aboutsummaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig7
-rw-r--r--arch/x86/boot/compressed/eboot.c121
-rw-r--r--arch/x86/boot/compressed/eboot.h52
-rw-r--r--arch/x86/include/asm/dma-contiguous.h1
-rw-r--r--arch/x86/include/asm/efi.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h15
-rw-r--r--arch/x86/include/uapi/asm/kvm.h6
-rw-r--r--arch/x86/kernel/devicetree.c3
-rw-r--r--arch/x86/kernel/reboot.c12
-rw-r--r--arch/x86/kernel/setup.c6
-rw-r--r--arch/x86/kvm/Kconfig2
-rw-r--r--arch/x86/kvm/Makefile13
-rw-r--r--arch/x86/kvm/cpuid.c57
-rw-r--r--arch/x86/kvm/cpuid.h5
-rw-r--r--arch/x86/kvm/mmu.c6
-rw-r--r--arch/x86/kvm/paging_tmpl.h20
-rw-r--r--arch/x86/kvm/svm.c4
-rw-r--r--arch/x86/kvm/vmx.c4
-rw-r--r--arch/x86/kvm/x86.c50
-rw-r--r--arch/x86/mm/hugetlbpage.c187
-rw-r--r--arch/x86/platform/efi/efi.c149
21 files changed, 249 insertions, 473 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4e5b80d883c8..b2c486f615df 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -21,6 +21,7 @@ config X86_64
config X86
def_bool y
select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+ select ARCH_HAS_GCOV_PROFILE_ALL
select HAVE_AOUT if X86_32
select HAVE_UNSTABLE_SCHED_CLOCK
select ARCH_SUPPORTS_NUMA_BALANCING
@@ -208,6 +209,12 @@ config ARCH_HIBERNATION_POSSIBLE
config ARCH_SUSPEND_POSSIBLE
def_bool y
+config ARCH_WANT_HUGE_PMD_SHARE
+ def_bool y
+
+config ARCH_WANT_GENERAL_HUGETLB
+ def_bool y
+
config ZONE_DMA32
bool
default X86_64
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 1308beed7abe..17177e80d466 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -878,14 +878,15 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
struct efi_info *efi;
efi_loaded_image_t *image;
void *options;
- u32 load_options_size;
efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
int options_size = 0;
efi_status_t status;
- unsigned long cmdline;
+ char *cmdline_ptr;
u16 *s2;
u8 *s1;
int i;
+ unsigned long ramdisk_addr;
+ unsigned long ramdisk_size;
sys_table = _table;
@@ -896,13 +897,14 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
status = efi_call_phys3(sys_table->boottime->handle_protocol,
handle, &proto, (void *)&image);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
+ efi_printk(sys_table, "Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
return NULL;
}
- status = low_alloc(0x4000, 1, (unsigned long *)&boot_params);
+ status = efi_low_alloc(sys_table, 0x4000, 1,
+ (unsigned long *)&boot_params);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc lowmem for boot params\n");
+ efi_printk(sys_table, "Failed to alloc lowmem for boot params\n");
return NULL;
}
@@ -927,40 +929,10 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
hdr->type_of_loader = 0x21;
/* Convert unicode cmdline to ascii */
- options = image->load_options;
- load_options_size = image->load_options_size / 2; /* ASCII */
- cmdline = 0;
- s2 = (u16 *)options;
-
- if (s2) {
- while (*s2 && *s2 != '\n' && options_size < load_options_size) {
- s2++;
- options_size++;
- }
-
- if (options_size) {
- if (options_size > hdr->cmdline_size)
- options_size = hdr->cmdline_size;
-
- options_size++; /* NUL termination */
-
- status = low_alloc(options_size, 1, &cmdline);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for cmdline\n");
- goto fail;
- }
-
- s1 = (u8 *)(unsigned long)cmdline;
- s2 = (u16 *)options;
-
- for (i = 0; i < options_size - 1; i++)
- *s1++ = *s2++;
-
- *s1 = '\0';
- }
- }
-
- hdr->cmd_line_ptr = cmdline;
+ cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size);
+ if (!cmdline_ptr)
+ goto fail;
+ hdr->cmd_line_ptr = (unsigned long)cmdline_ptr;
hdr->ramdisk_image = 0;
hdr->ramdisk_size = 0;
@@ -970,16 +942,20 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
memset(sdt, 0, sizeof(*sdt));
- status = handle_ramdisks(image, hdr);
+ status = handle_cmdline_files(sys_table, image,
+ (char *)(unsigned long)hdr->cmd_line_ptr,
+ "initrd=", hdr->initrd_addr_max,
+ &ramdisk_addr, &ramdisk_size);
if (status != EFI_SUCCESS)
goto fail2;
+ hdr->ramdisk_image = ramdisk_addr;
+ hdr->ramdisk_size = ramdisk_size;
return boot_params;
fail2:
- if (options_size)
- low_free(options_size, hdr->cmd_line_ptr);
+ efi_free(sys_table, options_size, hdr->cmd_line_ptr);
fail:
- low_free(0x4000, (unsigned long)boot_params);
+ efi_free(sys_table, 0x4000, (unsigned long)boot_params);
return NULL;
}
@@ -1002,7 +978,7 @@ static efi_status_t exit_boot(struct boot_params *boot_params,
again:
size += sizeof(*mem_map) * 2;
_size = size;
- status = low_alloc(size, 1, (unsigned long *)&mem_map);
+ status = efi_low_alloc(sys_table, size, 1, (unsigned long *)&mem_map);
if (status != EFI_SUCCESS)
return status;
@@ -1010,7 +986,7 @@ get_map:
status = efi_call_phys5(sys_table->boottime->get_memory_map, &size,
mem_map, &key, &desc_size, &desc_version);
if (status == EFI_BUFFER_TOO_SMALL) {
- low_free(_size, (unsigned long)mem_map);
+ efi_free(sys_table, _size, (unsigned long)mem_map);
goto again;
}
@@ -1112,44 +1088,10 @@ get_map:
return EFI_SUCCESS;
free_mem_map:
- low_free(_size, (unsigned long)mem_map);
+ efi_free(sys_table, _size, (unsigned long)mem_map);
return status;
}
-static efi_status_t relocate_kernel(struct setup_header *hdr)
-{
- unsigned long start, nr_pages;
- efi_status_t status;
-
- /*
- * The EFI firmware loader could have placed the kernel image
- * anywhere in memory, but the kernel has various restrictions
- * on the max physical address it can run at. Attempt to move
- * the kernel to boot_params.pref_address, or as low as
- * possible.
