123-257/+244
| | | | | | | | | | | | | | | | | | | This patch makes the rings a part of the q_vector directly instead of indirectly. Specifically on x86 systems this helps to avoid any cache set conflicts between the q_vector, the tx_rings, and the rx_rings as the critical stride is 4K and in order to cross that boundary you would need to have over 15 rings on a single q_vector. In addition this allows for smarter allocations when Flow Director is enabled. Previously Flow Director would set the irq_affinity hints based on the CPU and was still using a node interleaving approach which on some systems would end up with the two values mismatched. With the new approach we can set the affinity for the irq_vector and use the CPU for that affinity to determine the node value for the node and the rings. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Drop unnecessary napi_schedule_prep and spare blank line from ixgbe_intrAlexander Duyck2012-03-121-5/+2
| | | | | | | | | | This patch is a minor cleanup to address the unnecessary use of napi_schedule_prep in ixgbe_intr and to also remove a blank line that is not needed since it is separating a comment from the line it is explaining. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Default to queue pairs when number of queues is less than CPUsAlexander Duyck2012-03-122-8/+8
| | | | | | | | | | | | The old code had several errors in how it was determining the vector budget. In order to simplify things this patch updates the code so that it will attempt to always allocated paired Rx/Tx vectors instead of attempting to allocate individual vectors when the number of queues is less than the number of CPUs. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Correct Adaptive Interrupt Moderation so that it will change valuesAlexander Duyck2012-03-121-2/+2
| | | | | | | | | | | This change corrects an issue in which Adaptive Interrupt Moderation was not changing values due to the fact that we were performing an and operation on the resultant value that was causing the value to never change from the default 20K interrupts per second. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Address issues with Tx WHTRESH value not being set correctlyAlexander Duyck2012-03-121-2/+5
| | | | | | | | | | | | | This change is meant to address the fact that the tx_itr_setting was dropping to 0 when no separate Tx vectors were provided. This had resulted in the driver incorrectly configuring the Tx ring with a WTHRESH of 1 in order to avoid Tx hangs even though that was not necessary. This change makes it so that we instead take a look at the Tx ring's q_vector to determine if the ring will have an ITR value less than 8us. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Reorder adapter contents for better cache utilizationAlexander Duyck2012-03-121-46/+48
| | | | | | | | | This change moves several frequently accessed items together into one cache line in order to reduce cache misses in the hot-path. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Do no clear Tx status bits since eop_desc provides enough infoAlexander Duyck2012-03-121-4/+3
| | | | | | | | | | | | | | There isn't any need to clear the status bits in the descriptors due to the fact that the eop_desc provides enough information for us to know that we have cleaned to the last packet that the software has put on the ring. The status bits are cleared as a part of putting the frame on the ring so as long as we do not read the descriptor bit prior to reading the value eop_desc we should be able to guarantee that we will not clean beyond the end of the current data stream. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: add support for byte queue limitsAlexander Duyck2012-03-122-0/+12
| | | | | | | | | This adds support for byte queue limits (BQL). Based on patch from Eric Dumazet for igb. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com>
* ixgbe: remove tie between NAPI work limits and interrupt moderationJeff Kirsher2012-03-121-6/+0
| | | | | | | | | | | | | | As noted by Ben Hutchings and David Miller, work limits for NAPI should not be tied to interrupt moderation parameters. This should be handled by NAPI, possibly through sysfs. Neil Horman & Stephen Hemminger are working on a solution for NAPI currently. In the meantime, remove this tie between work limits and interrupt moderation. Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> CC: Ben Hutchings <bhutchings@solarflare.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
