diff options
Diffstat (limited to 'arch/powerpc')
96 files changed, 781 insertions, 381 deletions
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index d2824b0cc142..c4c03992ee82 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -160,8 +160,17 @@ else CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=powerpc64 endif +ifdef CONFIG_FUNCTION_TRACER +CC_FLAGS_FTRACE := -pg ifdef CONFIG_MPROFILE_KERNEL - CC_FLAGS_FTRACE := -pg -mprofile-kernel +CC_FLAGS_FTRACE += -mprofile-kernel +endif +# Work around gcc code-gen bugs with -pg / -fno-omit-frame-pointer in gcc <= 4.8 +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=44199 +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=52828 +ifneq ($(cc-name),clang) +CC_FLAGS_FTRACE += $(call cc-ifversion, -lt, 0409, -mno-sched-epilog) +endif endif CFLAGS-$(CONFIG_TARGET_CPU_BOOL) += $(call cc-option,-mcpu=$(CONFIG_TARGET_CPU)) @@ -229,11 +238,6 @@ ifdef CONFIG_6xx KBUILD_CFLAGS += -mcpu=powerpc endif -# Work around a gcc code-gen bug with -fno-omit-frame-pointer. -ifdef CONFIG_FUNCTION_TRACER -KBUILD_CFLAGS += -mno-sched-epilog -endif - cpu-as-$(CONFIG_4xx) += -Wa,-m405 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) cpu-as-$(CONFIG_E200) += -Wa,-me200 @@ -408,36 +412,9 @@ archprepare: checkbin # to stdout and these checks are run even on install targets. TOUT := .tmp_gas_check -# Check gcc and binutils versions: -# - gcc-3.4 and binutils-2.14 are a fatal combination -# - Require gcc 4.0 or above on 64-bit -# - gcc-4.2.0 has issues compiling modules on 64-bit +# Check toolchain versions: +# - gcc-4.6 is the minimum kernel-wide version so nothing required. checkbin: - @if test "$(cc-name)" != "clang" \ - && test "$(cc-version)" = "0304" ; then \ - if ! /bin/echo mftb 5 | $(AS) -v -mppc -many -o $(TOUT) >/dev/null 2>&1 ; then \ - echo -n '*** ${VERSION}.${PATCHLEVEL} kernels no longer build '; \ - echo 'correctly with gcc-3.4 and your version of binutils.'; \ - echo '*** Please upgrade your binutils or downgrade your gcc'; \ - false; \ - fi ; \ - fi - @if test "$(cc-name)" != "clang" \ - && test "$(cc-version)" -lt "0400" \ - && test "x${CONFIG_PPC64}" = "xy" ; then \ - echo -n "Sorry, GCC v4.0 or above is required to build " ; \ - echo "the 64-bit powerpc kernel." ; \ - false ; \ - fi - @if test "$(cc-name)" != "clang" \ - && test "$(cc-fullversion)" = "040200" \ - && test "x${CONFIG_MODULES}${CONFIG_PPC64}" = "xyy" ; then \ - echo -n '*** GCC-4.2.0 cannot compile the 64-bit powerpc ' ; \ - echo 'kernel with modules enabled.' ; \ - echo -n '*** Please use a different GCC version or ' ; \ - echo 'disable kernel modules' ; \ - false ; \ - fi @if test "x${CONFIG_CPU_LITTLE_ENDIAN}" = "xy" \ && $(LD) --version | head -1 | grep ' 2\.24$$' >/dev/null ; then \ echo -n '*** binutils 2.24 miscompiles weak symbols ' ; \ diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 0fb96c26136f..25e3184f11f7 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -55,6 +55,11 @@ BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -traditional -nostdinc BOOTARFLAGS := -cr$(KBUILD_ARFLAGS) +ifdef CONFIG_CC_IS_CLANG +BOOTCFLAGS += $(CLANG_FLAGS) +BOOTAFLAGS += $(CLANG_FLAGS) +endif + ifdef CONFIG_DEBUG_INFO BOOTCFLAGS += -g endif diff --git a/arch/powerpc/boot/addnote.c b/arch/powerpc/boot/addnote.c index 9d9f6f334d3c..3da3e2b1b51b 100644 --- a/arch/powerpc/boot/addnote.c +++ b/arch/powerpc/boot/addnote.c @@ -223,7 +223,11 @@ main(int ac, char **av) PUT_16(E_PHNUM, np + 2); /* write back */ - lseek(fd, (long) 0, SEEK_SET); + i = lseek(fd, (long) 0, SEEK_SET); + if (i < 0) { + perror("lseek"); + exit(1); + } i = write(fd, buf, n); if (i < 0) { perror("write"); diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S index 32dfe6d083f3..9b9d17437373 100644 --- a/arch/powerpc/boot/crt0.S +++ b/arch/powerpc/boot/crt0.S @@ -15,7 +15,7 @@ RELA = 7 RELACOUNT = 0x6ffffff9 - .text + .data /* A procedure descriptor used when booting this as a COFF file. * When making COFF, this comes first in the link and we're * linked at 0x500000. @@ -23,6 +23,8 @@ RELACOUNT = 0x6ffffff9 .globl _zimage_start_opd _zimage_start_opd: .long 0x500000, 0, 0, 0 + .text + b _zimage_start #ifdef __powerpc64__ .balign 8 diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index 6bd5e7261335..ffeaed63675b 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -195,6 +195,7 @@ CONFIG_UDF_FS=m CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m CONFIG_PROC_KCORE=y +CONFIG_HUGETLBFS=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y # CONFIG_MISC_FILESYSTEMS is not set diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 1f4691ce4126..e398173ae67d 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -38,7 +38,7 @@ extern struct static_key hcall_tracepoint_key; void __trace_hcall_entry(unsigned long opcode, unsigned long *args); void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf); /* OPAL tracing */ -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL extern struct static_key opal_tracepoint_key; #endif diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h index 50888388a359..02544939ef0b 100644 --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h @@ -35,6 +35,14 @@ static inline int hstate_get_psize(struct hstate *hstate) #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE static inline bool gigantic_page_supported(void) { + /* + * We used gigantic page reservation with hypervisor assist in some case. + * We cannot use runtime allocation of gigantic pages in those platforms + * This is hash translation mode LPARs. + */ + if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled()) + return false; + return true; } #endif diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 391ed2c3b697..f9019b579903 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -83,6 +83,9 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), pgtable_gfp_flags(mm, GFP_KERNEL)); + if (unlikely(!pgd)) + return pgd; + /* * Don't scan the PGD for pointers, it contains references to PUDs but * those references are not full pointers and so can't be recognised by diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 2a2486526d1f..855dbae6d351 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1234,21 +1234,13 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, #define pmd_move_must_withdraw pmd_move_must_withdraw struct spinlock; -static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, - struct spinlock *old_pmd_ptl, - struct vm_area_struct *vma) -{ - if (radix_enabled()) - return false; - /* - * Archs like ppc64 use pgtable to store per pmd - * specific information. So when we switch the pmd, - * we should also withdraw and deposit the pgtable - */ - return true; -} - - +extern int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl, + struct vm_area_struct *vma); +/* + * Hash translation mode use the deposited table to store hash pte + * slot information. + */ #define arch_needs_pgtable_deposit arch_needs_pgtable_deposit static inline bool arch_needs_pgtable_deposit(void) { diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h index 1e7a33592e29..15bc07a31c46 100644 --- a/arch/powerpc/include/asm/fadump.h +++ b/arch/powerpc/include/asm/fadump.h @@ -200,7 +200,7 @@ struct fad_crash_memory_ranges { unsigned long long size; }; -extern int is_fadump_boot_memory_area(u64 addr, ulong size); +extern int is_fadump_memory_area(u64 addr, ulong size); extern int early_init_dt_scan_fw_dump(unsigned long node, const char *uname, int depth, void *data); extern int fadump_reserve_mem(void); diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index 33b6f9c892c8..40a6c9261a6b 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -221,6 +221,17 @@ label##3: \ FTR_ENTRY_OFFSET 953b-954b; \ .popsection; +#define START_BTB_FLUSH_SECTION \ +955: \ + +#define END_BTB_FLUSH_SECTION \ +956: \ + .pushsection __btb_flush_fixup,"a"; \ + .align 2; \ +957: \ + FTR_ENTRY_OFFSET 955b-957b; \ + FTR_ENTRY_OFFSET 956b-957b; \ + .popsection; #ifndef __ASSEMBLY__ #include <linux/types.h> @@ -230,6 +241,7 @@ extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; +extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; void apply_feature_fixups(void); void setup_feature_keys(void); diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 906bcbdfd2a1..bccc5051249e 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -822,7 +822,7 @@ struct kvm_vcpu_arch { static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} -static inline void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) {} +static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_exit(void) {} diff --git a/arch/powerpc/include/asm/powernv.h b/arch/powerpc/include/asm/powernv.h index 2f3ff7a27881..d85fcfea32ca 100644 --- a/arch/powerpc/include/asm/powernv.h +++ b/arch/powerpc/include/asm/powernv.h @@ -23,6 +23,8 @@ extern int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea, unsigned long *flags, unsigned long *status, int count); +void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val); + void pnv_tm_init(void); #else static inline void powernv_set_nmmu_ptcr(unsigned long ptcr) { } diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 665af14850e4..2b7135391231 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -300,6 +300,7 @@ /* 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 @@ -307,6 +308,7 @@ #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/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index b5d023680801..5c901bf4c505 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -821,4 +821,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) stringify_in_c(.long (_target) - . ;) \ stringify_in_c(.previous) +#ifdef CONFIG_PPC_FSL_BOOK3E +#define BTB_FLUSH(reg) \ + lis reg,BUCSR_INIT@h; \ + ori reg,reg,BUCSR_INIT@l; \ + mtspr SPRN_BUCSR,reg; \ + isync; +#else +#define BTB_FLUSH(reg) +#endif /* CONFIG_PPC_FSL_BOOK3E */ + #endif /* _ASM_POWERPC_PPC_ASM_H */ diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index eb2a33d5df26..e382bd6ede84 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -41,7 +41,7 @@ #if defined(CONFIG_PPC_BOOK3E_64) #define MSR_64BIT MSR_CM -#define MSR_ (MSR_ME | MSR_CE) +#define MSR_ (MSR_ME | MSR_RI | MSR_CE) #define MSR_KERNEL (MSR_ | MSR_64BIT) #define MSR_USER32 (MSR_ | MSR_PR | MSR_EE) #define MSR_USER64 (MSR_USER32 | MSR_64BIT) diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 1fffbba8d6a5..65676e2325b8 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -67,6 +67,13 @@ void do_barrier_nospec_fixups_range(bool enable, void *start, void *end); static inline void do_barrier_nospec_fixups_range(bool enable, void *start, void *end) { }; #endif +#ifdef CONFIG_PPC_FSL_BOOK3E +void setup_spectre_v2(void); +#else +static inline void setup_spectre_v2(void) {}; +#endif +void do_btb_flush_fixups(void); + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_SETUP_H */ diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index ce316076bc52..64c3d1a720e2 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -83,18 +83,18 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src #define TIF_SIGPENDING 1 /* signal pending */ #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ #define TIF_FSCHECK 3 /* Check FS is USER_DS on return */ -#define TIF_NEED_RESCHED_LAZY 4 /* lazy rescheduling necessary */ #define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */ #define TIF_PATCH_PENDING 6 /* pending live patching update */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SINGLESTEP 8 /* singlestepping active */ #define TIF_NOHZ 9 /* in adaptive nohz mode */ #define TIF_SECCOMP 10 /* secure computing */ -#define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */ -#define TIF_NOERROR 12 /* Force successful syscall return */ + +#define TIF_NEED_RESCHED_LAZY 11 /* lazy rescheduling necessary */ +#define TIF_SYSCALL_TRACEPOINT 12 /* syscall tracepoint instrumentation */ + #define TIF_NOTIFY_RESUME 13 /* callback before returning to user */ #define TIF_UPROBE 14 /* breakpointed or single-stepping */ -#define TIF_SYSCALL_TRACEPOINT 15 /* syscall tracepoint instrumentation */ #define TIF_EMULATE_STACK_STORE 16 /* Is an instruction emulation for stack store? */ #define TIF_MEMDIE 17 /* is terminating due to OOM killer */ @@ -103,6 +103,9 @@ extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src #endif #define TIF_POLLING_NRFLAG 19 /* true if poll_idle() is polling TIF_NEED_RESCHED */ #define TIF_32BIT 20 /* 32 bit binary */ +#define TIF_RESTOREALL 21 /* Restore all regs (implies NOERROR) */ +#define TIF_NOERROR 22 /* Force successful syscall return */ + /* as above, but as bit values */ #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index a4a718dbfec6..f85e2b01c3df 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -132,6 +132,8 @@ static inline void shared_proc_topology_init(void) {} #define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) #define topology_core_id(cpu) (cpu_to_core_id(cpu)) + +int dlpar_cpu_readd(int cpu); #endif #endif diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index bac225bb7f64..23bea99bf8d5 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -63,7 +63,7 @@ static inline int __access_ok(unsigned long addr, unsigned long size, #endif #define access_ok(type, addr, size) \ - (__chk_user_ptr(addr), \ + (__chk_user_ptr(addr), (void)(type), \ __access_ok((__force unsigned long)(addr), (size), get_fs())) /* diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index 1afe90ade595..bbc06bd72b1f 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -82,10 +82,10 @@ struct vdso_data { __u32 icache_block_size; /* L1 i-cache block size */ __u32 dcache_log_block_size; /* L1 d-cache log block size */ __u32 icache_log_block_size; /* L1 i-cache log block size */ - __s32 wtom_clock_sec; /* Wall to monotonic clock */ - __s32 wtom_clock_nsec; - struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ - __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */ + __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */ + __s32 wtom_clock_nsec; /* Wall to monotonic clock nsec */ + __s64 wtom_clock_sec; /* Wall to monotonic clock sec */ + struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */ __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */ __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */ }; diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 3b66f2c19c84..eac18790d1b1 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -5,6 +5,9 @@ CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' +# Disable clang warning for using setjmp without setjmp.h header +CFLAGS_crash.o += $(call cc-disable-warning, builtin-requires-header) + subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror ifdef CONFIG_PPC64 @@ -22,10 +25,10 @@ CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code -CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_prom_init.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_btext.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_prom.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_cputable.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_prom_init.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_btext.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_prom.o = $(CC_FLAGS_FTRACE) endif obj-y := cputable.o ptrace.o syscalls.o \ diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 6c21f637075c..44bcf1585bd1 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -393,7 +393,9 @@ ret_from_syscall: MTMSRD(r10) lwz r9,TI_FLAGS(r12) li r8,-MAX_ERRNO - andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK) + lis r0,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)@h + ori r0,r0, (_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)@l + and. r0,r9,r0 bne- syscall_exit_work cmplw 0,r3,r8 blt+ syscall_exit_cont @@ -511,13 +513,13 @@ syscall_dotrace: b syscall_dotrace_cont syscall_exit_work: - andi. r0,r9,_TIF_RESTOREALL + andis. r0,r9,_TIF_RESTOREALL@h beq+ 0f REST_NVGPRS(r1) b 2f 0: cmplw 0,r3,r8 blt+ 1f - andi. r0,r9,_TIF_NOERROR + andis. r0,r9,_TIF_NOERROR@h bne- 1f lwz r11,_CCR(r1) /* Load CR */ neg r3,r3 @@ -526,12 +528,12 @@ syscall_exit_work: 1: stw r6,RESULT(r1) /* Save result */ stw r3,GPR3(r1) /* Update return value */ -2: andi. r0,r9,(_TIF_PERSYSCALL_MASK) +2: andis. r0,r9,(_TIF_PERSYSCALL_MASK)@h beq 4f /* Clear per-syscall TIF flags if any are set. */ - li r11,_TIF_PERSYSCALL_MASK + lis r11,_TIF_PERSYSCALL_MASK@h addi r12,r12,TI_FLAGS 3: lwarx r8,0,r12 andc r8,r8,r11 @@ -745,6 +747,9 @@ fast_exception_return: mtcr r10 lwz r10,_LINK(r11) mtlr r10 + /* Clear the exception_marker on the stack to avoid confusing stacktrace */ + li r10, 0 + stw r10, 8(r11) REST_GPR(10, r11) #if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS) mtspr SPRN_NRI, r0 @@ -989,6 +994,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) mtcrf 0xFF,r10 mtlr r11 + /* Clear the exception_marker on the stack to avoid confusing stacktrace */ + li r10, 0 + stw r10, 8(r1) /* * Once we put values in SRR0 and SRR1, we are in a state * where exceptions are not recoverable, since taking an @@ -1028,6 +1036,9 @@ exc_exit_restart_end: mtlr r11 lwz r10,_CCR(r1) mtcrf 0xff,r10 + /* Clear the exception_marker on the stack to avoid confusing stacktrace */ + li r10, 0 + stw r10, 8(r1) REST_2GPRS(9, r1) .globl exc_exit_restart exc_exit_restart: diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 970c3643789a..fe713d014220 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -80,6 +80,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM) std r0,GPR0(r1) std r10,GPR1(r1) beq 2f /* if from kernel mode */ +#ifdef CONFIG_PPC_FSL_BOOK3E +START_BTB_FLUSH_SECTION + BTB_FLUSH(r10) +END_BTB_FLUSH_SECTION +#endif ACCOUNT_CPU_USER_ENTRY(r13, r10, r11) 2: std r2,GPR2(r1) std r3,GPR3(r1) @@ -245,7 +250,9 @@ system_call_exit: ld r9,TI_FLAGS(r12) li r11,-MAX_ERRNO - andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK) + lis r0,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)@h + ori r0,r0,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)@l + and. r0,r9,r0 bne- .Lsyscall_exit_work andi. r0,r8,MSR_FP @@ -358,25 +365,25 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) /* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr. If TIF_NOERROR is set, just save r3 as it is. */ - andi. r0,r9,_TIF_RESTOREALL + andis. r0,r9,_TIF_RESTOREALL@h beq+ 0f REST_NVGPRS(r1) b 2f 0: cmpld r3,r11 /* r11 is -MAX_ERRNO */ blt+ 1f - andi. r0,r9,_TIF_NOERROR + andis. r0,r9,_TIF_NOERROR@h bne- 1f ld r5,_CCR(r1) neg r3,r3 oris r5,r5,0x1000 /* Set SO bit in CR */ std r5,_CCR(r1) 1: std r3,GPR3(r1) -2: andi. r0,r9,(_TIF_PERSYSCALL_MASK) +2: andis. r0,r9,(_TIF_PERSYSCALL_MASK)@h beq 4f /* Clear per-syscall TIF flags if any are set. */ - li r11,_TIF_PERSYSCALL_MASK + lis r11,(_TIF_PERSYSCALL_MASK)@h addi r12,r12,TI_FLAGS 3: ldarx r10,0,r12 andc r10,r10,r11 @@ -997,6 +1004,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r2,_NIP(r1) mtspr SPRN_SRR0,r2 + /* + * Leaving a stale exception_marker on the stack can confuse + * the reliable stack unwinder later on. Clear it. + */ + li r2,0 + std r2,STACK_FRAME_OVERHEAD-16(r1) + ld r0,GPR0(r1) ld r2,GPR2(r1) ld r3,GPR3(r1) diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 6d6e144a28ce..447defdd4503 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -296,7 +296,8 @@ ret_from_mc_except: andi. r10,r11,MSR_PR; /* save stack pointer */ \ beq 1f; /* branch around if supervisor */ \ ld r1,PACAKSAVE(r13); /* get kernel stack coming from usr */\ -1: cmpdi cr1,r1,0; /* check if SP makes sense */ \ +1: type##_BTB_FLUSH \ + cmpdi cr1,r1,0; /* check if SP makes sense */ \ bge- cr1,exc_##n##_bad_stack;/* bad stack (TODO: out of line) */ \ mfspr r10,SPRN_##type##_SRR0; /* read SRR0 before touching stack */ @@ -328,6 +329,30 @@ ret_from_mc_except: #define SPRN_MC_SRR0 SPRN_MCSRR0 #define SPRN_MC_SRR1 SPRN_MCSRR1 +#ifdef CONFIG_PPC_FSL_BOOK3E +#define GEN_BTB_FLUSH \ + START_BTB_FLUSH_SECTION \ + beq 1f; \ + BTB_FLUSH(r10) \ + 1: \ + END_BTB_FLUSH_SECTION + +#define CRIT_BTB_FLUSH \ + START_BTB_FLUSH_SECTION \ + BTB_FLUSH(r10) \ + END_BTB_FLUSH_SECTION + +#define DBG_BTB_FLUSH CRIT_BTB_FLUSH +#define MC_BTB_FLUSH CRIT_BTB_FLUSH +#define GDBELL_BTB_FLUSH GEN_BTB_FLUSH +#else +#define GEN_BTB_FLUSH +#define CRIT_BTB_FLUSH +#define DBG_BTB_FLUSH +#define MC_BTB_FLUSH +#define GDBELL_BTB_FLUSH +#endif + #define NORMAL_EXCEPTION_PROLOG(n, intnum, addition) \ EXCEPTION_PROLOG(n, intnum, GEN, addition##_GEN(n)) diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index a711d22339ea..c02c95287a5f 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -118,13 +118,19 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, /* * If