mirror of
https://github.com/torvalds/linux.git
synced 2025-11-04 02:30:34 +02:00
powerpc/64/syscall: Remove non-volatile GPR save optimisation
powerpc has an optimisation where interrupts avoid saving the non-volatile (or callee saved) registers to the interrupt stack frame if they are not required. Two problems with this are that an interrupt does not always know whether it will need non-volatiles; and if it does need them, they can only be saved from the entry-scoped asm code (because we don't control what the C compiler does with these registers). system calls are the most difficult: some system calls always require all registers (e.g., fork, to copy regs into the child). Sometimes registers are only required under certain conditions (e.g., tracing, signal delivery). These cases require ugly logic in the call chains (e.g., ppc_fork), and require a lot of logic to be implemented in asm. So remove the optimisation for system calls, and always save NVGPRs on entry. Modern high performance CPUs are not so sensitive, because the stores are dense in cache and can be hidden by other expensive work in the syscall path -- the null syscall selftests benchmark on POWER9 is not slowed (124.40ns before and 123.64ns after, i.e., within the noise). Other interrupts retain the NVGPR optimisation for now. Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200225173541.1549955-24-npiggin@gmail.com
This commit is contained in:
Nicholas Piggin
Michael Ellerman
parent
71c3b05a80
commit
965dd3ad30
2 changed files with 28 additions and 66 deletions
|
|
@ -98,13 +98,14 @@ END_BTB_FLUSH_SECTION
|
|||
std r11,_XER(r1)
|
||||
std r11,_CTR(r1)
|
||||
std r9,GPR13(r1)
|
||||
SAVE_NVGPRS(r1)
|
||||
mflr r10
|
||||
/*
|
||||
* This clears CR0.SO (bit 28), which is the error indication on
|
||||
* return from this system call.
|
||||
*/
|
||||
rldimi r2,r11,28,(63-28)
|
||||
li r11,0xc01
|
||||
li r11,0xc00
|
||||
std r10,_LINK(r1)
|
||||
std r11,_TRAP(r1)
|
||||
std r3,ORIG_GPR3(r1)
|
||||
|
|
@ -323,7 +324,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
|
|||
|
||||
/* Traced system call support */
|
||||
.Lsyscall_dotrace:
|
||||
bl save_nvgprs
|
||||
addi r3,r1,STACK_FRAME_OVERHEAD
|
||||
bl do_syscall_trace_enter
|
||||
|
||||
|
|
@ -408,7 +408,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
|
|||
mtmsrd r10,1
|
||||
#endif /* CONFIG_PPC_BOOK3E */
|
||||
|
||||
bl save_nvgprs
|
||||
addi r3,r1,STACK_FRAME_OVERHEAD
|
||||
bl do_syscall_trace_leave
|
||||
b ret_from_except
|
||||
|
|
@ -442,62 +441,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
|
|||
_ASM_NOKPROBE_SYMBOL(system_call_common);
|
||||
_ASM_NOKPROBE_SYMBOL(system_call_exit);
|
||||
|
||||
/* Save non-volatile GPRs, if not already saved. */
|
||||
_GLOBAL(save_nvgprs)
|
||||
ld r11,_TRAP(r1)
|
||||
andi. r0,r11,1
|
||||
beqlr-
|
||||
SAVE_NVGPRS(r1)
|
||||
clrrdi r0,r11,1
|
||||
std r0,_TRAP(r1)
|
||||
blr
|
||||
_ASM_NOKPROBE_SYMBOL(save_nvgprs);
|
||||
|
||||
|
||||
/*
|
||||
* The sigsuspend and rt_sigsuspend system calls can call do_signal
|
||||
* and thus put the process into the stopped state where we might
|
||||
* want to examine its user state with ptrace. Therefore we need
|
||||
* to save all the nonvolatile registers (r14 - r31) before calling
|
||||
* the C code. Similarly, fork, vfork and clone need the full
|
||||
* register state on the stack so that it can be copied to the child.
