search for: ia32_sysenter_target

I implemented sysenter for 32-on-64, since it seemed straightforward enough. It mostly works, but every now and again I get vcpus just hanging in blocked state, as if events are being lost or ignored. Its very similar to the symptoms that other people have reported against the pvops kernel, which I have not managed to reproduce. Perhaps using sysenter is exacerbating an existing bug...

...============================================================ --- clean-start.orig/arch/x86_64/ia32/syscall32.c +++ clean-start/arch/x86_64/ia32/syscall32.c @@ -119,5 +119,5 @@ void syscall32_cpu_init(void) checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL); checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); - wrmsrl(MSR_CSTAR, ia32_cstar_target); + wrmsrl(MSR_CSTAR, (u64)ia32_cstar_target); } Index: clean-start/arch/x86_64/mm/pageattr.c =================================================================== --- clean-start.orig/arch/x86_64/mm/pageattr.c +++ clean-start/arch/x86_64/mm/pageattr.c @@ -8...

...============================================================ --- clean-start.orig/arch/x86_64/ia32/syscall32.c +++ clean-start/arch/x86_64/ia32/syscall32.c @@ -119,5 +119,5 @@ void syscall32_cpu_init(void) checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL); checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); - wrmsrl(MSR_CSTAR, ia32_cstar_target); + wrmsrl(MSR_CSTAR, (u64)ia32_cstar_target); } Index: clean-start/arch/x86_64/mm/pageattr.c =================================================================== --- clean-start.orig/arch/x86_64/mm/pageattr.c +++ clean-start/arch/x86_64/mm/pageattr.c @@ -8...

...e_kernel) #endif CFI_ENDPROC -/* - * End of kprobes section - */ - .popsection /* SYSENTER_RETURN points to after the "sysenter" instruction in the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */ @@ -495,10 +487,6 @@ sysexit_audit: PTGS_TO_GS_EX ENDPROC(ia32_sysenter_target) -/* - * syscall stub including irq exit should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" # system call handler stub ENTRY(system_call) RING0_INT_FRAME # can't unwind into user space anyway @@ -691,10 +679,6 @@ syscall_badsys: jmp resume_userspace...

...inux/linkage.h> +#ifdef CONFIG_PARAVIRT +#include <asm/paravirt.h> +#else +#define ENABLE_INTERRUPTS(CLBR) sti +#define DISABLE_INTERRUPTS(CLBR) cli +#endif + #define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8) .macro IA32_ARG_FIXUP noebp=0 @@ -81,7 +88,7 @@ ENTRY(ia32_sysenter_target) * No need to follow this irqs on/off section: the syscall * disabled irqs, here we enable it straight after entry: */ - sti + ENABLE_INTERRUPTS(CLBR_NONE) movl %ebp,%ebp /* zero extension */ pushq $__USER32_DS CFI_ADJUST_CFA_OFFSET 8 @@ -123,7 +130,7 @@ sysenter_do_call: call...

...inux/linkage.h> +#ifdef CONFIG_PARAVIRT +#include <asm/paravirt.h> +#else +#define ENABLE_INTERRUPTS(CLBR) sti +#define DISABLE_INTERRUPTS(CLBR) cli +#endif + #define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8) .macro IA32_ARG_FIXUP noebp=0 @@ -81,7 +88,7 @@ ENTRY(ia32_sysenter_target) * No need to follow this irqs on/off section: the syscall * disabled irqs, here we enable it straight after entry: */ - sti + ENABLE_INTERRUPTS(CLBR_NONE) movl %ebp,%ebp /* zero extension */ pushq $__USER32_DS CFI_ADJUST_CFA_OFFSET 8 @@ -123,7 +130,7 @@ sysenter_do_call: call...

Currently the blacklist is maintained by hand in kprobes.c which is separated from the function definition and is hard to catch up the kernel update. To solve this issue, I've tried to implement new NOKPROBE_SYMBOL() macro for making kprobe blacklist at build time. Since the NOKPROBE_SYMBOL() macros can be placed right after the function is defined, it is easy to maintain. At this moment, I

Currently the blacklist is maintained by hand in kprobes.c which is separated from the function definition and is hard to catch up the kernel update. To solve this issue, I've tried to implement new NOKPROBE_SYMBOL() macro for making kprobe blacklist at build time. Since the NOKPROBE_SYMBOL() macros can be placed right after the function is defined, it is easy to maintain. At this moment, I

...rch/x86_64/ia32/syscall32.c 2007-01-11 21:51:35.000000000 -0200 +++ linux-2.6.19-paravirt1/arch/x86_64/ia32/syscall32.c 2007-01-09 11:01:19.000000000 -0200 @@ -104,5 +104,5 @@ void syscall32_cpu_init(void) checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL); checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); - wrmsrl(MSR_CSTAR, ia32_cstar_target); + wrmsrl(MSR_CSTAR, (u64)ia32_cstar_target); } diff -urp linux-2.6.19-paravirt0/arch/x86_64/kernel/asm-offsets.c linux-2.6.19-paravirt1/arch/x86_64/kernel/asm-offsets.c --- linux-2.6.19-paravirt0/arch/x86_64/kernel/asm-offsets.c 2007-01-11 21:56:03.00000...

...rch/x86_64/ia32/syscall32.c 2007-01-11 21:51:35.000000000 -0200 +++ linux-2.6.19-paravirt1/arch/x86_64/ia32/syscall32.c 2007-01-09 11:01:19.000000000 -0200 @@ -104,5 +104,5 @@ void syscall32_cpu_init(void) checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL); checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); - wrmsrl(MSR_CSTAR, ia32_cstar_target); + wrmsrl(MSR_CSTAR, (u64)ia32_cstar_target); } diff -urp linux-2.6.19-paravirt0/arch/x86_64/kernel/asm-offsets.c linux-2.6.19-paravirt1/arch/x86_64/kernel/asm-offsets.c --- linux-2.6.19-paravirt0/arch/x86_64/kernel/asm-offsets.c 2007-01-11 21:56:03.00000...

Currently the blacklist is maintained by hand in kprobes.c which is separated from the function definition and is hard to catch up the kernel update. To solve this issue, I've tried to implement new NOKPROBE_SYMBOL() macro for making kprobe blacklist at build time. Since the NOKPROBE_SYMBOL() macros can be placed right after the function is defined, it is easy to maintain. This series

Currently the blacklist is maintained by hand in kprobes.c which is separated from the function definition and is hard to catch up the kernel update. To solve this issue, I've tried to implement new NOKPROBE_SYMBOL() macro for making kprobe blacklist at build time. Since the NOKPROBE_SYMBOL() macros can be placed right after the function is defined, it is easy to maintain. This series

Hi, Here is the version 3 of NOKPORBE_SYMBOL series. Currently the blacklist is maintained by hand in kprobes.c which is separated from the function definition and is hard to catch up the kernel update. To solve this issue, I've introduced NOKPROBE_SYMBOL() macro for making kprobe blacklist at build time. Since the NOKPROBE_SYMBOL() macros can be placed right after the function is defined

Hi, Here is the version 3 of NOKPORBE_SYMBOL series. Currently the blacklist is maintained by hand in kprobes.c which is separated from the function definition and is hard to catch up the kernel update. To solve this issue, I've introduced NOKPROBE_SYMBOL() macro for making kprobe blacklist at build time. Since the NOKPROBE_SYMBOL() macros can be placed right after the function is defined