1. 24 Jan, 2013 1 commit
  2. 20 Dec, 2012 1 commit
  3. 28 Jun, 2012 1 commit
    • Alex Shi's avatar
      x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range · e7b52ffd
      Alex Shi authored
      x86 has no flush_tlb_range support in instruction level. Currently the
      flush_tlb_range just implemented by flushing all page table. That is not
      the best solution for all scenarios. In fact, if we just use 'invlpg' to
      flush few lines from TLB, we can get the performance gain from later
      remain TLB lines accessing.
      
      But the 'invlpg' instruction costs much of time. Its execution time can
      compete with cr3 rewriting, and even a bit more on SNB CPU.
      
      So, on a 512 4KB TLB entries CPU, the balance points is at:
      	(512 - X) * 100ns(assumed TLB refill cost) =
      		X(TLB flush entries) * 100ns(assumed invlpg cost)
      
      Here, X is 256, that is 1/2 of 512 entries.
      
      But with the mysterious CPU pre-fetcher and page miss handler Unit, the
      assumed TLB refill cost is far lower then 100ns in sequential access. And
      2 HT siblings in one core makes the memory access more faster if they are
      accessing the same memory. So, in the patch, I just do the change when
      the target entries is less than 1/16 of whole active tlb entries.
      Actually, I have no data support for the percentage '1/16', so any
      suggestions are welcomed.
      
      As to hugetlb, guess due to smaller page table, and smaller active TLB
      entries, I didn't see benefit via my benchmark, so no optimizing now.
      
      My micro benchmark show in ideal scenarios, the performance improves 70
      percent in reading. And in worst scenario, the reading/writing
      performance is similar with unpatched 3.4-rc4 kernel.
      
      Here is the reading data on my 2P * 4cores *HT NHM EP machine, with THP
      'always':
      
      multi thread testing, '-t' paramter is thread number:
      	       	        with patch   unpatched 3.4-rc4
      ./mprotect -t 1           14ns		24ns
      ./mprotect -t 2           13ns		22ns
      ./mprotect -t 4           12ns		19ns
      ./mprotect -t 8           14ns		16ns
      ./mprotect -t 16          28ns		26ns
      ./mprotect -t 32          54ns		51ns
      ./mprotect -t 128         200ns		199ns
      
      Single process with sequencial flushing and memory accessing:
      
      		       	with patch   unpatched 3.4-rc4
      ./mprotect		    7ns			11ns
      ./mprotect -p 4096  -l 8 -n 10240
      			    21ns		21ns
      
      [ hpa: http://lkml.kernel.org/r/1B4B44D9196EFF41AE41FDA404FC0A100BFF94@SHSMSX101.ccr.corp.intel.com
      
      
        has additional performance numbers. ]
      
      Signed-off-by: default avatarAlex Shi <alex.shi@intel.com>
      Link: http://lkml.kernel.org/r/1340845344-27557-3-git-send-email-alex.shi@intel.com
      
      
      Signed-off-by: default avatarH. Peter Anvin <hpa@zytor.com>
      e7b52ffd
  4. 25 Jun, 2012 3 commits
    • Cliff Wickman's avatar
      x86/uv: Work around UV2 BAU hangs · 8b6e511e
      Cliff Wickman authored
      
      
      On SGI's UV2 the BAU (Broadcast Assist Unit) driver can hang
      under a heavy load. To cure this:
      
      - Disable the UV2 extended status mode (see UV2_EXT_SHFT), as
        this mode changes BAU behavior in more ways then just delivering
        an extra bit of status.  Revert status to just two meaningful bits,
        like UV1.
      
      - Use no IPI-style resets on UV2.  Just give up the request for
        whatever the reason it failed and let it be accomplished with
        the legacy IPI method.
      
      - Use no alternate sending descriptor (the former UV2 workaround
        bcp->using_desc and handle_uv2_busy() stuff).  Just disable the
        use of the BAU for a period of time in favor of the legacy IPI
        method when the h/w bug leaves a descriptor busy.
      
