summaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/intel
Commit message (Collapse)AuthorAgeFilesLines
...
* | igb: reset the PHY before reading the PHY IDAaron Sierra2017-01-061-0/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Several people have reported firmware leaving the I210/I211 PHY's page select register set to something other than the default of zero. This causes the first accesses, PHY_IDx register reads, to access something else, resulting in device probe failure: igb: Intel(R) Gigabit Ethernet Network Driver - version 5.4.0-k igb: Copyright (c) 2007-2014 Intel Corporation. igb: probe of 0000:01:00.0 failed with error -2 This problem began for them after a previous patch I submitted was applied: commit 2a3cdead8b408351fa1e3079b220fa331480ffbc Author: Aaron Sierra <asierra@xes-inc.com> Date: Tue Nov 3 12:37:09 2015 -0600 igb: Remove GS40G specific defines/functions I personally experienced this problem after attempting to PXE boot from I210 devices using this firmware: Intel(R) Boot Agent GE v1.5.78 Copyright (C) 1997-2014, Intel Corporation Resetting the PHY before reading from it, ensures the page select register is in its default state and doesn't make assumptions about the PHY's register set before the PHY has been probed. Cc: Matwey V. Kornilov <matwey@sai.msu.ru> Cc: Chris Arges <carges@vectranetworks.com> Cc: Jochen Henneberg <jh@henneberg-systemdesign.com> Signed-off-by: Aaron Sierra <asierra@xes-inc.com> Tested-by: Matwey V. Kornilov <matwey@sai.msu.ru> Tested-by: Chris J Arges <christopherarges@gmail.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: use igb_adapter->io_addr instead of e1000_hw->hw_addrCao jin2017-01-061-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When running as guest, under certain condition, it will oops as following. writel() in igb_configure_tx_ring() results in oops, because hw->hw_addr is NULL. While other register access won't oops kernel because they use wr32/rd32 which have a defense against NULL pointer. [ 141.225449] pcieport 0000:00:1c.0: AER: Multiple Uncorrected (Fatal) error received: id=0101 [ 141.225523] igb 0000:01:00.1: PCIe Bus Error: severity=Uncorrected (Fatal), type=Unaccessible, id=0101(Unregistered Agent ID) [ 141.299442] igb 0000:01:00.1: broadcast error_detected message [ 141.300539] igb 0000:01:00.0 enp1s0f0: PCIe link lost, device now detached [ 141.351019] igb 0000:01:00.1 enp1s0f1: PCIe link lost, device now detached [ 143.465904] pcieport 0000:00:1c.0: Root Port link has been reset [ 143.465994] igb 0000:01:00.1: broadcast slot_reset message [ 143.466039] igb 0000:01:00.0: enabling device (0000 -> 0002) [ 144.389078] igb 0000:01:00.1: enabling device (0000 -> 0002) [ 145.312078] igb 0000:01:00.1: broadcast resume message [ 145.322211] BUG: unable to handle kernel paging request at 0000000000003818 [ 145.361275] IP: [<ffffffffa02fd38d>] igb_configure_tx_ring+0x14d/0x280 [igb] [ 145.400048] PGD 0 [ 145.438007] Oops: 0002 [#1] SMP A similar issue & solution could be found at: http://patchwork.ozlabs.org/patch/689592/ Signed-off-by: Cao jin <caoj.fnst@cn.fujitsu.com> Acked-by: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: Workaround for igb i210 firmware issueChris J Arges2017-01-061-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | Sometimes firmware may not properly initialize I347AT4_PAGE_SELECT causing the probe of an igb i210 NIC to fail. This patch adds an addition zeroing of this register during igb_get_phy_id to workaround this issue. Thanks for Jochen Henneberg for the idea and original patch. Signed-off-by: Chris J Arges <christopherarges@gmail.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: correct register commentsCao jin2017-01-061-1/+1
| | | | | | | | | | | | Signed-off-by: Cao jin <caoj.fnst@cn.fujitsu.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | e1000e: driver trying to free already-free irqkhalidm2017-01-061-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | During systemd reboot sequence network driver interface is shutdown by e1000_close. The PCI driver interface is shut by e1000_shutdown. The e1000_shutdown checks for netif_running status, if still up it brings down driver. But it disables msi outside of this if statement, regardless of netif status. All this is OK when e1000_close happens after shutdown. However, by default, everything in systemd is done in parallel. This creates a conditions where e1000_shutdown is called after e1000_close, therefore hitting BUG_ON assert in free_msi_irqs. CC: xe-kernel@external.cisco.com Signed-off-by: khalidm <khalidm@cisco.com> Signed-off-by: David Singleton <davsingl@cisco.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | igb: Realign bad indentationJoe Perches2017-01-061-9/+6
