Re: [PATCH v2] powerpc/64: system call implement the bulk of the logic in C

2019-09-04 Thread Nicholas Piggin 
Michael Ellerman's on September 5, 2019 2:14 pm:
> Nicholas Piggin  writes:
>> System call entry and particularly exit code is beyond the limit of what
>> is reasonable to implement in asm.
>>
>> This conversion moves all conditional branches out of the asm code,
>> except for the case that all GPRs should be restored at exit.
>>
>> Null syscall test is about 5% faster after this patch, because the exit
>> work is handled under local_irq_disable, and the hard mask and pending
>> interrupt replay is handled after that, which avoids games with MSR.
>>
>> Signed-off-by: Nicholas Piggin 
>> ---
>> Since v1:
>> - Fix big endian build (mpe)
>> - Fix order of exit tracing to after the result registers have been set.
>> - Move ->softe store before MSR[EE] is set, fix the now obsolete comment.
>> - More #ifdef tidyups and writing the accounting helpers nicer (Christophe)
>> - Minor things like move the TM debug store into C
> 
> This doesn't build in a few configs.
> 
> It needed:
> 
> +#else
> +static inline void kuap_check_amr(void) { }
> 
> In kup-radix.h to fix the KUAP=n build.

Thanks.

> 
> It still fails to build on ppc64e with:
> 
>   arch/powerpc/kernel/syscall_64.c:161:2: error: implicit declaration of 
> function '__mtmsrd' [-Werror=implicit-function-declaration]

Ah, no __mtmsrd or RI on BookE, so that will need a new function in
hw_irq.h. I think I also need to do the irq tracing with RI=1 now I 
think about it.

I'll resend a fixed patch.

Thanks,
Nick

Re: [PATCH v2] powerpc/64: system call implement the bulk of the logic in C

2019-09-04 Thread Michael Ellerman 
Nicholas Piggin  writes:
> System call entry and particularly exit code is beyond the limit of what
> is reasonable to implement in asm.
>
> This conversion moves all conditional branches out of the asm code,
> except for the case that all GPRs should be restored at exit.
>
> Null syscall test is about 5% faster after this patch, because the exit
> work is handled under local_irq_disable, and the hard mask and pending
> interrupt replay is handled after that, which avoids games with MSR.
>
> Signed-off-by: Nicholas Piggin 
> ---
> Since v1:
> - Fix big endian build (mpe)
> - Fix order of exit tracing to after the result registers have been set.
> - Move ->softe store before MSR[EE] is set, fix the now obsolete comment.
> - More #ifdef tidyups and writing the accounting helpers nicer (Christophe)
> - Minor things like move the TM debug store into C

This doesn't build in a few configs.

It needed:

+#else
+static inline void kuap_check_amr(void) { }

In kup-radix.h to fix the KUAP=n build.

It still fails to build on ppc64e with:

  arch/powerpc/kernel/syscall_64.c:161:2: error: implicit declaration of 
function '__mtmsrd' [-Werror=implicit-function-declaration]

  http://kisskb.ellerman.id.au/kisskb/buildresult/13946972/

Which I haven't debugged yet.

cheers

[PATCH v2] powerpc/64: system call implement the bulk of the logic in C

2019-09-02 Thread Nicholas Piggin 
System call entry and particularly exit code is beyond the limit of what
is reasonable to implement in asm.

This conversion moves all conditional branches out of the asm code,
except for the case that all GPRs should be restored at exit.

Null syscall test is about 5% faster after this patch, because the exit
work is handled under local_irq_disable, and the hard mask and pending
interrupt replay is handled after that, which avoids games with MSR.

Signed-off-by: Nicholas Piggin 
---
Since v1:
- Fix big endian build (mpe)
- Fix order of exit tracing to after the result registers have been set.
- Move ->softe store before MSR[EE] is set, fix the now obsolete comment.
- More #ifdef tidyups and writing the accounting helpers nicer (Christophe)
- Minor things like move the TM debug store into C

