aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/intel/i40evf/i40e_txrx.c (follow)
AgeCommit message (Collapse)AuthorFilesLines
2017-04-08i40e/i40evf: Use build_skb to build framesAlexander Duyck1-0/+47
This patch is meant to improve the performance of the Rx path. Specifically by using build_skb we have several distinct advantages. In the case of small frames we were previously using a copy-break approach. This means that we were allocating a page fragment to use for skb->head, and were having to copy the packet into that region. Both of those calls are now avoided since we just build the skb around the data. In the case of large frames the gains are much more significant. Specifically we were having to allocate skb->head, and copy the headers as before. However in addition we were having to parse the header using eth_get_headlen which could be quite expensive. All of this is avoided by building the frame around the data. I have seen gains as high as 30% when using VXLAN for instance due to just header pulling overhead. Finally with all this in place it also sets us up to start looking at enabling XDP. Specifically we now have a path in which the data is in the page and the frame is built around it. So if we parse it with XDP before we call build_skb we can take care of any necessary processing there. Change-ID: Id4bdd618e94473d41f892417e5d8019639e421e3 Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-04-08i40e/i40evf: Add support for padding start of framesAlexander Duyck1-2/+13
This patch adds padding to the start of frames to make room for headroom for us to eventually start using build_skb. Right now we guarantee at least NET_SKB_PAD + NET_IP_ALIGN, however we allocate more space if more is available. For example on x86 the headroom should be 192 bytes. On systems that have too large of a cache line size to support storing 1.5K padding and shared info we default to using 3K buffers and reserve everything that isn't used for skb_shared_info or the data buffer for headroom. Change-ID: I33c641c9a1ea10cf7cc484c2d20985368d2d709a Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-04-08i40e/i40evf: Add support for using order 1 pages with a 3K bufferAlexander Duyck1-13/+14
There are situations where adding padding to the front and back of an Rx buffer will require that we add additional padding. Specifically if NET_IP_ALIGN is non-zero, or the MTU size is larger than 7.5K we would need to use 2K buffers which leaves us with no room for the padding. To preemptively address these cases I am adding support for 3K buffers to the Rx path so that we can provide the additional padding needed in the event of NET_IP_ALIGN being non-zero or a cache line being greater than 64. Change-ID: I938bc1ba611285428df39a613cd66f98e60b55c7 Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-03-29i40e/i40evf: Break i40e_fetch_rx_buffer up to allow for reuse of frag codeAlexander Duyck1-73/+65
This patch is meant to clean up the code in preparation for us adding support for build_skb. Specifically we deconstruct i40e_fetch_buffer into several functions so that those functions can later be reused when we add a path for build_skb. Specifically with this change we split out the code for adding a page to an exiting skb. Change-ID: Iab1efbab6b8b97cb60ab9fdd0be1d37a056a154d Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-03-29i40e/i40evf: Pull out code for cleaning up Rx buffersAlexander Duyck1-28/+44
This patch pulls out the code responsible for handling buffer recycling and page counting and distributes it through several functions. This allows us to commonize the bits that handle either freeing or recycling the buffers. As far as the page count tracking one change to the logic is that pagecnt_bias is decremented as soon as we call i40e_get_rx_buffer. It is then the responsibility of the function that pulls the data to either increment the pagecnt_bias if the buffer can be recycled as-is, or to update page_offset so that we are pointing at the correct location for placement of the next buffer. Change-ID: Ibac576360cb7f0b1627f2a993d13c1a8a2bf60af Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-03-29i40e/i40evf: Pull code for grabbing and syncing rx_buffer from fetch_bufferAlexander Duyck1-24/+34
This patch pulls the code responsible for fetching the Rx buffer and synchronizing DMA into a function, specifically called i40e_get_rx_buffer. The general idea is to allow for better code reuse by pulling this out of i40e_fetch_rx_buffer. We dropped a couple of prefetches since the time between the prefetch being called and the data being accessed was too small to be useful. Change-ID: I4885fce4b2637dbedc8e16431169d23d3d7e79b9 Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-03-29i40e/i40evf: Use length to determine if descriptor is doneAlexander Duyck1-12/+12
