From 2eafc4748bc08c5b9b6ee0b5b65ad20b30f7d704 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 5 Nov 2021 13:50:42 +1000 Subject: powerpc: select CPUMASK_OFFSTACK if NR_CPUS >= 8192 Some core kernel code starts to go beyond the 2048 byte stack size warning at NR_CPUS=8192, so select CPUMASK_OFFSTACK in that case. x86 does similarly for very large NR_CPUS. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20211105035042.1398309-2-npiggin@gmail.com --- arch/powerpc/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc/Kconfig') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index dea74d7717c0..bb5e44e4d7c7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -165,6 +165,7 @@ config PPC select BINFMT_ELF select BUILDTIME_TABLE_SORT select CLONE_BACKWARDS + select CPUMASK_OFFSTACK if NR_CPUS >= 8192 select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN select DMA_OPS_BYPASS if PPC64 select DMA_OPS if PPC64 -- cgit v1.2.3 From 7dfbfb87c243cf08bc2b9cc23699ac207b726458 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Thu, 28 Oct 2021 14:24:04 +0200 Subject: powerpc/ftrace: Activate HAVE_DYNAMIC_FTRACE_WITH_REGS on PPC32 Unlike PPC64, PPC32 doesn't require any special compiler option to get _mcount() call not clobbering registers. Provide ftrace_regs_caller() and ftrace_regs_call() and activate HAVE_DYNAMIC_FTRACE_WITH_REGS. That's heavily copied from ftrace_64_mprofile.S For the time being leave livepatching aside, it will come with following patch. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/1862dc7719855cc2a4eec80920d94c955877557e.1635423081.git.christophe.leroy@csgroup.eu --- arch/powerpc/Kconfig | 4 +- arch/powerpc/kernel/module_32.c | 8 +++ arch/powerpc/kernel/trace/ftrace.c | 16 ++++- arch/powerpc/kernel/trace/ftrace_32.S | 109 +++++++++++++++++++++++++++++++--- 4 files changed, 125 insertions(+), 12 deletions(-) (limited to 'arch/powerpc/Kconfig') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index bb5e44e4d7c7..5c61f3511d5a 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -206,7 +206,7 @@ config PPC select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_STACKOVERFLOW select HAVE_DYNAMIC_FTRACE - select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL + select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL || PPC32 select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU) select HAVE_FAST_GUP @@ -230,7 +230,7 @@ config PPC select HAVE_KPROBES_ON_FTRACE select HAVE_KRETPROBES select HAVE_LD_DEAD_CODE_DATA_ELIMINATION - select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS + select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS && PPC64 select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S) select HAVE_OPTPROBES diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index 5dedd76346b2..a491ad481d85 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -306,6 +306,14 @@ int module_finalize_ftrace(struct module *module, const Elf_Shdr *sechdrs) if (!module->arch.tramp) return -ENOENT; +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + module->arch.tramp_regs = do_plt_call(module->core_layout.base, + (unsigned long)ftrace_regs_caller, + sechdrs, module); + if (!module->arch.tramp_regs) + return -ENOENT; +#endif + return 0; } #endif diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index c1d54c18e912..faa0fa29ac20 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -561,6 +561,8 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) int err; struct ppc_inst op; u32 *ip = (u32 *)rec->ip; + struct module *mod = rec->arch.mod; + unsigned long tramp; /* read where this goes */ if (copy_inst_from_kernel_nofault(&op, ip)) @@ -573,13 +575,23 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) } /* If we never set up a trampoline to ftrace_caller, then bail */ - if (!rec->arch.mod->arch.tramp) { +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + if (!mod->arch.tramp || !mod->arch.tramp_regs) { +#else + if (!mod->arch.tramp) { +#endif pr_err("No ftrace trampoline\n"); return -EINVAL; } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + if (rec->flags & FTRACE_FL_REGS) + tramp = mod->arch.tramp_regs; + else +#endif + tramp = mod->arch.tramp; /* create the branch to the trampoline */ - err = create_branch(&op, ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK); + err = create_branch(&op, ip, tramp, BRANCH_SET_LINK); if (err) { pr_err("REL24 out of range!\n"); return -EINVAL; diff --git a/arch/powerpc/kernel/trace/ftrace_32.S b/arch/powerpc/kernel/trace/ftrace_32.S index c7d57124cc59..0a02c0cb12d9 100644 --- a/arch/powerpc/kernel/trace/ftrace_32.S +++ b/arch/powerpc/kernel/trace/ftrace_32.S @@ -9,6 +9,7 @@ #include #include #include +#include _GLOBAL(mcount) _GLOBAL(_mcount) @@ -29,17 +30,21 @@ _GLOBAL(ftrace_caller) MCOUNT_SAVE_FRAME /* r3 ends up with link register */ subi r3, r3, MCOUNT_INSN_SIZE + lis r5,function_trace_op@ha + lwz r5,function_trace_op@l(r5) + li r6, 0 .globl ftrace_call ftrace_call: bl ftrace_stub nop + MCOUNT_RESTORE_FRAME +ftrace_caller_common: #ifdef CONFIG_FUNCTION_GRAPH_TRACER .globl ftrace_graph_call ftrace_graph_call: b ftrace_graph_stub _GLOBAL(ftrace_graph_stub) #endif - MCOUNT_RESTORE_FRAME /* old link register ends up in ctr reg */ bctr @@ -47,16 +52,92 @@ _GLOBAL(ftrace_graph_stub) _GLOBAL(ftrace_stub) blr +_GLOBAL(ftrace_regs_caller) + /* Save the original return address in A's stack frame */ + stw r0,LRSAVE(r1) + + /* Create our stack frame + pt_regs */ + stwu r1,-INT_FRAME_SIZE(r1) + + /* Save all gprs to pt_regs */ + stw r0, GPR0(r1) + stmw r2, GPR2(r1) + + /* Save previous stack pointer (r1) */ + addi r8, r1, INT_FRAME_SIZE + stw r8, GPR1(r1) + + /* Load special regs for save below */ + mfmsr r8 + mfctr r9 + mfxer r10 + mfcr r11 + + /* Get the _mcount() call site out of LR */ + mflr r7 + /* Save it as pt_regs->nip */ + stw r7, _NIP(r1) + /* Save the read LR in pt_regs->link */ + stw r0, _LINK(r1) + + lis r3,function_trace_op@ha + lwz r5,function_trace_op@l(r3) + + /* Calculate ip from nip-4 into r3 for call below */ + subi r3, r7, MCOUNT_INSN_SIZE + + /* Put the original return address in r4 as parent_ip */ + mr r4, r0 + + /* Save special regs */ + stw r8, _MSR(r1) + stw r9, _CTR(r1) + stw r10, _XER(r1) + stw r11, _CCR(r1) + + /* Load &pt_regs in r6 for call below */ + addi r6, r1, STACK_FRAME_OVERHEAD + + /* ftrace_call(r3, r4, r5, r6) */ +.globl ftrace_regs_call +ftrace_regs_call: + bl ftrace_stub + nop + + /* Load ctr with the possibly modified NIP */ + lwz r3, _NIP(r1) + mtctr r3 + + /* Restore gprs */ + lmw r2, GPR2(r1) + + /* Restore possibly modified LR */ + lwz r0, _LINK(r1) + mtlr r0 + + /* Pop our stack frame */ + addi r1, r1, INT_FRAME_SIZE + + b ftrace_caller_common + #ifdef CONFIG_FUNCTION_GRAPH_TRACER _GLOBAL(ftrace_graph_caller) + stwu r1,-48(r1) + stw r3, 12(r1) + stw r4, 16(r1) + stw r5, 20(r1) + stw r6, 24(r1) + stw r7, 28(r1) + stw r8, 32(r1) + stw r9, 36(r1) + stw r10,40(r1) + addi r5, r1, 48 - /* load r4 with local address */ - lwz r4, 44(r1) + mfctr r4 /* ftrace_caller has moved local addr here */ + stw r4, 44(r1) + mflr r3 /* ftrace_caller has restored LR from stack */ subi r4, r4, MCOUNT_INSN_SIZE - /* Grab the LR out of the caller stack frame */ - lwz r3,52(r1) - bl prepare_ftrace_return nop @@ -65,9 +146,21 @@ _GLOBAL(ftrace_graph_caller) * Change the LR in the callers stack frame to this. */ stw r3,52(r1) + mtlr r3 + lwz r0,44(r1) + mtctr r0 + + lwz r3, 12(r1) + lwz r4, 16(r1) + lwz r5, 20(r1) + lwz r6, 24(r1) + lwz r7, 28(r1) + lwz r8, 32(r1) + lwz r9, 36(r1) + lwz r10,40(r1) + + addi r1, r1, 48 - MCOUNT_RESTORE_FRAME - /* old link register ends up in ctr reg */ bctr _GLOBAL(return_to_handler) -- cgit v1.2.3 From 20626177c9de726c48802c15e8635cc154645588 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 2 Dec 2021 00:41:47 +1000 Subject: powerpc: make memremap_compat_align 64s-only memremap_compat_align is only relevant when ZONE_DEVICE is selected. ZONE_DEVICE depends on ARCH_HAS_PTE_DEVMAP, which is only selected by PPC_BOOK3S_64. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20211201144153.2456614-13-npiggin@gmail.com --- arch/powerpc/Kconfig | 2 +- arch/powerpc/mm/book3s64/pgtable.c | 20 ++++++++++++++++++++ arch/powerpc/mm/ioremap.c | 20 -------------------- 3 files changed, 21 insertions(+), 21 deletions(-) (limited to 'arch/powerpc/Kconfig') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 5c61f3511d5a..e3e281a35327 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -129,7 +129,7 @@ config PPC select ARCH_HAS_KCOV select ARCH_HAS_MEMBARRIER_CALLBACKS select ARCH_HAS_MEMBARRIER_SYNC_CORE - select ARCH_HAS_MEMREMAP_COMPAT_ALIGN + select ARCH_HAS_MEMREMAP_COMPAT_ALIGN if PPC_BOOK3S_64 select ARCH_HAS_MMIOWB if PPC64 select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PHYS_TO_DMA diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 0e6254160673..d3b01f6ba530 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -528,3 +528,23 @@ static int __init pgtable_debugfs_setup(void) return 0; } arch_initcall(pgtable_debugfs_setup); + +#ifdef CONFIG_ZONE_DEVICE +/* + * Override the generic version in mm/memremap.c. + * + * With hash translation, the direct-map range is mapped with just one + * page size selected by htab_init_page_sizes(). Consult + * mmu_psize_defs[] to determine the minimum page size alignment. +*/ +unsigned long memremap_compat_align(void) +{ + if (!radix_enabled()) { + unsigned int shift = mmu_psize_defs[mmu_linear_psize].shift; + return max(SUBSECTION_SIZE, 1UL << shift); + } + + return SUBSECTION_SIZE; +} +EXPORT_SYMBOL_GPL(memremap_compat_align); +#endif diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c index 57342154d2b0..4f12504fb405 100644 --- a/arch/powerpc/mm/ioremap.c +++ b/arch/powerpc/mm/ioremap.c @@ -98,23 +98,3 @@ void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size, return NULL; } - -#ifdef CONFIG_ZONE_DEVICE -/* - * Override the generic version in mm/memremap.c. - * - * With hash translation, the direct-map range is mapped with just one - * page size selected by htab_init_page_sizes(). Consult - * mmu_psize_defs[] to determine the minimum page size alignment. -*/ -unsigned long memremap_compat_align(void) -{ - unsigned int shift = mmu_psize_defs[mmu_linear_psize].shift; - - if (radix_enabled()) - return SUBSECTION_SIZE; - return max(SUBSECTION_SIZE, 1UL << shift); - -} -EXPORT_SYMBOL_GPL(memremap_compat_align); -#endif -- cgit v1.2.3 From c28573744b74eb6de19add503d6a986795c4c137 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 2 Dec 2021 00:41:51 +1000 Subject: powerpc/64s: Make hash MMU support configurable This adds Kconfig selection which allows 64s hash MMU support to be disabled. It can be disabled if radix support is enabled, the minimum supported CPU type is POWER9 (or higher), and KVM is not selected. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20211201144153.2456614-17-npiggin@gmail.com --- arch/powerpc/Kconfig | 3 ++- arch/powerpc/include/asm/mmu.h | 16 +++++++++++++--- arch/powerpc/kernel/dt_cpu_ftrs.c | 14 ++++++++++---- arch/powerpc/kvm/Kconfig | 1 + arch/powerpc/mm/init_64.c | 13 +++++++++++-- arch/powerpc/platforms/Kconfig.cputype | 28 ++++++++++++++++++++++++++-- arch/powerpc/platforms/cell/Kconfig | 1 + arch/powerpc/platforms/maple/Kconfig | 1 + arch/powerpc/platforms/microwatt/Kconfig | 2 +- arch/powerpc/platforms/pasemi/Kconfig | 1 + arch/powerpc/platforms/powermac/Kconfig | 1 + arch/powerpc/platforms/powernv/Kconfig | 2 +- drivers/misc/cxl/Kconfig | 1 + drivers/misc/lkdtm/Makefile | 2 +- 14 files changed, 71 insertions(+), 15 deletions(-) (limited to 'arch/powerpc/Kconfig') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index e3e281a35327..2555563efff0 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -846,7 +846,7 @@ config FORCE_MAX_ZONEORDER config PPC_SUBPAGE_PROT bool "Support setting protections for 4k subpages (subpage_prot syscall)" default n - depends on PPC_BOOK3S_64 && PPC_64K_PAGES + depends on PPC_64S_HASH_MMU && PPC_64K_PAGES help This option adds support for system call to allow user programs to set access permissions (read/write, readonly, or no access) @@ -944,6 +944,7 @@ config PPC_MEM_KEYS prompt "PowerPC Memory Protection Keys" def_bool y depends on PPC_BOOK3S_64 + depends on PPC_64S_HASH_MMU select ARCH_USES_HIGH_VMA_FLAGS select ARCH_HAS_PKEYS help diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 8abe8e42e045..5f41565a1e5d 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -157,7 +157,7 @@ DECLARE_PER_CPU(int, next_tlbcam_idx); enum { MMU_FTRS_POSSIBLE = -#if defined(CONFIG_PPC_BOOK3S_64) || defined(CONFIG_PPC_BOOK3S_604) +#if defined(CONFIG_PPC_BOOK3S_604) MMU_FTR_HPTE_TABLE | #endif #ifdef CONFIG_PPC_8xx @@ -184,15 +184,18 @@ enum { MMU_FTR_USE_TLBRSRV | MMU_FTR_USE_PAIRED_MAS | #endif #ifdef CONFIG_PPC_BOOK3S_64 + MMU_FTR_KERNEL_RO | +#ifdef CONFIG_PPC_64S_HASH_MMU MMU_FTR_NO_SLBIE_B | MMU_FTR_16M_PAGE | MMU_FTR_TLBIEL | MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_CI_LARGE_PAGE | MMU_FTR_1T_SEGMENT | MMU_FTR_TLBIE_CROP_VA | - MMU_FTR_KERNEL_RO | MMU_FTR_68_BIT_VA | + MMU_FTR_68_BIT_VA | MMU_FTR_HPTE_TABLE | #endif #ifdef CONFIG_PPC_RADIX_MMU MMU_FTR_TYPE_RADIX | MMU_FTR_GTSE | #endif /* CONFIG_PPC_RADIX_MMU */ +#endif #ifdef CONFIG_PPC_KUAP MMU_FTR_BOOK3S_KUAP | #endif /* CONFIG_PPC_KUAP */ @@ -224,6 +227,13 @@ enum { #define MMU_FTRS_ALWAYS MMU_FTR_TYPE_FSL_E #endif +/* BOOK3S_64 options */ +#if defined(CONFIG_PPC_RADIX_MMU) && !defined(CONFIG_PPC_64S_HASH_MMU) +#define MMU_FTRS_ALWAYS MMU_FTR_TYPE_RADIX +#elif !defined(CONFIG_PPC_RADIX_MMU) && defined(CONFIG_PPC_64S_HASH_MMU) +#define MMU_FTRS_ALWAYS MMU_FTR_HPTE_TABLE +#endif + #ifndef MMU_FTRS_ALWAYS #define MMU_FTRS_ALWAYS 0 #endif @@ -329,7 +339,7 @@ static __always_inline bool radix_enabled(void) return mmu_has_feature(MMU_FTR_TYPE_RADIX); } -static inline bool early_radix_enabled(void) +static __always_inline bool early_radix_enabled(void) { return early_mmu_has_feature(MMU_FTR_TYPE_RADIX); } diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index d2b35fb9181d..1ac8d7357195 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -273,6 +273,9 @@ static int __init feat_enable_mmu_hash(struct dt_cpu_feature *f) { u64 lpcr; + if (!IS_ENABLED(CONFIG_PPC_64S_HASH_MMU)) + return 0; + lpcr = mfspr(SPRN_LPCR); lpcr &= ~LPCR_ISL; @@ -292,6 +295,9 @@ static int __init feat_enable_mmu_hash_v3(struct dt_cpu_feature *f) { u64 lpcr; + if (!IS_ENABLED(CONFIG_PPC_64S_HASH_MMU)) + return 0; + lpcr = mfspr(SPRN_LPCR); lpcr &= ~(LPCR_ISL | LPCR_UPRT | LPCR_HR); mtspr(SPRN_LPCR, lpcr); @@ -305,15 +311,15 @@ static int __init feat_enable_mmu_hash_v3(struct dt_cpu_feature *f) static int __init feat_enable_mmu_radix(struct dt_cpu_feature *f) { -#ifdef CONFIG_PPC_RADIX_MMU + if (!IS_ENABLED(CONFIG_PPC_RADIX_MMU)) + return 0; + + cur_cpu_spec->mmu_features |= MMU_FTR_KERNEL_RO; cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX; - cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE; cur_cpu_spec->mmu_features |= MMU_FTR_GTSE; cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU; return 1; -#endif - return 0; } static int __init feat_enable_dscr(struct dt_cpu_feature *f) diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 6a58532300c5..f947b77386a9 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -69,6 +69,7 @@ config KVM_BOOK3S_64 select KVM_BOOK3S_64_HANDLER select KVM select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE + select PPC_64S_HASH_MMU select SPAPR_TCE_IOMMU if IOMMU_SUPPORT && (PPC_PSERIES || PPC_POWERNV) help Support running unmodified book3s_64 and book3s_32 guest kernels diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 3e5f9ac9dded..35f46bf54281 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -472,8 +472,12 @@ void __init mmu_early_init_devtree(void) bool hvmode = !!(mfmsr() & MSR_HV); /* Disable radix mode based on kernel command line. */ - if (disable_radix) - cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; + if (disable_radix) { + if (IS_ENABLED(CONFIG_PPC_64S_HASH_MMU)) + cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; + else + pr_warn("WARNING: Ignoring cmdline option disable_radix\n"); + } of_scan_flat_dt(dt_scan_mmu_pid_width, NULL); if (hvmode && !mmu_lpid_bits) { @@ -498,6 +502,7 @@ void __init mmu_early_init_devtree(void) if (early_radix_enabled()) { radix__early_init_devtree(); + /* * We have finalized the translation we are going to use by now. * Radix mode is not limited by RMA / VRMA addressing. @@ -507,5 +512,9 @@ void __init mmu_early_init_devtree(void) memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE); } else hash__early_init_devtree(); + + if (!