* net: dcb: getnumtcs()/setnumtcs() should return an intJohn Fastabend2012-03-021-2/+2
| | | | | | | | | | | | | | | {g|s}etnumtcs() today returns a u8 that is only used by the DCB code to verify no error occurred. Today the driver implementations return negative error codes which end up being non-zero so the logic works out but triggers some sparse warnings. To fix the sparse warnings convert the return value to an int. CC: Eilon Greenstein <eilong@broadcom.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Tested-by: Ross Brattain <ross.b.brattain@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: dcb: check setup_tc return codesJohn Fastabend2012-03-021-8/+18
| | | | | | | | | | | | | | | dcb netlink code calls setup_tc to init hardware traffic classes to use for DCB. At some call sites the return values are not checked for errors and in one case may return -EINVAL back to the net/dcbnl.c caller which is expecting a u8. This fixes some smatch hits and although failures are never seen in practive its best to check return codes. Reported-by: Dan Carenter <dan.carpenter@oracle.com> Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Tested-by: Ross Brattain <ross.b.brattain@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Fix comments that are out of date or formatted incorrectlyAlexander Duyck2012-02-291-4/+9
| | | | | | | | | This patch corrects several comments that are either incorrect or formatted incorrectly for multiline comments. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: fix spelling errorsDon Skidmore2012-02-291-1/+1
| | | | | | | | Correct spelling error caught with codespell.py. Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* ixgbe: Minor formatting and comment corrections for ixgbe_xmit_frame_ringAlexander Duyck2012-02-291-6/+11
| | | | | | | | | | This patch is meant to address several minor issues in ixgbe_xmit_frame_ring. Specifically it adds a comment explaining the TXSW flag, and correctly wraps a line over 80 characters. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* drivers/net: Remove boolean comparisons to true/falseJoe Perches2012-02-133-4/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Booleans should not be compared to true or false but be directly tested or tested with !. Done via cocci script: @@ bool t; @@ - t == true + t @@ bool t; @@ - t != true + !t @@ bool t; @@ - t == false + !t @@ bool t; @@ - t != false + t Signed-off-by: Joe Perches <joe@perches.com> Reviewed-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge branch 'master' of ↵David S. Miller2012-02-124-278/+500
|\ | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next
| * ixgbe: Combine post-DMA processing of sk_buff fields into single functionAlexander Duyck2012-02-102-59/+71
| | | | | | | | | | | | | | | | | | | | | | This change combines a number of post-DMA Rx packet processing functions into a single function. The advantage of this is that it combines most of the Rx descriptor processing into one spot so it should all be warm in the cache. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * ixgbe: Drop the _ADV of descriptor macros since all ixgbe descriptors are ADVAlexander Duyck2012-02-103-18/+18
| | | | | | | | | | | | | | | | | | | | | | It doesn't make much sense to differentiate between advanced and legacy descriptors when the only descriptors that ixgbe uses are advanced descriptors. As such we can drop the _ADV suffix since all ixgbe descriptors are automatically advanced. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * ixgbe: Add function for testing status bits in Rx descriptorAlexander Duyck2012-02-103-55/+65
| | | | | | | | | | | | | | | | | | | | This change adds a small function for testing Rx status bits in the descriptor. The advantage to this is that we can avoid unnecessary byte swaps on big endian systems. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * ixgbe: Let the Rx buffer allocation clear status bits instead of cleanupAlexander Duyck2012-02-101-62/+93