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. Change-ID: Iebdf9cdb36c454ef092df27199b92ad09c374231 Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-03-29i40evf: enforce descriptor write-back mechanism for VFPreethi Banala1-57/+7
The current driver mode is to use a write-back mechanism for the head register which indicates transmit completions. The VF driver needs to be able to work on hardware that exclusively uses descriptor write-back, so change the default driver mode of operation to descriptor write-back for VF. In our analysis, performance wasn't significantly different with either write-back method. Change-ID: Ia92e4ec77c2df8dc4515c71d53746d57d77759af Signed-off-by: Preethi Banala <preethi.banala@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-03-27i40e/i40evf: Clean-up process_skb_fieldsAlexander Duyck1-5/+3
This is a minor clean-up to make the i40e/i40evf process_skb_fields function look a little more like what we have in igb. The Rx checksum function called out a need for skb->protocol but I can't see where it actually needs it. I am assuming this is something that was likely refactored out some time ago as the Rx checksum code has gone through a few rewrites. Change-ID: I0b4668a34d90b61b66ded7c7c26e19a3e2d06251 Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-03-27i40e/i40evf: Fix use after free in Rx cleanup pathAlexander Duyck1-0/+1
We need to reset skb back to NULL when we have freed it in the Rx cleanup path. I found one spot where this wasn't occurring so this patch fixes it. Change-ID: Iaca68934200732cd4a63eb0bd83b539c95f8c4dd Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-03-27i40e/i40evf: Update code to better handle incrementing page countAlexander Duyck1-6/+18
Update the driver code so that we do bulk updates of the page reference count instead of just incrementing it by one reference at a time. The advantage to doing this is that we cut down on atomic operations and this in turn should give us a slight improvement in cycles per packet. In addition if we eventually move this over to using build_skb the gains will be more noticeable. I also found and fixed a store forwarding stall from where we were assigning "*new_buff = *old_buff". By breaking it up into individual copies we can avoid this and as a result the performance is slightly improved. Change-ID: I1d3880dece4133eca3c32423b04a5467321ccc52 Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-03-15i40e/i40evf: Add support for mapping pages with DMA attributesAlexander Duyck1-5/+26
This patch adds support for DMA_ATTR_SKIP_CPU_SYNC and DMA_ATTR_WEAK_ORDERING. By enabling both of these for the Rx path we are able to see performance improvements on architectures that implement either one due to the fact that page mapping and unmapping only has to sync what is actually being used instead of the entire buffer. In addition by enabling the weak ordering attribute enables a performance improvement for architectures that can associate a memory ordering with a DMA buffer such as Sparc. Change-ID: If176824e8231c5b24b8a5d55b339a6026738fc75 Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-02-18i40e: mark the value passed to csum_replace_by_diff as __wsumJacob Keller1-2/+3
Fix, or rather, avoid a sparse warning caused by the fact that csum_replace_by_diff expects to receive a __wsum value. Since the calculation appears to work, simply typecast the passed paylen value to __wsum to avoid the warning. This seems pretty fishy since __wsum was obviously annotated as a separate type on purpose, so this throws the entire calculation into question. Since it currently appears to behave as expected, the typecast is probably safe. Change-ID: I4fdc5cddd589abc16098176e8a61127e761488f4 Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-02-18i40e: Fix Adaptive ITR enablingCarolyn Wyborny1-6/+6
This patch fixes a bug introduced with the addition of the per queue ITR feature support in ethtool. With that addition, there were functions added which converted the ITR settings to binary values. The IS_ENABLED macros that run on those values check whether a bit is set or not and with the value being binary, the bit check always returned ITR disabled which prevents any updating of the ITR rate. This patch fixes the problem by changing the functions to return the current ITR value instead and renaming it to better reflect its function. These functions now provide a value which will be accurately asessed and update the ITR as intended. Change-ID: I14f1d088d052e27f652aaa3113e186415ddea1fc Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-02-11i40e/i40evf: eliminate i40e_pull_tail()Scott Peterson1-76/+93