(cur_cpu_spec->mmu_features & MMU_FTR_HPTE_TABLE) && + !(cur_cpu_spec->mmu_features & MMU_FTR_TYPE_RADIX)) + panic("kernel does not support any MMU type offered by platform"); } #endif /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index a208997ade88..7ca07df1c374 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -105,9 +105,9 @@ config PPC_BOOK3S_64 select HAVE_MOVE_PMD select HAVE_MOVE_PUD select IRQ_WORK - select PPC_MM_SLICES select PPC_HAVE_KUEP select PPC_HAVE_KUAP + select PPC_64S_HASH_MMU if !PPC_RADIX_MMU config PPC_BOOK3E_64 bool "Embedded processors" @@ -130,11 +130,13 @@ choice config GENERIC_CPU bool "Generic (POWER4 and above)" depends on PPC64 && !CPU_LITTLE_ENDIAN + select PPC_64S_HASH_MMU if PPC_BOOK3S_64 config GENERIC_CPU bool "Generic (POWER8 and above)" depends on PPC64 && CPU_LITTLE_ENDIAN select ARCH_HAS_FAST_MULTIPLIER + select PPC_64S_HASH_MMU config GENERIC_CPU bool "Generic 32 bits powerpc" @@ -143,24 +145,29 @@ config GENERIC_CPU config CELL_CPU bool "Cell Broadband Engine" depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN + select PPC_64S_HASH_MMU config POWER5_CPU bool "POWER5" depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN + select PPC_64S_HASH_MMU config POWER6_CPU bool "POWER6" depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN + select PPC_64S_HASH_MMU config POWER7_CPU bool "POWER7" depends on PPC_BOOK3S_64 select ARCH_HAS_FAST_MULTIPLIER + select PPC_64S_HASH_MMU config POWER8_CPU bool "POWER8" depends on PPC_BOOK3S_64 select ARCH_HAS_FAST_MULTIPLIER + select PPC_64S_HASH_MMU config POWER9_CPU bool "POWER9" @@ -364,6 +371,22 @@ config SPE If in doubt, say Y here. +config PPC_64S_HASH_MMU + bool "Hash MMU Support" + depends on PPC_BOOK3S_64 + select PPC_MM_SLICES + default y + help + Enable support for the Power ISA Hash style MMU. This is implemented + by all IBM Power and other 64-bit Book3S CPUs before ISA v3.0. The + OpenPOWER ISA does not mandate the hash MMU and some CPUs do not + implement it (e.g., Microwatt). + + Note that POWER9 PowerVM platforms only support the hash + MMU. From POWER10 radix is also supported by PowerVM. + + If you're unsure, say Y. + config PPC_RADIX_MMU bool "Radix MMU Support" depends on PPC_BOOK3S_64 @@ -375,7 +398,8 @@ config PPC_RADIX_MMU you can probably disable this. config PPC_RADIX_MMU_DEFAULT - bool "Default to using the Radix MMU when possible" + bool "Default to using the Radix MMU when possible" if PPC_64S_HASH_MMU + depends on PPC_BOOK3S_64 depends on PPC_RADIX_MMU default y help diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index db4465c51b56..34669b060f36 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 config PPC_CELL + select PPC_64S_HASH_MMU if PPC64 bool config PPC_CELL_COMMON diff --git a/arch/powerpc/platforms/maple/Kconfig b/arch/powerpc/platforms/maple/Kconfig index 7fd84311ade5..4c058cc57c90 100644 --- a/arch/powerpc/platforms/maple/Kconfig +++ b/arch/powerpc/platforms/maple/Kconfig @@ -9,6 +9,7 @@ config PPC_MAPLE select GENERIC_TBSYNC select PPC_UDBG_16550 select PPC_970_NAP + select PPC_64S_HASH_MMU select PPC_HASH_MMU_NATIVE select PPC_RTAS select MMIO_NVRAM diff --git a/arch/powerpc/platforms/microwatt/Kconfig b/arch/powerpc/platforms/microwatt/Kconfig index 62b51e37fc05..823192e9d38a 100644 --- a/arch/powerpc/platforms/microwatt/Kconfig +++ b/arch/powerpc/platforms/microwatt/Kconfig @@ -5,7 +5,7 @@ config PPC_MICROWATT select PPC_XICS select PPC_ICS_NATIVE select PPC_ICP_NATIVE - select PPC_HASH_MMU_NATIVE + select PPC_HASH_MMU_NATIVE if PPC_64S_HASH_MMU select PPC_UDBG_16550 select ARCH_RANDOM help diff --git a/arch/powerpc/platforms/pasemi/Kconfig b/arch/powerpc/platforms/pasemi/Kconfig index bc7137353a7f..85ae18ddd911 100644 --- a/arch/powerpc/platforms/pasemi/Kconfig +++ b/arch/powerpc/platforms/pasemi/Kconfig @@ -5,6 +5,7 @@ config PPC_PASEMI select MPIC select FORCE_PCI select PPC_UDBG_16550 + select PPC_64S_HASH_MMU select PPC_HASH_MMU_NATIVE select MPIC_BROKEN_REGREAD help diff --git a/arch/powerpc/platforms/powermac/Kconfig b/arch/powerpc/platforms/powermac/Kconfig index 2b56df145b82..130707ec9f99 100644 --- a/arch/powerpc/platforms/powermac/Kconfig +++ b/arch/powerpc/platforms/powermac/Kconfig @@ -6,6 +6,7 @@ config PPC_PMAC select FORCE_PCI select PPC_INDIRECT_PCI if PPC32 select PPC_MPC106 if PPC32 + select PPC_64S_HASH_MMU if PPC64 select PPC_HASH_MMU_NATIVE select ZONE_DMA if PPC32 default y diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index cd754e116184..161dfe024085 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -2,7 +2,7 @@ config PPC_POWERNV depends on PPC64 && PPC_BOOK3S bool "IBM PowerNV (Non-Virtualized) platform support" - select PPC_HASH_MMU_NATIVE + select PPC_HASH_MMU_NATIVE if PPC_64S_HASH_MMU select PPC_XICS select PPC_ICP_NATIVE select PPC_XIVE_NATIVE diff --git a/drivers/misc/cxl/Kconfig b/drivers/misc/cxl/Kconfig index 51aecafdcbdf..5efc4151bf58 100644 --- a/drivers/misc/cxl/Kconfig +++ b/drivers/misc/cxl/Kconfig @@ -6,6 +6,7 @@ config CXL_BASE bool select PPC_COPRO_BASE + select PPC_64S_HASH_MMU config CXL tristate "Support for IBM Coherent Accelerators (CXL)" diff --git a/drivers/misc/lkdtm/Makefile b/drivers/misc/lkdtm/Makefile index aa12097668d3..83a7baf5df82 100644 --- a/drivers/misc/lkdtm/Makefile +++ b/drivers/misc/lkdtm/Makefile @@ -11,7 +11,7 @@ lkdtm-$(CONFIG_LKDTM) += usercopy.o lkdtm-$(CONFIG_LKDTM) += stackleak.o lkdtm-$(CONFIG_LKDTM) += cfi.o lkdtm-$(CONFIG_LKDTM) += fortify.o -lkdtm-$(CONFIG_PPC_BOOK3S_64) += powerpc.o +lkdtm-$(CONFIG_PPC_64S_HASH_MMU) += powerpc.o KASAN_SANITIZE_rodata.o := n KASAN_SANITIZE_stackleak.o := n -- cgit v1.2.3 From 387e220a2e5e630794e1f5219ed6f11e56271c21 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 2 Dec 2021 00:41:52 +1000 Subject: powerpc/64s: Move hash MMU support code under CONFIG_PPC_64S_HASH_MMU Compiling out hash support code when CONFIG_PPC_64S_HASH_MMU=n saves 128kB kernel image size (90kB text) on powernv_defconfig minus KVM, 350kB on pseries_defconfig minus KVM, 40kB on a tiny config. Signed-off-by: Nicholas Piggin [mpe: Fixup defined(ARCH_HAS_MEMREMAP_COMPAT_ALIGN), which needs CONFIG. Fix radix_enabled() use in setup_initial_memory_limit(). Add some stubs to reduce number of ifdefs.] Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20211201144153.2456614-18-npiggin@gmail.com --- arch/powerpc/Kconfig | 2 +- arch/powerpc/include/asm/book3s/64/mmu-hash.h | 8 +++++- arch/powerpc/include/asm/book3s/64/mmu.h | 21 ++++++++++++-- arch/powerpc/include/asm/book3s/64/tlbflush-hash.h | 6 ++++ arch/powerpc/include/asm/book3s/pgtable.h | 4 +++ arch/powerpc/include/asm/mmu_context.h | 2 ++ arch/powerpc/include/asm/paca.h | 8 ++++++ arch/powerpc/kernel/asm-offsets.c | 2 ++ arch/powerpc/kernel/entry_64.S | 4 +-- arch/powerpc/kernel/exceptions-64s.S | 16 +++++++++++ arch/powerpc/kernel/mce.c | 2 +- arch/powerpc/kernel/mce_power.c | 10 +++++-- arch/powerpc/kernel/paca.c | 18 +++++------- arch/powerpc/kernel/process.c | 13 +++++---- arch/powerpc/kernel/prom.c | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- arch/powerpc/kexec/core_64.c | 4 +-- arch/powerpc/kexec/ranges.c | 2 +- arch/powerpc/mm/book3s64/Makefile | 15 ++++++---- arch/powerpc/mm/book3s64/hugetlbpage.c | 2 ++ arch/powerpc/mm/book3s64/mmu_context.c | 32 ++++++++++++++++++---- arch/powerpc/mm/book3s64/pgtable.c | 2 +- arch/powerpc/mm/book3s64/radix_pgtable.c | 4 ++- arch/powerpc/mm/copro_fault.c | 2 ++ arch/powerpc/mm/ptdump/Makefile | 2 +- arch/powerpc/platforms/powernv/idle.c | 2 ++ arch/powerpc/platforms/powernv/setup.c | 2 ++ arch/powerpc/platforms/pseries/lpar.c | 11 ++++++-- arch/powerpc/platforms/pseries/lparcfg.c | 2 +- arch/powerpc/platforms/pseries/mobility.c | 4 +++ arch/powerpc/platforms/pseries/pseries.h | 5 ++++ arch/powerpc/platforms/pseries/ras.c | 2 ++ arch/powerpc/platforms/pseries/setup.c | 6 ++-- arch/powerpc/xmon/xmon.c | 8 ++++-- drivers/misc/lkdtm/core.c | 2 +- 35 files changed, 172 insertions(+), 57 deletions(-) (limited to 'arch/powerpc/Kconfig') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2555563efff0..0631c9241af3 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -129,7 +129,7 @@ config PPC select ARCH_HAS_KCOV select ARCH_HAS_MEMBARRIER_CALLBACKS select ARCH_HAS_MEMBARRIER_SYNC_CORE - select