| | | | | | | | | | | | | | | | | | | | | | | | This change makes it so that we always clear the status/error bits in the Rx descriptor in the allocation path instead of the cleanup path. The advantage to this is that we spend less time modifying data. As such we can modify the data once and then let it go cold in the cache instead of writing it, reading it, and then writing it again. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * ixgbe: Address fact that RSC was not setting GSO size for incoming framesAlexander Duyck2012-02-101-5/+125
| | | | | | | | | | | | | | | | | | | | | | This patch is meant to address the fact that RSC has not been setting the gso_size value on the skb. As a result performance on lossy TCP connections was negatively impacted. This change resolves the issue by setting gso_size to the average size for incoming packets. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * ixgbe: Minor refactor of RSCAlexander Duyck2012-02-102-98/+147
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This change addresses several issue. First I had left the use of the next and prev skb pointers floating around in the code and they were overdue to be pulled since I had rewritten the RSC code in the out-of-tree driver some time ago to address issues brought up by David Miller in regards to this. I am also now defaulting to always leaving the first buffer unmapped on any packet and then unmapping it after we read the EOP descriptor. This allows a simplification of the path with less branching. Instead of counting packets received the code was changed some time ago to track the number of buffers received. This leads to inaccurate counting when you compare numbers of packets received by the hardware versus what is tracked by the software. To correct this I am revising things so that the append_cnt value for RSC accurately tracks the number of frames received. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2012-02-104-47/+73
|\ \ | |/ |/| | | | | | | | | | | | | Conflicts: drivers/infiniband/hw/nes/nes_cm.c Simple whitespace conflict. Signed-off-by: David S. Miller <davem@davemloft.net>
| * ixgbe: ethtool: stats user buffer overrunJohn Fastabend2012-02-091-37/+51
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If the number of tx/rx queues changes the ethtool ioctl ETHTOOL_GSTATS may overrun the userspace buffer. This occurs because the general practice in user space to query stats is to issue a ETHTOOL_GSSET cmd to learn the buffer size needed, allocate the buffer, then call ETHTOOL_GSTIRNGS and ETHTOOL_GSTATS. If the number of real_num_queues is changed or flow control attributes are changed after ETHTOOL_GSSET but before the ETHTOOL_GSTRINGS/ETHTOOL_GSTATS a user space buffer overrun occurs. To fix the overrun always return the max buffer size needed from get_sset_count() then return all strings and stats from get_strings()/get_ethtool_stats(). This _will_ change the output from the ioctl() call which could break applications and script parsing in theory. I believe these changes should not break existing tools because the only changes will be more {tx|rx}_queues and the {tx|rx}_pb_* stats will always be returned. Existing scripts already need to handle changing number of queues because this occurs today depending on system and current features. The {tx|rx}_pb_* stats are at the end of the output and should be handled by scripts today regardless. Finally get_ethtool_stats and get_strings are free-form outputs tools parsing these outputs should be defensive anyways. In the end these updates are better then having a tool segfault because of a buffer overrun. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * ixgbe: dcb: up2tc mapping lost on disable/enable CEE DCB stateJohn Fastabend2012-02-091-2/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Users expect the up2tc mapping to be maintained across a DCB enable/disable/enable transition. And since we maintain all the other DCB attributes we should do this for up2tc mappings as well just to be consistent. Also without this we break user space applications that expect this to occur that previously worked. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Tested-by: Ross Brattain <ross.b.brattain@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * ixgbe: do not update real num queues when netdev is going awayYi Zou2012-02-091-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If the netdev is already in NETREG_UNREGISTERING/_UNREGISTERED state, do not update the real num tx queues. netdev_queue_update_kobjects() is already called via remove_queue_kobjects() at NETREG_UNREGISTERING time. So, when upper layer driver, e.g., FCoE protocol stack is monitoring the netdev event of NETDEV_UNREGISTER and calls back to LLD ndo_fcoe_disable() to remove extra queues allocated for FCoE, the associated txq sysfs kobjects are already removed, and trying to update the real num queues would cause something like below: ... PID: 25138 TASK: ffff88021e64c440 CPU: 3 COMMAND: "kworker/3:3" #0 [ffff88021f007760] machine_kexec at ffffffff810226d9 #1 [ffff88021f0077d0] crash_kexec at ffffffff81089d2d #2 [ffff88021f0078a0] oops_end at ffffffff813bca78 #3 [ffff88021f0078d0] no_context at ffffffff81029e72 #4 [ffff88021f007920] __bad_area_nosemaphore at ffffffff8102a155 #5 [ffff88021f0079f0] bad_area_nosemaphore at ffffffff8102a23e #6 [ffff88021f007a00] do_page_fault at ffffffff813bf32e #7 [ffff88021f007b10] page_fault at ffffffff813bc045 [exception RIP: sysfs_find_dirent+17] RIP: ffffffff81178611 RSP: ffff88021f007bc0 RFLAGS: 00010246 RAX: ffff88021e64c440 RBX: ffffffff8156cc63 RCX: 0000000000000004 RDX: ffffffff8156cc63 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff88021f007be0 R8: 0000000000000004 R9: 0000000000000008 R10: ffffffff816fed00 R11: 0000000000000004 R12: 0000000000000000 R13: ffffffff8156cc63 R14: 0000000000000000 R15: ffff8802222a0000 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 #8 [ffff88021f007be8] sysfs_get_dirent at ffffffff81178c07 #9 [ffff88021f007c18] sysfs_remove_group at ffffffff8117ac27 #10 [ffff88021f007c48] netdev_queue_update_kobjects at ffffffff813178f9 #11 [ffff88021f007c88] netif_set_real_num_tx_queues at ffffffff81303e38 #12 [ffff88021f007cc8] ixgbe_set_num_queues at ffffffffa0249763 [ixgbe] #13 [ffff88021f007cf8] ixgbe_init_interrupt_scheme at ffffffffa024ea89 [ixgbe] #14 [ffff88021f007d48] ixgbe_fcoe_disable at ffffffffa0267113 [ixgbe] #15 [ffff88021f007d68] vlan_dev_fcoe_disable at ffffffffa014fef5 [8021q] #16 [ffff88021f007d78] fcoe_interface_cleanup at ffffffffa02b7dfd [fcoe] #17 [ffff88021f007df8] fcoe_destroy_work at ffffffffa02b7f08 [fcoe] #18 [ffff88021f007e18] process_one_work at ffffffff8105d7ca #19 [ffff88021f007e68] worker_thread at ffffffff81060513 #20 [ffff88021f007ee8] kthread at ffffffff810648b6 #21 [ffff88021f007f48] kernel_thread_helper at ffffffff813c40f4 Signed-off-by: Yi Zou <yi.zou@intel.com> Tested-by: Ross Brattain <ross.b.brattain@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * ixgbe: Fix broken dependency on MAX_SKB_FRAGS being related to page sizeAlexander Duyck2012-02-091-6/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes an issue in which RSC will generate corrupted frames when PAGE_SIZE is larger than 8K. Specifically it looks like that in 2.6.39 a change was made so that GRO would always have at least 16 frags available for coalescing, but the ixgbe RSC logic was not updated. As such the RSC feature would generate a frame larger than 64K and then overflow the value in the IP length field. To correct that I am now basing things on the PAGE_SIZE. Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Stephen Ko <stephen.s.ko@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * ixgbe: Fix case of Tx Hang in PF with 32 VFsGreg Rose2012-02-091-1/+1
| | | | | | | | | | | | | | | | | | | | A check for the number of VFs allocated should have used a greater than equal operator instead of just greater than. This caused allocation of exactly 32 VFs to not enable the PF transmit and receive enables. Signed-off-by: Greg Rose <gregory.v.rose@intel.com> Tested-by: Robert E Garrett <robertX.e.garrett@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
| * ixgbe: fix vf lookupGreg Rose2012-02-091-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Recent addition of code to find already allocated VFs failed to take account that systems with 2 or more multi-port SR-IOV capable controllers might have already enabled VFs. Make sure that the VFs the function is finding are actually subordinate to the particular instance of the adapter that is looking for them and not subordinate to some device that has previously enabled SR-IOV. This bug exists in 3.2 stable as well as 3.3 release candidates. CC: stable@vger.kernel.org Reported-by: David Ahern <daahern@cisco.com> Signed-off-by: Greg Rose <gregory.v.rose@intel.com> Tested-by: Robert E Garrett <robertX.e.garrett@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2012-02-0425-28/+31
|\|
OpenPOWER on IntegriCloud