summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig32
-rw-r--r--arch/x86/boot/Makefile2
-rw-r--r--arch/x86/boot/compressed/Makefile2
-rw-r--r--arch/x86/boot/compressed/misc.c1
-rw-r--r--arch/x86/boot/compressed/sev.c3
-rw-r--r--arch/x86/boot/compressed/vmlinux.lds.S6
-rw-r--r--arch/x86/boot/header.S211
-rw-r--r--arch/x86/boot/setup.ld14
-rw-r--r--arch/x86/boot/tools/build.c273
-rw-r--r--arch/x86/events/amd/lbr.c6
-rw-r--r--arch/x86/events/core.c1
-rw-r--r--arch/x86/include/asm/apic.h3
-rw-r--r--arch/x86/include/asm/boot.h1
-rw-r--r--arch/x86/include/asm/coco.h5
-rw-r--r--arch/x86/include/asm/init.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h1
-rw-r--r--arch/x86/include/asm/mem_encrypt.h8
-rw-r--r--arch/x86/include/asm/page_types.h12
-rw-r--r--arch/x86/include/asm/pgtable_types.h3
-rw-r--r--arch/x86/include/asm/sev.h10
-rw-r--r--arch/x86/kernel/amd_gart_64.c2
-rw-r--r--arch/x86/kernel/apic/apic.c6
-rw-r--r--arch/x86/kernel/cpu/bugs.c87
-rw-r--r--arch/x86/kernel/cpu/common.c48
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c6
-rw-r--r--arch/x86/kernel/head64.c7
-rw-r--r--arch/x86/kernel/platform-quirks.c1
-rw-r--r--arch/x86/kernel/process_64.c2
-rw-r--r--arch/x86/kernel/sev-shared.c23
-rw-r--r--arch/x86/kernel/sev.c11
-rw-r--r--arch/x86/kvm/cpuid.c1
-rw-r--r--arch/x86/kvm/cpuid.h10
-rw-r--r--arch/x86/kvm/lapic.c3
-rw-r--r--arch/x86/kvm/mmu/mmu.c2
-rw-r--r--arch/x86/kvm/vmx/vmx.c24
-rw-r--r--arch/x86/kvm/x86.c2
-rw-r--r--arch/x86/mm/mem_encrypt_boot.S4
-rw-r--r--arch/x86/mm/mem_encrypt_identity.c58
-rw-r--r--arch/x86/mm/pat/set_memory.c6
-rw-r--r--arch/x86/mm/pti.c2
40 files changed, 309 insertions, 592 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ba815ac47..49cea5b81 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -61,6 +61,7 @@ config X86
select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
select ARCH_32BIT_OFF_T if X86_32
select ARCH_CLOCKSOURCE_INIT
+ select ARCH_CONFIGURES_CPU_MITIGATIONS
select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
select ARCH_ENABLE_HUGEPAGE_MIGRATION if X86_64 && HUGETLB_PAGE && MIGRATION
select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64
@@ -2449,17 +2450,17 @@ config CC_HAS_SLS
config CC_HAS_RETURN_THUNK
def_bool $(cc-option,-mfunction-return=thunk-extern)
-menuconfig SPECULATION_MITIGATIONS
- bool "Mitigations for speculative execution vulnerabilities"
+menuconfig CPU_MITIGATIONS
+ bool "Mitigations for CPU vulnerabilities"
default y
help
- Say Y here to enable options which enable mitigations for
- speculative execution hardware vulnerabilities.
+ Say Y here to enable options which enable mitigations for hardware
+ vulnerabilities (usually related to speculative execution).
If you say N, all mitigations will be disabled. You really
should know what you are doing to say so.
-if SPECULATION_MITIGATIONS
+if CPU_MITIGATIONS
config PAGE_TABLE_ISOLATION
bool "Remove the kernel mapping in user mode"
@@ -2563,31 +2564,16 @@ config MITIGATION_RFDS
stored in floating point, vector and integer registers.
See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst>
-choice
- prompt "Clear branch history"
+config MITIGATION_SPECTRE_BHI
+ bool "Mitigate Spectre-BHB (Branch History Injection)"
depends on CPU_SUP_INTEL
- default SPECTRE_BHI_ON
+ default y
help
Enable BHI mitigations. BHI attacks are a form of Spectre V2 attacks
where the branch history buffer is poisoned to speculatively steer
indirect branches.
See <file:Documentation/admin-guide/hw-vuln/spectre.rst>
-config SPECTRE_BHI_ON
- bool "on"
- help
- Equivalent to setting spectre_bhi=on command line parameter.
-config SPECTRE_BHI_OFF
- bool "off"
- help
- Equivalent to setting spectre_bhi=off command line parameter.
-config SPECTRE_BHI_AUTO
- bool "auto"
- help
- Equivalent to setting spectre_bhi=auto command line parameter.