ARCH_HAS_MEMREMAP_COMPAT_ALIGN if PPC_BOOK3S_64 + select ARCH_HAS_MEMREMAP_COMPAT_ALIGN if PPC_64S_HASH_MMU select ARCH_HAS_MMIOWB if PPC64 select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PHYS_TO_DMA diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 3004f3323144..21f780942911 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -523,8 +523,14 @@ void slb_save_contents(struct slb_entry *slb_ptr); void slb_dump_contents(struct slb_entry *slb_ptr); extern void slb_vmalloc_update(void); -extern void slb_set_size(u16 size); void preload_new_slb_context(unsigned long start, unsigned long sp); + +#ifdef CONFIG_PPC_64S_HASH_MMU +void slb_set_size(u16 size); +#else +static inline void slb_set_size(u16 size) { } +#endif + #endif /* __ASSEMBLY__ */ /* diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index a265c5618ce8..7fee46e50377 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -105,7 +105,9 @@ typedef struct { * from EA and new context ids to build the new VAs. */ mm_context_id_t id; +#ifdef CONFIG_PPC_64S_HASH_MMU mm_context_id_t extended_id[TASK_SIZE_USER64/TASK_CONTEXT_SIZE]; +#endif }; /* Number of bits in the mm_cpumask */ @@ -117,7 +119,9 @@ typedef struct { /* Number of user space windows opened in process mm_context */ atomic_t vas_windows; +#ifdef CONFIG_PPC_64S_HASH_MMU struct hash_mm_context *hash_context; +#endif void __user *vdso; /* @@ -140,6 +144,7 @@ typedef struct { #endif } mm_context_t; +#ifdef CONFIG_PPC_64S_HASH_MMU static inline u16 mm_ctx_user_psize(mm_context_t *ctx) { return ctx->hash_context->user_psize; @@ -200,8 +205,15 @@ static inline struct subpage_prot_table *mm_ctx_subpage_prot(mm_context_t *ctx) extern int mmu_linear_psize; extern int mmu_virtual_psize; extern int mmu_vmalloc_psize; -extern int mmu_vmemmap_psize; extern int mmu_io_psize; +#else /* CONFIG_PPC_64S_HASH_MMU */ +#ifdef CONFIG_PPC_64K_PAGES +#define mmu_virtual_psize MMU_PAGE_64K +#else +#define mmu_virtual_psize MMU_PAGE_4K +#endif +#endif +extern int mmu_vmemmap_psize; /* MMU initialization */ void mmu_early_init_devtree(void); @@ -240,8 +252,9 @@ static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base, * know which translations we will pick. Hence go with hash * restrictions. */ - return hash__setup_initial_memory_limit(first_memblock_base, - first_memblock_size); + if (!early_radix_enabled()) + hash__setup_initial_memory_limit(first_memblock_base, + first_memblock_size); } #ifdef CONFIG_PPC_PSERIES @@ -262,6 +275,7 @@ static inline void radix_init_pseries(void) { } void cleanup_cpu_mmu_context(void); #endif +#ifdef CONFIG_PPC_64S_HASH_MMU static inline int get_user_context(mm_context_t *ctx, unsigned long ea) { int index = ea >> MAX_EA_BITS_PER_CONTEXT; @@ -281,6 +295,7 @@ static inline unsigned long get_user_vsid(mm_context_t *ctx, return get_vsid(context, ea, ssize); } +#endif #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_MMU_H_ */ diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h index 3b95769739c7..8b762f282190 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h @@ -112,8 +112,14 @@ static inline void hash__flush_tlb_kernel_range(unsigned long start, struct mmu_gather; extern void hash__tlb_flush(struct mmu_gather *tlb); +void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr); + +#ifdef CONFIG_PPC_64S_HASH_MMU /* Private function for use by PCI IO mapping code */ extern void __flush_hash_table_range(unsigned long start, unsigned long end); extern void flush_tlb_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr); +#else +static inline void __flush_hash_table_range(unsigned long start, unsigned long end) { } +#endif #endif /* _ASM_POWERPC_BOOK3S_64_TLBFLUSH_HASH_H */ diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h index ad130e15a126..e8269434ecbe 100644 --- a/arch/powerpc/include/asm/book3s/pgtable.h +++ b/arch/powerpc/include/asm/book3s/pgtable.h @@ -25,6 +25,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); #define __HAVE_PHYS_MEM_ACCESS_PROT +#if defined(CONFIG_PPC32) || defined(CONFIG_PPC_64S_HASH_MMU) /* * This gets called at the end of handling a page fault, when * the kernel has put a new PTE into the page table for the process. @@ -35,6 +36,9 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, * waiting for the inevitable extra hash-table miss exception. */ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); +#else +static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) {} +#endif #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 9ba6b585337f..e46394d27785 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -75,6 +75,7 @@ extern void hash__reserve_context_id(int id); extern void __destroy_context(int context_id); static inline void mmu_context_init(void) { } +#ifdef CONFIG_PPC_64S_HASH_MMU static inline int alloc_extended_context(struct mm_struct *mm, unsigned long ea) { @@ -100,6 +101,7 @@ static inline bool need_extra_context(struct mm_struct *mm, unsigned long ea) return true; return false; } +#endif #else extern void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next, diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index dc05a862e72a..295573a82c66 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -97,7 +97,9 @@ struct paca_struct { /* this becomes non-zero. */ u8 kexec_state; /* set when kexec down has irqs off */ #ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU struct slb_shadow *slb_shadow_ptr; +#endif struct dtl_entry *dispatch_log; struct dtl_entry *dispatch_log_end; #endif @@ -110,6 +112,7 @@ struct paca_struct { /* used for most interrupts/exceptions */ u64 exgen[EX_SIZE] __attribute__((aligned(0x80))); +#ifdef CONFIG_PPC_64S_HASH_MMU /* SLB related definitions */ u16 vmalloc_sllp; u8 slb_cache_ptr; @@ -120,6 +123,7 @@ struct paca_struct { u32 slb_used_bitmap; /* Bitmaps for first 32 SLB entries. */ u32 slb_kern_bitmap; u32 slb_cache[SLB_CACHE_ENTRIES]; +#endif #endif /* CONFIG_PPC_BOOK3S_64 */ #ifdef CONFIG_PPC_BOOK3E @@ -149,6 +153,7 @@ struct paca_struct { #endif /* CONFIG_PPC_BOOK3E */ #ifdef CONFIG_PPC_BOOK3S +#ifdef CONFIG_PPC_64S_HASH_MMU #ifdef CONFIG_PPC_MM_SLICES unsigned char mm_ctx_low_slices_psize[BITS_PER_LONG / BITS_PER_BYTE]; unsigned char mm_ctx_high_slices_psize[SLICE_ARRAY_SIZE]; @@ -156,6 +161,7 @@ struct paca_struct { u16 mm_ctx_user_psize; u16 mm_ctx_sllp; #endif +#endif #endif /* @@ -268,9 +274,11 @@ struct paca_struct { #endif /* CONFIG_PPC_PSERIES */ #ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU /* Capture SLB related old contents in MCE handler. */ struct slb_entry *mce_faulty_slbs; u16 slb_save_cache_ptr; +#endif #endif /* CONFIG_PPC_BOOK3S_64 */ #ifdef CONFIG_STACKPROTECTOR unsigned long canary; diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index cc05522f50bf..b823f484c640 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -218,10 +218,12 @@ int main(void) OFFSET(PACA_EXGEN, paca_struct, exgen); OFFSET(PACA_EXMC, paca_struct, exmc); OFFSET(PACA_EXNMI, paca_struct, exnmi); +#ifdef CONFIG_PPC_64S_HASH_MMU OFFSET(PACA_SLBSHADOWPTR, paca_struct, slb_shadow_ptr); OFFSET(SLBSHADOW_STACKVSID, slb_shadow, save_area[SLB_NUM_BOLTED - 1].vsid); OFFSET(SLBSHADOW_STACKESID, slb_shadow, save_area[SLB_NUM_BOLTED - 1].esid); OFFSET(SLBSHADOW_SAVEAREA, slb_shadow, save_area); +#endif OFFSET(LPPACA_PMCINUSE, lppaca, pmcregs_in_use); #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE OFFSET(PACA_PMCINUSE, paca_struct, pmcregs_in_use); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 70cff7b49e17..9581906b5ee9 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -180,7 +180,7 @@ _GLOBAL(_switch) #endif ld r8,KSP(r4) /* new stack pointer */ -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU BEGIN_MMU_FTR_SECTION b 2f END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) @@ -232,7 +232,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) slbmte r7,r0 isync 2: -#endif /* CONFIG_PPC_BOOK3S_64 */ +#endif /* CONFIG_PPC_64S_HASH_MMU */ clrrdi r7, r8, THREAD_SHIFT /* base of new stack */ /* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 2acd7e66694e..a30f563bc7a8 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1367,11 +1367,15 @@ EXC_COMMON_BEGIN(data_access_common) addi r3,r1,STACK_FRAME_OVERHEAD andis. r0,r4,DSISR_DABRMATCH@h bne- 1f +#ifdef CONFIG_PPC_64S_HASH_MMU BEGIN_MMU_FTR_SECTION bl do_hash_fault