| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Conflicts:
drivers/net/ethernet/emulex/benet/be.h
drivers/net/netconsole.c
net/bridge/br_private.h
Three mostly trivial conflicts.
The net/bridge/br_private.h conflict was a function signature (argument
addition) change overlapping with the extern removals from Joe Perches.
In drivers/net/netconsole.c we had one change adjusting a printk message
whilst another changed "printk(KERN_INFO" into "pr_info(".
Lastly, the emulex change was a new inline function addition overlapping
with Joe Perches's extern removals.
Signed-off-by: David S. Miller <[email protected]>
|
|
In function mlx4_master_deactivate_admin_state() __mlx4_unregister_mac was
called using the MAC index. It should be called with the value of the MAC itself.
Signed-off-by: Jack Morgenstein <[email protected]>
Signed-off-by: Or Gerlitz <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Signed-off-by: Ben Boeckel <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Also snipes some trailing whitespace.
Signed-off-by: Ben Boeckel <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Also snipes some whitespace errors.
Signed-off-by: Ben Boeckel <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Signed-off-by: Ben Boeckel <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Also fixes an incorrect function comment (probably copy/paste).
Signed-off-by: Ben Boeckel <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Also snipes some whitespace errors.
Signed-off-by: Ben Boeckel <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Also snipes some whitespace errors.
Signed-off-by: Ben Boeckel <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next
Jeff Kirsher says:
====================
This series contains updates to e1000, igb, ixgbe and ixgbevf.
Hong Zhiguo provides a fix for e1000 where tx_ring and adapter->tx_ring
are already of type "struct e1000_tx_ring" so no need to divide by
e1000_tx_ring size in the idx calculation.
Emil provides a fix for ixgbevf to remove a redundant workaround related
to header split and a fix for ixgbe to resolve an issue where the MTA table
can be cleared when the interface is reset while in promisc mode.
Todd provides a fix for igb to prevent ethtool from writing to the iNVM
in i210/i211 devices. This issue was reported by Marek Vasut <[email protected]>.
Anton Blanchard provides a fix for ixgbe to reduce memory consumption
with larger page sizes, seen on PPC.
Don provides a cleanup in ixgbe to replace the IXGBE_DESC_UNUSED macro with
the inline function ixgbevf_desc_unused() to make the logic a bit more
readable.
====================
Signed-off-by: David S. Miller <[email protected]>
|
|
This patch resolves an issue where the MTA table can be cleared when the
interface is reset while in promisc mode. As result IPv6 traffic between
VFs will be interrupted.
This patch makes the update of the MTA table unconditional to avoid the
inconsistent clearing on reset.
Signed-off-by: Emil Tantilov <[email protected]>
Tested-by: Phil Schmitt <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
This patch just replaces the IXGBE_DESC_UNUSED macro with a like named
inline function ixgbevf_desc_unused. The inline function makes the logic
a bit more readable.
Signed-off-by: Alexander Duyck <[email protected]>
Signed-off-by: Don Skidmore <[email protected]>
Tested-by: Phil Schmitt <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
The ixgbe driver allocates pages for its receive rings. It currently
uses 512 pages, regardless of page size. During receive handling it
adds the unused part of the page back into the rx ring, avoiding the
need for a new allocation.
On a ppc64 box with 64 threads and 64kB pages, we end up with
512 entries * 64 rx queues * 64kB = 2GB memory used. Even more of a
concern is that we use up 2GB of IOMMU space in order to map all this
memory.
The driver makes a number of decisions based on if PAGE_SIZE is less
than 8kB, so use this as the breakpoint and only allocate 128 entries
on 8kB or larger page sizes.
Signed-off-by: Anton Blanchard <[email protected]>
Tested-by: Phil Schmitt <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
Don't let ethtool try to write to iNVM in i210/i211.
This fixes an issue seen by Marek Vasut.
Reported-by: Marek Vasut <[email protected]>
Signed-off-by: Todd Fujinaka <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
This patch removes a workaround related to header split, which is redundant
because the driver does not support splitting packet headers on Rx.
Signed-off-by: Emil Tantilov <[email protected]>
Tested-by: Phil Schmitt <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
tx_ring and adapter->tx_ring are already of type "struct
e1000_tx_ring *"
Signed-off-by: Hong Zhiguo <[email protected]>
Tested-by: Aaron Brown <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
When using firmware assisted TSO, we use a single DMA mapping for
the linear area of a TSO skb.
We still have to segment the super-packet and insert a descriptor
containing the original headers before each segment of payload, so we
can unmap the linear area only after the last segment is completed.
The unmapping information for the linear area is therefore associated
with the last header descriptor.
We calculate the DMA address to unmap from using the map length and
the invariant that the end of the DMA mapping matches the end of
the data referenced by the last descriptor. But this invariant is
broken when there is TCP payload in the linear area.
