- 30 Aug, 2015 8 commits
-
-
Haggai Eran authored
Add helper functions to access the IDRs by port-space and port number. Pass around the port-space enum in cma.c instead of using pointers to port-space IDRs. Signed-off-by:
Haggai Eran <haggaie@mellanox.com> Signed-off-by:
Yotam Kenneth <yotamke@mellanox.com> Signed-off-by:
Shachar Raindel <raindel@mellanox.com> Signed-off-by:
Guy Shapiro <guysh@mellanox.com> Signed-off-by:
Doug Ledford <dledford@redhat.com>
-
Haggai Eran authored
When receiving a connection request, rdma_cm needs to associate the request with a network device, in order to disambiguate requests. To do this, it needs to know the request's destination IP. For this the module needs to allow getting this information from the private data in the request packet, instead of relying on the information already being in the listening RDMA CM ID. When creating a new incoming connection ID, the code in cma_save_ip{4,6}_info can no longer rely on the listener's private data to find the port number, so it reads it from the requested service ID. Signed-off-by: -
Haggai Eran authored
Enabling network namespaces for RDMA CM will allow processes on different namespaces to listen on the same port. In order to leave namespace support out of the CM layer, this requires that multiple RDMA CM IDs will be able to share a single CM ID. This patch adds infrastructure to retrieve an existing listening ib_cm_id, based on its device and service ID, or create a new one if one does not already exist. It also adds a reference count for such instances (cm_id_private.listen_sharecount), and prevents cm_destroy_id from destroying a CM if it is still shared. See the relevant discussion [1]. [1] Re: [PATCH v3 for-next 05/13] IB/cm: Reference count ib_cm_ids http://www.spinics.net/lists/netdev/msg328860.htmlReviewed-by:Jason Gunthorpe <jgunthorpe@obsidianresearch.com> Signed-off-by:
-
Haggai Eran authored
Expose the service ID on an incoming CM or SIDR request to the event handler. This will allow the RDMA CM module to de-multiplex connection requests based on the information encoded in the service ID. Acked-by:
Sean Hefty <sean.hefty@intel.com> Signed-off-by:
-
Guy Shapiro authored
Implement the get_net_device_by_port_pkey_ip callback that returns network device to ib_core according to connection parameters. Check the ipoib device and iterate over all child devices to look for a match. For each IPoIB device we iterate through all upper devices when searching for a matching IP, in order to support bonding. Signed-off-by:
-
Yotam Kenneth authored
In the case of IPoIB, and maybe in other cases, the network device is managed by an upper-layer protocol (ULP). In order to expose this network device to other users of the IB device, let ULPs implement a callback that returns network device according to connection parameters. The IB device and port, together with the P_Key and the GID should be enough to uniquely identify the ULP net device. However, in current kernels there can be multiple IPoIB interfaces created with the same GID. Furthermore, such configuration may be desireable to support ipvlan-like configurations for RDMA CM with IPoIB. To resolve the device in these cases the code will also take the IP address as an additional input. Reviewed-by:
-
Haggai Eran authored
An ib_client callback that is called with the lists_rwsem locked only for read is protected from changes to the IB client lists, but not from ib_unregister_device() freeing its client data. This is because ib_unregister_device() will remove the device from the device list with lists_rwsem locked for write, but perform the rest of the cleanup, including the call to remove() without that lock. Mark client data that is undergoing de-registration with a new going_down flag in the client data context. Lock the client data list with lists_rwsem for write in addition to using the spinlock, so that functions calling the callback would be able to lock only lists_rwsem for read and let callbacks sleep. Since ib_unregister_client() now marks the client data context, no need for remove() to search the context again, so pass the client data directly to remove() callbacks. Reviewed-by:
-
Haggai Eran authored