Reorganize the i40e_pull_tail() logic, doing it in i40e_add_rx_frag() where it's cheaper. The igb driver does this the same way. Also renames i40e_page_is_reserved() to reflect what it actually tests. Change-ID: Icd9cc507aae1fcdc02308b3a09034111b4c24071 Signed-off-by: Scott Peterson <scott.d.peterson@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-02-11i40e/i40evf: Moves skb from i40e_rx_buffer to i40e_ringScott Peterson1-15/+15
This patch reduces the size of struct i40e_rx_buffer by one pointer, and makes the i40e driver a little more consistent with the igb driver in terms of packets that span buffers. We do this by moving the skb field from struct i40e_rx_buffer to struct i40e_ring. We pass the skb we already have (or NULL if we don't) to i40e_fetch_rx_buffer(), which skips the skb allocation if we already have one for this packet. Change-ID: I4ad48a531844494ba0c5d8e1a62209a057f661b0 Signed-off-by: Scott Peterson <scott.d.peterson@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-02-11i40e/i40evf: Limit DMA sync of RX buffers to actual packet sizeScott Peterson1-7/+9
On packet RX, we perform a DMA sync for CPU before passing the packet up. Here we limit that sync to the actual length of the incoming packet, rather than always syncing the entire buffer. Change-ID: I626aaf6c37275a8ce9e81efcaa773f327b331487 Signed-off-by: Scott Peterson <scott.d.peterson@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-02-02i40e: Quick refactor to start moving data off stack and into Tx buffer infoAlexander Duyck1-20/+27
This patch does some quick work to pull some of the data off of the stack and hopefully start storing it in the Tx buffer info section of the Tx ring. Ideally we should be moving away from having to store much of anything on the stack and can just maintain it all in the descriptor rings. Change-ID: I4b4715ea1920e122502482b3f9e56a9a6cb1e9fe Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-12-06i40e/i40evf: napi_poll must return the work doneAlexander Duyck1-1/+1
Currently the function i40e_napi-poll() returns 0 when it clean completely the Rx rings, but this foul budget accounting in core code. Fix this by returning the actual work done, capped to budget - 1, since the core doesn't allow to return the full budget when the driver modifies the NAPI status This is based on a similar change that was made for the ixgbe driver by Paolo Abeni. Change-ID: Ic3d93ad2fa2fc8ce3164bc461e69367da0f9173b Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-10-31i40e: Reorder logic for coalescing RS bitsAlexander Duyck1-51/+54
This patch reorders the logic at the end of i40e_tx_map to address the fact that the logic was rather convoluted and much larger than it needed to be. In order to try and coalesce the code paths I have updated some of the comments and repurposed some of the variables in order to reduce unnecessary overhead. This patch does the following: 1. Quit tracking skb->xmit_more with a flag, just max out packet_stride 2. Drop tail_bump and do_rs and instead just use desc_count and td_cmd 3. Pull comments from ixgbe that make need for wmb() more explicit. Change-ID: Ic7da85ec75043c634e87fef958109789bcc6317c Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-10-28i40e: Drop redundant Rx descriptor processing codeAlexander Duyck1-12/+6
This patch cleans up several pieces of redundant code in the Rx clean-up paths. The first bit is that hdr_addr and the status_err_len portions of the Rx descriptor represent the same value. As such there is no point in setting them to 0 before setting them to 0. I'm dropping the second spot where we are updating the value to 0 so that we only have 1 write for this value instead of 2. The second piece is the checking for the DD bit in the packet. We only need to check for a non-zero value for the status_err_len because if the device is done with the descriptor it will have written something back and the DD is just one piece of it. In addition I have moved the reading of the Rx descriptor bits related to rx_ptype down so that they are actually below the dma_rmb() call so that we are guaranteed that we don't have any funky 64b on 32b calls causing any ordering issues. Change-ID: I256e44a025d3c64a7224aaaec37c852bfcb1871b Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-10-28i40e/i40evf: fix interrupt affinity bugAlan Brady1-5/+26
