diff options
Diffstat (limited to 'arch/powerpc')
33 files changed, 228 insertions, 179 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2d0be82c3061..fa7219ffeadc 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -103,13 +103,6 @@ config LOCKDEP_SUPPORT bool default y -config RWSEM_GENERIC_SPINLOCK - bool - -config RWSEM_XCHGADD_ALGORITHM - bool - default y - config GENERIC_LOCKBREAK bool default y @@ -132,6 +125,7 @@ config PPC select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV + select ARCH_HAS_MMIOWB if PPC64 select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_PMEM_API if PPC64 select ARCH_HAS_PTE_SPECIAL @@ -218,6 +212,8 @@ config PPC select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE if SMP + select HAVE_RCU_TABLE_NO_INVALIDATE if HAVE_RCU_TABLE_FREE + select HAVE_MMU_GATHER_PAGE_SIZE select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN select HAVE_SYSCALL_TRACEPOINTS @@ -318,6 +314,10 @@ config ARCH_SUSPEND_POSSIBLE (PPC_85xx && !PPC_E500MC) || PPC_86xx || PPC_PSERIES \ || 44x || 40x +config ARCH_SUSPEND_NONZERO_CPU + def_bool y + depends on PPC_POWERNV || PPC_PSERIES + config PPC_DCR_NATIVE bool diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index 5ba131c30f6b..1bcd468ab422 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -266,6 +266,7 @@ CONFIG_UDF_FS=m CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m CONFIG_PROC_KCORE=y +CONFIG_HUGETLBFS=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_NLS=y diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c index fd1d6c83f0c0..c4fa242dd652 100644 --- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c +++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c @@ -1,10 +1,12 @@ #include <linux/crc32.h> #include <crypto/internal/hash.h> +#include <crypto/internal/simd.h> #include <linux/init.h> #include <linux/module.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/cpufeature.h> +#include <asm/simd.h> #include <asm/switch_to.h> #define CHKSUM_BLOCK_SIZE 1 @@ -22,7 +24,7 @@ static u32 crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len) unsigned int prealign; unsigned int tail; - if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || in_interrupt()) + if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || !crypto_simd_usable()) return __crc32c_le(crc, p, len); if ((unsigned long)p & VMX_ALIGN_MASK) { diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c b/arch/powerpc/crypto/crct10dif-vpmsum_glue.c index 02ea277863d1..e27ff16573b5 100644 --- a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c +++ b/arch/powerpc/crypto/crct10dif-vpmsum_glue.c @@ -12,11 +12,13 @@ #include <linux/crc-t10dif.h> #include <crypto/internal/hash.h> +#include <crypto/internal/simd.h> #include <linux/init.h> #include <linux/module.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/cpufeature.h> +#include <asm/simd.h> #include <asm/switch_to.h> #define VMX_ALIGN 16 @@ -32,7 +34,7 @@ static u16 crct10dif_vpmsum(u16 crci, unsigned char const *p, size_t len) unsigned int tail; u32 crc = crci; - if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || in_interrupt()) + if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || !crypto_simd_usable()) return crc_t10dif_generic(crc, p, len); if ((unsigned long)p & VMX_ALIGN_MASK) { diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index a0c132bedfae..b9f6e72bf4e5 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -8,6 +8,6 @@ generic-y += irq_regs.