From 63f501e07a8557bc8ab79d17ef76ae21df1e395d Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 17 Sep 2021 15:57:12 +0200 Subject: [PATCH] powerpc/8xx: Simplify TLB handling In the old days, TLB handling for 8xx was using tlbie and tlbia instructions directly as much as possible. But commit f048aace29e0 ("powerpc/mm: Add SMP support to no-hash TLB handling") broke that by introducing out-of-line unnecessary complex functions for booke/smp which don't have tlbie/tlbia instructions and require more complex handling. Restore direct use of tlbie and tlbia for 8xx which is never SMP. With this patch we now get c00ecc68 : c00ecc68: 39 00 00 00 li r8,0 c00ecc6c: 81 46 00 00 lwz r10,0(r6) c00ecc70: 91 06 00 00 stw r8,0(r6) c00ecc74: 7c 00 2a 64 tlbie r5,r0 c00ecc78: 7c 00 04 ac hwsync c00ecc7c: 91 43 00 00 stw r10,0(r3) c00ecc80: 4e 80 00 20 blr Before it was c0012880 : c0012880: 2c 03 00 00 cmpwi r3,0 c0012884: 41 82 00 54 beq c00128d8 c0012888: 81 22 00 00 lwz r9,0(r2) c001288c: 81 43 00 20 lwz r10,32(r3) c0012890: 39 29 00 01 addi r9,r9,1 c0012894: 91 22 00 00 stw r9,0(r2) c0012898: 2c 0a 00 00 cmpwi r10,0 c001289c: 41 82 00 10 beq c00128ac c00128a0: 81 2a 01 dc lwz r9,476(r10) c00128a4: 2c 09 ff ff cmpwi r9,-1 c00128a8: 41 82 00 0c beq c00128b4 c00128ac: 7c 00 22 64 tlbie r4,r0 c00128b0: 7c 00 04 ac hwsync c00128b4: 81 22 00 00 lwz r9,0(r2) c00128b8: 39 29 ff ff addi r9,r9,-1 c00128bc: 2c 09 00 00 cmpwi r9,0 c00128c0: 91 22 00 00 stw r9,0(r2) c00128c4: 4c a2 00 20 bclr+ 4,eq c00128c8: 81 22 00 70 lwz r9,112(r2) c00128cc: 71 29 00 04 andi. r9,r9,4 c00128d0: 4d 82 00 20 beqlr c00128d4: 48 65 76 74 b c0669f48 c00128d8: 81 22 00 00 lwz r9,0(r2) c00128dc: 39 29 00 01 addi r9,r9,1 c00128e0: 91 22 00 00 stw r9,0(r2) c00128e4: 4b ff ff c8 b c00128ac ... c00ecdc8 : c00ecdc8: 94 21 ff f0 stwu r1,-16(r1) c00ecdcc: 39 20 00 00 li r9,0 c00ecdd0: 93 c1 00 08 stw r30,8(r1) c00ecdd4: 83 c6 00 00 lwz r30,0(r6) c00ecdd8: 91 26 00 00 stw r9,0(r6) c00ecddc: 93 e1 00 0c stw r31,12(r1) c00ecde0: 7c 08 02 a6 mflr r0 c00ecde4: 7c 7f 1b 78 mr r31,r3 c00ecde8: 7c 83 23 78 mr r3,r4 c00ecdec: 7c a4 2b 78 mr r4,r5 c00ecdf0: 90 01 00 14 stw r0,20(r1) c00ecdf4: 4b f2 5a 8d bl c0012880 c00ecdf8: 93 df 00 00 stw r30,0(r31) c00ecdfc: 7f e3 fb 78 mr r3,r31 c00ece00: 80 01 00 14 lwz r0,20(r1) c00ece04: 83 c1 00 08 lwz r30,8(r1) c00ece08: 83 e1 00 0c lwz r31,12(r1) c00ece0c: 7c 08 03 a6 mtlr r0 c00ece10: 38 21 00 10 addi r1,r1,16 c00ece14: 4e 80 00 20 blr Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/fb324f1c8f2ddb57cf6aad1cea26329558f1c1c0.1631887021.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/nohash/tlbflush.h | 15 +++++++++++++++ arch/powerpc/mm/nohash/tlb.c | 2 ++ 2 files changed, 17 insertions(+) diff --git a/arch/powerpc/include/asm/nohash/tlbflush.h b/arch/powerpc/include/asm/nohash/tlbflush.h index 1edb7243e515..c08d25e3e626 100644 --- a/arch/powerpc/include/asm/nohash/tlbflush.h +++ b/arch/powerpc/include/asm/nohash/tlbflush.h @@ -32,11 +32,26 @@ extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +#ifdef CONFIG_PPC_8xx +static inline void local_flush_tlb_mm(struct mm_struct *mm) +{ + unsigned int pid = READ_ONCE(mm->context.id); + + if (pid != MMU_NO_CONTEXT) + asm volatile ("sync; tlbia; isync" : : : "memory"); +} + +static inline void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) +{ + asm volatile ("tlbie %0; sync" : : "r" (vmaddr) : "memory"); +} +#else extern void local_flush_tlb_mm(struct mm_struct *mm); extern void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); extern void __local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, int tsize, int ind); +#endif #ifdef CONFIG_SMP extern void flush_tlb_mm(struct mm_struct *mm); diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c index fc195b9f524b..89353d4f5604 100644 --- a/arch/powerpc/mm/nohash/tlb.c +++ b/arch/powerpc/mm/nohash/tlb.c @@ -185,6 +185,7 @@ EXPORT_PER_CPU_SYMBOL(next_tlbcam_idx); * processor */ +#ifndef CONFIG_PPC_8xx /* * These are the base non-SMP variants of page and mm flushing */ @@ -218,6 +219,7 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) mmu_get_tsize(mmu_virtual_psize), 0); } EXPORT_SYMBOL(local_flush_tlb_page); +#endif /* * And here are the SMP non-local implementations