There exists a bug in which a 'perfect storm' can occur and cause interrupts to fail to be correctly affinitized. This causes unexpected behavior and has a substantial impact on performance when it happens. The bug occurs if there is heavy traffic, any number of CPUs that have an i40e interrupt are pegged at 100%, and the interrupt afffinity for those CPUs is changed. Instead of moving to the new CPU, the interrupt continues to be polled while there is heavy traffic. The bug is most readily realized as the driver is first brought up and all interrupts start on CPU0. If there is heavy traffic and the interrupt starts polling before the interrupt is affinitized, the interrupt will be stuck on CPU0 until traffic stops. The bug, however, can also be wrought out more simply by affinitizing all the interrupts to a single CPU and then attempting to move any of those interrupts off while there is heavy traffic. This patch fixes the bug by registering for update notifications from the kernel when the interrupt affinity changes. When that fires, we cache the intended affinity mask. Then, while polling, if the cpu is pegged at 100% and we failed to clean the rings, we check to make sure we have the correct affinity and stop polling if we're firing on the wrong CPU. When the kernel successfully moves the interrupt, it will start polling on the correct CPU. The performance impact is minimal since the only time this section gets executed is when performance is already compromised by the CPU. Change-ID: I4410a880159b9dba1f8297aa72bef36dca34e830 Signed-off-by: Alan Brady <alan.brady@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-09-24i40evf: support queue-specific settings for interrupt moderationJacob Keller1-4/+22
In commit a75e8005d506f3 ("i40e: queue-specific settings for interrupt moderation") the i40e driver gained support for setting interrupt moderation values per queue. This patch adds support for this feature to the i40evf driver as well. In addition, a few changes are made to the i40e implementation to add function header documentation comments, as well. This behaves in a similar fashion to the implementation in i40e. Thus, requesting the moderation value when no queue is provided will report queue 0 value, while setting the value without a queue will set all queues at once. Change-ID: I1f310a57c8e6c84a8524c178d44d1b7a6d3a848e Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-09-24i40e/i40evf: Add txring_txq function to match fm10k and ixgbeAlexander Duyck1-11/+6
This patch adds a txring_txq function which allows us to convert a i40e_ring/i40evf_ring to a netdev_tx_queue structure. This way we can avoid having to make a multi-line function call for all the spots that need access to this. Change-ID: Ic063b71d8b92ea406d2c32e798c8e2b02809d65b Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-09-24i40e: Fix Flow Director raw_buf cleanupAlexander Duyck1-4/+4
The Tx cleanup flow was incorrectly assuming it could check for the flow director bits after it had unmapped the buffer. However in this case it results in us trying to free a raw_buf as though it is an sk_buff. To fix this I am moving up the flag test for the FD_SB bit so that when find a non-NULL skb or raw_buf value we then check the flag and use the appropriate call to free the buffer. Change-ID: I6284034ba1ea87c9922e56f6eb3181f7f09bddde Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-09-22i40e: Limit TX descriptor count in cases where frag size is greater than 16KAlexander Duyck1-5/+2
The i40e driver was incorrectly assuming that we would always be pulling no more than 1 descriptor from each fragment. It is in fact possible for us to end up with the case where 2 descriptors worth of data may be pulled when a frame is larger than one of the pieces generated when aligning the payload to either 4K or pieces smaller than 16K. To adjust for this we just need to make certain to test all the way to the end of the fragments as it is possible for us to span 2 descriptors in the block before us so we need to guarantee that even the last 6 descriptors have enough data to fill a full frame. Change-ID: Ic2ecb4d6b745f447d334e66c14002152f50e2f99 Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-08-19i40e: refactor tail_bump checkCarolyn Wyborny1-4/+2
This patch refactors tail bump check. Change-ID: Ide0e19171d67d90cb2b06b8dcd4fa791ae120160 Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-07-25Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queueDavid S. Miller1-2/+1