MMU_FTR_SECTION_ELSE bl do_page_fault ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) +#else + bl do_page_fault +#endif b interrupt_return_srr 1: bl do_break @@ -1414,6 +1418,7 @@ EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80) EXC_VIRT_END(data_access_slb, 0x4380, 0x80) EXC_COMMON_BEGIN(data_access_slb_common) GEN_COMMON data_access_slb +#ifdef CONFIG_PPC_64S_HASH_MMU BEGIN_MMU_FTR_SECTION /* HPT case, do SLB fault */ addi r3,r1,STACK_FRAME_OVERHEAD @@ -1426,6 +1431,9 @@ MMU_FTR_SECTION_ELSE /* Radix case, access is outside page table range */ li r3,-EFAULT ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) +#else + li r3,-EFAULT +#endif std r3,RESULT(r1) addi r3,r1,STACK_FRAME_OVERHEAD bl do_bad_segment_interrupt @@ -1460,11 +1468,15 @@ EXC_VIRT_END(instruction_access, 0x4400, 0x80) EXC_COMMON_BEGIN(instruction_access_common) GEN_COMMON instruction_access addi r3,r1,STACK_FRAME_OVERHEAD +#ifdef CONFIG_PPC_64S_HASH_MMU BEGIN_MMU_FTR_SECTION bl do_hash_fault MMU_FTR_SECTION_ELSE bl do_page_fault ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) +#else + bl do_page_fault +#endif b interrupt_return_srr @@ -1494,6 +1506,7 @@ EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80) EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80) EXC_COMMON_BEGIN(instruction_access_slb_common) GEN_COMMON instruction_access_slb +#ifdef CONFIG_PPC_64S_HASH_MMU BEGIN_MMU_FTR_SECTION /* HPT case, do SLB fault */ addi r3,r1,STACK_FRAME_OVERHEAD @@ -1506,6 +1519,9 @@ MMU_FTR_SECTION_ELSE /* Radix case, access is outside page table range */ li r3,-EFAULT ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) +#else + li r3,-EFAULT +#endif std r3,RESULT(r1) addi r3,r1,STACK_FRAME_OVERHEAD bl do_bad_segment_interrupt diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index fd829f7f25a4..2503dd4713b9 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -586,7 +586,7 @@ void machine_check_print_event_info(struct machine_check_event *evt, mc_error_class[evt->error_class] : "Unknown"; printk("%sMCE: CPU%d: %s\n", level, evt->cpu, subtype); -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU /* Display faulty slb contents for SLB errors. */ if (evt->error_type == MCE_ERROR_TYPE_SLB && !in_guest) slb_dump_contents(local_paca->mce_faulty_slbs); diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index cf5263b648fc..a48ff18d6d65 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -77,7 +77,7 @@ static bool mce_in_guest(void) } /* flush SLBs and reload */ -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU void flush_and_reload_slb(void) { if (early_radix_enabled()) @@ -99,7 +99,7 @@ void flush_and_reload_slb(void) void flush_erat(void) { -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU if (!early_cpu_has_feature(CPU_FTR_ARCH_300)) { flush_and_reload_slb(); return; @@ -114,7 +114,7 @@ void flush_erat(void) static int mce_flush(int what) { -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU if (what == MCE_FLUSH_SLB) { flush_and_reload_slb(); return 1; @@ -499,8 +499,10 @@ static int mce_handle_ierror(struct pt_regs *regs, unsigned long srr1, /* attempt to correct the error */ switch (table[i].error_type) { case MCE_ERROR_TYPE_SLB: +#ifdef CONFIG_PPC_64S_HASH_MMU if (local_paca->in_mce == 1) slb_save_contents(local_paca->mce_faulty_slbs); +#endif handled = mce_flush(MCE_FLUSH_SLB); break; case MCE_ERROR_TYPE_ERAT: @@ -588,8 +590,10 @@ static int mce_handle_derror(struct pt_regs *regs, /* attempt to correct the error */ switch (table[i].error_type) { case MCE_ERROR_TYPE_SLB: +#ifdef CONFIG_PPC_64S_HASH_MMU if (local_paca->in_mce == 1) slb_save_contents(local_paca->mce_faulty_slbs); +#endif if (mce_flush(MCE_FLUSH_SLB)) handled = 1; break; diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 4208b4044d12..39da688a9455 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -139,8 +139,7 @@ static struct lppaca * __init new_lppaca(int cpu, unsigned long limit) } #endif /* CONFIG_PPC_PSERIES */ -#ifdef CONFIG_PPC_BOOK3S_64 - +#ifdef CONFIG_PPC_64S_HASH_MMU /* * 3 persistent SLBs are allocated here. The buffer will be zero * initially, hence will all be invaild until we actually write them. @@ -169,8 +168,7 @@ static struct slb_shadow * __init new_slb_shadow(int cpu, unsigned long limit) return s; } - -#endif /* CONFIG_PPC_BOOK3S_64 */ +#endif /* CONFIG_PPC_64S_HASH_MMU */ #ifdef CONFIG_PPC_PSERIES /** @@ -226,7 +224,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) new_paca->kexec_state = KEXEC_STATE_NONE; new_paca->__current = &init_task; new_paca->data_offset = 0xfeeeeeeeeeeeeeeeULL; -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU new_paca->slb_shadow_ptr = NULL; #endif @@ -307,7 +305,7 @@ void __init allocate_paca(int cpu) #ifdef CONFIG_PPC_PSERIES paca->lppaca_ptr = new_lppaca(cpu, limit); #endif -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU paca->slb_shadow_ptr = new_slb_shadow(cpu, limit); #endif #ifdef CONFIG_PPC_PSERIES @@ -328,7 +326,7 @@ void __init free_unused_pacas(void) paca_nr_cpu_ids = nr_cpu_ids; paca_ptrs_size = new_ptrs_size; -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU if (early_radix_enabled()) { /* Ugly fixup, see new_slb_shadow() */ memblock_phys_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr), @@ -341,9 +339,9 @@ void __init free_unused_pacas(void) paca_ptrs_size + paca_struct_size, nr_cpu_ids); } +#ifdef CONFIG_PPC_64S_HASH_MMU void copy_mm_to_paca(struct mm_struct *mm) { -#ifdef CONFIG_PPC_BOOK3S mm_context_t *context = &mm->context; #ifdef CONFIG_PPC_MM_SLICES @@ -356,7 +354,5 @@ void copy_mm_to_paca(struct mm_struct *mm) get_paca()->mm_ctx_user_psize = context->user_psize; get_paca()->mm_ctx_sllp = context->sllp; #endif -#else /* !CONFIG_PPC_BOOK3S */ - return; -#endif } +#endif /* CONFIG_PPC_64S_HASH_MMU */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 5d2333d2a283..a64cfbb85ca2 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1240,7 +1240,7 @@ struct task_struct *__switch_to(struct task_struct *prev, { struct thread_struct *new_thread, *old_thread; struct task_struct *last; -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU struct ppc64_tlb_batch *batch; #endif @@ -1249,7 +1249,7 @@ struct task_struct *__switch_to(struct task_struct *prev, WARN_ON(!irqs_disabled()); -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU batch = this_cpu_ptr(&ppc64_tlb_batch); if (batch->active) { current_thread_info()->local_flags |= _TLF_LAZY_MMU; @@ -1328,6 +1328,7 @@ struct task_struct *__switch_to(struct task_struct *prev, */ #ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU /* * This applies to a process that was context switched while inside * arch_enter_lazy_mmu_mode(), to re-activate the batch that was @@ -1339,6 +1340,7 @@ struct task_struct *__switch_to(struct task_struct *prev, batch = this_cpu_ptr(&ppc64_tlb_batch); batch->active = 1; } +#endif /* * Math facilities are masked out of the child MSR in copy_thread. @@ -1689,7 +1691,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) static void setup_ksp_vsid(struct task_struct *p, unsigned long sp) { -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU unsigned long sp_vsid; unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp; @@ -2333,10 +2335,9 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) * the heap, we can put it above 1TB so it is backed by a 1TB * segment. Otherwise the heap will be in the bottom 1TB * which always uses 256MB segments and this may result in a - * performance penalty. We don't need to worry about radix. For - * radix, mmu_highuser_ssize remains unchanged from 256MB. + * performance penalty. */ - if (!is_32bit_task() && (mmu_highuser_ssize == MMU_SEGSIZE_1T)) + if (!radix_enabled() && !is_32bit_task() && (mmu_highuser_ssize == MMU_SEGSIZE_1T)) base = max_t(unsigned long, mm->brk, 1UL << SID_SHIFT_1T); #endif diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 2e67588f6f6e..75678ff04dd7 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -231,7 +231,7 @@ static void __init check_cpu_pa_features(unsigned long node) ibm_pa_features, ARRAY_SIZE(ibm_pa_features)); } -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU static void __init init_mmu_slb_size(unsigned long node) { const __be32 *slb_size_ptr; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 9a493796ce66..703a2e6ab08d 