def_bool y
depends on KPROBES || PERF_EVENTS || UPROBES
-config PERF_EVENTS_INTEL_UNCORE
- def_bool y
- depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
-
config OUTPUT_FORMAT
string
default "elf32-i386" if X86_32
def_bool y
depends on X86_MCE_INTEL
+source "arch/x86/events/Kconfig"
+
config X86_LEGACY_VM86
bool "Legacy VM86 support"
default n
def_bool y
depends on MICROCODE
-config PERF_EVENTS_AMD_POWER
- depends on PERF_EVENTS && CPU_SUP_AMD
- tristate "AMD Processor Power Reporting Mechanism"
- ---help---
- Provide power reporting mechanism support for AMD processors.
- Currently, it leverages X86_FEATURE_ACC_POWER
- (CPUID Fn8000_0007_EDX[12]) interface to calculate the
- average power consumption on Family 15h processors.
-
config X86_MSR
tristate "/dev/cpu/*/msr - Model-specific register support"
---help---
(CONFIG_PHYSICAL_START) is used as the minimum location.
config RANDOMIZE_BASE
- bool "Randomize the address of the kernel image"
+ bool "Randomize the address of the kernel image (KASLR)"
depends on RELOCATABLE
default n
---help---
- Randomizes the physical and virtual address at which the
- kernel image is decompressed, as a security feature that
- deters exploit attempts relying on knowledge of the location
- of kernel internals.
+ In support of Kernel Address Space Layout Randomization (KASLR),
+ this randomizes the physical address at which the kernel image
+ is decompressed and the virtual address where the kernel
+ image is mapped, as a security feature that deters exploit
+ attempts relying on knowledge of the location of kernel
+ code internals.
+
+ The kernel physical and virtual address can be randomized
+ from 16MB up to 1GB on 64-bit and 512MB on 32-bit. (Note that
+ using RANDOMIZE_BASE reduces the memory space available to
+ kernel modules from 1.5GB to 1GB.)
+
+ Entropy is generated using the RDRAND instruction if it is
+ supported. If RDTSC is supported, its value is mixed into
+ the entropy pool as well. If neither RDRAND nor RDTSC are
+ supported, then entropy is read from the i8254 timer.
+
+ Since the kernel is built using 2GB addressing, and
+ PHYSICAL_ALIGN must be at a minimum of 2MB, only 10 bits of
+ entropy is theoretically possible. Currently, with the
+ default value for PHYSICAL_ALIGN and due to page table
+ layouts, 64-bit uses 9 bits of entropy and 32-bit uses 8 bits.
+
+ If CONFIG_HIBERNATE is also enabled, KASLR is disabled at boot
+ time. To enable it, boot with "kaslr" on the kernel command
+ line (which will also disable hibernation).
- Entropy is generated using the RDRAND instruction if it is
- supported. If RDTSC is supported, it is used as well. If
- neither RDRAND nor RDTSC are supported, then randomness is
- read from the i8254 timer.
-
- The kernel will be offset by up to RANDOMIZE_BASE_MAX_OFFSET,
- and aligned according to PHYSICAL_ALIGN. Since the kernel is
- built using 2GiB addressing, and PHYSICAL_ALGIN must be at a
- minimum of 2MiB, only 10 bits of entropy is theoretically
- possible. At best, due to page table layouts, 64-bit can use
- 9 bits of entropy and 32-bit uses 8 bits.
-
- If unsure, say N.
-
- config RANDOMIZE_BASE_MAX_OFFSET
- hex "Maximum kASLR offset allowed" if EXPERT
- depends on RANDOMIZE_BASE
- range 0x0 0x20000000 if X86_32
- default "0x20000000" if X86_32
- range 0x0 0x40000000 if X86_64
- default "0x40000000" if X86_64
- ---help---
- The lesser of RANDOMIZE_BASE_MAX_OFFSET and available physical
- memory is used to determine the maximal offset in bytes that will
- be applied to the kernel when kernel Address Space Layout
- Randomization (kASLR) is active. This must be a multiple of
- PHYSICAL_ALIGN.
-
- On 32-bit this is limited to 512MiB by page table layouts. The
- default is 512MiB.
