1. 20 Nov, 2008 2 commits
    • Alexander van Heukelum's avatar
      x86: move entry_64.S register saving out of the macros · d99015b1
      Alexander van Heukelum authored
      Here is a combined patch that moves "save_args" out-of-line for
      the interrupt macro and moves "error_entry" mostly out-of-line
      for the zeroentry and errorentry macros.
      
      The save_args function becomes really straightforward and easy
      to understand, with the possible exception of the stack switch
      code, which now needs to copy the return address of to the
      calling function. Normal interrupts arrive with ((~vector)-0x80)
      on the stack, which gets adjusted in common_interrupt:
      
      <common_interrupt>:
      (5)  addq   $0xffffffffffffff80,(%rsp)		/* -> ~(vector) */
      (4)  sub    $0x50,%rsp				/* space for registers */
      (5)  callq  ffffffff80211290 <save_args>
      (5)  callq  ffffffff80214290 <do_IRQ>
      <ret_from_intr>:
           ...
      
      An apic interrupt stub now look like this:
      
      <thermal_interrupt>:
      (5)  pushq  $0xffffffffffffff05			/* ~(vector) */
      (4)  sub    $0x50,%rsp				/* space for registers */
      (5)  callq  ffffffff80211290 <save_args>
      (5)  callq  ffffffff80212b8f <smp_thermal_interrupt>
      (5)  jmpq   ffffffff80211f93 <ret_from_intr>
      
      Similarly the exception handler register saving function becomes
      simpler, without the need of any parameter shuffling. The stub
      for an exception without errorcode looks like this:
      
      <overflow>:
      (6)  callq  *0x1cad12(%rip)        # ffffffff803dd448 <pv_irq_ops+0x38>
      (2)  pushq  $0xffffffffffffffff			/* no syscall */
      (4)  sub    $0x78,%rsp				/* space for registers */
      (5)  callq  ffffffff8030e3b0 <error_entry>
      (3)  mov    %rsp,%rdi				/* pt_regs pointer */
      (2)  xor    %esi,%esi				/* no error code */
      (5)  callq  ffffffff80213446 <do_overflow>
      (5)  jmpq   ffffffff8030e460 <error_exit>
      
      And one for an exception with errorcode like this:
      
      <segment_not_present>:
      (6)  callq  *0x1cab92(%rip)        # ffffffff803dd448 <pv_irq_ops+0x38>
      (4)  sub    $0x78,%rsp				/* space for registers */
      (5)  callq  ffffffff8030e3b0 <error_entry>
      (3)  mov    %rsp,%rdi				/* pt_regs pointer */
      (5)  mov    0x78(%rsp),%rsi			/* load error code */
      (9)  movq   $0xffffffffffffffff,0x78(%rsp)	/* no syscall */
      (5)  callq  ffffffff80213209 <do_segment_not_present>
      (5)  jmpq   ffffffff8030e460 <error_exit>
      
      Unfortunately, this last type is more than 32 bytes. But the total space
      savings due to this patch is about 2500 bytes on an smp-configuration,
      and I think the code is clearer than it was before. The tested kernels
      were non-paravirt ones (i.e., without the indirect call at the top of
      the exception handlers).
      
      Anyhow, I tested this patch on top of a recent -tip. The machine
      was an 2x4-core Xeon at 2333MHz. Measured where the delays between
      (almost-)adjacent rdtsc instructions. The graphs show how much
      time is spent outside of the program as a function of the measured
      delay. The area under the graph represents the total time spent
      outside the program. Eight instances of the rdtsctest were
      started, each pinned to a single cpu. The histogams are added.
      For each kernel two measurements were done: one in mostly idle
      condition, the other while running "bonnie++ -f", bound to cpu 0.
      Each measurement took 40 minutes runtime. See the attached graphs
      for the results. The graphs overlap almost everywhere, but there
      are small differences.
      Signed-off-by: default avatarAlexander van Heukelum <heukelum@fastmail.fm>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      d99015b1
    • Ingo Molnar's avatar
      Merge branch 'x86/cleanups' into x86/irq · c032a2de
      Ingo Molnar authored
      [ merged x86/cleanups into x86/irq to enable a wider IRQ entry code
        patch to be applied, which depends on a cleanup patch in x86/cleanups. ]
      c032a2de
  2. 18 Nov, 2008 2 commits
    • Ingo Molnar's avatar
      Merge branch 'x86/urgent' into x86/cleanups · cbe9ee00
      Ingo Molnar authored
      cbe9ee00
    • Ingo Molnar's avatar
      x86, PEBS/DS: fix code flow in ds_request() · 10db4ef7
      Ingo Molnar authored
      this compiler warning:
      
        arch/x86/kernel/ds.c: In function 'ds_request':
        arch/x86/kernel/ds.c:368: warning: 'context' may be used uninitialized in this function
      
      Shows that the code flow in ds_request() is buggy - it goes into
      the unlock+release-context path even when the context is not allocated
      yet.
      
      First allocate the context, then do the other checks.
      
      Also, take care with GFP allocations under the ds_lock spinlock.
      
      Cc: <stable@kernel.org>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      10db4ef7
  3. 17 Nov, 2008 4 commits
  4. 16 Nov, 2008 2 commits
    • Yinghai Lu's avatar
      x86: fix es7000 compiling · d3c6aa1e
      Yinghai Lu authored
      Impact: fix es7000 build
      
        CC      arch/x86/kernel/es7000_32.o
      arch/x86/kernel/es7000_32.c: In function find_unisys_acpi_oem_table:
      arch/x86/kernel/es7000_32.c:255: error: implicit declaration of function acpi_get_table_with_size
      arch/x86/kernel/es7000_32.c:261: error: implicit declaration of function early_acpi_os_unmap_memory
      arch/x86/kernel/es7000_32.c: In function unmap_unisys_acpi_oem_table:
      arch/x86/kernel/es7000_32.c:277: error: implicit declaration of function __acpi_unmap_table
      make[1]: *** [arch/x86/kernel/es7000_32.o] Error 1
      
      we applied one patch out of order...
      
      | commit a73aaedd
      | Author: Yinghai Lu <yhlu.kernel@gmail.com>
      | Date:   Sun Sep 14 02:33:14 2008 -0700
      |
      |    x86: check dsdt before find oem table for es7000, v2
      |
      |    v2: use __acpi_unmap_table()
      
      that patch need:
      
      	x86: use early_ioremap in __acpi_map_table
      	x86: always explicitly map acpi memory
      	acpi: remove final __acpi_map_table mapping before setting acpi_gbl_permanent_mmap
      	acpi/x86: introduce __apci_map_table, v4
      
      submitted to the ACPI tree but not upstream yet.
      
      fix it until those patches applied, need to revert this one
      Signed-off-by: default avatarYinghai Lu <yinghai@kernel.org>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      d3c6aa1e
    • Markus Metzger's avatar
      x86, bts: fix unlock problem in ds.c · d1f1e9c0
      Markus Metzger authored
      Fix a problem where ds_request() returned an error without releasing the
      ds lock.
      Reported-by: default avatarStephane Eranian <eranian@gmail.com>
      Signed-off-by: default avatarMarkus Metzger <markus.t.metzger@gmail.com>
      Cc: <stable@kernel.org>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      d1f1e9c0
  5. 15 Nov, 2008 17 commits
  6. 14 Nov, 2008 13 commits