| | | | | | | | | | | | | | | | | | | | Statements should start on tabstops. Use a single statement and test instead of multiple tests. Signed-off-by: Joe Perches <joe@perches.com> Tested-by: Aaron Brown <aaron.f.brown@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: Add PF support for VF promiscuous modeDon Skidmore2017-01-034-6/+45
| | | | | | | | | | | | | | | | | | | | | | | | This patch extends the xcast mailbox message to include support for unicast promiscuous mode. To allow a VF to enter this mode the PF must be in promiscuous mode. A later patch will add the support needed in the VF driver (ixgbevf) Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbevf: Add support for VF promiscuous modeDon Skidmore2017-01-034-5/+36
| | | | | | | | | | | | | | | | | | This patch extends the mailbox message to allow for VF promiscuous mode support. Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: Implement support for firmware-controlled PHYsMark Rustad2017-01-037-6/+642
| | | | | | | | | | | | | | | | Implement support for devices that have firmware-controlled PHYs. Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Krishneil Singh <krishneil.k.singh@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: Implement firmware interface to access some PHYsMark Rustad2017-01-033-0/+113
| | | | | | | | | | | | | | | | Implement new interface for firmware commands to access some PHYs. Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Krishneil Singh <krishneil.k.singh@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: Remove unused firmware version functions and methodMark Rustad2017-01-037-46/+1
| | | | | | | | | | | | | | | | | | The firmware version method and functions are not used anywhere, so remove them all. Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Krishneil Singh <krishneil.k.singh@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: Fix issues with EEPROM accessMark Rustad2017-01-033-82/+91
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There are two problems with EEPROM access. One is that it needs to hold the semaphore until the entire response is read or else the response can be corrupted by other firmware accesses. The second problem is that acquiring and releasing the semaphore is slow, so it should be taken and released once when multiple EEPROM accesses will be done. Both of these issues can be solved by adding a new function, ixgbe_hic_unlocked, to issue firmware commands that will assume that the caller has acquired the needed semaphore. Signed-off-by: Mark Rustad <mark.d.rustad@intel.com> Tested-by: Krishneil Singh <krishneil.k.singh@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: Configure advertised speeds correctly for KR/KX backplaneDon Skidmore2017-01-031-3/+2
| | | | | | | | | | | | | | | | | | This patch ensures that the advertised link speeds are configured for X553 KR/KX backplane. Without this patch the link remains at 1G when resuming from low power after being downshifted by LPLU. Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbevf: restore hw_addr on resume or errorEmil Tantilov2017-01-031-0/+3
| | | | | | | | | | | | | | | | | | Restore adapter->hw.hw_addr after handling an error, or a resume operation to make sure we can access the registers. Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: Fix incorrect bitwise operations of PTP Rx timestamp flagsYusuke Suzuki2017-01-031-6/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Rx timestamp does not work on 82599 and X540 because bitwise operation of RX_HWTSTAMP flags is incorrect and ixgbe_ptp_rx_hwtstamp() is never called. This patch fixes it to enable Rx timestamp on 82599 and X540. Without this fix: ptp4l[278.730]: selected /dev/ptp8 as PTP clock ptp4l[278.733]: port 1: INITIALIZING to LISTENING on INITIALIZE ptp4l[278.733]: port 0: INITIALIZING to LISTENING on INITIALIZE ptp4l[278.834]: port 1: received SYNC without timestamp