Home| summaryrefslogtreecommitdiff |
diff options
| author | Olaf Hering <ohering@suse.de> | 2019-10-07 12:53:34 +0200 |
|---|---|---|
| committer | Olaf Hering <ohering@suse.de> | 2019-10-07 12:53:34 +0200 |
| commit | 83592698a44914a69bf5aff9884e9560d978c258 (patch) | |
| tree | 5f141160bbe2ebd9e851d349efe31fb254cc2492 | |
| parent | e3882dd8b8bc50d7e30cf0d4df1853e7508b2599 (diff) | |
| parent | 37817a44490652c8984e1c5eb7e45f975b2b75d0 (diff) | |
Merge remote-tracking branch 'kerncvs/SLE12-SP4' into SLE12-SP4-AZURErpm-4.12.14-6.26--sle12-sp4-updatesrpm-4.12.14-6.26
suse-commit: 46c227c830cfb927be15835bac9e470a363d04f8
64 files changed, 1957 insertions, 952 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index d8a598601a1a..871e6719fd3d 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -496,9 +496,6 @@ config ARCH_CPU_PROBE_RELEASE config ARCH_ENABLE_MEMORY_HOTPLUG def_bool y -config ARCH_HAS_WALK_MEMORY - def_bool y - config ARCH_ENABLE_MEMORY_HOTREMOVE def_bool y diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 59d72a25131c..5c18655ed23e 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -38,13 +38,10 @@ extern struct static_key hcall_tracepoint_key; void __trace_hcall_entry(unsigned long opcode, unsigned long *args); void __trace_hcall_exit(long opcode, unsigned long retval, unsigned long *retbuf); -/* OPAL tracing */ -#ifdef HAVE_JUMP_LABEL -extern struct static_key opal_tracepoint_key; -#endif - -void __trace_opal_entry(unsigned long opcode, unsigned long *args); -void __trace_opal_exit(long opcode, unsigned long retval); +/* OPAL */ +int64_t __opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3, + int64_t a4, int64_t a5, int64_t a6, int64_t a7, + int64_t opcode, uint64_t msr); /* VMX copying */ int enter_vmx_usercopy(void); diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index fba8c4b2015c..f6262d28dad9 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -44,4 +44,11 @@ extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); extern void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr); extern void radix__flush_tlb_all(void); +extern void radix__flush_tlb_lpid_page(unsigned int lpid, + unsigned long addr, + unsigned long page_size); +extern void radix__flush_pwc_lpid(unsigned int lpid); +extern void radix__local_flush_tlb_lpid(unsigned int lpid); +extern void radix__local_flush_tlb_lpid_guest(unsigned int lpid); + #endif diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index e4527faf3853..a5d3dba5109c 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -212,7 +212,8 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_POWER9_DD2_1 LONG_ASM_CONST(0x0000080000000000) #define CPU_FTR_P9_TM_HV_ASSIST LONG_ASM_CONST(0x0000100000000000) #define CPU_FTR_P9_TM_XER_SO_BUG LONG_ASM_CONST(0x0000200000000000) -#define CPU_FTR_P9_TLBIE_BUG LONG_ASM_CONST(0x0000400000000000) +#define CPU_FTR_P9_TLBIE_STQ_BUG LONG_ASM_CONST(0x0000400000000000) +#define CPU_FTR_P9_TLBIE_ERAT_BUG LONG_ASM_CONST(0x0001000000000000) #ifndef __ASSEMBLY__ @@ -460,7 +461,7 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \ CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY | \ - CPU_FTR_P9_TLBIE_BUG) + CPU_FTR_P9_TLBIE_STQ_BUG | CPU_FTR_P9_TLBIE_ERAT_BUG) #define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9 #define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1) #define CPU_FTRS_POWER9_DD2_2 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1 | \ diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index ecbcafb59714..4aff6ac0ec7b 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -40,12 +40,6 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma, return radix__flush_hugetlb_page(vma, vmaddr); } -static inline void __local_flush_hugetlb_page(struct vm_area_struct *vma, - unsigned long vmaddr) -{ - if (radix_enabled()) - return radix__local_flush_hugetlb_page(vma, vmaddr); -} #else static inline pte_t *hugepd_page(hugepd_t hpd) diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 8eb3ebca02df..163970c56e2f 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -266,7 +266,7 @@ int64_t opal_xive_get_vp_info(uint64_t vp, int64_t opal_xive_set_vp_info(uint64_t vp, uint64_t flags, uint64_t report_cl_pair); -int64_t opal_xive_allocate_irq(uint32_t chip_id); +int64_t opal_xive_allocate_irq_raw(uint32_t chip_id); int64_t opal_xive_free_irq(uint32_t girq); int64_t opal_xive_sync(uint32_t type, uint32_t id); int64_t opal_xive_dump(uint32_t type, uint32_t id); diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 40aee9396556..aae13946dbd2 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -319,7 +319,6 @@ struct page; extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg); extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *p); -extern int page_is_ram(unsigned long pfn); extern int devmem_is_allowed(unsigned long pfn); #ifdef CONFIG_PPC_SMLPAR diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 7719896657a7..78e20016bc25 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -690,9 +690,37 @@ static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f) return true; } +/* + * Handle POWER9 broadcast tlbie invalidation issue using + * cpu feature flag. + */ +static __init void update_tlbie_feature_flag(unsigned long pvr) +{ + if (PVR_VER(pvr) == PVR_POWER9) { + /* + * Set the tlbie feature flag for anything below + * Nimbus DD 2.3 and Cumulus DD 1.3 + */ + if ((pvr & 0xe000) == 0) { + /* Nimbus */ + if ((pvr & 0xfff) < 0x203) + cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG; + } else if ((pvr & 0xc000) == 0) { + /* Cumulus */ + if ((pvr & 0xfff) < 0x103) + cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG; + } else { + WARN_ONCE(1, "Unknown PVR"); + cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_STQ_BUG; + } + + cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_ERAT_BUG; + } +} + static __init void cpufeatures_cpu_quirks(void) { - int version = mfspr(SPRN_PVR); + unsigned long version = mfspr(SPRN_PVR); /* * Not all quirks can be derived from the cpufeatures device tree. @@ -711,9 +739,9 @@ static __init void cpufeatures_cpu_quirks(void) if ((version & 0xffff0000) == 0x004e0000) { cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR); - cur_cpu_spec->cpu_features |= CPU_FTR_P9_TLBIE_BUG; } + update_tlbie_feature_flag(version); /* * PKEY was not in the initial base or feature node * specification, but it should become optional in the next diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 48fda67fb092..505433ea630f 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -265,7 +265,7 @@ notrace void arch_local_irq_restore(unsigned long en) * warn if we are wrong. Only do that when IRQ tracing * is enabled as mfmsr() can be costly. */ - if (WARN_ON(mfmsr() & MSR_EE)) + if (WARN_ON_ONCE(mfmsr() & MSR_EE)) __hard_irq_disable(); } #endif /* CONFIG_TRACE_IRQFLAGS */ @@ -775,11 +775,6 @@ int irq_choose_cpu(const struct cpumask *mask) } #endif -int arch_early_irq_init(void) -{ - return 0; -} - #ifdef CONFIG_PPC64 static int __init setup_noirqdistrib(char *str) { diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 20dd82d565e2..96e344ad27f9 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -692,7 +692,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, /* * If found, replace it with: * addis r2, r12, (.TOC.-func)@ha - * addi r2, r12, (.TOC.-func)@l + * addi r2, r2, (.TOC.-func)@l */ ((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value); ((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value); diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 5e97d4f836ca..2a42c8e6e522 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -156,7 +156,7 @@ static void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr, asm volatile("ptesync": : :"memory"); asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1) : : "r" (addr), "r" (kvm->arch.lpid) : "memory"); - if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) asm volatile(PPC_TLBIE_5(%0, %1, 0, 0, 1) : : "r" (addr), "r" (kvm->arch.lpid) : "memory"); asm volatile("eieio ; tlbsync ; ptesync": : :"memory"); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index f350c20f5d43..17c684545b85 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2974,25 +2974,26 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) for (sub = 0; sub < core_info.n_subcores; ++sub) spin_unlock(&core_info.vc[sub]->lock); - /* - * Interrupts will be enabled once we get into the guest, - * so tell lockdep that we're about to enable interrupts. - */ - trace_hardirqs_on(); - guest_enter_irqoff(); srcu_idx = srcu_read_lock(&vc->kvm->srcu); this_cpu_disable_ftrace(); + /* + * Interrupts will be enabled once we get into the guest, + * so tell lockdep that we're about to enable interrupts. + */ + trace_hardirqs_on(); + trap = __kvmppc_vcore_entry(); + trace_hardirqs_off(); + this_cpu_enable_ftrace(); srcu_read_unlock(&vc->kvm->srcu, srcu_idx); - trace_hardirqs_off(); set_irq_happened(trap); spin_lock(&vc->lock); diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 19b1d08dbc90..5e1e62206f1d 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -435,6 +435,37 @@ static inline int is_mmio_hpte(unsigned long v, unsigned long r) (HPTE_R_KEY_HI | HPTE_R_KEY_LO)); } +static inline void fixup_tlbie_lpid(unsigned long rb_value, unsigned long lpid) +{ + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + /* Radix flush for a hash guest */ + + unsigned long rb,rs,prs,r,ric; + + rb = PPC_BIT(52); /* IS = 2 */ + rs = 0; /* lpid = 0 */ + prs = 0; /* partition scoped */ + r = 1; /* radix format */ + ric = 0; /* RIC_FLSUH_TLB */ + + /* + * Need the extra ptesync to make sure we don't + * re-order the tlbie + */ + asm volatile("ptesync": : :"memory"); + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), + "i"(ric), "r"(rs) : "memory"); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync": : :"memory"); + asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : : + "r" (rb_value), "r" (lpid)); + } +} + static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues, long npages, int global, bool need_sync) { @@ -453,16 +484,7 @@ static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues, "r" (rbvalues[i]), "r" (kvm->arch.lpid)); } - if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) { - /* - * Need the extra ptesync to make sure we don't - * re-order the tlbie - */ - asm volatile("ptesync": : :"memory"); - asm volatile(PPC_TLBIE_5(%0,%1,0,0,0) : : - "r" (rbvalues[0]), "r" (kvm->arch.lpid)); - } - + fixup_tlbie_lpid(rbvalues[i - 1], kvm->arch.lpid); asm volatile("eieio; tlbsync; ptesync" : : : "memory"); } else { if (need_sync) diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 1fd21f191e4c..c433851cfd32 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -201,9 +201,32 @@ static inline unsigned long ___tlbie(unsigned long vpn, int psize, return va; } -static inline void fixup_tlbie(unsigned long vpn, int psize, int apsize, int ssize) +static inline void fixup_tlbie_vpn(unsigned long vpn, int psize, + int apsize, int ssize) { - if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) { + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + /* Radix flush for a hash guest */ + + unsigned long rb,rs,prs,r,ric; + + rb = PPC_BIT(52); /* IS = 2 */ + rs = 0; /* lpid = 0 */ + prs = 0; /* partition scoped */ + r = 1; /* radix format */ + ric = 0; /* RIC_FLSUH_TLB */ + + /* + * Need the extra ptesync to make sure we don't + * re-order the tlbie + */ + asm volatile("ptesync": : :"memory"); + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), + "i"(ric), "r"(rs) : "memory"); + } + + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { /* Need the extra ptesync to ensure we don't reorder tlbie*/ asm volatile("ptesync": : :"memory"); ___tlbie(vpn, psize, apsize, ssize); @@ -287,7 +310,7 @@ static inline void tlbie(unsigned long vpn, int psize, int apsize, asm volatile("ptesync": : :"memory"); } else { __tlbie(vpn, psize, apsize, ssize); - fixup_tlbie(vpn, psize, apsize, ssize); + fixup_tlbie_vpn(vpn, psize, apsize, ssize); asm volatile("eieio; tlbsync; ptesync": : :"memory"); } if (lock_tlbie && !use_local) @@ -824,7 +847,7 @@ static void native_flush_hash_range(unsigned long number, int local) /* * Just do one more with the last used values. */ - fixup_tlbie(vpn, psize, psize, ssize); + fixup_tlbie_vpn(vpn, psize, psize, ssize); asm volatile("eieio; tlbsync; ptesync":::"memory"); if (lock_tlbie) diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 4bc55e5ea93c..63ae402dbabc 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -80,21 +80,6 @@ static inline pte_t *virt_to_kpte(unsigned long vaddr) #define TOP_ZONE ZONE_NORMAL #endif -int page_is_ram(unsigned long pfn) -{ -#ifndef CONFIG_PPC64 /* XXX for now */ - return pfn < max_pfn; -#else - unsigned long paddr = (pfn << PAGE_SHIFT); - struct memblock_region *reg; - - for_each_memblock(memory, reg) - if (paddr >= reg->base && paddr < (reg->base + reg->size)) - return 1; - return 0; -#endif -} - pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { @@ -177,34 +162,6 @@ int arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) #endif #endif /* CONFIG_MEMORY_HOTPLUG */ -/* - * walk_memory_resource() needs to make sure there is no holes in a given - * memory range. PPC64 does not maintain the memory layout in /proc/iomem. - * Instead it maintains it in memblock.memory structures. Walk through the - * memory regions, find holes and callback for contiguous regions. - */ -int -walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, - void *arg, int (*func)(unsigned long, unsigned long, void *)) -{ - struct memblock_region *reg; - unsigned long end_pfn = start_pfn + nr_pages; - unsigned long tstart, tend; - int ret = -1; - - for_each_memblock(memory, reg) { - tstart = max(start_pfn, memblock_region_memory_base_pfn(reg)); - tend = min(end_pfn, memblock_region_memory_end_pfn(reg)); - if (tstart >= tend) - continue; - ret = (*func)(tstart, tend - tstart, arg); - if (ret) - break; - } - return ret; -} -EXPORT_SYMBOL_GPL(walk_system_ram_range); - #ifndef CONFIG_NEED_MULTIPLE_NODES void __init initmem_init(void) { @@ -592,3 +549,9 @@ int devmem_is_allowed(unsigned long pfn) return 0; } #endif /* CONFIG_STRICT_DEVMEM */ + +/* + * This is defined in kernel/resource.c but only powerpc needs to export it, for + * the EHEA driver. Drop this when drivers/net/ethernet/ibm/ehea is removed. + */ +EXPORT_SYMBOL_GPL(walk_system_ram_range); diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 672730f4665b..9004bc5bee5a 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -104,6 +104,67 @@ static inline void __tlbiel_pid(unsigned long pid, int set, trace_tlbie(0, 1, rb, rs, ric, prs, r); } +static inline void __tlbie_pid(unsigned long pid, unsigned long ric) +{ + unsigned long rb,rs,prs,r; + + rb = PPC_BIT(53); /* IS = 1 */ + rs = pid << PPC_BITLSHIFT(31); + prs = 1; /* process scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(0, 0, rb, rs, ric, prs, r); +} + +static inline void __tlbiel_lpid(unsigned long lpid, int set, + unsigned long ric) +{ + unsigned long rb,rs,prs,r; + + rb = PPC_BIT(52); /* IS = 2 */ + rb |= set << PPC_BITLSHIFT(51); + rs = 0; /* LPID comes from LPIDR */ + prs = 0; /* partition scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(lpid, 1, rb, rs, ric, prs, r); +} + +static inline void __tlbie_lpid(unsigned long lpid, unsigned long ric) +{ + unsigned long rb,rs,prs,r; + + rb = PPC_BIT(52); /* IS = 2 */ + rs = lpid; + prs = 0; /* partition scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(lpid, 0, rb, rs, ric, prs, r); +} + +static inline void __tlbiel_lpid_guest(unsigned long lpid, int set, + unsigned long ric) +{ + unsigned long rb,rs,prs,r; + + rb = PPC_BIT(52); /* IS = 2 */ + rb |= set << PPC_BITLSHIFT(51); + rs = 0; /* LPID comes from LPIDR */ + prs = 1; /* process scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(lpid, 1, rb, rs, ric, prs, r); +} + + static inline void __tlbiel_va(unsigned long va, unsigned long pid, unsigned long ap, unsigned long ric) { @@ -136,17 +197,104 @@ static inline void __tlbie_va(unsigned long va, unsigned long pid, trace_tlbie(0, 0, rb, rs, ric, prs, r); } -static inline void fixup_tlbie(void) +static inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid, + unsigned long ap, unsigned long ric) +{ + unsigned long rb,rs,prs,r; + + rb = va & ~(PPC_BITMASK(52, 63)); + rb |= ap << PPC_BITLSHIFT(58); + rs = lpid; + prs = 0; /* partition scoped */ + r = 1; /* radix format */ + + asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) + : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); + trace_tlbie(lpid, 0, rb, rs, ric, prs, r); +} + + +static inline void fixup_tlbie_va(unsigned long va, unsigned long pid, + unsigned long ap) { - unsigned long pid = 0; + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync": : :"memory"); + __tlbie_va(va, 0, ap, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync": : :"memory"); + __tlbie_va(va, pid, ap, RIC_FLUSH_TLB); + } +} + +static inline void fixup_tlbie_va_range(unsigned long va, unsigned long pid, + unsigned long ap) +{ + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync": : :"memory"); + __tlbie_pid(0, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync": : :"memory"); + __tlbie_va(va, pid, ap, RIC_FLUSH_TLB); + } +} + +static inline void fixup_tlbie_pid(unsigned long pid) +{ + /* + * We can use any address for the invalidation, pick one which is + * probably unused as an optimisation. + */ unsigned long va = ((1UL << 52) - 1); - if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) { + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync": : :"memory"); + __tlbie_pid(0, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { asm volatile("ptesync": : :"memory"); __tlbie_va(va, pid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB); } } + +static