- */
- start = hdr->pref_address;
- nr_pages = round_up(hdr->init_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
-
- status = efi_call_phys4(sys_table->boottime->allocate_pages,
- EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
- nr_pages, &start);
- if (status != EFI_SUCCESS) {
- status = low_alloc(hdr->init_size, hdr->kernel_alignment,
- &start);
- if (status != EFI_SUCCESS)
- efi_printk("Failed to alloc mem for kernel\n");
- }
-
- if (status == EFI_SUCCESS)
- memcpy((void *)start, (void *)(unsigned long)hdr->code32_start,
- hdr->init_size);
-
- hdr->pref_address = hdr->code32_start;
- hdr->code32_start = (__u32)start;
-
- return status;
-}
/*
* On success we return a pointer to a boot_params structure, and NULL
@@ -1178,14 +1120,15 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
EFI_LOADER_DATA, sizeof(*gdt),
(void **)&gdt);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for gdt structure\n");
+ efi_printk(sys_table, "Failed to alloc mem for gdt structure\n");
goto fail;
}
gdt->size = 0x800;
- status = low_alloc(gdt->size, 8, (unsigned long *)&gdt->address);
+ status = efi_low_alloc(sys_table, gdt->size, 8,
+ (unsigned long *)&gdt->address);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for gdt\n");
+ efi_printk(sys_table, "Failed to alloc mem for gdt\n");
goto fail;
}
@@ -1193,7 +1136,7 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
EFI_LOADER_DATA, sizeof(*idt),
(void **)&idt);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for idt structure\n");
+ efi_printk(sys_table, "Failed to alloc mem for idt structure\n");
goto fail;
}
@@ -1205,10 +1148,16 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
* address, relocate it.
*/
if (hdr->pref_address != hdr->code32_start) {
- status = relocate_kernel(hdr);
-
+ unsigned long bzimage_addr = hdr->code32_start;
+ status = efi_relocate_kernel(sys_table, &bzimage_addr,
+ hdr->init_size, hdr->init_size,
+ hdr->pref_address,
+ hdr->kernel_alignment);
if (status != EFI_SUCCESS)
goto fail;
+
+ hdr->pref_address = hdr->code32_start;
+ hdr->code32_start = bzimage_addr;
}
status = exit_boot(boot_params, handle);
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index e5b0a8f91c5f..cc78e2da7af9 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -10,8 +10,6 @@
#define SEG_GRANULARITY_4KB (1 << 0)
#define DESC_TYPE_CODE_DATA (1 << 0)
-
-#define EFI_PAGE_SIZE (1UL << EFI_PAGE_SHIFT)
#define EFI_READ_CHUNK_SIZE (1024 * 1024)
#define EFI_CONSOLE_OUT_DEVICE_GUID \
@@ -40,6 +38,24 @@ struct efi_graphics_output_mode_info {
u32 pixels_per_scan_line;
} __packed;
+struct efi_graphics_output_protocol_mode_32 {
+ u32 max_mode;
+ u32 mode;
+ u32 info;
+ u32 size_of_info;
+ u64 frame_buffer_base;
+ u32 frame_buffer_size;
+} __packed;
+
+struct efi_graphics_output_protocol_mode_64 {
+ u32 max_mode;
+ u32 mode;
+ u64 info;
+ u64 size_of_info;
+ u64 frame_buffer_base;
+ u64 frame_buffer_size;
+} __packed;
+
struct efi_graphics_output_protocol_mode {
u32 max_mode;
u32 mode;
@@ -49,6 +65,20 @@ struct efi_graphics_output_protocol_mode {
unsigned long frame_buffer_size;
} __packed;
+struct efi_graphics_output_protocol_32 {
+ u32 query_mode;
+ u32 set_mode;
+ u32 blt;
+ u32 mode;
+};
+
+struct efi_graphics_output_protocol_64 {
+ u64 query_mode;
+ u64 set_mode;
+ u64 blt;
+ u64 mode;
+};
+
struct efi_graphics_output_protocol {
void *query_mode;
unsigned long set_mode;
@@ -56,16 +86,22 @@ struct efi_graphics_output_protocol {
struct efi_graphics_output_protocol_mode *mode;
};
+struct efi_uga_draw_protocol_32 {
+ u32 get_mode;
+ u32 set_mode;
+ u32 blt;
+};
+
+struct efi_uga_draw_protocol_64 {
+ u64 get_mode;
+ u64 set_mode;
+ u64 blt;
+};
+
struct efi_uga_draw_protocol {
void *get_mode;
void *set_mode;
void *blt;
};
-struct efi_simple_text_output_protocol {
- void *reset;
- void *output_string;
- void *test_string;
-};
-
#endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h
index c09241659971..b4b38bacb404 100644
--- a/arch/x86/include/asm/dma-contiguous.h
+++ b/arch/x86/include/asm/dma-contiguous.h