Fix this by adding and using an explicit dma_offset field.
Signed-off-by: Ben Hutchings <[email protected]>
|
|
The code sequence:
pdev->dev.coherent_dma_mask = DMA_BIT_MASK(64);
pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask;
bypasses the architectures check on the DMA mask. It can be replaced
with dma_coerce_mask_and_coherent(), avoiding the direct initialization
of this mask.
Signed-off-by: Russell King <[email protected]>
|
|
The code sequence:
pldat->pdev->dev.coherent_dma_mask = 0xFFFFFFFF;
pldat->pdev->dev.dma_mask = &pldat->pdev->dev.coherent_dma_mask;
bypasses the architectures check on the DMA mask. It can be replaced
with dma_coerce_mask_and_coherent(), avoiding the direct initialization
of this mask.
Signed-off-by: Russell King <[email protected]>
|
|
Copying whole packets with skb_copy_from_linear_data_offset is a pretty
bad idea. CPU was spending time in __copy_user_common and network
performance was lower. With the new solution iperf-measured speed
increased from 116Mb/s to 134Mb/s.
Signed-off-by: Rafał Miłecki <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Don't update the slot in "bgmac_dma_rx_skb_for_slot" unless both the
skb alloc and dma mapping are successful; and free the newly allocated
skb if a dma mapping error occurs. This relieves the caller of the need
to deduce/execute the appropriate cleanup action required when an error
occurs.
Signed-off-by: Nathan Hintz <[email protected]>
Acked-by: Rafał Miłecki <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Calls to mal_enable_eob_irq perform a read-write-modify of a dcr to
enable device irqs which is protected by a spin lock. However calls to
mal_disable_eob_irq do not take the corresponding lock.
This patch resolves the problem by ensuring that calls to
mal_disable_eob_irq also take the lock.
Signed-off-by: Alistair Popple <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
This patch fixes a bug which would trigger the BUG_ON() at
net/core/dev.c:4156. It was found that this was due to continuing
processing in the current poll call even when the call to
napi_reschedule failed, indicating the device was already on the
polling list. This resulted in an extra call to napi_complete which
triggered the BUG_ON().
This patch ensures that we only contine processing rotting packets in
the current mal_poll call if we are not already on the polling list.
Signed-off-by: Alistair Popple <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Checking if MAC address is valid using is_valid_ether_addr() is already done in
of_get_mac_address(). While at it, reorganize checking so it matches checks in
other drivers.
Signed-off-by: Luka Perkov <[email protected]>
CC: Alexey Brodkin <[email protected]>
CC: David Miller <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Checking if MAC address is valid using is_valid_ether_addr() is already done in
of_get_mac_address().
Signed-off-by: Luka Perkov <[email protected]>
Acked-by: Thomas Petazzoni <[email protected]>
CC: David Miller <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Checking if MAC address is valid using is_valid_ether_addr() is already done in
of_get_mac_address().
Signed-off-by: Luka Perkov <[email protected]>
Acked-by: David Daney <[email protected]>
CC: David Miller <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next
Jeff Kirsher says:
====================
This series contains updates to vxlan, net, ixgbe, ixgbevf, and i40e.
Joseph provides a single patch against vxlan which removes the burden
from the NIC drivers to check if the vxlan driver is enabled in the
kernel and also makes available the vxlan headrooms to the drivers.
Jacob provides majority of the patches, with patches against net, ixgbe
and ixgbevf. His net patch adds might_sleep() call to napi_disable so
that every use of napi_disable during atomic context will be visible.
Then Jacob provides a patch to fix qv_lock_napi call in
ixgbe_napi_disable_all. The other ixgbe patches cleanup
ixgbe_check_minimum_link function to correctly show that there are some
minor loss of encoding, even though we don't calculate it and remove
unnecessary duplication of PCIe bandwidth display. Lastly, Jacob
provides 4 patches against ixgbevf to add ixgbevf_rx_skb in line with
how ixgbe handles the variations on how packets can be received, adds
support in order to track how many packets were cleaned during busy poll
as part of the extended statistics.
Wei Yongjun provides a fix for i40e to return -ENOMEN in the memory
allocation error handling case instead of returning 0, as done
elsewhere in this function.
====================
Signed-off-by: David S. Miller <[email protected]>
|
|
Amend the documentation in the mvmdio driver to note the fact
that it is now used by both the mvneta and mv643xx_eth drivers.
Signed-off-by: Leigh Brown <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Make only a single call to mutex_unlock in orion_mdio_write.
Signed-off-by: Leigh Brown <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Replace manual poll of MVMDIO_SMI_READ_VALID with a call to
orion_mdio_wait_ready. This ensures a consistent timeout,
eliminates a busy loop, and allows for use of interrupts on
systems that support them.