Conflicts: drivers/net/ethernet/intel/i40e/i40e_main.c Jeff Kirsher says: ==================== 40GbE Intel Wired LAN Driver Updates 2016-07-22 This series contains updates to i40e and i40evf. Heinrich Schuchardt found a possible null pointer being dereferenced in i40e_debug_aq(), fixed the issue by doing the variable assignment after we are sure the pointer is not null. Avinash fixed an issue when link was down, we were not showing the correct advertised link modes. Mitch cleans up a useless initializer since the variable is assigned right away. Refactors the receive filter handling to properly track filter adds and deletes so the driver will not lose filters during a reset and up/down cycles. Also added a tracking mechanism so that the driver knows when to enter and leave promiscuous mode. Catherine removes a device id which is not needed (or used). Moves a mutex lock since we need to lock the client list around the i40e_client_release() call to prevent the release from interrupting the client instances while they are being added. Joshua adds Hyper-V specific VF device ids. Amitoj Kaur Chawla cleans up a redundant memset() call before a memcpy(). Stefan Assmann adds the missing link advertise for some x710 NICs. Tushar Dave fixes and issue found on SPARC, where a PF reset clears MAC filters and if a platform-specific MAC address is used, the driver has to explicitly write default MAC address to MAC filters otherwise all incoming traffic destined to the default MAC address will be dropped after reset. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-22i40e/i40evf: remove useless initializerMitch Williams1-2/+1
This initializer isn't needed because the variable is assigned right away. Change-ID: I6ce3edb3f4e0364db248a7a0bcc62ca95c01d941 Signed-off-by: Mitch Williams <mitch.a.williams@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-07-14i40e/i40evf: Fix i40e_rx_checksumAlexander Duyck1-13/+17
There are a couple of issues I found in i40e_rx_checksum while doing some recent testing. As a result I have found the Rx checksum logic is pretty much broken and returning that the checksum is valid for tunnels in cases where it is not. First the inner types are not the correct values to use to test for if a tunnel is present or not. In addition the inner protocol types are not a bitmask as such performing an OR of the values doesn't make sense. I have instead changed the code so that the inner protocol types are used to determine if we report CHECKSUM_UNNECESSARY or not. For anything that does not end in UDP, TCP, or SCTP it doesn't make much sense to report a checksum offload since it won't contain a checksum anyway. This leaves us with the need to set the csum_level based on some value. For that purpose I am using the tunnel_type field. If the tunnel type is GRENAT or greater then this means we have a GRE or UDP tunnel with an inner header. In the case of GRE or UDP we will have a possible checksum present so for this reason it should be safe to set the csum_level to 1 to indicate that we are reporting the state of the inner header. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-05-20intel: Add support for IPv6 IP-in-IP offloadAlexander Duyck1-0/+1
This patch adds support for offloading IPXIP6 type packets that represent either IPv4 or IPv6 encapsulated inside of an IPv6 outer IP header. In addition with this change we should also be able to support FOU encapsulated traffic with outer IPv6 headers. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-20net: define gso types for IPx over IPv4 and IPv6Tom Herbert1-2/+1
This patch defines two new GSO definitions SKB_GSO_IPXIP4 and SKB_GSO_IPXIP6 along with corresponding NETIF_F_GSO_IPXIP4 and NETIF_F_GSO_IPXIP6. These are used to described IP in IP tunnel and what the outer protocol is. The inner protocol can be deduced from other GSO types (e.g. SKB_GSO_TCPV4 and SKB_GSO_TCPV6). The GSO types of SKB_GSO_IPIP and SKB_GSO_SIT are removed (these are both instances of SKB_GSO_IPXIP4). SKB_GSO_IPXIP6 will be used when support for GSO with IP encapsulation over IPv6 is added. Signed-off-by: Tom Herbert <tom@herbertland.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-05i40evf: refactor receive routineJesse Brandeburg1-443/+455
This is part 2 of the Rx refactor series, just including changes to i40evf. This refactor aligns the receive routine with the one in ixgbe which was highly optimized. This reduces the code we have to maintain and allows for (hopefully) more readable and maintainable RX hot path. In order to do this: - consolidate the receive path into a single function that doesn't use packet split but *does* use pages for Rx buffers. - remove the old _1buf routine - consolidate several routines into helper functions - remove VF ethtool control over packet split - remove priv_flags interface since it is unused Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-05-05i40evf: Drop packet split receive routineJesse Brandeburg1-20/+1
As part of preparation for the rx-refactor, remove the packet split receive routine and ancillary code. Some of the split related context set up code stays in i40e_virtchnl_pf.c in case an older VF driver tries to load and still wants to use packet split. Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-05-05i40e/i40evf: Refactor tunnel interpretationJesse Brandeburg1-7/+6
