diff options
Diffstat (limited to 'arch/x86/kernel')
84 files changed, 2671 insertions, 2216 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index a20a5ebfacd7..cceaafdd2d84 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -3,10 +3,6 @@ # Makefile for the linux kernel. # -extra-y := head_$(BITS).o -extra-y += head$(BITS).o -extra-y += ebda.o -extra-y += platform-quirks.o extra-y += vmlinux.lds CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE) @@ -33,6 +29,8 @@ KASAN_SANITIZE_sev.o := n # With some compiler versions the generated code results in boot hangs, caused # by several compilation units. To be safe, disable all instrumentation. KCSAN_SANITIZE := n +KMSAN_SANITIZE_head$(BITS).o := n +KMSAN_SANITIZE_nmi.o := n # If instrumentation of this dir is enabled, boot hangs during first second. # Probably could be more selective here, but note that files related to irqs, @@ -42,7 +40,11 @@ KCOV_INSTRUMENT := n CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace -obj-y := process_$(BITS).o signal.o +obj-y += head_$(BITS).o +obj-y += head$(BITS).o +obj-y += ebda.o +obj-y += platform-quirks.o +obj-y += process_$(BITS).o signal.o signal_$(BITS).o obj-$(CONFIG_COMPAT) += signal_compat.o obj-y += traps.o idt.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o dumpstack.o nmi.o @@ -52,7 +54,7 @@ obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o obj-$(CONFIG_X86_32) += sys_ia32.o -obj-$(CONFIG_IA32_EMULATION) += sys_ia32.o +obj-$(CONFIG_IA32_EMULATION) += sys_ia32.o signal_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o @@ -139,6 +141,8 @@ obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev.o +obj-$(CONFIG_CFI_CLANG) += cfi.o + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 7945eae5b315..401808b47af3 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -52,17 +52,25 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags, if (c->x86_vendor == X86_VENDOR_INTEL && (c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 0x0f))) flags->bm_control = 0; - /* - * For all recent Centaur CPUs, the ucode will make sure that each - * core can keep cache coherence with each other while entering C3 - * type state. So, set bm_check to 1 to indicate that the kernel - * doesn't need to execute a cache flush operation (WBINVD) when - * entering C3 type state. - */ + if (c->x86_vendor == X86_VENDOR_CENTAUR) { if (c->x86 > 6 || (c->x86 == 6 && c->x86_model == 0x0f && - c->x86_stepping >= 0x0e)) + c->x86_stepping >= 0x0e)) { + /* + * For all recent Centaur CPUs, the ucode will make sure that each + * core can keep cache coherence with each other while entering C3 + * type state. So, set bm_check to 1 to indicate that the kernel + * doesn't need to execute a cache flush operation (WBINVD) when + * entering C3 type state. + */ flags->bm_check = 1; + /* + * For all recent Centaur platforms, ARB_DISABLE is a nop. + * Set bm_control to zero to indicate that ARB_DISABLE is + * not required while entering C3 type state. + */ + flags->bm_control = 0; + } } if (c->x86_vendor == X86_VENDOR_ZHAOXIN) { diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 62f6b8b7c4a5..a9bea860e22a 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -453,6 +453,15 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) return ret; i += ret; + /* + * The compiler is supposed to EMIT an INT3 after every unconditional + * JMP instruction due to AMD BTC. However, if the compiler is too old + * or SLS isn't enabled, we still need an INT3 after indirect JMPs + * even on Intel. + */ + if (op == JMP32_INSN_OPCODE && i < insn->length) + bytes[i++] = INT3_INSN_OPCODE; + for (; i < insn->length;) bytes[i++] = BYTES_NOP1; @@ -615,7 +624,7 @@ void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end) #else -void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end) { } +void __init_or_module apply_ibt_endbr(s32 *start, s32 *end) { } #endif /* CONFIG_X86_KERNEL_IBT */ @@ -1319,22 +1328,23 @@ struct bp_patching_desc { atomic_t refs; }; -static struct bp_patching_desc *bp_desc; +static struct bp_patching_desc bp_desc; static __always_inline -struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp) +struct bp_patching_desc *try_get_desc(void) { - /* rcu_dereference */ - struct bp_patching_desc *desc = __READ_ONCE(*descp); + struct bp_patching_desc *desc = &bp_desc; - if (!desc || !arch_atomic_inc_not_zero(&desc->refs)) + if (!arch_atomic_inc_not_zero(&desc->refs)) return NULL; return desc; } -static __always_inline void put_desc(struct bp_patching_desc *desc) +static __always_inline void put_desc(void) { + struct bp_patching_desc *desc = &bp_desc; + smp_mb__before_atomic(); arch_atomic_dec(&desc->refs); } @@ -1367,15 +1377,15 @@ noinstr int poke_int3_handler(struct pt_regs *regs) /* * Having observed our INT3 instruction, we now must observe - * bp_desc: + * bp_desc with non-zero refcount: * - * bp_desc = desc INT3 + * bp_desc.refs = 1 INT3 * WMB