ptp4l[278.835]: port 1: new foreign master 1c3947.fffe.60f9cc-1 ptp4l[279.834]: port 1: received SYNC without timestamp ptp4l[280.834]: port 1: received SYNC without timestamp ptp4l[281.834]: port 1: received SYNC without timestamp ptp4l[282.834]: port 1: received SYNC without timestamp ptp4l[282.835]: selected best master clock 1c3947.fffe.60f9cc ptp4l[282.835]: port 1: LISTENING to UNCALIBRATED on RS_SLAVE ptp4l[283.834]: port 1: received SYNC without timestamp With this fix: ptp4l[239.154]: selected /dev/ptp8 as PTP clock ptp4l[239.157]: port 1: INITIALIZING to LISTENING on INITIALIZE ptp4l[239.157]: port 0: INITIALIZING to LISTENING on INITIALIZE ptp4l[240.989]: port 1: new foreign master 1c3947.fffe.60f9cc-1 ptp4l[244.989]: selected best master clock 1c3947.fffe.60f9cc ptp4l[244.989]: port 1: LISTENING to UNCALIBRATED on RS_SLAVE ptp4l[246.977]: master offset -899583339542096 s0 freq +0 path delay 16222 ptp4l[247.977]: master offset -899583339617265 s1 freq -75169 path delay 16177 ptp4l[248.977]: master offset -130 s2 freq -75299 path delay 16177 ptp4l[248.977]: port 1: UNCALIBRATED to SLAVE on MASTER_CLOCK_SELECTED ptp4l[249.977]: master offset -9 s2 freq -75217 path delay 16177 ptp4l[250.977]: master offset 88 s2 freq -75123 path delay 16132 Fixes: a9763f3cb54c ("ixgbe: Update PTP to support X550EM_x devices") Signed-off-by: Yusuke Suzuki <yus-suzuki@uf.jp.nec.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbevf: fix AER error handlingEmil Tantilov2017-01-031-18/+25
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Make sure that we free the IRQs in ixgbevf_io_error_detected() when responding to an PCIe AER error and also restore them when the interface recovers from it. Previously it was possible to trigger BUG_ON() check in free_msix_irqs() in the case where we call ixgbevf_remove() after a failed recovery from AER error because the interrupts were not freed. Also moved the down and free functions into ixgbevf_close_suspend() same as with ixgbe. Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: fix AER error handlingEmil Tantilov2017-01-031-2/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Make sure that we free the IRQs in ixgbe_io_error_detected() when responding to an PCIe AER error and also restore them when the interface recovers from it. Previously it was possible to trigger BUG_ON() check in free_msix_irqs() in the case where we call ixgbe_remove() after a failed recovery from AER error because the interrupts were not freed. Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: test for trust in macvlan adjustments for VFKen Cox2017-01-031-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There are two methods for setting mac addresses in a Macvlan, that differentiate themselves in the function macvlan_set_mac_Address. If the macvlan mode is passthru, then we use the dev_set_mac_address method, otherwise we use the dev_uc api via macvlan_sync_addresses. The latter method (which would stem from using any non-passthru mode, like bridge, or vepa), calls down into the driver in a path that terminates in ixgbevf_set_uc_addr_vf, which sends a IXGBE_VF_SET_MACVLAN message, which causes the pf to spawn the noted error message. This occurs because it appears that the guest is trying to delete the mac address of the macvlan before adding another. The other path in macvlan_set_mac_address uses dev_set_mac_address, which calls into ixgbevf_set_mac which uses the IXGBE_VF_SET_MAC_ADDR to the pf to set the macvlan mac address. The discrepancy here is in the handlers. The handler function for IXGBE_VF_SET_MAC_ADDR (ixgbe_set_vf_mac_addr) has a check for the vfinfo[].trusted bit to allow the operation if the vf is trusted. In comparison, the IXGBE_VF_SET_MACVLAN message handler (ixgbe_set_vf_macvlan_msg) has no such check of the trusted bit. Signed-off-by: Ken Cox <jkc@redhat.