fadump is registered, check if the memory provided - * falls within boot memory area. + * falls within boot memory area and reserved memory area. */ -int is_fadump_boot_memory_area(u64 addr, ulong size) +int is_fadump_memory_area(u64 addr, ulong size) { + u64 d_start = fw_dump.reserve_dump_area_start; + u64 d_end = d_start + fw_dump.reserve_dump_area_size; + if (!fw_dump.dump_registered) return 0; + if (((addr + size) > d_start) && (addr <= d_end)) + return 1; + return (addr + size) > RMA_START && addr <= fw_dump.boot_memory_size; } diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 4898e9491a1c..9168a247e24f 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -970,7 +970,9 @@ start_here_multiplatform: /* Restore parameters passed from prom_init/kexec */ mr r3,r31 - bl early_setup /* also sets r13 and SPRG_PACA */ + LOAD_REG_ADDR(r12, DOTSYM(early_setup)) + mtctr r12 + bctrl /* also sets r13 and SPRG_PACA */ LOAD_REG_ADDR(r3, start_here_common) ld r4,PACAKMSR(r13) diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 81d4574d1f37..9fd2ff28b8ff 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -919,11 +919,12 @@ start_here: /* set up the PTE pointers for the Abatron bdiGDB. */ - tovirt(r6,r6) lis r5, abatron_pteptrs@h ori r5, r5, abatron_pteptrs@l stw r5, 0xf0(0) /* Must match your Abatron config file */ tophys(r5,r5) + lis r6, swapper_pg_dir@h + ori r6, r6, swapper_pg_dir@l stw r6, 0(r5) /* Now turn on the MMU for real! */ diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index d0862a100d29..306e26c073a0 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -32,6 +32,16 @@ */ #define THREAD_NORMSAVE(offset) (THREAD_NORMSAVES + (offset * 4)) +#ifdef CONFIG_PPC_FSL_BOOK3E +#define BOOKE_CLEAR_BTB(reg) \ +START_BTB_FLUSH_SECTION \ + BTB_FLUSH(reg) \ +END_BTB_FLUSH_SECTION +#else +#define BOOKE_CLEAR_BTB(reg) +#endif + + #define NORMAL_EXCEPTION_PROLOG(intno) \ mtspr SPRN_SPRG_WSCRATCH0, r10; /* save one register */ \ mfspr r10, SPRN_SPRG_THREAD; \ @@ -43,6 +53,7 @@ andi. r11, r11, MSR_PR; /* check whether user or kernel */\ mr r11, r1; \ beq 1f; \ + BOOKE_CLEAR_BTB(r11) \ /* if from user, start at top of this thread's kernel stack */ \ lwz r11, THREAD_INFO-THREAD(r10); \ ALLOC_STACK_FRAME(r11, THREAD_SIZE); \ @@ -128,6 +139,7 @@ stw r9,_CCR(r8); /* save CR on stack */\ mfspr r11,exc_level_srr1; /* check whether user or kernel */\ DO_KVM BOOKE_INTERRUPT_##intno exc_level_srr1; \ + BOOKE_CLEAR_BTB(r10) \ andi. r11,r11,MSR_PR; \ mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\ lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\ diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index e2750b856c8f..2386ce2a9c6e 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -453,6 +453,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mfcr r13 stw r13, THREAD_NORMSAVE(3)(r10) DO_KVM BOOKE_INTERRUPT_DTLB_MISS SPRN_SRR1 +START_BTB_FLUSH_SECTION + mfspr r11, SPRN_SRR1 + andi. r10,r11,MSR_PR + beq 1f + BTB_FLUSH(r10) +1: +END_BTB_FLUSH_SECTION mfspr r10, SPRN_DEAR /* Get faulting address */ /* If we are faulting a kernel address, we have to use the @@ -547,6 +554,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mfcr r13 stw r13, THREAD_NORMSAVE(3)(r10) DO_KVM BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR1 +START_BTB_FLUSH_SECTION + mfspr r11, SPRN_SRR1 + andi. r10,r11,MSR_PR + beq 1f + BTB_FLUSH(r10) +1: +END_BTB_FLUSH_SECTION + mfspr r10, SPRN_SRR0 /* Get faulting address */ /* If we are faulting a kernel address, we have to use the diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 7f5ac2e8581b..36178000a2f2 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -170,6 +170,9 @@ core_idle_lock_held: bne- core_idle_lock_held blr +/* Reuse an unused pt_regs slot for IAMR */ +#define PNV_POWERSAVE_IAMR _DAR + /* * Pass requested state in r3: * r3 - PNV_THREAD_NAP/SLEEP/WINKLE in POWER8 @@ -200,6 +203,12 @@ pnv_powersave_common: /* Continue saving state */ SAVE_GPR(2, r1) SAVE_NVGPRS(r1) + +BEGIN_FTR_SECTION + mfspr r5, SPRN_IAMR + std r5, PNV_POWERSAVE_IAMR(r1) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) + mfcr r5 std r5,_CCR(r1) std r1,PACAR1(r13) @@ -924,6 +933,17 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) REST_NVGPRS(r1) REST_GPR(2, r1) + +BEGIN_FTR_SECTION + /* IAMR was saved in pnv_powersave_common() */ + ld r5, PNV_POWERSAVE_IAMR(r1) + mtspr SPRN_IAMR, r5 + /* + * We don't need an isync here because the upcoming mtmsrd is + * execution synchronizing. + */ +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) + ld r4,PACAKMSR(r13) ld r5,_LINK(r1) ld r6,_CCR(r1) diff --git a/arch/powerpc/kernel/jump_label.c b/arch/powerpc/kernel/jump_label.c index 6472472093d0..0080c5fbd225 100644 --- a/arch/powerpc/kernel/jump_label.c +++ b/arch/powerpc/kernel/jump_label.c @@ -11,7 +11,6 @@ #include <linux/jump_label.h> #include <asm/code-patching.h> -#ifdef HAVE_JUMP_LABEL void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type) { @@ -22,4 +21,3 @@ void arch_jump_label_transform(struct jump_entry *entry, else patch_instruction(addr, PPC_INST_NOP); } -#endif 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/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 33b34a58fc62..5b9dce17f0c9 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -372,6 +372,8 @@ void __init find_legacy_serial_ports(void) /* Now find out if one of these is out firmware console */ path = of_get_property(of_chosen, "linux,stdout-path", NULL); + if (path == NULL) + path = of_get_property(of_chosen, "stdout-path", NULL); if (path != NULL) { stdout = of_find_node_by_path(path); if (stdout) @@ -595,8 +597,10 @@ static int __init check_legacy_serial_console(void) /* We are getting a weird phandle from OF ... */ /* ... So use the full path instead */ name = of_get_property(of_chosen, "linux,stdout-path", NULL); + if (name == NULL) + name = of_get_property(of_chosen, "stdout-path", NULL); if (name == NULL) { - DBG(" no linux,stdout-path !\n"); + DBG(" no stdout-path !\n"); return -ENODEV; } prom_stdout = of_find_node_by_path(name); diff --git a/arch/powerpc/kernel/msi.c b/arch/powerpc/kernel/msi.c index dab616a33b8d..f2197654be07 100644 --- a/arch/powerpc/kernel/msi.c +++ b/arch/powerpc/kernel/msi.c @@ -34,5 +34,10 @@ void arch_teardown_msi_irqs(struct pci_dev *dev) { struct pci_controller *phb = pci_bus_to_host(dev->bus); - phb->controller_ops.teardown_msi_irqs(dev); + /* + * We can be called even when arch_setup_msi_irqs() returns -ENOSYS, + * so check the pointer again. + */ + if (phb->controller_ops.teardown_msi_irqs) + phb->controller_ops.teardown_msi_irqs(dev); } diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 22e9d281324d..e7d4ce6964ae 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -563,8 +563,6 @@ static int nvram_pstore_init(void) nvram_pstore_info.buf = oops_data; nvram_pstore_info.bufsize = oops_data_sz; - spin_lock_init(&nvram_pstore_info.buf_lock); - rc = pstore_register(&nvram_pstore_info); if (rc && (rc != -EPERM)) /* Print error only when pstore.backend == nvram */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index bb6ac471a784..d29f2dca725b 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -180,7 +180,7 @@ static void __giveup_fpu(struct task_struct *tsk) save_fpu(tsk); msr = tsk->thread.regs->msr; - msr &= ~MSR_FP; + msr &= ~(MSR_FP|MSR_FE0|MSR_FE1); #ifdef CONFIG_VSX if (cpu_has_feature(CPU_FTR_VSX)) msr &= ~MSR_VSX; diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 9667666eb18e..e08b32ccf1d9 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -561,6 +561,7 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, /* * Copy out only the low-order word of vrsave. */ + int start, end; union { elf_vrreg_t reg; u32 word; @@ -569,8 +570,10 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset, vrsave.word = target->thread.vrsave; + start = 33 * sizeof(vector128); + end = start + sizeof(vrsave); ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave, - 33 * sizeof(vector128), -1); + start, end); } return ret; @@ -608,6 +611,7 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset, /* * We use only the first word of vrsave. */ + int start, end; union { elf_vrreg_t reg; u32 word; @@ -616,8 +620,10 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset, vrsave.word = target->thread.vrsave; + start = 33 * sizeof(vector128); + end = start + sizeof(vrsave); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave, - 33 * sizeof(vector128), -1); + start, end); if (!ret) target->thread.vrsave = vrsave.word; } diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 44d66c33d59d..23b88b923f06 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -274,27 +274,16 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal) } #ifdef CONFIG_PPC_PSERIES -static s32 prrn_update_scope; - -static void prrn_work_fn(struct work_struct *work) +static void handle_prrn_event(s32 scope) { /* * For PRRN, we must pass the negative of the scope value in * the RTAS event. */ - pseries_devicetree_update(-prrn_update_scope); + pseries_devicetree_update(-scope); numa_update_cpu_topology(false); } -static DECLARE_WORK(prrn_work, prrn_work_fn); - -static void prrn_schedule_update(u32 scope) -{ - flush_work(&prrn_work); - prrn_update_scope = scope; - schedule_work(&prrn_work); -} - static void handle_rtas_event(const struct rtas_error_log *log) { if (rtas_error_type(log) != RTAS_TYPE_PRRN || !prrn_is_enabled()) @@ -303,7 +292,7 @@ static void handle_rtas_event(const struct rtas_error_log *log) /* For PRRN Events the extended log length is used to denote * the scope for calling rtas update-nodes. */ - prrn_schedule_update(rtas_error_extended_log_length(log)); + handle_prrn_event(rtas_error_extended_log_length(log)); } #else diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index f6f469fc4073..70568ccbd9fd 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -4,6 +4,7 @@ // // Copyright 2018, Michael Ellerman, IBM Corporation. +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/device.h> #include <linux/seq_buf.h> @@ -22,10 +23,14 @@ enum count_cache_flush_type { COUNT_CACHE_FLUSH_SW = 0x2, COUNT_CACHE_FLUSH_HW = 0x4, }; -static enum count_cache_flush_type count_cache_flush_type; +static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; bool barrier_nospec_enabled; static bool no_nospec; +static bool btb_flush_enabled; +#ifdef