-
- On 64-bit this is limited by how the kernel fixmap page table is
- positioned, so this cannot be larger than 1GiB currently. Without
- RANDOMIZE_BASE, there is a 512MiB to 1.5GiB split between kernel
- and modules. When RANDOMIZE_BASE_MAX_OFFSET is above 512MiB, the
- modules area will shrink to compensate, up to the current maximum
- 1GiB to 1GiB split. The default is 1GiB.
-
- If unsure, leave at the default value.
+ If unsure, say N.
# Relocation on x86 needs some additional build support
config X86_NEED_RELOCS
#include <linux/cpumask.h>
#include <asm/frame.h>
- static inline int paravirt_enabled(void)
- {
- return pv_info.paravirt_enabled;
- }
-
- static inline int paravirt_has_feature(unsigned int feature)
- {
- WARN_ON_ONCE(!pv_info.paravirt_enabled);
- return (pv_info.features & feature);
- }
-
static inline void load_sp0(struct tss_struct *tss,
struct thread_struct *thread)
{
#define get_kernel_rpl() (pv_info.kernel_rpl)
-static inline u64 paravirt_read_msr(unsigned msr, int *err)
+static inline u64 paravirt_read_msr(unsigned msr)
{
- return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
+ return PVOP_CALL1(u64, pv_cpu_ops.read_msr, msr);
}
-static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
+static inline void paravirt_write_msr(unsigned msr,
+ unsigned low, unsigned high)
{
- return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
+ return PVOP_VCALL3(pv_cpu_ops.write_msr, msr, low, high);
+}
+
+static inline u64 paravirt_read_msr_safe(unsigned msr, int *err)
+{
+ return PVOP_CALL2(u64, pv_cpu_ops.read_msr_safe, msr, err);
+}
+
+static inline int paravirt_write_msr_safe(unsigned msr,
+ unsigned low, unsigned high)
+{
+ return PVOP_CALL3(int, pv_cpu_ops.write_msr_safe, msr, low, high);
}
-/* These should all do BUG_ON(_err), but our headers are too tangled. */
#define rdmsr(msr, val1, val2) \
do { \
- int _err; \
- u64 _l = paravirt_read_msr(msr, &_err); \
+ u64 _l = paravirt_read_msr(msr); \
val1 = (u32)_l; \
val2 = _l >> 32; \
} while (0)
#define rdmsrl(msr, val) \
do { \
- int _err; \
- val = paravirt_read_msr(msr, &_err); \
+ val = paravirt_read_msr(msr); \
} while (0)
static inline void wrmsrl(unsigned msr, u64 val)
wrmsr(msr, (u32)val, (u32)(val>>32));
}
-#define wrmsr_safe(msr, a, b) paravirt_write_msr(msr, a, b)
+#define wrmsr_safe(msr, a, b) paravirt_write_msr_safe(msr, a, b)
/* rdmsr with exception handling */
-#define rdmsr_safe(msr, a, b) \
-({ \
- int _err; \
- u64 _l = paravirt_read_msr(msr, &_err); \
- (*a) = (u32)_l; \
- (*b) = _l >> 32; \
- _err; \
+#define rdmsr_safe(msr, a, b) \
+({ \
+ int _err; \
+ u64 _l = paravirt_read_msr_safe(msr, &_err); \
+ (*a) = (u32)_l; \
+ (*b) = _l >> 32; \
+ _err; \
})
static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
{
int err;
- *p = paravirt_read_msr(msr, &err);
+ *p = paravirt_read_msr_safe(msr, &err);
return err;
}
u16 extra_user_64bit_cs; /* __USER_CS if none */
#endif
- int paravirt_enabled;
- unsigned int features; /* valid only if paravirt_enabled is set */
const char *name;
};
- #define paravirt_has(x) paravirt_has_feature(PV_SUPPORTED_##x)
- /* Supported features */
- #define PV_SUPPORTED_RTC (1<<0)
-
struct pv_init_ops {
/*
* Patch may replace one of the defined code sequences with
void (*cpuid)(unsigned int *eax, unsigned int *ebx,
unsigned int *ecx, unsigned int *edx);
- /* MSR, PMC and TSR operations.