RMB - * write INT3 if (desc) + * write INT3 if (bp_desc.refs != 0) */ smp_rmb(); - desc = try_get_desc(&bp_desc); + desc = try_get_desc(); if (!desc) return 0; @@ -1429,7 +1439,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs) ret = 1; out_put: - put_desc(desc); + put_desc(); return ret; } @@ -1460,18 +1470,20 @@ static int tp_vec_nr; */ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) { - struct bp_patching_desc desc = { - .vec = tp, - .nr_entries = nr_entries, - .refs = ATOMIC_INIT(1), - }; unsigned char int3 = INT3_INSN_OPCODE; unsigned int i; int do_sync; lockdep_assert_held(&text_mutex); - smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */ + bp_desc.vec = tp; + bp_desc.nr_entries = nr_entries; + + /* + * Corresponds to the implicit memory barrier in try_get_desc() to + * ensure reading a non-zero refcount provides up to date bp_desc data. + */ + atomic_set_release(&bp_desc.refs, 1); /* * Corresponding read barrier in int3 notifier for making sure the @@ -1559,12 +1571,10 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries text_poke_sync(); /* - * Remove and synchronize_rcu(), except we have a very primitive - * refcount based completion. + * Remove and wait for refs to be zero. */ - WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */ - if (!atomic_dec_and_test(&desc.refs)) - atomic_cond_read_acquire(&desc.refs, !VAL); + if (!atomic_dec_and_test(&bp_desc.refs)) + atomic_cond_read_acquire(&bp_desc.refs, !VAL); } static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, @@ -1598,7 +1608,7 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, default: BUG_ON(len != insn.length); - }; + } switch (tp->opcode) { diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 194d54eed537..19a0207e529f 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -53,7 +53,7 @@ static u32 *iommu_gatt_base; /* Remapping table */ * of only flushing when an mapping is reused. With it true the GART is * flushed for every mapping. Problem is that doing the lazy flush seems * to trigger bugs with some popular PCI cards, in particular 3ware (but - * has been also also seen with Qlogic at least). + * has been also seen with Qlogic at least). */ static int iommu_fullflush = 1; diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 7a5630d904b2..4feaa670d578 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -36,7 +36,7 @@ /* * Using 512M as goal, in case kexec will load kernel_big * that will do the on-position decompress, and could overlap with - * with the gart aperture that is used. + * the gart aperture that is used. * Sequence: * kernel_small * ==> kexec (with kdump trigger path or gart still enabled) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 6d303d1d276c..20d9a604da7c 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -61,6 +61,7 @@ #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include <asm/irq_regs.h> +#include <asm/cpu.h> unsigned int num_processors; @@ -1751,11 +1752,26 @@ EXPORT_SYMBOL_GPL(x2apic_mode); enum { X2APIC_OFF, - X2APIC_ON, X2APIC_DISABLED, + /* All states below here have X2APIC enabled */ + X2APIC_ON, + X2APIC_ON_LOCKED }; static int x2apic_state; +static bool x2apic_hw_locked(void) +{ + u64 ia32_cap; + u64 msr; + + ia32_cap = x86_read_arch_cap_msr(); + if (ia32_cap & ARCH_CAP_XAPIC_DISABLE) { + rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr); + return (msr & LEGACY_XAPIC_DISABLED); + } + return false; +} + static void __x2apic_disable(void) { u64 msr; @@ -1793,6 +1809,10 @@ static int __init setup_nox2apic(char *str) apicid); return 0; } + if (x2apic_hw_locked()) { + pr_warn("APIC locked in x2apic mode, can't disable\n"); + return 0; + } pr_warn("x2apic already enabled.\n"); __x2apic_disable(); } @@ -1807,10 +1827,18 @@ early_param("nox2apic", setup_nox2apic); void x2apic_setup(void) { /* - * If x2apic is not in ON state, disable it if already enabled + * Try to make the AP's APIC state match that of the BSP, but if the + * BSP is unlocked and the AP is locked then there is a state mismatch. + * Warn about the mismatch in case a GP fault occurs due to a locked AP + * trying to be turned off. + */ + if (x2apic_state != X2APIC_ON_LOCKED && x2apic_hw_locked()) + pr_warn("x2apic lock mismatch between BSP and AP.\n"); + /* + * If x2apic is not in ON or LOCKED state, disable it if already enabled * from BIOS. */ - if (x2apic_state != X2APIC_ON) { + if (x2apic_state < X2APIC_ON) { __x2apic_disable(); return; } @@ -1831,6 +1859,11 @@ static __init void x2apic_disable(void) if (x2apic_id >= 255) panic("Cannot disable x2apic, id: %08x\n", x2apic_id); + if (x2apic_hw_locked()) { + pr_warn("Cannot disable locked x2apic, id: %08x\n", x2apic_id); + return; + } + __x2apic_disable(); register_lapic_address(mp_lapic_addr); } @@ -1889,22 +1922,28 @@ void __init check_x2apic(void) if (x2apic_enabled()) { pr_info("x2apic: enabled by BIOS, switching to x2apic ops\n"); x2apic_mode = 1; - x |