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -886,7 +886,7 @@ void __init setup_per_cpu_areas(void) atom_size = SZ_1M; } else if (radix_enabled()) { atom_size = PAGE_SIZE; - } else { + } else if (IS_ENABLED(CONFIG_PPC_64S_HASH_MMU)) { /* * Linear mapping is one of 4K, 1M and 16M. For 4K, no need * to group units. For larger mappings, use 1M atom which diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index 66678518b938..635b5fc30b53 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -378,7 +378,7 @@ void default_machine_kexec(struct kimage *image) /* NOTREACHED */ } -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU /* Values we need to export to the second kernel via the device tree. */ static unsigned long htab_base; static unsigned long htab_size; @@ -420,4 +420,4 @@ static int __init export_htab_values(void) return 0; } late_initcall(export_htab_values); -#endif /* CONFIG_PPC_BOOK3S_64 */ +#endif /* CONFIG_PPC_64S_HASH_MMU */ diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c index 6b81c852feab..563e9989a5bf 100644 --- a/arch/powerpc/kexec/ranges.c +++ b/arch/powerpc/kexec/ranges.c @@ -296,7 +296,7 @@ int add_initrd_mem_range(struct crash_mem **mem_ranges) return ret; } -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU /** * add_htab_mem_range - Adds htab range to the given memory ranges list, * if it exists diff --git a/arch/powerpc/mm/book3s64/Makefile b/arch/powerpc/mm/book3s64/Makefile index 501efadb287f..2d50cac499c5 100644 --- a/arch/powerpc/mm/book3s64/Makefile +++ b/arch/powerpc/mm/book3s64/Makefile @@ -2,20 +2,23 @@ ccflags-y := $(NO_MINIMAL_TOC) +obj-y += mmu_context.o pgtable.o trace.o +ifdef CONFIG_PPC_64S_HASH_MMU CFLAGS_REMOVE_slb.o = $(CC_FLAGS_FTRACE) - -obj-y += hash_pgtable.o hash_utils.o slb.o \ - mmu_context.o pgtable.o hash_tlb.o trace.o +obj-y += hash_pgtable.o hash_utils.o hash_tlb.o slb.o obj-$(CONFIG_PPC_HASH_MMU_NATIVE) += hash_native.o -obj-$(CONFIG_PPC_RADIX_MMU) += radix_pgtable.o radix_tlb.o obj-$(CONFIG_PPC_4K_PAGES) += hash_4k.o obj-$(CONFIG_PPC_64K_PAGES) += hash_64k.o +obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += hash_hugepage.o +obj-$(CONFIG_PPC_SUBPAGE_PROT) += subpage_prot.o +endif + obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o + +obj-$(CONFIG_PPC_RADIX_MMU) += radix_pgtable.o radix_tlb.o ifdef CONFIG_HUGETLB_PAGE obj-$(CONFIG_PPC_RADIX_MMU) += radix_hugetlbpage.o endif -obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += hash_hugepage.o -obj-$(CONFIG_PPC_SUBPAGE_PROT) += subpage_prot.o obj-$(CONFIG_SPAPR_TCE_IOMMU) += iommu_api.o obj-$(CONFIG_PPC_PKEY) += pkeys.o diff --git a/arch/powerpc/mm/book3s64/hugetlbpage.c b/arch/powerpc/mm/book3s64/hugetlbpage.c index a688e1324ae5..95b2a283fd6e 100644 --- a/arch/powerpc/mm/book3s64/hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/hugetlbpage.c @@ -16,6 +16,7 @@ unsigned int hpage_shift; EXPORT_SYMBOL(hpage_shift); +#ifdef CONFIG_PPC_64S_HASH_MMU int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, pte_t *ptep, unsigned long trap, unsigned long flags, int ssize, unsigned int shift, unsigned int mmu_psize) @@ -122,6 +123,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid, *ptep = __pte(new_pte & ~H_PAGE_BUSY); return 0; } +#endif pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c index c10fc8a72fb3..24aa953c9311 100644 --- a/arch/powerpc/mm/book3s64/mmu_context.c +++ b/arch/powerpc/mm/book3s64/mmu_context.c @@ -31,6 +31,7 @@ static int alloc_context_id(int min_id, int max_id) return ida_alloc_range(&mmu_context_ida, min_id, max_id, GFP_KERNEL); } +#ifdef CONFIG_PPC_64S_HASH_MMU void hash__reserve_context_id(int id) { int result = ida_alloc_range(&mmu_context_ida, id, id, GFP_KERNEL); @@ -50,7 +51,9 @@ int hash__alloc_context_id(void) return alloc_context_id(MIN_USER_CONTEXT, max); } EXPORT_SYMBOL_GPL(hash__alloc_context_id); +#endif +#ifdef CONFIG_PPC_64S_HASH_MMU static int realloc_context_ids(mm_context_t *ctx) { int i, id; @@ -150,6 +153,13 @@ void hash__setup_new_exec(void) slb_setup_new_exec(); } +#else +static inline int hash__init_new_context(struct mm_struct *mm) +{ + BUILD_BUG(); + return 0; +} +#endif static int radix__init_new_context(struct mm_struct *mm) { @@ -175,7 +185,9 @@ static int radix__init_new_context(struct mm_struct *mm) */ asm volatile("ptesync;isync" : : : "memory"); +#ifdef CONFIG_PPC_64S_HASH_MMU mm->context.hash_context = NULL; +#endif return index; } @@ -213,14 +225,22 @@ EXPORT_SYMBOL_GPL(__destroy_context); static void destroy_contexts(mm_context_t *ctx) { - int index, context_id; + if (radix_enabled()) { + ida_free(&mmu_context_ida, ctx->id); + } else { +#ifdef CONFIG_PPC_64S_HASH_MMU + int index, context_id; - for (index = 0; index < ARRAY_SIZE(ctx->extended_id); index++) { - context_id = ctx->extended_id[index]; - if (context_id) - ida_free(&mmu_context_ida, context_id); + for (index = 0; index < ARRAY_SIZE(ctx->extended_id); index++) { + context_id = ctx->extended_id[index]; + if (context_id) + ida_free(&mmu_context_ida, context_id); + } + kfree(ctx->hash_context); +#else + BUILD_BUG(); // radix_enabled() should be constant true +#endif } - kfree(ctx->hash_context); } static void pmd_frag_destroy(void *pmd_frag) diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index d3b01f6ba530..79ce3c22a29d 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -529,7 +529,7 @@ static int __init pgtable_debugfs_setup(void) } arch_initcall(pgtable_debugfs_setup); -#ifdef CONFIG_ZONE_DEVICE +#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_ARCH_HAS_MEMREMAP_COMPAT_ALIGN) /* * Override the generic version in mm/memremap.c. * diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 1f4afc37843d..3c4f0ebe5df8 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -334,7 +334,7 @@ static void __init radix_init_pgtable(void) u64 i; /* We don't support slb for radix */ - mmu_slb_size = 0; + slb_set_size(0); /* * Create the linear mapping @@ -565,6 +565,7 @@ void __init radix__early_init_mmu(void) { unsigned long lpcr; +#ifdef CONFIG_PPC_64S_HASH_MMU #ifdef CONFIG_PPC_64K_PAGES /* PAGE_SIZE mappings */ mmu_virtual_psize = MMU_PAGE_64K; @@ -581,6 +582,7 @@ void __init radix__early_init_mmu(void) mmu_vmemmap_psize = MMU_PAGE_2M; } else mmu_vmemmap_psize = mmu_virtual_psize; +#endif #endif /* * initialize page table size diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index 8acd00178956..c1cb21a00884 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -82,6 +82,7 @@ out_unlock: } EXPORT_SYMBOL_GPL(copro_handle_mm_fault); +#ifdef CONFIG_PPC_64S_HASH_MMU int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb) { u64 vsid, vsidkey; @@ -146,3 +147,4 @@ void copro_flush_all_slbs(struct mm_struct *mm) cxl_slbia(mm); } EXPORT_SYMBOL_GPL(copro_flush_all_slbs); +#endif diff --git a/arch/powerpc/mm/ptdump/Makefile b/arch/powerpc/mm/ptdump/Makefile index 4050cbb55acf..b533caaf0910 100644 --- a/arch/powerpc/mm/ptdump/Makefile +++ b/arch/powerpc/mm/ptdump/Makefile @@ -10,5 +10,5 @@ obj-$(CONFIG_PPC_BOOK3S_64) += book3s64.o ifdef CONFIG_PTDUMP_DEBUGFS obj-$(CONFIG_PPC_BOOK3S_32) += bats.o segment_regs.o -obj-$(CONFIG_PPC_BOOK3S_64) += hashpagetable.o +obj-$(CONFIG_PPC_64S_HASH_MMU) += hashpagetable.o endif diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 95458fd9572c..885ef229aba1 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -491,12 +491,14 @@ subcore_woken: mtspr(SPRN_SPRG3, local_paca->sprg_vdso); +#ifdef CONFIG_PPC_64S_HASH_MMU /* * The SLB has to be restored here, but it sometimes still * contains entries, so the __ variant must be used to prevent * multi hits. */ __slb_restore_bolted_realmode(); +#endif return srr1; } diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 5ef6b8afb3d0..f37d6524a24d 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -211,6 +211,7 @@ static void __init pnv_init(void) #endif add_preferred_console("hvc", 0, NULL); +#ifdef CONFIG_PPC_64S_HASH_MMU if (!radix_enabled()) { size_t size = sizeof(struct slb_entry) * mmu_slb_size; int i; @@ -223,6 +224,7 @@ static void __init pnv_init(void) cpu_to_node(i)); } } +#endif } static void __init pnv_init_IRQ(void) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 06d6a824c0dc..fac5d86777db 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -58,6 +58,7 @@ EXPORT_SYMBOL(plpar_hcall); EXPORT_SYMBOL(plpar_hcall9); EXPORT_SYMBOL(plpar_hcall_norets); +#ifdef CONFIG_PPC_64S_HASH_MMU /* * H_BLOCK_REMOVE supported block size for this page size in segment who's base * page size is that page size. @@ -66,6 +67,7 @@ EXPORT_SYMBOL(plpar_hcall_norets); * page size. */ static int hblkrm_size[MMU_PAGE_COUNT][MMU_PAGE_COUNT] __ro_after_init; +#endif /* * Due to the involved complexity, and that the current hypervisor is only @@ -689,7 +691,7 @@ void vpa_init(int cpu) return; } -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU /* * PAPR says this feature is SLB-Buffer but firmware never * reports that. All SPLPAR support SLB shadow buffer. @@ -702,7 +704,7 @@ void vpa_init(int cpu) "cpu %d (hw %d) of area %lx failed with %ld\n", cpu, hwcpu, addr, ret); } -#endif /* CONFIG_PPC_BOOK3S_64 */ +#endif /* CONFIG_PPC_64S_HASH_MMU */ /* * Register dispatch trace log, if one has been allocated. @@ -740,6 +742,8 @@ static int pseries_lpar_register_process_table(unsigned long base, return rc; } +#ifdef CONFIG_PPC_64S_HASH_MMU + static long pSeries_lpar_hpte_insert(unsigned long hpte_group, unsigned long vpn, unsigned long pa, unsigned long rflags, unsigned long vflags, @@ -1730,6 +1734,7 @@ void __init hpte_init_pseries(void) if (cpu_has_feature(CPU_FTR_ARCH_300)) pseries_lpar_register_process_table(0, 0, 0); } +#endif /* CONFIG_PPC_64S_HASH_MMU */ #ifdef CONFIG_PPC_RADIX_MMU void radix_init_pseries(void) @@ -1932,6 +1937,7 @@ int h_get_mpp_x(struct hvcall_mpp_x_data *mpp_x_data) return rc; } +#ifdef CONFIG_PPC_64S_HASH_MMU static unsigned long vsid_unscramble(unsigned long vsid, int ssize) { unsigned long protovsid; @@ -1992,6 +1998,7 @@ static int __init reserve_vrma_context_id(void) return 0; } machine_device_initcall(pseries, reserve_vrma_context_id); +#endif #ifdef CONFIG_DEBUG_FS /* debugfs file interface for vpa data */ diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index 3354c00914fa..c7940fcfc911 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -531,7 +531,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) seq_printf(m, "shared_processor_mode=%d\n", lppaca_shared_proc(get_lppaca())); -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU if (!radix_enabled()) seq_printf(m, "slb_size=%d\n", mmu_slb_size); #endif diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 210a37a065fb..85033f392c78 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -451,11 +451,15 @@ static void prod_others(void) static u16 clamp_slb_size(void) { +#ifdef CONFIG_PPC_64S_HASH_MMU u16 prev = mmu_slb_size; slb_set_size(SLB_MIN_SIZE); return prev; +#else + return 0; +#endif } static int do_suspend(void) diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 3544778e06d0..b4c63c481f33 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -113,6 +113,11 @@ int dlpar_workqueue_init(void); extern u32 pseries_security_flavor; void pseries_setup_security_mitigations(void); + +#ifdef CONFIG_PPC_64S_HASH_MMU void pseries_lpar_read_hblkrm_characteristics(void); +#else +static inline void pseries_lpar_read_hblkrm_characteristics(void) { } +#endif #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 56092dccfdb8..74c9b1b5bc66 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -526,6 +526,7 @@ static int mce_handle_err_realmode(int disposition, u8 error_type) disposition = RTAS_DISP_FULLY_RECOVERED; break; case MC_ERROR_TYPE_SLB: +#ifdef CONFIG_PPC_64S_HASH_MMU /* * Store the old slb content in paca before flushing. * Print this when we go to virtual mode. @@ -538,6 +539,7 @@ static int mce_handle_err_realmode(int disposition, u8 error_type) slb_save_contents(local_paca->mce_faulty_slbs); flush_and_reload_slb(); disposition = RTAS_DISP_FULLY_RECOVERED; +#endif break; default: break; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 8a62af5b9c24..7f69237d4fa4 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -112,7 +112,7 @@ static void __init fwnmi_init(void) u8 *mce_data_buf; unsigned int i; int nr_cpus = num_possible_cpus(); -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU struct slb_entry *slb_ptr; size_t size; #endif @@ -152,7 +152,7 @@ static void __init fwnmi_init(void) (RTAS_ERROR_LOG_MAX * i); } -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU if (!radix_enabled()) { /* Allocate per cpu area to save old slb contents during MCE */ size = sizeof(struct slb_entry) * mmu_slb_size * nr_cpus; @@ -801,7 +801,9 @@ static void __init pSeries_setup_arch(void) fwnmi_init(); pseries_setup_security_mitigations(); +#ifdef CONFIG_PPC_64S_HASH_MMU pseries_lpar_read_hblkrm_characteristics(); +#endif /* By default, only probe PCI (can be overridden by rtas_pci) */ pci_add_flags(PCI_PROBE_ONLY); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 83100c6524cc..0c65dc01c325 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1159,7 +1159,7 @@ cmds(struct pt_regs *excp) case 'P': show_tasks(); break; -#ifdef CONFIG_PPC_BOOK3S +#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_64S_HASH_MMU) case 'u': dump_segments(); break; @@ -2614,7 +2614,7 @@ static void dump_tracing(void) static void dump_one_paca(int cpu) { struct paca_struct *p; -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU int i = 0; #endif @@ -2656,6 +2656,7 @@ static void dump_one_paca(int cpu) DUMP(p, cpu_start, "%#-*x"); DUMP(p, kexec_state, "%#-*x"); #ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU if (!early_radix_enabled()) { for (i = 0; i < SLB_NUM_BOLTED; i++) { u64 esid, vsid; @@ -2683,6 +2684,7 @@ static void dump_one_paca(int cpu) 22, "slb_cache", i, p->slb_cache[i]); } } +#endif DUMP(p, rfi_flush_fallback_area, "%-*px"); #endif @@ -3746,7 +3748,7 @@ static void xmon_print_symbol(unsigned long address, const char *mid, printf("%s", after); } -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU void dump_segments(void) { int i; diff --git a/drivers/misc/lkdtm/core.c b/drivers/misc/lkdtm/core.c index 609d9ee2acc0..82fb276f7e09 100644 --- a/drivers/misc/lkdtm/core.c +++ b/drivers/misc/lkdtm/core.c @@ -182,7 +182,7 @@ static const struct crashtype crashtypes[] = { CRASHTYPE(FORTIFIED_SUBOBJECT), CRASHTYPE(FORTIFIED_STRSCPY), CRASHTYPE(DOUBLE_FAULT), -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU CRASHTYPE(PPC_SLB_MULTIHIT), #endif }; -- cgit v1.2.3 From 7ecd19cfdfcbb625cc059dfa5b267d2436732c1c Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 19 Jan 2022 18:07:41 -0800 Subject: mm: percpu: generalize percpu related config Patch series "mm: percpu: Cleanup percpu first chunk function". When supporting page mapping percpu first chunk allocator on arm64, we found there are lots of duplicated codes in percpu embed/page first chunk allocator. This patchset is aimed to cleanup them and should no function change. The currently supported status about 'embed' and 'page' in Archs shows below, embed: NEED_PER_CPU_PAGE_FIRST_CHUNK page: NEED_PER_CPU_EMBED_FIRST_CHUNK embed page ------------------------ arm64 Y Y mips Y N powerpc Y Y riscv Y N sparc Y Y x86 Y Y ------------------------ There are two interfaces about percpu first chunk allocator, extern int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn); + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); extern int __init pcpu_page_first_chunk(size_t reserved_size, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn, - pcpu_fc_populate_pte_fn_t populate_pte_fn); + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); The pcpu_fc_alloc_fn_t/pcpu_fc_free_fn_t is killed, we provide generic pcpu_fc_alloc() and pcpu_fc_free() function, which are called in the pcpu_embed/page_first_chunk(). 