-
-endchoice
-
endif
config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 9e38ffaad..3c1b35203 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -91,7 +91,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|efi32_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi.._stub_entry\|efi\(32\)\?_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|_e\?data\|z_.*\)$$/\#define ZO_\2 0x\1/p'
quiet_cmd_zoffset = ZOFFSET $@
cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 3965b2c9e..6e61baff2 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -84,7 +84,7 @@ LDFLAGS_vmlinux += -T
hostprogs := mkpiggy
HOST_EXTRACFLAGS += -I$(srctree)/tools/include
-sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p'
+sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__start_rodata\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p'
quiet_cmd_voffset = VOFFSET $@
cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 8ae7893d7..45435ff88 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -330,6 +330,7 @@ static size_t parse_elf(void *output)
return ehdr.e_entry - LOAD_PHYSICAL_ADDR;
}
+const unsigned long kernel_text_size = VO___start_rodata - VO__text;
const unsigned long kernel_total_size = VO__end - VO__text;
static u8 boot_heap[BOOT_HEAP_SIZE] __aligned(4);
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index d07e665bb..3c5d5c97f 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -118,6 +118,9 @@ static bool fault_in_kernel_space(unsigned long address)
#define __init
#define __pa(x) ((unsigned long)(x))
+#undef __head
+#define __head
+
#define __BOOT_COMPRESSED
/* Basic instruction decoding support needed */
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index 112b2375d..bcf0e4e4c 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -42,11 +42,13 @@ SECTIONS
*(.rodata.*)
_erodata = . ;
}
- .data : {
+ .data : ALIGN(0x1000) {
_data = . ;
*(.data)
*(.data.*)
- *(.bss.efistub)
+
+ /* Add 4 bytes of extra space for a CRC-32 checksum */
+ . = ALIGN(. + 4, 0x200);
_edata = . ;
}
. = ALIGN(L1_CACHE_BYTES);
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index d31982509..7593339b5 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -36,65 +36,19 @@ SYSSEG = 0x1000 /* historical load address >> 4 */
#define ROOT_RDONLY 1
#endif
+ .set salign, 0x1000
+ .set falign, 0x200
+
.code16
.section ".bstext", "ax"
-
- .global bootsect_start
-bootsect_start:
#ifdef CONFIG_EFI_STUB
# "MZ", MS-DOS header
.word MZ_MAGIC
-#endif
-
- # Normalize the start address
- ljmp $BOOTSEG, $start2
-
-start2:
- movw %cs, %ax
- movw %ax, %ds
- movw %ax, %es
- movw %ax, %ss
- xorw %sp, %sp
- sti
- cld
-
- movw $bugger_off_msg, %si
-
-msg_loop:
- lodsb
- andb %al, %al
- jz bs_die
- movb $0xe, %ah
- movw $7, %bx
- int $0x10
- jmp msg_loop
-
-bs_die:
- # Allow the user to press a key, then reboot
- xorw %ax, %ax
- int $0x16
- int $0x19
-
- # int 0x19 should never return. In case it does anyway,
- # invoke the BIOS reset code...
- ljmp $0xf000,$0xfff0
-
-#ifdef CONFIG_EFI_STUB
.org 0x3c
#
# Offset to the PE header.
#
.long pe_header
-#endif /* CONFIG_EFI_STUB */
-
- .section ".bsdata", "a"
-bugger_off_msg:
- .ascii "Use a boot loader.\r\n"
- .ascii "\n"
- .ascii "Remove disk and press any key to reboot...\r\n"
- .byte 0
-
-#ifdef CONFIG_EFI_STUB
pe_header:
.long PE_MAGIC
@@ -123,30 +77,26 @@ optional_header:
.byte 0x02 # MajorLinkerVersion
.byte 0x14 # MinorLinkerVersion
- # Filled in by build.c
- .long 0 # SizeOfCode
+ .long ZO__data # SizeOfCode
- .long 0 # SizeOfInitializedData
+ .long ZO__end - ZO__data # SizeOfInitializedData
.long 0 # SizeOfUninitializedData
- # Filled in by build.c
- .long 0x0000 # AddressOfEntryPoint
+ .long setup_size + ZO_efi_pe_entry # AddressOfEntryPoint
- .long 0x0200 # BaseOfCode
+ .long setup_size # BaseOfCode
#ifdef CONFIG_X86_32
.long 0 # data
#endif
extra_header_fields:
- # PE specification requires ImageBase to be 64k aligned
- .set image_base, (LOAD_PHYSICAL_ADDR + 0xffff) & ~0xffff
#ifdef CONFIG_X86_32
- .long image_base # ImageBase
+ .long 0 # ImageBase
#else
- .quad image_base # ImageBase
+ .quad 0 # ImageBase
#endif
- .long 0x20 # SectionAlignment
- .long 0x20 # FileAlignment
+ .long salign # SectionAlignment
+ .long falign # FileAlignment
.word 0 # MajorOperatingSystemVersion
.word 0 # MinorOperatingSystemVersion
.word LINUX_EFISTUB_MAJOR_VERSION # MajorImageVersion
@@ -155,12 +105,9 @@ extra_header_fields:
.word 0 # MinorSubsystemVersion
.long 0 # Win32VersionValue
- #
- # The size of the bzImage is written in tools/build.c
- #
- .long 0 # SizeOfImage
+ .long setup_size + ZO__end # SizeOfImage
- .long 0x200 # SizeOfHeaders
+ .long salign # SizeOfHeaders
.long 0 # CheckSum
.word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application)
#ifdef CONFIG_EFI_DXE_MEM_ATTRIBUTES
@@ -191,87 +138,77 @@ extra_header_fields:
# Section table
section_table:
- #
- # The offset & size fields are filled in by build.c.
- #
.ascii ".setup"
.byte 0
.byte 0
- .long 0
- .long 0x0 # startup_{32,64}
- .long 0 # Size of initialized data
- # on disk
- .long 0x0 # startup_{32,64}
- .long 0 # PointerToRelocations
- .long 0 # PointerToLineNumbers
- .word 0 # NumberOfRelocations
- .word 0 # NumberOfLineNumbers
- .long IMAGE_SCN_CNT_CODE | \
- IMAGE_SCN_MEM_READ | \
- IMAGE_SCN_MEM_EXECUTE | \
- IMAGE_SCN_ALIGN_16BYTES # Characteristics
+ .long pecompat_fstart - salign # VirtualSize
+ .long salign # VirtualAddress
+ .long pecompat_fstart - salign # SizeOfRawData
+ .long salign # PointerToRawData
- #
- # The EFI application loader requires a relocation section
- # because EFI applications must be relocatable. The .reloc
- # offset & size fields are filled in by build.c.