Currently the RDMA subsystem's device list and client list are protected by a single mutex. This prevents adding user-facing APIs that iterate these lists, since using them may cause a deadlock. The patch attempts to solve this problem by adding a read-write semaphore to protect the lists. Readers now don't need the mutex, and are safe just by read-locking the semaphore. The ib_register_device, ib_register_client, ib_unregister_device, and ib_unregister_client functions are modified to lock the semaphore for write during their respective list modification. Also, in order to make sure client callbacks are called only between add() and remove() calls, the code is changed to only add items to the lists after the add() calls and remove from the lists before the remove() calls. This patch attempts to solve a similar need [1] that was seen in the RoCE v2 patch series. [1] http://www.spinics.net/lists/linux-rdma/msg24733.htmlReviewed-by:
-
- 29 Aug, 2015 19 commits
-
-
Steve Wise authored
This functionality already exists via the max_sge_rd device capability. Signed-off-by:
Steve Wise <swise@opengridcomputing.com> Signed-off-by:
-
Steve Wise authored
Signed-off-by:
-
Steve Wise authored
Applications must not assume that max_sge and max_sge_rd are the same, Hence expose max_sge_rd correctly as well. Signed-off-by:
Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by:
-
Sagi Grimberg authored
Applications must not assume that max_sge and max_sge_rd are the same, Hence expose max_sge_rd correctly as well. Reported-by:
Sagi Grimberg <sagig@mellanox.com> Signed-off-by:
-
Jeff Becker authored
Running checkpatch.pl on mad.c produces several "ERROR: code indent should use tabs where possible" messages. This patch fixes these. Signed-off-by:
Jeff Becker <Jeffrey.C.Becker@nasa.gov> Signed-off-by:
-
Mike Marciniszyn authored
Signed-off-by:
Andrew Friedley <andrew.friedley@intel.com> Signed-off-by:
Arthur Kepner <arthur.kepner@intel.com> Signed-off-by:
Brendan Cunningham <brendan.cunningham@intel.com> Signed-off-by:
Brian Welty <brian.welty@intel.com> Signed-off-by:
Caz Yokoyama <caz.yokoyama@intel.com> Signed-off-by:
Dean Luick <dean.luick@intel.com> Signed-off-by:
Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by:
Easwar Hariharan <easwar.hariharan@intel.com> Signed-off-by:
Harish Chegondi <harish.chegondi@intel.com> Signed-off-by:
Ira Weiny <ira.weiny@intel.com> Signed-off-by:
Jim Snow <jim.m.snow@intel.com> Signed-off-by:
John Gregor <john.a.gregor@intel.com> Signed-off-by:
Jubin John <jubin.john@intel.com> Signed-off-by:
Kaike Wan <kaike.wan@intel.com> Signed-off-by:
Kevin Pine <kevin.pine@intel.com> Signed-off-by:
Kyle Liddell <kyle.liddell@intel.com> Signed-off-by:
Mitko Haralanov <mitko.haralanov@intel.com> Signed-off-by:
Ravi Krishnaswamy <ravi.krishnaswamy@intel.com> Signed-off-by:
Sadanand Warrier <sadanand.warrier@intel.com> Signed-off-by:
Sanath Kumar <sanath.s.kumar@intel.com> Signed-off-by:
Sudeep Dutt <sudeep.dutt@intel.com> Signed-off-by:
Vlad Danushevsky <vladimir.danusevsky@intel.com> Signed-off-by:
-
Dennis Dalessandro authored
This patch adds the value of the CNP opcode to the existing list of enumerated opcodes in ib_pack.h Add common OPA header definitions for driver build: - opa_port_info.h - opa_smi.h - hfi1_user.h Additionally, ib_mad.h, has additional definitions that are common to ib_drivers including: - trap support - cca support The qib driver has the duplication removed in favor those in ib_mad.h Reviewed-by:
-
Steve Wise authored
The HW hasn't been sold since 2005, and the SW has definite bit rot. Its time to remove it. So move it to staging for a few releases and then remove it after that. Signed-off-by:
-
Dennis Dalessandro authored
It is now time for the ipath driver to begin to be phased out of the kernel. This patch moves the ipath driver from the Infiniband sub tree to the staging area where it will remain until the code is removed from the kernel in a few releases. Reviewed-by:
-
Doug Ledford authored
Create the rdma directory in the staging area for use as we deprecate some older drivers and as we bring in some new drivers that are in need of work. Update the MAINTAINERS file so that updates to these files go to linux-rdma@vger.kernel.org. Expected lifespan of this directory is three releases for any deprecated drivers moved here and an unknown, but theoretically bounded amount of time for the new drivers as a new core RDMA transfer library needs to be written and the drivers modified to use it in order for them to move out of this directory. Signed-off-by: -
Hariprasad S authored
Add support for ipv6 address handling clip api provided by lld Signed-off-by:
Hariprasad Shenai <hariprasad@chelsio.com> Acked-by:
-
Spencer Baugh authored