- err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */
- u64 (*read_msr)(unsigned int msr, int *err);
- int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
+ /* Unsafe MSR operations. These will warn or panic on failure. */
+ u64 (*read_msr)(unsigned int msr);
+ void (*write_msr)(unsigned int msr, unsigned low, unsigned high);
+
+ /*
+ * Safe MSR operations.
+ * read sets err to 0 or -EIO. write returns 0 or -EIO.
+ */
+ u64 (*read_msr_safe)(unsigned int msr, int *err);
+ int (*write_msr_safe)(unsigned int msr, unsigned low, unsigned high);
u64 (*read_pmc)(int counter);
unsigned long ip;
#endif
#ifdef CONFIG_X86_64
- unsigned long fs;
+ unsigned long fsbase;
+ unsigned long gsbase;
+#else
+ /*
+ * XXX: this could presumably be unsigned short. Alternatively,
+ * 32-bit kernels could be taught to use fsindex instead.
+ */
+ unsigned long fs;
+ unsigned long gs;
#endif
- unsigned long gs;
/* Save middle states of ptrace breakpoints */
struct perf_event *ptrace_bps[HBP_NUM];
#include <asm/paravirt.h>
#else
#define __cpuid native_cpuid
- #define paravirt_enabled() 0
- #define paravirt_has(x) 0
static inline void load_sp0(struct tss_struct *tss,
struct thread_struct *thread)
{
struct acpi_table_madt *madt = NULL;
- if (!cpu_has_apic)
+ if (!boot_cpu_has(X86_FEATURE_APIC))
return -EINVAL;
madt = (struct acpi_table_madt *)table;
static int __init acpi_parse_fadt(struct acpi_table_header *table)
{
+ if (!(acpi_gbl_FADT.boot_flags & ACPI_FADT_LEGACY_DEVICES)) {
+ pr_debug("ACPI: no legacy devices present\n");
+ x86_platform.legacy.devices.pnpbios = 0;
+ }
+
+ if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) {
+ pr_debug("ACPI: not registering RTC platform device\n");
+ x86_platform.legacy.rtc = 0;
+ }
#ifdef CONFIG_X86_PM_TIMER
/* detect the location of the ACPI PM Timer */
{
int count;
- if (!cpu_has_apic)
+ if (!boot_cpu_has(X86_FEATURE_APIC))
return -ENODEV;
/*
int ret;
struct acpi_subtable_proc madt_proc[2];
- if (!cpu_has_apic)
+ if (!boot_cpu_has(X86_FEATURE_APIC))
return -ENODEV;
/*
if (acpi_disabled || acpi_noirq)
return -ENODEV;
- if (!cpu_has_apic)
+ if (!boot_cpu_has(X86_FEATURE_APIC))
return -ENODEV;
/*
* the TLB when any changes are made to any of the page table entries.
* The operating system must reload CR3 to cause the TLB to be flushed"
*
- * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should
- * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
- * to be modified
+ * As a result, boot_cpu_has(X86_FEATURE_PGE) in arch/x86/include/asm/tlbflush.h
+ * should be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
+ * to be modified.
*/
if (c->x86 == 5 && c->x86_model == 9) {
pr_info("Disabling PGE capability bit\n");
* The Quark is also family 5, but does not have the same bug.
*/
clear_cpu_bug(c, X86_BUG_F00F);
- if (!paravirt_enabled() && c->x86 == 5 && c->x86_model < 9) {
+ if (c->x86 == 5 && c->x86_model < 9) {
static int f00f_workaround_enabled;
set_cpu_bug(c, X86_BUG_F00F);
* integrated APIC (see 11AP erratum in "Pentium Processor
* Specification Update").
