mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-14 06:35:12 +00:00
5c810ced36
Add support for out-of-line static calls on PPC32. This change improve performance of calls to global function pointers by using direct calls instead of indirect calls. The trampoline is initialy populated with a 'blr' or branch to target, followed by an unreachable long jump sequence. In order to cater with parallele execution, the trampoline needs to be updated in a way that ensures it remains consistent at all time. This means we can't use the traditional lis/addi to load r12 with the target address, otherwise there would be a window during which the first instruction contains the upper part of the new target address while the second instruction still contains the lower part of the old target address. To avoid that the target address is stored just after the 'bctr' and loaded from there with a single instruction. Then, depending on the target distance, arch_static_call_transform() will either replace the first instruction by a direct 'bl <target>' or 'nop' in order to have the trampoline fall through the long jump sequence. For the special case of __static_call_return0(), to avoid the risk of a far branch, a version of it is inlined at the end of the trampoline. Performancewise the long jump sequence is probably not better than the indirect calls set by GCC when we don't use static calls, but such calls are unlikely to be required on powerpc32: With most configurations the kernel size is far below 32 Mbytes so only modules may happen to be too far. And even modules are likely to be close enough as they are allocated below the kernel core and as close as possible of the kernel text. static_call selftest is running successfully with this change. With this patch, __do_irq() has the following sequence to trace irq entries: c0004a00 <__SCT__tp_func_irq_entry>: c0004a00: 48 00 00 e0 b c0004ae0 <__traceiter_irq_entry> c0004a04: 3d 80 c0 00 lis r12,-16384 c0004a08: 81 8c 4a 1c lwz r12,18972(r12) c0004a0c: 7d 89 03 a6 mtctr r12 c0004a10: 4e 80 04 20 bctr c0004a14: 38 60 00 00 li r3,0 c0004a18: 4e 80 00 20 blr c0004a1c: 00 00 00 00 .long 0x0 ... c0005654 <__do_irq>: ... c0005664: 7c 7f 1b 78 mr r31,r3 ... c00056a0: 81 22 00 00 lwz r9,0(r2) c00056a4: 39 29 00 01 addi r9,r9,1 c00056a8: 91 22 00 00 stw r9,0(r2) c00056ac: 3d 20 c0 af lis r9,-16209 c00056b0: 81 29 74 cc lwz r9,29900(r9) c00056b4: 2c 09 00 00 cmpwi r9,0 c00056b8: 41 82 00 10 beq c00056c8 <__do_irq+0x74> c00056bc: 80 69 00 04 lwz r3,4(r9) c00056c0: 7f e4 fb 78 mr r4,r31 c00056c4: 4b ff f3 3d bl c0004a00 <__SCT__tp_func_irq_entry> Before this patch, __do_irq() was doing the following to trace irq entries: c0005700 <__do_irq>: ... c0005710: 7c 7e 1b 78 mr r30,r3 ... c000574c: 93 e1 00 0c stw r31,12(r1) c0005750: 81 22 00 00 lwz r9,0(r2) c0005754: 39 29 00 01 addi r9,r9,1 c0005758: 91 22 00 00 stw r9,0(r2) c000575c: 3d 20 c0 af lis r9,-16209 c0005760: 83 e9 f4 cc lwz r31,-2868(r9) c0005764: 2c 1f 00 00 cmpwi r31,0 c0005768: 41 82 00 24 beq c000578c <__do_irq+0x8c> c000576c: 81 3f 00 00 lwz r9,0(r31) c0005770: 80 7f 00 04 lwz r3,4(r31) c0005774: 7d 29 03 a6 mtctr r9 c0005778: 7f c4 f3 78 mr r4,r30 c000577c: 4e 80 04 21 bctrl c0005780: 85 3f 00 0c lwzu r9,12(r31) c0005784: 2c 09 00 00 cmpwi r9,0 c0005788: 40 82 ff e4 bne c000576c <__do_irq+0x6c> Behind the fact of now using a direct 'bl' instead of a 'load/mtctr/bctr' sequence, we can also see that we get one less register on the stack. Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/6ec2a7865ed6a5ec54ab46d026785bafe1d837ea.1630484892.git.christophe.leroy@csgroup.eu |
