diff options
Diffstat (limited to 'arch')
29 files changed, 317 insertions, 135 deletions
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 17fd1ed700cc..9152782444b5 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -67,7 +67,22 @@ sr r5, [ARC_REG_LPB_CTRL] 1: #endif /* CONFIG_ARC_LPB_DISABLE */ -#endif + + /* On HSDK, CCMs need to remapped super early */ +#ifdef CONFIG_ARC_SOC_HSDK + mov r6, 0x60000000 + lr r5, [ARC_REG_ICCM_BUILD] + breq r5, 0, 1f + sr r6, [ARC_REG_AUX_ICCM] +1: + lr r5, [ARC_REG_DCCM_BUILD] + breq r5, 0, 2f + sr r6, [ARC_REG_AUX_DCCM] +2: +#endif /* CONFIG_ARC_SOC_HSDK */ + +#endif /* CONFIG_ISA_ARCV2 */ + ; Config DSP_CTRL properly, so kernel may use integer multiply, ; multiply-accumulate, and divide operations DSP_EARLY_INIT diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index feba91c9d969..b23986f98450 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -112,7 +112,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, int (*consumer_fn) (unsigned int, void *), void *arg) { #ifdef CONFIG_ARC_DW2_UNWIND - int ret = 0; + int ret = 0, cnt = 0; unsigned int address; struct unwind_frame_info frame_info; @@ -132,6 +132,11 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, break; frame_info.regs.r63 = frame_info.regs.r31; + + if (cnt++ > 128) { + printk("unwinder looping too long, aborting !\n"); + return 0; + } } return address; /* return the last address it saw */ diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c index 0b63fc095b99..b3ea1fa11f87 100644 --- a/arch/arc/plat-hsdk/platform.c +++ b/arch/arc/plat-hsdk/platform.c @@ -17,22 +17,6 @@ int arc_hsdk_axi_dmac_coherent __section(".data") = 0; #define ARC_CCM_UNUSED_ADDR 0x60000000 -static void __init hsdk_init_per_cpu(unsigned int cpu) -{ - /* - * By default ICCM is mapped to 0x7z while this area is used for - * kernel virtual mappings, so move it to currently unused area. - */ - if (cpuinfo_arc700[cpu].iccm.sz) - write_aux_reg(ARC_REG_AUX_ICCM, ARC_CCM_UNUSED_ADDR); - - /* - * By default DCCM is mapped to 0x8z while this area is used by kernel, - * so move it to currently unused area. - */ - if (cpuinfo_arc700[cpu].dccm.sz) - write_aux_reg(ARC_REG_AUX_DCCM, ARC_CCM_UNUSED_ADDR); -} #define ARC_PERIPHERAL_BASE 0xf0000000 #define CREG_BASE (ARC_PERIPHERAL_BASE + 0x1000) @@ -339,5 +323,4 @@ static const char *hsdk_compat[] __initconst = { MACHINE_START(SIMULATION, "hsdk") .dt_compat = hsdk_compat, .init_early = hsdk_init_early, - .init_per_cpu = hsdk_init_per_cpu, MACHINE_END diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index d57112a276f5..c23dbf8bebee 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -354,8 +354,8 @@ static void __init free_highpages(void) /* set highmem page free */ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &range_start, &range_end, NULL) { - unsigned long start = PHYS_PFN(range_start); - unsigned long end = PHYS_PFN(range_end); + unsigned long start = PFN_UP(range_start); + unsigned long end = PFN_DOWN(range_end); /* Ignore complete lowmem entries */ if (end <= max_low) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 1d466addb078..1515f6f153a0 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1002,7 +1002,7 @@ config NUMA config NODES_SHIFT int "Maximum NUMA Nodes (as a power of 2)" range 1 10 - default "2" + default "4" depends on NEED_MULTIPLE_NODES help Specify the maximum number of NUMA Nodes available on the target diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h index e3d47b52161d..ec7720dbe2c8 100644 --- a/arch/arm64/include/asm/brk-imm.h +++ b/arch/arm64/include/asm/brk-imm.h @@ -10,6 +10,7 @@ * #imm16 values used for BRK instruction generation * 0x004: for installing kprobes * 0x005: for installing uprobes + * 0x006: for kprobe software single-step * Allowed values for kgdb are 0x400 - 