- #
- .ascii ".reloc"
- .byte 0
- .byte 0
- .long 0
- .long 0
- .long 0 # SizeOfRawData
- .long 0 # PointerToRawData
- .long 0 # PointerToRelocations
- .long 0 # PointerToLineNumbers
- .word 0 # NumberOfRelocations
- .word 0 # NumberOfLineNumbers
+ .long 0, 0, 0
.long IMAGE_SCN_CNT_INITIALIZED_DATA | \
IMAGE_SCN_MEM_READ | \
- IMAGE_SCN_MEM_DISCARDABLE | \
- IMAGE_SCN_ALIGN_1BYTES # Characteristics
+ IMAGE_SCN_MEM_DISCARDABLE # Characteristics
#ifdef CONFIG_EFI_MIXED
- #
- # The offset & size fields are filled in by build.c.
- #
.asciz ".compat"
- .long 0
- .long 0x0
- .long 0 # Size of initialized data
- # on disk
- .long 0x0
- .long 0 # PointerToRelocations
- .long 0 # PointerToLineNumbers
- .word 0 # NumberOfRelocations
- .word 0 # NumberOfLineNumbers
+
+ .long pecompat_fsize # VirtualSize
+ .long pecompat_fstart # VirtualAddress
+ .long pecompat_fsize # SizeOfRawData
+ .long pecompat_fstart # PointerToRawData
+
+ .long 0, 0, 0
.long IMAGE_SCN_CNT_INITIALIZED_DATA | \
IMAGE_SCN_MEM_READ | \
- IMAGE_SCN_MEM_DISCARDABLE | \
- IMAGE_SCN_ALIGN_1BYTES # Characteristics
+ IMAGE_SCN_MEM_DISCARDABLE # Characteristics
+
+ /*
+ * Put the IA-32 machine type and the associated entry point address in
+ * the .compat section, so loaders can figure out which other execution
+ * modes this image supports.
+ */
+ .pushsection ".pecompat", "a", @progbits
+ .balign salign
+ .globl pecompat_fstart
+pecompat_fstart:
+ .byte 0x1 # Version
+ .byte 8 # Size
+ .word IMAGE_FILE_MACHINE_I386 # PE machine type
+ .long setup_size + ZO_efi32_pe_entry # Entrypoint
+ .byte 0x0 # Sentinel
+ .popsection
+#else
+ .set pecompat_fstart, setup_size
#endif
-
- #
- # The offset & size fields are filled in by build.c.
- #
.ascii ".text"
.byte 0
.byte 0
.byte 0
- .long 0
- .long 0x0 # startup_{32,64}
- .long 0 # Size of initialized data
+ .long ZO__data
+ .long setup_size
+ .long ZO__data # Size of initialized data
# on disk
- .long 0x0 # startup_{32,64}
+ .long setup_size
.long 0 # PointerToRelocations
.long 0 # PointerToLineNumbers
.word 0 # NumberOfRelocations
.word 0 # NumberOfLineNumbers
.long IMAGE_SCN_CNT_CODE | \
IMAGE_SCN_MEM_READ | \
- IMAGE_SCN_MEM_EXECUTE | \
- IMAGE_SCN_ALIGN_16BYTES # Characteristics
+ IMAGE_SCN_MEM_EXECUTE # Characteristics
+
+ .ascii ".data\0\0\0"
+ .long ZO__end - ZO__data # VirtualSize
+ .long setup_size + ZO__data # VirtualAddress
+ .long ZO__edata - ZO__data # SizeOfRawData
+ .long setup_size + ZO__data # PointerToRawData
+
+ .long 0, 0, 0
+ .long IMAGE_SCN_CNT_INITIALIZED_DATA | \
+ IMAGE_SCN_MEM_READ | \
+ IMAGE_SCN_MEM_WRITE # Characteristics
.set section_count, (. - section_table) / 40
#endif /* CONFIG_EFI_STUB */
@@ -285,12 +222,12 @@ sentinel: .byte 0xff, 0xff /* Used to detect broken loaders */
.globl hdr
hdr:
-setup_sects: .byte 0 /* Filled in by build.c */
+ .byte setup_sects - 1
root_flags: .word ROOT_RDONLY
-syssize: .long 0 /* Filled in by build.c */
+syssize: .long ZO__edata / 16
ram_size: .word 0 /* Obsolete */
vid_mode: .word SVGA_MODE
-root_dev: .word 0 /* Filled in by build.c */
+root_dev: .word 0 /* Default to major/minor 0/0 */
boot_flag: .word 0xAA55
# offset 512, entry point
@@ -578,9 +515,25 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr
# define INIT_SIZE VO_INIT_SIZE
#endif
+ .macro __handover_offset
+#ifndef CONFIG_EFI_HANDOVER_PROTOCOL
+ .long 0
+#elif !defined(CONFIG_X86_64)
+ .long ZO_efi32_stub_entry
+#else
+ /* Yes, this is really how we defined it :( */
+ .long ZO_efi64_stub_entry - 0x200
+#ifdef CONFIG_EFI_MIXED
+ .if ZO_efi32_stub_entry != ZO_efi64_stub_entry - 0x200
+ .error "32-bit and 64-bit EFI entry points do not match"
+ .endif
+#endif
+#endif
+ .endm
+
init_size: .long INIT_SIZE # kernel initialization size
-handover_offset: .long 0 # Filled in by build.c
-kernel_info_offset: .long 0 # Filled in by build.c
+handover_offset: __handover_offset
+kernel_info_offset: .long ZO_kernel_info
# End of setup header #####################################################
diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld
index 49546c247..3a2d1360a 100644
--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -10,10 +10,11 @@ ENTRY(_start)
SECTIONS
{
. = 0;
- .bstext : { *(.bstext) }
- .bsdata : { *(.bsdata) }
+ .bstext : {
+ *(.bstext)
+ . = 495;
+ } =0xffffffff
- . = 495;
.header : { *(.header) }