        -- new tunable: giveup_limit determines the threshold at which a hub is
           so plugged that it should do all requests with the legacy IPI method for a
           period of time
        -- generalize disable_for_congestion() (renamed disable_for_period()) for
           use whenever a hub should avoid using the BAU for a period of time
      
      Also:
      
       - Fix find_another_by_swack(), which is part of the UV2 bug workaround
      
       - Correct and clarify the statistics (new stats s_overipilimit, s_giveuplimit,
         s_enters, s_ipifordisabled, s_plugged, s_congested)
      
      Signed-off-by: default avatarCliff Wickman <cpw@sgi.com>
      Link: http://lkml.kernel.org/r/20120622131459.GC31884@sgi.com
      
      
      Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
      8b6e511e
    • Cliff Wickman's avatar
      x86/uv: Implement UV BAU runtime enable and disable control via /proc/sgi_uv/ · 26ef8577
      Cliff Wickman authored
      
      
      This patch enables the BAU to be turned on or off dynamically.
      
        echo "on"  > /proc/sgi_uv/ptc_statistics
        echo "off" > /proc/sgi_uv/ptc_statistics
      
      The system may be booted with or without the nobau option.
      
      Whether the system currently has the BAU off can be seen in
      the /proc file -- normally with the baustats script.
      Each cpu will have a 1 in the bauoff field if the BAU was turned
      off, so baustats will give a count of cpus that have it off.
      
      Signed-off-by: default avatarCliff Wickman <cpw@sgi.com>
      Link: http://lkml.kernel.org/r/20120622131330.GB31884@sgi.com
      
      
      Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
      26ef8577
    • Cliff Wickman's avatar
      x86/uv: Fix the UV BAU destination timeout period · 11cab711
      Cliff Wickman authored
      
      
      Correct the calculation of a destination timeout period, which
      is used to distinguish between a destination timeout and the
      situation where all the target software ack resources are full
      and a request is returned immediately.
      
      The problem is that integer arithmetic was overflowing, yielding
      a very large result.
      
      Without this fix destination timeouts are identified as resource
      'plugged' events and an ipi method of resource releasing is
      unnecessarily employed.
      
      Signed-off-by: default avatarCliff Wickman <cpw@sgi.com>
      Link: http://lkml.kernel.org/r/20120622131212.GA31884@sgi.com
      
      
      Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
      11cab711
  5. 08 Jun, 2012 1 commit
  6. 26 Jan, 2012 1 commit
  7. 17 Jan, 2012 6 commits
  8. 21 Sep, 2011 1 commit
    • Jack Steiner's avatar
      x86: uv2: Workaround for UV2 Hub bug (system global address format) · 6a469e46
      Jack Steiner authored
      
      
      This is a workaround for a UV2 hub bug that affects the format of system
      global addresses.
      
      The GRU API for UV2 was inadvertently broken by a hardware change.  The
      format of the physical address used for TLB dropins and for addresses used
      with instructions running in unmapped mode has changed.  This change was
      not documented and became apparent only when diags failed running on
      system simulators.
      
      For UV1, TLB and GRU instruction physical addresses are identical to
      socket physical addresses (although high NASID bits must be OR'ed into the
      address).
      
      For UV2, socket physical addresses need to be converted.  The NODE portion
      of the physical address needs to be shifted so that the low bit is in bit
      39 or bit 40, depending on an MMR value.
      
      It is not yet clear if this bug will be fixed in a silicon respin.  If it
      is fixed, the hub revision will be incremented & the workaround disabled.
      
      Signed-off-by: default avatarJack Steiner <steiner@sgi.com>
      Cc: Ingo Molnar <mingo@elte.hu>
      Cc: "H. Peter Anvin" <hpa@zytor.com>
      Cc: <stable@kernel.org>
      Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
      6a469e46
  9. 21 Jun, 2011 6 commits
  10. 25 May, 2011 2 commits
    • Cliff Wickman's avatar
      x86, UV: Clean up uv_tlb.c · f073cc8f
      Cliff Wickman authored
      
      
      SGI UV's uv_tlb.c driver has become rather hard to read, with overly large
      functions, non-standard coding style and (way) too long variable, constant
      and function names and non-obvious code flow sequences.
      
      This patch improves the readability and maintainability of the driver
      significantly, by doing the following strict code cleanups with no side
      effects:
      
       - Split long functions into shorter logical functions.
      
