diff options
Diffstat (limited to 'arch/x86')
34 files changed, 227 insertions, 98 deletions
diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 2d449337a360..a94a4d10f2df 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -120,10 +120,6 @@ else # -funit-at-a-time shrinks the kernel .text considerably # unfortunately it makes reading oopses harder. KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time) - - # this works around some issues with generating unwind tables in older gccs - # newer gccs do it by default - KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args) endif ifdef CONFIG_X86_X32 @@ -147,6 +143,37 @@ ifeq ($(CONFIG_KMEMCHECK),y) KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy) endif +# +# If the function graph tracer is used with mcount instead of fentry, +# '-maccumulate-outgoing-args' is needed to prevent a GCC bug +# (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=42109) +# +ifdef CONFIG_FUNCTION_GRAPH_TRACER + ifndef CONFIG_HAVE_FENTRY + ACCUMULATE_OUTGOING_ARGS := 1 + else + ifeq ($(call cc-option-yn, -mfentry), n) + ACCUMULATE_OUTGOING_ARGS := 1 + endif + endif +endif + +# +# Jump labels need '-maccumulate-outgoing-args' for gcc < 4.5.2 to prevent a +# GCC bug (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46226). There's no way +# to test for this bug at compile-time because the test case needs to execute, +# which is a no-go for cross compilers. So check the GCC version instead. +# +ifdef CONFIG_JUMP_LABEL + ifneq ($(ACCUMULATE_OUTGOING_ARGS), 1) + ACCUMULATE_OUTGOING_ARGS = $(call cc-if-fullversion, -lt, 040502, 1) + endif +endif + +ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1) + KBUILD_CFLAGS += -maccumulate-outgoing-args +endif + # Stackpointer is addressed different for 32 bit and 64 bit x86 sp-$(CONFIG_X86_32) := esp sp-$(CONFIG_X86_64) := rsp diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index 6647ed49c66c..a45eb15b7cf2 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -45,24 +45,6 @@ cflags-$(CONFIG_MGEODE_LX) += $(call cc-option,-march=geode,-march=pentium-mmx) # cpu entries cflags-$(CONFIG_X86_GENERIC) += $(call tune,generic,$(call tune,i686)) -# Work around the pentium-mmx code generator madness of gcc4.4.x which -# does stack alignment by generating horrible code _before_ the mcount -# prologue (push %ebp, mov %esp, %ebp) which breaks the function graph -# tracer assumptions. For i686, generic, core2 this is set by the -# compiler anyway -ifeq ($(CONFIG_FUNCTION_GRAPH_TRACER), y) -ADD_ACCUMULATE_OUTGOING_ARGS := y -endif - -# Work around to a bug with asm goto with first implementations of it -# in gcc causing gcc to mess up the push and pop of the stack in some -# uses of asm goto. -ifeq ($(CONFIG_JUMP_LABEL), y) -ADD_ACCUMULATE_OUTGOING_ARGS := y -endif - -cflags-$(ADD_ACCUMULATE_OUTGOING_ARGS) += $(call cc-option,-maccumulate-outgoing-args) - # Bug fix for binutils: this option is required in order to keep # binutils from generating NOPL instructions against our will. ifneq ($(CONFIG_X86_P6_NOP),y) diff --git a/arch/x86/boot/compressed/error.c b/arch/x86/boot/compressed/error.c index 6248740b68b5..31922023de49 100644 --- a/arch/x86/boot/compressed/error.c +++ b/arch/x86/boot/compressed/error.c @@ -4,6 +4,7 @@ * memcpy() and memmove() are defined for the compressed boot environment. */ #include "misc.h" +#include "error.h" void warn(char *m) { diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 7853b53959cd..3f9d1a83891a 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -30,8 +30,10 @@ static int __init vdso32_setup(char *s) { vdso32_enabled = simple_strtoul(s, NULL, 0); - if (vdso32_enabled > 1) + if (vdso32_enabled > 1) { pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n"); + vdso32_enabled = 0; + } return 1; } @@ -62,13 +64,18 @@ subsys_initcall(sysenter_setup); /* Register vsyscall32 into the ABI table */ #include <linux/sysctl.h> +static const int zero; +static const int one = 1; + static struct ctl_table abi_table2[] = { { .procname = "vsyscall32", .data = &vdso32_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = (int *)&zero, + .extra2 = (int *)&one, }, {} }; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 2aa1ad194db2..580b60f5ac83 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2256,6 +2256,7 @@ void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now) { struct cyc2ns_data *data; + u64 offset; userpg->cap_user_time = 0; userpg->cap_user_time_zero = 0; @@ -2263,11 +2264,13 @@ void arch_perf_update_userpage(struct perf_event *event, !!