.entrytext : { *(.entrytext) }
.inittext : { *(.inittext) }
@@ -23,6 +24,9 @@ SECTIONS
.text : { *(.text .text.*) }
.text32 : { *(.text32) }
+ .pecompat : { *(.pecompat) }
+ PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
+
. = ALIGN(16);
.rodata : { *(.rodata*) }
@@ -38,8 +42,10 @@ SECTIONS
.signature : {
setup_sig = .;
LONG(0x5a5aaa55)
- }
+ setup_size = ALIGN(ABSOLUTE(.), 4096);
+ setup_sects = ABSOLUTE(setup_size / 512);
+ }
. = ALIGN(16);
.bss :
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index bd247692b..10311d77c 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -40,10 +40,6 @@ typedef unsigned char u8;
typedef unsigned short u16;
typedef unsigned int u32;
-#define DEFAULT_MAJOR_ROOT 0
-#define DEFAULT_MINOR_ROOT 0
-#define DEFAULT_ROOT_DEV (DEFAULT_MAJOR_ROOT << 8 | DEFAULT_MINOR_ROOT)
-
/* Minimal number of setup sectors */
#define SETUP_SECT_MIN 5
#define SETUP_SECT_MAX 64
@@ -51,22 +47,7 @@ typedef unsigned int u32;
/* This must be large enough to hold the entire setup */
u8 buf[SETUP_SECT_MAX*512];
-#define PECOFF_RELOC_RESERVE 0x20
-
-#ifdef CONFIG_EFI_MIXED
-#define PECOFF_COMPAT_RESERVE 0x20
-#else
-#define PECOFF_COMPAT_RESERVE 0x0
-#endif
-
-static unsigned long efi32_stub_entry;
-static unsigned long efi64_stub_entry;
-static unsigned long efi_pe_entry;
-static unsigned long efi32_pe_entry;
-static unsigned long kernel_info;
-static unsigned long startup_64;
-static unsigned long _ehead;
-static unsigned long _end;
+static unsigned long _edata;
/*----------------------------------------------------------------------*/
@@ -152,180 +133,6 @@ static void usage(void)
die("Usage: build setup system zoffset.h image");
}
-#ifdef CONFIG_EFI_STUB
-
-static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset)
-{
- unsigned int pe_header;
- unsigned short num_sections;
- u8 *section;
-
- pe_header = get_unaligned_le32(&buf[0x3c]);
- num_sections = get_unaligned_le16(&buf[pe_header + 6]);
-
-#ifdef CONFIG_X86_32
- section = &buf[pe_header + 0xa8];
-#else
- section = &buf[pe_header + 0xb8];
-#endif
-
- while (num_sections > 0) {
- if (strncmp((char*)section, section_name, 8) == 0) {
- /* section header size field */
- put_unaligned_le32(size, section + 0x8);
-
- /* section header vma field */
- put_unaligned_le32(vma, section + 0xc);
-
- /* section header 'size of initialised data' field */
- put_unaligned_le32(datasz, section + 0x10);
-
- /* section header 'file offset' field */
- put_unaligned_le32(offset, section + 0x14);
-
- break;
- }
- section += 0x28;
- num_sections--;
- }
-}
-
-static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
-{
- update_pecoff_section_header_fields(section_name, offset, size, size, offset);
-}
-
-static void update_pecoff_setup_and_reloc(unsigned int size)
-{
- u32 setup_offset = 0x200;
- u32 reloc_offset = size - PECOFF_RELOC_RESERVE - PECOFF_COMPAT_RESERVE;
-#ifdef CONFIG_EFI_MIXED
- u32 compat_offset = reloc_offset + PECOFF_RELOC_RESERVE;
-#endif
- u32 setup_size = reloc_offset - setup_offset;
-
- update_pecoff_section_header(".setup", setup_offset, setup_size);
- update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE);
-
- /*
- * Modify .reloc section contents with a single entry. The
- * relocation is applied to offset 10 of the relocation section.
- */
- put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]);
- put_unaligned_le32(10, &buf[reloc_offset + 4]);
-
-#ifdef CONFIG_EFI_MIXED
- update_pecoff_section_header(".compat", compat_offset, PECOFF_COMPAT_RESERVE);
-
- /*
- * Put the IA-32 machine type (0x14c) and the associated entry point
- * address in the .compat section, so loaders can figure out which other
- * execution modes this image supports.
- */
- buf[compat_offset] = 0x1;
- buf[compat_offset + 1] = 0x8;
- put_unaligned_le16(0x14c, &buf[compat_offset + 2]);
- put_unaligned_le32(efi32_pe_entry + size, &buf[compat_offset + 4]);
-#endif
-}
-
-static void update_pecoff_text(unsigned int text_start, unsigned int file_sz,
- unsigned int init_sz)
-{
- unsigned int pe_header;
- unsigned int text_sz = file_sz - text_start;
- unsigned int bss_sz = init_sz - file_sz;
-
- pe_header = get_unaligned_le32(&buf[0x3c]);
-
- /*
- * The PE/COFF loader may load the image at an address which is
- * misaligned with respect to the kernel_alignment field in the setup
- * header.