Refactor the interpretation of a tunnel. This removes some code and lets us start using the hardware's parsing. Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-05-01i40e/i40evf: Add support for GSO partial with UDP_TUNNEL_CSUM and GRE_CSUMAlexander Duyck1-1/+6
This patch makes it so that i40e and i40evf can use GSO_PARTIAL to support segmentation for frames with checksums enabled in outer headers. As a result we can now send data over these types of tunnels at over 20Gb/s versus the 12Gb/s that was previously possible on my system. The advantage with the i40e parts is that this offload is mostly transparent as the hardware still deals with the inner and/or outer IPv4 headers so the IP ID is still incrementing for both when this offload is performed. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-04-27i40e/i40evf: Only offload VLAN tag if enabledJesse Brandeburg1-1/+2
The driver was offloading the VLAN tag into the skb any time there was a VLAN tag and the hardware stripping was enabled. Just check to make sure it's enabled before put_tag. Change-Id: Ife95290c06edd9a616393b38679923938b382241 Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-04-26i40e/i40evf: Add support for IPIP and SIT offloadsAlexander Duyck1-8/+16
Looking over the documentation it turns out enabling IPIP and SIT offloads for i40e is pretty straightforward. As such I decided to enable them with this patch. In my testing I am seeing an improvement of 8 to 10 Gb/s for IPIP and SIT tunnels with this offload enabled. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-04-23Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller1-25/+24
Conflicts were two cases of simple overlapping changes, nothing serious. In the UDP case, we need to add a hlist_add_tail_rcu() to linux/rculist.h, because we've moved UDP socket handling away from using nulls lists. Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-13i40e/i40evf: Limit TSO to 7 descriptors for payload instead of 8 per packetAlexander Duyck1-25/+24
This patch addresses a bug introduced based on my interpretation of the XL710 datasheet. Specifically section 8.4.1 states that "A single transmit packet may span up to 8 buffers (up to 8 data descriptors per packet including both the header and payload buffers)." It then later goes on to say that each segment for a TSO obeys the previous rule, however it then refers to TSO header and the segment payload buffers. I believe the actual limit for fragments with TSO and a skbuff that has payload data in the header portion of the buffer is actually only 7 fragments as the skb->data portion counts as 2 buffers, one for the TSO header, and one for a segment payload buffer. Fixes: 2d37490b82af ("i40e/i40evf: Rewrite logic for 8 descriptor per packet check") Reported-by: Sowmini Varadhan <sowmini.varadhan@oracle.com> Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Acked-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Sowmini Varadhan <sowmini.varadhan@oracle.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-04-06i40e/i40evf: Faster RX via avoiding FCoEJesse Brandeburg1-1/+3
As it turns out, calling into other files from hot path hurts performance a lot. In this case the majority of the time we call "check FCoE" and the packet is *not* FCoE, but this call was taking 5% of our total cycles spent on receive. Change-ID: I080552c26e7060bc7b78504dc2763f6f0b3d8c76 Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-04-06i40e/i40evf: Drop unused tx_ring argumentJesse Brandeburg1-4/+2
Some of the tx_ring arguments can be deleted since they are not used. Change-ID: I99275b0f191d7f63ec2f05061919904940c36f31 Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-04-06i40e/i40evf: Move stack var deeperJesse Brandeburg1-1/+2
A local variable could move down inside the context where it is used. Change-ID: I9caba9e1eacf921037077f2665cbce83fd8e95d6 Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-04-05i40e/i40evf: Fix TSO checksum pseudo-header adjustmentAlexander Duyck1-7/+4
With IPv4 and IPv6 now using the same format for checksums based on the length of the frame we need to update the i40e and i40evf drivers so that they correctly account for lengths greater than or equal to 64K. With this patch the driver should now correctly update checksums for frames up to 16776960 in length which should be more than large enough for all possible TSO frames in the near future. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-04-05i40e/i40evf: Fix casting in transmit codeJesse Brandeburg1-2/+3