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED); userpg->pmc_width = x86_pmu.cntval_bits; - if (!sched_clock_stable()) + if (!using_native_sched_clock() || !sched_clock_stable()) return; data = cyc2ns_read_begin(); + offset = data->cyc2ns_offset + __sched_clock_offset; + /* * Internal timekeeping for enabled/running/stopped times * is always in the local_clock domain. @@ -2275,7 +2278,7 @@ void arch_perf_update_userpage(struct perf_event *event, userpg->cap_user_time = 1; userpg->time_mult = data->cyc2ns_mul; userpg->time_shift = data->cyc2ns_shift; - userpg->time_offset = data->cyc2ns_offset - now; + userpg->time_offset = offset - now; /* * cap_user_time_zero doesn't make sense when we're using a different @@ -2283,7 +2286,7 @@ void arch_perf_update_userpage(struct perf_event *event, */ if (!event->attr.use_clockid) { userpg->cap_user_time_zero = 1; - userpg->time_zero = data->cyc2ns_offset; + userpg->time_zero = offset; } cyc2ns_read_end(data); diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 81b321ace8e0..f924629836a8 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -507,6 +507,9 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) cpuc->lbr_entries[i].to = msr_lastbranch.to; cpuc->lbr_entries[i].mispred = 0; cpuc->lbr_entries[i].predicted = 0; + cpuc->lbr_entries[i].in_tx = 0; + cpuc->lbr_entries[i].abort = 0; + cpuc->lbr_entries[i].cycles = 0; cpuc->lbr_entries[i].reserved = 0; } cpuc->lbr_stack.nr = i; diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 9d49c18b5ea9..3762536619f8 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -287,7 +287,7 @@ struct task_struct; #define ARCH_DLINFO_IA32 \ do { \ - if (vdso32_enabled) { \ + if (VDSO_CURRENT_BASE) { \ NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \ NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \ } \ diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index d74747b031ec..c4eda791f877 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -46,6 +46,7 @@ struct kvm_page_track_notifier_node { }; void kvm_page_track_init(struct kvm *kvm); +void kvm_page_track_cleanup(struct kvm *kvm); void kvm_page_track_free_memslot(struct kvm_memory_slot *free, struct kvm_memory_slot *dont); diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h index 2c1ebeb4d737..529bb4a6487a 100644 --- a/arch/x86/include/asm/pmem.h +++ b/arch/x86/include/asm/pmem.h @@ -55,7 +55,8 @@ static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n) * @size: number of bytes to write back * * Write back a cache range using the CLWB (cache line write back) - * instruction. + * instruction. Note that @size is internally rounded up to be cache + * line size aligned. */ static inline void arch_wb_cache_pmem(void *addr, size_t size) { @@ -69,15 +70,6 @@ static inline void arch_wb_cache_pmem(void *addr, size_t size) clwb(p); } -/* - * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec - * iterators, so for other types (bvec & kvec) we must do a cache write-back. - */ -static inline bool __iter_needs_pmem_wb(struct iov_iter *i) -{ - return iter_is_iovec(i) == false; -} - /** * arch_copy_from_iter_pmem - copy data from an iterator to PMEM * @addr: PMEM destination address @@ -94,7 +86,35 @@ static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes, /* TODO: skip the write-back by always using non-temporal stores */ len = copy_from_iter_nocache(addr, bytes, i); - if (__iter_needs_pmem_wb(i)) + /* + * In the iovec case on x86_64 copy_from_iter_nocache() uses + * non-temporal stores for the bulk of the transfer, but we need + * to manually flush if the transfer is unaligned. A cached + * memory copy is used when destination or size is not naturally + * aligned. That is: + * - Require 8-byte alignment when size is 8 bytes or larger. + * - Require 4-byte alignment when size is 4 bytes. + * + * In the non-iovec case the entire