fs: use fast counters for vfs caches

fs: use fast counters for vfs caches

percpu_counter library generates quite nasty code, so unless you need
to dynamically allocate counters or take fast approximate value, a
simple per cpu set of counters is much better.

The percpu_counter can never be made to work as well, because it has an
indirection from pointer to percpu memory, and it can't use direct
this_cpu_inc interfaces because it doesn't use static PER_CPU data, so
code will always be worse.

In the fastpath, it is the difference between this:

        incl %gs:nr_dentry      # nr_dentry

and this:

        movl    percpu_counter_batch(%rip), %edx        # percpu_counter_batch,
        movl    $1, %esi        #,
        movq    $nr_dentry, %rdi        #,
        call    __percpu_counter_add    # (plus I clobber registers)

__percpu_counter_add:
        pushq   %rbp    #
        movq    %rsp, %rbp      #,
        subq    $32, %rsp       #,
        movq    %rbx, -24(%rbp) #,
        movq    %r12, -16(%rbp) #,
        movq    %r13, -8(%rbp)  #,
        movq    %rdi, %rbx      # fbc, fbc
#APP
# 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1
        movq %gs:kernel_stack,%rax      #, pfo_ret__
# 0 "" 2
#NO_APP
        incl    -8124(%rax)     # <variable>.preempt_count
        movq    32(%rdi), %r12  # <variable>.counters, tcp_ptr__
#APP
# 78 "lib/percpu_counter.c" 1
        add %gs:this_cpu_off, %r12      # this_cpu_off, tcp_ptr__
# 0 "" 2
#NO_APP
        movslq  (%r12),%r13     #* tcp_ptr__, tmp73
        movslq  %edx,%rax       # batch, batch
        addq    %rsi, %r13      # amount, count
        cmpq    %rax, %r13      # batch, count
        jge     .L27    #,
        negl    %edx    # tmp76
        movslq  %edx,%rdx       # tmp76, tmp77
        cmpq    %rdx, %r13      # tmp77, count
        jg      .L28    #,
.L27:
        movq    %rbx, %rdi      # fbc,
        call    _raw_spin_lock  #
        addq    %r13, 8(%rbx)   # count, <variable>.count
        movq    %rbx, %rdi      # fbc,
        movl    $0, (%r12)      #,* tcp_ptr__
        call    _raw_spin_unlock        #
.L29:
#APP
# 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1
        movq %gs:kernel_stack,%rax      #, pfo_ret__
# 0 "" 2
#NO_APP
        decl    -8124(%rax)     # <variable>.preempt_count
        movq    -8136(%rax), %rax       #, D.14625
        testb   $8, %al #, D.14625
        jne     .L32    #,
.L31:
        movq    -24(%rbp), %rbx #,
        movq    -16(%rbp), %r12 #,
        movq    -8(%rbp), %r13  #,
        leave
        ret
        .p2align 4,,10
        .p2align 3
.L28:
        movl    %r13d, (%r12)   # count,*
        jmp     .L29    #
.L32:
        call    preempt_schedule        #
        .p2align 4,,6
        jmp     .L31    #
        .size   __percpu_counter_add, .-__percpu_counter_add
        .p2align 4,,15

Signed-off-by: Nick Piggin <npiggin@kernel.dk>