- *
- * In order to avoid relocating the kernel to correct the misalignment,
- * add slack to allow the buffer to be aligned within the declared size
- * of the image.
- */
- bss_sz += CONFIG_PHYSICAL_ALIGN;
- init_sz += CONFIG_PHYSICAL_ALIGN;
-
- /*
- * Size of code: Subtract the size of the first sector (512 bytes)
- * which includes the header.
- */
- put_unaligned_le32(file_sz - 512 + bss_sz, &buf[pe_header + 0x1c]);
-
- /* Size of image */
- put_unaligned_le32(init_sz, &buf[pe_header + 0x50]);
-
- /*
- * Address of entry point for PE/COFF executable
- */
- put_unaligned_le32(text_start + efi_pe_entry, &buf[pe_header + 0x28]);
-
- update_pecoff_section_header_fields(".text", text_start, text_sz + bss_sz,
- text_sz, text_start);
-}
-
-static int reserve_pecoff_reloc_section(int c)
-{
- /* Reserve 0x20 bytes for .reloc section */
- memset(buf+c, 0, PECOFF_RELOC_RESERVE);
- return PECOFF_RELOC_RESERVE;
-}
-
-static void efi_stub_defaults(void)
-{
- /* Defaults for old kernel */
-#ifdef CONFIG_X86_32
- efi_pe_entry = 0x10;
-#else
- efi_pe_entry = 0x210;
- startup_64 = 0x200;
-#endif
-}
-
-static void efi_stub_entry_update(void)
-{
- unsigned long addr = efi32_stub_entry;
-
-#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
-#ifdef CONFIG_X86_64
- /* Yes, this is really how we defined it :( */
- addr = efi64_stub_entry - 0x200;
-#endif
-
-#ifdef CONFIG_EFI_MIXED
- if (efi32_stub_entry != addr)
- die("32-bit and 64-bit EFI entry points do not match\n");
-#endif
-#endif
- put_unaligned_le32(addr, &buf[0x264]);
-}
-
-#else
-
-static inline void update_pecoff_setup_and_reloc(unsigned int size) {}
-static inline void update_pecoff_text(unsigned int text_start,
- unsigned int file_sz,
- unsigned int init_sz) {}
-static inline void efi_stub_defaults(void) {}
-static inline void efi_stub_entry_update(void) {}
-
-static inline int reserve_pecoff_reloc_section(int c)
-{
- return 0;
-}
-#endif /* CONFIG_EFI_STUB */
-
-static int reserve_pecoff_compat_section(int c)
-{
- /* Reserve 0x20 bytes for .compat section */
- memset(buf+c, 0, PECOFF_COMPAT_RESERVE);
- return PECOFF_COMPAT_RESERVE;
-}
-
/*
* Parse zoffset.h and find the entry points. We could just #include zoffset.h
* but that would mean tools/build would have to be rebuilt every time. It's
@@ -354,14 +161,7 @@ static void parse_zoffset(char *fname)
p = (char *)buf;
while (p && *p) {
- PARSE_ZOFS(p, efi32_stub_entry);
- PARSE_ZOFS(p, efi64_stub_entry);
- PARSE_ZOFS(p, efi_pe_entry);
- PARSE_ZOFS(p, efi32_pe_entry);
- PARSE_ZOFS(p, kernel_info);
- PARSE_ZOFS(p, startup_64);
- PARSE_ZOFS(p, _ehead);
- PARSE_ZOFS(p, _end);
+ PARSE_ZOFS(p, _edata);
p = strchr(p, '\n');
while (p && (*p == '\r' || *p == '\n'))
@@ -371,17 +171,14 @@ static void parse_zoffset(char *fname)
int main(int argc, char ** argv)
{
- unsigned int i, sz, setup_sectors, init_sz;
+ unsigned int i, sz, setup_sectors;
int c;
- u32 sys_size;
struct stat sb;
FILE *file, *dest;
int fd;
void *kernel;
u32 crc = 0xffffffffUL;
- efi_stub_defaults();
-
if (argc != 5)
usage();
parse_zoffset(argv[3]);
@@ -403,72 +200,27 @@ int main(int argc, char ** argv)
die("Boot block hasn't got boot flag (0xAA55)");
fclose(file);
- c += reserve_pecoff_compat_section(c);
- c += reserve_pecoff_reloc_section(c);
-
/* Pad unused space with zeros */
- setup_sectors = (c + 511) / 512;
+ setup_sectors = (c + 4095) / 4096;
+ setup_sectors *= 8;
if (setup_sectors < SETUP_SECT_MIN)
setup_sectors = SETUP_SECT_MIN;
i = setup_sectors*512;
memset(buf+c, 0, i-c);
- update_pecoff_setup_and_reloc(i);
-
- /* Set the default root device */
- put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]);
-
/* Open and stat the kernel file */
fd = open(argv[2], O_RDONLY);
if (fd < 0)
die("Unable to open `%s': %m", argv[2]);
if (fstat(fd, &sb))
die("Unable to stat `%s': %m", argv[2]);
- sz = sb.st_size;
+ if (_edata != sb.st_size)
+ die("Unexpected file size `%s': %u != %u", argv[2], _edata,
+ sb.st_size);
+ sz = _edata - 4;
kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0);
if (kernel == MAP_FAILED)
die("Unable to mmap '%s': %m", argv[2]);
- /* Number of 16-byte paragraphs, including space for a 4-byte CRC */
- sys_size = (sz + 15 + 4) / 16;
-#ifdef CONFIG_EFI_STUB
- /*
- * COFF requires minimum 32-byte alignment of sections, and
- * adding a signature is problematic without that alignment.
