1. 31 1月, 2009 3 次提交
    • J
      x86/paravirt: add register-saving thunks to reduce caller register pressure · ecb93d1c
      Jeremy Fitzhardinge 提交于
      Impact: Optimization
      
      One of the problems with inserting a pile of C calls where previously
      there were none is that the register pressure is greatly increased.
      The C calling convention says that the caller must expect a certain
      set of registers may be trashed by the callee, and that the callee can
      use those registers without restriction.  This includes the function
      argument registers, and several others.
      
      This patch seeks to alleviate this pressure by introducing wrapper
      thunks that will do the register saving/restoring, so that the
      callsite doesn't need to worry about it, but the callee function can
      be conventional compiler-generated code.  In many cases (particularly
      performance-sensitive cases) the callee will be in assembler anyway,
      and need not use the compiler's calling convention.
      
      Standard calling convention is:
      	 arguments	    return	scratch
      x86-32	 eax edx ecx	    eax		?
      x86-64	 rdi rsi rdx rcx    rax		r8 r9 r10 r11
      
      The thunk preserves all argument and scratch registers.  The return
      register is not preserved, and is available as a scratch register for
      unwrapped callee code (and of course the return value).
      
      Wrapped function pointers are themselves wrapped in a struct
      paravirt_callee_save structure, in order to get some warning from the
      compiler when functions with mismatched calling conventions are used.
      
      The most common paravirt ops, both statically and dynamically, are
      interrupt enable/disable/save/restore, so handle them first.  This is
      particularly easy since their calls are handled specially anyway.
      
      XXX Deal with VMI.  What's their calling convention?
      Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
      ecb93d1c
    • J
      x86: fix paravirt clobber in entry_64.S · b8aa287f
      Jeremy Fitzhardinge 提交于
      Impact: Fix latent bug
      
      The clobber is trying to say that anything except RDI is available for
      clobbering, but actually clobbers everything.  This hasn't mattered
      because the clobbers were basically ignored, but subsequent patches
      will rely on them.
      Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
      Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
      b8aa287f
    • J
      x86/pvops: add a paravirt_ident functions to allow special patching · 41edafdb
      Jeremy Fitzhardinge 提交于
      Impact: Optimization
      
      Several paravirt ops implementations simply return their arguments,
      the most obvious being the make_pte/pte_val class of operations on
      native.
      
      On 32-bit, the identity function is literally a no-op, as the calling
      convention uses the same registers for the first argument and return.
      On 64-bit, it can be implemented with a single "mov".
      
      This patch adds special identity functions for 32 and 64 bit argument,
      and machinery to recognize them and replace them with either nops or a
      mov as appropriate.
      
      At the moment, the only users for the identity functions are the
      pagetable entry conversion functions.
      
      The result is a measureable improvement on pagetable-heavy benchmarks
      (2-3%, reducing the pvops overhead from 5 to 2%).
      Signed-off-by: NJeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
      Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
      41edafdb
  2. 30 1月, 2009 1 次提交
  3. 27 1月, 2009 13 次提交
  4. 26 1月, 2009 2 次提交
    • R
      x86: fix section mismatch warning · 659d2618
      Rakib Mullick 提交于
      Here function vmi_activate calls a init function activate_vmi , which
      causes the following section mismatch warnings:
      
        LD      arch/x86/kernel/built-in.o
      WARNING: arch/x86/kernel/built-in.o(.text+0x13ba9): Section mismatch
      in reference from the function vmi_activate() to the function
      .init.text:vmi_time_init()
      The function vmi_activate() references
      the function __init vmi_time_init().
      This is often because vmi_activate lacks a __init
      annotation or the annotation of vmi_time_init is wrong.
      
      WARNING: arch/x86/kernel/built-in.o(.text+0x13bd1): Section mismatch
      in reference from the function vmi_activate() to the function
      .devinit.text:vmi_time_bsp_init()
      The function vmi_activate() references
      the function __devinit vmi_time_bsp_init().
      This is often because vmi_activate lacks a __devinit
      annotation or the annotation of vmi_time_bsp_init is wrong.
      
      WARNING: arch/x86/kernel/built-in.o(.text+0x13bdb): Section mismatch
      in reference from the function vmi_activate() to the function
      .devinit.text:vmi_time_ap_init()
      The function vmi_activate() references
      the function __devinit vmi_time_ap_init().
      This is often because vmi_activate lacks a __devinit
      annotation or the annotation of vmi_time_ap_init is wrong.
      
      Fix it by marking vmi_activate() as __init too.
      Signed-off-by: NRakib Mullick <rakib.mullick@gmail.com>
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      659d2618
    • I
      x86: unmask CPUID levels on Intel CPUs, fix · 99fb4d34
      Ingo Molnar 提交于
      Impact: fix boot hang on pre-model-15 Intel CPUs
      
      rdmsrl_safe() does not work in very early bootup code yet, because we
      dont have the pagefault handler installed yet so exception section
      does not get parsed. rdmsr_safe() will just crash and hang the bootup.
      
      So limit the MSR_IA32_MISC_ENABLE MSR read to those CPU types that
      support it.
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      99fb4d34
  5. 23 1月, 2009 3 次提交
  6. 22 1月, 2009 2 次提交
  7. 21 1月, 2009 11 次提交
  8. 20 1月, 2009 5 次提交
    • I
      x86, cpumask: fix tlb flush race · 5766b842
      Ingo Molnar 提交于
      Impact: fix bootup crash
      
      The cpumask is now passed in as a reference to mm->cpu_vm_mask, not on
      the stack - hence it is not constant anymore during the TLB flush.
      