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbevf: handle race between close and suspend on shutdownEmil Tantilov2017-01-031-2/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When an interface is part of a namespace it is possible that ixgbevf_close() may be called while ixgbevf_suspend() is running which ends up in a double free WARN and/or a BUG in free_msi_irqs() To handle this situation we extend the rtnl_lock() to protect the call to netif_device_detach() and check for !netif_device_present() to avoid entering close while in suspend. Also added rtnl locks to ixgbevf_queue_reset_subtask(). CC: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: handle close/suspend race with netif_device_detach/presentEmil Tantilov2017-01-031-9/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When an interface is part of a namespace it is possible that ixgbe_close() may be called while __ixgbe_shutdown() is running which ends up in a double free WARN and/or a BUG in free_msi_irqs(). To handle this situation we extend the rtnl_lock() to protect the call to netif_device_detach() and ixgbe_clear_interrupt_scheme() in __ixgbe_shutdown() and check for netif_device_present() to avoid clearing the interrupts second time in ixgbe_close(); Also extend the rtnl lock in ixgbe_resume() to netif_device_attach(). Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: Fix reporting of 100Mb capabilityTony Nguyen2017-01-031-1/+1
| | | | | | | | | | | | | | | | | | | | BaseT adapters that are capable of supporting 100Mb are not reporting this capability. This patch corrects the reporting so that 100Mb is shown as supported on those adapters. Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: Reduce I2C retry count on X550 devicesTony Nguyen2017-01-031-1/+3
| | | | | | | | | | | | | | | | | | | | | | A retry count of 10 is likely to run into problems on X550 devices that have to detect and reset unresponsive CS4227 devices. So, reduce the I2C retry count to 3 for X550 and above. This should avoid any possible regressions in existing devices. Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: Add bounds check for x540 LED functionsTony Nguyen2017-01-031-2/+7
| | | | | | | | | | | | | | | | | | | | This is an extension of commit 003287e0f087 ("ixgbevf: Correct parameter sent to LED function"); add bounds checking to x540 functions to ensure the index is valid. Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: add mask for 64 RSS queuesEmil Tantilov2017-01-031-1/+7
| | | | | | | | | | | | | | | | | | | | The indirection table was reported incorrectly for X550 and newer where we can support up to 64 RSS queues. Reported-by Krishneil Singh <krishneil.k.singh@intel.com> Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: Fix check for ixgbe_phy_x550em_ext_t resetTony Nguyen2017-01-031-4/+21
| | | | | | | | | | | | | | | | | | | | The generic PHY reset check we had previously is not sufficient for the ixgbe_phy_x550em_ext_t PHY type. Check 1.CC02.0 instead - same as ixgbe_init_ext_t_x550(). Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: Report driver version to firmware for x550 devicesTony Nguyen2017-01-035-7/+80
| | | | | | | | | | | | | | | | | | | | Some x550 devices require the driver version reported to its firmware; this patch sends the driver version string to the firmware through the host interface command for x550 devices. Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | ixgbe: do not disable FEC from the driverEmil Tantilov2017-01-031-2/+0
|/ | | | | | | | | FEC is configured by the NVM and the driver should not be overriding it. Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com> Tested-by: Krishneil Singh <krishneil.k.singh@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* clocksource: Use a plain u64 instead of cycle_tThomas Gleixner2016-12-254-15/+15
| | | | | | | | | | | | | | | | | | | | | There is no point in having an extra type for extra confusion. u64 is unambiguous. Conversion was done with the following coccinelle script: @rem@ @@ -typedef u64 cycle_t; @fix@ typedef cycle_t; @@ -cycle_t +u64 Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: John Stultz <john.stultz@linaro.org>
* Replace <asm/uaccess.h> with <linux/uaccess.h> globallyLinus Torvalds2016-12-241-1/+1
| | | | | | | | | | | | | This was entirely automated, using the script by Al: PATT='^[[:blank:]]*#[[:blank:]]*include[[:blank:]]*<asm/uaccess.h>' sed -i -e "s!$PATT!#include <linux/uaccess.h>!" \ $(git grep -l "$PATT"|grep -v ^include/linux/uaccess.h) to do the replacement at the end of the merge window. Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* igb: update code to better handle incrementing page countAlexander Duyck2016-12-142-8/+23