@@ -4,7 +4,6 @@
#ifdef __KERNEL__
#include <linux/types.h>
-#include <asm-generic/dma-contiguous.h>
static inline void
dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 60c89f30c727..7a76dc284166 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -94,7 +94,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
#endif /* CONFIG_X86_32 */
extern int add_efi_memmap;
-extern unsigned long x86_efi_facility;
+extern struct efi_scratch efi_scratch;
extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
extern int efi_memblock_x86_reserve_range(void);
extern void efi_call_phys_prelog(void);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4c481e751e8e..b15a6b5fa341 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -79,6 +79,13 @@
#define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1))
#define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE)
+static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
+{
+ /* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */
+ return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
+ (base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
+}
+
#define SELECTOR_TI_MASK (1 << 2)
#define SELECTOR_RPL_MASK 0x03
@@ -96,10 +103,6 @@
#define ASYNC_PF_PER_VCPU 64
-struct kvm_vcpu;
-struct kvm;
-struct kvm_async_pf;
-
enum kvm_reg {
VCPU_REGS_RAX = 0,
VCPU_REGS_RCX = 1,
@@ -632,8 +635,8 @@ struct msr_data {
struct kvm_x86_ops {
int (*cpu_has_kvm_support)(void); /* __init */
int (*disabled_by_bios)(void); /* __init */
- int (*hardware_enable)(void *dummy);
- void (*hardware_disable)(void *dummy);
+ int (*hardware_enable)(void);
+ void (*hardware_disable)(void);
void (*check_processor_compatibility)(void *rtn);
int (*hardware_setup)(void); /* __init */
void (*hardware_unsetup)(void); /* __exit */
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 5d9a3033b3d7..d3a87780c70b 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -211,9 +211,9 @@ struct kvm_cpuid_entry2 {
__u32 padding[3];
};
-#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1
-#define KVM_CPUID_FLAG_STATEFUL_FUNC 2
-#define KVM_CPUID_FLAG_STATE_READ_NEXT 4
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)
/* for KVM_SET_CPUID2 */
struct kvm_cpuid2 {
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index b1581527a236..2fbad6b9f23c 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -52,8 +52,7 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
}
#ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
- unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
{
initrd_start = (unsigned long)__va(start);
initrd_end = (unsigned long)__va(end);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 90fd1195f276..3876c04feef9 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -36,7 +36,7 @@ void (*pm_power_off)(void);
EXPORT_SYMBOL(pm_power_off);
static const struct desc_ptr no_idt = {};
-static int reboot_mode;
+static enum reboot_mode reboot_mode;
enum reboot_type reboot_type = BOOT_ACPI;
int reboot_force;
@@ -88,11 +88,11 @@ static int __init reboot_setup(char *str)
switch (*str) {
case 'w':
- reboot_mode = 0x1234;
+ reboot_mode = REBOOT_WARM;
break;
case 'c':
- reboot_mode = 0;
+ reboot_mode = REBOOT_COLD;
break;
#ifdef CONFIG_SMP
@@ -552,6 +552,7 @@ static void native_machine_emergency_restart(void)
int i;
int attempt = 0;
int orig_reboot_type = reboot_type;
+ unsigned short mode;
if (reboot_emergency)
emergency_vmx_disable_all();
@@ -559,7 +560,8 @@ static void native_machine_emergency_restart(void)
tboot_shutdown(TB_SHUTDOWN_REBOOT);
/* Tell the BIOS if we want cold or warm reboot */
- *((unsigned short *)__va(0x472)) = reboot_mode;
+ mode = reboot_mode == REBOOT_WARM ? 0x1234 : 0;
+ *((unsigned short *)__va(0x472)) = mode;
for (;;) {
/* Could also try the reset bit in the Hammer NB */
@@ -601,7 +603,7 @@ static void native_machine_emergency_restart(void)
case BOOT_EFI:
if (efi_enabled(EFI_RUNTIME_SERVICES))
- efi.reset_system(reboot_mode ?
+ efi.reset_system(reboot_mode == REBOOT_WARM ?