destination needs to be + * flushed. + */ + if (iter_is_iovec(i)) { + unsigned long flushed, dest = (unsigned long) addr; + + if (bytes < 8) { + if (!IS_ALIGNED(dest, 4) || (bytes != 4)) + arch_wb_cache_pmem(addr, 1); + } else { + if (!IS_ALIGNED(dest, 8)) { + dest = ALIGN(dest, boot_cpu_data.x86_clflush_size); + arch_wb_cache_pmem(addr, 1); + } + + flushed = dest - (unsigned long) addr; + if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8)) + arch_wb_cache_pmem(addr + bytes - 1, 1); + } + } else arch_wb_cache_pmem(addr, bytes); return len; diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index a04eabd43d06..27e9f9d769b8 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -12,6 +12,8 @@ extern int recalibrate_cpu_khz(void); extern int no_timer_check; +extern bool using_native_sched_clock(void); + /* * We use the full linear equation: f(x) = a + b*x, in order to allow * a continuous function in the face of dynamic freq changes. diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 72e8300b1e8a..9cffb44a3cf5 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -485,15 +485,17 @@ static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr) if (paddr < uv_hub_info->lowmem_remap_top) paddr |= uv_hub_info->lowmem_remap_base; - paddr |= uv_hub_info->gnode_upper; - if (m_val) + + if (m_val) { + paddr |= uv_hub_info->gnode_upper; paddr = ((paddr << uv_hub_info->m_shift) >> uv_hub_info->m_shift) | ((paddr >> uv_hub_info->m_val) << uv_hub_info->n_lshift); - else + } else { paddr |= uv_soc_phys_ram_to_nasid(paddr) << uv_hub_info->gpa_shift; + } return paddr; } diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index e9f8f8cdd570..86f20cc0a65e 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -1105,7 +1105,8 @@ void __init uv_init_hub_info(struct uv_hub_info_s *hi) node_id.v = uv_read_local_mmr(UVH_NODE_ID); uv_cpuid.gnode_shift = max_t(unsigned int, uv_cpuid.gnode_shift, mn.n_val); hi->gnode_extra = (node_id.s.node_id & ~((1 << uv_cpuid.gnode_shift) - 1)) >> 1; - hi->gnode_upper = (unsigned long)hi->gnode_extra << mn.m_val; + if (mn.m_val) + hi->gnode_upper = (u64)hi->gnode_extra << mn.m_val; if (uv_gp_table) { hi->global_mmr_base = uv_gp_table->mmr_base; diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_schemata.c index f369cb8db0d5..badd2b31a560 100644 --- a/arch/x86/kernel/cpu/intel_rdt_schemata.c +++ b/arch/x86/kernel/cpu/intel_rdt_schemata.c @@ -200,11 +200,11 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, } out: - rdtgroup_kn_unlock(of->kn); for_each_enabled_rdt_resource(r) { kfree(r->tmp_cbms); r->tmp_cbms = NULL; } + rdtgroup_kn_unlock(of->kn); return ret ?: nbytes; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 1e5a50c11d3c..217cd4449bc9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -85,7 +85,7 @@ void mce_gen_pool_process(struct work_struct *__unused) head = llist_reverse_order(head); llist_for_each_entry_safe(node, tmp, head, llnode) { mce = &node->mce; - atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); + blocking_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node)); } } diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 903043e6a62b..19592ba1a320 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -13,7 +13,7 @@ enum severity_level { MCE_PANIC_SEVERITY, }; -extern struct atomic_notifier_head x86_mce_decoder_chain; +extern struct blocking_notifier_head x86_mce_decoder_chain; #define ATTR_LEN 16 #define INITIAL_CHECK_INTERVAL 5 * 60 /* 5 minutes */ diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8e9725c607ea..af44ebeb593f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -54,6 +54,8 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); +static int mce_chrdev_open_count; /* #times opened */ + #define mce_log_get_idx_check(p) \ ({ \ RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ @@ -121,7 +123,7 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. */ -ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain); +BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain); /* Do initial initialization of a struct mce */ void mce_setup(struct mce *m) @@ -218,7 +220,7 @@ void mce_register_decode_chain(struct notifier_block *nb) WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC); - atomic_notifier_chain_register(&x86_mce_decoder_chain, nb); + blocking_notifier_chain_register(&x86_mce_decoder_chain, nb); } EXPORT_SYMBOL_GPL(mce_register_decode_chain); @@ -226,7 +228,7 @@ void mce_unregister_decode_chain(struct notifier_block *nb) { atomic_dec(&num_notifiers); - atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb); + blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb); } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); @@ -319,18 +321,7 @@ static void __print_mce(struct mce *m) static void print_mce(struct mce *m) { - int ret = 0; - __print_mce(m); - - /* - * Print out human-readable details about the MCE error, - * (if the CPU has an implementation for that) - */ - ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m); - if (ret == NOTIFY_STOP) - return; - pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n"); } @@ -598,6 +589,10 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val, if (atomic_read(&num_notifiers) > 2) return NOTIFY_DONE; + /* Don't print when mcelog is running */ + if (mce_chrdev_open_count > 0) + return NOTIFY_DONE; + __print_mce(m); return NOTIFY_DONE; @@ -1828,7 +1823,6 @@ void mcheck_cpu_clear(struct cpuinfo_x86 *c) */ static DEFINE_SPINLOCK(mce_chrdev_state_lock); -static int mce_chrdev_open_count; /* #times opened */ static int mce_chrdev_open_exclu; /* already open exclusive? */ static int mce_chrdev_open(struct inode *inode, struct file *file) diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 524cc5780a77..6e4a047e4b68 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -60,7 +60,7 @@ static const char * const th_names[] = { "load_store", "insn_fetch", "combined_unit", - "", + "decode_unit", "northbridge", "execution_unit", }; diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 8f3d9cf26ff9..cbd73eb42170 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -29,6 +29,12 @@ #include <asm/ftrace.h> #include <asm/nops.h> +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && \ + !defined(CC_USING_FENTRY) && \ + !defined(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE) +# error The following combination is not supported: ((compiler missing -mfentry) || (CONFIG_X86_32 and !CONFIG_DYNAMIC_FTRACE)) && CONFIG_FUNCTION_GRAPH_TRACER && CONFIG_CC_OPTIMIZE_FOR_SIZE +#endif + #ifdef CONFIG_DYNAMIC_FTRACE int ftrace_arch_code_modify_prepare(void) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 396c042e9d0e..cc30a74e4adb 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -846,7 +846,7 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where) task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG, me->comm, me->pid, where, frame, regs->ip, regs->sp, regs->orig_ax); - print_vma_addr(" in ", regs->ip); + print_vma_addr(KERN_CONT " in ", regs->ip); pr_cont("\n"); } diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index ec1f756f9dc9..71beb28600d4 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -151,8 +151,8 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from, if (from->si_signo == SIGSEGV) { if (from->si_code == SEGV_BNDERR) { - compat_uptr_t lower = (unsigned long)&to->si_lower; - compat_uptr_t upper = (unsigned long)&to->si_upper; + compat_uptr_t lower = (unsigned long)from->si_lower; + compat_uptr_t upper = (unsigned long)from->si_upper; put_user_ex(lower, &to->si_lower); put_user_ex(upper, &to->si_upper); } diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index b868fa1b812b..edbdfe6ab60a 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -510,6 +510,9 @@ int tboot_force_iommu(void) if (!tboot_enabled()) return 0; + if (!intel_iommu_tboot_noforce) + return 1; + if (no_iommu || swiotlb || dmar_disabled) pr_warning("Forcing Intel-IOMMU to enabled\n"); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 948443e115c1..4e496379a871 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -255,7 +255,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx", tsk->comm, tsk->pid, str, regs->ip, regs->sp, error_code); - print_vma_addr(" in ", regs->ip); + print_vma_addr(KERN_CONT " in ", regs->ip); pr_cont("\n"); } @@ -519,7 +519,7 @@ do_general_protection(struct pt_regs *regs, long