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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. Link: http://lkml.kernel.org/r/20161110113616.76501.17072.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: David Howells <dhowells@redhat.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Hans-Christian Noren Egtvedt <egtvedt@samfundet.no> Cc: Helge Deller <deller@gmx.de> Cc: James Hogan <james.hogan@imgtec.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Keguang Zhang <keguang.zhang@gmail.com> Cc: Ley Foon Tan <lftan@altera.com> Cc: Mark Salter <msalter@redhat.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Rich Felker <dalias@libc.org> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Steven Miao <realmz6@gmail.com> Cc: Tobias Klauser <tklauser@distanz.ch> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* igb: update driver to make use of DMA_ATTR_SKIP_CPU_SYNCAlexander Duyck2016-12-141-20/+33
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The ARM architecture provides a mechanism for deferring cache line invalidation in the case of map/unmap. This patch makes use of this mechanism to avoid unnecessary synchronization. A secondary effect of this change is that the portion of the page that has been synchronized for use by the CPU should be writable and could be passed up the stack (at least on ARM). The last bit that occurred to me is that on architectures where the sync_for_cpu call invalidates cache lines we were prefetching and then invalidating the first 128 bytes of the packet. To avoid that I have moved the sync up to before we perform the prefetch and allocate the skbuff so that we can actually make use of it. Link: http://lkml.kernel.org/r/20161110113611.76501.98897.stgit@ahduyck-blue-test.jf.intel.com Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: David Howells <dhowells@redhat.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Hans-Christian Noren Egtvedt <egtvedt@samfundet.no> Cc: Helge Deller <deller@gmx.de> Cc: James Hogan <james.hogan@imgtec.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Keguang Zhang <keguang.zhang@gmail.com> Cc: Ley Foon Tan <lftan@altera.com> Cc: Mark Salter <msalter@redhat.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Rich Felker <dalias@libc.org> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Steven Miao <realmz6@gmail.com> Cc: Tobias Klauser <tklauser@distanz.ch> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* Merge branch 'timers-core-for-linus' of ↵Linus Torvalds2016-12-121-5/+5
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull timer updates from Thomas Gleixner: "The time/timekeeping/timer folks deliver with this update: - Fix a reintroduced signed/unsigned issue and cleanup the whole signed/unsigned mess in the timekeeping core so this wont happen accidentaly again. - Add a new trace clock based on boot time - Prevent injection of random sleep times when PM tracing abuses the RTC for storage - Make posix timers configurable for real tiny systems - Add tracepoints for the alarm timer subsystem so timer based suspend wakeups can be instrumented - The usual pile of fixes and updates to core and drivers" * 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits) timekeeping: Use mul_u64_u32_shr() instead of open coding it timekeeping: Get rid of pointless typecasts timekeeping: Make the conversion call chain consistently unsigned timekeeping_Force_unsigned_clocksource_to_nanoseconds_conversion alarmtimer: Add tracepoints for alarm timers trace: Update documentation for mono, mono_raw and boot clock trace: Add an option for boot clock as trace clock timekeeping: Add a fast and NMI safe boot clock timekeeping/clocksource_cyc2ns: Document intended range limitation timekeeping: Ignore the bogus sleep time if pm_trace is enabled selftests/timers: Fix spelling mistake "Asyncrhonous" -> "Asynchronous" clocksource/drivers/bcm2835_timer: Unmap region obtained by of_iomap clocksource/drivers/arm_arch_timer: Map frame with of_io_request_and_map() arm64: dts: rockchip: Arch counter doesn't tick in system suspend clocksource/drivers/arm_arch_timer: Don't assume clock runs in suspend posix-timers: Make them configurable posix_cpu_timers: Move the add_device_randomness() call to a proper place timer: Move sys_alarm from timer.c to itimer.c ptp_clock: Allow for it to be optional Kconfig: Regenerate *.c_shipped files after previous changes ...
