diff options
Diffstat (limited to 'arch')
62 files changed, 494 insertions, 170 deletions
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 0c4805a572c8..04a4a138ed13 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -555,11 +555,6 @@ config SMP If you don't know what to do here, say N. -config HAVE_DEC_LOCK - bool - depends on SMP - default y - config NR_CPUS int "Maximum number of CPUs (2-32)" range 2 32 diff --git a/arch/alpha/lib/Makefile b/arch/alpha/lib/Makefile index 04f9729de57c..854d5e79979e 100644 --- a/arch/alpha/lib/Makefile +++ b/arch/alpha/lib/Makefile @@ -35,8 +35,6 @@ lib-y = __divqu.o __remqu.o __divlu.o __remlu.o \ callback_srm.o srm_puts.o srm_printk.o \ fls.o -lib-$(CONFIG_SMP) += dec_and_lock.o - # The division routines are built from single source, with different defines. AFLAGS___divqu.o = -DDIV AFLAGS___remqu.o = -DREM diff --git a/arch/alpha/lib/dec_and_lock.c b/arch/alpha/lib/dec_and_lock.c deleted file mode 100644 index a117707f57fe..000000000000 --- a/arch/alpha/lib/dec_and_lock.c +++ /dev/null @@ -1,44 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * arch/alpha/lib/dec_and_lock.c - * - * ll/sc version of atomic_dec_and_lock() - * - */ - -#include <linux/spinlock.h> -#include <linux/atomic.h> -#include <linux/export.h> - - asm (".text \n\ - .global _atomic_dec_and_lock \n\ - .ent _atomic_dec_and_lock \n\ - .align 4 \n\ -_atomic_dec_and_lock: \n\ - .prologue 0 \n\ -1: ldl_l $1, 0($16) \n\ - subl $1, 1, $1 \n\ - beq $1, 2f \n\ - stl_c $1, 0($16) \n\ - beq $1, 4f \n\ - mb \n\ - clr $0 \n\ - ret \n\ -2: br $29, 3f \n\ -3: ldgp $29, 0($29) \n\ - br $atomic_dec_and_lock_1..ng \n\ - .subsection 2 \n\ -4: br 1b \n\ - .previous \n\ - .end _atomic_dec_and_lock"); - -static int __used atomic_dec_and_lock_1(atomic_t *atomic, spinlock_t *lock) -{ - /* Slow path */ - spin_lock(lock); - if (atomic_dec_and_test(atomic)) - return 1; - spin_unlock(lock); - return 0; -} -EXPORT_SYMBOL(_atomic_dec_and_lock); diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 8073625371f5..07060e5b5864 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -59,6 +59,9 @@ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; static __read_mostly unsigned int xen_events_irq; +uint32_t xen_start_flags; +EXPORT_SYMBOL(xen_start_flags); + int xen_remap_domain_gfn_array(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *gfn, int nr, @@ -293,9 +296,7 @@ void __init xen_early_init(void) xen_setup_features(); if (xen_feature(XENFEAT_dom0)) - xen_start_info->flags |= SIF_INITDOMAIN|SIF_PRIVILEGED; - else - xen_start_info->flags &= ~(SIF_INITDOMAIN|SIF_PRIVILEGED); + xen_start_flags |= SIF_INITDOMAIN|SIF_PRIVILEGED; if (!console_set_on_cmdline && !xen_initial_domain()) add_preferred_console("hvc", 0, NULL); diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c index 253188fb8cb0..e3e50950a863 100644 --- a/arch/arm64/crypto/aes-glue.c +++ b/arch/arm64/crypto/aes-glue.c @@ -223,8 +223,8 @@ static int ctr_encrypt(struct skcipher_request *req) kernel_neon_begin(); aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr, (u8 *)ctx->key_enc, rounds, blocks, walk.iv); - err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE); kernel_neon_end(); + err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE); } if (walk.nbytes) { u8 __aligned(8) tail[AES_BLOCK_SIZE]; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index fda9a8ca48be..fe8777b12f86 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -306,6 +306,7 @@ struct kvm_vcpu_arch { #define KVM_ARM64_FP_ENABLED (1 << 1) /* guest FP regs loaded */ #define KVM_ARM64_FP_HOST (1 << 2) /* host FP regs loaded */ #define KVM_ARM64_HOST_SVE_IN_USE (1 << 3) /* backup for host TIF_SVE */ +#define KVM_ARM64_HOST_SVE_ENABLED (1 << 4) /* SVE enabled for EL0 */ #define vcpu_gp_regs(v) (&(v)->arch.ctxt.gp_regs) diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 6171178075dc..a8f84812c6e8 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -728,6 +728,17 @@ asm( asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val)); \ } while (0) +/* + * Modify bits in a sysreg. Bits in the clear mask are zeroed, then bits in the + * set mask are set. Other bits are left as-is. + */ +#define sysreg_clear_set(sysreg, clear, set) do { \ + u64 __scs_val = read_sysreg(sysreg); \ + u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set); \ + if (__scs_new != __scs_val) \ + write_sysreg(__scs_new, sysreg); \ +} while (0) + static inline void config_sctlr_el1(u32 clear, u32 set) { u32 val; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index d2856b129097..f24892a40d2c 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -937,7 +937,7 @@ static int __init parse_kpti(char *str) __kpti_forced = enabled ? 1 : -1; return 0; } -__setup("kpti=", parse_kpti); +early_param("kpti", parse_kpti); #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ #ifdef CONFIG_ARM64_HW_AFDBM diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index f3e2e3aec0b0..2faa9863d2e5 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -179,7 +179,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) * This is the secondary CPU boot entry. We're using this CPUs * idle thread stack, but a set of temporary page tables. */ -asmlinkage void secondary_start_kernel(void) +asmlinkage notrace void secondary_start_kernel(void) { u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK; struct mm_struct *mm = &init_mm; diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index dc6ecfa5a2d2..aac7808ce216 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -5,13 +5,14 @@ * Copyright 2018 Arm Limited * Author: Dave Martin <Dave.Martin@arm.com> */ -#include <linux/bottom_half.h> +#include <linux/irqflags.h> #include <linux/sched.h> #include <linux/thread_info.h> #include <linux/kvm_host.h> #include <asm/kvm_asm.h> #include <asm/kvm_host.h> #include <asm/kvm_mmu.h> +#include <asm/sysreg.h> /* * Called on entry to KVM_RUN unless this vcpu previously ran at least @@ -61,10 +62,16 