- */
- sys_size = (sys_size + 1) & ~1;
-#endif
-
- /* Patch the setup code with the appropriate size parameters */
- buf[0x1f1] = setup_sectors-1;
- put_unaligned_le32(sys_size, &buf[0x1f4]);
-
- init_sz = get_unaligned_le32(&buf[0x260]);
-#ifdef CONFIG_EFI_STUB
- /*
- * The decompression buffer will start at ImageBase. When relocating
- * the compressed kernel to its end, we must ensure that the head
- * section does not get overwritten. The head section occupies
- * [i, i + _ehead), and the destination is [init_sz - _end, init_sz).
- *
- * At present these should never overlap, because 'i' is at most 32k
- * because of SETUP_SECT_MAX, '_ehead' is less than 1k, and the
- * calculation of INIT_SIZE in boot/header.S ensures that
- * 'init_sz - _end' is at least 64k.
- *
- * For future-proofing, increase init_sz if necessary.
- */
-
- if (init_sz - _end < i + _ehead) {
- init_sz = (i + _ehead + _end + 4095) & ~4095;
- put_unaligned_le32(init_sz, &buf[0x260]);
- }
-#endif
- update_pecoff_text(setup_sectors * 512, i + (sys_size * 16), init_sz);
-
- efi_stub_entry_update();
-
- /* Update kernel_info offset. */
- put_unaligned_le32(kernel_info, &buf[0x268]);
crc = partial_crc32(buf, i, crc);
if (fwrite(buf, 1, i, dest) != i)
@@ -479,13 +231,6 @@ int main(int argc, char ** argv)
if (fwrite(kernel, 1, sz, dest) != sz)
die("Writing kernel failed");
- /* Add padding leaving 4 bytes for the checksum */
- while (sz++ < (sys_size*16) - 4) {
- crc = partial_crc32_one('\0', crc);
- if (fwrite("\0", 1, 1, dest) != 1)
- die("Writing padding failed");
- }
-
/* Write the CRC */
put_unaligned_le32(crc, buf);
if (fwrite(buf, 1, 4, dest) != 4)
diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c
index b8fe74e8e..48f4095f5 100644
--- a/arch/x86/events/amd/lbr.c
+++ b/arch/x86/events/amd/lbr.c
@@ -173,9 +173,11 @@ void amd_pmu_lbr_read(void)
/*
* Check if a branch has been logged; if valid = 0, spec = 0
- * then no branch was recorded
+ * then no branch was recorded; if reserved = 1 then an
+ * erroneous branch was recorded (see Erratum 1452)
*/
- if (!entry.to.split.valid && !entry.to.split.spec)
+ if ((!entry.to.split.valid && !entry.to.split.spec) ||
+ entry.to.split.reserved)
continue;
perf_clear_branch_entry_bitfields(br + out);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 30fb4931d..1394312b7 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1644,6 +1644,7 @@ static void x86_pmu_del(struct perf_event *event, int flags)
while (++i < cpuc->n_events) {
cpuc->event_list[i-1] = cpuc->event_list[i];
cpuc->event_constraint[i-1] = cpuc->event_constraint[i];
+ cpuc->assign[i-1] = cpuc->assign[i];
}
cpuc->event_constraint[i-1] = NULL;
--cpuc->n_events;
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 3216da707..36ceecd40 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -12,6 +12,7 @@
#include <asm/mpspec.h>
#include <asm/msr.h>
#include <asm/hardirq.h>
+#include <asm/io.h>
#define ARCH_APICTIMER_STOPS_ON_C3 1
@@ -109,7 +110,7 @@ static inline void native_apic_mem_write(u32 reg, u32 v)
static inline u32 native_apic_mem_read(u32 reg)
{
- return *((volatile u32 *)(APIC_BASE + reg));
+ return readl((void __iomem *)(APIC_BASE + reg));
}
extern void native_apic_wait_icr_idle(void);
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index a38cc0afc..a3e0be047 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -81,6 +81,7 @@
#ifndef __ASSEMBLY__
extern unsigned int output_len;
+extern const unsigned long kernel_text_size;
extern const unsigned long kernel_total_size;
unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr,
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index 1f97d00ad..100a752c3 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -13,9 +13,10 @@ enum cc_vendor {
};
extern enum cc_vendor cc_vendor;
-extern u64 cc_mask;
#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
+extern u64 cc_mask;
+
static inline void cc_set_mask(u64 mask)
{
RIP_REL_REF(cc_mask) = mask;
@@ -25,6 +26,8 @@ u64 cc_mkenc(u64 val);
u64 cc_mkdec(u64 val);
void cc_random_init(void);
#else
+static const u64 cc_mask = 0;
+
static inline u64 cc_mkenc(u64 val)
{
return val;
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 5f1d3c421..cc9ccf61b 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -2,6 +2,8 @@
#ifndef _ASM_X86_INIT_H
#define _ASM_X86_INIT_H
+#define __head __section(".head.text")
+
struct x86_mapping_info {
void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
void *context; /* context for alloc_pgt_page */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index dfcdcafe3..887a17148 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -773,6 +773,7 @@ struct kvm_vcpu_arch {
int cpuid_nent;
struct kvm_cpuid_entry2 *cpuid_entries;
u32 kvm_cpuid_base;
+ bool is_amd_compatible;
u64 reserved_gpa_bits;
int maxphyaddr;
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 41d06822b..853f423b1 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -46,8 +46,8 @@ void __init sme_unmap_bootdata(char *real_mode_data);
void __init sme_early_init(void);
void __init sev_setup_arch(void);
-void __init sme_encrypt_kernel(struct boot_params *bp);
-void __init sme_enable(struct boot_params *bp);
+void sme_encrypt_kernel(struct boot_params *bp);
+void sme_enable(struct boot_params *bp);
int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size);
int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size);
@@ -80,8 +80,8 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { }
static inline void __init sme_early_init(void) { }
static inline void __init sev_setup_arch(void) { }
-static inline void __init sme_encrypt_kernel(struct boot_params *bp) { }
-static inline void __init sme_enable(struct boot_params *bp) { }
+static inline void sme_encrypt_kernel(struct boot_params *bp) { }
+static inline void sme_enable(struct boot_params *bp) { }
static inline void sev_es_init_vc_handling(void) { }
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index a506a4114..86bd4311d 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -11,20 +11,14 @@
#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT)
#define PAGE_MASK (~(PAGE_SIZE-1))
-#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT)
-#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1))
-
-#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT)
-#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1))
-
#define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1)
-/* Cast *PAGE_MASK to a signed type so that it is sign-extended if
+/* Cast P*D_MASK to a signed type so that it is sign-extended if
virtual addresses are 32-bits but physical addresses are larger
(ie, 32-bit PAE). */
#define PHYSICAL_PAGE_MASK (((signed long)PAGE_MASK) & __PHYSICAL_MASK)
-#define PHYSICAL_PMD_PAGE_MASK (((signed long)PMD_PAGE_MASK) & __PHYSICAL_MASK)
-#define PHYSICAL_PUD_PAGE_MASK (((signed long)PUD_PAGE_MASK) & __PHYSICAL_MASK)
+#define PHYSICAL_PMD_PAGE_MASK (((signed long)PMD_MASK) & __PHYSICAL_MASK)
+#define PHYSICAL_PUD_PAGE_MASK (((signed long)PUD_MASK) & __PHYSICAL_MASK)
#define HPAGE_SHIFT PMD_SHIFT
#define HPAGE_SIZE (_AC(1,UL) << HPAGE_SHIFT)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index f6116b66f..f0b9b37c4 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -127,7 +127,7 @@
*/
#define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \
_PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |\
- _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC | \
+ _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_CC | \
_PAGE_UFFD_WP)
#define _PAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PAT)
#define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE)
@@ -153,6 +153,7 @@ enum page_cache_mode {
};
#endif
+#define _PAGE_CC (_AT(pteval_t, cc_mask))
#define _PAGE_ENC (_AT(pteval_t, sme_me_mask))
#define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index c57dd2115..bcac2e53d 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -192,15 +192,15 @@ static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate)
struct snp_guest_request_ioctl;
void setup_ghcb(void);
-void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
- unsigned long npages);
-void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
- unsigned long npages);
+void early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
+ unsigned long npages);
+void early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
+ unsigned long npages);
void snp_set_memory_shared(unsigned long vaddr, unsigned long npages);
void snp_set_memory_private(unsigned long vaddr, unsigned long npages);
void snp_set_wakeup_secondary_cpu(void);
bool snp_init(struct boot_params *bp);
-void __init __noreturn snp_abort(void);
+void __noreturn snp_abort(void);
void snp_dmi_setup(void);
int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio);
u64 snp_get_unsupported_features(u64 status);
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 19a0207e5..56a917df4 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -504,7 +504,7 @@ static __init unsigned long check_iommu_size(unsigned long aper, u64 aper_size)
}
a = aper + iommu_size;
- iommu_size -= round_up(a, PMD_PAGE_SIZE) - a;
+ iommu_size -= round_up(a, PMD_SIZE) - a;
if (iommu_size < 64*1024*1024) {
pr_warn("PCI-DMA: Warning: Small IOMMU %luMB."
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 770557110..e1672cc77 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1760,11 +1760,11 @@ static int x2apic_state;
static bool x2apic_hw_locked(void)
{
- u64 ia32_cap;
+ u64 x86_arch_cap_msr;
u64 msr;
- ia32_cap = x86_read_arch_cap_msr();
- if (ia32_cap & ARCH_CAP_XAPIC_DISABLE) {
+ x86_arch_cap_msr = x86_read_arch_cap_msr();
+ if (x86_arch_cap_msr & ARCH_CAP_XAPIC_DISABLE) {
rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr);
return (msr & LEGACY_XAPIC_DISABLED);
}
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 96bd3ee83..3f38592ec 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -60,6 +60,8 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_current);
u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB;
EXPORT_SYMBOL_GPL(x86_pred_cmd);
+static u64 __ro_after_init x86_arch_cap_msr;
+
static DEFINE_MUTEX(spec_ctrl_mutex);
void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk;
@@ -143,6 +145,8 @@ void __init cpu_select_mitigations(void)
x86_spec_ctrl_base &= ~SPEC_CTRL_MITIGATIONS_MASK;
}
+ x86_arch_cap_msr = x86_read_arch_cap_msr();
+
/* Select the proper CPU mitigations before patching alternatives: */
spectre_v1_select_mitigation();
spectre_v2_select_mitigation();
@@ -300,8 +304,6 @@ static const char * const taa_strings[] = {
static void __init taa_select_mitigation(void)
{
- u64 ia32_cap;
-
if (!boot_cpu_has_bug(X86_BUG_TAA)) {
taa_mitigation = TAA_MITIGATION_OFF;
return;
@@ -340,9 +342,8 @@ static void __init taa_select_mitigation(void)
* On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode
* update is required.