| * ptp_clock: Allow for it to be optionalNicolas Pitre2016-11-161-5/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In order to break the hard dependency between the PTP clock subsystem and ethernet drivers capable of being clock providers, this patch provides simple PTP stub functions to allow linkage of those drivers into the kernel even when the PTP subsystem is configured out. Drivers must be ready to accept NULL from ptp_clock_register() in that case. And to make it possible for PTP to be configured out, the select statement in those driver's Kconfig menu entries is converted to the new "imply" statement. This way the PTP subsystem may have Kconfig dependencies of its own, such as POSIX_TIMERS, without having to make those ethernet drivers unavailable if POSIX timers are cconfigured out. And when support for POSIX timers is selected again then the default config option for PTP clock support will automatically be adjusted accordingly. The pch_gbe driver is a bit special as it relies on extra code in drivers/ptp/ptp_pch.c. Therefore we let the make process descend into drivers/ptp/ even if PTP_1588_CLOCK is unselected. Signed-off-by: Nicolas Pitre <nico@linaro.org> Acked-by: Richard Cochran <richardcochran@gmail.com> Acked-by: Edward Cree <ecree@solarflare.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: John Stultz <john.stultz@linaro.org> Reviewed-by: Josh Triplett <josh@joshtriplett.org> Cc: Paul Bolle <pebolle@tiscali.nl> Cc: linux-kbuild@vger.kernel.org Cc: netdev@vger.kernel.org Cc: Michal Marek <mmarek@suse.com> Link: http://lkml.kernel.org/r/1478841010-28605-4-git-send-email-nicolas.pitre@linaro.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* | e1000: use disable_hardirq() for e1000_netpoll()WANG Cong2016-12-102-6/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In commit 02cea3958664 ("genirq: Provide disable_hardirq()") Peter introduced disable_hardirq() for netpoll, but it is forgotten to use it for e1000. This patch changes disable_irq() to disable_hardirq() for e1000. Reported-by: Dave Jones <davej@codemonkey.org.uk> Suggested-by: Sabrina Dubroca <sd@queasysnail.net> Cc: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | i40e: don't truncate match_method assignmentKeller, Jacob E2016-12-101-2/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | The .match_method field is a u8, so we shouldn't be casting to a u16, and because it is only one byte, we do not need to byte swap anything. Just assign the value directly. This avoids issues on Big Endian architectures which would have byte swapped and then incorrectly truncated the value. Signed-off-by: Jacob Keller <jacob.e.keller@intel.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bimmy Pujari <bimmy.pujari@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | i40e: move all updates for VLAN mode into i40e_sync_vsi_filtersJacob Keller2016-12-061-101/+113
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In a similar fashion to how we handled exiting VLAN mode, move the logic in i40e_vsi_add_vlan into i40e_sync_vsi_filters. Extract this logic into its own function for ease of understanding as it will become quite complex. The new function, i40e_correct_mac_vlan_filters() correctly updates all filters for when we need to enter VLAN mode, exit VLAN mode, and also enforces the PVID when assigned. Call i40e_correct_mac_vlan_filters from i40e_sync_vsi_filters passing it the number of active VLAN filters, and the two temporary lists. Remove the function for updating VLAN=0 filters from i40e_vsi_add_vlan. The end result is that the logic for entering and exiting VLAN mode is in one location which has the most knowledge about all filters. This ensures that we always correctly have the non-VLAN filters assigned to VID=0 or VID=-1 regardless of how we ended up getting to this result. Additionally this enforces the PVID at sync time so that we know for certain that an assigned PVID results in only filters with that PVID will be added to the firmware. Change-ID: I895cee81e9c92d0a16baee38bd0ca51bbb14e372 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>
* | i40e: use (add|rm)_vlan_all_mac helper functions when changing PVIDJacob Keller2016-12-063-17/+32