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) { BUG_ON(!current->mm); - vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | KVM_ARM64_HOST_SVE_IN_USE); + vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | + KVM_ARM64_HOST_SVE_IN_USE | + KVM_ARM64_HOST_SVE_ENABLED); vcpu->arch.flags |= KVM_ARM64_FP_HOST; + if (test_thread_flag(TIF_SVE)) vcpu->arch.flags |= KVM_ARM64_HOST_SVE_IN_USE; + + if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) + vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED; } /* @@ -92,19 +99,30 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) */ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) { - local_bh_disable(); + unsigned long flags; - update_thread_flag(TIF_SVE, - vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE); + local_irq_save(flags); if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { /* Clean guest FP state to memory and invalidate cpu view */ fpsimd_save(); fpsimd_flush_cpu_state(); - } else if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { - /* Ensure user trap controls are correctly restored */ - fpsimd_bind_task_to_cpu(); + } else if (system_supports_sve()) { + /* + * The FPSIMD/SVE state in the CPU has not been touched, and we + * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been + * reset to CPACR_EL1_DEFAULT by the Hyp code, disabling SVE + * for EL0. To avoid spurious traps, restore the trap state + * seen by kvm_arch_vcpu_load_fp(): + */ + if (vcpu->arch.flags & KVM_ARM64_HOST_SVE_ENABLED) + sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN); + else + sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0); } - local_bh_enable(); + update_thread_flag(TIF_SVE, + vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE); + + local_irq_restore(flags); } diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 49e217ac7e1e..61e93f0b5482 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -583,13 +583,14 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, size >> PAGE_SHIFT); return NULL; } - if (!coherent) - __dma_flush_area(page_to_virt(page), iosize); - addr = dma_common_contiguous_remap(page, size, VM_USERMAP, prot, __builtin_return_address(0)); - if (!addr) { + if (addr) { + memset(addr, 0, size); + if (!coherent) + __dma_flush_area(page_to_virt(page), iosize); + } else { iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs); dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 5f9a73a4452c..03646e6a2ef4 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -217,8 +217,9 @@ ENDPROC(idmap_cpu_replace_ttbr1) .macro __idmap_kpti_put_pgtable_ent_ng, type orr \type, \type, #PTE_NG // Same bit for blocks and pages - str \type, [cur_\()\type\()p] // Update the entry and ensure it - dc civac, cur_\()\type\()p // is visible to all CPUs. + str \type, [cur_\()\type\()p] // Update the entry and ensure + dmb sy // that it is visible to all + dc civac, cur_\()\type\()p // CPUs. .endm /* diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 3f9deec70b92..08c10c518f83 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -65,6 +65,7 @@ config MIPS select HAVE_OPROFILE select HAVE_PERF_EVENTS select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RSEQ select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING_GEN if 64BIT || !SMP diff --git a/arch/mips/ath79/mach-pb44.c b/arch/mips/ath79/mach-pb44.c index 6b2c6f3baefa..75fb96ca61db 100644 --- a/arch/mips/ath79/mach-pb44.c +++ b/arch/mips/ath79/mach-pb44.c @@ -34,7 +34,7 @@ #define PB44_KEYS_DEBOUNCE_INTERVAL (3 * PB44_KEYS_POLL_INTERVAL) static struct gpiod_lookup_table pb44_i2c_gpiod_table = { - .dev_id = "i2c-gpio", + .dev_id = "i2c-gpio.0", .table = { GPIO_LOOKUP_IDX("ath79-gpio", PB44_GPIO_I2C_SDA, NULL, 0, GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index 6054d49e608e..8c9cbf13d32a 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -212,6 +212,12 @@ static int __init bcm47xx_cpu_fixes(void) */ if (bcm47xx_bus.bcma.bus.chipinfo.id == BCMA_CHIP_ID_BCM4706) cpu_wait = NULL; + + /* + * BCM47XX Erratum "R10: PCIe Transactions Periodically Fail" + * Enable ExternalSync for sync instruction to take effect + */ + set_c0_config7(MIPS_CONF7_ES); break; #endif } diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index a7d0b836f2f7..cea8ad864b3f 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -414,6 +414,8 @@ static inline type pfx##in##bwlq##p(unsigned long port) \ __val = *__addr; \ slow; \ \ + /* prevent prefetching of coherent DMA data prematurely */ \ + rmb(); \ return pfx##ioswab##bwlq(__addr, __val); \ } diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index ae461d91cd1f..0bc270806ec5 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -681,6 +681,8 @@ #define MIPS_CONF7_WII (_ULCAST_(1) << 31) #define MIPS_CONF7_RPS (_ULCAST_(1) << 2) +/* ExternalSync */ +#define MIPS_CONF7_ES (_ULCAST_(1) << 8) #define MIPS_CONF7_IAR (_ULCAST_(1) << 10) #define MIPS_CONF7_AR (_ULCAST_(1) << 16) @@ -2765,6 +2767,7 @@ __BUILD_SET_C0(status) __BUILD_SET_C0(cause) __BUILD_SET_C0(config) __BUILD_SET_C0(config5) +__BUILD_SET_C0(config7) __BUILD_SET_C0(intcontrol) __BUILD_SET_C0(intctl) __BUILD_SET_C0(srsmap) diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h index bb05e9916a5f..f25dd1d83fb7 100644 --- a/arch/mips/include/uapi/asm/unistd.h +++ b/arch/mips/include/uapi/asm/unistd.h @@ -388,17 +388,19 @@ #define __NR_pkey_alloc (__NR_Linux + 364) #define __NR_pkey_free (__NR_Linux + 365) #define __NR_statx (__NR_Linux + 366) +#define __NR_rseq (__NR_Linux + 367) +#define __NR_io_pgetevents (__NR_Linux + 368) /* * Offset of the last Linux o32 flavoured syscall */ -#define __NR_Linux_syscalls 366 +#define __NR_Linux_syscalls 368 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */ #define __NR_O32_Linux 4000 -#define __NR_O32_Linux_syscalls 366 +#define __NR_O32_Linux_syscalls 368 #if _MIPS_SIM == _MIPS_SIM_ABI64 @@ -733,16 +735,18 @@ #define __NR_pkey_alloc (__NR_Linux + 324) #define __NR_pkey_free (__NR_Linux + 325) #define __NR_statx (__NR_Linux + 326) +#define __NR_rseq (__NR_Linux + 327) +#define __NR_io_pgetevents (__NR_Linux + 328) /* * Offset of the last Linux 64-bit flavoured syscall */ -#define __NR_Linux_syscalls 