inline void fixup_tlbie_lpid_va(unsigned long va, unsigned long lpid, + unsigned long ap) +{ + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync": : :"memory"); + __tlbie_lpid_va(va, 0, ap, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync": : :"memory"); + __tlbie_lpid_va(va, lpid, ap, RIC_FLUSH_TLB); + } +} + +static inline void fixup_tlbie_lpid(unsigned long lpid) +{ + /* + * We can use any address for the invalidation, pick one which is + * probably unused as an optimisation. + */ + unsigned long va = ((1UL << 52) - 1); + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) { + asm volatile("ptesync": : :"memory"); + __tlbie_lpid(0, RIC_FLUSH_TLB); + } + + if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) { + asm volatile("ptesync": : :"memory"); + __tlbie_lpid_va(va, lpid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB); + } +} + /* * We use 128 set in radix mode and 256 set in hpt mode. */ @@ -178,38 +326,187 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric) static inline void _tlbie_pid(unsigned long pid, unsigned long ric) { - unsigned long rb,rs,prs,r; + asm volatile("ptesync": : :"memory"); - rb = PPC_BIT(53); /* IS = 1 */ - rs = pid << PPC_BITLSHIFT(31); - prs = 1; /* process scoped */ - r = 1; /* radix format */ + /* + * Workaround the fact that the "ric" argument to __tlbie_pid + * must be a compile-time contraint to match the "i" constraint + * in the asm statement. + */ + switch (ric) { + case RIC_FLUSH_TLB: + __tlbie_pid(pid, RIC_FLUSH_TLB); + fixup_tlbie_pid(pid); + break; + case RIC_FLUSH_PWC: + __tlbie_pid(pid, RIC_FLUSH_PWC); + break; + case RIC_FLUSH_ALL: + default: + __tlbie_pid(pid, RIC_FLUSH_ALL); + fixup_tlbie_pid(pid); + } + asm volatile("eieio; tlbsync; ptesync": : :"memory"); +} + +static inline void _tlbiel_lpid(unsigned long lpid, unsigned long ric) +{ + int set; + + VM_BUG_ON(mfspr(SPRN_LPID) != lpid); asm volatile("ptesync": : :"memory"); - asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1) - : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); - fixup_tlbie(); + + /* + * Flush the first set of the TLB, and if we're doing a RIC_FLUSH_ALL, + * also flush the entire Page Walk Cache. + */ + __tlbiel_lpid(lpid, 0, ric); + + /* For PWC, only one flush is needed */ + if (ric == RIC_FLUSH_PWC) { + asm volatile("ptesync": : :"memory"); + return; + } + + /* For the remaining sets, just flush the TLB */ + for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++) + __tlbiel_lpid(lpid, set, RIC_FLUSH_TLB); + + asm volatile("ptesync": : :"memory"); + asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory"); +} + +static inline void _tlbie_lpid(unsigned long lpid, unsigned long ric) +{ + asm volatile("ptesync": : :"memory"); + + /* + * Workaround the fact that the "ric" argument to __tlbie_pid + * must be a compile-time contraint to match the "i" constraint + * in the asm statement. + */ + switch (ric) { + case RIC_FLUSH_TLB: + __tlbie_lpid(lpid, RIC_FLUSH_TLB); + fixup_tlbie_lpid(lpid); + break; + case RIC_FLUSH_PWC: + __tlbie_lpid(lpid, RIC_FLUSH_PWC); + break; + case RIC_FLUSH_ALL: + default: + __tlbie_lpid(lpid, RIC_FLUSH_ALL); + fixup_tlbie_lpid(lpid); + } asm volatile("eieio; tlbsync; ptesync": : :"memory"); - trace_tlbie(0, 0, rb, rs, ric, prs, r); +} + +static inline void _tlbiel_lpid_guest(unsigned long lpid, unsigned long ric) +{ + int set; + + VM_BUG_ON(mfspr(SPRN_LPID) != lpid); + + asm volatile("ptesync": : :"memory"); + + /* + * Flush the first set of the TLB, and if we're doing a RIC_FLUSH_ALL, + * also flush the entire Page Walk Cache. + */ + __tlbiel_lpid_guest(lpid, 0, ric); + + /* For PWC, only one flush is needed */ + if (ric == RIC_FLUSH_PWC) { + asm volatile("ptesync": : :"memory"); + return; + } + + /* For the remaining sets, just flush the TLB */ + for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++) + __tlbiel_lpid_guest(lpid, set, RIC_FLUSH_TLB); + + asm volatile("ptesync": : :"memory"); +} + + +static inline void __tlbiel_va_range(unsigned long start, unsigned long end, + unsigned long pid, unsigned long page_size, + unsigned long psize) +{ + unsigned long addr; + unsigned long ap = mmu_get_ap(psize); + + for (addr = start; addr < end; addr += page_size) + __tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB); } static inline void _tlbiel_va(unsigned long va, unsigned long pid, - unsigned long ap, unsigned long ric) + unsigned long psize, unsigned long ric) { + unsigned long ap = mmu_get_ap(psize); + asm volatile("ptesync": : :"memory"); __tlbiel_va(va, pid, ap, ric); asm volatile("ptesync": : :"memory"); } +static inline void _tlbiel_va_range(unsigned long start, unsigned long end, + unsigned long pid, unsigned long page_size, + unsigned long psize, bool also_pwc) +{ + asm volatile("ptesync": : :"memory"); + if (also_pwc) + __tlbiel_pid(pid, 0, RIC_FLUSH_PWC); + __tlbiel_va_range(start, end, pid, page_size, psize); + asm volatile("ptesync": : :"memory"); +} + +static inline void __tlbie_va_range(unsigned long start, unsigned long end, + unsigned long pid, unsigned long page_size, + unsigned long psize) +{ + unsigned long addr; + unsigned long ap = mmu_get_ap(psize); + + for (addr = start; addr < end; addr += page_size) + __tlbie_va(addr, pid, ap, RIC_FLUSH_TLB); + + fixup_tlbie_va_range(addr - page_size, pid, ap); +} + static inline void _tlbie_va(unsigned long va, unsigned long pid, - unsigned long ap, unsigned long ric) + unsigned long psize, unsigned long ric) { + unsigned long ap = mmu_get_ap(psize); + asm volatile("ptesync": : :"memory"); __tlbie_va(va, pid, ap, ric); - fixup_tlbie(); + fixup_tlbie_va(va, pid, ap); + asm volatile("eieio; tlbsync; ptesync": : :"memory"); +} + +static inline void _tlbie_lpid_va(unsigned long va, unsigned long lpid, + unsigned long psize, unsigned long ric) +{ + unsigned long ap = mmu_get_ap(psize); + + asm volatile("ptesync": : :"memory"); + __tlbie_lpid_va(va, lpid, ap, ric); + fixup_tlbie_lpid_va(va, lpid, ap); asm volatile("eieio; tlbsync; ptesync": : :"memory"); } +static inline void _tlbie_va_range(unsigned long start, unsigned long end, + unsigned long pid, unsigned long page_size, + unsigned long psize, bool also_pwc) +{ + asm volatile("ptesync": : :"memory"); + if (also_pwc) + __tlbie_pid(pid, RIC_FLUSH_PWC); + __tlbie_va_range(start, end, pid, page_size, psize); + asm volatile("eieio; tlbsync; ptesync": : :"memory"); +} /* * Base TLB flushing operations: @@ -252,12 +549,11 @@ void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmadd int psize) { unsigned long pid; - unsigned long ap = mmu_get_ap(psize); preempt_disable(); - pid = mm ? mm->context.id : 0; + pid = mm->context.id; if (pid != MMU_NO_CONTEXT) - _tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB); + _tlbiel_va(vmaddr, pid, psize, RIC_FLUSH_TLB); preempt_enable(); } @@ -265,11 +561,10 @@ void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmadd { #ifdef CONFIG_HUGETLB_PAGE /* need the return fix for nohash.c */ - if (vma && is_vm_hugetlb_page(vma)) - return __local_flush_hugetlb_page(vma, vmaddr); + if (is_vm_hugetlb_page(vma)) + return radix__local_flush_hugetlb_page(vma, vmaddr); #endif - radix__local_flush_tlb_page_psize(vma ? vma->vm_mm : NULL, vmaddr, - mmu_virtual_psize); + radix__local_flush_tlb_page_psize(vma->vm_mm, vmaddr, mmu_virtual_psize); } EXPORT_SYMBOL(radix__local_flush_tlb_page); @@ -288,11 +583,11 @@ void radix__flush_tlb_mm(struct mm_struct *mm) { unsigned long pid; - preempt_disable(); pid = mm->context.id; if (unlikely(pid == MMU_NO_CONTEXT)) - goto no_context; + return; + preempt_disable(); if (!mm_is_thread_local(mm)) { if (mm_needs_flush_escalation(mm)) _tlbie_pid(pid, RIC_FLUSH_ALL); @@ -300,7 +595,6 @@ void radix__flush_tlb_mm(struct mm_struct *mm) _tlbie_pid(pid, RIC_FLUSH_TLB); } else _tlbiel_pid(pid, RIC_FLUSH_TLB); -no_context: preempt_enable(); } EXPORT_SYMBOL(radix__flush_tlb_mm); @@ -309,16 +603,15 @@ void radix__flush_all_mm(struct mm_struct *mm) { unsigned long pid; - preempt_disable(); pid = mm->context.id; if (unlikely(pid == MMU_NO_CONTEXT)) - goto no_context; + return; + preempt_disable(); if (!mm_is_thread_local(mm)) _tlbie_pid(pid, RIC_FLUSH_ALL); else _tlbiel_pid(pid, RIC_FLUSH_ALL); -no_context: preempt_enable(); } EXPORT_SYMBOL(radix__flush_all_mm); @@ -333,28 +626,26 @@ void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, int psize) { unsigned long pid; - unsigned long ap = mmu_get_ap(psize); - preempt_disable(); - pid = mm ? mm->context.id : 0; + pid = mm->context.id; if (unlikely(pid == MMU_NO_CONTEXT)) - goto bail; + return; + + preempt_disable(); if (!mm_is_thread_local(mm)) - _tlbie_va(vmaddr, pid, ap, RIC_FLUSH_TLB); + _tlbie_va(vmaddr, pid, psize, RIC_FLUSH_TLB); else - _tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB); -bail: + _tlbiel_va(vmaddr, pid, psize, RIC_FLUSH_TLB); preempt_enable(); } void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) { #ifdef CONFIG_HUGETLB_PAGE - if (vma && is_vm_hugetlb_page(vma)) - return flush_hugetlb_page(vma, vmaddr); + if (is_vm_hugetlb_page(vma)) + return radix__flush_hugetlb_page(vma, vmaddr); #endif - radix__flush_tlb_page_psize(vma ? vma->vm_mm : NULL, vmaddr, - mmu_virtual_psize); + radix__flush_tlb_page_psize(vma->vm_mm, vmaddr, mmu_virtual_psize); } EXPORT_SYMBOL(radix__flush_tlb_page); @@ -368,17 +659,113 @@ void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end) } EXPORT_SYMBOL(radix__flush_tlb_kernel_range); +#define TLB_FLUSH_ALL -1UL + /* - * Currently, for range flushing, we just do a full mm flush. Because - * we use this in code path where we don' track the page size. + * Number of pages above which we invalidate the entire PID rather than + * flush individual pages, for local and global flushes respectively. + * + * tlbie goes out to the interconnect and individual ops are more costly. + * It also does not iterate over sets like the local tlbiel variant when + * invalidating a full PID, so it has a far lower threshold to change from + * individual page flushes to full-pid flushes. */ +static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33; +static unsigned long tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2; + +static inline void __radix__flush_tlb_range(struct mm_struct *mm, + unsigned long start, unsigned long end, + bool flush_all_sizes) + +{ + unsigned long pid; + unsigned int page_shift = mmu_psize_defs[mmu_virtual_psize].shift; + unsigned long page_size = 1UL << page_shift; + unsigned long nr_pages = (end - start) >> page_shift; + bool local, full; + + pid = mm->context.id; + if (unlikely(pid == MMU_NO_CONTEXT)) + return; + + preempt_disable(); + if (mm_is_thread_local(mm)) { + local = true; + full = (end == TLB_FLUSH_ALL || + nr_pages > tlb_local_single_page_flush_ceiling); + } else { + local = false; + full = (end == TLB_FLUSH_ALL || + nr_pages > tlb_single_page_flush_ceiling); + } + + if (full) { + if (local) { + _tlbiel_pid(pid, RIC_FLUSH_TLB); + } else { + if (mm_needs_flush_escalation(mm)) + _tlbie_pid(pid, RIC_FLUSH_ALL); + else + _tlbie_pid(pid, RIC_FLUSH_TLB); + } + } else { + bool hflush = flush_all_sizes; + bool gflush = flush_all_sizes; + unsigned long hstart, hend; + unsigned long gstart, gend; + + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + hflush = true; + + if (hflush) { + hstart = (start + PMD_SIZE - 1) & PMD_MASK; + hend = end & PMD_MASK; + if (hstart == hend) + hflush = false; + } + + if (gflush) { + gstart = (start + PUD_SIZE - 1) & PUD_MASK; + gend = end & PUD_MASK; + if (gstart == gend) + gflush = false; + } + + asm volatile("ptesync": : :"memory"); + if (local) { + __tlbiel_va_range(start, end, pid, page_size, mmu_virtual_psize); + if (hflush) + __tlbiel_va_range(hstart, hend, pid, + PMD_SIZE, MMU_PAGE_2M); + if (gflush) + __tlbiel_va_range(gstart, gend, pid, + PUD_SIZE, MMU_PAGE_1G); + asm volatile("ptesync": : :"memory"); + } else { + __tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize); + if (hflush) + __tlbie_va_range(hstart, hend, pid, + PMD_SIZE, MMU_PAGE_2M); + if (gflush) + __tlbie_va_range(gstart, gend, pid, + PUD_SIZE, MMU_PAGE_1G); + + asm volatile("eieio; tlbsync; ptesync": : :"memory"); + } + } + preempt_enable(); +} + void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - struct mm_struct *mm = vma->vm_mm; +#ifdef CONFIG_HUGETLB_PAGE + if (is_vm_hugetlb_page(vma)) + return radix__flush_hugetlb_tlb_range(vma, start, end); +#endif - radix__flush_tlb_mm(mm); + __radix__flush_tlb_range(vma->vm_mm, start, end, false); } EXPORT_SYMBOL(radix__flush_tlb_range); @@ -397,13 +784,60 @@ static int radix_get_mmu_psize(int page_size) return psize; } +/* + * Flush partition scoped LPID address translation for all CPUs. + */ +void radix__flush_tlb_lpid_page(unsigned int lpid, + unsigned long addr, + unsigned long page_size) +{ + int psize = radix_get_mmu_psize(page_size); + + _tlbie_lpid_va(addr, lpid, psize, RIC_FLUSH_TLB); +} +EXPORT_SYMBOL_GPL(radix__flush_tlb_lpid_page); + +/* + * Flush partition scoped PWC from LPID for all CPUs. + */ +void radix__flush_pwc_lpid(unsigned int lpid) +{ + _tlbie_lpid(lpid, RIC_FLUSH_PWC); +} +EXPORT_SYMBOL_GPL(radix__flush_pwc_lpid); + +/* + * Flush partition scoped translations from LPID (=LPIDR) + */ +void radix__local_flush_tlb_lpid(unsigned int lpid) +{ + _tlbiel_lpid(lpid, RIC_FLUSH_ALL); +} +EXPORT_SYMBOL_GPL(radix__local_flush_tlb_lpid); + +/* + * Flush process scoped translations from LPID (=LPIDR). + * Important difference, the guest normally manages its own translations, + * but some cases e.g., vCPU CPU migration require KVM to flush. + */ +void radix__local_flush_tlb_lpid_guest(unsigned int lpid) +{ + _tlbiel_lpid_guest(lpid, RIC_FLUSH_ALL); +} +EXPORT_SYMBOL_GPL(radix__local_flush_tlb_lpid_guest); + + +static void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start, + unsigned long end, int psize); + void radix__tlb_flush(struct mmu_gather *tlb) { int psize = 0; struct mm_struct *mm = tlb->mm; int page_size = tlb->page_size; + unsigned long start = tlb->start; + unsigned long end = tlb->end; - psize = radix_get_mmu_psize(page_size); /* * if page size is not something we understand, do a full mm flush * @@ -411,108 +845,135 @@ void radix__tlb_flush(struct mmu_gather *tlb) * that flushes the process table entry cache upon process teardown. * See the comment for radix in arch_exit_mmap(). */ - if (psize != -1 && !tlb->fullmm && !tlb->need_flush_all) - radix__flush_tlb_range_psize(mm, tlb->start, tlb->end, psize); - else if (tlb->fullmm || tlb->need_flush_all) { - tlb->need_flush_all = 0; + if (tlb->fullmm) { radix__flush_all_mm(mm); - } else - radix__flush_tlb_mm(mm); +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE) + } else if (mm_tlb_flush_nested(mm)) { + /* + * If there is a concurrent invalidation that is clearing ptes, + * then it's possible this invalidation will miss one of those + * cleared ptes and miss flushing the TLB. If this invalidate + * returns before the other one flushes TLBs, that can result + * in it returning while there are still valid TLBs inside the + * range to be invalidated. + * + * See mm/memory.c:tlb_finish_mmu() for more details. + * + * The solution to this is ensure the entire range is always + * flushed here. The problem for powerpc is that the flushes + * are page size specific, so this "forced flush" would not + * do the right thing if there are a mix of page sizes in + * the range to be invalidated. So use __flush_tlb_range + * which invalidates all possible page sizes in the range. + * + * PWC flush probably is not be required because the core code + * shouldn't free page tables in this path, but accounting + * for the possibility makes us a bit more robust. + * + * need_flush_all is an uncommon case because page table + * teardown should be done with exclusive locks held (but + * after locks are dropped another invalidate could come + * in), it could be optimized further if necessary. + */ + if (!tlb->need_flush_all) + __radix__flush_tlb_range(mm, start, end, true); + else + radix__flush_all_mm(mm); +#endif + } else if ( (psize = radix_get_mmu_psize(page_size)) == -1) { + if (!tlb->need_flush_all) + radix__flush_tlb_mm(mm); + else + radix__flush_all_mm(mm); + } else { + if (!tlb->need_flush_all) + radix__flush_tlb_range_psize(mm, start, end, psize); + else + radix__flush_tlb_pwc_range_psize(mm, start, end, psize); + } + tlb->need_flush_all = 0; } -#define TLB_FLUSH_ALL -1UL -/* - * Number of pages above which we will do a bcast tlbie. Just a - * number at this point copied from x86 - */ -static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33; - -void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start, - unsigned long end, int psize) +static inline void __radix__flush_tlb_range_psize(struct mm_struct *mm, + unsigned long start, unsigned long end, + int psize, bool also_pwc) { unsigned long pid; - unsigned long addr; - int local = mm_is_thread_local(mm); - unsigned long ap = mmu_get_ap(psize); - unsigned long page_size = 1UL << mmu_psize_defs[psize].shift; - + unsigned int page_shift = mmu_psize_defs[psize].shift; + unsigned long page_size = 1UL << page_shift; + unsigned long nr_pages = (end - start) >> page_shift; + bool local, full; - preempt_disable(); - pid = mm ? mm->context.id : 0; + pid = mm->context.id; if (unlikely(pid == MMU_NO_CONTEXT)) - goto err_out; + return; - if (end == TLB_FLUSH_ALL || - (end - start) > tlb_single_page_flush_ceiling * page_size) { - if (local) { - _tlbiel_pid(pid, RIC_FLUSH_TLB); - } else { - if (mm_needs_flush_escalation(mm)) - _tlbie_pid(pid, RIC_FLUSH_ALL); - else - _tlbie_pid(pid, RIC_FLUSH_TLB); - } - goto err_out; + preempt_disable(); + if (mm_is_thread_local(mm)) { + local = true; + full = (end == TLB_FLUSH_ALL || + nr_pages > tlb_local_single_page_flush_ceiling); + } else { + local = false; + full = (end == TLB_FLUSH_ALL || + nr_pages > tlb_single_page_flush_ceiling); } - asm