Resolving a link-local IPv6 address with an unspecified source address was broken by commit 5462eddd, which prevented the IPv6 stack from learning the scope id of the link-local IPv6 address, causing random failures as the IP stack chose a random link to resolve the address on. This commit 5462eddd made us bail out of cma_check_linklocal early if the address passed in was not an IPv6 link-local address. On the address resolution path, the address passed in is the source address; if the source address is the unspecified address, which is not link-local, we will bail out early. This is mostly correct, but if the destination address is a link-local address, then we will be following a link-local route, and we'll need to tell the IPv6 stack what the scope id of the destination address is. This used to be done by last line of cma_check_linklocal, which is skipped when bailing out early: dev_addr->bound_dev_if = sin6->sin6_scope_id; (In cma_bind_addr, the sin6_scope_id of the source address is set to the sin6_scope_id of the destination address, so this is correct) This line is required in turn for the following line, L279 of addr6_resolve, to actually inform the IPv6 stack of the scope id: fl6.flowi6_oif = addr->bound_dev_if; Since we can only know we are in this failure case when we have access to both the source IPv6 address and destination IPv6 address, we have to deal with this further up the stack. So detect this failure case in cma_bind_addr, and set bound_dev_if to the destination address scope id to correct it. Signed-off-by:
Spencer Baugh <sbaugh@catern.com> Signed-off-by:
-
Jason Gunthorpe authored
Something like this: CPU A CPU B Acked-by:
-
Hariprasad S authored
This enables ORD/IRD negotiation and its about time to enable it by default Signed-off-by:
-
Steve Wise authored
Currently the sg tablesize, which dictates fast register page list depth to use, does not take into account the limits of the rdma device. So adjust it once we discover the device fastreg max depth limit. Also adjust the max_sectors based on the resulting sg tablesize. Signed-off-by:
-
Roland Dreier authored
The only place that assigns mr inside the loop already does a break. So "if (mr)" will never be true here since the function initializes mr to NULL at the top. We can just drop the extra if and break here. Signed-off-by:
Roland Dreier <roland@purestorage.com> Acked-by:
Eli Cohen <eli@mellanox.com> Signed-off-by:
-
Mike Marciniszyn authored
The lkey table is allocated with with a get_user_pages() with an order based on a number of index bits from a module parameter. The underlying kernel code cannot allocate that many contiguous pages. There is no reason the underlying memory needs to be physically contiguous. This patch: - switches the allocation/deallocation to vmalloc/vfree - caps the number of bits to 23 to insure at least 1 generation bit o this matches the module parameter description Cc: stable@vger.kernel.org Reviewed-by:
Vinit Agnihotri <vinit.abhay.agnihotri@intel.com> Signed-off-by:
-
Sagi Grimberg authored
Should be all the page sizes that are supported by the device. Reported-by:
-
Sagi Grimberg authored
The mlx5 driver exposes device capability IB_DEVICE_LOCAL_DMA_LKEY but does not set the the device local_dma_lkey. This breaks rpcrdma drivers. Query and set this lkey when creating the device resources. Signed-off-by:
-
- 24 Aug, 2015 2 commits
-
-
Linus Torvalds authored
-
git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsiLinus Torvalds authored
Pull SCSI fixes from James Bottomley: "A couple of major (hang and deadlock) fixes with fortunately fairly rare triggering conditions. The PM oops is only really triggered by people using enclosure services (rare) and the fnic driver is mostly used in enterprise environments" * tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: SCSI: Fix NULL pointer dereference in runtime PM fnic: Use the local variable instead of I/O flag to acquire io_req_lock in fnic_queuecommand() to avoid deadloack
-
- 23 Aug, 2015 3 commits
-
-
git://git.linux-mips.org/pub/scm/ralf/upstream-linusLinus Torvalds authored
Pull MIPS bug fixes from Ralf Baechle: "Two more fixes for 4.2. One fixes a build issue with the LLVM assembler - LLVM assembler macro names are case sensitive, GNU as macro names are insensitive; the other corrects a license string (GPL v2, not GPLv2) such that the module loader will recognice the license correctly" * 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: FIRMWARE: bcm47xx_nvram: Fix module license. MIPS: Fix LLVM build issue.