326 +#define __NR_Linux_syscalls 328 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */ #define __NR_64_Linux 5000 -#define __NR_64_Linux_syscalls 326 +#define __NR_64_Linux_syscalls 328 #if _MIPS_SIM == _MIPS_SIM_NABI32 @@ -1081,15 +1085,17 @@ #define __NR_pkey_alloc (__NR_Linux + 328) #define __NR_pkey_free (__NR_Linux + 329) #define __NR_statx (__NR_Linux + 330) +#define __NR_rseq (__NR_Linux + 331) +#define __NR_io_pgetevents (__NR_Linux + 332) /* * Offset of the last N32 flavoured syscall */ -#define __NR_Linux_syscalls 330 +#define __NR_Linux_syscalls 332 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */ #define __NR_N32_Linux 6000 -#define __NR_N32_Linux_syscalls 330 +#define __NR_N32_Linux_syscalls 332 #endif /* _UAPI_ASM_UNISTD_H */ diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S index 38a302919e6b..d7de8adcfcc8 100644 --- a/arch/mips/kernel/entry.S +++ b/arch/mips/kernel/entry.S @@ -79,6 +79,10 @@ FEXPORT(ret_from_fork) jal schedule_tail # a0 = struct task_struct *prev FEXPORT(syscall_exit) +#ifdef CONFIG_DEBUG_RSEQ + move a0, sp + jal rseq_syscall +#endif local_irq_disable # make sure need_resched and # signals dont change between # sampling and return @@ -141,6 +145,10 @@ work_notifysig: # deal with pending signals and j resume_userspace_check FEXPORT(syscall_exit_partial) +#ifdef CONFIG_DEBUG_RSEQ + move a0, sp + jal rseq_syscall +#endif local_irq_disable # make sure need_resched doesn't # change between and return LONG_L a2, TI_FLAGS($28) # current->work diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S index f2ee7e1e3342..cff52b283e03 100644 --- a/arch/mips/kernel/mcount.S +++ b/arch/mips/kernel/mcount.S @@ -119,10 +119,20 @@ NESTED(_mcount, PT_SIZE, ra) EXPORT_SYMBOL(_mcount) PTR_LA t1, ftrace_stub PTR_L t2, ftrace_trace_function /* Prepare t2 for (1) */ - bne t1, t2, static_trace + beq t1, t2, fgraph_trace nop + MCOUNT_SAVE_REGS + + move a0, ra /* arg1: self return address */ + jalr t2 /* (1) call *ftrace_trace_function */ + move a1, AT /* arg2: parent's return address */ + + MCOUNT_RESTORE_REGS + +fgraph_trace: #ifdef CONFIG_FUNCTION_GRAPH_TRACER + PTR_LA t1, ftrace_stub PTR_L t3, ftrace_graph_return bne t1, t3, ftrace_graph_caller nop @@ -131,24 +141,11 @@ EXPORT_SYMBOL(_mcount) bne t1, t3, ftrace_graph_caller nop #endif - b ftrace_stub -#ifdef CONFIG_32BIT - addiu sp, sp, 8 -#else - nop -#endif -static_trace: - MCOUNT_SAVE_REGS - - move a0, ra /* arg1: self return address */ - jalr t2 /* (1) call *ftrace_trace_function */ - move a1, AT /* arg2: parent's return address */ - - MCOUNT_RESTORE_REGS #ifdef CONFIG_32BIT addiu sp, sp, 8 #endif + .globl ftrace_stub ftrace_stub: RETURN_BACK diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index a9a7d78803cd..91d3c8c46097 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -590,3 +590,5 @@ EXPORT(sys_call_table) PTR sys_pkey_alloc PTR sys_pkey_free /* 4365 */ PTR sys_statx + PTR sys_rseq + PTR sys_io_pgetevents diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 65d5aeeb9bdb..358d9599983d 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -439,4 +439,6 @@ EXPORT(sys_call_table) PTR sys_pkey_alloc PTR sys_pkey_free /* 5325 */ PTR sys_statx + PTR sys_rseq + PTR sys_io_pgetevents .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index cbf190ef9e8a..c65eaacc1abf 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -434,4 +434,6 @@ EXPORT(sysn32_call_table) PTR sys_pkey_alloc PTR sys_pkey_free PTR sys_statx /* 6330 */ + PTR sys_rseq + PTR compat_sys_io_pgetevents .size sysn32_call_table,.-sysn32_call_table diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 9ebe3e2403b1..73913f072e39 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -583,4 +583,6 @@ EXPORT(sys32_call_table) PTR sys_pkey_alloc PTR sys_pkey_free /* 4365 */ PTR sys_statx + PTR sys_rseq + PTR compat_sys_io_pgetevents .size sys32_call_table,.-sys32_call_table diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index 9e224469c788..00f2535d2226 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -801,6 +801,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) regs->regs[0] = 0; /* Don't deal with this again. */ } + rseq_signal_deliver(regs); + if (sig_uses_siginfo(&ksig->ka, abi)) ret = abi->setup_rt_frame(vdso + abi->vdso->off_rt_sigreturn, ksig, regs, oldset); @@ -868,6 +870,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused, if (thread_info_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); tracehook_notify_resume(regs); + rseq_handle_notify_resume(regs); } user_enter(); diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index bd06a3ccda31..2ea575cb3401 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -244,6 +244,7 @@ cpu-as-$(CONFIG_4xx) += -Wa,-m405 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) cpu-as-$(CONFIG_E200) += -Wa,-me200 cpu-as-$(CONFIG_PPC_BOOK3S_64) += -Wa,-mpower4 +cpu-as-$(CONFIG_PPC_E500MC) += $(call as-option,-Wa$(comma)-me500mc) KBUILD_AFLAGS += $(cpu-as-y) KBUILD_CFLAGS += $(cpu-as-y) diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h index 6a6673907e45..e4633803fe43 100644 --- a/arch/powerpc/include/asm/book3s/32/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h @@ -108,6 +108,7 @@ static inline void pgtable_free(void *table, unsigned index_size) } #define check_pgt_cache() do { } while (0) +#define get_hugepd_cache_index(x) (x) #ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h index af5f2baac80f..a069dfcac9a9 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h @@ -49,6 +49,27 @@ static inline int hugepd_ok(hugepd_t hpd) } #define is_hugepd(hpd) (hugepd_ok(hpd)) +/* + * 16M and 16G huge page directory tables are allocated from slab cache + * + */ +#define H_16M_CACHE_INDEX (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE - 24) +#define H_16G_CACHE_INDEX \ + (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + H_PUD_INDEX_SIZE - 34) + +static inline int get_hugepd_cache_index(int index) +{ + switch (index) { + case H_16M_CACHE_INDEX: + return HTLB_16M_INDEX; + case H_16G_CACHE_INDEX: + return HTLB_16G_INDEX; + default: + BUG(); + } + /* should not reach */ +} + #else /* !CONFIG_HUGETLB_PAGE */ static inline int pmd_huge(pmd_t pmd) { return 0; } static inline int pud_huge(pud_t pud) { return 0; } diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h index fb4b3ba52339..d7ee249d6890 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h @@ -45,8 +45,17 @@ static inline int hugepd_ok(hugepd_t hpd) { return 0; } + #define is_hugepd(pdep) 0 +/* + * This should never get called + */ +static inline int get_hugepd_cache_index(int index) +{ + BUG(); +} + #else /* !CONFIG_HUGETLB_PAGE */ static inline int pmd_huge(pmd_t pmd) { return 0; } static inline int pud_huge(pud_t pud) { return 0; } diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 63cee159022b..42aafba7a308 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -287,6 +287,11 @@ enum pgtable_index { PMD_INDEX, PUD_INDEX, PGD_INDEX, + /* + * Below are used with 4k page size and hugetlb + */ + HTLB_16M_INDEX, + HTLB_16G_INDEX, }; extern unsigned long __vmalloc_start; diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h index 0f571e0ebca1..bd9ba8defd72 100644 --- a/arch/powerpc/include/asm/nmi.h +++ b/arch/powerpc/include/asm/nmi.h @@ -8,7 +8,7 @@ extern void arch_touch_nmi_watchdog(void); static inline void arch_touch_nmi_watchdog(void) {} #endif -#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_STACKTRACE) +#if defined(CONFIG_NMI_IPI) && defined(CONFIG_STACKTRACE) extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self); #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h index 1707781d2f20..9de40eb614da 100644 --- a/arch/powerpc/include/asm/nohash/32/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h @@ -109,6 +109,7 @@ static inline void pgtable_free(void *table, unsigned index_size) } #define check_pgt_cache() do { } while (0) +#define get_hugepd_cache_index(x) (x) #ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h index 0e693f322cb2..e2d62d033708 100644 --- a/arch/powerpc/include/asm/nohash/64/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h @@ -141,6 +141,7 @@ static inline void pgtable_free(void *table, int shift) } } +#define get_hugepd_cache_index(x) (x) #ifdef CONFIG_SMP static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) { diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 4be1c0de9406..96dd3d871986 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -711,7 +711,8 @@ static __init void cpufeatures_cpu_quirks(void) cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST; cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG; cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; - } else /* DD2.1 and up have DD2_1 */ + } else if ((version & 0xffff0000) == 0x004e0000) + /* DD2.1 and up have DD2_1 */ cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1; if ((version & 0xffff0000) == 0x004e0000) { diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 62b1a40d8957..40b44bb53a4e 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -701,11 +701,18 @@ static int ppc_panic_event(struct notifier_block *this, unsigned long event, void *ptr) { /* + * panic does a local_irq_disable, but we really + * want interrupts to be hard disabled. + */ + hard_irq_disable(); + + /* * If firmware-assisted dump has been registered then trigger * firmware-assisted dump and let firmware handle everything else. */ crash_fadump(NULL, ptr); - ppc_md.panic(ptr); /* May not return */ + if (ppc_md.panic) + ppc_md.panic(ptr); /* May not return */ return NOTIFY_DONE; } @@ -716,7 +723,8 @@ static struct notifier_block ppc_panic_block = { void __init setup_panic(void) { - if (!ppc_md.panic) + /* PPC64 always does a hard irq disable in its panic handler */ + if (!IS_ENABLED(CONFIG_PPC64) && !ppc_md.panic) return; atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 7a7ce8ad455e..225bc5f91049 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -387,6 +387,14 @@ void early_setup_secondary(void) #endif /* CONFIG_SMP */ +void panic_smp_self_stop(void) +{ + hard_irq_disable(); + spin_begin(); + while (1) + spin_cpu_relax(); +} + #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE) static bool use_spinloop(void) { diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 5eadfffabe35..4794d6b4f4d2 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -600,9 +600,6 @@ static void nmi_stop_this_cpu(struct pt_regs *regs) nmi_ipi_busy_count--; nmi_ipi_unlock(); - /* Remove this CPU */ - set_cpu_online(smp_processor_id(), false); - spin_begin(); while (1) spin_cpu_relax(); @@ -617,9 +614,6 @@ void smp_send_stop(void) static void stop_this_cpu(void *dummy) { - /* Remove this CPU */ - set_cpu_online(smp_processor_id(), false); - hard_irq_disable(); spin_begin(); while (1) diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index 07e97f289c52..e2c50b55138f 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -196,7 +196,7 @@ save_stack_trace_tsk_reliable(struct task_struct *tsk, EXPORT_SYMBOL_GPL(save_stack_trace_tsk_reliable); #endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */ -#ifdef CONFIG_PPC_BOOK3S_64 +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) static void handle_backtrace_ipi(struct pt_regs *regs) { nmi_cpu_backtrace(regs); @@ -242,4 +242,4 @@ void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) { nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace_ipi); } -#endif /* CONFIG_PPC64 */ +#endif /* defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_NMI_IPI) */ diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 7c5f479c5c00..8a9a49c13865 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -337,7 +337,8 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif if (shift >= pdshift) hugepd_free(tlb, hugepte); else - pgtable_free_tlb(tlb, hugepte, pdshift - shift); + pgtable_free_tlb(tlb, hugepte, + get_hugepd_cache_index(pdshift - shift)); } static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index c1f4ca45c93a..4afbfbb64bfd 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -409,6 +409,18 @@ static inline void pgtable_free(void *table, int index) case PUD_INDEX: kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), table); break; +#if defined(CONFIG_PPC_4K_PAGES) && defined(CONFIG_HUGETLB_PAGE) + /* 16M hugepd directory at pud level */ + case HTLB_16M_INDEX: + BUILD_BUG_ON(H_16M_CACHE_INDEX <= 0); + kmem_cache_free(PGT_CACHE(H_16M_CACHE_INDEX), table); + break; + /* 16G hugepd directory at the pgd level */ + case HTLB_16G_INDEX: + BUILD_BUG_ON(H_16G_CACHE_INDEX <= 0); + kmem_cache_free(PGT_CACHE(H_16G_CACHE_INDEX), table); + break; +#endif /* We don't free pgd table via RCU callback */ default: BUG(); diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 67a6e86d3e7e..1135b43a597c 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -689,22 +689,17 @@ EXPORT_SYMBOL(radix__flush_tlb_kernel_range); static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33; static unsigned long tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2; -void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end) +static inline void __radix__flush_tlb_range(struct mm_struct *mm, + unsigned long start, unsigned long end, + bool flush_all_sizes) { - struct mm_struct *mm = vma->vm_mm; unsigned long pid; unsigned int page_shift = mmu_psize_defs[mmu_virtual_psize].shift; unsigned long page_size = 1UL << page_shift; unsigned long nr_pages = (end - start) >> page_shift; bool local, full; -#ifdef CONFIG_HUGETLB_PAGE - if (is_vm_hugetlb_page(vma)) - return radix__flush_hugetlb_tlb_range(vma, start, end); -#endif - pid = mm->context.id; if (unlikely(pid == MMU_NO_CONTEXT)) return; @@ -738,37 +733,64 @@ is_local: _tlbie_pid(pid, RIC_FLUSH_TLB); } } else { - bool hflush = false; + bool hflush = flush_all_sizes; + bool gflush = flush_all_sizes; unsigned long hstart, hend; + unsigned long gstart, gend; -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - hstart = (start + HPAGE_PMD_SIZE - 1) >> HPAGE_PMD_SHIFT; - hend = end >> HPAGE_PMD_SHIFT; - if (hstart < hend) { - hstart <<= HPAGE_PMD_SHIFT; - hend <<= HPAGE_PMD_SHIFT; + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) hflush = true; + + if (hflush) { + hstart = (start + PMD_SIZE - 1) & PMD_MASK; + hend = end & PMD_MASK; + if (hstart == hend) + hflush = false; + } + + if (gflush) { + gstart = (start + PUD_SIZE - 1) & PUD_MASK; + gend = end & PUD_MASK; + if (gstart == gend) + gflush = false; } -#endif asm volatile("ptesync": : :"memory"); if (local) { __tlbiel_va_range(start, end, pid, page_size, mmu_virtual_psize); if (hflush) __tlbiel_va_range(hstart, hend, pid, - HPAGE_PMD_SIZE, MMU_PAGE_2M); + PMD_SIZE, MMU_PAGE_2M); + if (gflush) + __tlbiel_va_range(gstart, gend, pid, + PUD_SIZE, MMU_PAGE_1G); asm volatile("ptesync": : :"memory"); } else { __tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize); if (hflush) __tlbie_va_range(hstart, hend, pid, - HPAGE_PMD_SIZE, MMU_PAGE_2M); + PMD_SIZE, MMU_PAGE_2M); + if (gflush) + __tlbie_va_range(gstart, gend, pid, + PUD_SIZE, MMU_PAGE_1G); fixup_tlbie(); asm volatile("eieio; tlbsync; ptesync": : :"memory"); } } preempt_enable(); } + +void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) + +{ +#ifdef CONFIG_HUGETLB_PAGE + if (is_vm_hugetlb_page(vma)) + return radix__flush_hugetlb_tlb_range(vma, start, end); +#endif + + __radix__flush_tlb_range(vma->vm_mm, start, end, false); +} EXPORT_SYMBOL(radix__flush_tlb_range); static int radix_get_mmu_psize(int page_size) @@ -837,6 +859,8 @@ void radix__tlb_flush(struct mmu_gather *tlb) int psize = 0; struct mm_struct *mm = tlb->mm; int page_size = tlb->page_size; + unsigned long start = tlb->start; + unsigned long end = tlb->end; /* * if page size is not something we understand, do a full mm flush @@ -847,15 +871,45 @@ void radix__tlb_flush(struct mmu_gather *tlb) */ if (tlb->fullmm) { __flush_all_mm(mm, true); +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE) + } else if (mm_tlb_flush_nested(mm)) { + /* + * If there is a concurrent invalidation that is clearing ptes, + * then it's possible this invalidation will miss one of those + * cleared ptes and miss flushing the TLB. If this invalidate + * returns before the other one flushes TLBs, that can result + * in it returning while there are still valid TLBs inside the + * range to be invalidated. + * + * See mm/memory.c:tlb_finish_mmu() for more details. + * + * The solution to this is ensure the entire range is always + * flushed here. The problem for powerpc is that the flushes + * are page size specific, so this "forced flush" would not + * do the right thing if there are a mix of page sizes in + * the range to be invalidated. So use __flush_tlb_range + * which invalidates all possible page sizes in the range. + * + * PWC flush probably is not be required because the core code + * shouldn't free page tables in this path, but accounting + * for the possibility makes us a bit more robust. + * + * need_flush_all is an uncommon case because page table + * teardown should be done with exclusive locks held (but + * after locks are dropped another invalidate could come + * in), it could be optimized further if necessary. + */ + if (!tlb->need_flush_all) + __radix__flush_tlb_range(mm, start, end, true); + else + radix__flush_all_mm(mm); +#endif } else if ( (psize = radix_get_mmu_psize(page_size)) == -1) { if (!tlb->need_flush_all) radix__flush_tlb_mm(mm); else radix__flush_all_mm(mm); } else { - unsigned long start = tlb->start; - unsigned long end = tlb->end; - if (!tlb->need_flush_all) radix__flush_tlb_range_psize(mm, start, end, psize); else @@ -1043,6 +1097,8 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm) for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) { if (sib == cpu) continue; + if (!cpu_possible(sib)) + continue; if (paca_ptrs[sib]->kvm_hstate.kvm_vcpu) flush = true; } diff --git a/arch/x86/Makefile b/arch/x86/Makefile index f0a6ea22429d..a08e82856563 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -258,11 +258,6 @@ archscripts: scripts_basic archheaders: $(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all -archprepare: -ifeq ($(CONFIG_KEXEC_FILE),y) - $(Q)$(MAKE) $(build)=arch/x86/purgatory arch/x86/purgatory/kexec-purgatory.c -endif - ### # Kernel objects @@ -327,7 +322,6 @@ archclean: $(Q)rm -rf $(objtree)/arch/x86_64 $(Q)$(MAKE) $(clean)=$(boot) $(Q)$(MAKE) $(clean)=arch/x86/tools - $(Q)$(MAKE) $(clean)=arch/x86/purgatory define archhelp echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)' diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index a8a8642d2b0b..e57665b4ba1c 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -118,7 +118,7 @@ __setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom) void *romimage; status = efi_call_proto(efi_pci_io_protocol, attributes, pci, - EfiPciIoAttributeOperationGet, 0, 0, + EfiPciIoAttributeOperationGet, 0ULL, &attributes); if (status != EFI_SUCCESS) return status; diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 042b5e892ed1..14de0432d288 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -38,7 +38,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, { unsigned long mask; - asm ("cmp %1,%2; sbb %0,%0;" + asm volatile ("cmp %1,%2; sbb %0,%0;" :"=r" (mask) :"g"(size),"r" (index) :"cc"); diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 425e6b8b9547..6aa8499e1f62 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -114,6 +114,7 @@ #define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f #define VMX_MISC_SAVE_EFER_LMA 0x00000020 #define VMX_MISC_ACTIVITY_HLT 0x00000040 +#define VMX_MISC_ZERO_LEN_INS 0x40000000 /* VMFUNC functions */ #define VMX_VMFUNC_EPTP_SWITCHING 0x00000001 @@ -351,11 +352,13 @@ enum vmcs_field { #define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK #define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */ +#define INTR_TYPE_RESERVED (1 << 8) /* reserved */ #define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */ #define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */ #define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */ #define INTR_TYPE_PRIV_SW_EXCEPTION (5 << 8) /* ICE breakpoint - undocumented */ #define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */ +#define INTR_TYPE_OTHER_EVENT (7 << 8) /* other event */ /* GUEST_INTERRUPTIBILITY_INFO flags. */ #define GUEST_INTR_STATE_STI 0x00000001 diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index efaf2d4f9c3c..d492752f79e1 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -26,6 +26,7 @@ #include <linux/delay.h> #include <linux/crash_dump.h> #include <linux/reboot.h> +#include <linux/memory.h> #include <asm/uv/uv_mmrs.h> #include <asm/uv/uv_hub.h> @@ -392,6 +393,51 @@ extern int uv_hub_info_version(void) } EXPORT_SYMBOL(uv_hub_info_version); +/* Default UV memory block size is 2GB */ +static unsigned long mem_block_size = (2UL << 30); + +/* Kernel parameter to specify UV mem block size */ +static int parse_mem_block_size(char *ptr) +{ + unsigned long size = memparse(ptr, NULL); + + /* Size will be rounded down by set_block_size() below */ + mem_block_size = size; + return 0; +} +early_param("uv_memblksize", parse_mem_block_size); + +static __init int adj_blksize(u32 lgre) +{ + unsigned long base = (unsigned long)lgre << UV_GAM_RANGE_SHFT; + unsigned long size; + + for (size = mem_block_size; size > MIN_MEMORY_BLOCK_SIZE; size >>= 1) + if (IS_ALIGNED(base, size)) + break; + + if (size >= mem_block_size) + return 0; + + mem_block_size = size; + return 1; +} + +static __init void set_block_size(void) +{ + unsigned int order = ffs(mem_block_size); + + if (order) { + /* adjust for ffs return of 1..64 */ + set_memory_block_size_order(order - 1); + pr_info("UV: mem_block_size set to 0x%lx\n", mem_block_size); + } else { + /* bad or zero value, default to 1UL << 31 (2GB) */ + pr_err("UV: mem_block_size error with 0x%lx\n", mem_block_size); + set_memory_block_size_order(31); + } +} + /* Build GAM range lookup table: */ static __init void build_uv_gr_table(void) { @@ -1180,23 +1226,30 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) << UV_GAM_RANGE_SHFT); int order = 0; char suffix[] = " KMGTPE"; + int flag = ' '; while (size > 9999 && order < sizeof(suffix)) { size /= 1024; order++; } + /* adjust max block size to current range start */ + if (gre->type == 1 || gre->type == 2) + if (adj_blksize(lgre)) + flag = '*'; + if (!index) { pr_info("UV: GAM Range Table...\n"); - pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN"); + pr_info("UV: # %20s %14s %6s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN"); } - pr_info("UV: %2d: 0x%014lx-0x%014lx %5lu%c %3d %04x %02x %02x\n", + pr_info("UV: %2d: 0x%014lx-0x%014lx%c %5lu%c %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, - size, suffix[order], + flag, size, suffix[order], gre->type, gre->nasid, gre->sockid, gre->pnode); + /* update to next range start */ lgre = gre->limit; if (sock_min > gre->sockid) sock_min = gre->sockid; @@ -1427,6 +1480,7 @@ static void __init uv_system_init_hub(void) build_socket_tables(); build_uv_gr_table(); + set_block_size(); uv_init_hub_info(&hub_info); uv_possible_blades = num_possible_nodes(); if (!_node_to_pnode) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index cd0fda1fff6d..404df26b7de8 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -27,6 +27,7 @@ #include <asm/pgtable.h> #include <asm/set_memory.h> #include <asm/intel-family.h> +#include <asm/hypervisor.h> static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); @@ -664,6 +665,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr if (boot_cpu_has(X86_FEATURE_PTI)) return sprintf(buf, "Mitigation: PTI\n"); + if (hypervisor_is_type(X86_HYPER_XEN_PV)) + return sprintf(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); + break; case X86_BUG_SPECTRE_V1: diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 38354c66df81..0c5fcbd998cf 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -671,7 +671,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id) num_sharing_cache = ((eax >> 14) & 0xfff) + 1; if (num_sharing_cache) { - int bits = get_count_order(num_sharing_cache) - 1; + int bits = get_count_order(num_sharing_cache); per_cpu(cpu_llc_id, cpu) = c->apicid >> bits; } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0df7151cfef4..eb4cb3efd20e 