volatile("ptesync": : :"memory"); - for (addr = start; addr < end; addr += page_size) { + + if (full) { + if (!local && mm_needs_flush_escalation(mm)) + also_pwc = true; + if (local) - __tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB); - else { - __tlbie_va(addr, pid, ap, RIC_FLUSH_TLB); - fixup_tlbie(); - } + _tlbiel_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB); + else + _tlbie_pid(pid, also_pwc ? RIC_FLUSH_ALL: RIC_FLUSH_TLB); + } else { + if (local) + _tlbiel_va_range(start, end, pid, page_size, psize, also_pwc); + else + _tlbie_va_range(start, end, pid, page_size, psize, also_pwc); } - if (local) - asm volatile("ptesync": : :"memory"); - else - asm volatile("eieio; tlbsync; ptesync": : :"memory"); -err_out: preempt_enable(); } +void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start, + unsigned long end, int psize) +{ + return __radix__flush_tlb_range_psize(mm, start, end, psize, false); +} + +static void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start, + unsigned long end, int psize) +{ + __radix__flush_tlb_range_psize(mm, start, end, psize, true); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr) { - int local = mm_is_thread_local(mm); - unsigned long ap = mmu_get_ap(mmu_virtual_psize); unsigned long pid, end; - - pid = mm ? mm->context.id : 0; - preempt_disable(); + pid = mm->context.id; if (unlikely(pid == MMU_NO_CONTEXT)) - goto no_context; + return; /* 4k page size, just blow the world */ if (PAGE_SIZE == 0x1000) { radix__flush_all_mm(mm); - preempt_enable(); return; } - /* Otherwise first do the PWC */ - if (local) - _tlbiel_pid(pid, RIC_FLUSH_PWC); - else - _tlbie_pid(pid, RIC_FLUSH_PWC); - - /* Then iterate the pages */ - asm volatile("ptesync": : :"memory"); end = addr + HPAGE_PMD_SIZE; - for (; addr < end; addr += PAGE_SIZE) { - if (local) - _tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB); - else - _tlbie_va(addr, pid, ap, RIC_FLUSH_TLB); - } - if (local) - asm volatile("ptesync": : :"memory"); - else - asm volatile("eieio; tlbsync; ptesync": : :"memory"); + /* Otherwise first do the PWC, then iterate the pages. */ + preempt_disable(); + + if (mm_is_thread_local(mm)) { + _tlbiel_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true); + } else { + _tlbie_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true); + } -no_context: preempt_enable(); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index be975390c4a6..67b4950825ec 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -1,5 +1,5 @@ -obj-y += setup.o opal-wrappers.o opal.o opal-async.o idle.o -obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o +obj-y += setup.o opal-call.o opal-wrappers.o opal.o opal-async.o +obj-y += idle.o opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o obj-y += opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o obj-y += opal-kmsg.o opal-powercap.o opal-psr.o opal-sensor-groups.o @@ -10,6 +10,5 @@ obj-$(CONFIG_CXL_BASE) += pci-cxl.o obj-$(CONFIG_EEH) += eeh-powernv.o obj-$(CONFIG_PPC_SCOM) += opal-xscom.o obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o -obj-$(CONFIG_TRACEPOINTS) += opal-tracepoints.o obj-$(CONFIG_OPAL_PRD) += opal-prd.o obj-$(CONFIG_PERF_EVENTS) += opal-imc.o diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index 8b9042376819..cf3428bf9604 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -46,10 +46,6 @@ static DEFINE_SPINLOCK(npu_context_lock); */ #define ATSD_THRESHOLD (2*1024*1024) -/* - * Other types of TCE cache invalidation are not functional in the - * hardware. - */ static struct pci_dev *get_pci_dev(struct device_node *dn) { return PCI_DN(dn)->pcidev; diff --git a/arch/powerpc/platforms/powernv/opal-call.c b/arch/powerpc/platforms/powernv/opal-call.c new file mode 100644 index 000000000000..5297676a903f --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-call.c @@ -0,0 +1,274 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/percpu.h> +#include <linux/jump_label.h> +#include <asm/opal-api.h> +#include <asm/trace.h> +#include <asm/asm-prototypes.h> + +#ifdef CONFIG_TRACEPOINTS +/* + * Since the tracing code might execute OPAL calls we need to guard against + * recursion. + */ +static DEFINE_PER_CPU(unsigned int, opal_trace_depth); + +static void __trace_opal_entry(s64 a0, s64 a1, s64 a2, s64 a3, + s64 a4, s64 a5, s64 a6, s64 a7, + unsigned long opcode) +{ + unsigned int *depth; + unsigned long args[8]; + + depth = this_cpu_ptr(&opal_trace_depth); + + if (*depth) + return; + + args[0] = a0; + args[1] = a1; + args[2] = a2; + args[3] = a3; + args[4] = a4; + args[5] = a5; + args[6] = a6; + args[7] = a7; + + (*depth)++; + trace_opal_entry(opcode, &args[0]); + (*depth)--; +} + +static void __trace_opal_exit(unsigned long opcode, unsigned long retval) +{ + unsigned int *depth; + + depth = this_cpu_ptr(&opal_trace_depth); + + if (*depth) + return; + + (*depth)++; + trace_opal_exit(opcode, retval); + (*depth)--; +} + +static DEFINE_STATIC_KEY_FALSE(opal_tracepoint_key); + +int opal_tracepoint_regfunc(void) +{ + static_branch_inc(&opal_tracepoint_key); + return 0; +} + +void opal_tracepoint_unregfunc(void) +{ + static_branch_dec(&opal_tracepoint_key); +} + +static s64 __opal_call_trace(s64 a0, s64 a1, s64 a2, s64 a3, + s64 a4, s64 a5, s64 a6, s64 a7, + unsigned long opcode, unsigned long msr) +{ + s64 ret; + + __trace_opal_entry(a0, a1, a2, a3, a4, a5, a6, a7, opcode); + ret = __opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr); + __trace_opal_exit(opcode, ret); + + return ret; +} + +#define DO_TRACE (static_branch_unlikely(&opal_tracepoint_key)) + +#else /* CONFIG_TRACEPOINTS */ + +static s64 __opal_call_trace(s64 a0, s64 a1, s64 a2, s64 a3, + s64 a4, s64 a5, s64 a6, s64 a7, + unsigned long opcode, unsigned long msr) +{ + return 0; +} + +#define DO_TRACE false +#endif /* CONFIG_TRACEPOINTS */ + +static int64_t opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3, + int64_t a4, int64_t a5, int64_t a6, int64_t a7, int64_t opcode) +{ + unsigned long flags; + unsigned long msr = mfmsr(); + bool mmu = (msr & (MSR_IR|MSR_DR)); + int64_t ret; + + msr &= ~MSR_EE; + + if (unlikely(!mmu)) + return __opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr); + + local_save_flags(flags); + hard_irq_disable(); + + if (DO_TRACE) { + ret = __opal_call_trace(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr); + } else { + ret = __opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode, msr); + } + + local_irq_restore(flags); + + return ret; +} + +#define OPAL_CALL(name, opcode) \ +int64_t name(int64_t a0, int64_t a1, int64_t a2, int64_t a3, \ + int64_t a4, int64_t a5, int64_t a6, int64_t a7) \ +{ \ + return opal_call(a0, a1, a2, a3, a4, a5, a6, a7, opcode); \ +} + +OPAL_CALL(opal_invalid_call, OPAL_INVALID_CALL); +OPAL_CALL(opal_console_write, OPAL_CONSOLE_WRITE); +OPAL_CALL(opal_console_read, OPAL_CONSOLE_READ); +OPAL_CALL(opal_console_write_buffer_space, OPAL_CONSOLE_WRITE_BUFFER_SPACE); +OPAL_CALL(opal_rtc_read, OPAL_RTC_READ); +OPAL_CALL(opal_rtc_write, OPAL_RTC_WRITE); +OPAL_CALL(opal_cec_power_down, OPAL_CEC_POWER_DOWN); +OPAL_CALL(opal_cec_reboot, OPAL_CEC_REBOOT); +OPAL_CALL(opal_cec_reboot2, OPAL_CEC_REBOOT2); +OPAL_CALL(opal_read_nvram, OPAL_READ_NVRAM); +OPAL_CALL(opal_write_nvram, OPAL_WRITE_NVRAM); +OPAL_CALL(opal_handle_interrupt, OPAL_HANDLE_INTERRUPT); +OPAL_CALL(opal_poll_events, OPAL_POLL_EVENTS); +OPAL_CALL(opal_pci_set_hub_tce_memory, OPAL_PCI_SET_HUB_TCE_MEMORY); +OPAL_CALL(opal_pci_set_phb_tce_memory, OPAL_PCI_SET_PHB_TCE_MEMORY); +OPAL_CALL(opal_pci_config_read_byte, OPAL_PCI_CONFIG_READ_BYTE); +OPAL_CALL(opal_pci_config_read_half_word, OPAL_PCI_CONFIG_READ_HALF_WORD); +OPAL_CALL(opal_pci_config_read_word, OPAL_PCI_CONFIG_READ_WORD); +OPAL_CALL(opal_pci_config_write_byte, OPAL_PCI_CONFIG_WRITE_BYTE); +OPAL_CALL(opal_pci_config_write_half_word, OPAL_PCI_CONFIG_WRITE_HALF_WORD); +OPAL_CALL(opal_pci_config_write_word, OPAL_PCI_CONFIG_WRITE_WORD); +OPAL_CALL(opal_set_xive, OPAL_SET_XIVE); +OPAL_CALL(opal_get_xive, OPAL_GET_XIVE); +OPAL_CALL(opal_register_exception_handler, OPAL_REGISTER_OPAL_EXCEPTION_HANDLER); +OPAL_CALL(opal_pci_eeh_freeze_status, OPAL_PCI_EEH_FREEZE_STATUS); +OPAL_CALL(opal_pci_eeh_freeze_clear, OPAL_PCI_EEH_FREEZE_CLEAR); +OPAL_CALL(opal_pci_eeh_freeze_set, OPAL_PCI_EEH_FREEZE_SET); +OPAL_CALL(opal_pci_err_inject, OPAL_PCI_ERR_INJECT); +OPAL_CALL(opal_pci_shpc, OPAL_PCI_SHPC); +OPAL_CALL(opal_pci_phb_mmio_enable, OPAL_PCI_PHB_MMIO_ENABLE); +OPAL_CALL(opal_pci_set_phb_mem_window, OPAL_PCI_SET_PHB_MEM_WINDOW); +OPAL_CALL(opal_pci_map_pe_mmio_window, OPAL_PCI_MAP_PE_MMIO_WINDOW); +OPAL_CALL(opal_pci_set_phb_table_memory, OPAL_PCI_SET_PHB_TABLE_MEMORY); +OPAL_CALL(opal_pci_set_pe, OPAL_PCI_SET_PE); +OPAL_CALL(opal_pci_set_peltv, OPAL_PCI_SET_PELTV); +OPAL_CALL(opal_pci_set_mve, OPAL_PCI_SET_MVE); +OPAL_CALL(opal_pci_set_mve_enable, OPAL_PCI_SET_MVE_ENABLE); +OPAL_CALL(opal_pci_get_xive_reissue, OPAL_PCI_GET_XIVE_REISSUE); +OPAL_CALL(opal_pci_set_xive_reissue, OPAL_PCI_SET_XIVE_REISSUE); +OPAL_CALL(opal_pci_set_xive_pe, OPAL_PCI_SET_XIVE_PE); +OPAL_CALL(opal_get_xive_source, OPAL_GET_XIVE_SOURCE); +OPAL_CALL(opal_get_msi_32, OPAL_GET_MSI_32); +OPAL_CALL(opal_get_msi_64, OPAL_GET_MSI_64); +OPAL_CALL(opal_start_cpu, OPAL_START_CPU); +OPAL_CALL(opal_query_cpu_status, OPAL_QUERY_CPU_STATUS); +OPAL_CALL(opal_write_oppanel, OPAL_WRITE_OPPANEL); +OPAL_CALL(opal_pci_map_pe_dma_window, OPAL_PCI_MAP_PE_DMA_WINDOW); +OPAL_CALL(opal_pci_map_pe_dma_window_real, OPAL_PCI_MAP_PE_DMA_WINDOW_REAL); +OPAL_CALL(opal_pci_reset, OPAL_PCI_RESET); +OPAL_CALL(opal_pci_get_hub_diag_data, OPAL_PCI_GET_HUB_DIAG_DATA); +OPAL_CALL(opal_pci_get_phb_diag_data, OPAL_PCI_GET_PHB_DIAG_DATA); +OPAL_CALL(opal_pci_fence_phb, OPAL_PCI_FENCE_PHB); +OPAL_CALL(opal_pci_reinit, OPAL_PCI_REINIT); +OPAL_CALL(opal_pci_mask_pe_error, OPAL_PCI_MASK_PE_ERROR); +OPAL_CALL(opal_set_slot_led_status, OPAL_SET_SLOT_LED_STATUS); +OPAL_CALL(opal_get_epow_status, OPAL_GET_EPOW_STATUS); +OPAL_CALL(opal_get_dpo_status, OPAL_GET_DPO_STATUS); +OPAL_CALL(opal_set_system_attention_led, OPAL_SET_SYSTEM_ATTENTION_LED); +OPAL_CALL(opal_pci_next_error, OPAL_PCI_NEXT_ERROR); +OPAL_CALL(opal_pci_poll, OPAL_PCI_POLL); +OPAL_CALL(opal_pci_msi_eoi, OPAL_PCI_MSI_EOI); +OPAL_CALL(opal_pci_get_phb_diag_data2, OPAL_PCI_GET_PHB_DIAG_DATA2); +OPAL_CALL(opal_xscom_read, OPAL_XSCOM_READ); +OPAL_CALL(opal_xscom_write, OPAL_XSCOM_WRITE); +OPAL_CALL(opal_lpc_read, OPAL_LPC_READ); +OPAL_CALL(opal_lpc_write, OPAL_LPC_WRITE); +OPAL_CALL(opal_return_cpu, OPAL_RETURN_CPU); +OPAL_CALL(opal_reinit_cpus, OPAL_REINIT_CPUS); +OPAL_CALL(opal_read_elog, OPAL_ELOG_READ); +OPAL_CALL(opal_send_ack_elog, OPAL_ELOG_ACK); +OPAL_CALL(opal_get_elog_size, OPAL_ELOG_SIZE); +OPAL_CALL(opal_resend_pending_logs, OPAL_ELOG_RESEND); +OPAL_CALL(opal_write_elog, OPAL_ELOG_WRITE); +OPAL_CALL(opal_validate_flash, OPAL_FLASH_VALIDATE); +OPAL_CALL(opal_manage_flash, OPAL_FLASH_MANAGE); +OPAL_CALL(opal_update_flash, OPAL_FLASH_UPDATE); +OPAL_CALL(opal_resync_timebase, OPAL_RESYNC_TIMEBASE); +OPAL_CALL(opal_check_token, OPAL_CHECK_TOKEN); +OPAL_CALL(opal_dump_init, OPAL_DUMP_INIT); +OPAL_CALL(opal_dump_info, OPAL_DUMP_INFO); +OPAL_CALL(opal_dump_info2, OPAL_DUMP_INFO2); +OPAL_CALL(opal_dump_read, OPAL_DUMP_READ); +OPAL_CALL(opal_dump_ack, OPAL_DUMP_ACK); +OPAL_CALL(opal_get_msg, OPAL_GET_MSG); +OPAL_CALL(opal_write_oppanel_async, OPAL_WRITE_OPPANEL_ASYNC); +OPAL_CALL(opal_check_completion, OPAL_CHECK_ASYNC_COMPLETION); +OPAL_CALL(opal_dump_resend_notification, OPAL_DUMP_RESEND); +OPAL_CALL(opal_sync_host_reboot, OPAL_SYNC_HOST_REBOOT); +OPAL_CALL(opal_sensor_read, OPAL_SENSOR_READ); +OPAL_CALL(opal_get_param, OPAL_GET_PARAM); +OPAL_CALL(opal_set_param, OPAL_SET_PARAM); +OPAL_CALL(opal_handle_hmi, OPAL_HANDLE_HMI); +OPAL_CALL(opal_config_cpu_idle_state, OPAL_CONFIG_CPU_IDLE_STATE); +OPAL_CALL(opal_slw_set_reg, OPAL_SLW_SET_REG); +OPAL_CALL(opal_register_dump_region, OPAL_REGISTER_DUMP_REGION); +OPAL_CALL(opal_unregister_dump_region, OPAL_UNREGISTER_DUMP_REGION); +OPAL_CALL(opal_pci_set_phb_cxl_mode, OPAL_PCI_SET_PHB_CAPI_MODE); +OPAL_CALL(opal_tpo_write, OPAL_WRITE_TPO); +OPAL_CALL(opal_tpo_read, OPAL_READ_TPO); +OPAL_CALL(opal_ipmi_send, OPAL_IPMI_SEND); +OPAL_CALL(opal_ipmi_recv, OPAL_IPMI_RECV); +OPAL_CALL(opal_i2c_request, OPAL_I2C_REQUEST); +OPAL_CALL(opal_flash_read, OPAL_FLASH_READ); +OPAL_CALL(opal_flash_write, OPAL_FLASH_WRITE); +OPAL_CALL(opal_flash_erase, OPAL_FLASH_ERASE); +OPAL_CALL(opal_prd_msg, OPAL_PRD_MSG); +OPAL_CALL(opal_leds_get_ind, OPAL_LEDS_GET_INDICATOR); +OPAL_CALL(opal_leds_set_ind, OPAL_LEDS_SET_INDICATOR); +OPAL_CALL(opal_console_flush, OPAL_CONSOLE_FLUSH); +OPAL_CALL(opal_get_device_tree, OPAL_GET_DEVICE_TREE); +OPAL_CALL(opal_pci_get_presence_state, OPAL_PCI_GET_PRESENCE_STATE); +OPAL_CALL(opal_pci_get_power_state, OPAL_PCI_GET_POWER_STATE); +OPAL_CALL(opal_pci_set_power_state, OPAL_PCI_SET_POWER_STATE); +OPAL_CALL(opal_int_get_xirr, OPAL_INT_GET_XIRR); +OPAL_CALL(opal_int_set_cppr, OPAL_INT_SET_CPPR); +OPAL_CALL(opal_int_eoi, OPAL_INT_EOI); +OPAL_CALL(opal_int_set_mfrr, OPAL_INT_SET_MFRR); +OPAL_CALL(opal_pci_tce_kill, OPAL_PCI_TCE_KILL); +OPAL_CALL(opal_nmmu_set_ptcr, OPAL_NMMU_SET_PTCR); +OPAL_CALL(opal_xive_reset, OPAL_XIVE_RESET); +OPAL_CALL(opal_xive_get_irq_info, OPAL_XIVE_GET_IRQ_INFO); +OPAL_CALL(opal_xive_get_irq_config, OPAL_XIVE_GET_IRQ_CONFIG); +OPAL_CALL(opal_xive_set_irq_config, OPAL_XIVE_SET_IRQ_CONFIG); +OPAL_CALL(opal_xive_get_queue_info, OPAL_XIVE_GET_QUEUE_INFO); +OPAL_CALL(opal_xive_set_queue_info, OPAL_XIVE_SET_QUEUE_INFO); +OPAL_CALL(opal_xive_donate_page, OPAL_XIVE_DONATE_PAGE); +OPAL_CALL(opal_xive_alloc_vp_block, OPAL_XIVE_ALLOCATE_VP_BLOCK); +OPAL_CALL(opal_xive_free_vp_block, OPAL_XIVE_FREE_VP_BLOCK); +OPAL_CALL(opal_xive_allocate_irq_raw, OPAL_XIVE_ALLOCATE_IRQ); +OPAL_CALL(opal_xive_free_irq, OPAL_XIVE_FREE_IRQ); +OPAL_CALL(opal_xive_get_vp_info, OPAL_XIVE_GET_VP_INFO); +OPAL_CALL(opal_xive_set_vp_info, OPAL_XIVE_SET_VP_INFO); +OPAL_CALL(opal_xive_sync, OPAL_XIVE_SYNC); +OPAL_CALL(opal_xive_dump, OPAL_XIVE_DUMP); +OPAL_CALL(opal_npu_init_context, OPAL_NPU_INIT_CONTEXT); +OPAL_CALL(opal_npu_destroy_context, OPAL_NPU_DESTROY_CONTEXT); +OPAL_CALL(opal_npu_map_lpar, OPAL_NPU_MAP_LPAR); +OPAL_CALL(opal_imc_counters_init, OPAL_IMC_COUNTERS_INIT); +OPAL_CALL(opal_imc_counters_start, OPAL_IMC_COUNTERS_START); +OPAL_CALL(opal_imc_counters_stop, OPAL_IMC_COUNTERS_STOP); +OPAL_CALL(opal_pci_set_p2p, OPAL_PCI_SET_P2P); +OPAL_CALL(opal_get_powercap, OPAL_GET_POWERCAP); +OPAL_CALL(opal_set_powercap, OPAL_SET_POWERCAP); +OPAL_CALL(opal_get_power_shift_ratio, OPAL_GET_POWER_SHIFT_RATIO); +OPAL_CALL(opal_set_power_shift_ratio, OPAL_SET_POWER_SHIFT_RATIO); +OPAL_CALL(opal_sensor_group_clear, OPAL_SENSOR_GROUP_CLEAR); diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index a4abedc85b60..7cf3a64951b2 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -15,307 +15,53 @@ #include <asm/asm-offsets.h> #include <asm/opal.h> - .section ".text" - -#ifdef CONFIG_TRACEPOINTS -#ifdef HAVE_JUMP_LABEL -#define OPAL_BRANCH(LABEL) \ - ARCH_STATIC_BRANCH(LABEL, opal_tracepoint_key) -#else - - .section ".toc","aw" - - .globl opal_tracepoint_refcount -opal_tracepoint_refcount: - .llong 0 - - .section ".text" + .section ".text" /* - * We branch around this in early init by using an unconditional cpu - * feature. + * r3-r10 - OPAL call arguments + * STK_PARAM(R11) - OPAL opcode + * STK_PARAM(R12) - MSR to restore */ -#define OPAL_BRANCH(LABEL) \ -BEGIN_FTR_SECTION; \ - b 1f; \ -END_FTR_SECTION(0, 1); \ - ld r11,opal_tracepoint_refcount@toc(r2); \ - cmpdi r11,0; \ - bne- LABEL; \ -1: - -#endif - -#else -#define OPAL_BRANCH(LABEL) -#endif - -/* - * DO_OPAL_CALL assumes: - * r0 = opal call token - * r12 = msr - * LR has been saved - */ -#define DO_OPAL_CALL() \ - mfcr r11; \ - stw r11,8(r1); \ - li r11,0; \ - ori r11,r11,MSR_EE; \ - std r12,PACASAVEDMSR(r13); \ - andc r12,r12,r11; \ - mtmsrd r12,1; \ - LOAD_REG_ADDR(r11,opal_return); \ - mtlr r11; \ - li r11,MSR_DR|MSR_IR|MSR_LE;\ - andc r12,r12,r11; \ - mtspr SPRN_HSRR1,r12; \ - LOAD_REG_ADDR(r11,opal); \ - ld r12,8(r11); \ - ld r2,0(r11); \ - mtspr SPRN_HSRR0,r12; \ +_GLOBAL_TOC(__opal_call) + mflr r0 + std r0,PPC_LR_STKOFF(r1) + ld r12,STK_PARAM(R12)(r1) + li r0,MSR_IR|MSR_DR|MSR_LE + andc r12,r12,r0 + LOAD_REG_ADDR(r11, opal_return) + mtlr r11 + LOAD_REG_ADDR(r11, opal) + ld r2,0(r11) + ld r11,8(r11) + mtspr SPRN_HSRR0,r11 + mtspr SPRN_HSRR1,r12 + /* set token to r0 */ + ld r0,STK_PARAM(R11)(r1) hrfid -#define OPAL_CALL(name, token) \ - _GLOBAL_TOC(name); \ - mfmsr r12; \ - mflr r0; \ - andi. r11,r12,MSR_IR|MSR_DR; \ - std r0,PPC_LR_STKOFF(r1); \ - li r0,token; \ - beq opal_real_call; \ - OPAL_BRANCH(opal_tracepoint_entry) \ - DO_OPAL_CALL() - - opal_return: /* - * Fixup endian on OPAL return... we should be able to simplify - * this by instead converting the below trampoline to a set of - * bytes (always BE) since MSR:LE will end up fixed up as a side - * effect of the rfid. + * Restore MSR on OPAL return. The MSR is set to big-endian. */ - FIXUP_ENDIAN - ld r2,PACATOC(r13); - lwz r4,8(r1); - ld r5,PPC_LR_STKOFF(r1); - ld r6,PACASAVEDMSR(r13); - mtspr SPRN_SRR0,r5; - mtspr SPRN_SRR1,r6; - mtcr r4; - rfid - -opal_real_call: - mfcr r11 - stw r11,8(r1) - /* Set opal return address */ - LOAD_REG_ADDR(r11, opal_return_realmode) - mtlr r11 - li r11,MSR_LE - andc r12,r12,r11 - mtspr SPRN_HSRR1,r12 - LOAD_REG_ADDR(r11,opal) - ld r12,8(r11) - ld r2,0(r11) - mtspr SPRN_HSRR0,r12 - hrfid - -opal_return_realmode: - FIXUP_ENDIAN - ld r2,PACATOC(r13); - lwz r11,8(r1); - ld r12,PPC_LR_STKOFF(r1) - mtcr r11; - mtlr r12 - blr - -#ifdef CONFIG_TRACEPOINTS -opal_tracepoint_entry: - stdu r1,-STACKFRAMESIZE(r1) - std r0,STK_REG(R23)(r1) - std r3,STK_REG(R24)(r1) - std r4,STK_REG(R25)(r1) - std r5,STK_REG(R26)(r1) - std r6,STK_REG(R27)(r1) - std