EFI_RESET_WARM :
EFI_RESET_COLD,
EFI_SUCCESS, 0, NULL);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 91964c663f0d..a3627ade4b15 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -908,11 +908,11 @@ void __init setup_arch(char **cmdline_p)
#ifdef CONFIG_EFI
if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
"EL32", 4)) {
- set_bit(EFI_BOOT, &x86_efi_facility);
+ set_bit(EFI_BOOT, &efi.flags);
} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
"EL64", 4)) {
- set_bit(EFI_BOOT, &x86_efi_facility);
- set_bit(EFI_64BIT, &x86_efi_facility);
+ set_bit(EFI_BOOT, &efi.flags);
+ set_bit(EFI_64BIT, &efi.flags);
}
if (efi_enabled(EFI_BOOT))
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index a47a3e54b964..bdccfb62aa0d 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -27,6 +27,7 @@ config KVM
select MMU_NOTIFIER
select ANON_INODES
select HAVE_KVM_IRQCHIP
+ select HAVE_KVM_IRQFD
select HAVE_KVM_IRQ_ROUTING
select HAVE_KVM_EVENTFD
select KVM_APIC_ARCHITECTURE
@@ -38,6 +39,7 @@ config KVM
select PERF_EVENTS
select HAVE_KVM_MSI
select HAVE_KVM_CPU_RELAX_INTERCEPT
+ select KVM_VFIO
---help---
Support hosting fully virtualized guest machines using hardware
virtualization extensions. You will need a fairly recent
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index d609e1d84048..25d22b2d6509 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -5,12 +5,13 @@ CFLAGS_x86.o := -I.
CFLAGS_svm.o := -I.
CFLAGS_vmx.o := -I.
-kvm-y += $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \
- coalesced_mmio.o irq_comm.o eventfd.o \
- irqchip.o)
-kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(addprefix ../../../virt/kvm/, \
- assigned-dev.o iommu.o)
-kvm-$(CONFIG_KVM_ASYNC_PF) += $(addprefix ../../../virt/kvm/, async_pf.o)
+KVM := ../../../virt/kvm
+
+kvm-y += $(KVM)/kvm_main.o $(KVM)/ioapic.o \
+ $(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o \
+ $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
+kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(KVM)/assigned-dev.o $(KVM)/iommu.o
+kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
i8254.o cpuid.o pmu.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index a20ecb5b6cbf..89d288237b9c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -187,8 +187,14 @@ static bool supported_xcr0_bit(unsigned bit)
#define F(x) bit(X86_FEATURE_##x)
-static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
- u32 index, int *nent, int maxnent)
+static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry,
+ u32 func, u32 index, int *nent, int maxnent)
+{
+ return 0;
+}
+
+static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
+ u32 index, int *nent, int maxnent)
{
int r;
unsigned f_nx = is_efer_nx() ? F(NX) : 0;
@@ -480,6 +486,15 @@ out:
return r;
}
+static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func,
+ u32 idx, int *nent, int maxnent, unsigned int type)
+{
+ if (type == KVM_GET_EMULATED_CPUID)
+ return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent);
+
+ return __do_cpuid_ent(entry, func, idx, nent, maxnent);
+}
+
#undef F
struct kvm_cpuid_param {
@@ -494,8 +509,34 @@ static bool is_centaur_cpu(const struct kvm_cpuid_param *param)
return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR;
}
-int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
- struct kvm_cpuid_entry2 __user *entries)
+static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries,
+ __u32 num_entries, unsigned int ioctl_type)
+{
+ int i;
+
+ if (ioctl_type != KVM_GET_EMULATED_CPUID)
+ return false;
+
+ /*
+ * We want to make sure that ->padding is being passed clean from
+ * userspace in case we want to use it for something in the future.
+ *
+ * Sadly, this wasn't enforced for KVM_GET_SUPPORTED_CPUID and so we
+ * have to give ourselves satisfied only with the emulated side. /me
+ * sheds a tear.
+ */
+ for (i = 0; i < num_entries; i++) {
+ if (entries[i].padding[0] ||
+ entries[i].padding[1] ||
+ entries[i].padding[2])
+ return true;
+ }
+ return false;
+}
+
+int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
+ struct kvm_cpuid_entry2 __user *entries,
+ unsigned int type)
{
struct kvm_cpuid_entry2 *cpuid_entries;
int limit, nent = 0, r = -E2BIG, i;
@@ -512,6 +553,10 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
goto out;
if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
cpuid->nent = KVM_MAX_CPUID_ENTRIES;
+
+ if (sanity_check_entries(entries, cpuid->nent, type))
+ return -EINVAL;
+
r = -ENOMEM;
cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
if (!cpuid_entries)
@@ -525,7 +570,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
continue;
r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx,
- &nent, cpuid->nent);
+ &nent, cpuid->nent, type);
if (r)
goto out_free;
@@ -536,7 +581,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
limit = cpuid_entries[nent - 1].eax;
for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func)
r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx,
- &nent, cpuid->nent);
+ &nent, cpuid->nent, type);
if (r)
goto out_free;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index b7fd07984888..f1e4895174b2 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -6,8 +6,9 @@
void kvm_update_cpuid(struct kvm_vcpu *vcpu);
struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
u32 function, u32 index);
-int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
- struct kvm_cpuid_entry2 __user *entries);
+int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
+ struct kvm_cpuid_entry2 __user *entries,
+ unsigned int type);
int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
struct kvm_cpuid *cpuid,
struct kvm_cpuid_entry __user *entries);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e14b1f8667bb..0cc34f594c2a 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3241,7 +3241,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
arch.direct_map = vcpu->arch.mmu.direct_map;
arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu);
- return kvm_setup_async_pf(vcpu, gva, gfn, &arch);
+ return kvm_setup_async_pf(vcpu, gva, gfn_to_hva(vcpu->kvm, gfn), &arch);
}
static bool can_do_async_pf(struct kvm_vcpu *vcpu)
@@ -4229,7 +4229,7 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
if (nr_to_scan == 0)
goto out;
- raw_spin_lock(&kvm_lock);
+ spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
int idx;
@@ -4265,7 +4265,7 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
break;
}
- raw_spin_unlock(&kvm_lock);
+ spin_unlock(&kvm_lock);
out:
return percpu_counter_read_positive(&kvm_total_used_mmu_pages);
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 7e6090e13237..a6a6370c2010 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -69,6 +69,7 @@ struct guest_walker {
pt_element_t prefetch_ptes[PTE_PREFETCH_NUM];
gpa_t pte_gpa[PT_MAX_FULL_LEVELS];
pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS];
+ bool pte_writable[PT_MAX_FULL_LEVELS];
unsigned pt_access;
unsigned pte_access;
gfn_t gfn;
@@ -130,6 +131,22 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
if (pte == orig_pte)
continue;
+ /*
+ * If the slot is read-only, simply do not process the accessed
+ * and dirty bits. This is the correct thing to do if the slot
+ * is ROM, and page tables in read-as-ROM/write-as-MMIO slots
+ * are only supported if the accessed and dirty bits are already
+ * set in the ROM (so that MMIO writes are never needed).