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += preempt.h -generic-y += rwsem.h generic-y += vtime.h generic-y += msi.h +generic-y += simd.h diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 4b73847e9b95..1fad67b46409 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -34,14 +34,11 @@ extern struct pci_dev *isa_bridge_pcidev; #include <asm/byteorder.h> #include <asm/synch.h> #include <asm/delay.h> +#include <asm/mmiowb.h> #include <asm/mmu.h> #include <asm/ppc_asm.h> #include <asm/pgtable.h> -#ifdef CONFIG_PPC64 -#include <asm/paca.h> -#endif - #define SIO_CONFIG_RA 0x398 #define SIO_CONFIG_RD 0x399 @@ -107,12 +104,6 @@ extern bool isa_io_special; * */ -#ifdef CONFIG_PPC64 -#define IO_SET_SYNC_FLAG() do { local_paca->io_sync = 1; } while(0) -#else -#define IO_SET_SYNC_FLAG() -#endif - #define DEF_MMIO_IN_X(name, size, insn) \ static inline u##size name(const volatile u##size __iomem *addr) \ { \ @@ -127,7 +118,7 @@ static inline void name(volatile u##size __iomem *addr, u##size val) \ { \ __asm__ __volatile__("sync;"#insn" %1,%y0" \ : "=Z" (*addr) : "r" (val) : "memory"); \ - IO_SET_SYNC_FLAG(); \ + mmiowb_set_pending(); \ } #define DEF_MMIO_IN_D(name, size, insn) \ @@ -144,7 +135,7 @@ static inline void name(volatile u##size __iomem *addr, u##size val) \ { \ __asm__ __volatile__("sync;"#insn"%U0%X0 %1,%0" \ : "=m" (*addr) : "r" (val) : "memory"); \ - IO_SET_SYNC_FLAG(); \ + mmiowb_set_pending(); \ } DEF_MMIO_IN_D(in_8, 8, lbz); @@ -652,24 +643,6 @@ static inline void name at \ #include <asm-generic/iomap.h> -#ifdef CONFIG_PPC32 -#define mmiowb() -#else -/* - * Enforce synchronisation of stores vs. spin_unlock - * (this does it explicitly, though our implementation of spin_unlock - * does it implicitely too) - */ -static inline void mmiowb(void) -{ - unsigned long tmp; - - __asm__ __volatile__("sync; li %0,0; stb %0,%1(13)" - : "=&r" (tmp) : "i" (offsetof(struct paca_struct, io_sync)) - : "memory"); -} -#endif /* !CONFIG_PPC32 */ - static inline void iosync(void) { __asm__ __volatile__ ("sync" : : : "memory"); diff --git a/arch/powerpc/include/asm/mmiowb.h b/arch/powerpc/include/asm/mmiowb.h new file mode 100644 index 000000000000..74a00127eb20 --- /dev/null +++ b/arch/powerpc/include/asm/mmiowb.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_MMIOWB_H +#define _ASM_POWERPC_MMIOWB_H + +#ifdef CONFIG_MMIOWB + +#include <linux/compiler.h> +#include <asm/barrier.h> +#include <asm/paca.h> + +#define arch_mmiowb_state() (&local_paca->mmiowb_state) +#define mmiowb() mb() + +#endif /* CONFIG_MMIOWB */ + +#include <asm-generic/mmiowb.h> + +#endif /* _ASM_POWERPC_MMIOWB_H */ diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 598cdcdd1355..8ddd4a91bdc1 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -352,7 +352,7 @@ static inline bool strict_kernel_rwx_enabled(void) #if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) && \ defined (CONFIG_PPC_64K_PAGES) #define MAX_PHYSMEM_BITS 51 -#elif defined(CONFIG_SPARSEMEM) +#elif defined(CONFIG_PPC64) #define MAX_PHYSMEM_BITS 46 #endif diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index e843bc5d1a0f..134e912d403f 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -34,6 +34,8 @@ #include <asm/cpuidle.h> #include <asm/atomic.h> +#include <asm-generic/mmiowb_types.h> + register struct paca_struct *local_paca asm("r13"); #if defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_SMP) @@ -171,7 +173,6 @@ struct paca_struct { u16 trap_save; /* Used when bad stack is encountered */ u8 irq_soft_mask; /* mask for irq soft masking */ u8 irq_happened; /* irq happened while soft-disabled */ - u8 io_sync; /* writel() needs spin_unlock sync */ u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */ u8 nap_state_lost; /* NV GPR values lost in power7_idle */ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE @@ -264,6 +265,9 @@ struct paca_struct { #ifdef CONFIG_STACKPROTECTOR unsigned long canary; #endif +#ifdef CONFIG_MMIOWB + struct mmiowb_state mmiowb_state; +#endif } ____cacheline_aligned; extern void copy_mm_to_paca(struct mm_struct *mm); diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index c5698a523bb1..23f7ed796f38 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -302,6 +302,7 @@ /* Misc instructions for BPF compiler */ #define PPC_INST_LBZ 0x88000000 #define PPC_INST_LD 0xe8000000 +#define PPC_INST_LDX 0x7c00002a #define PPC_INST_LHZ 0xa0000000 #define PPC_INST_LWZ 0x80000000 #define PPC_INST_LHBRX 