*/
- if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
+ if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
(c->x86_mask < 0x6 || c->x86_mask == 0xb))
set_cpu_bug(c, X86_BUG_11AP);
{
unsigned int eax, ebx, ecx, edx;
- if (c->cpuid_level < 4)
+ if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4)
return 1;
/* Intel has a non-standard dependency on %ecx for this CPUID level. */
set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
}
- if (cpu_has_xmm2)
+ if (cpu_has(c, X86_FEATURE_XMM2))
set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
if (boot_cpu_has(X86_FEATURE_DS)) {
set_cpu_cap(c, X86_FEATURE_PEBS);
}
- if (c->x86 == 6 && cpu_has_clflush &&
+ if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_CLFLUSH) &&
(c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR);
{
pv_info.name = "KVM";
- /*
- * KVM isn't paravirt in the sense of paravirt_enabled. A KVM
- * guest kernel works like a bare metal kernel with additional
- * features, and paravirt_enabled is about features that are
- * missing.
- */
- pv_info.paravirt_enabled = 0;
-
if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
pv_cpu_ops.io_delay = kvm_io_delay;
if (boot_cpu_data.cpuid_level < 0)
return 0; /* So we don't blow up on old processors */
- if (cpu_has_hypervisor)
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0);
return 0;
struct pv_info pv_info = {
.name = "bare hardware",
- .paravirt_enabled = 0,
.kernel_rpl = 0,
.shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */
.write_cr8 = native_write_cr8,
#endif
.wbinvd = native_wbinvd,
- .read_msr = native_read_msr_safe,
- .write_msr = native_write_msr_safe,
+ .read_msr = native_read_msr,
+ .write_msr = native_write_msr,
+ .read_msr_safe = native_read_msr_safe,
+ .write_msr_safe = native_write_msr_safe,
.read_pmc = native_read_pmc,
.load_tr_desc = native_load_tr_desc,
.set_ldt = native_set_ldt,
*/
mapping_iter = 1;
- if (!cpu_has_pse)
+ if (!boot_cpu_has(X86_FEATURE_PSE))
use_pse = 0;
repeat:
BUILD_BUG_ON(VMALLOC_START >= VMALLOC_END);
#undef high_memory
#undef __FIXADDR_TOP
- #ifdef CONFIG_RANDOMIZE_BASE
- BUILD_BUG_ON(CONFIG_RANDOMIZE_BASE_MAX_OFFSET > KERNEL_IMAGE_SIZE);
- #endif
#ifdef CONFIG_HIGHMEM
BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE > FIXADDR_START);
#include "mm_internal.h"
- static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page,
- unsigned long addr, unsigned long end)
- {
- addr &= PMD_MASK;
- for (; addr < end; addr += PMD_SIZE) {
- pmd_t *pmd = pmd_page + pmd_index(addr);
-
- if (!pmd_present(*pmd))
- set_pmd(pmd, __pmd(addr | pmd_flag));
- }
- }
- static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
- unsigned long addr, unsigned long end)
- {
- unsigned long next;
-
- for (; addr < end; addr = next) {
- pud_t *pud = pud_page + pud_index(addr);
- pmd_t *pmd;
-
- next = (addr & PUD_MASK) + PUD_SIZE;
- if (next > end)
- next = end;
-
- if (pud_present(*pud)) {
- pmd = pmd_offset(pud, 0);
- ident_pmd_init(info->pmd_flag, pmd, addr, next);
- continue;
- }
- pmd = (pmd_t *)info->alloc_pgt_page(info->context);
- if (!pmd)
- return -ENOMEM;
- ident_pmd_init(info->pmd_flag, pmd, addr, next);
- set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
- }
-
- return 0;
- }
-
- int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
- unsigned long addr, unsigned long end)
- {
- unsigned long next;
- int result;
- int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0;
-
- for (; addr < end; addr = next) {
- pgd_t *pgd = pgd_page + pgd_index(addr) + off;
- pud_t *pud;
-
- next = (addr & PGDIR_MASK) + PGDIR_SIZE;
- if (next > end)
- next = end;
-
- if (pgd_present(*pgd)) {
- pud = pud_offset(pgd, 0);
- result = ident_pud_init(info, pud, addr, next);
- if (result)
- return result;
- continue;
- }
-
- pud = (pud_t *)info->alloc_pgt_page(info->context);
- if (!pud)
- return -ENOMEM;
- result = ident_pud_init(info, pud, addr, next);
- if (result)
- return result;
- set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
- }
-
- return 0;
- }
+ #include "ident_map.c"
/*
* NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
struct vmem_altmap *altmap = to_vmem_altmap(start);
int err;
- if (cpu_has_pse)
+ if (boot_cpu_has(X86_FEATURE_PSE))
err = vmemmap_populate_hugepages(start, end, node, altmap);
else if (altmap) {
pr_err_once("%s: no cpu support for altmap allocations\n",
}
get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO);
- if (!cpu_has_pse) {
+ if (!boot_cpu_has(X86_FEATURE_PSE)) {
next = (addr + PAGE_SIZE) & PAGE_MASK;
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd))
#include <asm/mach_traps.h>
#include <asm/mwait.h>
#include <asm/pci_x86.h>
-#include <asm/pat.h>
#include <asm/cpu.h>
#ifdef CONFIG_ACPI
return ret;
}
+static u64 xen_read_msr(unsigned int msr)
+{
+ /*
+ * This will silently swallow a #GP from RDMSR. It may be worth
+ * changing that.
