search for: frame_end

...t;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. > */ That should work for now. I have done something similar for __pv_queued_spin_unlock. However, this has the problem of creatin...

...t;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. > */ That should work for now. I have done something similar for __pv_queued_spin_unlock. However, this has the problem of creatin...

I'm seeing Asterisk crashes with the following frame at func_speex.c:188: (gdb) p *frame $6 = {frametype = AST_FRAME_VOICE, subclass = {integer = 0, format = 0xe2f9e20, frame_ending = 0}, datalen = 0, samples = 640, mallocd = 1, mallocd_hdr_len = 232, offset = 64, src = 0x2ac07413e7f8 "siren14tolin32", data = {ptr = 0x3cab9378, uint32 = 1017877368, pad = "x\223\253<\000\000\000"}, delivery = { tv_sec = 1491485582, tv_usec = 407272}, fra...

The DoubleRenderError exception recently introduced is forcing me to go back and rewrite my apps authentication handler. Before I could do a redirect right in the middle of a request. Whatever was happening after that went unnoticed, I assumed it was simply ending the request after the redirect was called, but apparently it was going on and rendering the page. Why can''t a redirect

Another crash with a packet: $10 = {frametype = AST_FRAME_VOICE, subclass = {integer = 0, format = 0x12c62170, frame_ending = 0}, datalen = 0, samples = 640, mallocd = 1, mallocd_hdr_len = 324, offset = 64, src = 0x2ad290064a08 "siren14tolin32/speex", data = {ptr = 0x80893318, uint32 = 2156475160, pad = "\030\063\211\200\000\000\000"}, delivery = { tv_sec = 1492000520, tv_usec = 225...

...id of the sign extend on edi we could avoid all the push-pop nonsense, but I'm not sure I see how to do that (then again, this asm foo isn't my strongest point). > >> +"setne %al;" > >> +"pop %rdx;" > >> +"pop %rdi;" > >> +FRAME_END > >> +"ret;" > >> +".popsection"); > >> + > >> +#endif > >> + > >> /* > >> * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. > >> */ > > That should work for now. I have done someth...

...id of the sign extend on edi we could avoid all the push-pop nonsense, but I'm not sure I see how to do that (then again, this asm foo isn't my strongest point). > >> +"setne %al;" > >> +"pop %rdx;" > >> +"pop %rdi;" > >> +FRAME_END > >> +"ret;" > >> +".popsection"); > >> + > >> +#endif > >> + > >> /* > >> * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. > >> */ > > That should work for now. I have done someth...

...RAME_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. */

...ot;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. >> */ > That should work for now. I have done something similar for > __pv_queued_spin_unlock....

.../include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index c25c38a05c1c..d6f5ae2c79ab 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -746,6 +746,7 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu); PV_RESTORE_ALL_CALLER_REGS \ FRAME_END \ "ret;" \ + ".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";" \ ".popsection") /* Get a reference to a callee-save function */ diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 5169b8cc35bb..3...

...86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index e375d4266b53..a04677038872 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -768,6 +768,7 @@ static __always_inline bool pv_vcpu_is_preempted(long cpu) PV_RESTORE_ALL_CALLER_REGS \ FRAME_END \ "ret;" \ + ".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";" \ ".popsection") /* Get a reference to a callee-save function */ diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 7f89d609095a..c...

...86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index c83a2f418cea..4471f0da6ed7 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -758,6 +758,7 @@ static __always_inline bool pv_vcpu_is_preempted(long cpu) PV_RESTORE_ALL_CALLER_REGS \ FRAME_END \ "ret;" \ + ".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";" \ ".popsection") /* Get a reference to a callee-save function */ diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 652bdd867782..5...

It was found when running fio sequential write test with a XFS ramdisk on a VM running on a 2-socket x86-64 system, the %CPU times as reported by perf were as follows: 69.75% 0.59% fio [k] down_write 69.15% 0.01% fio [k] call_rwsem_down_write_failed 67.12% 1.12% fio [k] rwsem_down_write_failed 63.48% 52.77% fio [k] osq_lock 9.46% 7.88% fio [k]

It was found when running fio sequential write test with a XFS ramdisk on a VM running on a 2-socket x86-64 system, the %CPU times as reported by perf were as follows: 69.75% 0.59% fio [k] down_write 69.15% 0.01% fio [k] call_rwsem_down_write_failed 67.12% 1.12% fio [k] rwsem_down_write_failed 63.48% 52.77% fio [k] osq_lock 9.46% 7.88% fio [k]

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.

...9a 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -925,7 +925,7 @@ ENTRY(native_load_gs_index) SWAPGS .Lgs_change: movl %edi, %gs -2: ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE +2: ALTERNATIVE(, mfence, X86_BUG_SWAPGS_FENCE) SWAPGS popfq FRAME_END @@ -938,12 +938,8 @@ EXPORT_SYMBOL(native_load_gs_index) /* running with kernelgs */ bad_gs: SWAPGS /* switch back to user gs */ -.macro ZAP_GS - /* This can't be a string because the preprocessor needs to see it. */ - movl $__USER_DS, %eax - movl %eax, %gs -.endm - ALTERNATIVE "&...

This is a small series getting rid of paravirt patching by switching completely to alternative patching for the same functionality. The basic idea is to add the capability to switch from indirect to direct calls via a special alternative patching option. This removes _some_ of the paravirt macro maze, but most of it needs to stay due to the need of hiding the call instructions from the compiler

This is a small series getting rid of paravirt patching by switching completely to alternative patching for the same functionality. The basic idea is to add the capability to switch from indirect to direct calls via a special alternative patching option. This removes _some_ of the paravirt macro maze, but most of it needs to stay due to the need of hiding the call instructions from the compiler

This changes the pv ops code generation to more closely match reality. For example, instead of: callq *0xffffffff81e3a400 (pv_irq_ops.save_fl) vmlinux will now show: pushfq pop %rax nop nop nop nop nop which is what the runtime version of the code will show in most cases. This idea was suggested by Andy Lutomirski. The benefits are: - For the most common runtime cases