CONFIG_PPC_FSL_BOOK3E +static bool no_spectrev2; +#endif static void enable_barrier_nospec(bool enable) { @@ -52,7 +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); } @@ -101,6 +106,23 @@ static __init int barrier_nospec_debugfs_init(void) device_initcall(barrier_nospec_debugfs_init); #endif /* CONFIG_DEBUG_FS */ +#ifdef CONFIG_PPC_FSL_BOOK3E +static int __init handle_nospectre_v2(char *p) +{ + no_spectrev2 = true; + + return 0; +} +early_param("nospectre_v2", handle_nospectre_v2); +void setup_spectre_v2(void) +{ + if (no_spectrev2 || cpu_mitigations_off()) + do_btb_flush_fixups(); + else + btb_flush_enabled = true; +} +#endif /* CONFIG_PPC_FSL_BOOK3E */ + #ifdef CONFIG_PPC_BOOK3S_64 ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { @@ -168,31 +190,27 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c bcs = security_ftr_enabled(SEC_FTR_BCCTRL_SERIALISED); ccd = security_ftr_enabled(SEC_FTR_COUNT_CACHE_DISABLED); - if (bcs || ccd || count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) { - bool comma = false; + if (bcs || ccd) { seq_buf_printf(&s, "Mitigation: "); - if (bcs) { + if (bcs) seq_buf_printf(&s, "Indirect branch serialisation (kernel only)"); - comma = true; - } - - if (ccd) { - if (comma) - seq_buf_printf(&s, ", "); - seq_buf_printf(&s, "Indirect branch cache disabled"); - comma = true; - } - if (comma) + if (bcs && ccd) seq_buf_printf(&s, ", "); - seq_buf_printf(&s, "Software count cache flush"); + if (ccd) + seq_buf_printf(&s, "Indirect branch cache disabled"); + } else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) { + seq_buf_printf(&s, "Mitigation: Software count cache flush"); if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW) - seq_buf_printf(&s, "(hardware accelerated)"); - } else + seq_buf_printf(&s, " (hardware accelerated)"); + } else if (btb_flush_enabled) { + seq_buf_printf(&s, "Mitigation: Branch predictor state flush"); + } else { seq_buf_printf(&s, "Vulnerable"); + } seq_buf_printf(&s, "\n"); @@ -282,7 +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-common.c b/arch/powerpc/kernel/setup-common.c index 93fa0c99681e..508244bcf19c 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -973,6 +973,7 @@ void __init setup_arch(char **cmdline_p) ppc_md.setup_arch(); setup_barrier_nospec(); + setup_spectre_v2(); paging_init(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index faf00222b324..eaf7300be5ab 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -955,7 +955,7 @@ 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/signal_32.c b/arch/powerpc/kernel/signal_32.c index e6474a45cef5..fd59fef9931b 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -848,7 +848,23 @@ static long restore_tm_user_regs(struct pt_regs *regs, /* If TM bits are set to the reserved value, it's an invalid context */ if (MSR_TM_RESV(msr_hi)) return 1; - /* Pull in the MSR TM bits from the user context */ + + /* + * Disabling preemption, since it is unsafe to be preempted + * with MSR[TS] set without recheckpointing. + */ + preempt_disable(); + + /* + * CAUTION: + * After regs->MSR[TS] being updated, make sure that get_user(), + * put_user() or similar functions are *not* called. These + * functions can generate page faults which will cause the process + * to be de-scheduled with MSR[TS] set but without calling + * tm_recheckpoint(). This can cause a bug. + * + * Pull in the MSR TM bits from the user context + */ regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr_hi & MSR_TS_MASK); /* Now, recheckpoint. This loads up all of the checkpointed (older) * registers, including FP and V[S]Rs. After recheckpointing, the @@ -873,6 +889,8 @@ static long restore_tm_user_regs(struct pt_regs *regs, } #endif + preempt_enable(); + return 0; } #endif diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 83d51bf586c7..14b0f5b6a373 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -467,20 +467,6 @@ static long restore_tm_sigcontexts(struct task_struct *tsk, if (MSR_TM_RESV(msr)) return -EINVAL; - /* pull in MSR TS bits from user context */ - regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK); - - /* - * Ensure that TM is enabled in regs->msr before we leave the signal - * handler. It could be the case that (a) user disabled the TM bit - * through the manipulation of the MSR bits in uc_mcontext or (b) the - * TM bit was disabled because a sufficient number of context switches - * happened whilst in the signal handler and load_tm overflowed, - * disabling the TM bit. In either case we can end up with an illegal - * TM state leading to a TM Bad Thing when we return to userspace. - */ - regs->msr |= MSR_TM; - /* pull in MSR LE from user context */ regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE); @@ -572,6 +558,34 @@ static long restore_tm_sigcontexts(struct task_struct *tsk, tm_enable(); /* Make sure the transaction is marked as failed */ tsk->thread.tm_texasr |= TEXASR_FS; + + /* + * Disabling preemption, since it is unsafe to be preempted + * with MSR[TS] set without recheckpointing. + */ + preempt_disable(); + + /* pull in MSR TS bits from user context */ + regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK); + + /* + * Ensure that TM is enabled in regs->msr before we leave the signal + * handler. It could be the case that (a) user disabled the TM bit + * through the manipulation of the MSR bits in uc_mcontext or (b) the + * TM bit was disabled because a sufficient number of context switches + * happened whilst in the signal handler and load_tm overflowed, + * disabling the TM bit. In either case we can end up with an illegal + * TM state leading to a TM Bad Thing when we return to userspace. + * + * CAUTION: + * After regs->MSR[TS] being updated, make sure that get_user(), + * put_user() or similar functions are *not* called. These + * functions can generate page faults which will cause the process + * to be de-scheduled with MSR[TS] set but without calling + * tm_recheckpoint(). This can cause a bug. + */ + regs->msr |= MSR_TM; + /* This loads the checkpointed FP/VEC state, if used */ tm_recheckpoint(&tsk->thread); @@ -585,6 +599,8 @@ static long restore_tm_sigcontexts(struct task_struct *tsk, regs->msr |= MSR_VEC; } + preempt_enable(); + return err; } #endif @@ -739,12 +755,25 @@ SYSCALL_DEFINE0(rt_sigreturn) if (restore_tm_sigcontexts(current, &uc->uc_mcontext, &uc_transact->uc_mcontext)) goto badframe; - } - else - /* Fall through, for non-TM restore */ + } else #endif - if (restore_sigcontext(current, NULL, 1, &uc->uc_mcontext)) - goto badframe; + { + /* + * Fall through, for non-TM restore + * + * Unset MSR[TS] on the thread regs since MSR from user + * context does not have MSR active, and recheckpoint was + * not called since restore_tm_sigcontexts() was not called + * also. + * + * If not unsetting it, the code can RFID to userspace with + * MSR[TS] set, but without CPU in the proper state, + * causing a TM bad thing. + */ + current->thread.regs->msr &= ~MSR_TS_MASK; + if (restore_sigcontext(current, NULL, 1, &uc->uc_mcontext)) + goto badframe; + } if (restore_altstack(&uc->uc_stack)) goto badframe; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 61c1fadbc644..6dc43205382b 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -338,13 +338,12 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask) * NMI IPIs may not be recoverable, so should not be used as ongoing part of * a running system. They can be used for crash, debug, halt/reboot, etc. * - * NMI IPIs are globally single threaded. No more than one in progress at - * any time. - * * The IPI call waits with interrupts disabled until all targets enter the - * NMI handler, then the call returns. + * NMI handler, then returns. Subsequent IPIs can be issued before targets + * have returned from their handlers, so there is no guarantee about + * concurrency or re-entrancy. * - * No new NMI can be initiated until targets exit the handler. + * A new NMI can be issued before all targets exit the handler. * * The IPI call may time out without all targets entering the NMI handler. * In that case, there is some logic to recover (and ignore subsequent @@ -355,7 +354,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask) static atomic_t __nmi_ipi_lock = ATOMIC_INIT(0); static struct cpumask nmi_ipi_pending_mask; -static int nmi_ipi_busy_count = 0; +static bool nmi_ipi_busy = false; static void (*nmi_ipi_function)(struct pt_regs *) = NULL; static void nmi_ipi_lock_start(unsigned long *flags) @@ -394,7 +393,7 @@ static void nmi_ipi_unlock_end(unsigned long *flags) */ int smp_handle_nmi_ipi(struct pt_regs *regs) { - void (*fn)(struct pt_regs *); + void (*fn)(struct pt_regs *) = NULL; unsigned long flags; int me = raw_smp_processor_id(); int ret = 0; @@ -405,29 +404,17 @@ int smp_handle_nmi_ipi(struct pt_regs *regs) * because the caller may have timed out. */ nmi_ipi_lock_start(&flags); - if (!nmi_ipi_busy_count) - goto out; - if (!cpumask_test_cpu(me, &nmi_ipi_pending_mask)) - goto out; - - fn = nmi_ipi_function; - if (!fn) - goto out; - - cpumask_clear_cpu(me, &nmi_ipi_pending_mask); - nmi_ipi_busy_count++; - nmi_ipi_unlock(); - - ret = 1; - - fn(regs); - - nmi_ipi_lock(); - if (nmi_ipi_busy_count > 1) /* Can race with caller time-out */ - nmi_ipi_busy_count--; -out: + if (cpumask_test_cpu(me, &nmi_ipi_pending_mask)) { + cpumask_clear_cpu(me, &nmi_ipi_pending_mask); + fn = READ_ONCE(nmi_ipi_function); + WARN_ON_ONCE(!fn); + ret = 1; + } nmi_ipi_unlock_end(&flags); + if (fn) + fn(regs); + return ret; } @@ -453,7 +440,7 @@ static void do_smp_send_nmi_ipi(int cpu, bool safe) * - cpu is the target CPU (must not be this CPU), or NMI_IPI_ALL_OTHERS. * - fn is the target callback function. * - delay_us > 0 is the delay before giving up waiting for targets to - * complete executing the handler, == 0 specifies indefinite delay. + * begin executing the handler, == 0 specifies indefinite delay. */ int __smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us, bool safe) { @@ -467,31 +454,33 @@ int __smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us, bool if (unlikely(!smp_ops)) return 0; - /* Take the nmi_ipi_busy count/lock with interrupts hard disabled */ nmi_ipi_lock_start(&flags); - while (nmi_ipi_busy_count) { + while (nmi_ipi_busy) { nmi_ipi_unlock_end(&flags); - spin_until_cond(nmi_ipi_busy_count == 