+ *
+ * Note that NPT does not allow this at all and faults, since
+ * it always wants nested page table entries for the guest
+ * page tables to be writable. And EPT works but will simply
+ * overwrite the read-only memory to set the accessed and dirty
+ * bits.
+ */
+ if (unlikely(!walker->pte_writable[level - 1]))
+ continue;
+
ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte);
if (ret)
return ret;
@@ -204,7 +221,8 @@ retry_walk:
goto error;
real_gfn = gpa_to_gfn(real_gfn);
- host_addr = gfn_to_hva(vcpu->kvm, real_gfn);
+ host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn,
+ &walker->pte_writable[walker->level - 1]);
if (unlikely(kvm_is_error_hva(host_addr)))
goto error;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 8bf40a243d75..03f7d03c92a2 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -606,7 +606,7 @@ static int has_svm(void)
return 1;
}
-static void svm_hardware_disable(void *garbage)
+static void svm_hardware_disable(void)
{
/* Make sure we clean up behind us */
if (static_cpu_has(X86_FEATURE_TSCRATEMSR))
@@ -617,7 +617,7 @@ static void svm_hardware_disable(void *garbage)
amd_pmu_disable_virt();
}
-static int svm_hardware_enable(void *garbage)
+static int svm_hardware_enable(void)
{
struct svm_cpu_data *sd;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 04cc2fa7744f..995fcc40fee9 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2570,7 +2570,7 @@ static void kvm_cpu_vmxon(u64 addr)
: "memory", "cc");
}
-static int hardware_enable(void *garbage)
+static int hardware_enable(void)
{
int cpu = raw_smp_processor_id();
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
@@ -2634,7 +2634,7 @@ static void kvm_cpu_vmxoff(void)
asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
}
-static void hardware_disable(void *garbage)
+static void hardware_disable(void)
{
if (vmm_exclusive) {
vmclear_local_loaded_vmcss();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 41ba726c1ce2..88365f2df594 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -247,7 +247,7 @@ int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
}
EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
-static void drop_user_return_notifiers(void *ignore)
+static void drop_user_return_notifiers(void)
{
unsigned int cpu = smp_processor_id();
struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
@@ -2551,7 +2551,7 @@ out:
return r;
}
-int kvm_dev_ioctl_check_extension(long ext)
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
@@ -2561,6 +2561,7 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
case KVM_CAP_SET_TSS_ADDR:
case KVM_CAP_EXT_CPUID:
+ case KVM_CAP_EXT_EMUL_CPUID:
case KVM_CAP_CLOCKSOURCE:
case KVM_CAP_PIT:
case KVM_CAP_NOP_IO_DELAY:
@@ -2670,15 +2671,17 @@ long kvm_arch_dev_ioctl(struct file *filp,
r = 0;
break;
}
- case KVM_GET_SUPPORTED_CPUID: {
+ case KVM_GET_SUPPORTED_CPUID:
+ case KVM_GET_EMULATED_CPUID: {
struct kvm_cpuid2 __user *cpuid_arg = argp;
struct kvm_cpuid2 cpuid;
r = -EFAULT;
if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
goto out;
- r = kvm_dev_ioctl_get_supported_cpuid(&cpuid,
- cpuid_arg->entries);
+
+ r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries,
+ ioctl);
if (r)
goto out;
@@ -5154,7 +5157,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
- raw_spin_lock(&kvm_lock);
+ spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
kvm_for_each_vcpu(i, vcpu, kvm) {
if (vcpu->cpu != freq->cpu)
@@ -5164,7 +5167,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
send_ipi = 1;
}
}
- raw_spin_unlock(&kvm_lock);
+ spin_unlock(&kvm_lock);
if (freq->old < freq->new && send_ipi) {
/*
@@ -5311,12 +5314,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
struct kvm_vcpu *vcpu;
int i;
- raw_spin_lock(&kvm_lock);
+ spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
kvm_for_each_vcpu(i, vcpu, kvm)
set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests);
atomic_set(&kvm_guest_has_master_clock, 0);
- raw_spin_unlock(&kvm_lock);
+ spin_unlock(&kvm_lock);
}
static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);
@@ -5959,7 +5962,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
}
if (need_resched()) {
srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
- kvm_resched(vcpu);
+ cond_resched();
vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
}
}
@@ -6613,7 +6616,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector)
kvm_rip_write(vcpu, 0);
}
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
{
struct kvm *kvm;
struct kvm_vcpu *vcpu;
@@ -6624,7 +6627,7 @@ int kvm_arch_hardware_enable(void *garbage)
