summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kbuild4
-rw-r--r--arch/x86/Kconfig18
-rw-r--r--arch/x86/Makefile6
-rw-r--r--arch/x86/include/asm/io_apic.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h2
-rw-r--r--arch/x86/include/asm/pgtable.h9
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/apic/io_apic.c27
-rw-r--r--arch/x86/kernel/crash.c6
-rw-r--r--arch/x86/kernel/entry_32.S2
-rw-r--r--arch/x86/kernel/irqinit.c2
-rw-r--r--arch/x86/kernel/machine_kexec_64.c11
-rw-r--r--arch/x86/kernel/time.c2
-rw-r--r--arch/x86/kvm/emulate.c11
-rw-r--r--arch/x86/mm/tlb.c10
-rw-r--r--arch/x86/pci/intel_mid_pci.c2
-rw-r--r--arch/x86/pci/irq.c2
-rw-r--r--arch/x86/purgatory/Makefile6
18 files changed, 87 insertions, 37 deletions
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
index 61b6d51866f8..3942f74c92d7 100644
--- a/arch/x86/Kbuild
+++ b/arch/x86/Kbuild
@@ -17,6 +17,4 @@ obj-$(CONFIG_IA32_EMULATION) += ia32/
obj-y += platform/
obj-y += net/
-ifeq ($(CONFIG_X86_64),y)
-obj-$(CONFIG_KEXEC) += purgatory/
-endif
+obj-$(CONFIG_KEXEC_FILE) += purgatory/
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5d0bf1aa9dcb..778178f4c7d1 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1585,9 +1585,6 @@ source kernel/Kconfig.hz
config KEXEC
bool "kexec system call"
- select BUILD_BIN2C
- select CRYPTO
- select CRYPTO_SHA256
---help---
kexec is a system call that implements the ability to shutdown your
current kernel, and to start another kernel. It is like a reboot
@@ -1602,9 +1599,22 @@ config KEXEC
interface is strongly in flux, so no good recommendation can be
made.
+config KEXEC_FILE
+ bool "kexec file based system call"
+ select BUILD_BIN2C
+ depends on KEXEC
+ depends on X86_64
+ depends on CRYPTO=y
+ depends on CRYPTO_SHA256=y
+ ---help---
+ This is new version of kexec system call. This system call is
+ file based and takes file descriptors as system call argument
+ for kernel and initramfs as opposed to list of segments as
+ accepted by previous system call.
+
config KEXEC_VERIFY_SIG
bool "Verify kernel signature during kexec_file_load() syscall"
- depends on KEXEC
+ depends on KEXEC_FILE
---help---
This option makes kernel signature verification mandatory for
kexec_file_load() syscall. If kernel is signature can not be
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index c1aa36887843..60087ca37679 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -184,11 +184,8 @@ archheaders:
$(Q)$(MAKE) $(build)=arch/x86/syscalls all
archprepare:
-ifeq ($(CONFIG_KEXEC),y)
-# Build only for 64bit. No loaders for 32bit yet.
- ifeq ($(CONFIG_X86_64),y)
+ifeq ($(CONFIG_KEXEC_FILE),y)
$(Q)$(MAKE) $(build)=arch/x86/purgatory arch/x86/purgatory/kexec-purgatory.c
- endif
endif
###
@@ -254,6 +251,7 @@ archclean:
$(Q)rm -rf $(objtree)/arch/x86_64
$(Q)$(MAKE) $(clean)=$(boot)
$(Q)$(MAKE) $(clean)=arch/x86/tools
+ $(Q)$(MAKE) $(clean)=arch/x86/purgatory
PHONY += kvmconfig
kvmconfig:
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 0aeed5ca356e..478c490f3654 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -227,6 +227,8 @@ static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned
extern void io_apic_eoi(unsigned int apic, unsigned int vector);
+extern bool mp_should_keep_irq(struct device *dev);
+
#else /* !CONFIG_X86_IO_APIC */
#define io_apic_assign_pci_irqs 0
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 572460175ba5..7c492ed9087b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -95,7 +95,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
#define KVM_REFILL_PAGES 25
#define KVM_MAX_CPUID_ENTRIES 80
#define KVM_NR_FIXED_MTRR_REGION 88
-#define KVM_NR_VAR_MTRR 10
+#define KVM_NR_VAR_MTRR 8
#define ASYNC_PF_PER_VCPU 64
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 0ec056012618..aa97a070f09f 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -131,8 +131,13 @@ static inline int pte_exec(pte_t pte)
static inline int pte_special(pte_t pte)
{
- return (pte_flags(pte) & (_PAGE_PRESENT|_PAGE_SPECIAL)) ==
- (_PAGE_PRESENT|_PAGE_SPECIAL);
+ /*
+ * See CONFIG_NUMA_BALANCING pte_numa in include/asm-generic/pgtable.h.