r7,STK_REG(R28)(r1) - std r8,STK_REG(R29)(r1) - std r9,STK_REG(R30)(r1) - std r10,STK_REG(R31)(r1) - mr r3,r0 - addi r4,r1,STK_REG(R24) - bl __trace_opal_entry - ld r0,STK_REG(R23)(r1) - ld r3,STK_REG(R24)(r1) - ld r4,STK_REG(R25)(r1) - ld r5,STK_REG(R26)(r1) - ld r6,STK_REG(R27)(r1) - ld r7,STK_REG(R28)(r1) - ld r8,STK_REG(R29)(r1) - ld r9,STK_REG(R30)(r1) - ld r10,STK_REG(R31)(r1) - - /* setup LR so we return via tracepoint_return */ - LOAD_REG_ADDR(r11,opal_tracepoint_return) - std r11,16(r1) - - mfmsr r12 - DO_OPAL_CALL() - -opal_tracepoint_return: - std r3,STK_REG(R31)(r1) - mr r4,r3 - ld r3,STK_REG(R23)(r1) - bl __trace_opal_exit - ld r3,STK_REG(R31)(r1) - addi r1,r1,STACKFRAMESIZE - ld r0,16(r1) +#ifdef __BIG_ENDIAN__ + ld r11,STK_PARAM(R12)(r1) + mtmsrd r11 +#else + /* Endian can only be switched with rfi, must byte reverse MSR load */ + .short 0x4039 /* li r10,STK_PARAM(R12) */ + .byte (STK_PARAM(R12) >> 8) & 0xff + .byte STK_PARAM(R12) & 0xff + + .long 0x280c6a7d /* ldbrx r11,r10,r1 */ + .long 0x05009f42 /* bcl 20,31,$+4 */ + .long 0xa602487d /* mflr r10 */ + .long 0x14004a39 /* addi r10,r10,20 */ + .long 0xa64b5a7d /* mthsrr0 r10 */ + .long 0xa64b7b7d /* mthsrr1 r11 */ + .long 0x2402004c /* hrfid */ +#endif + ld r2,PACATOC(r13) + ld r0,PPC_LR_STKOFF(r1) mtlr r0 blr -#endif - -OPAL_CALL(opal_invalid_call, OPAL_INVALID_CALL); -OPAL_CALL(opal_console_write, OPAL_CONSOLE_WRITE); -OPAL_CALL(opal_console_read, OPAL_CONSOLE_READ); -OPAL_CALL(opal_console_write_buffer_space, OPAL_CONSOLE_WRITE_BUFFER_SPACE); -OPAL_CALL(opal_rtc_read, OPAL_RTC_READ); -OPAL_CALL(opal_rtc_write, OPAL_RTC_WRITE); -OPAL_CALL(opal_cec_power_down, OPAL_CEC_POWER_DOWN); -OPAL_CALL(opal_cec_reboot, OPAL_CEC_REBOOT); -OPAL_CALL(opal_cec_reboot2, OPAL_CEC_REBOOT2); -OPAL_CALL(opal_read_nvram, OPAL_READ_NVRAM); -OPAL_CALL(opal_write_nvram, OPAL_WRITE_NVRAM); -OPAL_CALL(opal_handle_interrupt, OPAL_HANDLE_INTERRUPT); -OPAL_CALL(opal_poll_events, OPAL_POLL_EVENTS); -OPAL_CALL(opal_pci_set_hub_tce_memory, OPAL_PCI_SET_HUB_TCE_MEMORY); -OPAL_CALL(opal_pci_set_phb_tce_memory, OPAL_PCI_SET_PHB_TCE_MEMORY); -OPAL_CALL(opal_pci_config_read_byte, OPAL_PCI_CONFIG_READ_BYTE); -OPAL_CALL(opal_pci_config_read_half_word, OPAL_PCI_CONFIG_READ_HALF_WORD); -OPAL_CALL(opal_pci_config_read_word, OPAL_PCI_CONFIG_READ_WORD); -OPAL_CALL(opal_pci_config_write_byte, OPAL_PCI_CONFIG_WRITE_BYTE); -OPAL_CALL(opal_pci_config_write_half_word, OPAL_PCI_CONFIG_WRITE_HALF_WORD); -OPAL_CALL(opal_pci_config_write_word, OPAL_PCI_CONFIG_WRITE_WORD); -OPAL_CALL(opal_set_xive, OPAL_SET_XIVE); -OPAL_CALL(opal_get_xive, OPAL_GET_XIVE); -OPAL_CALL(opal_register_exception_handler, OPAL_REGISTER_OPAL_EXCEPTION_HANDLER); -OPAL_CALL(opal_pci_eeh_freeze_status, OPAL_PCI_EEH_FREEZE_STATUS); -OPAL_CALL(opal_pci_eeh_freeze_clear, OPAL_PCI_EEH_FREEZE_CLEAR); -OPAL_CALL(opal_pci_eeh_freeze_set, OPAL_PCI_EEH_FREEZE_SET); -OPAL_CALL(opal_pci_err_inject, OPAL_PCI_ERR_INJECT); -OPAL_CALL(opal_pci_shpc, OPAL_PCI_SHPC); -OPAL_CALL(opal_pci_phb_mmio_enable, OPAL_PCI_PHB_MMIO_ENABLE); -OPAL_CALL(opal_pci_set_phb_mem_window, OPAL_PCI_SET_PHB_MEM_WINDOW); -OPAL_CALL(opal_pci_map_pe_mmio_window, OPAL_PCI_MAP_PE_MMIO_WINDOW); -OPAL_CALL(opal_pci_set_phb_table_memory, OPAL_PCI_SET_PHB_TABLE_MEMORY); -OPAL_CALL(opal_pci_set_pe, OPAL_PCI_SET_PE); -OPAL_CALL(opal_pci_set_peltv, OPAL_PCI_SET_PELTV); -OPAL_CALL(opal_pci_set_mve, OPAL_PCI_SET_MVE); -OPAL_CALL(opal_pci_set_mve_enable, OPAL_PCI_SET_MVE_ENABLE); -OPAL_CALL(opal_pci_get_xive_reissue, OPAL_PCI_GET_XIVE_REISSUE); -OPAL_CALL(opal_pci_set_xive_reissue, OPAL_PCI_SET_XIVE_REISSUE); -OPAL_CALL(opal_pci_set_xive_pe, OPAL_PCI_SET_XIVE_PE); -OPAL_CALL(opal_get_xive_source, OPAL_GET_XIVE_SOURCE); -OPAL_CALL(opal_get_msi_32, OPAL_GET_MSI_32); -OPAL_CALL(opal_get_msi_64, OPAL_GET_MSI_64); -OPAL_CALL(opal_start_cpu, OPAL_START_CPU); -OPAL_CALL(opal_query_cpu_status, OPAL_QUERY_CPU_STATUS); -OPAL_CALL(opal_write_oppanel, OPAL_WRITE_OPPANEL); -OPAL_CALL(opal_pci_map_pe_dma_window, OPAL_PCI_MAP_PE_DMA_WINDOW); -OPAL_CALL(opal_pci_map_pe_dma_window_real, OPAL_PCI_MAP_PE_DMA_WINDOW_REAL); -OPAL_CALL(opal_pci_reset, OPAL_PCI_RESET); -OPAL_CALL(opal_pci_get_hub_diag_data, OPAL_PCI_GET_HUB_DIAG_DATA); -OPAL_CALL(opal_pci_get_phb_diag_data, OPAL_PCI_GET_PHB_DIAG_DATA); -OPAL_CALL(opal_pci_fence_phb, OPAL_PCI_FENCE_PHB); -OPAL_CALL(opal_pci_reinit, OPAL_PCI_REINIT); -OPAL_CALL(opal_pci_mask_pe_error, OPAL_PCI_MASK_PE_ERROR); -OPAL_CALL(opal_set_slot_led_status, OPAL_SET_SLOT_LED_STATUS); -OPAL_CALL(opal_get_epow_status, OPAL_GET_EPOW_STATUS); -OPAL_CALL(opal_get_dpo_status, OPAL_GET_DPO_STATUS); -OPAL_CALL(opal_set_system_attention_led, OPAL_SET_SYSTEM_ATTENTION_LED); -OPAL_CALL(opal_pci_next_error, OPAL_PCI_NEXT_ERROR); -OPAL_CALL(opal_pci_poll, OPAL_PCI_POLL); -OPAL_CALL(opal_pci_msi_eoi, OPAL_PCI_MSI_EOI); -OPAL_CALL(opal_pci_get_phb_diag_data2, OPAL_PCI_GET_PHB_DIAG_DATA2); -OPAL_CALL(opal_xscom_read, OPAL_XSCOM_READ); -OPAL_CALL(opal_xscom_write, OPAL_XSCOM_WRITE); -OPAL_CALL(opal_lpc_read, OPAL_LPC_READ); -OPAL_CALL(opal_lpc_write, OPAL_LPC_WRITE); -OPAL_CALL(opal_return_cpu, OPAL_RETURN_CPU); -OPAL_CALL(opal_reinit_cpus, OPAL_REINIT_CPUS); -OPAL_CALL(opal_read_elog, OPAL_ELOG_READ); -OPAL_CALL(opal_send_ack_elog, OPAL_ELOG_ACK); -OPAL_CALL(opal_get_elog_size, OPAL_ELOG_SIZE); -OPAL_CALL(opal_resend_pending_logs, OPAL_ELOG_RESEND); -OPAL_CALL(opal_write_elog, OPAL_ELOG_WRITE); -OPAL_CALL(opal_validate_flash, OPAL_FLASH_VALIDATE); -OPAL_CALL(opal_manage_flash, OPAL_FLASH_MANAGE); -OPAL_CALL(opal_update_flash, OPAL_FLASH_UPDATE); -OPAL_CALL(opal_resync_timebase, OPAL_RESYNC_TIMEBASE); -OPAL_CALL(opal_check_token, OPAL_CHECK_TOKEN); -OPAL_CALL(opal_dump_init, OPAL_DUMP_INIT); -OPAL_CALL(opal_dump_info, OPAL_DUMP_INFO); -OPAL_CALL(opal_dump_info2, OPAL_DUMP_INFO2); -OPAL_CALL(opal_dump_read, OPAL_DUMP_READ); -OPAL_CALL(opal_dump_ack, OPAL_DUMP_ACK); -OPAL_CALL(opal_get_msg, OPAL_GET_MSG); -OPAL_CALL(opal_write_oppanel_async, OPAL_WRITE_OPPANEL_ASYNC); -OPAL_CALL(opal_check_completion, OPAL_CHECK_ASYNC_COMPLETION); -OPAL_CALL(opal_dump_resend_notification, OPAL_DUMP_RESEND); -OPAL_CALL(opal_sync_host_reboot, OPAL_SYNC_HOST_REBOOT); -OPAL_CALL(opal_sensor_read, OPAL_SENSOR_READ); -OPAL_CALL(opal_get_param, OPAL_GET_PARAM); -OPAL_CALL(opal_set_param, OPAL_SET_PARAM); -OPAL_CALL(opal_handle_hmi, OPAL_HANDLE_HMI); -OPAL_CALL(opal_config_cpu_idle_state, OPAL_CONFIG_CPU_IDLE_STATE); -OPAL_CALL(opal_slw_set_reg, OPAL_SLW_SET_REG); -OPAL_CALL(opal_register_dump_region, OPAL_REGISTER_DUMP_REGION); -OPAL_CALL(opal_unregister_dump_region, OPAL_UNREGISTER_DUMP_REGION); -OPAL_CALL(opal_pci_set_phb_cxl_mode, OPAL_PCI_SET_PHB_CAPI_MODE); -OPAL_CALL(opal_tpo_write, OPAL_WRITE_TPO); -OPAL_CALL(opal_tpo_read, OPAL_READ_TPO); -OPAL_CALL(opal_ipmi_send, OPAL_IPMI_SEND); -OPAL_CALL(opal_ipmi_recv, OPAL_IPMI_RECV); -OPAL_CALL(opal_i2c_request, OPAL_I2C_REQUEST); -OPAL_CALL(opal_flash_read, OPAL_FLASH_READ); -OPAL_CALL(opal_flash_write, OPAL_FLASH_WRITE); -OPAL_CALL(opal_flash_erase, OPAL_FLASH_ERASE); -OPAL_CALL(opal_prd_msg, OPAL_PRD_MSG); -OPAL_CALL(opal_leds_get_ind, OPAL_LEDS_GET_INDICATOR); -OPAL_CALL(opal_leds_set_ind, OPAL_LEDS_SET_INDICATOR); -OPAL_CALL(opal_console_flush, OPAL_CONSOLE_FLUSH); -OPAL_CALL(opal_get_device_tree, OPAL_GET_DEVICE_TREE); -OPAL_CALL(opal_pci_get_presence_state, OPAL_PCI_GET_PRESENCE_STATE); -OPAL_CALL(opal_pci_get_power_state, OPAL_PCI_GET_POWER_STATE); -OPAL_CALL(opal_pci_set_power_state, OPAL_PCI_SET_POWER_STATE); -OPAL_CALL(opal_int_get_xirr, OPAL_INT_GET_XIRR); -OPAL_CALL(opal_int_set_cppr, OPAL_INT_SET_CPPR); -OPAL_CALL(opal_int_eoi, OPAL_INT_EOI); -OPAL_CALL(opal_int_set_mfrr, OPAL_INT_SET_MFRR); -OPAL_CALL(opal_pci_tce_kill, OPAL_PCI_TCE_KILL); -OPAL_CALL(opal_nmmu_set_ptcr, OPAL_NMMU_SET_PTCR); -OPAL_CALL(opal_xive_reset, OPAL_XIVE_RESET); -OPAL_CALL(opal_xive_get_irq_info, OPAL_XIVE_GET_IRQ_INFO); -OPAL_CALL(opal_xive_get_irq_config, OPAL_XIVE_GET_IRQ_CONFIG); -OPAL_CALL(opal_xive_set_irq_config, OPAL_XIVE_SET_IRQ_CONFIG); -OPAL_CALL(opal_xive_get_queue_info, OPAL_XIVE_GET_QUEUE_INFO); -OPAL_CALL(opal_xive_set_queue_info, OPAL_XIVE_SET_QUEUE_INFO); -OPAL_CALL(opal_xive_donate_page, OPAL_XIVE_DONATE_PAGE); -OPAL_CALL(opal_xive_alloc_vp_block, OPAL_XIVE_ALLOCATE_VP_BLOCK); -OPAL_CALL(opal_xive_free_vp_block, OPAL_XIVE_FREE_VP_BLOCK); -OPAL_CALL(opal_xive_allocate_irq, OPAL_XIVE_ALLOCATE_IRQ); -OPAL_CALL(opal_xive_free_irq, OPAL_XIVE_FREE_IRQ); -OPAL_CALL(opal_xive_get_vp_info, OPAL_XIVE_GET_VP_INFO); -OPAL_CALL(opal_xive_set_vp_info, OPAL_XIVE_SET_VP_INFO); -OPAL_CALL(opal_xive_sync, OPAL_XIVE_SYNC); -OPAL_CALL(opal_xive_dump, OPAL_XIVE_DUMP); -OPAL_CALL(opal_npu_init_context, OPAL_NPU_INIT_CONTEXT); -OPAL_CALL(opal_npu_destroy_context, OPAL_NPU_DESTROY_CONTEXT); -OPAL_CALL(opal_npu_map_lpar, OPAL_NPU_MAP_LPAR); -OPAL_CALL(opal_imc_counters_init, OPAL_IMC_COUNTERS_INIT); -OPAL_CALL(opal_imc_counters_start, OPAL_IMC_COUNTERS_START); -OPAL_CALL(opal_imc_counters_stop, OPAL_IMC_COUNTERS_STOP); -OPAL_CALL(opal_pci_set_p2p, OPAL_PCI_SET_P2P); -OPAL_CALL(opal_get_powercap, OPAL_GET_POWERCAP); -OPAL_CALL(opal_set_powercap, OPAL_SET_POWERCAP); -OPAL_CALL(opal_get_power_shift_ratio, OPAL_GET_POWER_SHIFT_RATIO); -OPAL_CALL(opal_set_power_shift_ratio, OPAL_SET_POWER_SHIFT_RATIO); -OPAL_CALL(opal_sensor_group_clear, OPAL_SENSOR_GROUP_CLEAR); diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index aa82a83e4c39..79aa32aeee4e 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -101,11 +101,12 @@ static struct property *dlpar_clone_property(struct property *prop, return new_prop; } -static u32 find_aa_index(struct device_node *dr_node, - struct property *ala_prop, const u32 *lmb_assoc) +static bool find_aa_index(struct device_node *dr_node, + struct property *ala_prop, + const u32 *lmb_assoc, u32 *aa_index) { - u32 *assoc_arrays; - u32 aa_index; + u32 *assoc_arrays, new_prop_size; + struct property *new_prop; int aa_arrays, aa_array_entries, aa_array_sz; int i, index; @@ -121,75 +122,68 @@ static u32 find_aa_index(struct device_node *dr_node, aa_array_entries = be32_to_cpu(assoc_arrays[1]); aa_array_sz = aa_array_entries * sizeof(u32); - aa_index = -1; for (i = 0; i < aa_arrays; i++) { index = (i * aa_array_entries) + 2; if (memcmp(&assoc_arrays[index], &lmb_assoc[1], aa_array_sz)) continue; - aa_index = i; - break; + *aa_index = i; + return true; } - if (aa_index == -1) { - struct property *new_prop; - u32 new_prop_size; - - new_prop_size = ala_prop->length + aa_array_sz; - new_prop = dlpar_clone_property(ala_prop, new_prop_size); - if (!new_prop) - return -1; + new_prop_size = ala_prop->length + aa_array_sz; + new_prop = dlpar_clone_property(ala_prop, new_prop_size); + if (!new_prop) + return false; - assoc_arrays = new_prop->value; + assoc_arrays = new_prop->value; - /* increment the number of entries in the lookup array */ - assoc_arrays[0] = cpu_to_be32(aa_arrays + 1); + /* increment the number of entries in the lookup array */ + assoc_arrays[0] = cpu_to_be32(aa_arrays + 1); - /* copy the new associativity into the lookup array */ - index = aa_arrays * aa_array_entries + 2; - memcpy(&assoc_arrays[index], &lmb_assoc[1], aa_array_sz); + /* copy the new associativity into the lookup array */ + index = aa_arrays * aa_array_entries + 2; + memcpy(&assoc_arrays[index], &lmb_assoc[1], aa_array_sz); - of_update_property(dr_node, new_prop); + of_update_property(dr_node, new_prop); - /* - * The associativity lookup array index for this lmb is - * number of entries - 1 since we added its associativity - * to the end of the lookup array. - */ - aa_index = be32_to_cpu(assoc_arrays[0]) - 1; - } - - return aa_index; + /* + * The associativity lookup array index for this lmb is + * number of entries - 1 since we added its associativity + * to the end of the lookup array. + */ + *aa_index = be32_to_cpu(assoc_arrays[0]) - 1; + return true; } -static u32 lookup_lmb_associativity_index(struct drmem_lmb *lmb) +static u32 lookup_lmb_associativity_index(struct drmem_lmb *lmb, u32 *aa_index) { struct device_node *parent, *lmb_node, *dr_node; struct property *ala_prop; const u32 *lmb_assoc; - u32 aa_index; + bool found; parent = of_find_node_by_path("/"); if (!parent) - return -ENODEV; + return false; lmb_node = dlpar_configure_connector(cpu_to_be32(lmb->drc_index), parent); of_node_put(parent); if (!lmb_node) - return -EINVAL; + return false; lmb_assoc = of_get_property(lmb_node, "ibm,associativity", NULL); if (!lmb_assoc) { dlpar_free_cc_nodes(lmb_node); - return -ENODEV; + return false; } dr_node = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); if (!dr_node) { dlpar_free_cc_nodes(lmb_node); - return -ENODEV; + return false; } ala_prop = of_find_property(dr_node, "ibm,associativity-lookup-arrays", @@ -197,26 +191,27 @@ static u32 lookup_lmb_associativity_index(struct drmem_lmb *lmb) if (!ala_prop) { of_node_put(dr_node); dlpar_free_cc_nodes(lmb_node); - return -ENODEV; + return false; } - aa_index = find_aa_index(dr_node, ala_prop, lmb_assoc); + found = find_aa_index(dr_node, ala_prop, lmb_assoc, aa_index); dlpar_free_cc_nodes(lmb_node); - return aa_index; + return found; } static int dlpar_add_device_tree_lmb(struct drmem_lmb *lmb) { int rc, aa_index; + bool found; lmb->flags |= DRCONF_MEM_ASSIGNED; - aa_index = lookup_lmb_associativity_index(lmb); - if (aa_index < 0) { + found = lookup_lmb_associativity_index(lmb, &aa_index); + if (!found) { pr_err("Couldn't find associativity index for drc index %x\n", lmb->drc_index); - return aa_index; + return -ENODEV; } lmb->aa_index = aa_index; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index fa3f19c5abca..ffe9b722ded3 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -64,6 +64,22 @@ EXPORT_SYMBOL(plpar_hcall); EXPORT_SYMBOL(plpar_hcall9); EXPORT_SYMBOL(plpar_hcall_norets); +/* + * H_BLOCK_REMOVE supported block size for this page size in segment who's base + * page size is that page size. + * + * The first index is the segment base page size, the second one is the actual + * page size. + */ +static int hblkrm_size[MMU_PAGE_COUNT][MMU_PAGE_COUNT] __ro_after_init; + +/* + * Due to the involved complexity, and that the current hypervisor is only + * returning this value or 0, we are limiting the support of the H_BLOCK_REMOVE + * buffer size to 8 size block. + */ +#define HBLKRM_SUPPORTED_BLOCK_SIZE 8 + void vpa_init(int cpu) { int hwcpu = get_hard_smp_processor_id(cpu); @@ -425,6 +441,17 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn, #define HBLKR_CTRL_ERRNOTFOUND 0x8800000000000000UL #define HBLKR_CTRL_ERRBUSY 0xa000000000000000UL +/* + * Returned true if we are supporting this block size for the specified segment + * base page size and actual page size. + * + * Currently, we only support 8 size block. + */ +static inline bool is_supported_hlbkrm(int bpsize, int psize) +{ + return (hblkrm_size[bpsize][psize] == HBLKRM_SUPPORTED_BLOCK_SIZE); +} + /** * H_BLOCK_REMOVE caller. * @idx should point to the latest @param entry set with a PTEX. @@ -584,7 +611,8 @@ static inline void __pSeries_lpar_hugepage_invalidate(unsigned long *slot, if (lock_tlbie) spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags); - if (firmware_has_feature(FW_FEATURE_BLOCK_REMOVE)) + /* Assuming THP size is 16M */ + if (is_supported_hlbkrm(psize, MMU_PAGE_16M)) hugepage_block_invalidate(slot, vpn, count, psize, ssize); else hugepage_bulk_invalidate(slot, vpn, count, psize, ssize); @@ -753,6 +781,137 @@ static void do_block_remove(unsigned long number, struct ppc64_tlb_batch *batch, } /* + * TLB Block Invalidate Characteristics + * + * These characteristics define the size of the block the hcall H_BLOCK_REMOVE + * is able to process for each couple segment base page size, actual page size. + * + * The ibm,get-system-parameter properties is returning a buffer with the + * following layout: + * + * [ 2 bytes size of the RTAS buffer (excluding these 2 bytes) ] + * ----------------- + * TLB Block Invalidate Specifiers: + * [ 1 byte LOG base 2 of the TLB invalidate block size being specified ] + * [ 1 byte Number of page sizes (N) that are supported for the specified + * TLB invalidate block size ] + * [ 1 byte Encoded segment base page size and actual page size + * MSB=0 means 4k segment base page size and actual page size + * MSB=1 the penc value in mmu_psize_def ] + * ... + * ----------------- + * Next TLB Block Invalidate Specifiers... + * ----------------- + * [ 0 ] + */ +static inline void set_hblkrm_bloc_size(int bpsize, int psize, + unsigned int block_size) +{ + if (block_size > hblkrm_size[bpsize][psize]) + hblkrm_size[bpsize][psize] = block_size; +} + +/* + * Decode the Encoded segment base page size and actual page size. + * PAPR specifies: + * - bit 7 is the L bit + * - bits 0-5 are the penc value + * If the L bit is 0, this means 4K segment base page size and actual page size + * otherwise the penc value should be read. + */ +#define HBLKRM_L_MASK 0x80 +#define HBLKRM_PENC_MASK 0x3f +static inline void __init check_lp_set_hblkrm(unsigned int lp, + unsigned int block_size) +{ + unsigned int bpsize, psize; + + /* First, check the L bit, if not set, this means 4K */ + if ((lp & HBLKRM_L_MASK) == 0) { + set_hblkrm_bloc_size(MMU_PAGE_4K, MMU_PAGE_4K, block_size); + return; + } + + lp &= HBLKRM_PENC_MASK; + for (bpsize = 0; bpsize < MMU_PAGE_COUNT; bpsize++) { + struct mmu_psize_def *def = &mmu_psize_defs[bpsize]; + + for (psize = 0; psize < MMU_PAGE_COUNT; psize++) { + if (def->penc[psize] == lp) { + set_hblkrm_bloc_size(bpsize, psize, block_size); + return; + } + } + } +} + +#define SPLPAR_TLB_BIC_TOKEN 50 + +/* + * The size of the TLB Block Invalidate Characteristics is variable. But at the + * maximum it will be the number of possible page sizes *2 + 10 bytes. + * Currently MMU_PAGE_COUNT is 16, which means 42 bytes. Use a cache line size + * (128 bytes) for the