bool stable, backwards_tsc = false;
kvm_shared_msr_cpu_online();
- ret = kvm_x86_ops->hardware_enable(garbage);
+ ret = kvm_x86_ops->hardware_enable();
if (ret != 0)
return ret;
@@ -6704,10 +6707,10 @@ int kvm_arch_hardware_enable(void *garbage)
return 0;
}
-void kvm_arch_hardware_disable(void *garbage)
+void kvm_arch_hardware_disable(void)
{
- kvm_x86_ops->hardware_disable(garbage);
- drop_user_return_notifiers(garbage);
+ kvm_x86_ops->hardware_disable();
+ drop_user_return_notifiers();
}
int kvm_arch_hardware_setup(void)
@@ -6819,6 +6822,10 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
static_key_slow_dec(&kvm_no_apic_vcpu);
}
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
if (type)
@@ -6910,7 +6917,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
}
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
struct kvm_memory_slot *dont)
{
int i;
@@ -6931,7 +6938,8 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free,
}
}
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+ unsigned long npages)
{
int i;
@@ -6989,6 +6997,10 @@ out_free:
return -ENOMEM;
}
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+}
+
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
struct kvm_userspace_memory_region *mem,
@@ -7127,7 +7139,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
int r;
if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) ||
- is_error_page(work->page))
+ work->wakeup_all)
return;
r = kvm_mmu_reload(vcpu);
@@ -7237,7 +7249,7 @@ 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 (is_error_page(work->page))
+ if (work->wakeup_all)
work->arch.token = ~0; /* broadcast wakeup */
else
kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index ae1aa71d0115..7e73e8c69096 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -16,169 +16,6 @@
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
-static unsigned long page_table_shareable(struct vm_area_struct *svma,
- struct vm_area_struct *vma,
- unsigned long addr, pgoff_t idx)
-{
- unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) +
- svma->vm_start;
- unsigned long sbase = saddr & PUD_MASK;
- unsigned long s_end = sbase + PUD_SIZE;
-
- /* Allow segments to share if only one is marked locked */
- unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
- unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;
-
- /*
- * match the virtual addresses, permission and the alignment of the
- * page table page.
- */
- if (pmd_index(addr) != pmd_index(saddr) ||
- vm_flags != svm_flags ||
- sbase < svma->vm_start || svma->vm_end < s_end)
- return 0;
-
- return saddr;
-}
-
-static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
-{
- unsigned long base = addr & PUD_MASK;
- unsigned long end = base + PUD_SIZE;
-
- /*
- * check on proper vm_flags and page table alignment
- */
- if (vma->vm_flags & VM_MAYSHARE &&
- vma->vm_start <= base && end <= vma->vm_end)
- return 1;
- return 0;
-}
-
-/*
- * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
- * and returns the corresponding pte. While this is not necessary for the
- * !shared pmd case because we can allocate the pmd later as well, it makes the
- * code much cleaner. pmd allocation is essential for the shared case because
- * pud has to be populated inside the same i_mmap_mutex section - otherwise
- * racing tasks could either miss the sharing (see huge_pte_offset) or select a
- * bad pmd for sharing.
- */
-static pte_t *
-huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
-{
- struct vm_area_struct *vma = find_vma(mm, addr);
- struct address_space *mapping = vma->vm_file->f_mapping;
- pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) +
- vma->vm_pgoff;
- struct vm_area_struct *svma;
- unsigned long saddr;
- pte_t *spte = NULL;
- pte_t *pte;
-
- if (!vma_shareable(vma, addr))
- return (pte_t *)pmd_alloc(mm, pud, addr);
-
- mutex_lock(&mapping->i_mmap_mutex);
- vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
- if (svma == vma)
- continue;
-
- saddr = page_table_shareable(svma, vma, addr, idx);
- if (saddr) {
- spte = huge_pte_offset(svma->vm_mm, saddr);
- if (spte) {
- get_page(virt_to_page(spte));
- break;
- }
- }
- }
-
- if (!spte)
- goto out;
-
- spin_lock(&mm->page_table_lock);
- if (pud_none(*pud))
- pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK));
- else
- put_page(virt_to_page(spte));
- spin_unlock(&mm->page_table_lock);
-out:
- pte = (pte_t *)pmd_alloc(mm, pud, addr);
- mutex_unlock(&mapping->i_mmap_mutex);
- return pte;
-}
-
-/*
- * unmap huge page backed by shared pte.
