[RFC PATCH 23/27] powerpc/64: system call implement the bulk of the logic in C

[Michal Suchánek]

On Sun, Sep 15, 2019 at 11:28:09AM +1000, Nicholas Piggin wrote:
> 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 <npiggin at gmail.com>
> 
> v3:
> - Fix !KUAP build [mpe]
> - Fix BookE build/boot [mpe]
> - Don't trace irqs with MSR[RI]=0
> - Don't allow syscall_exit_prepare to be ftraced, because function
>   graph tracing which traces exits barfs after the IRQ state is
>   prepared for kernel exit.
> - Fix BE syscall table to use normal function descriptors now that they
>   are called from C.
> - Comment syscall_exit_prepare.
...
> -#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC_SPLPAR)
> -BEGIN_FW_FTR_SECTION
> -	/* see if there are any DTL entries to process */
> -	ld	r10,PACALPPACAPTR(r13)	/* get ptr to VPA */
> -	ld	r11,PACA_DTL_RIDX(r13)	/* get log read index */
> -	addi	r10,r10,LPPACA_DTLIDX
> -	LDX_BE	r10,0,r10		/* get log write index */
> -	cmpd	r11,r10
> -	beq+	33f
> -	bl	accumulate_stolen_time
> -	REST_GPR(0,r1)
> -	REST_4GPRS(3,r1)
> -	REST_2GPRS(7,r1)
> -	addi	r9,r1,STACK_FRAME_OVERHEAD
> -33:
> -END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
> -#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE && CONFIG_PPC_SPLPAR */
...
> diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
> new file mode 100644
> index 000000000000..1d2529824588
> --- /dev/null
> +++ b/arch/powerpc/kernel/syscall_64.c
> @@ -0,0 +1,195 @@
> +#include <linux/err.h>
> +#include <asm/book3s/64/kup-radix.h>
> +#include <asm/cputime.h>
> +#include <asm/hw_irq.h>
> +#include <asm/kprobes.h>
> +#include <asm/paca.h>
> +#include <asm/ptrace.h>
> +#include <asm/reg.h>
> +#include <asm/signal.h>
> +#include <asm/switch_to.h>
> +#include <asm/syscall.h>
> +#include <asm/time.h>
> +
> +extern void __noreturn tabort_syscall(void);
> +
> +typedef long (*syscall_fn)(long, long, long, long, long, long);
> +
> +long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8, unsigned long r0, struct pt_regs *regs)
> +{
> +	unsigned long ti_flags;
> +	syscall_fn f;
> +
> +	BUG_ON(!(regs->msr & MSR_PR));
> +
> +	if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
> +			unlikely(regs->msr & MSR_TS_T))
> +		tabort_syscall();
> +
> +	account_cpu_user_entry();
> +
> +#ifdef CONFIG_PPC_SPLPAR
> +	if (IS_ENABLED(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) &&
> +			firmware_has_feature(FW_FEATURE_SPLPAR)) {
> +		struct lppaca *lp = get_lppaca();
> +
> +		if (unlikely(local_paca->dtl_ridx != lp->dtl_idx))

sparse complains about this, and in time.c this it converted like this:
if (unlikely(local_paca->dtl_ridx != be64_to_cpu(lp->dtl_idx)))
The removed code has a LDX_BE there so there should be some conversion
involved, right?

Thanks

Michal