0); + spin_until_cond(!nmi_ipi_busy); nmi_ipi_lock_start(&flags); } - + nmi_ipi_busy = true; nmi_ipi_function = fn; + WARN_ON_ONCE(!cpumask_empty(&nmi_ipi_pending_mask)); + if (cpu < 0) { /* ALL_OTHERS */ cpumask_copy(&nmi_ipi_pending_mask, cpu_online_mask); cpumask_clear_cpu(me, &nmi_ipi_pending_mask); } else { - /* cpumask starts clear */ cpumask_set_cpu(cpu, &nmi_ipi_pending_mask); } - nmi_ipi_busy_count++; + nmi_ipi_unlock(); + /* Interrupts remain hard disabled */ + do_smp_send_nmi_ipi(cpu, safe); nmi_ipi_lock(); - /* nmi_ipi_busy_count is held here, so unlock/lock is okay */ + /* nmi_ipi_busy is set here, so unlock/lock is okay */ while (!cpumask_empty(&nmi_ipi_pending_mask)) { nmi_ipi_unlock(); udelay(1); @@ -503,29 +492,15 @@ int __smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us, bool } } - while (nmi_ipi_busy_count > 1) { - nmi_ipi_unlock(); - udelay(1); - nmi_ipi_lock(); - if (delay_us) { - delay_us--; - if (!delay_us) - break; - } - } - if (!cpumask_empty(&nmi_ipi_pending_mask)) { /* Timeout waiting for CPUs to call smp_handle_nmi_ipi */ ret = 0; cpumask_clear(&nmi_ipi_pending_mask); } - if (nmi_ipi_busy_count > 1) { - /* Timeout waiting for CPUs to execute fn */ - ret = 0; - nmi_ipi_busy_count = 1; - } - nmi_ipi_busy_count--; + nmi_ipi_function = NULL; + nmi_ipi_busy = false; + nmi_ipi_unlock_end(&flags); return ret; @@ -593,17 +568,8 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) static void nmi_stop_this_cpu(struct pt_regs *regs) { /* - * This is a special case because it never returns, so the NMI IPI - * handling would never mark it as done, which makes any later - * smp_send_nmi_ipi() call spin forever. Mark it done now. - * * IRQs are already hard disabled by the smp_handle_nmi_ipi. */ - nmi_ipi_lock(); - if (nmi_ipi_busy_count > 1) - nmi_ipi_busy_count--; - nmi_ipi_unlock(); - spin_begin(); while (1) spin_cpu_relax(); diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile index d22d8bafb643..d868ba42032f 100644 --- a/arch/powerpc/kernel/trace/Makefile +++ b/arch/powerpc/kernel/trace/Makefile @@ -7,7 +7,7 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror ifdef CONFIG_FUNCTION_TRACER # do not trace tracer code -CFLAGS_REMOVE_ftrace.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) endif obj32-$(CONFIG_FUNCTION_TRACER) += ftrace_32.o diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 8689a02b7df8..02fe6d020174 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -767,15 +767,15 @@ void machine_check_exception(struct pt_regs *regs) if (check_io_access(regs)) goto bail; - /* Must die if the interrupt is not recoverable */ - if (!(regs->msr & MSR_RI)) - nmi_panic(regs, "Unrecoverable Machine check"); - if (!nested) nmi_exit(); die("Machine check", regs, SIGBUS); + /* Must die if the interrupt is not recoverable */ + if (!(regs->msr & MSR_RI)) + nmi_panic(regs, "Unrecoverable Machine check"); + return; bail: @@ -1545,8 +1545,8 @@ bail: void StackOverflow(struct pt_regs *regs) { - printk(KERN_CRIT "Kernel stack overflow in process %p, r1=%lx\n", - current, regs->gpr[1]); + pr_crit("Kernel stack overflow in process %s[%d], r1=%lx\n", + current->comm, task_pid_nr(current), regs->gpr[1]); debugger(regs); show_regs(regs); panic("kernel stack overflow"); diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 769c2624e0a6..75cff3f336b3 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/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S index c002adcc694c..afbad2ac3147 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -92,7 +92,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) * At this point, r4,r5 contain our sec/nsec values. */ - lwa r6,WTOM_CLOCK_SEC(r3) + ld r6,WTOM_CLOCK_SEC(r3) lwa r9,WTOM_CLOCK_NSEC(r3) /* We now have our result in r6,r9. We create a fake dependency @@ -125,7 +125,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) bne cr6,75f /* CLOCK_MONOTONIC_COARSE */ - lwa r6,WTOM_CLOCK_SEC(r3) + ld r6,WTOM_CLOCK_SEC(r3) lwa r9,WTOM_CLOCK_NSEC(r3) /* check if counter has updated */ diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 07ae018e550e..fd35eddf3266 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -164,6 +164,14 @@ SECTIONS } #endif /* CONFIG_PPC_BARRIER_NOSPEC */ +#ifdef CONFIG_PPC_FSL_BOOK3E + . = ALIGN(8); + __spec_btb_flush_fixup : AT(ADDR(__spec_btb_flush_fixup) - LOAD_OFFSET) { + __start__btb_flush_fixup = .; + *(__btb_flush_fixup) + __stop__btb_flush_fixup = .; + } +#endif EXCEPTION_TABLE(0) NOTES :kernel :notes @@ -296,6 +304,10 @@ SECTIONS #ifdef CONFIG_PPC32 .data : AT(ADDR(.data) - LOAD_OFFSET) { DATA_DATA +#ifdef CONFIG_UBSAN + *(.data..Lubsan_data*) + *(.data..Lubsan_type*) +#endif *(.data.rel*) *(SDATA_MAIN) *(.sdata2) diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index 3c6ab22a0c4e..af3c15a1d41e 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -77,7 +77,7 @@ static u64 wd_smp_panic_timeout_tb __read_mostly; /* panic other CPUs */ static u64 wd_timer_period_ms __read_mostly; /* interval between heartbeat */ -static DEFINE_PER_CPU(struct timer_list, wd_timer); +static DEFINE_PER_CPU(struct hrtimer, wd_hrtimer); static DEFINE_PER_CPU(u64, wd_timer_tb); /* SMP checker bits */ @@ -293,21 +293,21 @@ out: nmi_exit(); } -static void wd_timer_reset(unsigned int cpu, struct timer_list *t) -{ - t->expires = jiffies + msecs_to_jiffies(wd_timer_period_ms); - if (wd_timer_period_ms > 1000) - t->expires = __round_jiffies_up(t->expires, cpu); - add_timer_on(t, cpu); -} - -static void wd_timer_fn(struct timer_list *t) +static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { int cpu = smp_processor_id(); + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + return HRTIMER_NORESTART; + + if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) + return HRTIMER_NORESTART; + watchdog_timer_interrupt(cpu); - wd_timer_reset(cpu, t); + hrtimer_forward_now(hrtimer, ms_to_ktime(wd_timer_period_ms)); + + return HRTIMER_RESTART; } void arch_touch_nmi_watchdog(void) @@ -323,37 +323,22 @@ void arch_touch_nmi_watchdog(void) } EXPORT_SYMBOL(arch_touch_nmi_watchdog); -static void start_watchdog_timer_on(unsigned int cpu) -{ - struct timer_list *t = per_cpu_ptr(&wd_timer, cpu); - - per_cpu(wd_timer_tb, cpu) = get_tb(); - - timer_setup(t, wd_timer_fn, TIMER_PINNED); - wd_timer_reset(cpu, t); -} - -static void stop_watchdog_timer_on(unsigned int cpu) -{ - struct timer_list *t = per_cpu_ptr(&wd_timer, cpu); - - del_timer_sync(t); -} - -static int start_wd_on_cpu(unsigned int cpu) +static void start_watchdog(void *arg) { + struct hrtimer *hrtimer = this_cpu_ptr(&wd_hrtimer); + int cpu = smp_processor_id(); unsigned long flags; if (cpumask_test_cpu(cpu, &wd_cpus_enabled)) { WARN_ON(1); - return 0; + return; } if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - return 0; + return; if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) - return 0; + return; wd_smp_lock(&flags); cpumask_set_cpu(cpu, &wd_cpus_enabled); @@ -363,27 +348,40 @@ static int start_wd_on_cpu(unsigned int cpu) } wd_smp_unlock(&flags); - start_watchdog_timer_on(cpu); + *this_cpu_ptr(&wd_timer_tb) = get_tb(); - return 0; + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = watchdog_timer_fn; + hrtimer_start(hrtimer, ms_to_ktime(wd_timer_period_ms), + HRTIMER_MODE_REL_PINNED); } -static int stop_wd_on_cpu(unsigned int cpu) +static int start_watchdog_on_cpu(unsigned int cpu) { + return smp_call_function_single(cpu, start_watchdog, NULL, true); +} + +static void stop_watchdog(void *arg) +{ + struct hrtimer *hrtimer = this_cpu_ptr(&wd_hrtimer); + int cpu = smp_processor_id(); unsigned long flags; if (!cpumask_test_cpu(cpu, &wd_cpus_enabled)) - return 0; /* Can happen in CPU unplug case */ + return; /* Can happen in CPU unplug case */ - stop_watchdog_timer_on(cpu); + hrtimer_cancel(hrtimer); wd_smp_lock(&flags); cpumask_clear_cpu(cpu, &wd_cpus_enabled); wd_smp_unlock(&flags); wd_smp_clear_cpu_pending(cpu, get_tb()); +} - return 0; +static int stop_watchdog_on_cpu(unsigned int cpu) +{ + return smp_call_function_single(cpu, stop_watchdog, NULL, true); } static void watchdog_calc_timeouts(void) @@ -402,7 +400,7 @@ void watchdog_nmi_stop(void) int cpu; for_each_cpu(cpu, &wd_cpus_enabled) - stop_wd_on_cpu(cpu); + stop_watchdog_on_cpu(cpu); } void watchdog_nmi_start(void) @@ -411,7 +409,7 @@ void watchdog_nmi_start(void) watchdog_calc_timeouts(); for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask) - start_wd_on_cpu(cpu); + start_watchdog_on_cpu(cpu); } /* @@ -423,7 +421,8 @@ int __init watchdog_nmi_probe(void) err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "powerpc/watchdog:online", - start_wd_on_cpu, stop_wd_on_cpu); + start_watchdog_on_cpu, + stop_watchdog_on_cpu); if (err < 0) { pr_warn("could not be initialized"); return err; diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 30c2eb766954..aae34f218ab4 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1723,7 +1723,6 @@ static void kvmppc_xive_cleanup_irq(u32 hw_num, struct xive_irq_data *xd) { xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_01); xive_native_configure_irq(hw_num, 0, MASKED, 0); - xive_cleanup_irq_data(xd); } static void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb) @@ -1737,9 +1736,10 @@ static void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb) continue; kvmppc_xive_cleanup_irq(state->ipi_number, &state->ipi_data); + xive_cleanup_irq_data(&state->ipi_data); xive_native_free_irq(state->ipi_number); - /* Pass-through, cleanup too */ + /* Pass-through, cleanup too but keep IRQ hw data */ if (state->pt_number) kvmppc_xive_cleanup_irq(state->pt_number, state->pt_data); diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S index 81bd8a07aa51..612b7f6a887f 100644 --- a/arch/powerpc/kvm/bookehv_interrupts.S +++ b/arch/powerpc/kvm/bookehv_interrupts.S @@ -75,6 +75,10 @@ PPC_LL r1, VCPU_HOST_STACK(r4) PPC_LL r2, HOST_R2(r1) +START_BTB_FLUSH_SECTION + BTB_FLUSH(r10) +END_BTB_FLUSH_SECTION + mfspr r10, SPRN_PID lwz r8, VCPU_HOST_PID(r4) PPC_LL r11, VCPU_SHARED(r4) diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index 3f8189eb56ed..fde1de08b4d7 100644 --- a/arch/powerpc/kvm/e500_emulate.c +++ b/arch/powerpc/kvm/e500_emulate.c @@ -277,6 +277,13 @@ int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong spr_va vcpu->arch.pwrmgtcr0 = spr_val; break; + case SPRN_BUCSR: + /* + * If we are here, it means that we have already