Signed-off-by: Leigh Brown <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Amend orion_mdio_wait_ready so that the same timeout is used when
polling or using wait_event_timeout. Set the timeout to 1ms.
Replace udelay with usleep_range to avoid a busy loop, and set the
polling interval range as 45us to 55us, so that the first sleep
will be enough in almost all cases.
Generate the same log message at timeout when polling or using
wait_event_timeout.
Signed-off-by: Leigh Brown <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
The function needn't to be public, so to make it as static.
Signed-off-by: Gavin Shan <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
The interface type, which is being traced by "struct be_adapter::
if_type", isn't used currently. So we can remove that safely
according to Sathya's comments.
Signed-off-by: Gavin Shan <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
This cleans code a bit and will be useful when allocating buffers in
other places (like RX path, to avoid skb_copy_from_linear_data_offset).
Signed-off-by: Rafał Miłecki <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
This change complements commits d0da7c002f7b2a93582187a9e3f73891a01d8ee4
[MIPS: DEC: Convert to new irq_chip functions] and
5359b938c088423a28c41499f183cd10824c1816 [MIPS: DECstation I/O ASIC DMA
interrupt handling fix] and implements automatic handling of the two
classes of DMA interrupts the I/O ASIC implements, informational and
errors.
Informational DMA interrupts do not stop the transfer and use the
`handle_edge_irq' handler that clears the request right away so that
another request may be recorded while the previous is being handled.
DMA error interrupts stop the transfer and require a corrective action
before DMA can be reenabled. Therefore they use the `handle_fasteoi_irq'
handler that only clears the request on the way out. Because MIPS
processor interrupt inputs, one of which the I/O ASIC's interrupt
controller is cascaded to, are level-triggered it is recommended that
error DMA interrupt action handlers are registered with the IRQF_ONESHOT
flag set so that they are run with the interrupt line masked.
This change removes the export of clear_ioasic_dma_irq that now does not
have to be called by device drivers to clear interrupts explicitly
anymore. Originally these interrupts were cleared in the .end handler of
the `irq_chip' structure, before it was removed.
Signed-off-by: Maciej W. Rozycki <[email protected]>
Cc: [email protected]
Patchwork: https://patchwork.linux-mips.org/patch/5874/
Signed-off-by: Ralf Baechle <[email protected]>
|
|
Fix to return -ENOMEM in the memory alloc error handling
case instead of 0, as done elsewhere in this function.
Signed-off-by: Wei Yongjun <[email protected]>
Tested-by: Kavindya Deegala <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
This patch removes the need to keep a zero_base variable in the adapter
structure. Now we just use two different macros to set the non-zero and
zero base. This adds to readability and shortens some of the structure
initialization under 80 columns. The gathering of status for ethtool was
slightly modified to again better fit into 80 columns and become a bit
more readable.
Signed-off-by: Alexander Duyck <[email protected]>
Signed-off-by: Don Skidmore <[email protected]>
Tested-by: Phil Schmitt <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
This patch adds the extended statistics similar to the ixgbe driver. These
statistics keep track of how often the busy polling yields, as well as how many
packets are cleaned or missed by the polling routine.
Signed-off-by: Jacob Keller <[email protected]>
Tested-by: Phil Schmitt <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
This patch enables CONFIG_NET_RX_BUSY_POLL support in the VF code. This enables
sockets which have enabled the SO_BUSY_POLL socket option to use the
ndo_busy_poll_recv operation which could result in lower latency, at the cost
of higher CPU utilization, and increased power usage. This support is similar
to how the ixgbe driver works.
Signed-off-by: Jacob Keller <[email protected]>
Tested-by: Phil Schmitt <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
Rather than return true/false indicating whether there was budget left, return
the total packets cleaned. This currently has no use, but will be used in a
following patch which enables CONFIG_NET_RX_BUSY_POLL support in order to track
how many packets were cleaned during the busy poll as part of the extended
statistics.
Signed-off-by: Jacob Keller <[email protected]>
Tested-by: Phil Schmitt <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
This patch adds ixgbevf_rx_skb in line with how ixgbe handles the variations on
how packets can be received. It will be extended in a following patch for
CONFIG_NET_RX_BUSY_POLL support.
Signed-off-by: Jacob Keller <[email protected]>
Tested-by: Phil Schmitt <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
This patch removes the unnecessary display of PCIe bandwidth twice. Since the
ixgbe_check_minimum_link does a better job, and ensures accurate detection on
even complex chains, this older check is no longer necessary.
Signed-off-by: Jacob Keller <[email protected]>
Tested-by: Phil Schmitt <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
This patch updates the ixgbe_check_minimum_link function to correctly show that
there is some minor loss of encoding, even though we don't calculate it in the
max GT/s equation. It is small enough to not bother, but is better to report it
than not.