|
||||
*/
|
||||
|
||||
_GLOBAL(ppc_fork)
|
||||
bl save_nvgprs
|
||||
bl sys_fork
|
||||
b .Lsyscall_exit
|
||||
|
||||
_GLOBAL(ppc_vfork)
|
||||
bl save_nvgprs
|
||||
bl sys_vfork
|
||||
b .Lsyscall_exit
|
||||
|
||||
_GLOBAL(ppc_clone)
|
||||
bl save_nvgprs
|
||||
bl sys_clone
|
||||
b .Lsyscall_exit
|
||||
|
||||
_GLOBAL(ppc_clone3)
|
||||
bl save_nvgprs
|
||||
bl sys_clone3
|
||||
b .Lsyscall_exit
|
||||
|
||||
_GLOBAL(ppc32_swapcontext)
|
||||
bl save_nvgprs
|
||||
bl compat_sys_swapcontext
|
||||
b .Lsyscall_exit
|
||||
|
||||
_GLOBAL(ppc64_swapcontext)
|
||||
bl save_nvgprs
|
||||
bl sys_swapcontext
|
||||
b .Lsyscall_exit
|
||||
|
||||
_GLOBAL(ppc_switch_endian)
|
||||
bl save_nvgprs
|
||||
bl sys_switch_endian
|
||||
b .Lsyscall_exit
|
||||
|
||||
_GLOBAL(ret_from_fork)
|
||||
bl schedule_tail
|
||||
REST_NVGPRS(r1)
|
||||
|
|
@ -516,6 +459,17 @@ _GLOBAL(ret_from_kernel_thread)
|
|||
li r3,0
|
||||
b .Lsyscall_exit
|
||||
|
||||
/* Save non-volatile GPRs, if not already saved. */
|
||||
_GLOBAL(save_nvgprs)
|
||||
ld r11,_TRAP(r1)
|
||||
andi. r0,r11,1
|
||||
beqlr-
|
||||
SAVE_NVGPRS(r1)
|
||||
clrrdi r0,r11,1
|
||||
std r0,_TRAP(r1)
|
||||
blr
|
||||
_ASM_NOKPROBE_SYMBOL(save_nvgprs);
|
||||
|
||||
#ifdef CONFIG_PPC_BOOK3S_64
|
||||
|
||||
#define FLUSH_COUNT_CACHE \
|
||||
|
|
|
|||
|
|
@ -9,7 +9,9 @@
|
|||
#
|
||||
0 nospu restart_syscall sys_restart_syscall
|
||||
1 nospu exit sys_exit
|
||||
2 nospu fork ppc_fork
|
||||
2 32 fork ppc_fork sys_fork
|
||||
2 64 fork sys_fork
|
||||
2 spu fork sys_ni_syscall
|
||||
3 common read sys_read
|
||||
4 common write sys_write
|
||||
5 common open sys_open compat_sys_open
|
||||
|
|
@ -158,7 +160,9 @@
|
|||
119 32 sigreturn sys_sigreturn compat_sys_sigreturn
|
||||
119 64 sigreturn sys_ni_syscall
|
||||
119 spu sigreturn sys_ni_syscall
|
||||
120 nospu clone ppc_clone
|
||||
120 32 clone ppc_clone sys_clone
|
||||
120 64 clone sys_clone
|
||||
120 spu clone sys_ni_syscall
|
||||
121 common setdomainname sys_setdomainname
|
||||
122 common uname sys_newuname
|
||||
123 common modify_ldt sys_ni_syscall
|
||||
|
|
@ -240,7 +244,9 @@
|
|||
186 spu sendfile sys_sendfile64
|
||||
187 common getpmsg sys_ni_syscall
|
||||
188 common putpmsg sys_ni_syscall
|
||||
189 nospu vfork ppc_vfork
|
||||
189 32 vfork ppc_vfork sys_vfork
|
||||
189 64 vfork sys_vfork
|
||||
189 spu vfork sys_ni_syscall
|
||||
190 common ugetrlimit sys_getrlimit compat_sys_getrlimit
|
||||
191 common readahead sys_readahead compat_sys_readahead
|
||||
192 32 mmap2 sys_mmap2 compat_sys_mmap2
|
||||
|
|
@ -316,8 +322,8 @@
|
|||
248 32 clock_nanosleep sys_clock_nanosleep_time32
|
||||
248 64 clock_nanosleep sys_clock_nanosleep
|
||||
248 spu clock_nanosleep sys_clock_nanosleep
|
||||
249 32 swapcontext ppc_swapcontext ppc32_swapcontext
|
||||
249 64 swapcontext ppc64_swapcontext
|
||||
249 32 swapcontext ppc_swapcontext compat_sys_swapcontext
|
||||
249 64 swapcontext sys_swapcontext
|
||||
249 spu swapcontext sys_ni_syscall
|
||||
250 common tgkill sys_tgkill
|
||||
251 32 utimes sys_utimes_time32
|
||||
|
|
@ -456,7 +462,7 @@
|
|||
361 common bpf sys_bpf
|
||||
362 nospu execveat sys_execveat compat_sys_execveat
|
||||
363 32 switch_endian sys_ni_syscall
|
||||
363 64 switch_endian ppc_switch_endian
|
||||
363 64 switch_endian sys_switch_endian
|
||||
363 spu switch_endian sys_ni_syscall
|
||||
364 common userfaultfd sys_userfaultfd
|
||||
365 common membarrier sys_membarrier
|
||||
|
|
@ -516,6 +522,8 @@
|
|||
432 common fsmount sys_fsmount
|
||||
433 common fspick sys_fspick
|
||||
434 common pidfd_open sys_pidfd_open
|
||||
435 nospu clone3 ppc_clone3
|
||||
435 32 clone3 ppc_clone3 sys_clone3
|
||||
435 64 clone3 sys_clone3
|
||||
435 spu clone3 sys_ni_syscall
|
||||
437 common openat2 sys_openat2
|
||||
438 common pidfd_getfd sys_pidfd_getfd
|
||||
|
|
|
|||
Loading…
Reference in a new issue