+ * On x86 we have _PAGE_BIT_NUMA == _PAGE_BIT_GLOBAL+1 ==
+ * __PAGE_BIT_SOFTW1 == _PAGE_BIT_SPECIAL.
+ */
+ return (pte_flags(pte) & _PAGE_SPECIAL) &&
+ (pte_flags(pte) & (_PAGE_PRESENT|_PAGE_PROTNONE));
}
static inline unsigned long pte_pfn(pte_t pte)
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index b5ea75c4a4b4..ada2e2d6be3e 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -71,6 +71,7 @@ obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o
obj-$(CONFIG_X86_TSC) += trace_clock.o
obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o
obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o
+obj-$(CONFIG_KEXEC_FILE) += kexec-bzimage64.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o
obj-y += kprobes/
obj-$(CONFIG_MODULES) += module.o
@@ -118,5 +119,4 @@ ifeq ($(CONFIG_X86_64),y)
obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o
obj-y += vsmp_64.o
- obj-$(CONFIG_KEXEC) += kexec-bzimage64.o
endif
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 29290f554e79..337ce5a9b15c 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1070,6 +1070,11 @@ static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin,
}
if (flags & IOAPIC_MAP_ALLOC) {
+ /* special handling for legacy IRQs */
+ if (irq < nr_legacy_irqs() && info->count == 1 &&
+ mp_irqdomain_map(domain, irq, pin) != 0)
+ irq = -1;
+
if (irq > 0)
info->count++;
else if (info->count == 0)
@@ -3896,7 +3901,15 @@ int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
info->polarity = 1;
}
info->node = NUMA_NO_NODE;
- info->set = 1;
+
+ /*
+ * setup_IO_APIC_irqs() programs all legacy IRQs with default
+ * trigger and polarity attributes. Don't set the flag for that
+ * case so the first legacy IRQ user could reprogram the pin
+ * with real trigger and polarity attributes.
+ */
+ if (virq >= nr_legacy_irqs() || info->count)
+ info->set = 1;
}
set_io_apic_irq_attr(&attr, ioapic, hwirq, info->trigger,
info->polarity);
@@ -3946,6 +3959,18 @@ int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node)
return ret;
}
+bool mp_should_keep_irq(struct device *dev)
+{
+ if (dev->power.is_prepared)
+ return true;
+#ifdef CONFIG_PM_RUNTIME
+ if (dev->power.runtime_status == RPM_SUSPENDING)
+ return true;
+#endif
+
+ return false;
+}
+
/* Enable IOAPIC early just for system timer */
void __init pre_init_apic_IRQ0(void)
{
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 0553a34fa0df..a618fcd2c07d 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -182,8 +182,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
crash_save_cpu(regs, safe_smp_processor_id());
}
-#ifdef CONFIG_X86_64
-
+#ifdef CONFIG_KEXEC_FILE
static int get_nr_ram_ranges_callback(unsigned long start_pfn,
unsigned long nr_pfn, void *arg)
{
@@ -696,5 +695,4 @@ int crash_load_segments(struct kimage *image)
return ret;
}
-
-#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_KEXEC_FILE */
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 47c410d99f5d..4b0e1dfa2226 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -683,7 +683,7 @@ END(syscall_badsys)
sysenter_badsys:
movl $-ENOSYS,%eax
jmp sysenter_after_call
-END(syscall_badsys)
+END(sysenter_badsys)
CFI_ENDPROC
.macro FIXUP_ESPFIX_STACK
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 1e6cff5814fa..44f1ed42fdf2 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -203,7 +203,7 @@ void __init native_init_IRQ(void)
set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]);
}
- if (!acpi_ioapic && !of_ioapic)
+ if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs())
setup_irq(2, &irq2);
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 8b04018e5d1f..485981059a40 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -25,9 +25,11 @@
#include <asm/debugreg.h>
#include <asm/kexec-bzimage64.h>
+#ifdef CONFIG_KEXEC_FILE
static struct kexec_file_ops *kexec_file_loaders[] = {
&kexec_bzImage64_ops,
};
+#endif
static void free_transition_pgtable(struct kimage *image)
{
@@ -178,6 +180,7 @@ static void load_segments(void)
);
}
+#ifdef CONFIG_KEXEC_FILE
/* Update purgatory as needed after various image segments have been prepared */
static int arch_update_purgatory(struct kimage *image)
{
@@ -209,6 +212,12 @@ static int arch_update_purgatory(struct kimage *image)
return ret;
}