 arch/powerpc/include/asm/asm-prototypes.h |  11 -
 .../powerpc/include/asm/book3s/64/kup-radix.h |  10 +-
 arch/powerpc/include/asm/cputime.h|  24 ++
 arch/powerpc/include/asm/ptrace.h |   3 +
 arch/powerpc/include/asm/signal.h |   3 +
 arch/powerpc/include/asm/switch_to.h  |   5 +
 arch/powerpc/include/asm/time.h   |   3 +
 arch/powerpc/kernel/Makefile  |   3 +-
 arch/powerpc/kernel/entry_64.S| 337 +++---
 arch/powerpc/kernel/signal.h  |   2 -
 arch/powerpc/kernel/syscall_64.c  | 183 ++
 11 files changed, 277 insertions(+), 307 deletions(-)
 create mode 100644 arch/powerpc/kernel/syscall_64.c

diff --git a/arch/powerpc/include/asm/asm-prototypes.h 
b/arch/powerpc/include/asm/asm-prototypes.h
index ec1c97a8e8cb..f00ef8924a99 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -92,14 +92,6 @@ long sys_switch_endian(void);
 notrace unsigned int __check_irq_replay(void);
 void notrace restore_interrupts(void);
 
-/* ptrace */
-long do_syscall_trace_enter(struct pt_regs *regs);
-void do_syscall_trace_leave(struct pt_regs *regs);
-
-/* process */
-void restore_math(struct pt_regs *regs);
-void restore_tm_state(struct pt_regs *regs);
-
 /* prom_init (OpenFirmware) */
 unsigned long __init prom_init(unsigned long r3, unsigned long r4,
   unsigned long pp,
@@ -110,9 +102,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned 
long r4,
 void __init early_setup(unsigned long dt_ptr);
 void early_setup_secondary(void);
 
-/* time */
-void accumulate_stolen_time(void);
-
 /* misc runtime */
 extern u64 __bswapdi2(u64);
 extern s64 __lshrdi3(s64, int);
diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h 
b/arch/powerpc/include/asm/book3s/64/kup-radix.h
index f254de956d6a..83f6bda0542b 100644
--- a/arch/powerpc/include/asm/book3s/64/kup-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h
@@ -3,6 +3,7 @@
 #define _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H
 
 #include 
+#include 
 
 #define AMR_KUAP_BLOCK_READUL(0x4000)
 #define AMR_KUAP_BLOCK_WRITE   UL(0x8000)
@@ -56,7 +57,14 @@
 
 #ifdef CONFIG_PPC_KUAP
 
-#include 
+#include 
+#include 
+
+static inline void kuap_check_amr(void)
+{
+   if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG) && 
mmu_has_feature(MMU_FTR_RADIX_KUAP))
+   WARN_ON_ONCE(mfspr(SPRN_AMR) != AMR_KUAP_BLOCKED);
+}
 
 /*
  * We support individually allowing read or write, but we don't support nesting
diff --git a/arch/powerpc/include/asm/cputime.h 
b/arch/powerpc/include/asm/cputime.h
index 2431b4ada2fa..c43614cffaac 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -60,6 +60,30 @@ static inline void arch_vtime_task_switch(struct task_struct 
*prev)
 }
 #endif
 
+static inline void account_cpu_user_entry(void)
+{
+   unsigned long tb = mftb();
+   struct cpu_accounting_data *acct = get_accounting(current);
+
+   acct->utime += (tb - acct->starttime_user);
+   acct->starttime = tb;
+}
+static inline void account_cpu_user_exit(void)
+{
+   unsigned long tb = mftb();
+   struct cpu_accounting_data *acct = get_accounting(current);
+
+   acct->stime += (tb - acct->starttime);
+   acct->starttime_user = tb;
+}
+
 #endif /* __KERNEL__ */
+#else /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+static inline void account_cpu_user_entry(void)
+{
+}
+static inline void account_cpu_user_exit(void)
+{
+}
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 #endif /* __POWERPC_CPUTIME_H */
diff --git a/arch/powerpc/include/asm/ptrace.h 
b/arch/powerpc/include/asm/ptrace.h
index feee1b21bbd5..af363086403a 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -138,6 +138,9 @@ extern unsigned long profile_pc(struct pt_regs *regs);
 #define profile_pc(regs) instruction_pointer(regs)
 #endif
 
+long do_syscall_trace_enter(struct pt_regs *regs);
+void do_syscall_trace_leave(struct pt_regs *regs);
+
 #define kernel_stack_pointer(regs) ((regs)->gpr[1])
 static inline int