flushed the + * branch predictor, so just return to guest. + */ + break; + /* extra exceptions */ #ifdef CONFIG_SPE_POSSIBLE case SPRN_IVOR32: diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index eba5756d5b41..578174a33d22 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -543,8 +543,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) #ifdef CONFIG_PPC_BOOK3S_64 case KVM_CAP_SPAPR_TCE: case KVM_CAP_SPAPR_TCE_64: - /* fallthrough */ + r = 1; + break; case KVM_CAP_SPAPR_TCE_VFIO: + r = !!cpu_has_feature(CPU_FTR_HVMODE); + break; case KVM_CAP_PPC_RTAS: case KVM_CAP_PPC_FIXUP_HCALL: case KVM_CAP_PPC_ENABLE_HCALL: @@ -629,6 +632,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; break; + case KVM_CAP_MAX_VCPU_ID: + r = KVM_MAX_VCPU_ID; + break; #ifdef CONFIG_PPC_BOOK3S_64 case KVM_CAP_PPC_GET_SMMU_INFO: r = 1; diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index e613b02bb2f0..dbe478e7b8e0 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -347,6 +347,29 @@ void do_barrier_nospec_fixups_range(bool enable, void *fixup_start, void *fixup_ printk(KERN_DEBUG "barrier-nospec: patched %d locations\n", i); } + +static void patch_btb_flush_section(long *curr) +{ + unsigned int *start, *end; + + start = (void *)curr + *curr; + end = (void *)curr + *(curr + 1); + for (; start < end; start++) { + pr_devel("patching dest %lx\n", (unsigned long)start); + patch_instruction(start, PPC_INST_NOP); + } +} + +void do_btb_flush_fixups(void) +{ + long *start, *end; + + start = PTRRELOC(&__start__btb_flush_fixup); + end = PTRRELOC(&__stop__btb_flush_fixup); + + for (; start < end; start += 2) + patch_btb_flush_section(start); +} #endif /* CONFIG_PPC_FSL_BOOK3E */ void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end) 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/dump_linuxpagetables.c b/arch/powerpc/mm/dump_linuxpagetables.c index bdf33b989f98..8464c2c01c0c 100644 --- a/arch/powerpc/mm/dump_linuxpagetables.c +++ b/arch/powerpc/mm/dump_linuxpagetables.c @@ -19,6 +19,7 @@ #include <linux/hugetlb.h> #include <linux/io.h> #include <linux/mm.h> +#include <linux/highmem.h> #include <linux/sched.h> #include <linux/seq_file.h> #include <asm/fixmap.h> diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index d51cf5f4e45e..365526ee29b8 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -221,7 +221,9 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, static bool bad_kernel_fault(bool is_exec, unsigned long error_code, unsigned long address) { - if (is_exec && (error_code & (DSISR_NOEXEC_OR_G | DSISR_KEYFAULT))) { + /* NX faults set DSISR_PROTFAULT on the 8xx, DSISR_NOEXEC_OR_G on others */ + if (is_exec && (error_code & (DSISR_NOEXEC_OR_G | DSISR_KEYFAULT | + DSISR_PROTFAULT))) { printk_ratelimited(KERN_CRIT "kernel tried to execute" " exec-protected page (%lx) -" "exploit attempt? (uid: %d)\n", diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/hugetlbpage-radix.c index 2486bee0f93e..97c7a39ebc00 100644 --- a/arch/powerpc/mm/hugetlbpage-radix.c +++ b/arch/powerpc/mm/hugetlbpage-radix.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/hugetlb.h> +#include <linux/security.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/cacheflush.h> @@ -73,7 +74,7 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr, if (addr) { addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); - if (high_limit - len >= addr && + if (high_limit - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -83,7 +84,7 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr, */ info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; - info.low_limit = PAGE_SIZE; + info.low_limit = max(PAGE_SIZE, mmap_min_addr); info.high_limit = mm->mmap_base + (high_limit - DEFAULT_MAP_WINDOW); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 7a9886f98b0c..a5091c034747 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -188,15 +188,20 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, pr_debug("vmemmap_populate %lx..%lx, node %d\n", start, end, node); for (; start < end; start += page_size) { - void *p; + void *p = NULL; int rc; if (vmemmap_populated(start, page_size)) continue; + /* + * Allocate from the altmap first if we have one. This may + * fail due to alignment issues when using 16MB hugepages, so + * fall back to system memory if the altmap allocation fail. + */ if (altmap) p = altmap_alloc_block_buf(page_size, altmap); - else + if (!p) p = vmemmap_alloc_block_buf(page_size, node); if (!p) return -ENOMEM; @@ -255,8 +260,15 @@ void __ref vmemmap_free(unsigned long start, unsigned long end, { unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; unsigned long page_order = get_order(page_size); + unsigned long alt_start = ~0, alt_end = ~0; + unsigned long base_pfn; start = _ALIGN_DOWN(start, page_size); + if (altmap) { + alt_start = altmap->base_pfn; + alt_end = altmap->base_pfn + altmap->reserve + + altmap->free + altmap->alloc + altmap->align; + } pr_debug("vmemmap_free %lx...%lx\n", start, end); @@ -280,8 +292,9 @@ void __ref vmemmap_free(unsigned long start, unsigned long end, page = pfn_to_page(addr >> PAGE_SHIFT); section_base = pfn_to_page(vmemmap_section_start(start)); nr_pages = 1 << page_order; + base_pfn = PHYS_PFN(addr); - if (altmap) { + if (base_pfn >= alt_start && base_pfn < alt_end) { vmem_altmap_free(altmap, nr_pages); } else if (PageReserved(page)) { /* allocated from bootmem */ diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 5500e4edabc6..f473c05e9649 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1461,13 +1461,6 @@ static void reset_topology_timer(void) #ifdef CONFIG_SMP -static void stage_topology_update(int core_id) -{ - cpumask_or(&cpu_associativity_changes_mask, - &cpu_associativity_changes_mask, cpu_sibling_mask(core_id)); - reset_topology_timer(); -} - static int dt_update_callback(struct notifier_block *nb, unsigned long action, void *data) { @@ -1480,7 +1473,7 @@ static int dt_update_callback(struct notifier_block *nb, !of_prop_cmp(update->prop->name, "ibm,associativity")) { u32 core_id; of_property_read_u32(update->dn, "reg", &core_id); - stage_topology_update(core_id); + rc = dlpar_cpu_readd(core_id); rc = NOTIFY_OK; } break; @@ -1502,6 +1495,9 @@ int start_topology_update(void) { int rc = 0; + if (!topology_updates_enabled) + return 0; + if (firmware_has_feature(FW_FEATURE_PRRN)) { if (!prrn_enabled) { prrn_enabled = 1; @@ -1531,6 +1527,9 @@ int stop_topology_update(void) { int rc = 0; + if (!topology_updates_enabled) + return 0; + if (prrn_enabled) { prrn_enabled = 0; #ifdef CONFIG_SMP @@ -1586,11 +1585,13 @@ static ssize_t topology_write(struct file *file, const char __user *buf, kbuf[read_len] = '\0'; - if (!strncmp(kbuf, "on", 2)) + if (!strncmp(kbuf, "on", 2)) { + topology_updates_enabled = true; start_topology_update(); - else if (!strncmp(kbuf, "off", 3)) + } else if (!strncmp(kbuf, "off", 3)) { stop_topology_update(); - else + topology_updates_enabled = false; + } else return -EINVAL; return count; @@ -1605,9 +1606,7 @@ static const struct file_operations topology_ops = { static int topology_update_init(void) { - /* Do not poll for changes if disabled at boot */ - if (topology_updates_enabled) - start_topology_update(); + start_topology_update(); if (vphn_enabled) topology_schedule_update(); diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 01d7c0f7c4f0..297db665d953 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -477,3 +477,25 @@ void arch_report_meminfo(struct seq_file *m) atomic_long_read(&direct_pages_count[MMU_PAGE_1G]) << 20); } #endif /* CONFIG_PROC_FS */ + +/* + * For hash translation mode, we use the deposited table to store hash slot + * information and they are stored at PTRS_PER_PMD offset from related pmd + * location. Hence a pmd move requires deposit and withdraw. + * + * For radix translation with split pmd ptl, we store the deposited table in the + * pmd page. Hence if we have different pmd page we need to withdraw during pmd + * move. + * + * With hash we use deposited table always irrespective of anon or not. + * With radix we use deposited table only for anonymous mapping. + */ +int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl, + struct vm_area_struct *vma) +{ + if (radix_enabled()) + return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma); + + return true; +} diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index 4f213ba33491..53e9b58e83c2 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -31,6 +31,7 @@ #include <linux/spinlock.h> #include <linux/export.h> #include <linux/hugetlb.h> +#include <linux/security.h> #include <asm/mman.h> #include <asm/mmu.h> #include <asm/copro.h> @@ -376,6 +377,7 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm, int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); unsigned long addr, found, prev; struct vm_unmapped_area_info info; + unsigned long min_addr = max(PAGE_SIZE, mmap_min_addr); info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; @@ -392,7 +394,7 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm, if (high_limit > DEFAULT_MAP_WINDOW) addr += mm->context.slb_addr_limit - DEFAULT_MAP_WINDOW; - while (addr > PAGE_SIZE) { + while (addr > min_addr) { info.high_limit = addr; if (!slice_scan_available(addr - 1, available, 0, &addr)) continue; @@ -404,8 +406,8 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm, * Check if we need to reduce the range, or if we can * extend it to cover the previous available slice. */ - if (addr < PAGE_SIZE) - addr = PAGE_SIZE; + if (addr < min_addr) + addr = min_addr; else if (slice_scan_available(addr - 1, available, 0, &prev)) { addr = prev; goto prev_slice; @@ -527,7 +529,7 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len, addr = _ALIGN_UP(addr, page_size); slice_dbg(" aligned addr=%lx\n", addr); /* Ignore hint if it's too large or overlaps a VMA */ - if (addr > high_limit - len || + if (addr > high_limit - len || addr < mmap_min_addr || !slice_area_is_free(mm, addr, len)) addr = 0; } diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S index 7fd20c52a8ec..9ed90064f542 100644 --- a/arch/powerpc/mm/tlb_low_64e.S +++ b/arch/powerpc/mm/tlb_low_64e.S @@ -70,6 +70,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) std r15,EX_TLB_R15(r12) std r10,EX_TLB_CR(r12) #ifdef CONFIG_PPC_FSL_BOOK3E +START_BTB_FLUSH_SECTION + mfspr r11, SPRN_SRR1 + andi. r10,r11,MSR_PR + beq 1f + BTB_FLUSH(r10) +1: +END_BTB_FLUSH_SECTION std r7,EX_TLB_R7(r12) #endif TLB_MISS_PROLOG_STATS diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 47fc6660845d..68dece206048 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 6f4daacad296..ade04547703f 100644 --- a/arch/powerpc/net/bpf_jit32.h +++ b/arch/powerpc/net/bpf_jit32.h @@ -123,6 +123,10 @@ 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 50b129785aee..226eec62d125 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -226,7 +226,7 @@ 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); @@ -239,7 +239,7 @@ 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) @@ -249,7 +249,7 @@ 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], @@ -573,7 +573,7 @@ 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; @@ -629,7 +629,7 @@ 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; /* @@ -676,7 +676,7 @@ 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/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 81f8a0c838ae..4004dbdab9c7 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1827,6 +1827,7 @@ static int power_pmu_event_init(struct perf_event *event) int n; int err; struct cpu_hw_events *cpuhw; + u64 bhrb_filter; if (!ppmu) return -ENOENT; @@ -1932,13 +1933,14 @@ static int power_pmu_event_init(struct perf_event *event) err = power_check_constraints(cpuhw, events, cflags, n + 1); if (has_branch_stack(event)) { - cpuhw->bhrb_filter = ppmu->bhrb_filter_map( + bhrb_filter = ppmu->bhrb_filter_map( event->attr.branch_sample_type); - if (cpuhw->bhrb_filter == -1) { + if (bhrb_filter == -1) { put_cpu_var(cpu_hw_events); return -EOPNOTSUPP; } + cpuhw->bhrb_filter = bhrb_filter; } put_cpu_var(cpu_hw_events); diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 1fafc32b12a0..555322677074 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -496,6 +496,11 @@ static int nest_imc_event_init(struct perf_event *event) * Get the base memory addresss for this cpu. */ chip_id = cpu_to_chip_id(event->cpu); + + /* Return, if chip_id is not valid */ + if (chip_id < 0) + return -ENODEV; + pcni = pmu->mem_info; do { if (pcni->id == chip_id) { @@ -503,7 +508,7 @@ static int nest_imc_event_init(struct perf_event *event) break; } pcni++; - } while (pcni); + } while (pcni->vbase != 0); if (!flag) return -ENODEV; diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 177de814286f..6a2f65d3d088 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -226,8 +226,13 @@ void isa207_get_mem_weight(u64 *weight) u64 mmcra = mfspr(SPRN_MMCRA); u64 exp = MMCRA_THR_CTR_EXP(mmcra); u64 mantissa = MMCRA_THR_CTR_MANT(mmcra); + u64 sier = mfspr(SPRN_SIER); + u64 val = (sier & ISA207_SIER_TYPE_MASK) >> ISA207_SIER_TYPE_SHIFT; - *weight = mantissa << (2 * exp); + if (val == 0 || val == 7) + *weight = 0; + else + *weight = mantissa << (2 * exp); } int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index d12a2db26353..d10feef93b6b 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -29,6 +29,7 @@ enum { #define POWER8_MMCRA_IFM1 0x0000000040000000UL #define POWER8_MMCRA_IFM2 0x0000000080000000UL #define POWER8_MMCRA_IFM3 0x00000000C0000000UL +#define POWER8_MMCRA_BHRB_MASK 0x00000000C0000000UL /* * Raw event encoding for PowerISA v2.07 (Power8): @@ -243,6 +244,8 @@ static u64 power8_bhrb_filter_map(u64 branch_sample_type) static void power8_config_bhrb(u64 pmu_bhrb_filter) { + pmu_bhrb_filter &= POWER8_MMCRA_BHRB_MASK; + /* Enable BHRB filter in PMU */ mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter)); } diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index e012b1030a5b..c07b1615ee39 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -100,6 +100,7 @@ enum { #define POWER9_MMCRA_IFM1 0x0000000040000000UL #define POWER9_MMCRA_IFM2 0x0000000080000000UL #define POWER9_MMCRA_IFM3 0x00000000C0000000UL +#define POWER9_MMCRA_BHRB_MASK 0x00000000C0000000UL /* Nasty Power9 specific hack */ #define PVR_POWER9_CUMULUS 0x00002000 @@ -308,6 +309,8 @@ static u64 power9_bhrb_filter_map(u64 branch_sample_type) static void power9_config_bhrb(u64 pmu_bhrb_filter) { + pmu_bhrb_filter &= POWER9_MMCRA_BHRB_MASK; + /* Enable BHRB filter in PMU */ mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter)); } diff --git a/arch/powerpc/platforms/83xx/suspend-asm.S b/arch/powerpc/platforms/83xx/suspend-asm.S index 3d1ecd211776..8137f77abad5 100644 --- a/arch/powerpc/platforms/83xx/suspend-asm.S +++ b/arch/powerpc/platforms/83xx/suspend-asm.S @@ -26,13 +26,13 @@ #define SS_MSR 0x74 #define SS_SDR1 0x78 #define SS_LR 0x7c -#define SS_SPRG 0x80 /* 4 SPRGs */ -#define SS_DBAT 0x90 /* 8 DBATs */ -#define SS_IBAT 0xd0 /* 8 IBATs */ -#define SS_TB 0x110 -#define SS_CR 0x118 -#define SS_GPREG 0x11c /* r12-r31 */ -#define STATE_SAVE_SIZE 0x16c +#define SS_SPRG 0x80 /* 8 SPRGs */ +#define SS_DBAT 0xa0 /* 8 DBATs */ +#define SS_IBAT 0xe0 /* 8 IBATs */ +#define SS_TB 0x120 +#define SS_CR 0x128 +#define SS_GPREG 0x12c /* r12-r31 */ +#define STATE_SAVE_SIZE 0x17c .section .data .align 5 @@ -103,6 +103,16 @@ _GLOBAL(mpc83xx_enter_deep_sleep) stw r7, SS_SPRG+12(r3) stw r8, SS_SDR1(r3) + mfspr r4, SPRN_SPRG4 + mfspr r5, SPRN_SPRG5 + mfspr r6, SPRN_SPRG6 + mfspr r7, SPRN_SPRG7 + + stw r4, SS_SPRG+16(r3) + stw r5, SS_SPRG+20(r3) + stw r6, SS_SPRG+24(r3) + stw r7, SS_SPRG+28(r3) + mfspr r4, SPRN_DBAT0U mfspr r5, SPRN_DBAT0L mfspr r6, SPRN_DBAT1U @@ -493,6 +503,16 @@ mpc83xx_deep_resume: mtspr SPRN_IBAT7U, r6 mtspr SPRN_IBAT7L, r7 + lwz r4, SS_SPRG+16(r3) + lwz r5, SS_SPRG+20(r3) + lwz r6, SS_SPRG+24(r3) + lwz r7, SS_SPRG+28(r3) + + mtspr SPRN_SPRG4, r4 + mtspr SPRN_SPRG5, r5 + mtspr SPRN_SPRG6, r6 + mtspr SPRN_SPRG7, r7 + lwz r4, SS_SPRG+0(r3) lwz r5, SS_SPRG+4(r3) lwz r6, SS_SPRG+8(r3) diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 6c6a7c72cae4..ad0216c41d2c 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -330,7 +330,7 @@ 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/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c index 403523c061ba..343bffd20fca 100644 --- a/arch/powerpc/platforms/embedded6xx/wii.c +++ b/arch/powerpc/platforms/embedded6xx/wii.c @@ -83,6 +83,10 @@ unsigned long __init wii_mmu_mapin_mem2(unsigned long top) /* MEM2 64MB@0x10000000 */ delta = wii_hole_start + wii_hole_size; size = top - delta; + + if (__map_without_bats) + return delta; + for (bl = 128<<10; bl < max_size; bl <<= 1) { if (bl * 2 > size) break; diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile index f2839eed0f89..561a67d65e4d 100644 --- a/arch/powerpc/platforms/powermac/Makefile +++ b/arch/powerpc/platforms/powermac/Makefile @@ -3,7 +3,7 @@ CFLAGS_bootx_init.o += -fPIC ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code -CFLAGS_REMOVE_bootx_init.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_bootx_init.o = $(CC_FLAGS_FTRACE) endif obj-y += pic.o setup.o time.o feature.o pci.o \ diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 35f699ebb662..e52f9b06dd9c 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -458,7 +458,8 @@ EXPORT_SYMBOL_GPL(pnv_power9_force_smt4_release); #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #ifdef CONFIG_HOTPLUG_CPU -static void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val) + +void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val) { u64 pir = get_hard_smp_processor_id(cpu); @@ -481,20 +482,6 @@ unsigned long pnv_cpu_offline(unsigned int cpu) { unsigned long srr1; u32 idle_states = pnv_get_supported_cpuidle_states(); - u64 lpcr_val; - - /* - * We don't want to take decrementer interrupts while we are - * offline, so clear LPCR:PECE1. We keep PECE2 (and - * LPCR_PECE_HVEE on P9) enabled as to let IPIs in. - * - * If the CPU gets woken up by a special wakeup, ensure that - * the SLW engine sets LPCR with decrementer bit cleared, else - * the CPU will come back to the kernel due to a spurious - * wakeup. - */ - lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1; - pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val); __ppc64_runlatch_off(); @@ -526,16 +513,6 @@ unsigned long pnv_cpu_offline(unsigned int cpu) __ppc64_runlatch_on(); - /* - * Re-enable decrementer interrupts in LPCR. - * - * Further, we want stop states to be woken up by decrementer - * for non-hotplug cases. So program the LPCR via stop api as - * well. - */ - lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1; - pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val); - return srr1; } #endif diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c index 58a07948c76e..3d27f02695e4 100644 --- a/arch/powerpc/platforms/powernv/opal-imc.c +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -127,7 +127,7 @@ static int imc_get_mem_addr_nest(struct device_node *node, nr_chips)) goto error; - pmu_ptr->mem_info = kcalloc(nr_chips, sizeof(*pmu_ptr->mem_info), + pmu_ptr->mem_info = kcalloc(nr_chips + 1, sizeof(*pmu_ptr->mem_info), GFP_KERNEL); if (!pmu_ptr->mem_info) goto error; diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c index acd3206dfae3..06628c71cef6 100644 --- a/arch/powerpc/platforms/powernv/opal-msglog.c +++ b/arch/powerpc/platforms/powernv/opal-msglog.c @@ -98,7 +98,7 @@ static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj, } static struct bin_attribute opal_msglog_attr = { - .attr = {.name = "msglog", .mode = 0444}, + .attr = {.name = "msglog", .mode = 0400}, .read = opal_msglog_read }; diff --git a/arch/powerpc/platforms/powernv/opal-tracepoints.c b/arch/powerpc/platforms/powernv/opal-tracepoints.c index 1ab7d26c0a2c..f16a43540e30 100644 --- a/arch/powerpc/platforms/powernv/opal-tracepoints.c +++ b/arch/powerpc/platforms/powernv/opal-tracepoints.c @@ -4,7 +4,7 @@ #include <asm/trace.h> #include <asm/asm-prototypes.h> -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL struct static_key opal_tracepoint_key = STATIC_KEY_INIT; int opal_tracepoint_regfunc(void) diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 251528231a9e..f4875fe3f8ff 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -20,7 +20,7 @@ .section ".text" #ifdef CONFIG_TRACEPOINTS -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL #define OPAL_BRANCH(LABEL) \ ARCH_STATIC_BRANCH(LABEL, opal_tracepoint_key) #else diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c index fe9691040f54..f5adb6b756f7 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c +++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c @@ -299,7 +299,7 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, if (alloc_userspace_copy) { offset = 0; uas = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift, - levels, tce_table_size, &offset, + tmplevels, tce_table_size, &offset, &total_allocated_uas); if (!uas) goto free_tces_exit; @@ -313,7 +313,6 @@ long pnv_pci_ioda2_table_alloc_pages(int nid, __u64 bus_offset, page_shift); tbl->it_level_size = 1ULL << (level_shift - 3); tbl->it_indirect_levels = levels - 1; - tbl->it_allocated_size = total_allocated; tbl->it_userspace = uas; tbl->it_nid = nid; diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index cde710297a4e..326ca6288bb1 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2603,8 +2603,13 @@ static long pnv_pci_ioda2_create_table_userspace( int num, __u32 page_shift, __u64 window_size, __u32 levels, struct iommu_table **ptbl) { - return pnv_pci_ioda2_create_table(table_group, + long ret = pnv_pci_ioda2_create_table(table_group, num, page_shift, window_size, levels, true, ptbl); + + if (!ret) + (*ptbl)->it_allocated_size = pnv_pci_ioda2_get_table_size( + page_shift, window_size, levels); + return ret; } static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group) diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 0d354e19ef92..db09c7022635 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -39,6 +39,7 @@ #include <asm/cpuidle.h> #include <asm/kexec.h> #include <asm/reg.h> +#include <asm/powernv.h> #include "powernv.h" @@ -153,6 +154,7 @@ static void pnv_smp_cpu_kill_self(void) { unsigned int cpu; unsigned long srr1, wmask; + u64 lpcr_val; /* Standard hot unplug procedure */ /* @@ -174,6 +176,19 @@ static void pnv_smp_cpu_kill_self(void) if (cpu_has_feature(CPU_FTR_ARCH_207S)) wmask = SRR1_WAKEMASK_P8; + /* + * We don't want to take decrementer interrupts while we are + * offline, so clear LPCR:PECE1. We keep PECE2 (and + * LPCR_PECE_HVEE on P9) enabled so as to let IPIs in. + * + * If the CPU gets woken up by a special wakeup, ensure that + * the SLW engine sets LPCR with decrementer bit cleared, else + * the CPU will come back to the kernel due to a spurious + * wakeup. + */ + lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1; + pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val); + while (!generic_check_cpu_restart(cpu)) { /* * Clear IPI flag, since we don't handle IPIs while @@ -246,6 +261,16 @@ static void pnv_smp_cpu_kill_self(void) } + /* + * Re-enable decrementer interrupts in LPCR. + * + * Further, we want stop states to be woken up by decrementer + * for non-hotplug cases. So program the LPCR via stop api as + * well. + */ + lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1; + pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val); + DBG("CPU%d coming online...\n", cpu); } diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index a0b20c03f078..e3010b14aea5 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -272,6 +272,8 @@ int dlpar_detach_node(struct device_node *dn) if (rc) return rc; + of_node_put(dn); + return 0; } diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 6ef77caf7bcf..1d3f9313c02f 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -802,6 +802,25 @@ static int dlpar_cpu_add_by_count(u32 cpus_to_add) return rc; } +int dlpar_cpu_readd(int cpu) +{ + struct device_node *dn; + struct device *dev; + u32 drc_index; + int rc; + + dev = get_cpu_device(cpu); + dn = dev->of_node; + + rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index); + + rc = dlpar_cpu_remove_by_index(drc_index); + if (!rc) + rc = dlpar_cpu_add(drc_index); + + return rc; +} + int dlpar_cpu(struct pseries_hp_errorlog *hp_elog) { u32 count, drc_index; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index c1578f54c626..e4c658cda3a7 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -389,8 +389,11 @@ static bool lmb_is_removable(struct drmem_lmb *lmb) phys_addr = lmb->base_addr; #ifdef CONFIG_FA_DUMP - /* Don't hot-remove memory that falls in fadump boot memory area */ - if (is_fadump_boot_memory_area(phys_addr, block_sz)) + /* + * Don't hot-remove memory that falls in fadump boot memory area + * and memory that is reserved for capturing old kernel memory. + */ + if (is_fadump_memory_area(phys_addr, block_sz)) return false; #endif diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index d91412c591ef..50dc9426d0be 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -19,7 +19,7 @@ #ifdef CONFIG_TRACEPOINTS -#ifndef HAVE_JUMP_LABEL +#ifndef CONFIG_JUMP_LABEL .section ".toc","aw" .globl hcall_tracepoint_refcount @@ -79,7 +79,7 @@ hcall_tracepoint_refcount: mr r5,BUFREG; \ __HCALL_INST_POSTCALL -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL #define HCALL_BRANCH(LABEL) \ ARCH_STATIC_BRANCH(LABEL, hcall_tracepoint_key) #else diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 06f02960b439..d80d919c78d3 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -38,6 +38,7 @@ #include <linux/of.h> #include <linux/iommu.h> #include <linux/rculist.h> +#include <linux/locallock.h> #include <asm/io.h> #include <asm/prom.h> #include <asm/rtas.h> @@ -212,6 +213,7 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum, } static DEFINE_PER_CPU(__be64 *, tce_page); +static DEFINE_LOCAL_IRQ_LOCK(tcp_page_lock); static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages, unsigned long uaddr, @@ -232,7 +234,8 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, direction, attrs); } - local_irq_save(flags); /* to protect tcep and the page behind it */ + /* to protect tcep and the page behind it */ + local_lock_irqsave(tcp_page_lock, flags); tcep = __this_cpu_read(tce_page); @@ -243,7 +246,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, tcep = (__be64 *)__get_free_page(GFP_ATOMIC); /* If allocation fails, fall back to the loop implementation */ if (!tcep) { - local_irq_restore(flags); + local_unlock_irqrestore(tcp_page_lock, flags); return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr, direction, attrs); } @@ -277,7 +280,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, tcenum += limit; } while (npages > 0 && !rc); - local_irq_restore(flags); + local_unlock_irqrestore(tcp_page_lock, flags); if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) { ret = (int)rc; @@ -435,13 +438,14 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, u64 rc = 0; long l, limit; - local_irq_disable(); /* to protect tcep and the page behind it */ + /* to protect tcep and the page behind it */ + local_lock_irq(tcp_page_lock); tcep = __this_cpu_read(tce_page); if (!tcep) { tcep = (__be64 *)__get_free_page(GFP_ATOMIC); if (!tcep) { - local_irq_enable(); + local_unlock_irq(tcp_page_lock); return -ENOMEM; } __this_cpu_write(tce_page, tcep); @@ -487,7 +491,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, /* error cleanup: caller will clear whole range */ - local_irq_enable(); + local_unlock_irq(tcp_page_lock); return rc; } diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index d3992ced0782..9e52b686a8fa 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -828,7 +828,7 @@ EXPORT_SYMBOL(arch_free_page); #endif /* CONFIG_PPC_BOOK3S_64 */ #ifdef CONFIG_TRACEPOINTS -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL struct static_key hcall_tracepoint_key = STATIC_KEY_INIT; int hcall_tracepoint_regfunc(void) 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/xmon/Makefile b/arch/powerpc/xmon/Makefile index 1bc3abb237cd..9d7d8e6d705c 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -1,14 +1,17 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for xmon -subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror +# Disable clang warning for using setjmp without setjmp.h header +subdir-ccflags-y := $(call cc-disable-warning, builtin-requires-header) + +subdir-ccflags-$(CONFIG_PPC_WERROR) += -Werror GCOV_PROFILE := n UBSAN_SANITIZE := n # Disable ftrace for the entire directory ORIG_CFLAGS := $(KBUILD_CFLAGS) -KBUILD_CFLAGS = $(subst -mno-sched-epilog,,$(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS))) +KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS)) ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) diff --git a/arch/powerpc/xmon/ppc-dis.c b/arch/powerpc/xmon/ppc-dis.c index 9deea5ee13f6..27f1e6415036 100644 --- a/arch/powerpc/xmon/ppc-dis.c +++ b/arch/powerpc/xmon/ppc-dis.c @@ -158,7 +158,7 @@ int print_insn_powerpc (unsigned long insn, unsigned long memaddr) dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 | PPC_OPCODE_POWER8 | PPC_OPCODE_POWER9 | PPC_OPCODE_HTM | PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2 - | PPC_OPCODE_VSX | PPC_OPCODE_VSX3), + | PPC_OPCODE_VSX | PPC_OPCODE_VSX3); /* Get the major opcode of the insn. */ opcode = NULL; diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 4264aedc7775..dd6badc31f45 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -75,6 +75,9 @@ static int xmon_gate; #define xmon_owner 0 #endif /* CONFIG_SMP */ +#ifdef CONFIG_PPC_PSERIES +static int set_indicator_token = RTAS_UNKNOWN_SERVICE; +#endif static unsigned long in_xmon __read_mostly = 0; static int xmon_on = IS_ENABLED(CONFIG_XMON_DEFAULT); @@ -358,7 +361,6 @@ static inline void disable_surveillance(void) #ifdef CONFIG_PPC_PSERIES /* Since this can't be a module, args should end up below 4GB. */ static struct rtas_args args; - int token; /* * At this point we have got all the cpus we can into @@ -367,11 +369,11 @@ static inline void disable_surveillance(void) * If we did try to take rtas.lock there would be a * real possibility of deadlock. */ - token = rtas_token("set-indicator"); - if (token == RTAS_UNKNOWN_SERVICE) + if (set_indicator_token == RTAS_UNKNOWN_SERVICE) return; - rtas_call_unlocked(&args, token, 3, 1, NULL, SURVEILLANCE_TOKEN, 0, 0); + rtas_call_unlocked(&args, set_indicator_token, 3, 1, NULL, + SURVEILLANCE_TOKEN, 0, 0); #endif /* CONFIG_PPC_PSERIES */ } @@ -3672,6 +3674,14 @@ static void xmon_init(int enable) __debugger_iabr_match = xmon_iabr_match; __debugger_break_match = xmon_break_match; __debugger_fault_handler = xmon_fault_handler; + +#ifdef CONFIG_PPC_PSERIES + /* + * Get the token here to avoid trying to get a lock + * during the crash, causing a deadlock. + */ + set_indicator_token = rtas_token("set-indicator"); +#endif } else { __debugger = NULL; __debugger_ipi = NULL; |