- *
- * Hugetlb pte page is ref counted at the time of mapping. If pte is shared
- * indicated by page_count > 1, unmap is achieved by clearing pud and
- * decrementing the ref count. If count == 1, the pte page is not shared.
- *
- * called with vma->vm_mm->page_table_lock held.
- *
- * returns: 1 successfully unmapped a shared pte page
- * 0 the underlying pte page is not shared, or it is the last user
- */
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
- pgd_t *pgd = pgd_offset(mm, *addr);
- pud_t *pud = pud_offset(pgd, *addr);
-
- BUG_ON(page_count(virt_to_page(ptep)) == 0);
- if (page_count(virt_to_page(ptep)) == 1)
- return 0;
-
- pud_clear(pud);
- put_page(virt_to_page(ptep));
- *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
- return 1;
-}
-
-pte_t *huge_pte_alloc(struct mm_struct *mm,
- unsigned long addr, unsigned long sz)
-{
- pgd_t *pgd;
- pud_t *pud;
- pte_t *pte = NULL;
-
- pgd = pgd_offset(mm, addr);
- pud = pud_alloc(mm, pgd, addr);
- if (pud) {
- if (sz == PUD_SIZE) {
- pte = (pte_t *)pud;
- } else {
- BUG_ON(sz != PMD_SIZE);
- if (pud_none(*pud))
- pte = huge_pmd_share(mm, addr, pud);
- else
- pte = (pte_t *)pmd_alloc(mm, pud, addr);
- }
- }
- BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
-
- return pte;
-}
-
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
-{
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd = NULL;
-
- pgd = pgd_offset(mm, addr);
- if (pgd_present(*pgd)) {
- pud = pud_offset(pgd, addr);
- if (pud_present(*pud)) {
- if (pud_large(*pud))
- return (pte_t *)pud;
- pmd = pmd_offset(pud, addr);
- }
- }
- return (pte_t *) pmd;
-}
-
#if 0 /* This is just for testing */
struct page *
follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
@@ -240,30 +77,6 @@ int pud_huge(pud_t pud)
return !!(pud_val(pud) & _PAGE_PSE);
}
-struct page *
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
- pmd_t *pmd, int write)
-{
- struct page *page;
-
- page = pte_page(*(pte_t *)pmd);
- if (page)
- page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
- return page;
-}
-
-struct page *
-follow_huge_pud(struct mm_struct *mm, unsigned long address,
- pud_t *pud, int write)
-{
- struct page *page;
-
- page = pte_page(*(pte_t *)pud);
- if (page)
- page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
- return page;
-}
-
#endif
/* x86_64 also uses this file */
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 6033be9ff81a..816e940b3998 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -60,34 +60,19 @@
static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
-struct efi __read_mostly efi = {
- .mps = EFI_INVALID_TABLE_ADDR,
- .acpi = EFI_INVALID_TABLE_ADDR,
- .acpi20 = EFI_INVALID_TABLE_ADDR,
- .smbios = EFI_INVALID_TABLE_ADDR,
- .sal_systab = EFI_INVALID_TABLE_ADDR,
- .boot_info = EFI_INVALID_TABLE_ADDR,
- .hcdp = EFI_INVALID_TABLE_ADDR,
- .uga = EFI_INVALID_TABLE_ADDR,
- .uv_systab = EFI_INVALID_TABLE_ADDR,
-};
-EXPORT_SYMBOL(efi);
-
struct efi_memory_map memmap;
static struct efi efi_phys __initdata;
static efi_system_table_t efi_systab __initdata;
-unsigned long x86_efi_facility;
+static __initdata efi_config_table_type_t arch_tables[] = {
+#ifdef CONFIG_X86_UV
+ {UV_SYSTEM_TABLE_GUID, "UVsystab", &efi.uv_systab},
+#endif
+ {NULL_GUID, NULL, 0},
+};
-/*
- * Returns 1 if 'facility' is enabled, 0 otherwise.
- */
-int efi_enabled(int facility)
-{
- return test_bit(facility, &x86_efi_facility) != 0;
-}
-EXPORT_SYMBOL(efi_enabled);
+u64 efi_setup; /* efi setup_data physical address */
static bool __initdata disable_runtime = false;
static int __init setup_noefi(char *arg)
@@ -397,6 +382,8 @@ int __init efi_memblock_x86_reserve_range(void)
memblock_reserve(pmap, memmap.nr_map * memmap.desc_size);
+ efi.memmap = &memmap;
+
return 0;
}
@@ -454,7 +441,7 @@ void __init efi_reserve_boot_services(void)
void __init efi_unmap_memmap(void)
{
- clear_bit(EFI_MEMMAP, &x86_efi_facility);
+ clear_bit(EFI_MEMMAP, &efi.flags);
if (memmap.map) {
early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
memmap.map = NULL;
@@ -576,80 +563,6 @@ static int __init efi_systab_init(void *phys)
return 0;
}
-static int __init efi_config_init(u64 tables, int nr_tables)
-{
- void *config_tables, *tablep;
- int i, sz;
-
- if (efi_enabled(EFI_64BIT))
- sz = sizeof(efi_config_table_64_t);
- else
- sz = sizeof(efi_config_table_32_t);
-
- /*
- * Let's see what config tables the firmware passed to us.