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1,3 +1,6 @@ +/* cpu_feature_enabled() cannot be used this early */ +#define USE_EARLY_PGTABLE_L5 + #include <linux/bootmem.h> #include <linux/linkage.h> #include <linux/bitops.h> diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 5bbd06f38ff6..f34d89c01edc 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -160,6 +160,11 @@ static struct severity { SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR), USER ), + MCESEV( + PANIC, "Data load in unrecoverable area of kernel", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), + KERNEL + ), #endif MCESEV( PANIC, "Action required: unknown MCACOD", diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index e4cf6ff1c2e1..c102ad51025e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -772,23 +772,25 @@ EXPORT_SYMBOL_GPL(machine_check_poll); static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, struct pt_regs *regs) { - int i, ret = 0; char *tmp; + int i; for (i = 0; i < mca_cfg.banks; i++) { m->status = mce_rdmsrl(msr_ops.status(i)); - if (m->status & MCI_STATUS_VAL) { - __set_bit(i, validp); - if (quirk_no_way_out) - quirk_no_way_out(i, m, regs); - } + if (!(m->status & MCI_STATUS_VAL)) + continue; + + __set_bit(i, validp); + if (quirk_no_way_out) + quirk_no_way_out(i, m, regs); if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { + mce_read_aux(m, i); *msg = tmp; - ret = 1; + return 1; } } - return ret; + return 0; } /* @@ -1205,13 +1207,18 @@ void do_machine_check(struct pt_regs *regs, long error_code) lmce = m.mcgstatus & MCG_STATUS_LMCES; /* + * Local machine check may already know that we have to panic. + * Broadcast machine check begins rendezvous in mce_start() * Go through all banks in exclusion of the other CPUs. This way we * don't report duplicated events on shared banks because the first one - * to see it will clear it. If this is a Local MCE, then no need to - * perform rendezvous. + * to see it will clear it. */ - if (!lmce) + if (lmce) { + if (no_way_out) + mce_panic("Fatal local machine check", &m, msg); + } else { order = mce_start(&no_way_out); + } for (i = 0; i < cfg->banks; i++) { __clear_bit(i, toclear); @@ -1287,12 +1294,17 @@ void do_machine_check(struct pt_regs *regs, long error_code) no_way_out = worst >= MCE_PANIC_SEVERITY; } else { /* - * Local MCE skipped calling mce_reign() - * If we found a fatal error, we need to panic here. + * If there was a fatal machine check we should have + * already called mce_panic earlier in this function. + * Since we re-read the banks, we might have found + * something new. Check again to see if we found a + * fatal error. We call "mce_severity()" again to + * make sure we have the right "msg". */ - if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) - mce_panic("Machine check from unknown source", - NULL, NULL); + if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) { + mce_severity(&m, cfg->tolerant, &msg, true); + mce_panic("Local fatal machine check!", &m, msg); + } } /* diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 1c2cfa0644aa..97ccf4c3b45b 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -190,8 +190,11 @@ static void save_microcode_patch(void *data, unsigned int size) p = memdup_patch(data, size); if (!p) pr_err("Error allocating buffer %p\n", data); - else + else { list_replace(&iter->plist, &p->plist); + kfree(iter->data); + kfree(iter); + } } } diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index a21d6ace648e..8047379e575a 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -44,7 +44,7 @@ static unsigned int __initdata next_early_pgt; pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); #ifdef CONFIG_X86_5LEVEL -unsigned int __pgtable_l5_enabled __initdata; +unsigned int __pgtable_l5_enabled __ro_after_init; unsigned int pgdir_shift __ro_after_init = 39; EXPORT_SYMBOL(pgdir_shift); unsigned int ptrs_per_p4d __ro_after_init = 1; diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 697a4ce04308..736348ead421 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -645,12 +645,19 @@ static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev) /* Skylake */ static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev) { - u32 capid0; + u32 capid0, capid5; pci_read_config_dword(pdev, 0x84, &capid0); + pci_read_config_dword(pdev, 0x98, &capid5); - if ((capid0 & 0xc0) == 0xc0) + /* + * CAPID0{7:6} indicate whether this is an advanced RAS SKU + * CAPID5{8:5} indicate that various NVDIMM usage modes are + * enabled, so memory machine check recovery is also enabled. + */ + if ((capid0 & 0xc0) == 0xc0 || (capid5 & 0x1e0)) static_branch_inc(&mcsafe_key); + } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x0ec3, quirk_intel_brickland_xeon_ras_cap); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ras_cap); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index a535dd64de63..e6db475164ed 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -835,16 +835,18 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" : "simd exception"; - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP) - return; cond_local_irq_enable(regs); if (!user_mode(regs)) { - if (!fixup_exception(regs, trapnr)) { - task->thread.error_code = error_code; - task->thread.trap_nr = trapnr; + if (fixup_exception(regs, trapnr)) + return; + + task->thread.error_code = error_code; + task->thread.trap_nr = trapnr; + + if (notify_die(DIE_TRAP, str, regs, error_code, + trapnr, SIGFPE) != NOTIFY_STOP) die(str, regs, error_code); - } return; } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 559a12b6184d..1689f433f3a0 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1705,6 +1705,17 @@ static inline bool nested_cpu_has_vmwrite_any_field(struct kvm_vcpu *vcpu) MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS; } +static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu) +{ + return to_vmx(vcpu)->nested.msrs.misc_low & VMX_MISC_ZERO_LEN_INS; +} + +static inline bool nested_cpu_supports_monitor_trap_flag(struct kvm_vcpu *vcpu) +{ + return to_vmx(vcpu)->nested.msrs.procbased_ctls_high & + CPU_BASED_MONITOR_TRAP_FLAG; +} + static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit) { return vmcs12->cpu_based_vm_exec_control & bit; @@ -11620,6 +11631,62 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) !nested_cr3_valid(vcpu, vmcs12->host_cr3)) return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD; + /* + * From the Intel SDM, volume 3: + * Fields relevant to VM-entry event injection must be set properly. + * These fields are the VM-entry interruption-information field, the + * VM-entry exception error code, and the VM-entry instruction length. + */ + if (vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) { + u32 intr_info = vmcs12->vm_entry_intr_info_field; + u8 vector = intr_info & INTR_INFO_VECTOR_MASK; + u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK; + bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK; + bool should_have_error_code; + bool urg = nested_cpu_has2(vmcs12, + SECONDARY_EXEC_UNRESTRICTED_GUEST); + bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE; + + /* VM-entry interruption-info field: interruption type */ + if (intr_type == INTR_TYPE_RESERVED || + (intr_type == INTR_TYPE_OTHER_EVENT && + !nested_cpu_supports_monitor_trap_flag(vcpu))) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry interruption-info field: vector */ + if ((intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) || + (intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) || + (intr_type == INTR_TYPE_OTHER_EVENT && vector != 0)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry interruption-info field: deliver error code */ + should_have_error_code = + intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode && + x86_exception_has_error_code(vector); + if (has_error_code != should_have_error_code) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry exception error code */ + if (has_error_code && + vmcs12->vm_entry_exception_error_code & GENMASK(31, 15)) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry interruption-info field: reserved bits */ + if (intr_info & INTR_INFO_RESVD_BITS_MASK) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + + /* VM-entry instruction length */ + switch (intr_type) { + case INTR_TYPE_SOFT_EXCEPTION: + case INTR_TYPE_SOFT_INTR: + case INTR_TYPE_PRIV_SW_EXCEPTION: + if ((vmcs12->vm_entry_instruction_len > 15) || + (vmcs12->vm_entry_instruction_len == 0 && + !nested_cpu_has_zero_length_injection(vcpu))) + return VMXERR_ENTRY_INVALID_CONTROL_FIELD; + } + } + return 0; } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 331993c49dae..257f27620bc2 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -110,6 +110,15 @@ static inline bool is_la57_mode(struct kvm_vcpu *vcpu) #endif } +static inline bool x86_exception_has_error_code(unsigned int vector) +{ + static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) | + BIT(NP_VECTOR) | BIT(SS_VECTOR) | BIT(GP_VECTOR) | + BIT(PF_VECTOR) | BIT(AC_VECTOR); + + return (1U << vector) & exception_has_error_code; +} + static inline bool mmu_is_nested(struct kvm_vcpu *vcpu) { return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 045f492d5f68..a688617c727e 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1350,16 +1350,28 @@ int kern_addr_valid(unsigned long addr) /* Amount of ram needed to start using large blocks */ #define MEM_SIZE_FOR_LARGE_BLOCK (64UL << 30) +/* Adjustable memory block size */ +static unsigned long set_memory_block_size; +int __init set_memory_block_size_order(unsigned int order) +{ + unsigned long size = 1UL << order; + + if (size > MEM_SIZE_FOR_LARGE_BLOCK || size < MIN_MEMORY_BLOCK_SIZE) + return -EINVAL; + + set_memory_block_size = size; + return 0; +} + static unsigned long probe_memory_block_size(void) { unsigned long boot_mem_end = max_pfn << PAGE_SHIFT; unsigned long bz; - /* If this is UV system, always set 2G block size */ - if (is_uv_system()) { - bz = MAX_BLOCK_SIZE; + /* If memory block size has been set, then use it */ + bz = set_memory_block_size; + if (bz) goto done; - } /* Use regular block if RAM is smaller than MEM_SIZE_FOR_LARGE_BLOCK */ if (boot_mem_end < MEM_SIZE_FOR_LARGE_BLOCK) { diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c9081c6671f0..3b5318505c69 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -65,6 +65,13 @@ __read_mostly int xen_have_vector_callback; EXPORT_SYMBOL_GPL(xen_have_vector_callback); /* + * NB: needs to live in .data because it's used by xen_prepare_pvh which runs + * before clearing the bss. + */ +uint32_t xen_start_flags __attribute__((section(".data"))) = 0; +EXPORT_SYMBOL(xen_start_flags); + +/* * Point at some empty memory to start with. We map the real shared_info * page as soon as fixmap is up and running. */ diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 357969a3697c..8d4e2e1ae60b 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1203,6 +1203,7 @@ asmlinkage __visible void __init xen_start_kernel(void) return; xen_domain_type = XEN_PV_DOMAIN; + xen_start_flags = xen_start_info->flags; xen_setup_features(); diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index aa1c6a6831a9..c85d1a88f476 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -97,6 +97,7 @@ void __init xen_prepare_pvh(void) } xen_pvh = 1; + xen_start_flags = pvh_start_info.flags; msr = cpuid_ebx(xen_cpuid_base() + 2); pfn = __pa(hypercall_page); diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 2e20ae2fa2d6..e3b18ad49889 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -32,6 +32,7 @@ #include <xen/interface/vcpu.h> #include <xen/interface/xenpmu.h> +#include <asm/spec-ctrl.h> #include <asm/xen/interface.h> #include <asm/xen/hypercall.h> @@ -70,6 +71,8 @@ static void cpu_bringup(void) cpu_data(cpu).x86_max_cores = 1; set_cpu_sibling_map(cpu); + speculative_store_bypass_ht_init(); + xen_setup_cpu_clockevents(); notify_cpu_starting(cpu); @@ -250,6 +253,8 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus) } set_cpu_sibling_map(0); + speculative_store_bypass_ht_init(); + xen_pmu_init(0); if (xen_smp_intr_init(0) || xen_smp_intr_init_pv(0)) |