error_code) pr_info("%s[%d] general protection ip:%lx sp:%lx error:%lx", tsk->comm, task_pid_nr(tsk), regs->ip, regs->sp, error_code); - print_vma_addr(" in ", regs->ip); + print_vma_addr(KERN_CONT " in ", regs->ip); pr_cont("\n"); } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index c73a7f9e881a..714dfba6a1e7 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -328,7 +328,7 @@ unsigned long long sched_clock(void) return paravirt_sched_clock(); } -static inline bool using_native_sched_clock(void) +bool using_native_sched_clock(void) { return pv_time_ops.sched_clock == native_sched_clock; } @@ -336,7 +336,7 @@ static inline bool using_native_sched_clock(void) unsigned long long sched_clock(void) __attribute__((alias("native_sched_clock"))); -static inline bool using_native_sched_clock(void) { return true; } +bool using_native_sched_clock(void) { return true; } #endif int check_tsc_unstable(void) diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 73ea24d4f119..047b17a26269 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -657,6 +657,9 @@ void kvm_pic_destroy(struct kvm *kvm) { struct kvm_pic *vpic = kvm->arch.vpic; + if (!vpic) + return; + kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master); kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave); kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 6e219e5c07d2..289270a6aecb 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -635,6 +635,9 @@ void kvm_ioapic_destroy(struct kvm *kvm) { struct kvm_ioapic *ioapic = kvm->arch.vioapic; + if (!ioapic) + return; + cancel_delayed_work_sync(&ioapic->eoi_inject); kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev); kvm->arch.vioapic = NULL; diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c index 37942e419c32..60168cdd0546 100644 --- a/arch/x86/kvm/page_track.c +++ b/arch/x86/kvm/page_track.c @@ -160,6 +160,14 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn, return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]); } +void kvm_page_track_cleanup(struct kvm *kvm) +{ + struct kvm_page_track_notifier_head *head; + + head = &kvm->arch.track_notifier_head; + cleanup_srcu_struct(&head->track_srcu); +} + void kvm_page_track_init(struct kvm *kvm) { struct kvm_page_track_notifier_head *head; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index d1efe2c62b3f..5fba70646c32 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1379,6 +1379,9 @@ static void avic_vm_destroy(struct kvm *kvm) unsigned long flags; struct kvm_arch *vm_data = &kvm->arch; + if (!avic) + return; + avic_free_vm_id(vm_data->avic_vm_id); if (vm_data->avic_logical_id_table_page) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 98e82ee1e699..259e9b28ccf8 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1239,6 +1239,11 @@ static inline bool cpu_has_vmx_invvpid_global(void) return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT; } +static inline bool cpu_has_vmx_invvpid(void) +{ + return vmx_capability.vpid & VMX_VPID_INVVPID_BIT; +} + static inline bool cpu_has_vmx_ept(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & @@ -2753,7 +2758,6 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_DESC | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | - SECONDARY_EXEC_ENABLE_VPID | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_WBINVD_EXITING | @@ -2781,10 +2785,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) * though it is treated as global context. The alternative is * not failing the single-context invvpid, and it is worse. */ - if (enable_vpid) + if (enable_vpid) { + vmx->nested.nested_vmx_secondary_ctls_high |= + SECONDARY_EXEC_ENABLE_VPID; vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT | VMX_VPID_EXTENT_SUPPORTED_MASK; - else + } else vmx->nested.nested_vmx_vpid_caps = 0; if (enable_unrestricted_guest) @@ -4024,6 +4030,12 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu) __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid); } +static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu) +{ + if (enable_ept) + vmx_flush_tlb(vcpu); +} + static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) { ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits; @@ -6517,8 +6529,10 @@ static __init int hardware_setup(void) if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); - if (!cpu_has_vmx_vpid()) + if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || + !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) enable_vpid = 0; + if (!cpu_has_vmx_shadow_vmcs()) enable_shadow_vmcs = 0; if (enable_shadow_vmcs) @@ -8184,6 +8198,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); case EXIT_REASON_PREEMPTION_TIMER: return false; + case EXIT_REASON_PML_FULL: + /* We don't expose PML support to L1. */ + return false; default: return true; } @@ -8501,7 +8518,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) && kvm_vmx_exit_handlers[exit_reason]) return kvm_vmx_exit_handlers[exit_reason](vcpu); else { - WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason); + vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", + exit_reason); kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -8547,6 +8565,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) } else { sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + vmx_flush_tlb_ept_only(vcpu); } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); @@ -8572,8 +8591,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) */ if (!is_guest_mode(vcpu) || !nested_cpu_has2(get_vmcs12(&vmx->vcpu), - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { vmcs_write64(APIC_ACCESS_ADDR, hpa); + vmx_flush_tlb_ept_only(vcpu); + } } static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) @@ -9974,7 +9995,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exec_control; - bool nested_ept_enabled = false; vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector); vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector); @@ -10121,8 +10141,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmcs12->guest_intr_status); } - nested_ept_enabled = (exec_control & SECONDARY_EXEC_ENABLE_EPT) != 0; - /* * Write an illegal value to APIC_ACCESS_ADDR. Later, * nested_get_vmcs12_pages will either fix it up or @@ -10252,9 +10270,24 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } + if (enable_pml) { + /* + * Conceptually we want to copy the PML address and index from + * vmcs01 here, and then back to vmcs01 on nested vmexit. But, + * since we always flush the log on each vmexit, this happens + * to be equivalent to simply resetting the fields in vmcs02. + */ + ASSERT(vmx->pml_pg); + vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); + vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + } + if (nested_cpu_has_ept(vmcs12)) { kvm_mmu_unload(vcpu); nested_ept_init_mmu_context(vcpu); + } else if (nested_cpu_has2(vmcs12, + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { + vmx_flush_tlb_ept_only(vcpu); } /* @@ -10282,12 +10315,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmx_set_efer(vcpu, vcpu->arch.efer); /* Shadow page tables on either EPT or shadow page tables. */ - if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_ept_enabled, + if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12), entry_failure_code)) return 1; - kvm_mmu_reset_context(vcpu); - if (!enable_ept) vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested; @@ -11056,6 +11087,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmx->nested.change_vmcs01_virtual_x2apic_mode = false; vmx_set_virtual_x2apic_mode(vcpu, vcpu->arch.apic_base & X2APIC_ENABLE); + } else if (!nested_cpu_has_ept(vmcs12) && + nested_cpu_has2(vmcs12, + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { + vmx_flush_tlb_ept_only(vcpu); } /* This is needed for same reason as it was needed in prepare_vmcs02 */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1faf620a6fdc..ccbd45ecd41a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8153,11 +8153,12 @@ void kvm_arch_destroy_vm(struct kvm *kvm) if (kvm_x86_ops->vm_destroy) kvm_x86_ops->vm_destroy(kvm); kvm_iommu_unmap_guest(kvm); - kfree(kvm->arch.vpic); - kfree(kvm->arch.vioapic); + kvm_pic_destroy(kvm); + kvm_ioapic_destroy(kvm); kvm_free_vcpus(kvm); kvfree(rcu_dereference_check(kvm->arch.apic_map, 1)); kvm_mmu_uninit_vm(kvm); + kvm_page_track_cleanup(kvm); } void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, @@ -8566,11 +8567,11 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, { struct x86_exception fault; - trace_kvm_async_pf_ready(work->arch.token, work->gva); if (work->wakeup_all) work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); + trace_kvm_async_pf_ready(work->arch.token, work->gva); if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) && !