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The current flow for adding or updating the PVID for a VF uses i40e_vsi_add_vlan and i40e_vsi_kill_vlan which each take, then release the hash lock. In addition the two functions also must take special care that they do not perform VLAN mode changes as this will make the code in i40e_ndo_set_vf_port_vlan behave incorrectly. Fix these issues by using the new helper functions i40e_add_vlan_all_mac and i40e_rm_vlan_all_mac which expect the hash lock to already be taken. Additionally these functions do not perform any state updates in regards to VLAN mode, so they are safe to use in the PVID update flow. It should be noted that we don't need the VLAN mode update code here, because there are only a few flows here. (a) we're adding a new PVID In this case, if we already had VLAN filters the VSI is knocked offline so we don't need to worry about pre-existing VLAN filters (b) we're replacing an existing PVID In this case, we can't have any VLAN filters except those with the old PVID which we already take care of manually. (c) we're removing an existing PVID Similarly to above, we can't have any existing VLAN filters except those with the old PVID which we already take care of correctly. Because of this, we do not need (or even want) the special accounting done in i40e_vsi_add_vlan, so use of the helpers is a saner alternative. It also opens the door for a future patch which will refactor the flow of i40e_vsi_add_vlan now that it is not needed in this function. Change-ID: Ia841f63da94e12b106f41cf7d28ce8ce92f2ad99 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>
* | i40e: factor out addition/deletion of VLAN per each MAC addressJacob Keller2016-12-061-13/+55
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | A future refactor of how the PF assigns a PVID to a VF will want to be able to add and remove a block of filters by VLAN without worrying about accidentally triggering the accounting for I40E_VLAN_ANY. Additionally the PVID assignment would like to be able to batch several changes under one use of the mac_filter_hash_lock. Factor out the addition and deletion of a VLAN on all MACs into their own function which i40e_vsi_(add|kill)_vlan can use. These new functions expect the caller to take the hash lock, as well as perform any necessary accounting for updating I40E_VLAN_ANY filters if we are now operating under VLAN mode. Change-ID: If79e5b60b770433275350a74b3f1880333a185d5 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>
* | i40e: delete filter after adding its replacement when convertingJacob Keller2016-12-061-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fix a subtle issue with the code for converting VID=-1 filters into VID=0 filters when adding a new VLAN. Previously the code deleted the VID=-1 filter, and then added a new VID=0 filter. In the rare case that the addition fails due to -ENOMEM, we end up completely deleting the filter which prevents recovery if memory pressure subsides. While it is not strictly an issue because it is likely that memory issues would result in many other problems, we shouldn't delete the filter until after the addition succeeds. Change-ID: Icba07ddd04ecc6a3b27c2e29f2c1c8673d266826 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>
* | i40e: refactor i40e_update_filter_state to avoid passing aq_errJacob Keller2016-12-061-37/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The current caller of i40e_update_filter_state incorrectly passes aq_ret, an i40e_status variable, instead of the expected aq_err. This happens to work because i40e_status is actually just a typedef integer, and 0 is still the successful return. However i40e_update_filter_state has special handling for ENOSPC which is currently being ignored. Also notice that firmware does not update the per-filter response for many types of errors, such as EINVAL. Thus, modify the filter setup so that the firmware response memory is pre-set with I40E_AQC_MM_ERR_NO_RES. This enables us to refactor i40e_update_filter_state, removing the need to pass aq_err and avoiding a need for having 3 different flows for checking the filter state. The resulting code for i40e_update_filter_state is much simpler, only a single loop and we always check each filter response value every time. Since we pre-set the response value to match our expected error this correctly works for all success and error flows. Change-ID: Ie292c9511f34ee18c6ef40f955ad13e28b7aea7d 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>
* | i40e: recalculate vsi->active_filters from hash contentsJacob Keller2016-12-061-23/+29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Previous code refactors have accidentally caused issues with the counting of active_filters. Avoid similar issues in the future by simply re-counting the active filters every time after we handle add and delete of all the filters. Additionally this allows us to simplify the check for when we exit promiscuous mode since we can combine the check for failed filters at the same time. Additionally since we recount filters at the end we need to set vsi->promisc_threshold as well. The resulting code takes a bit longer since we do have to loop over filters again. However, the result is more readable and less likely to become incorrect due to failed accounting of filters in the future. Finally, this ensures that it is not possible for vsi->active_filters to ever underflow since we never decrement it. Change-ID: Ib4f3a377e60eb1fa6c91ea86cc02238c08edd102 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>