buffer to get plenty of space. + */ +#define SPLPAR_TLB_BIC_MAXLENGTH 128 + +void __init pseries_lpar_read_hblkrm_characteristics(void) +{ + unsigned char local_buffer[SPLPAR_TLB_BIC_MAXLENGTH]; + int call_status, len, idx, bpsize; + + spin_lock(&rtas_data_buf_lock); + memset(rtas_data_buf, 0, RTAS_DATA_BUF_SIZE); + call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1, + NULL, + SPLPAR_TLB_BIC_TOKEN, + __pa(rtas_data_buf), + RTAS_DATA_BUF_SIZE); + memcpy(local_buffer, rtas_data_buf, SPLPAR_TLB_BIC_MAXLENGTH); + local_buffer[SPLPAR_TLB_BIC_MAXLENGTH - 1] = '\0'; + spin_unlock(&rtas_data_buf_lock); + + if (call_status != 0) { + pr_warn("%s %s Error calling get-system-parameter (0x%x)\n", + __FILE__, __func__, call_status); + return; + } + + /* + * The first two (2) bytes of the data in the buffer are the length of + * the returned data, not counting these first two (2) bytes. + */ + len = be16_to_cpu(*((u16 *)local_buffer)) + 2; + if (len > SPLPAR_TLB_BIC_MAXLENGTH) { + pr_warn("%s too large returned buffer %d", __func__, len); + return; + } + + idx = 2; + while (idx < len) { + u8 block_shift = local_buffer[idx++]; + u32 block_size; + unsigned int npsize; + + if (!block_shift) + break; + + block_size = 1 << block_shift; + + for (npsize = local_buffer[idx++]; + npsize > 0 && idx < len; npsize--) + check_lp_set_hblkrm((unsigned int) local_buffer[idx++], + block_size); + } + + for (bpsize = 0; bpsize < MMU_PAGE_COUNT; bpsize++) + for (idx = 0; idx < MMU_PAGE_COUNT; idx++) + if (hblkrm_size[bpsize][idx]) + pr_info("H_BLOCK_REMOVE supports base psize:%d psize:%d block size:%d", + bpsize, idx, hblkrm_size[bpsize][idx]); +} + +/* * Take a spinlock around flushes to avoid bouncing the hypervisor tlbie * lock. */ @@ -771,7 +930,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local) if (lock_tlbie) spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags); - if (firmware_has_feature(FW_FEATURE_BLOCK_REMOVE)) { + if (is_supported_hlbkrm(batch->psize, batch->psize)) { do_block_remove(number, batch, param); goto out; } diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 120b132ede25..fcea35f4409d 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -103,5 +103,6 @@ static inline unsigned long cmo_get_page_size(void) int dlpar_workqueue_init(void); void pseries_setup_rfi_flush(void); +void pseries_lpar_read_hblkrm_characteristics(void); #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 076d6e6c6c99..89da2bbe1b39 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -759,6 +759,7 @@ static void __init pSeries_setup_arch(void) pseries_setup_rfi_flush(); setup_stf_barrier(); + pseries_lpar_read_hblkrm_characteristics(); /* By default, only probe PCI (can be overridden by rtas_pci) */ pci_add_flags(PCI_PROBE_ONLY); diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index b46030e6f49d..5d127c81d25d 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -249,6 +249,17 @@ static bool xive_native_match(struct device_node *node) return of_device_is_compatible(node, "ibm,opal-xive-vc"); } +static s64 opal_xive_allocate_irq(u32 chip_id) +{ + s64 irq = opal_xive_allocate_irq_raw(chip_id); + + /* + * Old versions of skiboot can incorrectly return 0xffffffff to + * indicate no space, fix it up here. + */ + return irq == 0xffffffff ? OPAL_RESOURCE : irq; +} + #ifdef CONFIG_SMP static int xive_native_get_ipi(unsigned int cpu, struct xive_cpu *xc) { diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 4dd696907d3c..c98f757395a2 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -21,7 +21,6 @@ #include <linux/init.h> #include <linux/list.h> #include <linux/module.h> -#include <linux/memory.h> #include <trace/syscall.h> @@ -35,7 +34,6 @@ int ftrace_arch_code_modify_prepare(void) { - mutex_lock(&text_mutex); set_kernel_text_rw(); set_all_modules_text_rw(); return 0; @@ -45,7 +43,6 @@ int ftrace_arch_code_modify_post_process(void) { set_all_modules_text_ro(); set_kernel_text_ro(); - mutex_unlock(&text_mutex); return 0; } diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 682b24ebb604..9ae30c60bebe 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -196,9 +196,6 @@ static ssize_t write_mem(struct file *file, const char __user *buf, if (p != *ppos) return -EFBIG; - if (kernel_is_locked_down()) - return -EPERM; - if (!valid_phys_addr_range(p, count)) return -EFAULT; @@ -560,9 +557,6 @@ static ssize_t write_kmem(struct file *file, const char __user *buf, char *kbuf; /* k-addr because vwrite() takes vmlist_lock rwlock */ int err = 0; - if (kernel_is_locked_down()) - return -EPERM; - if (p < (unsigned long) high_memory) { unsigned long to_write = min_t(unsigned long, count, (unsigned long)high_memory - p); diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 4cc0b42f2acc..7568213f3c0f 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -769,7 +769,7 @@ static int at24_probe(struct i2c_client *client, const struct i2c_device_id *id) at24->nvmem_config.name = dev_name(&client->dev); at24->nvmem_config.dev = &client->dev; at24->nvmem_config.read_only = !writable; - at24->nvmem_config.root_only = true; + at24->nvmem_config.root_only = !(chip.flags & AT24_FLAG_IRUGO); at24->nvmem_config.owner = THIS_MODULE; at24->nvmem_config.compat = true; at24->nvmem_config.base_dev = &client->dev; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 4c1b1ad782a4..557bf4ccdc77 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1218,7 +1218,7 @@ static void ibmvnic_cleanup(struct net_device *netdev) struct ibmvnic_adapter *adapter = netdev_priv(netdev); /* ensure that transmissions are stopped if called by do_reset */ - if (adapter->resetting) + if (test_bit(0, &adapter->resetting)) netif_tx_disable(netdev); else netif_tx_stop_all_queues(netdev); @@ -1439,7 +1439,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) u8 proto = 0; netdev_tx_t ret = NETDEV_TX_OK; - if (adapter->resetting) { + if (test_bit(0, &adapter->resetting)) { if (!netif_subqueue_stopped(netdev, skb)) netif_stop_subqueue(netdev, queue_num); dev_kfree_skb_any(skb); @@ -1735,6 +1735,86 @@ static int ibmvnic_set_mac(struct net_device *netdev, void *p) } /** + * do_change_param_reset returns zero if we are able to keep processing reset + * events, or non-zero if we hit a fatal error and must halt. + */ +static int do_change_param_reset(struct ibmvnic_adapter *adapter, + struct ibmvnic_rwi *rwi, + u32 reset_state) +{ + struct net_device *netdev = adapter->netdev; + int i, rc; + + netdev_dbg(adapter->netdev, "Change param resetting driver (%d)\n", + rwi->reset_reason); + + netif_carrier_off(netdev); + adapter->reset_reason = rwi->reset_reason; + + ibmvnic_cleanup(netdev); + + if (reset_state == VNIC_OPEN) { + rc = __ibmvnic_close(netdev); + if (rc) + return rc; + } + + release_resources(adapter); + release_sub_crqs(adapter, 1); + release_crq_queue(adapter); + + adapter->state = VNIC_PROBED; + + rc = init_crq_queue(adapter); + + if (rc) { + netdev_err(adapter->netdev, + "Couldn't initialize crq. rc=%d\n", rc); + return rc; + } + + rc = ibmvnic_reset_init(adapter); + if (rc) + return IBMVNIC_INIT_FAILED; + + /* If the adapter was in PROBE state prior to the reset, + * exit here. + */ + if (reset_state == VNIC_PROBED) + return 0; + + rc = ibmvnic_login(netdev); + if (rc) { + adapter->state = reset_state; + return rc; + } + + rc = init_resources(adapter); + if (rc) + return rc; + + ibmvnic_disable_irqs(adapter); + + adapter->state = VNIC_CLOSED; + + if (reset_state == VNIC_CLOSED) + return 0; + + rc = __ibmvnic_open(netdev); + if (rc) + return IBMVNIC_OPEN_FAILED; + + /* refresh device's multicast list */ + ibmvnic_set_multi(netdev); + + /* kick napi */ + for (i = 0; i < adapter->req_rx_queues; i++) + napi_schedule(&adapter->napi[i]); + + return 0; +} + +/** * do_reset returns zero if we are able to keep processing reset events, or * non-zero if we hit a fatal error and must halt. */ @@ -1749,6 +1829,8 @@ static int do_reset(struct ibmvnic_adapter *adapter, netdev_dbg(adapter->netdev, "Re-setting driver (%d)\n", rwi->reset_reason); + rtnl_lock(); + netif_carrier_off(netdev); adapter->reset_reason = rwi->reset_reason; @@ -1762,16 +1844,25 @@ static int do_reset(struct ibmvnic_adapter *adapter, if (reset_state == VNIC_OPEN && adapter->reset_reason != VNIC_RESET_MOBILITY && adapter->reset_reason != VNIC_RESET_FAILOVER) { - rc = __ibmvnic_close(netdev); + adapter->state = VNIC_CLOSING; + + /* Release the RTNL lock before link state change and + * re-acquire after the link state change to allow + * linkwatch_event to grab the RTNL lock and run during + * a reset. + */ + rtnl_unlock(); + rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_DN); + rtnl_lock(); if (rc) - return rc; - } + goto out; - if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM || - adapter->wait_for_reset) { - release_resources(adapter); - release_sub_crqs(adapter, 1); - release_crq_queue(adapter); + if (adapter->state != VNIC_CLOSING) { + rc = -1; + goto out; + } + + adapter->state = VNIC_CLOSED; } if (adapter->reset_reason != VNIC_RESET_NON_FATAL) { @@ -1780,9 +1871,7 @@ static int do_reset(struct ibmvnic_adapter *adapter, */ adapter->state = VNIC_PROBED; - if (adapter->wait_for_reset) { - rc = init_crq_queue(adapter); - } else if (adapter->reset_reason == VNIC_RESET_MOBILITY) { + if (adapter->reset_reason == VNIC_RESET_MOBILITY) { rc = ibmvnic_reenable_crq_queue(adapter); release_sub_crqs(adapter, 1); } else { @@ -1794,36 +1883,35 @@ static int do_reset(struct ibmvnic_adapter *adapter, if (rc) { netdev_err(adapter->netdev, "Couldn't initialize crq. rc=%d\n", rc); - return rc; + goto out; } rc = ibmvnic_reset_init(adapter); - if (rc) - return IBMVNIC_INIT_FAILED; + if (rc) { + rc = IBMVNIC_INIT_FAILED; + goto out; + } /* If the adapter was in PROBE state prior to the reset, * exit here. */ - if (reset_state == VNIC_PROBED) - return 0; + if (reset_state == VNIC_PROBED) { + rc = 0; + goto out; + } rc = ibmvnic_login(netdev); if (rc) { adapter->state = reset_state; - return rc; + goto out; } - if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM || - adapter->wait_for_reset) { - rc = init_resources(adapter); - if (rc) - return rc; - } else if (adapter->req_rx_queues != old_num_rx_queues || - adapter->req_tx_queues != old_num_tx_queues || - adapter->req_rx_add_entries_per_subcrq != - old_num_rx_slots || - adapter->req_tx_entries_per_subcrq != - old_num_tx_slots) { + if (adapter->req_rx_queues != old_num_rx_queues || + adapter->req_tx_queues != old_num_tx_queues || + adapter->req_rx_add_entries_per_subcrq != + old_num_rx_slots || + adapter->req_tx_entries_per_subcrq != + old_num_tx_slots) { release_rx_pools(adapter); release_tx_pools(adapter); release_napi(adapter); @@ -1831,32 +1919,30 @@ static int do_reset(struct ibmvnic_adapter *adapter, rc = init_resources(adapter); if (rc) - return rc; + goto out; } else { rc = reset_tx_pools(adapter); if (rc) - return rc; + goto out; rc = reset_rx_pools(adapter); if (rc) - return rc; + goto out; } ibmvnic_disable_irqs(adapter); } adapter->state = VNIC_CLOSED; - if (reset_state == VNIC_CLOSED) - return 0; + if (reset_state == VNIC_CLOSED) { + rc = 0; + goto out; + } rc = __ibmvnic_open(netdev); if (rc) { - if (list_empty(&adapter->rwi_list)) - adapter->state = VNIC_CLOSED; - else - adapter->state = reset_state; - - return 0; + rc = IBMVNIC_OPEN_FAILED; + goto out; } /* refresh device's multicast list */ @@ -1866,11 +1952,15 @@ static int do_reset(struct ibmvnic_adapter *adapter, for (i = 0; i < adapter->req_rx_queues; i++) napi_schedule(&adapter->napi[i]); - if (adapter->reset_reason != VNIC_RESET_FAILOVER && - adapter->reset_reason != VNIC_RESET_CHANGE_PARAM) + if (adapter->reset_reason != VNIC_RESET_FAILOVER) call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, netdev); - return 0; + rc = 0; + +out: + rtnl_unlock(); + + return rc; } static int do_hard_reset(struct ibmvnic_adapter *adapter, @@ -1930,14 +2020,8 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter, return 0; rc = __ibmvnic_open(netdev); - if (rc) { - if (list_empty(&adapter->rwi_list)) - adapter->state = VNIC_CLOSED; - else - adapter->state = reset_state; - - return 0; - } + if (rc) + return IBMVNIC_OPEN_FAILED; return 0; } @@ -1976,20 +2060,17 @@ static void __ibmvnic_reset(struct work_struct *work) { struct ibmvnic_rwi *rwi; struct ibmvnic_adapter *adapter; - bool we_lock_rtnl = false; u32 reset_state; int rc = 0; adapter = container_of(work, struct ibmvnic_adapter, ibmvnic_reset); - /* netif_set_real_num_xx_queues needs to take rtnl lock here - * unless wait_for_reset is set, in which case the rtnl lock - * has already been taken before initializing the reset - */ - if (!adapter->wait_for_reset) { - rtnl_lock(); - we_lock_rtnl = true; + if (test_and_set_bit_lock(0, &adapter->resetting)) { + schedule_delayed_work(&adapter->ibmvnic_delayed_reset, + IBMVNIC_RESET_DELAY); + return; } + reset_state = adapter->state; rwi = get_next_rwi(adapter); @@ -2001,22 +2082,43 @@ static void __ibmvnic_reset(struct work_struct *work) break; } - if (adapter->force_reset_recovery) { - adapter->force_reset_recovery = false; - rc = do_hard_reset(adapter, rwi, reset_state); + if (rwi->reset_reason == VNIC_RESET_CHANGE_PARAM) { + /* CHANGE_PARAM requestor holds rtnl_lock */ + rc = do_change_param_reset(adapter, rwi, reset_state); + } else if (adapter->force_reset_recovery) { + /* Transport event occurred during previous reset */ + if (adapter->wait_for_reset) { + /* Previous was CHANGE_PARAM; caller locked */ + adapter->force_reset_recovery = false; + rc = do_hard_reset(adapter, rwi, reset_state); + } else { + rtnl_lock(); + adapter->force_reset_recovery = false; + rc = do_hard_reset(adapter, rwi, reset_state); + rtnl_unlock(); + } } else { rc = do_reset(adapter, rwi, reset_state); } kfree(rwi); - if (rc && rc != IBMVNIC_INIT_FAILED && + if (rc == IBMVNIC_OPEN_FAILED) { + if (list_empty(&adapter->rwi_list)) + adapter->state = VNIC_CLOSED; + else + adapter->state = reset_state; + rc = 0; + } else if (rc && rc != IBMVNIC_INIT_FAILED && !adapter->force_reset_recovery) break; rwi = get_next_rwi(adapter); + + if (rwi && (rwi->reset_reason == VNIC_RESET_FAILOVER || + rwi->reset_reason == VNIC_RESET_MOBILITY)) + adapter->force_reset_recovery = true; } if (adapter->wait_for_reset) { - adapter->wait_for_reset = false; adapter->reset_done_rc = rc; complete(&adapter->reset_done); } @@ -2026,9 +2128,16 @@ static void __ibmvnic_reset(struct work_struct *work) free_all_rwi(adapter); } - adapter->resetting = false; - if (we_lock_rtnl) - rtnl_unlock(); + clear_bit_unlock(0, &adapter->resetting); +} + +static void __ibmvnic_delayed_reset(struct work_struct *work) +{ + struct ibmvnic_adapter *adapter; + + adapter = container_of(work, struct ibmvnic_adapter, + ibmvnic_delayed_reset.work); + __ibmvnic_reset(&adapter->ibmvnic_reset); } static int ibmvnic_reset(struct ibmvnic_adapter *adapter, @@ -2083,14 +2192,11 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter, rwi->reset_reason = reason; list_add_tail(&rwi->list, &adapter->rwi_list); spin_unlock_irqrestore(&adapter->rwi_lock, flags); - adapter->resetting = true; netdev_dbg(adapter->netdev, "Scheduling reset (reason %d)\n", reason); schedule_work(&adapter->ibmvnic_reset); return 0; err: - if (adapter->wait_for_reset) - adapter->wait_for_reset = false; return -ret; } @@ -2130,7 +2236,7 @@ restart_poll: u16 offset; u8 flags = 0; - if (unlikely(adapter->resetting && + if (unlikely(test_bit(0, &adapter->resetting) && adapter->reset_reason != VNIC_RESET_NON_FATAL)) { enable_scrq_irq(adapter, adapter->rx_scrq[scrq_num]); napi_complete_done(napi, frames_processed); @@ -2781,7 +2887,7 @@ static int enable_scrq_irq(struct ibmvnic_adapter *adapter, return 1; } - if (adapter->resetting && + if (test_bit(0, &adapter->resetting) && adapter->reset_reason == VNIC_RESET_MOBILITY) { u64 val = (0xff000000) | scrq->hw_irq; @@ -3331,7 +3437,7 @@ static int ibmvnic_send_crq(struct ibmvnic_adapter *adapter, if (rc) { if (rc == H_CLOSED) { dev_warn(dev, "CRQ Queue closed\n"); - if (adapter->resetting) + if (test_bit(0, &adapter->resetting)) ibmvnic_reset(adapter, VNIC_RESET_FATAL); } @@ -4406,7 +4512,7 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, case IBMVNIC_CRQ_XPORT_EVENT: netif_carrier_off(netdev); adapter->crq.active = false; - if (adapter->resetting) + if (test_bit(0, &adapter->resetting)) adapter->force_reset_recovery = true; if (gen_crq->cmd == IBMVNIC_PARTITION_MIGRATED) { dev_info(dev, "Migrated, re-enabling adapter\n"); @@ -4744,7 +4850,7 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter) return -1; } - if (adapter->resetting && !adapter->wait_for_reset && + if (test_bit(0, &adapter->resetting) && !adapter->wait_for_reset && adapter->reset_reason != VNIC_RESET_MOBILITY) { if (adapter->req_rx_queues != old_num_rx_queues || adapter->req_tx_queues != old_num_tx_queues) { @@ -4856,10 +4962,12 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) spin_lock_init(&adapter->stats_lock); INIT_WORK(&adapter->ibmvnic_reset, __ibmvnic_reset); + INIT_DELAYED_WORK(&adapter->ibmvnic_delayed_reset, + __ibmvnic_delayed_reset); INIT_LIST_HEAD(&adapter->rwi_list); spin_lock_init(&adapter->rwi_lock); init_completion(&adapter->init_done); - adapter->resetting = false; + clear_bit(0, &adapter->resetting); do { rc = init_crq_queue(adapter); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index dcf2eb6d9290..ef050f948128 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -31,6 +31,7 @@ #define IBMVNIC_INVALID_MAP -1 #define IBMVNIC_STATS_TIMEOUT 1 #define IBMVNIC_INIT_FAILED 2 +#define IBMVNIC_OPEN_FAILED 3 /* basic structures plus 100 2k buffers */ #define IBMVNIC_IO_ENTITLEMENT_DEFAULT 610305 @@ -49,6 +50,8 @@ #define IBMVNIC_MAX_LTB_SIZE ((1 << (MAX_ORDER - 1)) * PAGE_SIZE) #define IBMVNIC_BUFFER_HLEN 500 +#define IBMVNIC_RESET_DELAY 100 + static const char ibmvnic_priv_flags[][ETH_GSTRING_LEN] = { #define