git commit b4f0d3755c5e9cc86292d5fd78261903b4f23d4a was very very dumb. It was writing over %esp/pt_regs semi-randomly on i686 with the expected "system can't boot" results. As noted in: https://bugs.freedesktop.org/show_bug.cgi?id=85277 This patch stops fscking with pt_regs. Instead it sets up the registers for the call to __audit_syscall_entry in the most obvious conceivable way. It then does just a tiny tiny touch of magic. We need to get what started in PT_EDX into 0(%esp) and PT_ESI into 4(%esp). This is as easy as a pair of pushes using the values still in those registers. After the call to __audit_syscall_entry all we need to do is get that now useless junk off the stack (pair of pops) and reload %eax with the original syscall so other stuff can keep going about it's business. Reported-by: Paulo Zanoni <przanoni(a)gmail.com&gt; Signed-off-by: Eric Paris <eparis(a)redhat.com&gt; Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; Cc: Thomas Gleixner <tglx(a)linutronix.de&gt; Cc: Ingo Molnar <mingo(a)redhat.com&gt; Cc: "H. Peter Anvin" <hpa(a)zytor.com&gt; Cc: x86(a)kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: linux-audit(a)redhat.com --- On 14/10/25, Thomas Gleixner wrote: > Why are we grabbing that from the stack? AFAICT all arguments are in > the registers still. Right, re-arranging the instructions slightly to avoid overwriting %edx with %ebx before needing it to push onto the stack, how does this look? arch/x86/kernel/entry_32.S | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index b553ed8..344b63f 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -447,15 +447,14 @@ sysenter_exit: sysenter_audit: testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp) jnz syscall_trace_entry - addl $4,%esp - CFI_ADJUST_CFA_OFFSET -4 - movl %esi,4(%esp) /* 5th arg: 4th syscall arg */ - movl %edx,(%esp) /* 4th arg: 3rd syscall arg */ - /* %ecx already in %ecx 3rd arg: 2nd syscall arg */ - movl %ebx,%edx /* 2nd arg: 1st syscall arg */ - /* %eax already in %eax 1st arg: syscall number */ + /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */ + /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */ + pushl_cfi %esi /* a3: 5th arg */ + pushl_cfi %edx /* a2: 4th arg */ + movl %ebx, %edx /* ebx/a0: 2nd arg to audit */ call __audit_syscall_entry - pushl_cfi %ebx + popl_cfi %ecx /* get that remapped edx off the stack */ + popl_cfi %ecx /* get that remapped esi off the stack */ movl PT_EAX(%esp),%eax /* reload syscall number */ jmp sysenter_do_call - RGB -- Richard Guy Briggs <rbriggs(a)redhat.com&gt; Senior Software Engineer, Kernel Security, AMER ENG Base Operating Systems, Red Hat Remote, Ottawa, Canada Voice: +1.647.777.2635, Internal: (81) 32635, Alt: +1.613.693.0684x3545

My patch was already committed to the -tip urgent branch. I believe any optimization should be based on that branch, Richard. If you are trying to wrangle every bit of speed out of this, should you push %esi; push %edi; CFI_ADJUST_CFA_OFFSET 8 call __audit_syscall_entry pop; pop; CFI_ADJUST_CFA_OFFSET -8 Instead of using the pushl_cfi and popl_cfi macros? I wrote my patch to be obviously correct, but agree there are certainly some speedups possible.