0x7ff * 0x100: for triggering a fault on purpose (reserved) * 0x400: for dynamic BRK instruction @@ -19,6 +20,7 @@ */ #define KPROBES_BRK_IMM 0x004 #define UPROBES_BRK_IMM 0x005 +#define KPROBES_BRK_SS_IMM 0x006 #define FAULT_BRK_IMM 0x100 #define KGDB_DYN_DBG_BRK_IMM 0x400 #define KGDB_COMPILED_DBG_BRK_IMM 0x401 diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index 0b298f48f5bf..657c921fd784 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -53,6 +53,7 @@ /* kprobes BRK opcodes with ESR encoding */ #define BRK64_OPCODE_KPROBES (AARCH64_BREAK_MON | (KPROBES_BRK_IMM << 5)) +#define BRK64_OPCODE_KPROBES_SS (AARCH64_BREAK_MON | (KPROBES_BRK_SS_IMM << 5)) /* uprobes BRK opcodes with ESR encoding */ #define BRK64_OPCODE_UPROBES (AARCH64_BREAK_MON | (UPROBES_BRK_IMM << 5)) diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h index 97e511d645a2..8699ce30f587 100644 --- a/arch/arm64/include/asm/kprobes.h +++ b/arch/arm64/include/asm/kprobes.h @@ -16,7 +16,7 @@ #include <linux/percpu.h> #define __ARCH_WANT_KPROBES_INSN_SLOT -#define MAX_INSN_SIZE 1 +#define MAX_INSN_SIZE 2 #define flush_insn_slot(p) do { } while (0) #define kretprobe_blacklist_size 0 diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c index af9987c154ca..66adee8b5fc8 100644 --- a/arch/arm64/kernel/kexec_image.c +++ b/arch/arm64/kernel/kexec_image.c @@ -43,7 +43,7 @@ static void *image_load(struct kimage *image, u64 flags, value; bool be_image, be_kernel; struct kexec_buf kbuf; - unsigned long text_offset; + unsigned long text_offset, kernel_segment_number; struct kexec_segment *kernel_segment; int ret; @@ -88,11 +88,37 @@ static void *image_load(struct kimage *image, /* Adjust kernel segment with TEXT_OFFSET */ kbuf.memsz += text_offset; - ret = kexec_add_buffer(&kbuf); - if (ret) + kernel_segment_number = image->nr_segments; + + /* + * The location of the kernel segment may make it impossible to satisfy + * the other segment requirements, so we try repeatedly to find a + * location that will work. + */ + while ((ret = kexec_add_buffer(&kbuf)) == 0) { + /* Try to load additional data */ + kernel_segment = &image->segment[kernel_segment_number]; + ret = load_other_segments(image, kernel_segment->mem, + kernel_segment->memsz, initrd, + initrd_len, cmdline); + if (!ret) + break; + + /* + * We couldn't find space for the other segments; erase the + * kernel segment and try the next available hole. + */ + image->nr_segments -= 1; + kbuf.buf_min = kernel_segment->mem + kernel_segment->memsz; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + } + + if (ret) { + pr_err("Could not find any suitable kernel location!"); return ERR_PTR(ret); + } - kernel_segment = &image->segment[image->nr_segments - 1]; + kernel_segment = &image->segment[kernel_segment_number]; kernel_segment->mem += text_offset; kernel_segment->memsz -= text_offset; image->start = kernel_segment->mem; @@ -101,12 +127,7 @@ static void *image_load(struct kimage *image, kernel_segment->mem, kbuf.bufsz, kernel_segment->memsz); - /* Load additional data */ - ret = load_other_segments(image, - kernel_segment->mem, kernel_segment->memsz, - initrd, initrd_len, cmdline); - - return ERR_PTR(ret); + return 0; } #ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 5b0e67b93cdc..03210f644790 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -240,6 +240,11 @@ static int prepare_elf_headers(void **addr, unsigned long *sz) return ret; } +/* + * Tries to add the initrd and DTB to the image. If it is not possible to find + * valid locations, this function will undo changes to the image and return non + * zero. + */ int load_other_segments(struct kimage *image, unsigned long kernel_load_addr, unsigned long kernel_size, @@ -248,7 +253,8 @@ int load_other_segments(struct kimage *image, { struct kexec_buf kbuf; void *headers, *dtb = NULL; - unsigned long headers_sz, initrd_load_addr = 0, dtb_len; + unsigned long headers_sz, initrd_load_addr = 0, dtb_len, + orig_segments = image->nr_segments; int ret = 0; kbuf.image = image; @@ -334,6 +340,7 @@ int load_other_segments(struct kimage *image, return 0; out_err: + image->nr_segments = orig_segments; vfree(dtb); return ret; } diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index deba738142ed..f11a1a1f7026 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -36,25 +36,16 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); static void __kprobes post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *); -static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode) -{ - void *addrs[1]; - u32 insns[1]; - - addrs[0] = addr; - insns[0] = opcode; - - return aarch64_insn_patch_text(addrs, insns, 1); -} - static void __kprobes arch_prepare_ss_slot(struct kprobe *p) { + kprobe_opcode_t *addr = p->ainsn.api.insn; + void *addrs[] = {addr, addr + 1}; + u32 insns[] = {p->opcode, BRK64_OPCODE_KPROBES_SS}; + /* prepare insn slot */ - patch_text(p->ainsn.api.insn, p->opcode); + aarch64_insn_patch_text(addrs, insns, 2); - flush_icache_range((uintptr_t) (p->ainsn.api.insn), - (uintptr_t) (p->ainsn.api.insn) + - MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + flush_icache_range((uintptr_t)addr, (uintptr_t)(addr + MAX_INSN_SIZE)); /* * Needs restoring of return address after stepping xol. @@ -128,13 +119,18 @@ void *alloc_insn_page(void) /* arm kprobe: install breakpoint in text */ void __kprobes arch_arm_kprobe(struct kprobe *p) { - patch_text(p->addr, BRK64_OPCODE_KPROBES); + void *addr = p->addr; + u32 insn = BRK64_OPCODE_KPROBES; + + aarch64_insn_patch_text(&addr, &insn, 1); } /* disarm kprobe: remove breakpoint from text */ void __kprobes arch_disarm_kprobe(struct kprobe *p) { - patch_text(p->addr, p->opcode); + void *addr = p->addr; + + aarch64_insn_patch_text(&addr, &p->opcode, 1); } void __kprobes arch_remove_kprobe(struct kprobe *p) @@ -163,20 +159,15 @@ static void __kprobes set_current_kprobe(struct kprobe *p) } /* - * Interrupts need to be disabled before single-step mode is set, and not - * reenabled until after single-step mode ends. - * Without disabling interrupt on local CPU, there is a chance of - * interrupt occurrence in the period of exception return and start of - * out-of-line single-step, that result in wrongly single stepping - * into the interrupt handler. + * Mask all of DAIF while executing the instruction out-of-line, to keep things + * simple and avoid nesting exceptions. Interrupts do have to be disabled since + * the kprobe state is per-CPU and doesn't get migrated. */ static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb, struct pt_regs *regs) { kcb->saved_irqflag = regs->pstate & DAIF_MASK; - regs->pstate |= PSR_I_BIT; - /* Unmask PSTATE.D for enabling software step exceptions. */ - regs->pstate &= ~PSR_D_BIT; + regs->pstate |= DAIF_MASK; } static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb, @@ -219,10 +210,7 @@ static void __kprobes setup_singlestep(struct kprobe *p, slot = (unsigned long)p->ainsn.api.insn; set_ss_context(kcb, slot); /* mark pending ss */ - - /* IRQs and single stepping do not mix well. */ kprobes_save_local_irqflag(kcb, regs); - kernel_enable_single_step(regs); instruction_pointer_set(regs, slot); } else { /* insn simulation */ @@ -273,12 +261,8 @@ post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs) } /* call post handler */ kcb->kprobe_status = KPROBE_HIT_SSDONE; - if (cur->post_handler) { - /* post_handler can hit breakpoint and single step - * again, so we enable D-flag for recursive exception. - */ + if (cur->post_handler) cur->post_handler(cur, regs, 0); - } reset_current_kprobe(); } @@ -302,8 +286,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr) if (!instruction_pointer(regs)) BUG(); - kernel_disable_single_step(); - if (kcb->kprobe_status == KPROBE_REENTER) restore_previous_kprobe(kcb); else @@ -365,10 +347,6 @@ static void __kprobes kprobe_handler(struct pt_regs *regs) * pre-handler and it returned non-zero, it will * modify the execution path and no need to single * stepping. Let's just reset current kprobe and exit. - * - * pre_handler can hit a breakpoint and can step thru - * before return, keep PSTATE D-flag enabled until - * pre_handler return back. */ if (!p->pre_handler || !p->pre_handler(p, regs)) { setup_singlestep(p, regs, kcb, 0); @@ -399,7 +377,7 @@ kprobe_ss_hit(struct kprobe_ctlblk *kcb, unsigned long addr) } static int __kprobes -kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr) +kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); int retval; @@ -409,16 +387,15 @@ kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr) if (retval == DBG_HOOK_HANDLED) { kprobes_restore_local_irqflag(kcb, regs); - kernel_disable_single_step(); - post_kprobe_handler(kcb, regs); } return retval; } -static struct step_hook kprobes_step_hook = { - .fn = kprobe_single_step_handler, +static struct break_hook kprobes_break_ss_hook = { + .imm = KPROBES_BRK_SS_IMM, + .fn = kprobe_breakpoint_ss_handler, }; static int __kprobes @@ -486,7 +463,7 @@ int __kprobes arch_trampoline_kprobe(struct kprobe *p) int __init arch_init_kprobes(void) { register_kernel_break_hook(&kprobes_break_hook); - register_kernel_step_hook(&kprobes_step_hook); + register_kernel_break_hook(&kprobes_break_ss_hook); return 0; } diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 0784bf3caf43..a4d3c578fbd8 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -93,9 +93,10 @@ CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y CONFIG_CMA_DEBUG=y CONFIG_CMA_DEBUGFS=y +CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y CONFIG_ZSWAP=y -CONFIG_ZSMALLOC=m +CONFIG_ZSMALLOC=y CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y @@ -378,7 +379,6 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m -# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y # CONFIG_PCIEASPM is not set CONFIG_PCI_DEBUG=y @@ -386,7 +386,7 @@ CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=y -CONFIG_ZRAM=m +CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m @@ -689,6 +689,7 @@ CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_SM2=m CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CHACHA20POLY1305=m @@ -709,7 +710,6 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA3=m -CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m @@ -753,6 +753,7 @@ CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_CRC32_S390=y +CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_CORDIC=m CONFIG_CRC32_SELFTEST=y CONFIG_CRC4=m @@ -829,6 +830,7 @@ CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m CONFIG_FAULT_INJECTION=y CONFIG_FAILSLAB=y CONFIG_FAIL_PAGE_ALLOC=y +CONFIG_FAULT_INJECTION_USERCOPY=y CONFIG_FAIL_MAKE_REQUEST=y CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 905bc8c4cfaf..17d5df2c1eff 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -87,9 +87,10 @@ CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y +CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y CONFIG_ZSWAP=y -CONFIG_ZSMALLOC=m +CONFIG_ZSMALLOC=y CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y @@ -371,7 +372,6 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m -# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y # CONFIG_PCIEASPM is not set CONFIG_HOTPLUG_PCI=y @@ -379,7 +379,7 @@ CONFIG_HOTPLUG_PCI_S390=y CONFIG_UEVENT_HELPER=y CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=y -CONFIG_ZRAM=m +CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m @@ -680,6 +680,7 @@ CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_SM2=m CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CHACHA20POLY1305=m @@ -701,7 +702,6 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA3=m -CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m @@ -745,6 +745,7 @@ CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_CRC32_S390=y +CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_CORDIC=m CONFIG_PRIME_NUMBERS=m CONFIG_CRC4=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 8f67c55625f9..a302630341ef 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -17,11 +17,11 @@ CONFIG_HZ_100=y # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set CONFIG_CRASH_DUMP=y -# CONFIG_SECCOMP is not set # CONFIG_PFAULT is not set # CONFIG_S390_HYPFS_FS is not set # CONFIG_VIRTUALIZATION is not set # CONFIG_S390_GUEST is not set +# CONFIG_SECCOMP is not set CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 6b8d8c69b1a1..b5dbae78969b 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -692,16 +692,6 @@ static inline int pud_large(pud_t pud) return !!(pud_val(pud) & _REGION3_ENTRY_LARGE); } -static inline unsigned long pud_pfn(pud_t pud) -{ - unsigned long origin_mask; - - origin_mask = _REGION_ENTRY_ORIGIN; - if (pud_large(pud)) - origin_mask = _REGION3_ENTRY_ORIGIN_LARGE; - return (pud_val(pud) & origin_mask) >> PAGE_SHIFT; -} - #define pmd_leaf pmd_large static inline int pmd_large(pmd_t pmd) { @@ -747,16 +737,6 @@ static inline int pmd_none(pmd_t pmd) return pmd_val(pmd) == _SEGMENT_ENTRY_EMPTY; } -static inline unsigned long pmd_pfn(pmd_t pmd) -{ - unsigned long origin_mask; - - origin_mask = _SEGMENT_ENTRY_ORIGIN; - if (pmd_large(pmd)) - origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE; - return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT; -} - #define pmd_write pmd_write static inline int pmd_write(pmd_t pmd) { @@ -1238,11 +1218,39 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) #define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) -#define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN) -#define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN) #define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN) #define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN) +static inline unsigned long pmd_deref(pmd_t pmd) +{ + unsigned long origin_mask; + + origin_mask = _SEGMENT_ENTRY_ORIGIN; + if (pmd_large(pmd)) + origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE; + return pmd_val(pmd) & origin_mask; +} + +static inline unsigned long pmd_pfn(pmd_t pmd) +{ + return pmd_deref(pmd) >> PAGE_SHIFT; +} + +static inline unsigned long pud_deref(pud_t pud) +{ + unsigned long origin_mask; + + origin_mask = _REGION_ENTRY_ORIGIN; + if (pud_large(pud)) + origin_mask = _REGION3_ENTRY_ORIGIN_LARGE; + return pud_val(pud) & origin_mask; +} + +static inline unsigned long pud_pfn(pud_t pud) +{ + return pud_deref(pud) >> PAGE_SHIFT; +} + /* * The pgd_offset function *always* adds the index for the top-level * region/segment table. This is done to get a sequence like the diff --git a/arch/s390/include/asm/vdso/vdso.h b/arch/s390/include/asm/vdso/vdso.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/arch/s390/include/asm/vdso/vdso.h +++ /dev/null diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index ece58f2217cb..2012c1cf0853 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -61,14 +61,6 @@ int main(void) BLANK(); OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val); BLANK(); - /* constants used by the vdso */ - DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME); - DEFINE(__CLOCK_MONOTONIC, CLOCK_MONOTONIC); - DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); - DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE); - DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID); - DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC); - BLANK(); /* idle