IBMVNIC_USE_SERVER_MAXES 0x1 "use-server-maxes" @@ -1087,7 +1090,8 @@ struct ibmvnic_adapter { spinlock_t rwi_lock; struct list_head rwi_list; struct work_struct ibmvnic_reset; - bool resetting; + struct delayed_work ibmvnic_delayed_reset; + unsigned long resetting; bool napi_enabled, from_passive_init; bool failover_pending; diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 937a5f577da8..fa20a36edfcd 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1432,6 +1432,8 @@ static void __ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) netif_wake_queue(ppp->dev); else netif_stop_queue(ppp->dev); + } else { + kfree_skb(skb); } ppp_xmit_unlock(ppp); } diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 45f28dec29a0..6345a0ec6a42 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -401,10 +401,17 @@ static int nvmem_setup_compat(struct nvmem_device *nvmem, if (!config->base_dev) return -EINVAL; - if (nvmem->read_only) - nvmem->eeprom = bin_attr_ro_root_nvmem; - else - nvmem->eeprom = bin_attr_rw_root_nvmem; + if (nvmem->read_only) { + if (config->root_only) + nvmem->eeprom = bin_attr_ro_root_nvmem; + else + nvmem->eeprom = bin_attr_ro_nvmem; + } else { + if (config->root_only) + nvmem->eeprom = bin_attr_rw_root_nvmem; + else + nvmem->eeprom = bin_attr_rw_nvmem; + } nvmem->eeprom.attr.name = "eeprom"; nvmem->eeprom.size = nvmem->size; #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c index 7af31a1247ee..fe8ac0d4dca3 100644 --- a/drivers/scsi/device_handler/scsi_dh_rdac.c +++ b/drivers/scsi/device_handler/scsi_dh_rdac.c @@ -546,6 +546,8 @@ static void send_mode_select(struct work_struct *work) spin_unlock(&ctlr->ms_lock); retry: + memset(cdb, 0, sizeof(cdb)); + data_size = rdac_failover_get(ctlr, &list, cdb); RDAC_LOG(RDAC_LOG_FAILOVER, sdev, "array %s, ctlr %d, " diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 9471e0376104..6c6b4a908ca9 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3452,6 +3452,9 @@ cleanup: clear_extent_bit(&BTRFS_I(inode)->io_tree, unode->val, unode->aux, EXTENT_QGROUP_RESERVED, 0, 0, NULL, GFP_NOFS); + /* Also free data bytes of already reserved one */ + btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, + orig_reserved, BTRFS_QGROUP_RSV_DATA); extent_changeset_release(reserved); return ret; } @@ -3496,7 +3499,7 @@ static int qgroup_free_reserved_data(struct inode *inode, * EXTENT_QGROUP_RESERVED, we won't double free. * So not need to rush. */ - ret = clear_record_extent_bits(&BTRFS_I(inode)->io_failure_tree, + ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, free_start, free_start + free_len - 1, EXTENT_QGROUP_RESERVED, &changeset); if (ret < 0) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 6f0f602d1013..94651898c559 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1478,6 +1478,13 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans, int clear_rsv = 0; int ret; + /* + * The subvolume has reloc tree but the swap is finished, no need to + * create/update the dead reloc tree + */ + if (test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state)) + return 0; + if (root->reloc_root) { reloc_root = root->reloc_root; reloc_root->last_trans = trans->transid; @@ -2228,7 +2235,6 @@ static int clean_dirty_subvols(struct reloc_control *rc) /* Merged subvolume, cleanup its reloc root */ struct btrfs_root *reloc_root = root->reloc_root; - clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state); list_del_init(&root->reloc_dirty_list); root->reloc_root = NULL; if (reloc_root) { @@ -2237,6 +2243,7 @@ static int clean_dirty_subvols(struct reloc_control *rc) if (ret2 < 0 && !ret) ret = ret2; } + clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state); btrfs_put_fs_root(root); } else { /* Orphan reloc tree, just clean it up */ diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 3b31de59fa50..559be941aefd 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -527,13 +527,16 @@ static void ceph_i_callback(struct rcu_head *head) kmem_cache_free(ceph_inode_cachep, ci); } -void ceph_destroy_inode(struct inode *inode) +void ceph_evict_inode(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_inode_frag *frag; struct rb_node *n; - dout("destroy_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode)); + dout("evict_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode)); + + truncate_inode_pages_final(&inode->i_data); + clear_inode(inode); ceph_fscache_unregister_inode_cookie(ci); @@ -575,7 +578,10 @@ void ceph_destroy_inode(struct inode *inode) ceph_buffer_put(ci->i_xattrs.prealloc_blob); ceph_put_string(rcu_dereference_raw(ci->i_layout.pool_ns)); +} +void ceph_destroy_inode(struct inode *inode) +{ call_rcu(&inode->i_rcu, ceph_i_callback); } diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 9a6102a0413c..8073f6ceb3ec 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -821,6 +821,7 @@ static const struct super_operations ceph_super_ops = { .destroy_inode = ceph_destroy_inode, .write_inode = ceph_write_inode, .drop_inode = ceph_drop_inode, + .evict_inode = ceph_evict_inode, .sync_fs = ceph_sync_fs, .put_super = ceph_put_super, .remount_fs = ceph_remount, diff --git a/fs/ceph/super.h b/fs/ceph/super.h index b8b059016884..2a544060f016 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -854,6 +854,7 @@ static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci) extern const struct inode_operations ceph_file_iops; extern struct inode *ceph_alloc_inode(struct super_block *sb); +extern void ceph_evict_inode(struct inode *inode); extern void ceph_destroy_inode(struct inode *inode); extern int ceph_drop_inode(struct inode *inode); diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 2b07d3ef5a5e..1a121ccf4bb8 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -931,7 +931,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r out_invalidcred: pr_warn_ratelimited("NFS: NFSv4 callback contains invalid cred\n"); - return rpc_autherr_badcred; + return svc_return_autherr(rqstp, rpc_autherr_badcred); } /* diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index a4d21aa24566..ee4c35ccc472 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -152,7 +152,7 @@ again: /* Block nfs4_proc_unlck */ mutex_lock(&sp->so_delegreturn_mutex); seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); - err = nfs4_open_delegation_recall(ctx, state, stateid, type); + err = nfs4_open_delegation_recall(ctx, state, stateid); if (!err) err = nfs_delegation_claim_locks(ctx, state, stateid); if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) @@ -991,6 +991,22 @@ void nfs_mark_test_expired_all_delegations(struct nfs_client *clp) rcu_read_unlock(); } +static void +nfs_delegation_test_free_expired(struct inode *inode, + nfs4_stateid *stateid, + struct rpc_cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + const struct nfs4_minor_version_ops *ops = server->nfs_client->cl_mvops; + int status; + + if (!cred) + return; + status = ops->test_and_free_expired(server, stateid, cred); + if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID) + nfs_remove_bad_delegation(inode, stateid); +} + /** * nfs_reap_expired_delegations - reap expired delegations * @clp: nfs_client to process @@ -1002,7 +1018,6 @@ void nfs_mark_test_expired_all_delegations(struct nfs_client *clp) */ void nfs_reap_expired_delegations(struct nfs_client *clp) { - const struct nfs4_minor_version_ops *ops = clp->cl_mvops; struct nfs_delegation *delegation; struct nfs_server *server; struct inode *inode; @@ -1033,11 +1048,7 @@ restart: nfs4_stateid_copy(&stateid, &delegation->stateid); clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags); rcu_read_unlock(); - if (cred != NULL && - ops->test_and_free_expired(server, &stateid, cred) < 0) { - nfs_revoke_delegation(inode, &stateid); - nfs_inode_find_state_and_recover(inode, &stateid); - } + nfs_delegation_test_free_expired(inode, &stateid, cred); put_rpccred(cred); if (nfs4_server_rebooted(clp)) { nfs_inode_mark_test_expired_delegation(server,inode); diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index a289fd424019..7a22c3f7540e 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -59,7 +59,7 @@ void nfs_reap_expired_delegations(struct nfs_client *clp); /* NFSv4 delegation-related procedures */ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync); -int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid, fmode_t type); +int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid); int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid); bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, struct rpc_cred **cred); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 349e9993d9cd..4e46628b8f37 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1059,6 +1059,100 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry, return !nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU); } +static int +nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry, + struct inode *inode, int error) +{ + switch (error) { + case 1: + dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is valid\n", + __func__, dentry); + return 1; + case 0: + nfs_mark_for_revalidate(dir); + if (inode && S_ISDIR(inode->i_mode)) { + /* Purge readdir caches. */ + nfs_zap_caches(inode); + /* + * We can't d_drop the root of a disconnected tree: + * its d_hash is on the s_anon list and d_drop() would hide + * it from shrink_dcache_for_unmount(), leading to busy + * inodes on unmount and further oopses. + */ + if (IS_ROOT(dentry)) + return 1; + } + dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n", + __func__, dentry); + return 0; + } + dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) lookup returned error %d\n", + __func__, dentry, error); + return error; +} + +static int +nfs_lookup_revalidate_negative(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + int ret = 1; + if (nfs_neg_need_reval(dir, dentry, flags)) { + if (flags & LOOKUP_RCU) + return -ECHILD; + ret = 0; + } + return nfs_lookup_revalidate_done(dir, dentry, NULL, ret); +} + +static int +nfs_lookup_revalidate_delegated(struct inode *dir, struct dentry *dentry, + struct inode *inode) +{ + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + return nfs_lookup_revalidate_done(dir, dentry, inode, 1); +} + +static int +nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, + struct inode *inode) +{ + struct nfs_fh *fhandle; + struct nfs_fattr *fattr; + struct nfs4_label *label; + int ret; + + ret = -ENOMEM; + fhandle = nfs_alloc_fhandle(); + fattr = nfs_alloc_fattr(); + label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL); + if (fhandle == NULL || fattr == NULL || IS_ERR(label)) + goto out; + + ret = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label); + if (ret < 0) { + if (ret == -ESTALE || ret == -ENOENT) + ret = 0; + goto out; + } + ret = 0; + if (nfs_compare_fh(NFS_FH(inode), fhandle)) + goto out; + if (nfs_refresh_inode(inode, fattr) < 0) + goto out; + + nfs_setsecurity(inode, fattr, label); + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + + /* set a readdirplus hint that we had a cache miss */ + nfs_force_use_readdirplus(dir); + ret = 1; +out: + nfs_free_fattr(fattr); + nfs_free_fhandle(fhandle); + nfs4_label_free(label); + return nfs_lookup_revalidate_done(dir, dentry, inode, ret); +} + /* * This is called every time the dcache has a lookup hit, * and we should check whether we can really trust that @@ -1070,58 +1164,36 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry, * If the parent directory is seen to have changed, we throw out the * cached dentry and do a new lookup. */ -static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) +static int +nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, + unsigned int flags) { - struct inode *dir; struct inode *inode; - struct dentry *parent; - struct nfs_fh *fhandle = NULL; - struct nfs_fattr *fattr = NULL; - struct nfs4_label *label = NULL; int error; - if (flags & LOOKUP_RCU) { - parent = READ_ONCE(dentry->d_parent); - dir = d_inode_rcu(parent); - if (!dir) - return -ECHILD; - } else { - parent = dget_parent(dentry); - dir = d_inode(parent); - } nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE); inode = d_inode(dentry); - if (!inode) { - if (nfs_neg_need_reval(dir, dentry, flags)) { - if (flags & LOOKUP_RCU) - return -ECHILD; - goto out_bad; - } - goto out_valid; - } + if (!inode) + return nfs_lookup_revalidate_negative(dir, dentry, flags); if (is_bad_inode(inode)) { - if (flags & LOOKUP_RCU) - return -ECHILD; dfprintk(LOOKUPCACHE, "%s: %pd2 has dud inode\n", __func__, dentry); goto out_bad; } if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ)) - goto out_set_verifier; + return nfs_lookup_revalidate_delegated(dir, dentry, inode); /* Force a full look up iff the parent directory has changed */ if (!nfs_is_exclusive_create(dir, flags) && nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) { error = nfs_lookup_verify_inode(inode, flags); if (error) { - if (flags & LOOKUP_RCU) - return -ECHILD; if (error == -ESTALE) - goto out_zap_parent; - goto out_error; + nfs_zap_caches(dir); + goto out_bad; } nfs_advise_use_readdirplus(dir); goto out_valid; @@ -1133,81 +1205,45 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) if (NFS_STALE(inode)) goto out_bad; - error = -ENOMEM; - fhandle = nfs_alloc_fhandle(); - fattr = nfs_alloc_fattr(); - if (fhandle == NULL || fattr == NULL) - goto out_error; - - label = nfs4_label_alloc(NFS_SERVER(inode), GFP_NOWAIT); - if (IS_ERR(label)) - goto out_error; - trace_nfs_lookup_revalidate_enter(dir, dentry, flags); - error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label); + error = nfs_lookup_revalidate_dentry(dir, dentry, inode); trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error); - if (error == -ESTALE || error == -ENOENT) - goto out_bad; - if (error) - goto out_error; - if (nfs_compare_fh(NFS_FH(inode), fhandle)) - goto out_bad; - if ((error = nfs_refresh_inode(inode, fattr)) != 0) - goto out_bad; - - nfs_setsecurity(inode, fattr, label); - - nfs_free_fattr(fattr); - nfs_free_fhandle(fhandle); - nfs4_label_free(label); + return error; +out_valid: + return nfs_lookup_revalidate_done(dir, dentry, inode, 1); +out_bad: + if (flags & LOOKUP_RCU) + return -ECHILD; + return nfs_lookup_revalidate_done(dir, dentry, inode, 0); +} - /* set a readdirplus hint that we had a cache miss */ - nfs_force_use_readdirplus(dir); +static int +__nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags, + int (*reval)(struct inode *, struct dentry *, unsigned int)) +{ + struct dentry *parent; + struct inode *dir; + int ret; -out_set_verifier: - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); - out_valid: if (flags & LOOKUP_RCU) { + parent = READ_ONCE(dentry->d_parent); + dir = d_inode_rcu(parent); + if (!dir) + return -ECHILD; + ret = reval(dir, dentry, flags); if (parent != READ_ONCE(dentry->d_parent)) return -ECHILD; - } else + } else { + parent = dget_parent(dentry); + ret = reval(d_inode(parent), dentry, flags); dput(parent); - dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is valid\n", - __func__, dentry); - return 1; -out_zap_parent: - nfs_zap_caches(dir); - out_bad: - WARN_ON(flags & LOOKUP_RCU); - nfs_free_fattr(fattr); - nfs_free_fhandle(fhandle); - nfs4_label_free(label); - nfs_mark_for_revalidate(dir); - if (inode && S_ISDIR(inode->i_mode)) { - /* Purge readdir caches. */ - nfs_zap_caches(inode); - /* - * We can't d_drop the root of a disconnected tree: - * its d_hash is on the s_anon list and d_drop() would hide - * it from shrink_dcache_for_unmount(), leading to busy - * inodes on unmount and further oopses. - */ - if (IS_ROOT(dentry)) - goto out_valid; } - dput(parent); - dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n", - __func__, dentry); - return 0; -out_error: - WARN_ON(flags & LOOKUP_RCU); - nfs_free_fattr(fattr); - nfs_free_fhandle(fhandle); - nfs4_label_free(label); - dput(parent); - dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) lookup returned error %d\n", - __func__, dentry, error); - return error; + return ret; +} + +static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) +{ + return __nfs_lookup_revalidate(dentry, flags, nfs_do_lookup_revalidate); } /* @@ -1558,62 +1594,55 @@ no_open: } EXPORT_SYMBOL_GPL(nfs_atomic_open); -static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) +static int +nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, + unsigned int flags) { struct inode *inode; - int ret = 0; if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY)) - goto no_open; + goto full_reval; if (d_mountpoint(dentry)) - goto no_open; - if (NFS_SB(dentry->d_sb)->caps & NFS_CAP_ATOMIC_OPEN_V1) - goto no_open; + goto full_reval; inode = d_inode(dentry); /* We can't create new files in nfs_open_revalidate(), so we * optimize away revalidation of negative dentries. */ - if (inode == NULL) { - struct dentry *parent; - struct inode *dir; - - if (flags & LOOKUP_RCU) { - parent = READ_ONCE(dentry->d_parent); - dir = d_inode_rcu(parent); - if (!dir) - return -ECHILD; - } else { - parent = dget_parent(dentry); - dir = d_inode(parent); - } - if (!nfs_neg_need_reval(dir, dentry, flags)) - ret = 1; - else if (flags & LOOKUP_RCU) - ret = -ECHILD; - if (!