0x7c00062c @@ -309,6 +310,7 @@ #define PPC_INST_STB 0x98000000 #define PPC_INST_STH 0xb0000000 #define PPC_INST_STD 0xf8000000 +#define PPC_INST_STDX 0x7c00012a #define PPC_INST_STDU 0xf8000001 #define PPC_INST_STW 0x90000000 #define PPC_INST_STWU 0x94000000 diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 685c72310f5d..15b39c407c4e 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -39,19 +39,6 @@ #define LOCK_TOKEN 1 #endif -#if defined(CONFIG_PPC64) && defined(CONFIG_SMP) -#define CLEAR_IO_SYNC (get_paca()->io_sync = 0) -#define SYNC_IO do { \ - if (unlikely(get_paca()->io_sync)) { \ - mb(); \ - get_paca()->io_sync = 0; \ - } \ - } while (0) -#else -#define CLEAR_IO_SYNC -#define SYNC_IO -#endif - #ifdef CONFIG_PPC_PSERIES #define vcpu_is_preempted vcpu_is_preempted static inline bool vcpu_is_preempted(int cpu) @@ -99,7 +86,6 @@ static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock) static inline int arch_spin_trylock(arch_spinlock_t *lock) { - CLEAR_IO_SYNC; return __arch_spin_trylock(lock) == 0; } @@ -130,7 +116,6 @@ extern void __rw_yield(arch_rwlock_t *lock); static inline void arch_spin_lock(arch_spinlock_t *lock) { - CLEAR_IO_SYNC; while (1) { if (likely(__arch_spin_trylock(lock) == 0)) break; @@ -148,7 +133,6 @@ void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) { unsigned long flags_dis; - CLEAR_IO_SYNC; while (1) { if (likely(__arch_spin_trylock(lock) == 0)) break; @@ -167,7 +151,6 @@ void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) static inline void arch_spin_unlock(arch_spinlock_t *lock) { - SYNC_IO; __asm__ __volatile__("# arch_spin_unlock\n\t" PPC_RELEASE_BARRIER: : :"memory"); lock->slock = 0; diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h index 1a0e7a8b1c81..1243045bad2d 100644 --- a/arch/powerpc/include/asm/syscall.h +++ b/arch/powerpc/include/asm/syscall.h @@ -65,22 +65,20 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { unsigned long val, mask = -1UL; - - BUG_ON(i + n > 6); + unsigned int n = 6; #ifdef CONFIG_COMPAT if (test_tsk_thread_flag(task, TIF_32BIT)) mask = 0xffffffff; #endif while (n--) { - if (n == 0 && i == 0) + if (n == 0) val = regs->orig_gpr3; else - val = regs->gpr[3 + i + n]; + val = regs->gpr[3 + n]; args[n] = val & mask; } @@ -88,15 +86,12 @@ static inline void syscall_get_arguments(struct task_struct *task, static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { - BUG_ON(i + n > 6); - memcpy(®s->gpr[3 + i], args, n * sizeof(args[0])); + memcpy(®s->gpr[3], args, 6 * sizeof(args[0])); /* Also copy the first argument into orig_gpr3 */ - if (i == 0 && n > 0) - regs->orig_gpr3 = args[0]; + regs->orig_gpr3 = args[0]; } static inline int syscall_get_arch(void) diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index e24c67d5ba75..34fba1ce27f7 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -27,8 +27,8 @@ #define tlb_start_vma(tlb, vma) do { } while (0) #define tlb_end_vma(tlb, vma) do { } while (0) #define __tlb_remove_tlb_entry __tlb_remove_tlb_entry -#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change +#define tlb_flush tlb_flush extern void tlb_flush(struct mmu_gather *tlb); /* Get the generic bits... */ @@ -46,22 +46,6 @@ static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, #endif } -static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, - unsigned int page_size) -{ - if (!tlb->page_size) - tlb->page_size = page_size; - else if (tlb->page_size != page_size) { - if (!tlb->fullmm) - tlb_flush_mmu(tlb); - /* - * update the page size after flush for the new - * mmu_gather. - */ - tlb->page_size = page_size; - } -} - #ifdef CONFIG_SMP static inline int mm_is_core_local(struct mm_struct *mm) { diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index a5b8fbae56a0..9481a117e242 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -656,11 +656,17 @@ EXC_COMMON_BEGIN(data_access_slb_common) ld r4,PACA_EXSLB+EX_DAR(r13) std r4,_DAR(r1) addi r3,r1,STACK_FRAME_OVERHEAD +BEGIN_MMU_FTR_SECTION + /* HPT case, do SLB fault */ bl do_slb_fault cmpdi r3,0 bne- 1f b fast_exception_return 1: /* Error case */ +MMU_FTR_SECTION_ELSE + /* Radix case, access is outside page table range */ + li r3,-EFAULT +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) std r3,RESULT(r1) bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) @@ -705,11 +711,17 @@ EXC_COMMON_BEGIN(instruction_access_slb_common) EXCEPTION_PROLOG_COMMON(0x480, PACA_EXSLB) ld r4,_NIP(r1) addi r3,r1,STACK_FRAME_OVERHEAD +BEGIN_MMU_FTR_SECTION + /* HPT case, do SLB fault */ bl do_slb_fault cmpdi r3,0 bne- 1f b fast_exception_return 1: /* Error case */ +MMU_FTR_SECTION_ELSE + /* Radix case, access is outside page table range */ + li r3,-EFAULT +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) std r3,RESULT(r1) bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 48051c8977c5..e25b615e9f9e 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -851,10 +851,6 @@ __secondary_start: tophys(r4,r2) addi r4,r4,THREAD /* phys address of our thread_struct */ mtspr SPRN_SPRG_THREAD,r4 -#ifdef CONFIG_PPC_RTAS - li r3,0 - stw r3, RTAS_SP(r4) /* 0 => not in RTAS */ -#endif lis r4, (swapper_pg_dir - PAGE_OFFSET)@h ori r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l mtspr SPRN_SPRG_PGDIR, r4 @@ -941,10 +937,6 @@ start_here: tophys(r4,r2) addi r4,r4,THREAD /* init task's THREAD */ mtspr SPRN_SPRG_THREAD,r4 -#ifdef CONFIG_PPC_RTAS - li r3,0 - stw r3, RTAS_SP(r4) /* 0 => not in RTAS */ -#endif lis r4, (swapper_pg_dir - PAGE_OFFSET)@h ori r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l mtspr SPRN_SPRG_PGDIR, r4 diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 683b5b3805bd..cd381e2291df 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -22,6 +22,7 @@ #include <linux/kvm_host.h> #include <linux/init.h> #include <linux/export.h> +#include <linux/kmemleak.h> #include <linux/kvm_para.h> #include <linux/slab.h> #include <linux/of.h> @@ -712,6 +713,12 @@ static void kvm_use_magic_page(void) static __init void kvm_free_tmp(void) { + /* + * Inform kmemleak about the hole in the .bss section since the + * corresponding pages will be unmapped with DEBUG_PAGEALLOC=y. + */ + kmemleak_free_part(&kvm_tmp[kvm_tmp_index], + ARRAY_SIZE(kvm_tmp) - kvm_tmp_index); free_reserved_area(&kvm_tmp[kvm_tmp_index], &kvm_tmp[ARRAY_SIZE(kvm_tmp)], -1, NULL); } diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index b33bafb8fcea..70568ccbd9fd 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -57,7 +57,7 @@ void setup_barrier_nospec(void) enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR); - if (!no_nospec) + if (!no_nospec && !cpu_mitigations_off()) enable_barrier_nospec(enable); } @@ -116,7 +116,7 @@ static int __init handle_nospectre_v2(char *p) early_param("nospectre_v2", handle_nospectre_v2); void setup_spectre_v2(void) { - if (no_spectrev2) + if (no_spectrev2 || cpu_mitigations_off()) do_btb_flush_fixups(); else btb_flush_enabled = true; @@ -300,7 +300,7 @@ void setup_stf_barrier(void) stf_enabled_flush_types = type; - if (!no_stf_barrier) + if (!no_stf_barrier && !cpu_mitigations_off()) stf_barrier_enable(enable); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index ba404dd9ce1d..4f49e1a3594c 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -932,7 +932,7 @@ void setup_rfi_flush(enum l1d_flush_type types, bool enable) enabled_flush_types = types; - if (!no_rfi_flush) + if (!no_rfi_flush && !cpu_mitigations_off()) rfi_flush_enable(enable); } diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index b18abb0c3dae..00f5a63c8d9a 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -505,3 +505,7 @@ 421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 422 32 futex_time64 sys_futex sys_futex 423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 1e0bc5955a40..afd516b572f8 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -98,7 +98,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) * can be