       - Shortened some variable and structure member names.
      
       - Added special functions for reads and writes of MMR regs with
         very long names.
      
       - Added the 'tunables' table to shortened tunables_write().
      
       - Added the 'stat_description' table to shorten uv_ptc_proc_write().
      
       - Pass fewer 'stat' arguments where it can be derived from the 'bcp'
         argument.
      
       - Function definitions consistent on one line, and inline in few (short) cases.
      
       - Moved some small structures and an atomic inline function to the header file.
      
       - Moved some local variables to the blocks where they are used.
      
       - Updated the copyright date.
      
       - Shortened uv_write_global_mmr64() etc. using some aliasing; no
         line breaks. Renamed many uv_.. functions that are not exported.
      
       - Aligned structure fields.
          [ note that not all structures are aligned the same way though; I'd like
            to keep the extensive commenting in some of them. ]
      
       - Shortened some long structure names.
      
       - Standard pass/fail exit from init_per_cpu()
      
       - Vertical alignment for mass initializations.
      
       - More separation between blocks of code.
      
      Tested on a 16-processor Altix UV.
      
      Signed-off-by: default avatarCliff Wickman <cpw@sgi.com>
      Cc: penberg@kernel.org
      Link: http://lkml.kernel.org/r/E1QOw12-0004MN-Lp@eag09.americas.sgi.com
      
      
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      f073cc8f
    • Jack Steiner's avatar
      x86, UV: Add support for SGI UV2 hub chip · 2a919596
      Jack Steiner authored
      
      
      This patch adds support for a new version of the SGI UV hub
      chip. The hub chip is the node controller that connects multiple
      blades into a larger coherent SSI.
      
      For the most part, UV2 is compatible with UV1. The majority of
      the changes are in the addresses of MMRs and in a few cases, the
      contents of MMRs. These changes are the result in changes in the
      system topology such as node configuration, processor types,
      maximum nodes, physical address sizes, etc.
      
      Signed-off-by: default avatarJack Steiner <steiner@sgi.com>
      Link: http://lkml.kernel.org/r/20110511175028.GA18006@sgi.com
      
      
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      2a919596
  11. 12 May, 2011 1 commit
    • Cliff Wickman's avatar
      x86: Fix UV BAU for non-consecutive nasids · 77ed23f8
      Cliff Wickman authored
      
      
      This is a fix for the SGI Altix-UV Broadcast Assist Unit code,
      which is used for TLB flushing.
      
      Certain hardware configurations (that customers are ordering)
      cause nasids (numa address space id's) to be non-consecutive.
      Specifically, once you have more than 4 blades in a IRU
      (Individual Rack Unit - or 1/2 rack) but less than the maximum
      of 16, the nasid numbering becomes non-consecutive.  This
      currently results in a 'catastrophic error' (CATERR) detected by
      the firmware during OS boot.  The BAU is generating an 'INTD'
      request that is targeting a non-existent nasid value. Such
      configurations may also occur when a blade is configured off
      because of hardware errors. (There is one UV hub per blade.)
      
      This patch is required to support such configurations.
      
      The problem with the tlb_uv.c code is that is using the
      consecutive hub numbers as indices to the BAU distribution bit
      map. These are simply the ordinal position of the hub or blade
      within its partition.  It should be using physical node numbers
      (pnodes), which correspond to the physical nasid values. Use of
      the hub number only works as long as the nasids in the partition
      are consecutive and increase with a stride of 1.
      
      This patch changes the index to be the pnode number, thus
      allowing nasids to be non-consecutive.
      It also provides a table in local memory for each cpu to
      translate target cpu number to target pnode and nasid.
      And it improves naming to properly reflect 'node' and 'uvhub'
      versus 'nasid'.
      
      Signed-off-by: default avatarCliff Wickman <cpw@sgi.com>
      Cc: <stable@kernel.org>
      Link: http://lkml.kernel.org/r/E1QJmxX-0002Mz-Fk@eag09.americas.sgi.com
      
      
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      77ed23f8
  12. 29 Mar, 2011 1 commit
    • Jean Delvare's avatar
      x86: Stop including <linux/delay.h> in two asm header files · ca444564
      Jean Delvare authored
      
      
      Stop including <linux/delay.h> in x86 header files which don't
      need it. This will let the compiler complain when this header is
      not included by source files when it should, so that
      contributors can fix the problem before building on other
      architectures starts to fail.
      