(flags & LOOKUP_RCU)) - dput(parent); - else if (parent != READ_ONCE(dentry->d_parent)) - return -ECHILD; - goto out; - } + if (inode == NULL) + goto full_reval; + + if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ)) + return nfs_lookup_revalidate_delegated(dir, dentry, inode); /* NFS only supports OPEN on regular files */ if (!S_ISREG(inode->i_mode)) - goto no_open; + goto full_reval; + /* We cannot do exclusive creation on a positive dentry */ - if (flags & LOOKUP_EXCL) - goto no_open; + if (flags & (LOOKUP_EXCL | LOOKUP_REVAL)) + goto reval_dentry; + + /* Check if the directory changed */ + if (!nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) + goto reval_dentry; /* Let f_op->open() actually open (and revalidate) the file */ - ret = 1; + return 1; +reval_dentry: + if (flags & LOOKUP_RCU) + return -ECHILD; + return nfs_lookup_revalidate_dentry(dir, dentry, inode); -out: - return ret; +full_reval: + return nfs_do_lookup_revalidate(dir, dentry, flags); +} -no_open: - return nfs_lookup_revalidate(dentry, flags); +static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) +{ + return __nfs_lookup_revalidate(dentry, flags, + nfs4_do_lookup_revalidate); } #endif /* CONFIG_NFSV4 */ diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index f6e68e953967..03fed7e18e75 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -397,15 +397,21 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) unsigned long bytes = 0; struct nfs_direct_req *dreq = hdr->dreq; - if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) - goto out_put; - spin_lock(&dreq->lock); - if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0)) + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) dreq->error = hdr->error; - else + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) { + spin_unlock(&dreq->lock); + goto out_put; + } + + if (hdr->good_bytes != 0) nfs_direct_good_bytes(dreq, hdr); + if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) + dreq->error = 0; + spin_unlock(&dreq->lock); while (!list_empty(&hdr->pages)) { @@ -768,16 +774,19 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) bool request_commit = false; struct nfs_page *req = nfs_list_entry(hdr->pages.next); - if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) - goto out_put; - nfs_init_cinfo_from_dreq(&cinfo, dreq); spin_lock(&dreq->lock); if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) dreq->error = hdr->error; - if (dreq->error == 0) { + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) { + spin_unlock(&dreq->lock); + goto out_put; + } + + if (hdr->good_bytes != 0) { nfs_direct_good_bytes(dreq, hdr); if (nfs_write_need_commit(hdr)) { if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index ca0b0e03619f..f37fbc2dbbae 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -932,7 +932,7 @@ fl_pnfs_update_layout(struct inode *ino, status = filelayout_check_deviceid(lo, fl, gfp_flags); if (status) { pnfs_put_lseg(lseg); - lseg = ERR_PTR(status); + lseg = NULL; } out: return lseg; diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index f32c58bbe556..37cbe316d224 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -305,7 +305,7 @@ int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo, if (status == 0) return 0; - if (mirror->mirror_ds == NULL) + if (IS_ERR_OR_NULL(mirror->mirror_ds)) return -EINVAL; dserr = kmalloc(sizeof(*dserr), gfp_flags); diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index d63bea8bbfbb..6367e7fd530c 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -71,6 +71,10 @@ void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int struct rb_node **p, *parent; int diff; + nfss->fscache_key = NULL; + nfss->fscache = NULL; + if (!(nfss->options & NFS_OPTION_FSCACHE)) + return; if (!uniq) { uniq = ""; ulen = 1; @@ -180,10 +184,11 @@ void nfs_fscache_release_super_cookie(struct super_block *sb) */ void nfs_fscache_init_inode(struct inode *inode) { + struct nfs_server *nfss = NFS_SERVER(inode); struct nfs_inode *nfsi = NFS_I(inode); nfsi->fscache = NULL; - if (!S_ISREG(inode->i_mode)) + if (!(nfss->fscache && S_ISREG(inode->i_mode))) return; nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache, &nfs_fscache_inode_object_def, diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index d7fe3e799f2f..7ead2158fe63 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -171,7 +171,7 @@ static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) */ static inline const char *nfs_server_fscache_state(struct nfs_server *server) { - if (server->fscache && (server->options & NFS_OPTION_FSCACHE)) + if (server->fscache) return "yes"; return "no "; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e906c5bcd01b..a9094c1c543b 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1006,6 +1006,7 @@ int nfs_open(struct inode *inode, struct file *filp) nfs_fscache_open_file(inode, filp); return 0; } +EXPORT_SYMBOL_GPL(nfs_open); /* * This function is called whenever some part of NFS notices that diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index c96280495e6e..808a1fe88cec 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -161,6 +161,7 @@ enum { NFS_STATE_POSIX_LOCKS, /* Posix locks are supported */ NFS_STATE_RECOVERY_FAILED, /* OPEN stateid state recovery failed */ NFS_STATE_MAY_NOTIFY_LOCK, /* server may CB_NOTIFY_LOCK */ + NFS_STATE_CHANGE_WAIT, /* A state changing operation is outstanding */ }; struct nfs4_state { @@ -432,7 +433,8 @@ static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *, gfp_t); extern void nfs4_put_state_owner(struct nfs4_state_owner *); -extern void nfs4_purge_state_owners(struct nfs_server *); +extern void nfs4_purge_state_owners(struct nfs_server *, struct list_head *); +extern void nfs4_free_state_owners(struct list_head *head); extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *); extern void nfs4_put_open_state(struct nfs4_state *); extern void nfs4_close_state(struct nfs4_state *, fmode_t); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index c5d3c0b4e54c..cd24080d13ba 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -744,9 +744,12 @@ out: static void nfs4_destroy_server(struct nfs_server *server) { + LIST_HEAD(freeme); + nfs_server_return_all_delegations(server); unset_pnfs_layoutdriver(server); - nfs4_purge_state_owners(server); + nfs4_purge_state_owners(server, &freeme); + nfs4_free_state_owners(&freeme); } /* diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 0efba77789b9..298df1db77a4 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -49,7 +49,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) return err; if ((openflags & O_ACCMODE) == 3) - openflags--; + return nfs_open(inode, filp); /* We can't create new files here */ openflags &= ~(O_CREAT|O_EXCL); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 672875b37460..7c8d66c489ae 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1396,6 +1396,25 @@ static bool nfs_open_stateid_recover_openmode(struct nfs4_state *state) } #endif /* CONFIG_NFS_V4_1 */ +static void nfs_state_log_update_open_stateid(struct nfs4_state *state) +{ + if (test_and_clear_bit(NFS_STATE_CHANGE_WAIT, &state->flags)) + wake_up_bit(&state->flags, NFS_STATE_CHANGE_WAIT); +} + +static void nfs_state_log_out_of_order_open_stateid(struct nfs4_state *state, + const nfs4_stateid *stateid) +{ + u32 state_seqid = be32_to_cpu(state->open_stateid.seqid); + u32 stateid_seqid = be32_to_cpu(stateid->seqid); + + if (stateid_seqid == state_seqid + 1U || + (stateid_seqid == 1U && state_seqid == 0xffffffffU)) + nfs_state_log_update_open_stateid(state); + else + set_bit(NFS_STATE_CHANGE_WAIT, &state->flags); +} + static void nfs_test_and_clear_all_open_stateid(struct nfs4_state *state) { struct nfs_client *clp = state->owner->so_server->nfs_client; @@ -1411,18 +1430,32 @@ static void nfs_test_and_clear_all_open_stateid(struct nfs4_state *state) nfs4_state_mark_reclaim_nograce(clp, state); } +/* + * Check for whether or not the caller may update the open stateid + * to the value passed in by stateid. + * + * Note: This function relies heavily on the server implementing + * RFC7530 Section 9.1.4.2, and RFC5661 Section 8.2.2 + * correctly. + * i.e. The stateid seqids have to be initialised to 1, and + * are then incremented on every state transition. + */ static bool nfs_need_update_open_stateid(struct nfs4_state *state, - const nfs4_stateid *stateid, nfs4_stateid *freeme) + const nfs4_stateid *stateid) { - if (test_and_set_bit(NFS_OPEN_STATE, &state->flags) == 0) - return true; - if (!nfs4_stateid_match_other(stateid, &state->open_stateid)) { - nfs4_stateid_copy(freeme, &state->open_stateid); - nfs_test_and_clear_all_open_stateid(state); + if (test_bit(NFS_OPEN_STATE, &state->flags) == 0 || + !nfs4_stateid_match_other(stateid, &state->open_stateid)) { + if (stateid->seqid == cpu_to_be32(1)) + nfs_state_log_update_open_stateid(state); + else + set_bit(NFS_STATE_CHANGE_WAIT, &state->flags); return true; } - if (nfs4_stateid_is_newer(stateid, &state->open_stateid)) + + if (nfs4_stateid_is_newer(stateid, &state->open_stateid)) { + nfs_state_log_out_of_order_open_stateid(state, stateid); return true; + } return false; } @@ -1461,11 +1494,13 @@ static void nfs_clear_open_stateid_locked(struct nfs4_state *state, if (nfs4_stateid_match_other(stateid, &state->open_stateid) && !nfs4_stateid_is_newer(stateid, &state->open_stateid)) { nfs_resync_open_stateid_locked(state); - return; + goto out; } if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) nfs4_stateid_copy(&state->stateid, stateid); nfs4_stateid_copy(&state->open_stateid, stateid); +out: + nfs_state_log_update_open_stateid(state); } static void nfs_clear_open_stateid(struct nfs4_state *state, @@ -1482,29 +1517,67 @@ static void nfs_clear_open_stateid(struct nfs4_state *state, } static void nfs_set_open_stateid_locked(struct nfs4_state *state, - const nfs4_stateid *stateid, fmode_t fmode, - nfs4_stateid *freeme) + const nfs4_stateid *stateid, nfs4_stateid *freeme) { - switch (fmode) { - case FMODE_READ: - set_bit(NFS_O_RDONLY_STATE, &state->flags); + struct wait_queue_head *wq_head = bit_waitqueue(&state->flags, + NFS_STATE_CHANGE_WAIT); + DEFINE_WAIT_BIT(wbq_entry, &state->flags, NFS_STATE_CHANGE_WAIT); + int status = 0; + for (;;) { + + if (!nfs_need_update_open_stateid(state, stateid)) + return; + if (!test_bit(NFS_STATE_CHANGE_WAIT, &state->flags)) break; - case FMODE_WRITE: - set_bit(NFS_O_WRONLY_STATE, &state->flags); + if (status) break; - case FMODE_READ|FMODE_WRITE: - set_bit(NFS_O_RDWR_STATE, &state->flags); + /* Rely on seqids for serialisation with NFSv4.0 */ + if (!nfs4_has_session(NFS_SERVER(state->inode)->nfs_client)) + break; + + prepare_to_wait(wq_head, &wbq_entry.wq_entry, TASK_KILLABLE); + /* + * Ensure we process the state changes in the same order + * in which the server processed them by delaying the + * update of the stateid until we are in sequence. + */ + write_sequnlock(&state->seqlock); + spin_unlock(&state->owner->so_lock); + rcu_read_unlock(); + if (!signal_pending(current)) { + if (schedule_timeout(5*HZ) == 0) + status = -EAGAIN; + else + status = 0; + } else + status = -EINTR; + finish_wait(wq_head, &wbq_entry.wq_entry); + rcu_read_lock(); + spin_lock(&state->owner->so_lock); + write_seqlock(&state->seqlock); } - if (!nfs_need_update_open_stateid(state, stateid, freeme)) - return; + + if (!nfs4_stateid_match_other(stateid, &state->open_stateid)) { + nfs4_stateid_copy(freeme, &state->open_stateid); + nfs_test_and_clear_all_open_stateid(state); + } + if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) nfs4_stateid_copy(&state->stateid, stateid); nfs4_stateid_copy(&state->open_stateid, stateid); + nfs_state_log_update_open_stateid(state); +} + +static void nfs_state_clear_open_state_flags(struct nfs4_state *state) +{ + clear_bit(NFS_O_RDWR_STATE, &state->flags); + clear_bit(NFS_O_WRONLY_STATE, &state->flags); + clear_bit(NFS_O_RDONLY_STATE, &state->flags); + clear_bit(NFS_OPEN_STATE, &state->flags); } -static void __update_open_stateid(struct nfs4_state *state, +static void nfs_state_set_open_stateid(struct nfs4_state *state, const nfs4_stateid *open_stateid, - const nfs4_stateid *deleg_stateid, fmode_t fmode, nfs4_stateid *freeme) { @@ -1512,17 +1585,42 @@ static void __update_open_stateid(struct nfs4_state *state, * Protect the call to nfs4_state_set_mode_locked and * serialise the stateid update */ - spin_lock(&state->owner->so_lock); write_seqlock(&state->seqlock); - if (deleg_stateid != NULL) { - nfs4_stateid_copy(&state->stateid, deleg_stateid); - set_bit(NFS_DELEGATED_STATE, &state->flags); + nfs_set_open_stateid_locked(state, open_stateid, freeme); + switch (fmode) { + case FMODE_READ: + set_bit(NFS_O_RDONLY_STATE, &state->flags); + break; + case FMODE_WRITE: + set_bit(NFS_O_WRONLY_STATE, &state->flags); + break; + case FMODE_READ|FMODE_WRITE: + set_bit(NFS_O_RDWR_STATE, &state->flags); } - if (open_stateid != NULL) - nfs_set_open_stateid_locked(state, open_stateid, fmode, freeme); + set_bit(NFS_OPEN_STATE, &state->flags); + write_sequnlock(&state->seqlock); +} + +static void nfs_state_set_delegation(struct nfs4_state *state, + const nfs4_stateid *deleg_stateid, + fmode_t fmode) +{ + /* + * Protect the call to nfs4_state_set_mode_locked and + * serialise the stateid update + */ + write_seqlock(&state->seqlock); + nfs4_stateid_copy(&state->stateid, deleg_stateid); + set_bit(NFS_DELEGATED_STATE, &state->flags); + write_sequnlock(&state->seqlock); +} + +static void nfs_state_clear_delegation(struct nfs4_state *state) +{ + write_seqlock(&state->seqlock); + nfs4_stateid_copy(&state->stateid, &state->open_stateid); + clear_bit(NFS_DELEGATED_STATE, &state->flags); write_sequnlock(&state->seqlock); - update_open_stateflags(state, fmode); - spin_unlock(&state->owner->so_lock); } static int update_open_stateid(struct nfs4_state *state, @@ -1540,6 +1638,12 @@ static int update_open_stateid(struct nfs4_state *state, fmode &= (FMODE_READ|FMODE_WRITE); rcu_read_lock(); + spin_lock(&state->owner->so_lock); + if (open_stateid != NULL) { + nfs_state_set_open_stateid(state, open_stateid, fmode, &freeme); + ret = 1; + } + deleg_cur = rcu_dereference(nfsi->delegation); if (deleg_cur == NULL) goto no_delegation; @@ -1556,18 +1660,16 @@ static int update_open_stateid(struct nfs4_state *state, goto no_delegation_unlock; nfs_mark_delegation_referenced(deleg_cur); - __update_open_stateid(state, open_stateid, &deleg_cur->stateid, - fmode, &freeme); + nfs_state_set_delegation(state, &deleg_cur->stateid, fmode); ret = 1; no_delegation_unlock: spin_unlock(&deleg_cur->lock); no_delegation: + if (ret) + update_open_stateflags(state, fmode); + spin_unlock(&state->owner->so_lock); rcu_read_unlock(); - if (!ret && open_stateid != NULL) { - __update_open_stateid(state, open_stateid, NULL, fmode, &freeme); - ret = 1; - } if (test_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags)) nfs4_schedule_state_manager(clp); if (freeme.type != 0) @@ -1714,8 +1816,9 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) if (data->o_res.delegation_type != 0) nfs4_opendata_check_deleg(data, state); update: - update_open_stateid(state, &data->o_res.stateid, NULL, - data->o_arg.fmode); + if (!update_open_stateid(state, &data->o_res.stateid, + NULL, data->o_arg.fmode)) + return ERR_PTR(-EAGAIN); atomic_inc(&state->count); return state; @@ -1747,9 +1850,11 @@ _nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data) goto err_put_inode; if (data->o_res.delegation_type != 0) nfs4_opendata_check_deleg(data, state); - update_open_stateid(state, &data->o_res.stateid, NULL, - data->o_arg.fmode); - iput(inode); + if (!update_open_stateid(state, &data->o_res.stateid, + NULL, data->o_arg.fmode)) { + nfs4_put_open_state(state); + state = ERR_PTR(-EAGAIN); + } out: nfs_release_seqid(data->o_arg.seqid); return state; @@ -1835,13 +1940,7 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state * { int ret; - /* Don't trigger recovery in nfs_test_and_clear_all_open_stateid */ - clear_bit(NFS_O_RDWR_STATE, &state->flags); - clear_bit(NFS_O_WRONLY_STATE, &state->flags); - clear_bit(NFS_O_RDONLY_STATE, &state->flags); /* memory barrier prior to reading state->n_* */ - clear_bit(NFS_DELEGATED_STATE, &state->flags); - clear_bit(NFS_OPEN_STATE, &state->flags); smp_rmb(); ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE); if (ret != 0) @@ -1917,6 +2016,8 @@ static int nfs4_open_reclaim(struct nfs4_state_owner *sp, struct nfs4_state *sta ctx = nfs4_state_find_open_context(state); if (IS_ERR(ctx)) return -EAGAIN; + clear_bit(NFS_DELEGATED_STATE, &state->flags); + nfs_state_clear_open_state_flags(state); ret = nfs4_do_open_reclaim(ctx, state); put_nfs_open_context(ctx); return ret; @@ -1938,12 +2039,10 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct case -NFS4ERR_BAD_HIGH_SLOT: case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: case -NFS4ERR_DEADSESSION: - set_bit(NFS_DELEGATED_STATE, &state->flags); nfs4_schedule_session_recovery(server->nfs_client->cl_session, err); return -EAGAIN; case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_STALE_STATEID: - set_bit(NFS_DELEGATED_STATE, &state->flags); /* Don't recall a delegation if it was lost */ nfs4_schedule_lease_recovery(server->nfs_client); return -EAGAIN; @@ -1964,7 +2063,6 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct return -EAGAIN; case -NFS4ERR_DELAY: case -NFS4ERR_GRACE: - set_bit(NFS_DELEGATED_STATE, &state->flags); ssleep(1); return -EAGAIN; case -ENOMEM: @@ -1980,8 +2078,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct } int nfs4_open_delegation_recall(struct nfs_open_context *ctx, - struct nfs4_state *state, const nfs4_stateid *stateid, - fmode_t type) + struct nfs4_state *state, const nfs4_stateid *stateid) { struct nfs_server *server = NFS_SERVER(state->inode); struct nfs4_opendata *opendata; @@ -1992,22 +2089,23 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, if (IS_ERR(opendata)) return PTR_ERR(opendata); nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid); - write_seqlock(&state->seqlock); - nfs4_stateid_copy(&state->stateid, &state->open_stateid); - write_sequnlock(&state->seqlock); - clear_bit(NFS_DELEGATED_STATE, &state->flags); - switch (type & (FMODE_READ|FMODE_WRITE)) { - case FMODE_READ|FMODE_WRITE: - case FMODE_WRITE: + if (!test_bit(NFS_O_RDWR_STATE, &state->flags)) { err = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE); if (err) - break; + goto out; + } + if (!test_bit(NFS_O_WRONLY_STATE, &state->flags)) { err = nfs4_open_recover_helper(opendata, FMODE_WRITE); if (err) - break; - case FMODE_READ: + goto out; + } + if (!test_bit(NFS_O_RDONLY_STATE, &state->flags)) { err = nfs4_open_recover_helper(opendata, FMODE_READ); + if (err) + goto out; } + nfs_state_clear_delegation(state); +out: nfs4_opendata_put(opendata); return nfs4_handle_delegation_recall_error(server, state, stateid, NULL, err); } @@ -2441,10 +2539,7 @@ static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state, const nfs4_stateid *stateid) { nfs_remove_bad_delegation(state->inode, stateid); - write_seqlock(&state->seqlock); - nfs4_stateid_copy(&state->stateid, &state->open_stateid); - write_sequnlock(&state->seqlock); - clear_bit(NFS_DELEGATED_STATE, &state->flags); + nfs_state_clear_delegation(state); } static void nfs40_clear_delegation_stateid(struct nfs4_state *state) @@ -2457,6 +2552,7 @@ static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st { /* NFSv4.0 doesn't allow for delegation recovery on open expire */ nfs40_clear_delegation_stateid(state); + nfs_state_clear_open_state_flags(state); return nfs4_open_expired(sp, state); } @@ -2499,33 +2595,29 @@ out_free: return -NFS4ERR_EXPIRED; } -static void nfs41_check_delegation_stateid(struct nfs4_state *state) +static int nfs41_check_delegation_stateid(struct nfs4_state *state) { struct nfs_server *server = NFS_SERVER(state->inode); nfs4_stateid stateid; struct nfs_delegation *delegation; struct rpc_cred *cred; - int status; + int status, ret = NFS_OK; /* Get the delegation credential for use by test/free_stateid */ rcu_read_lock(); delegation = rcu_dereference(NFS_I(state->inode)->delegation); if (delegation == NULL) { rcu_read_unlock(); - return; + nfs_state_clear_delegation(state); + return NFS_OK; } nfs4_stateid_copy(&stateid, &delegation->stateid); - if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { - rcu_read_unlock(); - nfs_finish_clear_delegation_stateid(state, &stateid); - return; - } if (!