* | i40e: defeature support for PTP L4 frame detection on XL710Jacob Keller2016-12-064-9/+31
| | | | | | | | | | | | | | | | | | | | | | A product decision has been made to defeature detection of PTP frames over L4 (UDP) on the XL710 MAC. Do not advertise support for L4 timestamping. Change-ID: I41fbb0f84ebb27c43e23098c08156f2625c6ee06 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>
* | i40e: lock service task correctlyMitch Williams2016-12-061-17/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The service task lock was being set in the scheduling function, not the actual service task. This would potentially leave the bit set for a long time before the task actually ran. Furthermore, if the service task takes too long, it calls the schedule function to reschedule itself - which would fail to take the lock and do nothing. Instead, set and clear the lock bit in the service task itself. In the process, get rid of the i40e_service_event_complete() function, which is really just two lines of code that can be put right in the service task itself. Change-ID: I83155e682b686121e2897f4429eb7d3f7c669168 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>
* | i40e: Add functions which apply correct PHY access method for read and write ↵Michal Kosiarz2016-12-063-0/+80
| | | | | | | | | | | | | | | | | | | | | | | | | | operation Depending on external PHY type, register access method should be different. Clause22 or Clause45 can be chosen for different PHYs. Implemented functions apply correct access method for used device. Change-ID: If39d5f0da9c0b905a8cbdc1ab89885535e7d0426 Signed-off-by: Michal Kosiarz <michal.kosiarz@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | i40e: Add FEC for 25gCarolyn Wyborny2016-12-063-4/+48
| | | | | | | | | | | | | | | | | | | | | | | | This patch adds adminq support for Forward Error Correction ("FEC")for 25g products. Change-ID: Iaff4910737c239d2c730e5c22a313ce9c37d3964 Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com> Signed-off-by: Mitch Williams <mitch.a.williams@intel.com> Signed-off-by: Jacek Naczyk <jacek.naczyk@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | i40e: Add support for 25G devicesCarolyn Wyborny2016-12-0613-79/+208
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add support for 25G devices - defines and data structures. One tricky part here is that the firmware support for these Devices introduces a mismatch between the PHY type enum and the bitfields for the phy types. This change creates a macro and uses it to increment the 25G PHY values when creating 25G bitfields. Change-ID: I69b24d837d44cf9220bf5cb8dd46c5be89ce490b Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com> 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>
* | i40e: use unsigned printf format specifier for active_filters countJacob Keller2016-12-061-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | Replace the %d specifier used for printing vsi->active_filters and vsi->promisc_threshold with an unsigned %u format specifier. While it is unlikely in practice that these values will ever reach such a large number they are unsigned values and thus should not be interpreted as negative numbers. Change-ID: Iff050fad5a1c8537c4c57fcd527441cd95cfc0d4 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>
* | Changed version from 1.6.21 to 1.6.25Bimmy Pujari2016-12-062-2/+2
| | | | | | | | | | | | Signed-off-by: Bimmy Pujari <bimmy.pujari@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | i40e: Blink LED on 1G BaseT boardsHenry Tieman2016-12-063-8/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Before this patch "ethtool -p" was not blinking the LEDs on boards with 1G BaseT PHYs. This commit identifies 1G BaseT boards as having the LEDs connected to the MAC. Also, renamed the flag to be more descriptive of usage. The flag is now I40E_FLAG_PHY_CONTROLS_LEDS. Change-ID: I4eb741da9780da7849ddf2dc4c0cb27ffa42a801 Signed-off-by: Henry Tieman <henry.w.tieman@intel.com> Signed-off-by: Harshitha Ramamurthy <harshitha.ramamurthy@intel.com> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
* | i40e: remove code to handle dev_addr speciallyJacob Keller2016-12-061-36/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The netdev->dev_addr MAC filter already exists in the MAC/VLAN hash table, as it is added when we configure the netdev in i40e_configure_netdev. Because we already know that this address will be updated in the hash_for_each loops, we do not need to handle it specially. This removes duplicate code and simplifies the i40e_vsi_add_vlan and i40e_vsi_kill_vlan functions. Because we know these filters must be part of the MAC/VLAN hash table, this should not have any functional impact on what filters are included and is merely a code simplification. Change-ID: I5e648302dbdd7cc29efc6d203b7019c11f0b5705 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>
OpenPOWER on IntegriCloud