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) { diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 779782f58324..9a53a06e5a3e 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -290,7 +290,7 @@ EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled) _ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail) _ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 22af912d66d2..889e7619a091 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -643,21 +643,40 @@ void __init init_mem_mapping(void) * devmem_is_allowed() checks to see if /dev/mem access to a certain address * is valid. The argument is a physical page number. * - * - * On x86, access has to be given to the first megabyte of ram because that area - * contains BIOS code and data regions used by X and dosemu and similar apps. - * Access has to be given to non-kernel-ram areas as well, these contain the PCI - * mmio resources as well as potential bios/acpi data regions. + * On x86, access has to be given to the first megabyte of RAM because that + * area traditionally contains BIOS code and data regions used by X, dosemu, + * and similar apps. Since they map the entire memory range, the whole range + * must be allowed (for mapping), but any areas that would otherwise be + * disallowed are flagged as being "zero filled" instead of rejected. + * Access has to be given to non-kernel-ram areas as well, these contain the + * PCI mmio resources as well as potential bios/acpi data regions. */ int devmem_is_allowed(unsigned long pagenr) { - if (pagenr < 256) - return 1; - if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) + if (page_is_ram(pagenr)) { + /* + * For disallowed memory regions in the low 1MB range, + * request that the page be shown as all zeros. + */ + if (pagenr < 256) + return 2; + + return 0; + } + + /* + * This must follow RAM test, since System RAM is considered a + * restricted resource under CONFIG_STRICT_IOMEM. + */ + if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) { + /* Low 1MB bypasses iomem restrictions. */ + if (pagenr < 256) + return 1; + return 0; - if (!page_is_ram(pagenr)) - return 1; - return 0; + } + + return 1; } void free_init_pages(char *what, unsigned long begin, unsigned long end) diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 887e57182716..aed206475aa7 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -48,7 +48,7 @@ static const unsigned long vaddr_start = __PAGE_OFFSET_BASE; #if defined(CONFIG_X86_ESPFIX64) static const unsigned long vaddr_end = ESPFIX_BASE_ADDR; #elif defined(CONFIG_EFI) -static const unsigned long vaddr_end = EFI_VA_START; +static const unsigned long vaddr_end = EFI_VA_END; #else static const unsigned long vaddr_end = __START_KERNEL_map; #endif @@ -105,7 +105,7 @@ void __init kernel_randomize_memory(void) */ BUILD_BUG_ON(vaddr_start >= vaddr_end); BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) && - vaddr_end >= EFI_VA_START); + vaddr_end >= EFI_VA_END); BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) || IS_ENABLED(CONFIG_EFI)) && vaddr_end >= __START_KERNEL_map); diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 30031d5293c4..cdfe8c628959 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -201,6 +201,10 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) return; } + /* No need to reserve regions that will never be freed. */ + if (md.attribute & EFI_MEMORY_RUNTIME) + return; + size += addr % EFI_PAGE_SIZE; size = round_up(size, EFI_PAGE_SIZE); addr = round_down(addr, EFI_PAGE_SIZE); diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 555b9fa0ad43..7dbdb780264d 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -8,6 +8,7 @@ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib targets += purgatory.ro +KASAN_SANITIZE := n KCOV_INSTRUMENT := n # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That |