used, r7 contains NSEC_PER_SEC. */ - lwz r5,WTOM_CLOCK_SEC(r9) + lwz r5,(WTOM_CLOCK_SEC+LOPART)(r9) lwz r6,WTOM_CLOCK_NSEC(r9) /* We now have our offset in r5,r6. We create a fake dependency diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index f02b04973710..f100e331e69b 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -543,14 +543,14 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, if (ret != H_SUCCESS) return ret; + idx = srcu_read_lock(&vcpu->kvm->srcu); + ret = kvmppc_tce_validate(stt, tce); if (ret != H_SUCCESS) - return ret; + goto unlock_exit; dir = iommu_tce_direction(tce); - idx = srcu_read_lock(&vcpu->kvm->srcu); - if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) { ret = H_PARAMETER; goto unlock_exit; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 06964350b97a..b2b29d4f9842 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3423,7 +3423,9 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit, vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2); vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3); - mtspr(SPRN_PSSCR, host_psscr); + /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */ + mtspr(SPRN_PSSCR, host_psscr | + (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); mtspr(SPRN_HFSCR, host_hfscr); mtspr(SPRN_CIABR, host_ciabr); mtspr(SPRN_DAWR, host_dawr); diff --git a/arch/powerpc/lib/memcmp_64.S b/arch/powerpc/lib/memcmp_64.S index 844d8e774492..b7f6f6e0b6e8 100644 --- a/arch/powerpc/lib/memcmp_64.S +++ b/arch/powerpc/lib/memcmp_64.S @@ -215,11 +215,20 @@ _GLOBAL_TOC(memcmp) beq .Lzero .Lcmp_rest_lt8bytes: - /* Here we have only less than 8 bytes to compare with. at least s1 - * Address is aligned with 8 bytes. - * The next double words are load and shift right with appropriate - * bits. + /* + * Here we have less than 8 bytes to compare. At least s1 is aligned to + * 8 bytes, but s2 may not be. We must make sure s2 + 7 doesn't cross a + * page boundary, otherwise we might read past the end of the buffer and + * trigger a page fault. We use 4K as the conservative minimum page + * size. If we detect that case we go to the byte-by-byte loop. + * + * Otherwise the next double word is loaded from s1 and s2, and shifted + * right to compare the appropriate bits. */ + clrldi r6,r4,(64-12) // r6 = r4 & 0xfff + cmpdi r6,0xff8 + bgt .Lshort + subfic r6,r5,8 slwi r6,r6,3 LD rA,0,r3 diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c index e7a9c4f6bfca..8330f135294f 100644 --- a/arch/powerpc/mm/mmu_context_iommu.c +++ b/arch/powerpc/mm/mmu_context_iommu.c @@ -95,28 +95,15 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, unsigned long entries, unsigned long dev_hpa, struct mm_iommu_table_group_mem_t **pmem) { - struct mm_iommu_table_group_mem_t *mem; - long i, ret, locked_entries = 0; + struct mm_iommu_table_group_mem_t *mem, *mem2; + long i, ret, locked_entries = 0, pinned = 0; unsigned int pageshift; - - mutex_lock(&mem_list_mutex); - - list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, - next) { - /* Overlap? */ - if ((mem->ua < (ua + (entries << PAGE_SHIFT))) && - (ua < (mem->ua + - (mem->entries << PAGE_SHIFT)))) { - ret = -EINVAL; - goto unlock_exit; - } - - } + unsigned long entry, chunk; if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) { ret = mm_iommu_adjust_locked_vm(mm, entries, true); if (ret) - goto unlock_exit; + return ret; locked_entries = entries; } @@ -148,17 +135,27 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, } down_read(&mm->mmap_sem); - ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL); + chunk = (1UL << (PAGE_SHIFT + MAX_ORDER - 1)) / + sizeof(struct vm_area_struct *); + chunk = min(chunk, entries); + for (entry = 0; entry < entries; entry += chunk) { + unsigned long n = min(entries - entry, chunk); + + ret = get_user_pages_longterm(ua + (entry << PAGE_SHIFT), n, + FOLL_WRITE, mem->hpages + entry, NULL); + if (ret == n) { + pinned += n; + continue; + } + if (ret > 0) + pinned += ret; + break; + } up_read(&mm->mmap_sem); - if (ret != entries) { - /* free the reference taken */ - for (i = 0; i < ret; i++) - put_page(mem->hpages[i]); - - vfree(mem->hpas); - kfree(mem); - ret = -EFAULT; - goto unlock_exit; + if (pinned != entries) { + if (!ret) + ret = -EFAULT; + goto free_exit; } pageshift = PAGE_SHIFT; @@ -183,21 +180,43 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, } good_exit: - ret = 0; atomic64_set(&mem->mapped, 1); mem->used = 1; mem->ua = ua; mem->entries = entries; - *pmem = mem; - list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list); + mutex_lock(&mem_list_mutex); -unlock_exit: - if (locked_entries && ret) - mm_iommu_adjust_locked_vm(mm, locked_entries, false); + list_for_each_entry_rcu(mem2, &mm->context.iommu_group_mem_list, next) { + /* Overlap? */ + if ((mem2->ua < (ua + (entries << PAGE_SHIFT))) && + (ua < (mem2->ua + + (mem2->entries << PAGE_SHIFT)))) { + ret = -EINVAL; + mutex_unlock(&mem_list_mutex); + goto free_exit; + } + } + + list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list); mutex_unlock(&mem_list_mutex); + *pmem = mem; + + return 0; + +free_exit: + /* free the reference taken */ + for (i = 0; i < pinned; i++) + put_page(mem->hpages[i]); + + vfree(mem->hpas); + kfree(mem); + +unlock_exit: + mm_iommu_adjust_locked_vm(mm, locked_entries, false); + return ret; } @@ -266,7 +285,7 @@ static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem) long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem) { long ret = 0; - unsigned long entries, dev_hpa; + unsigned long unlock_entries = 0; mutex_lock(&mem_list_mutex); @@ -287,17 +306,17 @@ long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem) goto unlock_exit; } + if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) + unlock_entries = mem->entries; + /* @mapped became 0 so now mappings are disabled, release the region */ - entries = mem->entries; - dev_hpa = mem->dev_hpa; mm_iommu_release(mem); - if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) - mm_iommu_adjust_locked_vm(mm, entries, false); - unlock_exit: mutex_unlock(&mem_list_mutex); + mm_iommu_adjust_locked_vm(mm, unlock_entries, false); + return ret; } EXPORT_SYMBOL_GPL(mm_iommu_put); diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c index f29d2f118b44..5d9c3ff728c9 100644 --- a/arch/powerpc/mm/ppc_mmu_32.c +++ b/arch/powerpc/mm/ppc_mmu_32.c @@ -98,10 +98,20 @@ static int find_free_bat(void) return -1; } +/* + * This function calculates the size of the larger block usable to map the + * beginning of an area based on the start address and size of that area: + * - max block size is 8M on 601 and 256 on other 6xx. + * - base address must be aligned to the block size. So the maximum block size + * is identified by the lowest bit set to 1 in the base address (for instance + * if base is 0x16000000, max size is 0x02000000). + * - block size has to be a power of two. This is calculated by finding the + * highest bit set to 1. + */ static unsigned int block_size(unsigned long base, unsigned long top) { unsigned int max_size = (cpu_has_feature(CPU_FTR_601) ? 8 : 256) << 20; - unsigned int base_shift = (fls(base) - 1) & 31; + unsigned int base_shift = (ffs(base) - 1) & 31; unsigned int block_shift = (fls(top - base) - 1) & 31; return min3(max_size, 1U << base_shift, 1U << block_shift); @@ -157,7 +167,7 @@ static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long to unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) { - int done; + unsigned long done; unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET; if (__map_without_bats) { @@ -169,10 +179,10 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) return __mmu_mapin_ram(base, top); done = __mmu_mapin_ram(base, border); - if (done != border - base) + if (done != border) return done; - return done + __mmu_mapin_ram(border, top); + return __mmu_mapin_ram(border, top); } void mmu_mark_initmem_nx(void) diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 