search for: cmpb

...ot; > >> +FRAME_BEGIN > >> +"push %rdi;" > >> +"push %rdx;" > >> +"movslq %edi, %rdi;" > >> +"movq $steal_time+16, %rax;" > >> +"movq __per_cpu_offset(,%rdi,8), %rdx;" > >> +"cmpb $0, (%rdx,%rax);" Could we not put the $steal_time+16 displacement as an immediate in the cmpb and save a whole register here? That way we'd end up with something like: asm(" push %rdi; movslq %edi, %rdi; movq __per_cpu_offset(,%rdi,8), %rax; cmpb $0, %[offset](%rax); setne %al;...

...ot; > >> +FRAME_BEGIN > >> +"push %rdi;" > >> +"push %rdx;" > >> +"movslq %edi, %rdi;" > >> +"movq $steal_time+16, %rax;" > >> +"movq __per_cpu_offset(,%rdi,8), %rdx;" > >> +"cmpb $0, (%rdx,%rax);" Could we not put the $steal_time+16 displacement as an immediate in the cmpb and save a whole register here? That way we'd end up with something like: asm(" push %rdi; movslq %edi, %rdi; movq __per_cpu_offset(,%rdi,8), %rax; cmpb $0, %[offset](%rax); setne %al;...

...2017 at 11:47:16AM +0100, Peter Zijlstra wrote: > >>> That way we'd end up with something like: > >>> > >>> asm(" > >>> push %rdi; > >>> movslq %edi, %rdi; > >>> movq __per_cpu_offset(,%rdi,8), %rax; > >>> cmpb $0, %[offset](%rax); > >>> setne %al; > >>> pop %rdi; > >>> " : : [offset] "i" (((unsigned long)&steal_time) + offsetof(struct steal_time, preempted))); > >>> > >>> And if we could get rid of the sign extend on edi we co...

...2017 at 11:47:16AM +0100, Peter Zijlstra wrote: > >>> That way we'd end up with something like: > >>> > >>> asm(" > >>> push %rdi; > >>> movslq %edi, %rdi; > >>> movq __per_cpu_offset(,%rdi,8), %rax; > >>> cmpb $0, %[offset](%rax); > >>> setne %al; > >>> pop %rdi; > >>> " : : [offset] "i" (((unsigned long)&steal_time) + offsetof(struct steal_time, preempted))); > >>> > >>> And if we could get rid of the sign extend on edi we co...

...02/13/2017 05:53 AM, Peter Zijlstra wrote: > On Mon, Feb 13, 2017 at 11:47:16AM +0100, Peter Zijlstra wrote: >> That way we'd end up with something like: >> >> asm(" >> push %rdi; >> movslq %edi, %rdi; >> movq __per_cpu_offset(,%rdi,8), %rax; >> cmpb $0, %[offset](%rax); >> setne %al; >> pop %rdi; >> " : : [offset] "i" (((unsigned long)&steal_time) + offsetof(struct steal_time, preempted))); >> >> And if we could get rid of the sign extend on edi we could avoid all the >> push-pop nonsense,...

...02/13/2017 05:53 AM, Peter Zijlstra wrote: > On Mon, Feb 13, 2017 at 11:47:16AM +0100, Peter Zijlstra wrote: >> That way we'd end up with something like: >> >> asm(" >> push %rdi; >> movslq %edi, %rdi; >> movq __per_cpu_offset(,%rdi,8), %rax; >> cmpb $0, %[offset](%rax); >> setne %al; >> pop %rdi; >> " : : [offset] "i" (((unsigned long)&steal_time) + offsetof(struct steal_time, preempted))); >> >> And if we could get rid of the sign extend on edi we could avoid all the >> push-pop nonsense,...

...tra <peterz at infradead.org> wrote: >On Mon, Feb 13, 2017 at 11:47:16AM +0100, Peter Zijlstra wrote: >> That way we'd end up with something like: >> >> asm(" >> push %rdi; >> movslq %edi, %rdi; >> movq __per_cpu_offset(,%rdi,8), %rax; >> cmpb $0, %[offset](%rax); >> setne %al; >> pop %rdi; >> " : : [offset] "i" (((unsigned long)&steal_time) + offsetof(struct >steal_time, preempted))); >> >> And if we could get rid of the sign extend on edi we could avoid all >the >> push-pop...

...tra <peterz at infradead.org> wrote: >On Mon, Feb 13, 2017 at 11:47:16AM +0100, Peter Zijlstra wrote: >> That way we'd end up with something like: >> >> asm(" >> push %rdi; >> movslq %edi, %rdi; >> movq __per_cpu_offset(,%rdi,8), %rax; >> cmpb $0, %[offset](%rax); >> setne %al; >> pop %rdi; >> " : : [offset] "i" (((unsigned long)&steal_time) + offsetof(struct >steal_time, preempted))); >> >> And if we could get rid of the sign extend on edi we could avoid all >the >> push-pop...

...esp),%eax push %ebx - push 4+8(%esp) - push 4+8(%esp) +0: + pushl 4+8(%esp) + push %eax call .Lstrstr add $8,%esp test %eax,%eax @@ -129,20 +131,20 @@ cmp %eax,4+4(%esp) je 1f cmpb $'' '',-1(%eax) - jne 2f + je 1f +2: inc %eax + jmp 0b 1: mov %eax,%ebx - push 4+8(%esp) + pushl 4+8(%esp) call .Lstrlen add $4,%esp - xchg %eax,%ebx - add %eax,%...

