1. 24 Jul, 2016 3 commits
    • Vishal Verma's avatar
      nfit: do an ARS scrub on hitting a latent media error · 6839a6d9
      Vishal Verma authored
      When a latent (unknown to 'badblocks') error is encountered, it will
      trigger a machine check exception. On a system with machine check
      recovery, this will only SIGBUS the process(es) which had the bad page
      mapped (as opposed to a kernel panic on platforms without machine
      check recovery features). In the former case, we want to trigger a full
      rescan of that nvdimm bus. This will allow any additional, new errors
      to be captured in the block devices' badblocks lists, and offending
      operations on them can be trapped early, avoiding machine checks.
      
      This is done by registering a callback function with the
      x86_mce_decoder_chain and calling the new ars_rescan functionality with
      the address in the mce notificatiion.
      
      Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
      Cc: Tony Luck <tony.luck@intel.com>
      Signed-off-by: default avatarVishal Verma <vishal.l.verma@intel.com>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      6839a6d9
    • Dan Williams's avatar
      nfit: move to nfit/ sub-directory · bdf97013
      Dan Williams authored
      With the arrival of x86-machine-check support the nfit driver will add a
      (conditionally-compiled) source file.  Prepare for this by moving all
      nfit source to drivers/acpi/nfit/.  This is pure code movement, no
      functional changes.
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      bdf97013
    • Vishal Verma's avatar
      nfit, libnvdimm: allow an ARS scrub to be triggered on demand · 37b137ff
      Vishal Verma authored
      Normally, an ARS (Address Range Scrub) only happens at
      boot/initialization time. There can however arise situations where a
      bus-wide rescan is needed - notably, in the case of discovering a latent
      media error, we should do a full rescan to figure out what other sectors
      are bad, and thus potentially avoid triggering an mce on them in the
      future. Also provide a sysfs trigger to start a bus-wide scrub.
      
      Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
      Signed-off-by: default avatarVishal Verma <vishal.l.verma@intel.com>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      37b137ff
  2. 23 Jul, 2016 4 commits
    • Dan Williams's avatar
      libnvdimm: register nvdimm_bus devices with an nd_bus driver · 18515942
      Dan Williams authored
      A recent effort to add a new nvdimm bus provider attribute highlighted a
      race between interrogating nvdimm_bus->nd_desc and nvdimm_bus tear down.
      The typical way to handle these races is to take the device_lock() in
      the attribute method and validate that the device is still active.  In
      order for a device to be 'active' it needs to be associated with a
      driver.  So, we create the small boilerplate for a driver and register
      nvdimm_bus devices on the 'nvdimm_bus_type' bus.
      
      A result of this change is that ndbusX devices now appear under
      /sys/bus/nd/devices.  In fact this makes /sys/class/nd somewhat
      redundant, but removing that will need to take a long deprecation period
      given its use by ndctl binaries in the field.
      
      This change naturally pulls code from drivers/nvdimm/core.c to
      drivers/nvdimm/bus.c, so it is a nice code organization clean-up as
      well.
      
      Cc: Vishal Verma <vishal.l.verma@intel.com>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      18515942
    • Vishal Verma's avatar
      pmem: clarify a debug print in pmem_clear_poison · 5bf0b6e1
      Vishal Verma authored
      Prefix the sector number being cleared with a '0x' to make it clear that
      this is a hex value.
      Signed-off-by: default avatarVishal Verma <vishal.l.verma@intel.com>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      5bf0b6e1
    • Dan Williams's avatar
      x86/insn: remove pcommit · fd1d961d
      Dan Williams authored
      The pcommit instruction is being deprecated in favor of either ADR
      (asynchronous DRAM refresh: flush-on-power-fail) at the platform level, or
      posted-write-queue flush addresses as defined by the ACPI 6.x NFIT (NVDIMM
      Firmware Interface Table).
      