      That way it could race and some static sanity checks would trigger:
      
      [  238.154287] ------------[ cut here ]------------
      [  238.156039] kernel BUG at arch/x86/kernel/tlb_32.c:130!
      [  238.156039] invalid opcode: 0000 [#1] SMP
      [  238.156039] last sysfs file: /sys/class/net/eth2/address
      [  238.156039] Modules linked in:
      [  238.156039]
      [  238.156039] Pid: 6493, comm: ifup-eth Not tainted (2.6.29-rc2-tip #1) P4DC6
      [  238.156039] EIP: 0060:[<c0118f87>] EFLAGS: 00010202 CPU: 2
      [  238.156039] EIP is at native_flush_tlb_others+0x35/0x158
      [  238.156039] EAX: c0ef972c EBX: f6143301 ECX: 00000000 EDX: 00000000
      [  238.156039] ESI: f61433a8 EDI: f6143200 EBP: f34f3e00 ESP: f34f3df0
      [  238.156039]  DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
      [  238.156039] Process ifup-eth (pid: 6493, ti=f34f2000 task=f399ab00 task.ti=f34f2000)
      [  238.156039] Stack:
      [  238.156039]  ffffffff f61433a8 ffffffff f6143200 f34f3e18 c0118e9c 00000000 f6143200
      [  238.156039]  f61433a8 f5bec738 f34f3e28 c0119435 c2b5b830 f6143200 f34f3e34 c01c2dc3
      [  238.156039]  bffd9000 f34f3e60 c01c3051 00000000 ffffffff f34f3e4c 00000000 00000071
      [  238.156039] Call Trace:
      [  238.156039]  [<c0118e9c>] ? flush_tlb_others+0x52/0x5b
      [  238.156039]  [<c0119435>] ? flush_tlb_mm+0x7f/0x8b
      [  238.156039]  [<c01c2dc3>] ? tlb_finish_mmu+0x2d/0x55
      [  238.156039]  [<c01c3051>] ? exit_mmap+0x124/0x170
      [  238.156039]  [<c013e965>] ? mmput+0x40/0xf5
      [  238.156039]  [<c01e4788>] ? flush_old_exec+0x640/0x94b
      [  238.156039]  [<c01ddb4e>] ? fsnotify_access+0x37/0x39
      [  238.156039]  [<c01e3435>] ? kernel_read+0x39/0x4b
      [  238.156039]  [<c021bc8a>] ? load_elf_binary+0x4a1/0x11bb
      [  238.156039]  [<c01c0af9>] ? might_fault+0x51/0x9c
      [  238.156039]  [<c010a2cc>] ? paravirt_read_tsc+0x20/0x4f
      [  238.156039]  [<c010a406>] ? native_sched_clock+0x5d/0x60
      [  238.156039]  [<c01e2fda>] ? search_binary_handler+0xab/0x2c4
      [  238.156039]  [<c021b7e9>] ? load_elf_binary+0x0/0x11bb
      [  238.156039]  [<c04ae9a5>] ? _raw_read_unlock+0x21/0x46
      [  238.156039]  [<c021b7e9>] ? load_elf_binary+0x0/0x11bb
      [  238.156039]  [<c01e2fe1>] ? search_binary_handler+0xb2/0x2c4
      [  238.156039]  [<c01e4076>] ? do_execve+0x21c/0x2ee
      [  238.156039]  [<c01029b7>] ? sys_execve+0x51/0x8c
      [  238.156039]  [<c0103eaf>] ? sysenter_do_call+0x12/0x43
      
      Fix it by not assuming that the cpumask is constant.
      Signed-off-by: NIngo Molnar <mingo@elte.hu>
      5766b842
    • B
      x86: remove pda.h · 0d974d45
      Brian Gerst 提交于
      Impact: cleanup
      Signed-off-by: NBrian Gerst <brgerst@gmail.com>
      0d974d45
    • B
      x86: move stack_canary into irq_stack · 947e76cd
      Brian Gerst 提交于
      Impact: x86_64 percpu area layout change, irq_stack now at the beginning
      
      Now that the PDA is empty except for the stack canary, it can be removed.
      The irqstack is moved to the start of the per-cpu section.  If the stack
      protector is enabled, the canary overlaps the bottom 48 bytes of the irqstack.
      
      tj: * updated subject
          * dropped asm relocation of irq_stack_ptr
          * updated comments a bit
          * rebased on top of stack canary changes
      Signed-off-by: NBrian Gerst <brgerst@gmail.com>
      Signed-off-by: NTejun Heo <tj@kernel.org>
      947e76cd
    • B
      x86: rework __per_cpu_load adjustments · 8c7e58e6
      Brian Gerst 提交于
      Impact: cleanup
      
      Use cpu_number to determine if the adjustment is necessary.
      Signed-off-by: NBrian Gerst <brgerst@gmail.com>
      Signed-off-by: NTejun Heo <tj@kernel.org>
      8c7e58e6
    • B
      x86: remove pda_init() · 8ce03197
      Brian Gerst 提交于
      Impact: cleanup
      
      Copy the code to cpu_init() to satisfy the requirement that the cpu
      be reinitialized.  Remove all other calls, since the segments are
      already initialized in head_64.S.
      Signed-off-by: NBrian Gerst <brgerst@gmail.com>
      Signed-off-by: NTejun Heo <tj@kernel.org>
      8ce03197