+ */
+ int err;
+
+ return xen_read_msr_safe(msr, &err);
+}
+
+static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
+{
+ /*
+ * This will silently swallow a #GP from WRMSR. It may be worth
+ * changing that.
+ */
+ xen_write_msr_safe(msr, low, high);
+}
+
void xen_setup_shared_info(void)
{
if (!xen_feature(XENFEAT_auto_translated_physmap)) {
}
static const struct pv_info xen_info __initconst = {
- .paravirt_enabled = 1,
.shared_kernel_pmd = 0,
#ifdef CONFIG_X86_64
.extra_user_64bit_cs = FLAT_USER_CS64,
#endif
- .features = 0,
.name = "Xen",
};
.wbinvd = native_wbinvd,
- .read_msr = xen_read_msr_safe,
- .write_msr = xen_write_msr_safe,
+ .read_msr = xen_read_msr,
+ .write_msr = xen_write_msr,
+
+ .read_msr_safe = xen_read_msr_safe,
+ .write_msr_safe = xen_write_msr_safe,
.read_pmc = xen_read_pmc,
* For BSP, PSE PGE are set in probe_page_size_mask(), for APs
* set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu().
*/
- if (cpu_has_pse)
+ if (boot_cpu_has(X86_FEATURE_PSE))
cr4_set_bits_and_update_boot(X86_CR4_PSE);
- if (cpu_has_pge)
+ if (boot_cpu_has(X86_FEATURE_PGE))
cr4_set_bits_and_update_boot(X86_CR4_PGE);
}
}
#endif /* CONFIG_XEN_PVH */
+ static void __init xen_dom0_set_legacy_features(void)
+ {
+ x86_platform.legacy.rtc = 1;
+ }
+
/* First C function to be called on Xen boot */
asmlinkage __visible void __init xen_start_kernel(void)
{
struct physdev_set_iopl set_iopl;
unsigned long initrd_start = 0;
- u64 pat;
int rc;
if (!xen_start_info)
/* Install Xen paravirt ops */
pv_info = xen_info;
- if (xen_initial_domain())
- pv_info.features |= PV_SUPPORTED_RTC;
pv_init_ops = xen_init_ops;
if (!xen_pvh_domain()) {
pv_cpu_ops = xen_cpu_ops;
xen_start_info->nr_pages);
xen_reserve_special_pages();
- /*
- * Modify the cache mode translation tables to match Xen's PAT
- * configuration.
- */
- rdmsrl(MSR_IA32_CR_PAT, pat);
- pat_init_cache_modes(pat);
-
/* keep using Xen gdt for now; no urgent need to change it */
#ifdef CONFIG_X86_32
boot_params.hdr.ramdisk_image = initrd_start;
boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line);
+ boot_params.hdr.hardware_subarch = X86_SUBARCH_XEN;
if (!xen_initial_domain()) {
add_preferred_console("xenboot", 0, NULL);
.u.firmware_info.type = XEN_FW_KBD_SHIFT_FLAGS,
};
+ x86_platform.set_legacy_features =
+ xen_dom0_set_legacy_features;
xen_init_vga(info, xen_start_info->console.dom0.info_size);
xen_start_info->console.domU.mfn = 0;
xen_start_info->console.domU.evtchn = 0;