      Cc: Thomas Gleixner <tglx@linutronix.de>
      Cc: "H. Peter Anvin" <hpa@zytor.com>
      Cc: x86@kernel.org
      Cc: Josh Poimboeuf <jpoimboe@redhat.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
      Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
      Cc: Borislav Petkov <bp@suse.de>
      Cc: Andy Lutomirski <luto@kernel.org>
      Cc: Xiao Guangrong <guangrong.xiao@linux.intel.com>
      Cc: Adrian Hunter <adrian.hunter@intel.com>
      Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
      Acked-by: default avatarIngo Molnar <mingo@redhat.com>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      fd1d961d
    • Dan Williams's avatar
      Revert "KVM: x86: add pcommit support" · dfa169bb
      Dan Williams authored
      This reverts commit 8b3e34e4.
      
      Given the deprecation of the pcommit instruction, the relevant VMX
      features and CPUID bits are not going to be rolled into the SDM.  Remove
      their usage from KVM.
      
      Cc: Xiao Guangrong <guangrong.xiao@linux.intel.com>
      Cc: Paolo Bonzini <pbonzini@redhat.com>
      Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      dfa169bb
  3. 22 Jul, 2016 2 commits
  4. 21 Jul, 2016 5 commits
    • Dan Williams's avatar
      nfit: cleanup acpi_nfit_init calling convention · e7a11b44
      Dan Williams authored
      Pass the nfit buffer as a parameter rather than hanging it off of
      acpi_desc.
      Reviewed-by: default avatar"Lee, Chun-Yi" <jlee@suse.com>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      e7a11b44
    • Dan Williams's avatar
      nfit: fix _FIT evaluation memory leak + use after free · 31932041
      Dan Williams authored
      acpi_evaluate_object() allocates memory. Free the buffer allocated
      during acpi_nfit_add(). In order for this memory to be freed
      acpi_nfit_init() needs to be converted to duplicate the nfit contents in
      its internal allocation.  Use zero-length arrays to minimize the thrash
      with the rest of the nfit driver implementation.
      
      All of the add_<nfit-sub-table>() routines now validate a minimum table
      size and expect hotplugged tables to match the size of the original
      table to count as a duplicate. For variable length tables, like 'idt'
      and 'flush', we calculate the dynamic size. Note that hotplug by
      definition cannot change the interleave as it would cause data
      corruption of in-use namespaces.
      
      Cc: Vishal Verma <vishal.l.verma@intel.com>
      Reported-by: default avatarXiao Guangrong <guangrong.xiao@intel.com>
      Reported-by: default avatarHaozhong Zhang <haozhong.zhang@intel.com>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      31932041
    • Dan Williams's avatar
      tools/testing/nvdimm: add manufacturing_{date|location} dimm properties · 5dc68e55
      Dan Williams authored
      New for ACPI 6.1, these fields are used in the common dimm
      representation format defined by section 5.2.25.9 "NVDIMM representation
      format".
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      5dc68e55
    • Dan Williams's avatar
      tools/testing/nvdimm: add virtual ramdisk range · 7bfe97c7
      Dan Williams authored
      Test the virtual disk ranges that platform firmware like EDK2/OVMF might
      emit.
      Tested-by: default avatar"Lee, Chun-Yi" <jlee@suse.com>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      7bfe97c7
    • Lee, Chun-Yi's avatar
      acpi, nfit: treat virtual ramdisk SPA as pmem region · c2f32acd
      Lee, Chun-Yi authored
      This patch adds logic to treat virtual ramdisk SPA as pmem region, then
      ramdisk's /dev/pmem* device can be mounted with iso9660.
      
      It's useful to work with the httpboot in EFI firmware to pull a remote
      ISO file to the local memory region for booting and installation.
      
      Wiki page of UEFI HTTPBoot with OVMF:
      	https://en.opensuse.org/UEFI_HTTPBoot_with_OVMF
      
      The ramdisk function in EDK2/OVMF generates a ACPI0012 root device that
      it contains empty _STA but without _DSM:
      
      DefinitionBlock ("ssdt2.aml", "SSDT", 2, "INTEL ", "RamDisk ", 0x00001000)
      {
          Scope (\_SB)
          {
              Device (NVDR)
              {
                  Name (_HID, "ACPI0012")  // _HID: Hardware ID
                  Name (_STR, Unicode ("NVDIMM Root Device"))  // _STR: Description String
                  Method (_STA, 0, NotSerialized)  // _STA: Status
                  {
                      Return (0x0F)
                  }
              }
          }
      }
      
      In section 5.2.25.2 of ACPI 6.1 spec, it mentions that the "SPA Range
      Structure Index" of virtual SPA shall be set to zero. That means virtual SPA
      will not be associated by any NVDIMM region mapping.
      