      Credits go to Geert for the idea.
      
      Signed-off-by: default avatarJean Delvare <khali@linux-fr.org>
      Cc: James E.J. Bottomley <James.Bottomley@suse.de>
      Cc: Geert Uytterhoeven <geert@linux-m68k.org>
      Cc: Stephen Rothwell <sfr@canb.auug.org.au>
      LKML-Reference: <20110325152014.297890ec@endymion.delvare>
      [ this also fixes an upstream build bug in drivers/media/rc/ite-cir.c ]
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      ca444564
  13. 09 Mar, 2011 1 commit
  14. 03 Jan, 2011 1 commit
    • Cliff Wickman's avatar
      x86, UV, BAU: Extend for more than 16 cpus per socket · cfa60917
      Cliff Wickman authored
      
      
      Fix a hard-coded limit of a maximum of 16 cpu's per socket.
      
      The UV Broadcast Assist Unit code initializes by scanning the
      cpu topology of the system and assigning a master cpu for each
      socket and UV hub. That scan had an assumption of a limit of 16
      cpus per socket. With Westmere we are going over that limit.
      The UV hub hardware will allow up to 32.
      
      If the scan finds the system has gone over that limit it returns
      an error and we print a warning and fall back to doing TLB
      shootdowns without the BAU.
      
      Signed-off-by: default avatarCliff Wickman <cpw@sgi.com>
      Cc: <stable@kernel.org> # .37.x
      LKML-Reference: <E1PZol7-0000mM-77@eag09.americas.sgi.com>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      cfa60917
  15. 18 Nov, 2010 1 commit
    • Dimitri Sivanich's avatar
      x86: UV: Address interrupt/IO port operation conflict · 8191c9f6
      Dimitri Sivanich authored
      
      
      This patch for SGI UV systems addresses a problem whereby
      interrupt transactions being looped back from a local IOH,
      through the hub to a local CPU can (erroneously) conflict with
      IO port operations and other transactions.
      
      To workaound this we set a high bit in the APIC IDs used for
      interrupts. This bit appears to be ignored by the sockets, but
      it avoids the conflict in the hub.
      
      Signed-off-by: default avatarDimitri Sivanich <sivanich@sgi.com>
      LKML-Reference: <20101116222352.GA8155@sgi.com>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      ___
      
       arch/x86/include/asm/uv/uv_hub.h   |    4 ++++
       arch/x86/include/asm/uv/uv_mmrs.h  |   19 ++++++++++++++++++-
       arch/x86/kernel/apic/x2apic_uv_x.c |   25 +++++++++++++++++++++++--
       arch/x86/platform/uv/tlb_uv.c      |    2 +-
       arch/x86/platform/uv/uv_time.c     |    4 +++-
       5 files changed, 49 insertions(+), 5 deletions(-)
      8191c9f6
  16. 10 Nov, 2010 1 commit
  17. 27 Oct, 2010 1 commit
  18. 15 Oct, 2010 1 commit
    • Arnd Bergmann's avatar
      llseek: automatically add .llseek fop · 6038f373
      Arnd Bergmann authored
      
      
      All file_operations should get a .llseek operation so we can make
      nonseekable_open the default for future file operations without a
      .llseek pointer.
      
      The three cases that we can automatically detect are no_llseek, seq_lseek
      and default_llseek. For cases where we can we can automatically prove that
      the file offset is always ignored, we use noop_llseek, which maintains
      the current behavior of not returning an error from a seek.
      
      New drivers should normally not use noop_llseek but instead use no_llseek
      and call nonseekable_open at open time.  Existing drivers can be converted
      to do the same when the maintainer knows for certain that no user code
      relies on calling seek on the device file.
      
      The generated code is often incorrectly indented and right now contains
      comments that clarify for each added line why a specific variant was
      chosen. In the version that gets submitted upstream, the comments will
      be gone and I will manually fix the indentation, because there does not
      seem to be a way to do that using coccinelle.
      