-Eric On Sun, 2014-10-26 at 22:34 -0400, Richard Guy Briggs wrote: > git commit b4f0d3755c5e9cc86292d5fd78261903b4f23d4a was very very dumb. > It was writing over %esp/pt_regs semi-randomly on i686 with the expected > "system can't boot" results. As noted in: > > https://bugs.freedesktop.org/show_bug.cgi?id=85277 > > This patch stops fscking with pt_regs. Instead it sets up the registers > for the call to __audit_syscall_entry in the most obvious conceivable > way. It then does just a tiny tiny touch of magic. We need to get what > started in PT_EDX into 0(%esp) and PT_ESI into 4(%esp). This is as easy > as a pair of pushes using the values still in those registers. > > After the call to __audit_syscall_entry all we need to do is get that > now useless junk off the stack (pair of pops) and reload %eax with the > original syscall so other stuff can keep going about it's business. > > Reported-by: Paulo Zanoni <przanoni(a)gmail.com&gt; > Signed-off-by: Eric Paris <eparis(a)redhat.com&gt; > Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; > Cc: Thomas Gleixner <tglx(a)linutronix.de&gt; > Cc: Ingo Molnar <mingo(a)redhat.com&gt; > Cc: "H. Peter Anvin" <hpa(a)zytor.com&gt; > Cc: x86(a)kernel.org > Cc: linux-kernel(a)vger.kernel.org > Cc: linux-audit(a)redhat.com > > --- > On 14/10/25, Thomas Gleixner wrote: > > Why are we grabbing that from the stack? AFAICT all arguments are in > > the registers still. > > Right, re-arranging the instructions slightly to avoid overwriting %edx > with %ebx before needing it to push onto the stack, how does this look? > > arch/x86/kernel/entry_32.S | 15 +++++++-------- > 1 file changed, 7 insertions(+), 8 deletions(-) > > diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S > index b553ed8..344b63f 100644 > --- a/arch/x86/kernel/entry_32.S > +++ b/arch/x86/kernel/entry_32.S > @@ -447,15 +447,14 @@ sysenter_exit: > sysenter_audit: > testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp) > jnz syscall_trace_entry > - addl $4,%esp > - CFI_ADJUST_CFA_OFFSET -4 > - movl %esi,4(%esp) /* 5th arg: 4th syscall arg */ > - movl %edx,(%esp) /* 4th arg: 3rd syscall arg */ > - /* %ecx already in %ecx 3rd arg: 2nd syscall arg */ > - movl %ebx,%edx /* 2nd arg: 1st syscall arg */ > - /* %eax already in %eax 1st arg: syscall number */ > + /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */ > + /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */ > + pushl_cfi %esi /* a3: 5th arg */ > + pushl_cfi %edx /* a2: 4th arg */ > + movl %ebx, %edx /* ebx/a0: 2nd arg to audit */ > call __audit_syscall_entry > - pushl_cfi %ebx > + popl_cfi %ecx /* get that remapped edx off the stack */ > + popl_cfi %ecx /* get that remapped esi off the stack */ > movl PT_EAX(%esp),%eax /* reload syscall number */ > jmp sysenter_do_call > > > - RGB > > -- > Richard Guy Briggs <rbriggs(a)redhat.com&gt; > Senior Software Engineer, Kernel Security, AMER ENG Base Operating Systems, Red Hat > Remote, Ottawa, Canada > Voice: +1.647.777.2635, Internal: (81) 32635, Alt: +1.613.693.0684x3545

On Sun, 26 Oct 2014, Richard Guy Briggs wrote: > diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S > index b553ed8..344b63f 100644 > --- a/arch/x86/kernel/entry_32.S > +++ b/arch/x86/kernel/entry_32.S > @@ -447,15 +447,14 @@ sysenter_exit: > sysenter_audit: > testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp) > jnz syscall_trace_entry > - addl $4,%esp > - CFI_ADJUST_CFA_OFFSET -4 > - movl %esi,4(%esp) /* 5th arg: 4th syscall arg */ > - movl %edx,(%esp) /* 4th arg: 3rd syscall arg */ > - /* %ecx already in %ecx 3rd arg: 2nd syscall arg */ > - movl %ebx,%edx /* 2nd arg: 1st syscall arg */ > - /* %eax already in %eax 1st arg: syscall number */ > + /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */ > + /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */ > + pushl_cfi %esi /* a3: 5th arg */ > + pushl_cfi %edx /* a2: 4th arg */ > + movl %ebx, %edx /* ebx/a0: 2nd arg to audit */ > call __audit_syscall_entry > - pushl_cfi %ebx > + popl_cfi %ecx /* get that remapped edx off the stack */ > + popl_cfi %ecx /* get that remapped esi off the stack */ Why use pop instead of simply adjusting esp and CFI by 8?