...quot; > +"__raw_callee_save___kvm_vcpu_is_preempted:" > +FRAME_BEGIN > +"push %rdi;" > +"push %rdx;" > +"movslq %edi, %rdi;" > +"movq $steal_time+16, %rax;" > +"movq __per_cpu_offset(,%rdi,8), %rdx;" > +"cmpb $0, (%rdx,%rax);" > +"setne %al;" > +"pop %rdx;" > +"pop %rdi;" > +FRAME_END > +"ret;" > +".popsection"); > + > +#endif > + > /* > * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. >...

...quot; > +"__raw_callee_save___kvm_vcpu_is_preempted:" > +FRAME_BEGIN > +"push %rdi;" > +"push %rdx;" > +"movslq %edi, %rdi;" > +"movq $steal_time+16, %rax;" > +"movq __per_cpu_offset(,%rdi,8), %rdx;" > +"cmpb $0, (%rdx,%rax);" > +"setne %al;" > +"pop %rdx;" > +"pop %rdi;" > +FRAME_END > +"ret;" > +".popsection"); > + > +#endif > + > /* > * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. >...

...try) pushfq .globl sysenter_eflags_saved sysenter_eflags_saved: - pushq $0 - pushq $0 + pushq $3 /* ring 3 null cs */ + pushq $0 /* null rip */ pushq $0 movl $TRAP_syscall,4(%rsp) SAVE_ALL GET_CURRENT(%rbx) cmpb $0,VCPU_sysenter_disables_events(%rbx) - movq $0,UREGS_rip(%rsp) /* null rip */ - movl $3,UREGS_cs(%rsp) /* ring 3 null cs */ movq VCPU_sysenter_addr(%rbx),%rax setne %cl leaq VCPU_trap_bounce(%rbx),%rdx @@ -292,7 +290,6 @@ sysenter_eflags_saved: UNLI...

On Mon, Feb 13, 2017 at 05:34:01PM -0500, Waiman Long wrote: > It is the address of &steal_time that will exceed the 32-bit limit. That seems extremely unlikely. That would mean we have more than 4G worth of per-cpu variables declared in the kernel.

On Mon, Feb 13, 2017 at 05:34:01PM -0500, Waiman Long wrote: > It is the address of &steal_time that will exceed the 32-bit limit. That seems extremely unlikely. That would mean we have more than 4G worth of per-cpu variables declared in the kernel.

...st on which (I swear!) clang used to perform load widening. Not any more. What's happened? % cat lw.cc struct S { int a; unsigned char x, y, z, w; }; int foo(S *s) { if (s->x == 0 && s->y == 0) return 0; return 1; } % clang -O2 -S -o - lw.cc | grep '(%' cmpb $0, 4(%rdi) cmpb $0, 5(%rdi) % gcc -O2 -S -o - lw.cc | grep '(%' cmpw $0, 4(%rdi) % --kcc -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20121123/ec7ea7a4/attachment.html>

On Mon, Feb 13, 2017 at 11:47:16AM +0100, Peter Zijlstra wrote: > That way we'd end up with something like: > > asm(" > push %rdi; > movslq %edi, %rdi; > movq __per_cpu_offset(,%rdi,8), %rax; > cmpb $0, %[offset](%rax); > setne %al; > pop %rdi; > " : : [offset] "i" (((unsigned long)&steal_time) + offsetof(struct steal_time, preempted))); > > And if we could get rid of the sign extend on edi we could avoid all the > push-pop nonsense, but I'm not sure I...

...tra wrote: >> On Mon, Feb 13, 2017 at 11:47:16AM +0100, Peter Zijlstra wrote: >>> That way we'd end up with something like: >>> >>> asm(" >>> push %rdi; >>> movslq %edi, %rdi; >>> movq __per_cpu_offset(,%rdi,8), %rax; >>> cmpb $0, %[offset](%rax); >>> setne %al; >>> pop %rdi; >>> " : : [offset] "i" (((unsigned long)&steal_time) + offsetof(struct steal_time, preempted))); >>> >>> And if we could get rid of the sign extend on edi we could avoid all the >&gt...

...gt; wrote: >> On Mon, Feb 13, 2017 at 11:47:16AM +0100, Peter Zijlstra wrote: >>> That way we'd end up with something like: >>> >>> asm(" >>> push %rdi; >>> movslq %edi, %rdi; >>> movq __per_cpu_offset(,%rdi,8), %rax; >>> cmpb $0, %[offset](%rax); >>> setne %al; >>> pop %rdi; >>> " : : [offset] "i" (((unsigned long)&steal_time) + offsetof(struct >> steal_time, preempted))); >>> And if we could get rid of the sign extend on edi we could avoid all >> the &g...

...0100, Peter Zijlstra wrote: >>>>> That way we'd end up with something like: >>>>> >>>>> asm(" >>>>> push %rdi; >>>>> movslq %edi, %rdi; >>>>> movq __per_cpu_offset(,%rdi,8), %rax; >>>>> cmpb $0, %[offset](%rax); >>>>> setne %al; >>>>> pop %rdi; >>>>> " : : [offset] "i" (((unsigned long)&steal_time) + offsetof(struct steal_time, preempted))); >>>>> >>>>> And if we could get rid of the sign exte...

...red across the syscall, thankfully. + * + */ + + .text + .align 64 ; cache-width aligned + .globl vfork + .type vfork, at function +vfork: + /* pid_t vfork(void) */ + ble 0x100(%sr2, %r0) ; jump to gateway page + nop + + ldi -0x1000,%r19 ; %r19 = -4096 + sub %r0,%ret0,%r22 ; %r22 = -%ret0 + cmpb,>>=,n %r19,%ret0,1f ; if %ret0 >= -4096UL + ldi -1,%ret0 ; nullified on taken forward + + /* store %r22 to errno... */ + ldil L%errno,%r1 + ldo R%errno(%r1),%r1 + stw %r22,0(%r1) +1: + bv %r0(%rp) ; jump back + nop + + .size vfork,.-vfork