data offsets */ OFFSET(__CLOCK_IDLE_ENTER, s390_idle_data, clock_idle_enter); OFFSET(__CLOCK_IDLE_EXIT, s390_idle_data, clock_idle_exit); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index ebfe86d097f0..390d97daa2b3 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -855,13 +855,14 @@ void __init smp_detect_cpus(void) static void smp_init_secondary(void) { - int cpu = smp_processor_id(); + int cpu = raw_smp_processor_id(); S390_lowcore.last_update_clock = get_tod_clock(); restore_access_regs(S390_lowcore.access_regs_save_area); set_cpu_flag(CIF_ASCE_PRIMARY); set_cpu_flag(CIF_ASCE_SECONDARY); cpu_init(); + rcu_cpu_starting(cpu); preempt_disable(); init_cpu_timer(); vtime_init(); diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index d33f21545dfd..9a6bae503fe6 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -101,6 +101,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) if (ret) break; + /* the PCI function will be scanned once function 0 appears */ + if (!zdev->zbus->bus) + break; + pdev = pci_scan_single_device(zdev->zbus->bus, zdev->devfn); if (!pdev) break; diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index a5e5db6ada3c..39b2eded7bc2 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -164,6 +164,7 @@ void initialize_identity_maps(void *rmode) add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); /* Load the new page-table. */ + sev_verify_cbit(top_level_pgt); write_cr3(top_level_pgt); } diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index dd07e7b41b11..aa561795efd1 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -68,6 +68,9 @@ SYM_FUNC_START(get_sev_encryption_bit) SYM_FUNC_END(get_sev_encryption_bit) .code64 + +#include "../../kernel/sev_verify_cbit.S" + SYM_FUNC_START(set_sev_encryption_mask) #ifdef CONFIG_AMD_MEM_ENCRYPT push %rbp @@ -81,6 +84,19 @@ SYM_FUNC_START(set_sev_encryption_mask) bts %rax, sme_me_mask(%rip) /* Create the encryption mask */ + /* + * Read MSR_AMD64_SEV again and store it to sev_status. Can't do this in + * get_sev_encryption_bit() because this function is 32-bit code and + * shared between 64-bit and 32-bit boot path. + */ + movl $MSR_AMD64_SEV, %ecx /* Read the SEV MSR */ + rdmsr + + /* Store MSR value in sev_status */ + shlq $32, %rdx + orq %rdx, %rax + movq %rax, sev_status(%rip) + .Lno_sev_mask: movq %rbp, %rsp /* Restore original stack pointer */ @@ -96,5 +112,7 @@ SYM_FUNC_END(set_sev_encryption_mask) #ifdef CONFIG_AMD_MEM_ENCRYPT .balign 8 -SYM_DATA(sme_me_mask, .quad 0) +SYM_DATA(sme_me_mask, .quad 0) +SYM_DATA(sev_status, .quad 0) +SYM_DATA(sev_check_data, .quad 0) #endif diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 6d31f1b4c4d1..d9a631c5973c 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -159,4 +159,6 @@ void boot_page_fault(void); void boot_stage1_vc(void); void boot_stage2_vc(void); +unsigned long sev_verify_cbit(unsigned long cr3); + #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 40e0e322161d..284e73661a18 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -273,11 +273,15 @@ void __init hv_apic_init(void) pr_info("Hyper-V: Using enlightened APIC (%s mode)", x2apic_enabled() ? "x2apic" : "xapic"); /* - * With x2apic, architectural x2apic MSRs are equivalent to the - * respective synthetic MSRs, so there's no need to override - * the apic accessors. The only exception is - * hv_apic_eoi_write, because it benefits from lazy EOI when - * available, but it works for both xapic and x2apic modes. + * When in x2apic mode, don't use the Hyper-V specific APIC + * accessors since the field layout in the ICR register is + * different in x2apic mode. Furthermore, the architectural + * x2apic MSRs function just as well as the Hyper-V + * synthetic APIC MSRs, so there's no benefit in having + * separate Hyper-V accessors for x2apic mode. The only + * exception is hv_apic_eoi_write, because it benefits from + * lazy EOI when available, but the same accessor works for + * both xapic and x2apic because the field layout is the same. */ apic_set_eoi_write(hv_apic_eoi_write); if (!x2apic_enabled()) { diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 7eb2a1c87969..3c417734790f 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -161,6 +161,21 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) /* Setup early boot stage 4-/5-level pagetables. */ addq phys_base(%rip), %rax + + /* + * For SEV guests: Verify that the C-bit is correct. A malicious + * hypervisor could lie about the C-bit position to perform a ROP + * attack on the guest by writing to the unencrypted stack and wait for + * the next RET instruction. + * %rsi carries pointer to realmode data and is callee-clobbered. Save + * and restore it. + */ + pushq %rsi + movq %rax, %rdi + call sev_verify_cbit + popq %rsi + + /* Switch to new page-table */ movq %rax, %cr3 /* Ensure I am executing from virtual addresses */ @@ -279,6 +294,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) SYM_CODE_END(secondary_startup_64) #include "verify_cpu.S" +#include "sev_verify_cbit.S" #ifdef CONFIG_HOTPLUG_CPU /* diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 5f83ccaab877..7d04b356d44d 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -178,6 +178,32 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) goto fail; regs->dx = val >> 32; + /* + * This is a VC handler and the #VC is only raised when SEV-ES is + * active, which means SEV must be active too. Do sanity checks on the + * CPUID results to make sure the hypervisor does not trick the kernel + * into the no-sev path. This could map sensitive data unencrypted and + * make it accessible to the hypervisor. + * + * In particular, check for: + * - Hypervisor CPUID bit + * - Availability of CPUID leaf 0x8000001f + * - SEV CPUID bit. + * + * The hypervisor might still report the wrong C-bit position, but this + * can't be checked here. + */ + + if ((fn == 1 && !(regs->cx & BIT(31)))) + /* Hypervisor bit */ + goto fail; + else if (fn == 0x80000000 && (regs->ax < 0x8000001f)) + /* SEV leaf check */ + goto fail; + else if ((fn == 0x8000001f && !(regs->ax & BIT(1)))) + /* SEV bit */ + goto fail; + /* Skip over the CPUID two-byte opcode */ regs->ip += 2; diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 4a96726fbaf8..0bd1a0fc587e 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -374,8 +374,8 @@ fault: return ES_EXCEPTION; } -static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, - unsigned long vaddr, phys_addr_t *paddr) +static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, + unsigned long vaddr, phys_addr_t *paddr) { unsigned long va = (unsigned long)vaddr; unsigned int level; @@ -394,15 +394,19 @@ static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, if (user_mode(ctxt->regs)) ctxt->fi.error_code |= X86_PF_USER; - return false; + return ES_EXCEPTION; } + if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC)) + /* Emulated MMIO to/from encrypted memory not supported */ + return ES_UNSUPPORTED; + pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; pa |= va & ~page_level_mask(level); *paddr = pa; - return true; + return ES_OK; } /* Include code shared with pre-decompression boot stage */ @@ -731,6 +735,7 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, { u64 exit_code, exit_info_1, exit_info_2; unsigned long ghcb_pa = __pa(ghcb); + enum es_result res; phys_addr_t paddr; void __user *ref; @@ -740,11 +745,12 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE; - if (!vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr)) { - if (!read) + res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr); + if (res != ES_OK) { + if (res == ES_EXCEPTION && !read) ctxt->fi.error_code |= X86_PF_WRITE; - return ES_EXCEPTION; + return res; } exit_info_1 = paddr; diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S new file mode 100644 index 000000000000..ee04941a6546 --- /dev/null +++ b/arch/x86/kernel/sev_verify_cbit.S @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * sev_verify_cbit.S - Code for verification of the C-bit position reported + * by the Hypervisor when running with SEV enabled. + * + * Copyright (c) 2020 Joerg Roedel (jroedel@suse.de) + * + * sev_verify_cbit() is called before switching to a new long-mode page-table + * at boot. + * + * Verify that the C-bit position is correct by writing a random value to + * an encrypted memory location while on the current page-table. Then it + * switches to the new page-table to verify the memory content is still the + * same. After that it switches back to the current page-table and when the + * check succeeded it returns. If the check failed the code invalidates the + * stack pointer and goes into a hlt loop. The stack-pointer is invalidated to + * make sure no interrupt or exception can get the CPU out of the hlt loop. + * + * New page-table pointer is expected in %rdi (first parameter) + * + */ +SYM_FUNC_START(sev_verify_cbit) +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* First check if a C-bit was detected */ + movq sme_me_mask(%rip), %rsi + testq %rsi, %rsi + jz 3f + + /* sme_me_mask != 0 could mean SME or SEV - Check also for SEV */ + movq sev_status(%rip), %rsi + testq %rsi, %rsi + jz 3f + + /* Save CR4 in %rsi */ + movq %cr4, %rsi + + /* Disable Global Pages */ + movq %rsi, %rdx + andq $(~X86_CR4_PGE), %rdx + movq %rdx, %cr4 + + /* + * Verified that running under SEV - now get a random value using + * RDRAND. This instruction is mandatory when running as an SEV guest. + * + * Don't bail out of the loop if RDRAND returns errors. It is better to + * prevent forward progress than to work with a non-random value here. + */ +1: rdrand %rdx + jnc 1b + + /* Store value to memory and keep it in %rdx */ + movq %rdx, sev_check_data(%rip) + + /* Backup current %cr3 value to restore it later */ + movq %cr3, %rcx + + /* Switch to new %cr3 - This might unmap the stack */ + movq %rdi, %cr3 + + /* + * Compare value in %rdx with memory location. If C-bit is incorrect + * this would read the encrypted data and make the check fail. + */ + cmpq %rdx, sev_check_data(%rip) + + /* Restore old %cr3 */ + movq %rcx, %cr3 + + /* Restore previous CR4 */ + movq %rsi, %cr4 + + /* Check CMPQ result */ + je 3f + + /* + * The check failed, prevent any forward progress to prevent ROP + * attacks, invalidate the stack and go into a hlt loop. + */ + xorq %rsp, %rsp + subq $0x1000, %rsp +2: hlt + jmp 2b +3: +#endif + /* Return page-table pointer */ + movq %rdi, %rax + ret +SYM_FUNC_END(sev_verify_cbit) diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index efbb3de472df..bc0833713be9 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -39,6 +39,7 @@ */ u64 sme_me_mask __section(".data") = 0; u64 sev_status __section(".data") = 0; +u64 sev_check_data __section(".data") = 0; EXPORT_SYMBOL(sme_me_mask); DEFINE_STATIC_KEY_FALSE(sev_enable_key); EXPORT_SYMBOL_GPL(sev_enable_key); diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index c6fc83efee0c..8731b7ad9308 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -89,8 +89,8 @@ static void __init free_highpages(void) /* set highmem page free */ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &range_start, &range_end, NULL) { - unsigned long start = PHYS_PFN(range_start); - unsigned long end = PHYS_PFN(range_end); + unsigned long start = PFN_UP(range_start); + unsigned long end = PFN_DOWN(range_end); /* Ignore complete lowmem entries */ if (end <= max_low) |