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags)) { rcu_read_unlock(); - return; + return NFS_OK; } cred = get_rpccred(delegation->cred); @@ -2534,8 +2626,24 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state) trace_nfs4_test_delegation_stateid(state, NULL, status); if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID) nfs_finish_clear_delegation_stateid(state, &stateid); + else + ret = status; put_rpccred(cred); + return ret; +} + +static void nfs41_delegation_recover_stateid(struct nfs4_state *state) +{ + nfs4_stateid tmp; + + if (test_bit(NFS_DELEGATED_STATE, &state->flags) && + nfs4_copy_delegation_stateid(state->inode, state->state, + &tmp, NULL) && + nfs4_stateid_match_other(&state->stateid, &tmp)) + nfs_state_set_delegation(state, &tmp, state->state); + else + nfs_state_clear_delegation(state); } /** @@ -2605,21 +2713,12 @@ static int nfs41_check_open_stateid(struct nfs4_state *state) struct rpc_cred *cred = state->owner->so_cred; int status; - if (test_bit(NFS_OPEN_STATE, &state->flags) == 0) { - if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) { - if (nfs4_have_delegation(state->inode, state->state)) - return NFS_OK; - return -NFS4ERR_OPENMODE; - } + if (test_bit(NFS_OPEN_STATE, &state->flags) == 0) return -NFS4ERR_BAD_STATEID; - } status = nfs41_test_and_free_expired_stateid(server, stateid, cred); trace_nfs4_test_open_stateid(state, NULL, status); if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID) { - clear_bit(NFS_O_RDONLY_STATE, &state->flags); - clear_bit(NFS_O_WRONLY_STATE, &state->flags); - clear_bit(NFS_O_RDWR_STATE, &state->flags); - clear_bit(NFS_OPEN_STATE, &state->flags); + nfs_state_clear_open_state_flags(state); stateid->type = NFS4_INVALID_STATEID_TYPE; } if (status != NFS_OK) @@ -2633,7 +2732,11 @@ static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st { int status; - nfs41_check_delegation_stateid(state); + status = nfs41_check_delegation_stateid(state); + if (status != NFS_OK) + return status; + nfs41_delegation_recover_stateid(state); + status = nfs41_check_expired_locks(state); if (status != NFS_OK) return status; @@ -2914,7 +3017,6 @@ static int _nfs4_do_setattr(struct inode *inode, }; struct rpc_cred *delegation_cred = NULL; unsigned long timestamp = jiffies; - fmode_t fmode; bool truncate; int status; @@ -2922,11 +3024,12 @@ static int _nfs4_do_setattr(struct inode *inode, /* Servers should only apply open mode checks for file size changes */ truncate = (arg->iap->ia_valid & ATTR_SIZE) ? true : false; - fmode = truncate ? FMODE_WRITE : FMODE_READ; + if (!truncate) + goto zero_stateid; - if (nfs4_copy_delegation_stateid(inode, fmode, &arg->stateid, &delegation_cred)) { + if (nfs4_copy_delegation_stateid(inode, FMODE_WRITE, &arg->stateid, &delegation_cred)) { /* Use that stateid */ - } else if (truncate && ctx != NULL) { + } else if (ctx != NULL && ctx->state) { struct nfs_lock_context *l_ctx; if (!nfs4_valid_open_stateid(ctx->state)) return -EBADF; @@ -2938,8 +3041,10 @@ static int _nfs4_do_setattr(struct inode *inode, nfs_put_lock_context(l_ctx); if (status == -EIO) return -EBADF; - } else + } else { +zero_stateid: nfs4_stateid_copy(&arg->stateid, &zero_stateid); + } if (delegation_cred) msg.rpc_cred = delegation_cred; @@ -6464,7 +6569,6 @@ struct nfs4_lock_waiter { struct task_struct *task; struct inode *inode; struct nfs_lowner *owner; - bool notified; }; static int @@ -6486,11 +6590,11 @@ nfs4_wake_lock_waiter(wait_queue_entry_t *wait, unsigned int mode, int flags, vo if (nfs_compare_fh(NFS_FH(waiter->inode), &cbnl->cbnl_fh)) return 0; - waiter->notified = true; - /* override "private" so we can use default_wake_function */ wait->private = waiter->task; - ret = autoremove_wake_function(wait, mode, flags, key); + ret = woken_wake_function(wait, mode, flags, key); + if (ret) + list_del_init(&wait->entry); wait->private = waiter; return ret; } @@ -6499,7 +6603,6 @@ static int nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) { int status = -ERESTARTSYS; - unsigned long flags; struct nfs4_lock_state *lsp = request->fl_u.nfs4_fl.owner; struct nfs_server *server = NFS_SERVER(state->inode); struct nfs_client *clp = server->nfs_client; @@ -6509,8 +6612,7 @@ nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) .s_dev = server->s_dev }; struct nfs4_lock_waiter waiter = { .task = current, .inode = state->inode, - .owner = &owner, - .notified = false }; + .owner = &owner}; wait_queue_entry_t wait; /* Don't bother with waitqueue if we don't expect a callback */ @@ -6528,15 +6630,9 @@ nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) break; status = -ERESTARTSYS; - spin_lock_irqsave(&q->lock, flags); - if (waiter.notified) { - spin_unlock_irqrestore(&q->lock, flags); - continue; - } - set_current_state(TASK_INTERRUPTIBLE); - spin_unlock_irqrestore(&q->lock, flags); - - freezable_schedule_timeout(NFS4_LOCK_MAXTIMEOUT); + freezer_do_not_count(); + wait_woken(&wait, TASK_INTERRUPTIBLE, NFS4_LOCK_MAXTIMEOUT); + freezer_count(); } finish_wait(q, &wait); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 0c78980b26ce..5dd473d00110 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -143,6 +143,10 @@ int nfs40_discover_server_trunking(struct nfs_client *clp, /* Sustain the lease, even if it's empty. If the clientid4 * goes stale it's of no use for trunking discovery. */ nfs4_schedule_state_renewal(*result); + + /* If the client state need to recover, do it. */ + if (clp->cl_state) + nfs4_schedule_state_manager(clp); } out: return status; @@ -604,24 +608,39 @@ void nfs4_put_state_owner(struct nfs4_state_owner *sp) /** * nfs4_purge_state_owners - Release all cached state owners * @server: nfs_server with cached state owners to release + * @head: resulting list of state owners * * Called at umount time. Remaining state owners will be on * the LRU with ref count of zero. + * Note that the state owners are not freed, but are added + * to the list @head, which can later be used as an argument + * to nfs4_free_state_owners. */ -void nfs4_purge_state_owners(struct nfs_server *server) +void nfs4_purge_state_owners(struct nfs_server *server, struct list_head *head) { struct nfs_client *clp = server->nfs_client; struct nfs4_state_owner *sp, *tmp; - LIST_HEAD(doomed); spin_lock(&clp->cl_lock); list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) { - list_move(&sp->so_lru, &doomed); + list_move(&sp->so_lru, head); nfs4_remove_state_owner_locked(sp); } spin_unlock(&clp->cl_lock); +} - list_for_each_entry_safe(sp, tmp, &doomed, so_lru) { +/** + * nfs4_purge_state_owners - Release all cached state owners + * @head: resulting list of state owners + * + * Frees a list of state owners that was generated by + * nfs4_purge_state_owners + */ +void nfs4_free_state_owners(struct list_head *head) +{ + struct nfs4_state_owner *sp, *tmp; + + list_for_each_entry_safe(sp, tmp, head, so_lru) { list_del(&sp->so_lru); nfs4_free_state_owner(sp); } @@ -1772,12 +1791,13 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov struct nfs4_state_owner *sp; struct nfs_server *server; struct rb_node *pos; + LIST_HEAD(freeme); int status = 0; restart: rcu_read_lock(); list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { - nfs4_purge_state_owners(server); + nfs4_purge_state_owners(server, &freeme); spin_lock(&clp->cl_lock); for (pos = rb_first(&server->state_owners); pos != NULL; @@ -1806,6 +1826,7 @@ restart: spin_unlock(&clp->cl_lock); } rcu_read_unlock(); + nfs4_free_state_owners(&freeme); return 0; } diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 827922e94a8f..68f65b73e19b 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -1262,21 +1262,24 @@ static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc, int nfs_pageio_resend(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr) { - LIST_HEAD(failed); + LIST_HEAD(pages); *pg_io_completion(desc) = hdr->io_completion; desc->pg_dreq = hdr->dreq; - while (!list_empty(&hdr->pages)) { - struct nfs_page *req = nfs_list_entry(hdr->pages.next); + list_splice_init(&hdr->pages, &pages); + while (!list_empty(&pages)) { + struct nfs_page *req = nfs_list_entry(pages.next); nfs_list_remove_request(req); if (!nfs_pageio_add_request(desc, req)) - nfs_list_add_request(req, &failed); + break; } nfs_pageio_complete(desc); - if (!list_empty(&failed)) { - list_move(&failed, &hdr->pages); - return desc->pg_error < 0 ? desc->pg_error : -EIO; + if (!list_empty(&pages)) { + int err = desc->pg_error < 0 ? desc->pg_error : -EIO; + hdr->completion_ops->error_cleanup(&pages); + nfs_set_pgio_error(hdr, err, hdr->io_start); + return err; } return 0; } diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index d40755a0984b..11474aac91bc 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -650,11 +650,15 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, /* Add this address as an alias */ rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args, rpc_clnt_test_and_add_xprt, NULL); - } else - clp = get_v3_ds_connect(mds_srv, - (struct sockaddr *)&da->da_addr, - da->da_addrlen, IPPROTO_TCP, - timeo, retrans); + continue; + } + clp = get_v3_ds_connect(mds_srv, + (struct sockaddr *)&da->da_addr, + da->da_addrlen, IPPROTO_TCP, + timeo, retrans); + if (IS_ERR(clp)) + continue; + clp->cl_rpcclient->cl_softrtry = 0; } if (IS_ERR(clp)) { diff --git a/fs/nfs/super.c b/fs/nfs/super.c index e483d906de13..7d1f0140ff5a 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2091,7 +2091,8 @@ static int nfs23_validate_mount_data(void *options, memcpy(sap, &data->addr, sizeof(data->addr)); args->nfs_server.addrlen = sizeof(data->addr); args->nfs_server.port = ntohs(data->addr.sin_port); - if (!nfs_verify_server_address(sap)) + if (sap->sa_family != AF_INET || + !nfs_verify_server_address(sap)) goto out_no_address; if (!(data->flags & NFS_MOUNT_TCP)) @@ -2277,6 +2278,7 @@ nfs_compare_remount_data(struct nfs_server *nfss, data->acdirmin != nfss->acdirmin / HZ || data->acdirmax != nfss->acdirmax / HZ || data->timeo != (10U * nfss->client->cl_timeout->to_initval / HZ) || + (data->options & NFS_OPTION_FSCACHE) != (nfss->options & NFS_OPTION_FSCACHE) || data->nfs_server.port != nfss->port || data->nfs_server.addrlen != nfss->nfs_client->cl_addrlen || !rpc_cmp_addr((struct sockaddr *)&data->nfs_server.address, diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 74915e17581a..cc422964732d 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -668,7 +668,7 @@ out: return ret; out_launder: nfs_write_error_remove_page(req); - return ret; + return 0; } static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 0274db6e65d0..c28e37d942ab 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -931,8 +931,9 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) cb->cb_seq_status = 1; cb->cb_status = 0; if (minorversion) { - if (!nfsd41_cb_get_slot(clp, task)) + if (!cb->cb_holds_slot && !nfsd41_cb_get_slot(clp, task)) return; + cb->cb_holds_slot = true; } rpc_call_start(task); } @@ -959,6 +960,9 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback return true; } + if (!cb->cb_holds_slot) + goto need_restart; + switch (cb->cb_seq_status) { case 0: /* @@ -996,6 +1000,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback cb->cb_seq_status); } + cb->cb_holds_slot = false; clear_bit(0, &clp->cl_cb_slot_busy); rpc_wake_up_next(&clp->cl_cb_waitq); dprintk("%s: freed slot, new seqid=%d\n", __func__, @@ -1203,6 +1208,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, cb->cb_seq_status = 1; cb->cb_status = 0; cb->cb_need_restart = false; + cb->cb_holds_slot = false; } void nfsd4_run_cb(struct nfsd4_callback *cb) diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 86aa92d200e1..133d8bf62a5c 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -69,6 +69,7 @@ struct nfsd4_callback { int cb_seq_status; int cb_status; bool cb_need_restart; + bool cb_holds_slot; }; struct nfsd4_callback_ops { diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 34d1e291fe95..93efb7704856 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -269,6 +269,7 @@ struct svc_rqst { #define RQ_VICTIM (5) /* about to be shut down */ #define RQ_BUSY (6) /* request is busy */ #define RQ_DATA (7) /* request has data */ +#define RQ_AUTHERR (8) /* Request status is auth error */ unsigned long rq_flags; /* flags field */ void * rq_argp; /* decoded arguments */ @@ -493,6 +494,7 @@ void svc_wake_up(struct svc_serv *); void svc_reserve(struct svc_rqst *rqstp, int space); struct svc_pool * svc_pool_for_cpu(struct svc_serv *serv, int cpu); char * svc_print_addr(struct svc_rqst *, char *, size_t); +__be32 svc_return_autherr(struct svc_rqst *rqstp, __be32 auth_err); #define RPC_MAX_ADDRBUFLEN (63U) diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 4f94a8ecf36f..b8070b6c7ca0 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -30,7 +30,6 @@ #include <linux/elf.h> #include <linux/moduleloader.h> #include <linux/completion.h> -#include <linux/memory.h> #include <asm/cacheflush.h> #include "core.h" #include "patch.h" @@ -730,21 +729,16 @@ static int klp_init_object_loaded(struct klp_patch *patch, struct klp_func *func; int ret; - mutex_lock(&text_mutex); - module_disable_ro(patch->mod); ret = klp_write_object_relocations(patch->mod, obj); if (ret) { module_enable_ro(patch->mod, true); - mutex_unlock(&text_mutex); return ret; } arch_klp_init_object_loaded(patch, obj); module_enable_ro(patch->mod, true); - mutex_unlock(&text_mutex); - klp_for_each_func(obj, func) { ret = klp_find_object_symbol(obj->name, func->old_name, func->old_sympos, diff --git a/kernel/resource.c b/kernel/resource.c index 54b59151f81c..7063ef16427f 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -486,8 +486,6 @@ int walk_mem_res(u64 start, u64 end, void *arg, arg, func); } -#if !defined(CONFIG_ARCH_HAS_WALK_MEMORY) - /* * This function calls the @func callback against all memory ranges of type * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY. @@ -519,8 +517,6 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, return ret; } -#endif - static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg) { return 1; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 60395aa7af33..8137077d9012 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2175,11 +2175,12 @@ call_status(struct rpc_task *task) case -ECONNREFUSED: case -ECONNRESET: case -ECONNABORTED: + case -ENOTCONN: rpc_force_rebind(clnt); + break; case -EADDRINUSE: rpc_delay(task, 3*HZ); case -EPIPE: - case -ENOTCONN: task->tk_action = call_bind; break; case -ENOBUFS: diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 1e589aa63ddf..83686d8fba26 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1144,6 +1144,22 @@ void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) static __printf(2,3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) {} #endif +__be32 +svc_return_autherr(struct svc_rqst *rqstp, __be32 auth_err) +{ + set_bit(RQ_AUTHERR, &rqstp->rq_flags); + return auth_err; +} +EXPORT_SYMBOL_GPL(svc_return_autherr); + +static __be32 +svc_get_autherr(struct svc_rqst *rqstp, __be32 *statp) +{ + if (test_and_clear_bit(RQ_AUTHERR, &rqstp->rq_flags)) + return *statp; + return rpc_auth_ok; +} + /* * Common routine for processing the RPC request. */ @@ -1295,11 +1311,9 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) procp->pc_release(rqstp, NULL, rqstp->rq_resp); goto dropit; } - if (*statp == rpc_autherr_badcred) { - if (procp->pc_release) - procp->pc_release(rqstp, NULL, rqstp->rq_resp); - goto err_bad_auth; - } + auth_stat = svc_get_autherr(rqstp, statp); + if (auth_stat != rpc_auth_ok) + goto err_release_bad_auth; if (*statp == rpc_success && (xdr = procp->pc_encode) && !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) { @@ -1357,6 +1371,9 @@ err_bad_rpc: svc_putnl(resv, 2); goto sendit; +err_release_bad_auth: + if (procp->pc_release) + procp->pc_release(rqstp, NULL, rqstp->rq_resp); err_bad_auth: dprintk("svc: authentication failed (%d)\n", ntohl(auth_stat)); serv->sv_stats->rpcbadauth++; |