549e9490ff2a..dcac37745b05 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -51,6 +51,8 @@ #define PPC_LIS(r, i) PPC_ADDIS(r, 0, i) #define PPC_STD(r, base, i) EMIT(PPC_INST_STD | ___PPC_RS(r) | \ ___PPC_RA(base) | ((i) & 0xfffc)) +#define PPC_STDX(r, base, b) EMIT(PPC_INST_STDX | ___PPC_RS(r) | \ + ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_STDU(r, base, i) EMIT(PPC_INST_STDU | ___PPC_RS(r) | \ ___PPC_RA(base) | ((i) & 0xfffc)) #define PPC_STW(r, base, i) EMIT(PPC_INST_STW | ___PPC_RS(r) | \ @@ -65,7 +67,9 @@ #define PPC_LBZ(r, base, i) EMIT(PPC_INST_LBZ | ___PPC_RT(r) | \ ___PPC_RA(base) | IMM_L(i)) #define PPC_LD(r, base, i) EMIT(PPC_INST_LD | ___PPC_RT(r) | \ - ___PPC_RA(base) | IMM_L(i)) + ___PPC_RA(base) | ((i) & 0xfffc)) +#define PPC_LDX(r, base, b) EMIT(PPC_INST_LDX | ___PPC_RT(r) | \ + ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_LWZ(r, base, i) EMIT(PPC_INST_LWZ | ___PPC_RT(r) | \ ___PPC_RA(base) | IMM_L(i)) #define PPC_LHZ(r, base, i) EMIT(PPC_INST_LHZ | ___PPC_RT(r) | \ @@ -85,17 +89,6 @@ ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_BPF_STDCX(s, a, b) EMIT(PPC_INST_STDCX | ___PPC_RS(s) | \ ___PPC_RA(a) | ___PPC_RB(b)) - -#ifdef CONFIG_PPC64 -#define PPC_BPF_LL(r, base, i) do { PPC_LD(r, base, i); } while(0) -#define PPC_BPF_STL(r, base, i) do { PPC_STD(r, base, i); } while(0) -#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0) -#else -#define PPC_BPF_LL(r, base, i) do { PPC_LWZ(r, base, i); } while(0) -#define PPC_BPF_STL(r, base, i) do { PPC_STW(r, base, i); } while(0) -#define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0) -#endif - #define PPC_CMPWI(a, i) EMIT(PPC_INST_CMPWI | ___PPC_RA(a) | IMM_L(i)) #define PPC_CMPDI(a, i) EMIT(PPC_INST_CMPDI | ___PPC_RA(a) | IMM_L(i)) #define PPC_CMPW(a, b) EMIT(PPC_INST_CMPW | ___PPC_RA(a) | \ diff --git a/arch/powerpc/net/bpf_jit32.h b/arch/powerpc/net/bpf_jit32.h index dc50a8d4b3b9..21744d8aa053 100644 --- a/arch/powerpc/net/bpf_jit32.h +++ b/arch/powerpc/net/bpf_jit32.h @@ -122,6 +122,10 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh); #define PPC_NTOHS_OFFS(r, base, i) PPC_LHZ_OFFS(r, base, i) #endif +#define PPC_BPF_LL(r, base, i) do { PPC_LWZ(r, base, i); } while(0) +#define PPC_BPF_STL(r, base, i) do { PPC_STW(r, base, i); } while(0) +#define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0) + #define SEEN_DATAREF 0x10000 /* might call external helpers */ #define SEEN_XREG 0x20000 /* X reg is used */ #define SEEN_MEM 0x40000 /* SEEN_MEM+(1<<n) = use mem[n] for temporary diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h index 3609be4692b3..47f441f351a6 100644 --- a/arch/powerpc/net/bpf_jit64.h +++ b/arch/powerpc/net/bpf_jit64.h @@ -68,6 +68,26 @@ static const int b2p[] = { /* PPC NVR range -- update this if we ever use NVRs below r27 */ #define BPF_PPC_NVR_MIN 27 +/* + * WARNING: These can use TMP_REG_2 if the offset is not at word boundary, + * so ensure that it isn't in use already. + */ +#define PPC_BPF_LL(r, base, i) do { \ + if ((i) % 4) { \ + PPC_LI(b2p[TMP_REG_2], (i)); \ + PPC_LDX(r, base, b2p[TMP_REG_2]); \ + } else \ + PPC_LD(r, base, i); \ + } while(0) +#define PPC_BPF_STL(r, base, i) do { \ + if ((i) % 4) { \ + PPC_LI(b2p[TMP_REG_2], (i)); \ + PPC_STDX(r, base, b2p[TMP_REG_2]); \ + } else \ + PPC_STD(r, base, i); \ + } while(0) +#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0) + #define SEEN_FUNC 0x1000 /* might call external helpers */ #define SEEN_STACK 0x2000 /* uses BPF stack */ #define SEEN_TAILCALL 0x4000 /* uses tail calls */ diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 4194d3cfb60c..21a1dcd4b156 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -252,7 +252,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 * if (tail_call_cnt > MAX_TAIL_CALL_CNT) * goto out; */ - PPC_LD(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx)); + PPC_BPF_LL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx)); PPC_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT); PPC_BCC(COND_GT, out); @@ -265,7 +265,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 /* prog = array->ptrs[index]; */ PPC_MULI(b2p[TMP_REG_1], b2p_index, 8); PPC_ADD(b2p[TMP_REG_1], b2p[TMP_REG_1], b2p_bpf_array); - PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs)); + PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs)); /* * if (prog == NULL) @@ -275,7 +275,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 PPC_BCC(COND_EQ, out); /* goto *(prog->bpf_func + prologue_size); */ - PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func)); + PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func)); #ifdef PPC64_ELF_ABI_v1 /* skip past the function descriptor */ PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], @@ -606,7 +606,7 @@ bpf_alu32_trunc: * the instructions generated will remain the * same across all passes */ - PPC_STD(dst_reg, 1, bpf_jit_stack_local(ctx)); + PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx)); PPC_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx)); PPC_LDBRX(dst_reg, 0, b2p[TMP_REG_1]); break; @@ -662,7 +662,7 @@ emit_clear: PPC_LI32(b2p[TMP_REG_1], imm); src_reg = b2p[TMP_REG_1]; } - PPC_STD(src_reg, dst_reg, off); + PPC_BPF_STL(src_reg, dst_reg, off); break; /* @@ -709,7 +709,7 @@ emit_clear: break; /* dst = *(u64 *)(ul) (src + off) */ case BPF_LDX | BPF_MEM | BPF_DW: - PPC_LD(dst_reg, src_reg, off); + PPC_BPF_LL(dst_reg, src_reg, off); break; /* diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 842b2c7e156a..50cd09b4e05d 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -324,7 +324,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK config PPC_RADIX_MMU bool "Radix MMU Support" - depends on PPC_BOOK3S_64 + depends on PPC_BOOK3S_64 && HUGETLB_PAGE select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA default y help diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c index 6ed22127391b..921f12182f3e 100644 --- a/arch/powerpc/platforms/pseries/pseries_energy.c +++ b/arch/powerpc/platforms/pseries/pseries_energy.c @@ -77,18 +77,27 @@ static u32 cpu_to_drc_index(int cpu) ret = drc.drc_index_start + (thread_index * drc.sequential_inc); } else { - const __be32 *indexes; - - indexes = of_get_property(dn, "ibm,drc-indexes", NULL); - if (indexes == NULL) - goto err_of_node_put; + u32 nr_drc_indexes, thread_drc_index; /* - * The first element indexes[0] is the number of drc_indexes - * returned in the list. Hence thread_index+1 will get the - * drc_index corresponding to core number thread_index. + * The first element of ibm,drc-indexes array is the + * number of drc_indexes returned in the list. Hence + * thread_index+1 will get the drc_index corresponding + * to core number thread_index. */ - ret = indexes[thread_index + 1]; + rc = of_property_read_u32_index(dn, "ibm,drc-indexes", + 0, &nr_drc_indexes); + if (rc) + goto err_of_node_put; + + WARN_ON_ONCE(thread_index > nr_drc_indexes); + rc = of_property_read_u32_index(dn, "ibm,drc-indexes", + thread_index + 1, + &thread_drc_index); + if (rc) + goto err_of_node_put; + + ret = thread_drc_index; } rc = 0; diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index d97d52772789..452dcfd7e5dd 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -550,6 +550,7 @@ static void pseries_print_mce_info(struct pt_regs *regs, "UE", "SLB", "ERAT", + "Unknown", "TLB", "D-Cache", "Unknown", diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index a0f44f992360..13c6a47e6150 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2429,7 +2429,10 @@ static void dump_one_paca(int cpu) DUMP(p, trap_save, "%#-*x"); DUMP(p, irq_soft_mask, "%#-*x"); DUMP(p, irq_happened, "%#-*x"); - DUMP(p, io_sync, "%#-*x"); +#ifdef CONFIG_MMIOWB + DUMP(p, mmiowb_state.nesting_count, "%#-*x"); + DUMP(p, mmiowb_state.mmiowb_pending, "%#-*x"); +#endif DUMP(p, irq_work_pending, "%#-*x"); DUMP(p, nap_state_lost, "%#-*x"); DUMP(p, sprg_vdso, "%#-*llx"); |