- */
- config_tables = early_ioremap(tables, nr_tables * sz);
- if (config_tables == NULL) {
- pr_err("Could not map Configuration table!\n");
- return -ENOMEM;
- }
-
- tablep = config_tables;
- pr_info("");
- for (i = 0; i < efi.systab->nr_tables; i++) {
- efi_guid_t guid;
- unsigned long table;
-
- if (efi_enabled(EFI_64BIT)) {
- u64 table64;
- guid = ((efi_config_table_64_t *)tablep)->guid;
- table64 = ((efi_config_table_64_t *)tablep)->table;
- table = table64;
-#ifdef CONFIG_X86_32
- if (table64 >> 32) {
- pr_cont("\n");
- pr_err("Table located above 4GB, disabling EFI.\n");
- early_iounmap(config_tables,
- efi.systab->nr_tables * sz);
- return -EINVAL;
- }
-#endif
- } else {
- guid = ((efi_config_table_32_t *)tablep)->guid;
- table = ((efi_config_table_32_t *)tablep)->table;
- }
- if (!efi_guidcmp(guid, MPS_TABLE_GUID)) {
- efi.mps = table;
- pr_cont(" MPS=0x%lx ", table);
- } else if (!efi_guidcmp(guid, ACPI_20_TABLE_GUID)) {
- efi.acpi20 = table;
- pr_cont(" ACPI 2.0=0x%lx ", table);
- } else if (!efi_guidcmp(guid, ACPI_TABLE_GUID)) {
- efi.acpi = table;
- pr_cont(" ACPI=0x%lx ", table);
- } else if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID)) {
- efi.smbios = table;
- pr_cont(" SMBIOS=0x%lx ", table);
-#ifdef CONFIG_X86_UV
- } else if (!efi_guidcmp(guid, UV_SYSTEM_TABLE_GUID)) {
- efi.uv_systab = table;
- pr_cont(" UVsystab=0x%lx ", table);
-#endif
- } else if (!efi_guidcmp(guid, HCDP_TABLE_GUID)) {
- efi.hcdp = table;
- pr_cont(" HCDP=0x%lx ", table);
- } else if (!efi_guidcmp(guid, UGA_IO_PROTOCOL_GUID)) {
- efi.uga = table;
- pr_cont(" UGA=0x%lx ", table);
- }
- tablep += sz;
- }
- pr_cont("\n");
- early_iounmap(config_tables, efi.systab->nr_tables * sz);
- return 0;
-}
-
static int __init efi_runtime_init(void)
{
efi_runtime_services_t *runtime;
@@ -725,7 +638,11 @@ void __init efi_init(void)
if (efi_systab_init(efi_phys.systab))
return;
- set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
+ set_bit(EFI_SYSTEM_TABLES, &efi.flags);
+
+ efi.config_table = (unsigned long)efi.systab->tables;
+ efi.fw_vendor = (unsigned long)efi.systab->fw_vendor;
+ efi.runtime = (unsigned long)efi.systab->runtime;
/*
* Show what we know for posterity
@@ -743,10 +660,10 @@ void __init efi_init(void)
efi.systab->hdr.revision >> 16,
efi.systab->hdr.revision & 0xffff, vendor);
- if (efi_config_init(efi.systab->tables, efi.systab->nr_tables))
+ if (efi_config_init(arch_tables))
return;
- set_bit(EFI_CONFIG_TABLES, &x86_efi_facility);
+ set_bit(EFI_CONFIG_TABLES, &efi.flags);
/*
* Note: We currently don't support runtime services on an EFI
@@ -758,13 +675,13 @@ void __init efi_init(void)
else {
if (disable_runtime || efi_runtime_init())
return;
- set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
+ set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
}
if (efi_memmap_init())
return;
- set_bit(EFI_MEMMAP, &x86_efi_facility);
+ set_bit(EFI_MEMMAP, &efi.flags);
#if EFI_DEBUG
print_efi_memmap();
@@ -807,34 +724,6 @@ static void __init runtime_code_page_mkexec(void)
}
}
-/*
- * We can't ioremap data in EFI boot services RAM, because we've already mapped
- * it as RAM. So, look it up in the existing EFI memory map instead. Only
- * callable after efi_enter_virtual_mode and before efi_free_boot_services.
- */
-void __iomem *efi_lookup_mapped_addr(u64 phys_addr)
-{
- void *p;
- if (WARN_ON(!memmap.map))
- return NULL;
- for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
- efi_memory_desc_t *md = p;
- u64 size = md->num_pages << EFI_PAGE_SHIFT;
- u64 end = md->phys_addr + size;
- if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
- md->type != EFI_BOOT_SERVICES_CODE &&
- md->type != EFI_BOOT_SERVICES_DATA)
- continue;
- if (!md->virt_addr)
- continue;
- if (phys_addr >= md->phys_addr && phys_addr < end) {
- phys_addr += md->virt_addr - md->phys_addr;
- return (__force void __iomem *)(unsigned long)phys_addr;
- }
- }
- return NULL;
-}
-
void efi_memory_uc(u64 addr, unsigned long size)
{
unsigned long page_shift = 1UL << EFI_PAGE_SHIFT;
generated by cgit v1.2.3 (git 2.25.1) at 2024-04-27 10:51:11 +0000