      Some amount of new code is currently sitting in linux-next that should get
      the same modifications, which I will do at the end of the merge window.
      
      Many thanks to Julia Lawall for helping me learn to write a semantic
      patch that does all this.
      
      ===== begin semantic patch =====
      // This adds an llseek= method to all file operations,
      // as a preparation for making no_llseek the default.
      //
      // The rules are
      // - use no_llseek explicitly if we do nonseekable_open
      // - use seq_lseek for sequential files
      // - use default_llseek if we know we access f_pos
      // - use noop_llseek if we know we don't access f_pos,
      //   but we still want to allow users to call lseek
      //
      @ open1 exists @
      identifier nested_open;
      @@
      nested_open(...)
      {
      <+...
      nonseekable_open(...)
      ...+>
      }
      
      @ open exists@
      identifier open_f;
      identifier i, f;
      identifier open1.nested_open;
      @@
      int open_f(struct inode *i, struct file *f)
      {
      <+...
      (
      nonseekable_open(...)
      |
      nested_open(...)
      )
      ...+>
      }
      
      @ read disable optional_qualifier exists @
      identifier read_f;
      identifier f, p, s, off;
      type ssize_t, size_t, loff_t;
      expression E;
      identifier func;
      @@
      ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
      {
      <+...
      (
         *off = E
      |
         *off += E
      |
         func(..., off, ...)
      |
         E = *off
      )
      ...+>
      }
      
      @ read_no_fpos disable optional_qualifier exists @
      identifier read_f;
      identifier f, p, s, off;
      type ssize_t, size_t, loff_t;
      @@
      ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
      {
      ... when != off
      }
      
      @ write @
      identifier write_f;
      identifier f, p, s, off;
      type ssize_t, size_t, loff_t;
      expression E;
      identifier func;
      @@
      ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
      {
      <+...
      (
        *off = E
      |
        *off += E
      |
        func(..., off, ...)
      |
        E = *off
      )
      ...+>
      }
      
      @ write_no_fpos @
      identifier write_f;
      identifier f, p, s, off;
      type ssize_t, size_t, loff_t;
      @@
      ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
      {
      ... when != off
      }
      
      @ fops0 @
      identifier fops;
      @@
      struct file_operations fops = {
       ...
      };
      
      @ has_llseek depends on fops0 @
      identifier fops0.fops;
      identifier llseek_f;
      @@
      struct file_operations fops = {
      ...
       .llseek = llseek_f,
      ...
      };
      
      @ has_read depends on fops0 @
      identifier fops0.fops;
      identifier read_f;
      @@
      struct file_operations fops = {
      ...
       .read = read_f,
      ...
      };
      
      @ has_write depends on fops0 @
      identifier fops0.fops;
      identifier write_f;
      @@
      struct file_operations fops = {
      ...
       .write = write_f,
      ...
      };
      
      @ has_open depends on fops0 @
      identifier fops0.fops;
      identifier open_f;
      @@
      struct file_operations fops = {
      ...
       .open = open_f,
      ...
      };
      
      // use no_llseek if we call nonseekable_open
      ////////////////////////////////////////////
      @ nonseekable1 depends on !has_llseek && has_open @
      identifier fops0.fops;
      identifier nso ~= "nonseekable_open";
      @@
      struct file_operations fops = {
      ...  .open = nso, ...
      +.llseek = no_llseek, /* nonseekable */
      };
      
      @ nonseekable2 depends on !has_llseek @
      identifier fops0.fops;
      identifier open.open_f;
      @@
      struct file_operations fops = {
      ...  .open = open_f, ...
      +.llseek = no_llseek, /* open uses nonseekable */
      };
      
      // use seq_lseek for sequential files
      /////////////////////////////////////
      @ seq depends on !has_llseek @
      identifier fops0.fops;
      identifier sr ~= "seq_read";
      @@
      struct file_operations fops = {
      ...  .read = sr, ...
      +.llseek = seq_lseek, /* we have seq_read */
      };
      