Simple cast to fix a sparse warning. Fixes: commit 5453205cd097 ("i40e/i40evf: Enable support for SKB_GSO_UDP_TUNNEL_CSUM") Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-04-05i40e/i40evf: Add support for bulk free in Tx cleanupAlexander Duyck1-9/+11
This patch enables bulk Tx clean for skbs. In order to enable it we need to pass the napi_budget value as that is used to determine if we are truly running in NAPI mode or if we are simply calling the routine from netpoll with a budget of 0. In order to avoid adding too many more variables I thought it best to pass the VSI directly in a fashion similar to what we do on igb and ixgbe with the q_vector. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-04-05i40e/i40evf: Fix handling of boolean logic in polling routinesAlexander Duyck1-5/+8
In the polling routines for i40e and i40evf we were using bitwise operators to avoid the side effects of the logical operators, specifically the fact that if the first case is true with "||" we skip the second case, or if it is false with "&&" we skip the second case. This fixes an earlier patch that converted the bitwise operators over to the logical operators and instead replaces the entire thing with just an if statement since it should be more readable what we are trying to do this way. Fixes: 1a36d7fadd14 ("i40e/i40evf: use logical operators, not bitwise") Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-04-05i40e/i40evf: Allow up to 12K bytes of data per Tx descriptor instead of 8KAlexander Duyck1-4/+9
From what I can tell the practical limitation on the size of the Tx data buffer is the fact that the Tx descriptor is limited to 14 bits. As such we cannot use 16K as is typically used on the other Intel drivers. However artificially limiting ourselves to 8K can be expensive as this means that we will consume up to 10 descriptors (1 context, 1 for header, and 9 for payload, non-8K aligned) in a single send. I propose that we can reduce this by increasing the maximum data for a 4K aligned block to 12K. We can reduce the descriptors used for a 32K aligned block by 1 by increasing the size like this. In addition we still have the 4K - 1 of space that is still unused. We can use this as a bit of extra padding when dealing with data that is not aligned to 4K. By aligning the descriptors after the first to 4K we can improve the efficiency of PCIe accesses as we can avoid using byte enables and can fetch full TLP transactions after the first fetch of the buffer. This helps to improve PCIe efficiency. Below is the results of testing before and after with this patch: Recv Send Send Utilization Service Demand Socket Socket Message Elapsed Send Recv Send Recv Size Size Size Time Throughput local remote local remote bytes bytes bytes secs. 10^6bits/s % S % U us/KB us/KB Before: 87380 16384 16384 10.00 33682.24 20.27 -1.00 0.592 -1.00 After: 87380 16384 16384 10.00 34204.08 20.54 -1.00 0.590 -1.00 So the net result of this patch is that we have a small gain in throughput due to a reduction in overhead for putting together the frame. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-02-18i40e/i40evf: Move Tx checksum closer to TSOAlexander Duyck1-5/+5
On all of the other Intel drivers we place checksum close to TSO as they have a significant amount in common and it can help to reduce the decision tree for how to handle the frame as the first check in TSO is to see if checksumming is offloaded, and if it is not we can skip _BOTH_ TSO and Tx checksum offload based on a single check. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2016-02-18i40e/i40evf: Rewrite logic for 8 descriptor per packet checkAlexander Duyck1-46/+59
This patch is meant to rewrite the logic for how we determine if we can transmit the frame or if it needs to be linearized. The previous code for this function was using a mix of division and modulus division as a part of computing if we need to take the slow path. Instead I have replaced this by simply working with a sliding window which will tell us if the frame would be capable of causing a single packet to span several descriptors. The logic for the scan is fairly simple. If any given group of 6 fragments is less than gso_size - 1 then it is possible for us to have one byte coming out of the first fragment, 6 fragments, and one or more bytes coming out of the last fragment. This gives us a total of 8 fragments which exceeds what we can allow so we send such frames to be linearized. Arguably the use of modulus might be more exact as the approach I propose may generate some false positives. However the likelihood of us taking much of a hit for those false positives is fairly low, and I would rather not add more overhead in the case where we are receiving a frame composed of 4K pages. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.