Signed-off-by: Jacob Keller <[email protected]>
Tested-by: Phil Schmitt <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
ixgbe_napi_disable_all calls napi_disable on each queue, however the busy
polling code introduced a local_bh_disable()d context around the napi_disable.
The original author did not realize that napi_disable might sleep, which would
cause a sleep while atomic BUG. In addition, on a single processor system, the
ixgbe_qv_lock_napi loop shouldn't have to mdelay. This patch adds an
ixgbe_qv_disable along with a new IXGBE_QV_STATE_DISABLED bit, which it uses to
indicate to the poll and napi routines that the q_vector has been disabled. Now
the ixgbe_napi_disable_all function will wait until all pending work has been
finished and prevent any future work from being started.
Signed-off-by: Jacob Keller <[email protected]>
Cc: Eliezer Tamir <[email protected]>
Cc: Alexander Duyck <[email protected]>
Cc: Hyong-Youb Kim <[email protected]>
Cc: Amir Vadai <[email protected]>
Cc: Dmitry Kravkov <[email protected]>
Tested-by: Phil Schmitt <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
|
|
The length calculation here is now invalid on 32-bit architectures,
since sk_buff::tail is a pointer and sk_buff::transport_header is
an integer offset:
drivers/net/ethernet/chelsio/cxgb3/sge.c: In function 'write_ofld_wr':
drivers/net/ethernet/chelsio/cxgb3/sge.c:1603:9: warning: passing argument 4 of 'make_sgl' makes integer from pointer without a cast [enabled by default]
adap->pdev);
^
drivers/net/ethernet/chelsio/cxgb3/sge.c:964:28: note: expected 'unsigned int' but argument is of type 'sk_buff_data_t'
static inline unsigned int make_sgl(const struct sk_buff *skb,
^
Use the appropriate skb accessor functions.
Compile-tested only.
Signed-off-by: Ben Hutchings <[email protected]>
Fixes: 1a37e412a022 ('net: Use 16bits for *_headers fields of struct skbuff')
Signed-off-by: David S. Miller <[email protected]>
|
|
When the bnx2x driver is rmmoded, if VFs of a given PF will be assigned
to a VM then that PF will be unable to call `pci_disable_sriov()'.
If for that same PF there would also exist unassigned VFs in the hypervisor,
the result will be that after the removal there will still be virtual PCI
functions on the hypervisor.
If the bnx2x module were to be re-inserted, the result will be that the VFs
on the hypervisor will be re-probed directly following the PF's probe, even
though that in regular loading flow sriov is only enabled once PF is loaded.
The probed VF will then try to access its bar, causing a PCI error as the HW
is not in a state enabling such a request.
This patch adds a missing disablement procedure to the PF's removal, one that
sets registers viewable to the VF to indicate that the VFs have no permission
to access the bar, thus resulting in probe errors instead of PCI errors.
Signed-off-by: Ariel Elior <[email protected]>
Signed-off-by: Yuval Mintz <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Buffers for FW statistics were allocated at an inappropriate time; In a machine
where the driver encounters problems allocating all of its queues, the driver
would still create FW requests for the statistics of the non-existing queues.
The wrong order of memory allocation could lead to zeroed statistics messages
being sent, leading to fw assert in case function 0 was down.
This changes the order of allocations, guaranteeing that statistic requests will
only be generated for actual queues.
Signed-off-by: Dmitry Kravkov <[email protected]>
Signed-off-by: Yuval Mintz <[email protected]>
Signed-off-by: Ariel Elior <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Includes:
- ndo_busy_poll implementation
- Locking between napi and busy_poll
- Fix rx_post_starvation (replenish rx-queues in out-of-mememory scenario)
logic to accomodate busy_poll.
v2 changes:
[Eric D.'s comment] call alloc_pages() with GFP_ATOMIC even in ndo_busy_poll
context as it is not allowed to sleep.
Signed-off-by: Sathya Perla <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
old FW versions with latest driver
On very old FW versions < 4.0, the mailbox command to set interrupts
on the card succeeds even though it is not supported and should have
failed, leading to a scenario where interrupts do not work.
Hence warn users to upgrade to a suitable FW version to avoid seeing
broken functionality.
Signed-off-by: Somnath Kotur <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|
|
Only 82xx adapter advertises QLCNIC_FW_CAPABILITY_MORE_CAPS bit.
Reading this bit from 83xx adapter causes the driver to skip
extra capabilities registers.
Because of this, driver was not issuing qlcnic_fw_cmd_set_drv_version()
for 83xx adapter.
This bug was introduced in commit 8af3f33db05c6d0146ad14905145a5c923770856
("qlcnic: Add support for 'set driver version' in 83XX").
Signed-off-by: Shahed Shaikh <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
|