||
|---|---|---|
| .. | ||
| ptrace | ||
| syscalls | ||
| trace | ||
| vdso32 | ||
| vdso64 | ||
| .gitignore | ||
| align.c | ||
| asm-offsets.c | ||
| btext.c | ||
| cacheinfo.c | ||
| cacheinfo.h | ||
| cpu_setup_6xx.S | ||
| cpu_setup_44x.S | ||
| cpu_setup_fsl_booke.S | ||
| cpu_setup_pa6t.S | ||
| cpu_setup_power.c | ||
| cpu_setup_ppc970.S | ||
| cputable.c | ||
| crash_dump.c | ||
| dawr.c | ||
| dbell.c | ||
| dma-iommu.c | ||
| dma-mask.c | ||
| dma-swiotlb.c | ||
| dt_cpu_ftrs.c | ||
| early_32.c | ||
| eeh.c | ||
| eeh_cache.c | ||
| eeh_driver.c | ||
| eeh_event.c | ||
| eeh_pe.c | ||
| eeh_sysfs.c | ||
| entry_32.S | ||
| entry_64.S | ||
| epapr_hcalls.S | ||
| epapr_paravirt.c | ||
| exceptions-64e.S | ||
| exceptions-64s.S | ||
| fadump.c | ||
| firmware.c | ||
| fpu.S | ||
| fsl_booke_entry_mapping.S | ||
| head_8xx.S | ||
| head_32.h | ||
| head_40x.S | ||
| head_44x.S | ||
| head_64.S | ||
| head_book3s_32.S | ||
| head_booke.h | ||
| head_fsl_booke.S | ||
| hw_breakpoint.c | ||
| hw_breakpoint_constraints.c | ||
| idle.c | ||
| idle_6xx.S | ||
| idle_book3e.S | ||
| idle_book3s.S | ||
| idle_e500.S | ||
| ima_arch.c | ||
| interrupt.c | ||
| interrupt_64.S | ||
| io-workarounds.c | ||
| io.c | ||
| iomap.c | ||
| iommu.c | ||
| irq.c | ||
| isa-bridge.c | ||
| jump_label.c | ||
| kdebugfs.c | ||
| kgdb.c | ||
| kprobes-ftrace.c | ||
| kprobes.c | ||
| kvm.c | ||
| kvm_emul.S | ||
| l2cr_6xx.S | ||
| legacy_serial.c | ||
| Makefile | ||
| mce.c | ||
| mce_power.c | ||
| misc.S | ||
| misc_32.S | ||
| misc_64.S | ||
| module.c | ||
| module_32.c | ||
| module_64.c | ||
| msi.c | ||
| note.S | ||
| nvram_64.c | ||
| of_platform.c | ||
| optprobes.c | ||
| optprobes_head.S | ||
| paca.c | ||
| pci-common.c | ||
| pci-hotplug.c | ||
| pci_32.c | ||
| pci_64.c | ||
| pci_dn.c | ||
| pci_of_scan.c | ||
| pmc.c | ||
| ppc32.h | ||
| ppc_save_regs.S | ||
| proc_powerpc.c | ||
| process.c | ||
| prom.c | ||
| prom_init.c | ||
| prom_init_check.sh | ||
| prom_parse.c | ||
| reloc_32.S | ||
| reloc_64.S | ||
| rtas-proc.c | ||
| rtas-rtc.c | ||
| rtas.c | ||
| rtas_flash.c | ||
| rtas_pci.c | ||
| rtasd.c | ||
| secure_boot.c | ||
| security.c | ||
| secvar-ops.c | ||
| secvar-sysfs.c | ||
| setup-common.c | ||
| setup.h | ||
| setup_32.c | ||
| setup_64.c | ||
| signal.c | ||
| signal.h | ||
| signal_32.c | ||
| signal_64.c | ||
| smp-tbsync.c | ||
| smp.c | ||
| stacktrace.c | ||
| static_call.c | ||
| suspend.c | ||
| swsusp.c | ||
| swsusp_32.S | ||
| swsusp_64.c | ||
| swsusp_asm64.S | ||
| swsusp_booke.S | ||
| sys_ppc32.c | ||
| syscalls.c | ||
| sysfs.c | ||
| systbl.S | ||
| systbl_chk.sh | ||
| tau_6xx.c | ||
| time.c | ||
| tm.S | ||
| traps.c | ||
| ucall.S | ||
| udbg.c | ||
| udbg_16550.c | ||
| uprobes.c | ||
| vdso.c | ||
| vdso32_wrapper.S | ||
| vdso64_wrapper.S | ||
| vecemu.c | ||
| vector.S | ||
| vmlinux.lds.S | ||
| watchdog.c | ||