      The VCD's SPA Range Structure in NFIT is similar to virtual disk region
      as following:
      
      [028h 0040   2]                Subtable Type : 0000 [System Physical Address Range]
      [02Ah 0042   2]                       Length : 0038
      
      [02Ch 0044   2]                  Range Index : 0000
      [02Eh 0046   2]        Flags (decoded below) : 0000
                         Add/Online Operation Only : 0
                            Proximity Domain Valid : 0
      [030h 0048   4]                     Reserved : 00000000
      [034h 0052   4]             Proximity Domain : 00000000
      [038h 0056  16]           Address Range GUID : 77AB535A-45FC-624B-5560-F7B281D1F96E
      [048h 0072   8]           Address Range Base : 00000000B6ABD018
      [050h 0080   8]         Address Range Length : 0000000005500000
      [058h 0088   8]         Memory Map Attribute : 0000000000000000
      
      The way to not associate a SPA range is to never reference it from a "flush hint",
      "interleave", or "control region" table.
      
      After testing on OVMF, pmem driver can support the region that it doesn't
      assoicate to any NVDIMM mapping. So, treat VCD like pmem is a idea to get
      a pmem block device that it contains iso.
      
      v4:
      Instoduce nfit_spa_is_virtual() to check virtual ramdisk SPA and create
      pmem region.
      
      v3:
      To simplify patch, removed useless VCD region in libnvdimm.
      
      v2:
      Removed the code for setting VCD to a read-only region.
      
      Cc: Gary Lin <GLin@suse.com>
      Cc: Dan Williams <dan.j.williams@intel.com>
      Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
      Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
      Cc: Linda Knippers <linda.knippers@hpe.com>
      Signed-off-by: default avatarLee, Chun-Yi <jlee@suse.com>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      c2f32acd
  5. 13 Jul, 2016 1 commit
    • Dan Williams's avatar
      pmem: kill __pmem address space · 7a9eb206
      Dan Williams authored
      The __pmem address space was meant to annotate codepaths that touch
      persistent memory and need to coordinate a call to wmb_pmem().  Now that
      wmb_pmem() is gone, there is little need to keep this annotation.
      
      Cc: Christoph Hellwig <hch@lst.de>
      Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      7a9eb206
  6. 12 Jul, 2016 4 commits
  7. 11 Jul, 2016 7 commits
    • Dan Williams's avatar
      libnvdimm, pmem: use REQ_FUA, REQ_FLUSH for nvdimm_flush() · 7e267a8c
      Dan Williams authored
      Given that nvdimm_flush() has higher overhead than wmb_pmem() (pointer
      chasing through nd_region), and that we otherwise assume a platform has
      ADR capability when flush hints are not present, move nvdimm_flush() to
      REQ_FLUSH context.
      
      Note that we still arrange for nvdimm_flush() to be called even in the
      ADR case. We need at least once wmb() fence to push buffered writes in
      the cpu out to the ADR protected domain.
      
      Cc: Toshi Kani <toshi.kani@hpe.com>
      Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      7e267a8c
    • Dan Williams's avatar
      libnvdimm: cycle flush hints · 0c27af60
      Dan Williams authored
      When the NFIT provides multiple flush hint addresses per-dimm it is
      expressing that the platform is capable of processing multiple flush
      requests in parallel.  There is some fixed cost per flush request, let
      the cost be shared in parallel on multiple cpus.
      
      Since there may not be enough flush hint addresses for each cpu to have
      one, keep a per-cpu index of the last used hint, hash it with current
      pid, and assume that access pattern and scheduler randomness will keep
      the flush-hint usage somewhat staggered across cpus.
      
      Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      0c27af60
    • Dan Williams's avatar
      libnvdimm: introduce nvdimm_flush() and nvdimm_has_flush() · f284a4f2
      Dan Williams authored
      nvdimm_flush() is a replacement for the x86 'pcommit' instruction.  It is
      an optional write flushing mechanism that an nvdimm bus can provide for
      the pmem driver to consume.  In the case of the NFIT nvdimm-bus-provider
      nvdimm_flush() is implemented as a series of flush-hint-address [1]
      writes to each dimm in the interleave set (region) that backs the
      namespace.
      
      The nvdimm_has_flush() routine relies on platform firmware to describe
      the flushing capabilities of a platform.  It uses the heuristic of
      whether an nvdimm bus provider provides flush address data to return a
      ternary result:
      
            1: flush addresses defined
            0: dimm topology described without flush addresses (assume ADR)
       -errno: no topology information, unable to determine flush mechanism
      
      The pmem driver is expected to take the following actions on this ternary
      result:
      
            1: nvdimm_flush() in response to REQ_FUA / REQ_FLUSH and shutdown
            0: do not set, WC or FUA on the queue, take no further action
       -errno: warn and then operate as if nvdimm_has_flush() returned '0'
      
      The caveat of this heuristic is that it can not distinguish the "dimm
      does not have flush address" case from the "platform firmware is broken
      and failed to describe a flush address".  Given we are already
      explicitly trusting the NFIT there's not much more we can do beyond
      blacklisting broken firmwares if they are ever encountered.
      
      Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      f284a4f2
    • Dan Williams's avatar
      libnvdimm: keep region data alive over namespace removal · a8f72022
      Dan Williams authored
      nd_region device driver data will be used in the namespace i/o path.
      Re-order nd_region_remove() to ensure this data stays live across
      namespace device removal
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      a8f72022
    • Dan Williams's avatar
      tools/testing/nvdimm: simulate multiple flush hints per-dimm · 85d3fa02
      Dan Williams authored
      Sample nfit data to test the kernel's handling of the multiple
      flush-hint case.
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      85d3fa02
    • Dan Williams's avatar
      libnvdimm, nfit: move flush hint mapping to region-device driver-data · e5ae3b25
      Dan Williams authored
      In preparation for triggering flushes of a DIMM's writes-posted-queue
      (WPQ) via the pmem driver move mapping of flush hint addresses to the
      region driver.  Since this uses devm_nvdimm_memremap() the flush
      addresses will remain mapped while any region to which the dimm belongs
      is active.
      
      We need to communicate more information to the nvdimm core to facilitate
      this mapping, namely each dimm object now carries an array of flush hint
      address resources.
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      e5ae3b25
    • Dan Williams's avatar
      libnvdimm, nfit: remove nfit_spa_map() infrastructure · a8a6d2e0
      Dan Williams authored
      Now that all shared mappings are handled by devm_nvdimm_memremap() we no
      longer need nfit_spa_map() nor do we need to trigger a callback to the
      bus provider at region disable time.
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      a8a6d2e0
  8. 08 Jul, 2016 4 commits
  9. 06 Jul, 2016 3 commits
  10. 27 Jun, 2016 1 commit
  11. 24 Jun, 2016 1 commit
    • Dan Williams's avatar
      libnvdimm, pmem: allow nfit_test to override pmem_direct_access() · f295e53b
      Dan Williams authored
      Currently phys_to_pfn_t() is an exported symbol to allow nfit_test to
      override it and indicate that nfit_test-pmem is not device-mapped.  Now,
      we want to enable nfit_test to operate without DMA_CMA and the pmem it
      provides will no longer be physically contiguous, i.e. won't be capable
      of supporting direct_access requests larger than a page.  Make
      pmem_direct_access() a weak symbol so that it can be replaced by the
      tools/testing/nvdimm/ version, and move phys_to_pfn_t() to a static
      inline now that it no longer needs to be overridden.
      Acked-by: default avatarJohannes Thumshirn <jthumshirn@suse.de>
      Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
      f295e53b
  12. 20 Jun, 2016 1 commit
  13. 17 Jun, 2016 3 commits
  14. 15 Jun, 2016 1 commit