1) For pcpu_embed_first_chunk(), pcpu_fc_cpu_to_node_fn_t is needed to be provided when archs supported NUMA. 2) For pcpu_page_first_chunk(), the pcpu_fc_populate_pte_fn_t is killed too, a generic pcpu_populate_pte() which marked '__weak' is provided, if you need a different function to populate pte on the arch(like x86), please provide its own implementation. [1] https://github.com/kevin78/linux.git percpu-cleanup This patch (of 4): The HAVE_SETUP_PER_CPU_AREA/NEED_PER_CPU_EMBED_FIRST_CHUNK/ NEED_PER_CPU_PAGE_FIRST_CHUNK/USE_PERCPU_NUMA_NODE_ID configs, which have duplicate definitions on platforms that subscribe it. Move them into mm, drop these redundant definitions and instead just select it on applicable platforms. Link: https://lkml.kernel.org/r/20211216112359.103822-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20211216112359.103822-2-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Acked-by: Catalin Marinas [arm64] Cc: Will Deacon Cc: Thomas Bogendoerfer Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Christoph Lameter Cc: Dennis Zhou Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/Kconfig | 20 ++++---------------- arch/ia64/Kconfig | 9 ++------- arch/mips/Kconfig | 10 ++-------- arch/powerpc/Kconfig | 17 ++++------------- arch/riscv/Kconfig | 10 ++-------- arch/sparc/Kconfig | 12 +++--------- arch/x86/Kconfig | 17 ++++------------- mm/Kconfig | 12 ++++++++++++ 8 files changed, 33 insertions(+), 74 deletions(-) (limited to 'arch/powerpc/Kconfig') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index c4207cf9bb17..4ff73299f8a9 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1135,6 +1135,10 @@ config NUMA select GENERIC_ARCH_NUMA select ACPI_NUMA if ACPI select OF_NUMA + select HAVE_SETUP_PER_CPU_AREA + select NEED_PER_CPU_EMBED_FIRST_CHUNK + select NEED_PER_CPU_PAGE_FIRST_CHUNK + select USE_PERCPU_NUMA_NODE_ID help Enable NUMA (Non-Uniform Memory Access) support. @@ -1151,22 +1155,6 @@ config NODES_SHIFT Specify the maximum number of NUMA Nodes available on the target system. Increases memory reserved to accommodate various tables. -config USE_PERCPU_NUMA_NODE_ID - def_bool y - depends on NUMA - -config HAVE_SETUP_PER_CPU_AREA - def_bool y - depends on NUMA - -config NEED_PER_CPU_EMBED_FIRST_CHUNK - def_bool y - depends on NUMA - -config NEED_PER_CPU_PAGE_FIRST_CHUNK - def_bool y - depends on NUMA - source "kernel/Kconfig.hz" config ARCH_SPARSEMEM_ENABLE diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 1e33666fa679..703952819e10 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -32,6 +32,7 @@ config IA64 select HAVE_FTRACE_MCOUNT_RECORD select HAVE_DYNAMIC_FTRACE if (!ITANIUM) select HAVE_FUNCTION_TRACER + select HAVE_SETUP_PER_CPU_AREA select TTY select HAVE_ARCH_TRACEHOOK select HAVE_VIRT_CPU_ACCOUNTING @@ -88,9 +89,6 @@ config GENERIC_CALIBRATE_DELAY bool default y -config HAVE_SETUP_PER_CPU_AREA - def_bool y - config DMI bool default y @@ -292,6 +290,7 @@ config NUMA bool "NUMA support" depends on !FLATMEM select SMP + select USE_PERCPU_NUMA_NODE_ID help Say Y to compile the kernel to support NUMA (Non-Uniform Memory Access). This option is for configuring high-end multiprocessor @@ -311,10 +310,6 @@ config HAVE_ARCH_NODEDATA_EXTENSION def_bool y depends on NUMA -config USE_PERCPU_NUMA_NODE_ID - def_bool y - depends on NUMA - config HAVE_MEMORYLESS_NODES def_bool NUMA diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 0215dc1529e9..9e77659641a2 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2666,6 +2666,8 @@ config NUMA bool "NUMA Support" depends on SYS_SUPPORTS_NUMA select SMP + select HAVE_SETUP_PER_CPU_AREA + select NEED_PER_CPU_EMBED_FIRST_CHUNK help Say Y to compile the kernel to support NUMA (Non-Uniform Memory Access). This option improves performance on systems with more @@ -2676,14 +2678,6 @@ config NUMA config SYS_SUPPORTS_NUMA bool -config HAVE_SETUP_PER_CPU_AREA - def_bool y - depends on NUMA - -config NEED_PER_CPU_EMBED_FIRST_CHUNK - def_bool y - depends on NUMA - config RELOCATABLE bool "Relocatable kernel" depends on SYS_SUPPORTS_RELOCATABLE diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index dea74d7717c0..8badd39854a0 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -55,15 +55,6 @@ config ARCH_MMAP_RND_COMPAT_BITS_MIN default 9 if PPC_16K_PAGES # 9 = 23 (8MB) - 14 (16K) default 11 # 11 = 23 (8MB) - 12 (4K) -config HAVE_SETUP_PER_CPU_AREA - def_bool PPC64 - -config NEED_PER_CPU_EMBED_FIRST_CHUNK - def_bool y if PPC64 - -config NEED_PER_CPU_PAGE_FIRST_CHUNK - def_bool y if PPC64 - config NR_IRQS int "Number of virtual interrupt numbers" range 32 1048576 @@ -240,6 +231,7 @@ config PPC select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE select HAVE_RSEQ + select HAVE_SETUP_PER_CPU_AREA if PPC64 select HAVE_SOFTIRQ_ON_OWN_STACK select HAVE_STACKPROTECTOR if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2) select HAVE_STACKPROTECTOR if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13) @@ -254,6 +246,8 @@ config PPC select MMU_GATHER_RCU_TABLE_FREE select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE if PPC64 || NOT_COHERENT_CACHE + select NEED_PER_CPU_EMBED_FIRST_CHUNK if PPC64 + select NEED_PER_CPU_PAGE_FIRST_CHUNK if PPC64 select NEED_SG_DMA_LENGTH select OF select OF_DMA_DEFAULT_COHERENT if !NOT_COHERENT_CACHE @@ -659,6 +653,7 @@ config NUMA bool "NUMA Memory Allocation and Scheduler Support" depends on PPC64 && SMP default y if PPC_PSERIES || PPC_POWERNV + select USE_PERCPU_NUMA_NODE_ID help Enable NUMA (Non-Uniform Memory Access) support. @@ -672,10 +667,6 @@ config NODES_SHIFT default "4" depends on NUMA -config USE_PERCPU_NUMA_NODE_ID - def_bool y - depends on NUMA - config HAVE_MEMORYLESS_NODES def_bool y depends on NUMA diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 821252b65f89..bf66bcbc5a39 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -334,6 +334,8 @@ config NUMA select GENERIC_ARCH_NUMA select OF_NUMA select ARCH_SUPPORTS_NUMA_BALANCING + select USE_PERCPU_NUMA_NODE_ID + select NEED_PER_CPU_EMBED_FIRST_CHUNK help Enable NUMA (Non-Uniform Memory Access) support. @@ -349,14 +351,6 @@ config NODES_SHIFT Specify the maximum number of NUMA Nodes available on the target system. Increases memory reserved to accommodate various tables. -config USE_PERCPU_NUMA_NODE_ID - def_bool y - depends on NUMA - -config NEED_PER_CPU_EMBED_FIRST_CHUNK - def_bool y - depends on NUMA - config RISCV_ISA_C bool "Emit compressed instructions when building Linux" default y diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 66fc08646be5..1cab1b284f1a 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -97,6 +97,9 @@ config SPARC64 select PCI_DOMAINS if PCI select ARCH_HAS_GIGANTIC_PAGE select HAVE_SOFTIRQ_ON_OWN_STACK + select HAVE_SETUP_PER_CPU_AREA + select NEED_PER_CPU_EMBED_FIRST_CHUNK + select NEED_PER_CPU_PAGE_FIRST_CHUNK config ARCH_PROC_KCORE_TEXT def_bool y @@ -123,15 +126,6 @@ config AUDIT_ARCH bool default y -config HAVE_SETUP_PER_CPU_AREA - def_bool y if SPARC64 - -config NEED_PER_CPU_EMBED_FIRST_CHUNK - def_bool y if SPARC64 - -config NEED_PER_CPU_PAGE_FIRST_CHUNK - def_bool y if SPARC64 - config MMU bool default y diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5c2ccb85f2ef..1275bab8be2c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -239,6 +239,7 @@ config X86 select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION select HAVE_FUNCTION_ARG_ACCESS_API + select HAVE_SETUP_PER_CPU_AREA select HAVE_SOFTIRQ_ON_OWN_STACK select HAVE_STACKPROTECTOR if CC_HAS_SANE_STACKPROTECTOR select HAVE_STACK_VALIDATION if X86_64 @@ -252,6 +253,8 @@ config X86 select HAVE_GENERIC_VDSO select HOTPLUG_SMT if SMP select IRQ_FORCED_THREADING + select NEED_PER_CPU_EMBED_FIRST_CHUNK + select NEED_PER_CPU_PAGE_FIRST_CHUNK select NEED_SG_DMA_LENGTH select PCI_DOMAINS if PCI select PCI_LOCKLESS_CONFIG if PCI @@ -331,15 +334,6 @@ config ARCH_HAS_CPU_RELAX config ARCH_HAS_FILTER_PGPROT def_bool y -config HAVE_SETUP_PER_CPU_AREA - def_bool y - -config NEED_PER_CPU_EMBED_FIRST_CHUNK - def_bool y - -config NEED_PER_CPU_PAGE_FIRST_CHUNK - def_bool y - config ARCH_HIBERNATION_POSSIBLE def_bool y @@ -1557,6 +1551,7 @@ config NUMA depends on SMP depends on X86_64 || (X86_32 && HIGHMEM64G && X86_BIGSMP) default y if X86_BIGSMP + select USE_PERCPU_NUMA_NODE_ID help Enable NUMA (Non-Uniform Memory Access) support. @@ -2431,10 +2426,6 @@ config ARCH_HAS_ADD_PAGES config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE def_bool y -config USE_PERCPU_NUMA_NODE_ID - def_bool y - depends on NUMA - menu "Power management and ACPI options" config ARCH_HIBERNATION_HEADER diff --git a/mm/Kconfig b/mm/Kconfig index 356f4f2c779e..9b5de3f54158 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -432,6 +432,18 @@ config NEED_PER_CPU_KM bool default y +config NEED_PER_CPU_EMBED_FIRST_CHUNK + bool + +config NEED_PER_CPU_PAGE_FIRST_CHUNK + bool + +config USE_PERCPU_NUMA_NODE_ID + bool + +config HAVE_SETUP_PER_CPU_AREA + bool + config CLEANCACHE bool "Enable cleancache driver to cache clean pages if tmem is present" help -- cgit v1.2.3