-
git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfsLinus Torvalds authored
Pull 9p regression fix from Al Viro: "Fix for breakage introduced when switching p9_client_{read,write}() to struct iov_iter * (went into 4.1)" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: 9p: ensure err is initialized to 0 in p9_client_read/write -
Vincent Bernat authored
Some use of those functions were providing unitialized values to those functions. Notably, when reading 0 bytes from an empty file on a 9P filesystem, the return code of read() was not 0. Tested with this simple program: #include <assert.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include <unistd.h> int main(int argc, const char **argv) { assert(argc == 2); char buffer[256]; int fd = open(argv[1], O_RDONLY|O_NOCTTY); assert(fd >= 0); assert(read(fd, buffer, 0) == 0); return 0; } Cc: stable@vger.kernel.org # v4.1 Signed-off-by:Vincent Bernat <vincent@bernat.im> Signed-off-by:
Al Viro <viro@zeniv.linux.org.uk>
-
- 22 Aug, 2015 7 commits
-
-
git://ftp.arm.linux.org.uk/~rmk/linux-armLinus Torvalds authored
Pull ARM fixes from Russell King: "Another couple of small ARM fixes. A patch from Masahiro Yamada who noticed that "make -jN all zImage" would end up generating bad images where N > 1, and a patch from Nicolas to fix the Marvell CPU user access optimisation code when page faults are disabled" * 'fixes' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: ARM: 8418/1: add boot image dependencies to not generate invalid images ARM: 8414/1: __copy_to_user_memcpy: fix mmap semaphore usage
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 fixes from Ingo Molnar: "Various low level fixes: fix more fallout from the FPU rework and the asm entry code rework, plus an MSI rework fix, and an idle-tracing fix" * 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/fpu/math-emu: Fix crash in fork() x86/fpu/math-emu: Fix math-emu boot crash x86/idle: Restore trace_cpu_idle to mwait_idle() calls x86/irq: Build correct vector mapping for multiple MSI interrupts Revert "sched/x86_64: Don't save flags on context switch"
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull perf fixes from Ingo Molnar: "Tooling fixes: a 'perf record' deadlock fix plus debuggability fixes" * 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: perf top: Show backtrace when handling a SIGSEGV on --stdio mode perf tools: Fix buildid processing perf tools: Make fork event processing more resilient perf tools: Avoid deadlock when map_groups are broken
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull irq fixes from Thomas Gleixner: "A series of small fixlets for a regression visible on OMAP devices caused by the conversion of the OMAP interrupt chips to hierarchical interrupt domains. Mostly one liners on the driver side plus a small helper function in the core to avoid open coded mess in the drivers" * 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: irqchip/crossbar: Restore set_wake functionality irqchip/crossbar: Restore the mask on suspend behaviour ARM: OMAP: wakeupgen: Restore the irq_set_type() mechanism irqchip/crossbar: Restore the irq_set_type() mechanism genirq: Introduce irq_chip_set_type_parent() helper genirq: Don't return ENOSYS in irq_chip_retrigger_hierarchy