      // use default_llseek if there is a readdir
      ///////////////////////////////////////////
      @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
      identifier fops0.fops;
      identifier readdir_e;
      @@
      // any other fop is used that changes pos
      struct file_operations fops = {
      ... .readdir = readdir_e, ...
      +.llseek = default_llseek, /* readdir is present */
      };
      
      // use default_llseek if at least one of read/write touches f_pos
      /////////////////////////////////////////////////////////////////
      @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
      identifier fops0.fops;
      identifier read.read_f;
      @@
      // read fops use offset
      struct file_operations fops = {
      ... .read = read_f, ...
      +.llseek = default_llseek, /* read accesses f_pos */
      };
      
      @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
      identifier fops0.fops;
      identifier write.write_f;
      @@
      // write fops use offset
      struct file_operations fops = {
      ... .write = write_f, ...
      +	.llseek = default_llseek, /* write accesses f_pos */
      };
      
      // Use noop_llseek if neither read nor write accesses f_pos
      ///////////////////////////////////////////////////////////
      
      @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
      identifier fops0.fops;
      identifier read_no_fpos.read_f;
      identifier write_no_fpos.write_f;
      @@
      // write fops use offset
      struct file_operations fops = {
      ...
       .write = write_f,
       .read = read_f,
      ...
      +.llseek = noop_llseek, /* read and write both use no f_pos */
      };
      
      @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
      identifier fops0.fops;
      identifier write_no_fpos.write_f;
      @@
      struct file_operations fops = {
      ... .write = write_f, ...
      +.llseek = noop_llseek, /* write uses no f_pos */
      };
      
      @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
      identifier fops0.fops;
      identifier read_no_fpos.read_f;
      @@
      struct file_operations fops = {
      ... .read = read_f, ...
      +.llseek = noop_llseek, /* read uses no f_pos */
      };
      
      @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
      identifier fops0.fops;
      @@
      struct file_operations fops = {
      ...
      +.llseek = noop_llseek, /* no read or write fn */
      };
      ===== End semantic patch =====
      
      Signed-off-by: default avatarArnd Bergmann <arnd@arndb.de>
      Cc: Julia Lawall <julia@diku.dk>
      Cc: Christoph Hellwig <hch@infradead.org>
      6038f373
  19. 30 Sep, 2010 1 commit
  20. 01 Aug, 2010 1 commit
    • Cliff Wickman's avatar
      x86, UV: Initialize BAU hub map · c4026cfd
      Cliff Wickman authored
      
      
      Fix uninitialized uvhub_mask:
      
      - An unitialized bit map variable was causing initialization of
        non-existant hubs (this one causes boot panics).
      
      - And the bit map was too small for large machines.  This patch
        makes it dynamic in size.
      
      - Fix the case where socket 0 has no enabled cpu's. Don't assume
        every hub has a socket 0.
      
      - uv_init_per_cpu() should be __init.
      
      Signed-off-by: default avatarCliff Wickman <cpw@sgi.com>
      Cc: <stable@kernel.org> # for .35.x
      LKML-Reference: <E1Oeuyt-0004XS-0y@eag09.americas.sgi.com>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      c4026cfd
  21. 17 Jul, 2010 1 commit
    • Cliff Wickman's avatar
      x86, UV: Initialize BAU MMRs only on hubs with cpus · 93a7ca0c
      Cliff Wickman authored
      
      
      Remove the initialization of MMRs
      UVH_LB_BAU_SB_ACTIVATION_CONTROL and UVH_BAU_DATA_BROADCAST on
      UV hubs that have no active cpus. Such initialization on hubs
      with no active cpus would result in a kernel page fault.
      
      This is not of real high priority, because we don't have any
      such systems (with UV hubs that have no active cpus).  But they
      will be coming.
      
      Signed-off-by: default avatarCliff Wickman <cpw@sgi.com>
      LKML-Reference: <E1OZmZN-0006cW-RC@eag09.americas.sgi.com>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      93a7ca0c
  22. 08 Jun, 2010 6 commits
    • Cliff Wickman's avatar
      x86, UV: Modularize BAU send and wait · f6d8a566
      Cliff Wickman authored
      
      
      Streamline the large uv_flush_send_and_wait() function by use of
      a couple of helper functions.
      