+#else /* !CONFIG_KEXEC_FILE */
+static inline int arch_update_purgatory(struct kimage *image)
+{
+ return 0;
+}
+#endif /* CONFIG_KEXEC_FILE */
int machine_kexec_prepare(struct kimage *image)
{
@@ -329,6 +338,7 @@ void arch_crash_save_vmcoreinfo(void)
/* arch-dependent functionality related to kexec file-based syscall */
+#ifdef CONFIG_KEXEC_FILE
int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
unsigned long buf_len)
{
@@ -522,3 +532,4 @@ overflow:
(int)ELF64_R_TYPE(rel[i].r_info), value);
return -ENOEXEC;
}
+#endif /* CONFIG_KEXEC_FILE */
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index bf7ef5ce29df..0fa29609b2c4 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -68,6 +68,8 @@ static struct irqaction irq0 = {
void __init setup_default_timer_irq(void)
{
+ if (!nr_legacy_irqs())
+ return;
setup_irq(0, &irq0);
}
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 56657b0bb3bb..03954f7900f5 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1491,9 +1491,6 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
goto exception;
break;
case VCPU_SREG_CS:
- if (in_task_switch && rpl != dpl)
- goto exception;
-
if (!(seg_desc.type & 8))
goto exception;
@@ -4394,8 +4391,11 @@ done_prefixes:
ctxt->execute = opcode.u.execute;
+ if (unlikely(ctxt->ud) && likely(!(ctxt->d & EmulateOnUD)))
+ return EMULATION_FAILED;
+
if (unlikely(ctxt->d &
- (NotImpl|EmulateOnUD|Stack|Op3264|Sse|Mmx|Intercept|CheckPerm))) {
+ (NotImpl|Stack|Op3264|Sse|Mmx|Intercept|CheckPerm))) {
/*
* These are copied unconditionally here, and checked unconditionally
* in x86_emulate_insn.
@@ -4406,9 +4406,6 @@ done_prefixes:
if (ctxt->d & NotImpl)
return EMULATION_FAILED;
- if (!(ctxt->d & EmulateOnUD) && ctxt->ud)
- return EMULATION_FAILED;
-
if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack))
ctxt->op_bytes = 8;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 1fe33987de02..ee61c36d64f8 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -49,7 +49,13 @@ void leave_mm(int cpu)
if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) {
cpumask_clear_cpu(cpu, mm_cpumask(active_mm));
load_cr3(swapper_pg_dir);
- trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+ /*
+ * This gets called in the idle path where RCU
+ * functions differently. Tracing normally
+ * uses RCU, so we have to call the tracepoint
+ * specially here.
+ */
+ trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
}
}
EXPORT_SYMBOL_GPL(leave_mm);
@@ -174,7 +180,7 @@ void flush_tlb_current_task(void)
*
* This is in units of pages.
*/
-unsigned long tlb_single_page_flush_ceiling = 33;
+static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
unsigned long end, unsigned long vmflag)
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 3865116c51fb..b9958c364075 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -229,7 +229,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
static void intel_mid_pci_irq_disable(struct pci_dev *dev)
{
- if (!dev->dev.power.is_prepared && dev->irq > 0)
+ if (!mp_should_keep_irq(&dev->dev) && dev->irq > 0)
mp_unmap_irq(dev->irq);
}
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index bc1a2c341891..eb500c2592ad 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -1256,7 +1256,7 @@ static int pirq_enable_irq(struct pci_dev *dev)
static void pirq_disable_irq(struct pci_dev *dev)
{
- if (io_apic_assign_pci_irqs && !dev->dev.power.is_prepared &&
+ if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) &&
dev->irq) {
mp_unmap_irq(dev->irq);
dev->irq = 0;
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 7fde9ee438a4..899dd2454256 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -11,6 +11,7 @@ targets += purgatory.ro
# sure how to relocate those. Like kexec-tools, use custom flags.
KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -MD -Os -mcmodel=large
+KBUILD_CFLAGS += -m$(BITS)
$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
$(call if_changed,ld)
@@ -24,7 +25,4 @@ $(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
$(call if_changed,bin2c)
-# No loaders for 32bits yet.
-ifeq ($(CONFIG_X86_64),y)
- obj-$(CONFIG_KEXEC) += kexec-purgatory.o
-endif
+obj-$(CONFIG_KEXEC_FILE) += kexec-purgatory.o
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-20 18:21:49 +0000