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull timer fixes from Thomas Gleixner: "Two minimalistic fixes for 4.2 regressions: - Eric fixed a thinko in the timer_list base switching code caused by the overhaul of the timer wheel. It can cause a cpu to see the wrong base for a timer while we move the timer around. - Guenter fixed a regression for IMX if booted w/o device tree, where the timer interrupt is not initialized and therefor the machine fails to boot" * 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: clocksource/imx: Fix boot with non-DT systems timer: Write timer->flags atomically -
Ingo Molnar authored
During later stages of math-emu bootup the following crash triggers: math_emulate: 0060:c100d0a8 Kernel panic - not syncing: Math emulation needed in kernel CPU: 0 PID: 1511 Comm: login Not tainted 4.2.0-rc7+ #1012 [...] Call Trace: [<c181d50d>] dump_stack+0x41/0x52 [<c181c918>] panic+0x77/0x189 [<c1003530>] ? math_error+0x140/0x140 [<c164c2d7>] math_emulate+0xba7/0xbd0 [<c100d0a8>] ? fpu__copy+0x138/0x1c0 [<c1109c3c>] ? __alloc_pages_nodemask+0x12c/0x870 [<c136ac20>] ? proc_clear_tty+0x40/0x70 [<c136ac6e>] ? session_clear_tty+0x1e/0x30 [<c1003530>] ? math_error+0x140/0x140 [<c1003575>] do_device_not_available+0x45/0x70 [<c100d0a8>] ? fpu__copy+0x138/0x1c0 [<c18258e6>] error_code+0x5a/0x60 [<c1003530>] ? math_error+0x140/0x140 [<c100d0a8>] ? fpu__copy+0x138/0x1c0 [<c100c205>] arch_dup_task_struct+0x25/0x30 [<c1048cea>] copy_process.part.51+0xea/0x1480 [<c115a8e5>] ? dput+0x175/0x200 [<c136af70>] ? no_tty+0x30/0x30 [<c1157242>] ? do_vfs_ioctl+0x322/0x540 [<c104a21a>] _do_fork+0xca/0x340 [<c1057b06>] ? SyS_rt_sigaction+0x66/0x90 [<c104a557>] SyS_clone+0x27/0x30 [<c1824a80>] sysenter_do_call+0x12/0x12 The reason is the incorrect assumption in fpu_copy(), that FNSAVE can be executed from math-emu kernels as well. Don't try to copy the registers, the soft state will be copied by fork anyway, so the child task inherits the parent task's soft math state. With this fix applied math-emu kernels boot up fine on modern hardware and the 'no387 nofxsr' boot options. Cc: Andy Lutomirski <luto@amacapital.net> Cc: Bobby Powers <bobbypowers@gmail.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by:Ingo Molnar <mingo@kernel.org>
-
Ingo Molnar authored
On a math-emu bootup the following crash occurs: Initializing CPU#0 ------------[ cut here ]------------ kernel BUG at arch/x86/kernel/traps.c:779! invalid opcode: 0000 [#1] SMP [...] EIP is at do_device_not_available+0xe/0x70 [...] Call Trace: [<c18238e6>] error_code+0x5a/0x60 [<c1002bd0>] ? math_error+0x140/0x140 [<c100bbd9>] ? fpu__init_cpu+0x59/0xa0 [<c1012322>] cpu_init+0x202/0x330 [<c104509f>] ? __native_set_fixmap+0x1f/0x30 [<c1b56ab0>] trap_init+0x305/0x346 [<c1b548af>] start_kernel+0x1a5/0x35d [<c1b542b4>] i386_start_kernel+0x82/0x86 The reason is that in the following commit: b1276c48 ("x86/fpu: Initialize fpregs in fpu__init_cpu_generic()") I failed to consider math-emu's limitation that it cannot execute the FNINIT instruction in kernel mode. The long term fix might be to allow math-emu to execute (certain) kernel mode FPU instructions, but for now apply the safe (albeit somewhat ugly) fix: initialize the emulation state explicitly without trapping out to the FPU emulator. Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Quentin Casasnovas <quentin.casasnovas@oracle.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by:
-
- 21 Aug, 2015 1 commit
-
-
Christoph Hellwig authored
While the idea behind get_maintainer seems highly useful it's unfortunately way to trigger happy to grab people that once had a few commits to files. For someone like me who does a lot of tree-wide API work that leads to an incredible amount of Cc spam. Signed-off-by:
Christoph Hellwig <hch@lst.de> Cc: Joe Perches <joe@perches.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