      And remove some excess comments.
      
      Signed-off-by: default avatarCliff Wickman <cpw@sgi.com>
      Cc: gregkh@suse.de
      LKML-Reference: <E1OJvNy-0004ay-IH@eag09.americas.sgi.com>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      f6d8a566
    • Cliff Wickman's avatar
      x86, UV: BAU broadcast to the local hub · 450a007e
      Cliff Wickman authored
      
      
      Make the Broadcast Assist Unit driver use the BAU for TLB
      shootdowns of cpu's on the local uvhub.
      
      It was previously thought that IPI might be faster to the cpu's
      on the local hub.  But the IPI operation would have to follow
      the completion of the BAU broadcast anyway.  So we broadcast to
      the local uvhub in all cases except when the current cpu was the
      only local cpu in the mask.
      
      This simplifies uv_flush_send_and_wait() in that it returns
      either all shootdowns complete, or none.
      
      Adjust the statistics to account for shootdowns on the local
      uvhub.
      
      Signed-off-by: default avatarCliff Wickman <cpw@sgi.com>
      Cc: gregkh@suse.de
      LKML-Reference: <E1OJvNy-0004aq-G7@eag09.americas.sgi.com>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      450a007e
    • Cliff Wickman's avatar
      x86, UV: Correct BAU regular message type · 7fba1bcd
      Cliff Wickman authored
      
      
      The Broadcast Assist Unit messages have a regular or retry
      message type. The regular type was not being set, but needs to
      be, because the lack of a message type is sometimes used to
      identify an unused entry in the message queue.
      Also removing some excess comments.
      
      Signed-off-by: default avatarCliff Wickman <cpw@sgi.com>
      Cc: gregkh@suse.de
      LKML-Reference: <E1OJvNy-0004ak-Dy@eag09.americas.sgi.com>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      7fba1bcd
    • Cliff Wickman's avatar
      x86, UV: Remove BAU check for stay-busy · 90cc7d94
      Cliff Wickman authored
      
      
      Remove a faulty assumption that a long running BAU request has
      encountered a hardware problem and will never finish.
      
      Numalink congestion can make a request appear to have
      encountered such a problem, but it is not safe to cancel the
      request.  If such a cancel is done but a reply is later received
      we can miss a TLB shootdown.
      
      We depend upon the max_bau_concurrent 'throttle' to prevent the
      stay-busy case from happening.
      
      Signed-off-by: default avatarCliff Wickman <cpw@sgi.com>
      Cc: gregkh@suse.de
      LKML-Reference: <E1OJvNy-0004ad-BV@eag09.americas.sgi.com>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      90cc7d94
    • Cliff Wickman's avatar
      x86, UV: Correct BAU discovery of hubs and sockets · a8328ee5
      Cliff Wickman authored
      
      
      Correct the initialization-time assumption of contigous blade
      numbers and of sockets numbered from zero.
      
      There may be hubs present with no cpu's enabled.
      There may be disabled sockets such that the active socket is not
      number zero.
      
      And assign a 'socket master' by assuming that a socket is a
      node. (it is not safe to extract socket number from an apicid)
      
      Signed-off-by: default avatarCliff Wickman <cpw@sgi.com>
      Cc: gregkh@suse.de
      LKML-Reference: <E1OJvNy-0004aW-9S@eag09.americas.sgi.com>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      a8328ee5
    • Cliff Wickman's avatar
      x86, UV: Correct BAU software acknowledge · 39847e7f
      Cliff Wickman authored
      
      
      Correct the acknowledgment and the reset of a BAU
      software-acknowledged message.
      
      A retry message should be testing only for timed-out resources
      (mask << 8). (And we delete a log message that might cause
      unnecessary concern) The acknowledge MMR is
      |--timed-out--|---pending--|,  each is 8 bits.
      
      The IPI-driven reset of software acknowledge resources frees
      both timed out and pending resources.
      
      Signed-off-by: default avatarCliff Wickman <cpw@sgi.com>
      Cc: gregkh@suse.de
      LKML-Reference: <E1OJvNy-0004aP-7O@eag09.americas.sgi.com>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      39847e7f