*/
- ia32_cap = x86_read_arch_cap_msr();
- if ( (ia32_cap & ARCH_CAP_MDS_NO) &&
- !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR))
+ if ( (x86_arch_cap_msr & ARCH_CAP_MDS_NO) &&
+ !(x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR))
taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
/*
@@ -400,8 +401,6 @@ static const char * const mmio_strings[] = {
static void __init mmio_select_mitigation(void)
{
- u64 ia32_cap;
-
if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) ||
boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) ||
cpu_mitigations_off()) {
@@ -412,8 +411,6 @@ static void __init mmio_select_mitigation(void)
if (mmio_mitigation == MMIO_MITIGATION_OFF)
return;
- ia32_cap = x86_read_arch_cap_msr();
-
/*
* Enable CPU buffer clear mitigation for host and VMM, if also affected
* by MDS or TAA. Otherwise, enable mitigation for VMM only.
@@ -436,7 +433,7 @@ static void __init mmio_select_mitigation(void)
* be propagated to uncore buffers, clearing the Fill buffers on idle
* is required irrespective of SMT state.
*/
- if (!(ia32_cap & ARCH_CAP_FBSDP_NO))
+ if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO))
static_branch_enable(&mds_idle_clear);
/*
@@ -446,10 +443,10 @@ static void __init mmio_select_mitigation(void)
* FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS
* affected systems.
*/
- if ((ia32_cap & ARCH_CAP_FB_CLEAR) ||
+ if ((x86_arch_cap_msr & ARCH_CAP_FB_CLEAR) ||
(boot_cpu_has(X86_FEATURE_MD_CLEAR) &&
boot_cpu_has(X86_FEATURE_FLUSH_L1D) &&
- !(ia32_cap & ARCH_CAP_MDS_NO)))
+ !(x86_arch_cap_msr & ARCH_CAP_MDS_NO)))
mmio_mitigation = MMIO_MITIGATION_VERW;
else
mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED;
@@ -507,7 +504,7 @@ static void __init rfds_select_mitigation(void)
if (rfds_mitigation == RFDS_MITIGATION_OFF)
return;
- if (x86_read_arch_cap_msr() & ARCH_CAP_RFDS_CLEAR)
+ if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR)
setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
else
rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED;
@@ -658,8 +655,6 @@ void update_srbds_msr(void)
static void __init srbds_select_mitigation(void)
{
- u64 ia32_cap;
-
if (!boot_cpu_has_bug(X86_BUG_SRBDS))
return;
@@ -668,8 +663,7 @@ static void __init srbds_select_mitigation(void)
* are only exposed to SRBDS when TSX is enabled or when CPU is affected
* by Processor MMIO Stale Data vulnerability.
*/
- ia32_cap = x86_read_arch_cap_msr();
- if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) &&
+ if ((x86_arch_cap_msr & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) &&
!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
srbds_mitigation = SRBDS_MITIGATION_TSX_OFF;
else if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
@@ -812,7 +806,7 @@ static void __init gds_select_mitigation(void)
/* Will verify below that mitigation _can_ be disabled */
/* No microcode */
- if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) {
+ if (!(x86_arch_cap_msr & ARCH_CAP_GDS_CTRL)) {
if (gds_mitigation == GDS_MITIGATION_FORCE) {
/*
* This only needs to be done on the boot CPU so do it
@@ -1521,20 +1515,25 @@ static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void)
return SPECTRE_V2_RETPOLINE;
}
+static bool __ro_after_init rrsba_disabled;
+
/* Disable in-kernel use of non-RSB RET predictors */
static void __init spec_ctrl_disable_kernel_rrsba(void)
{
- u64 ia32_cap;
+ if (rrsba_disabled)
+ return;
- if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL))
+ if (!(x86_arch_cap_msr & ARCH_CAP_RRSBA)) {
+ rrsba_disabled = true;
return;
+ }
- ia32_cap = x86_read_arch_cap_msr();
+ if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL))
+ return;
- if (ia32_cap & ARCH_CAP_RRSBA) {
- x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S;
- update_spec_ctrl(x86_spec_ctrl_base);
- }
+ x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S;
+ update_spec_ctrl(x86_spec_ctrl_base);
+ rrsba_disabled = true;
}
static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode)
@@ -1603,13 +1602,10 @@ static bool __init spec_ctrl_bhi_dis(void)
enum bhi_mitigations {
BHI_MITIGATION_OFF,
BHI_MITIGATION_ON,
- BHI_MITIGATION_AUTO,
};
static enum bhi_mitigations bhi_mitigation __ro_after_init =
- IS_ENABLED(CONFIG_SPECTRE_BHI_ON) ? BHI_MITIGATION_ON :
- IS_ENABLED(CONFIG_SPECTRE_BHI_OFF) ? BHI_MITIGATION_OFF :
- BHI_MITIGATION_AUTO;
+ IS_ENABLED(CONFIG_MITIGATION_SPECTRE_BHI) ? BHI_MITIGATION_ON : BHI_MITIGATION_OFF;
static int __init spectre_bhi_parse_cmdline(char *str)
{
@@ -1620,8 +1616,6 @@ static int __init spectre_bhi_parse_cmdline(char *str)
bhi_mitigation = BHI_MITIGATION_OFF;
else if (!strcmp(str, "on"))
bhi_mitigation = BHI_MITIGATION_ON;
- else if (!strcmp(str, "auto"))
- bhi_mitigation = BHI_MITIGATION_AUTO;
else
pr_err("Ignoring unknown spectre_bhi option (%s)", str);
@@ -1635,9 +1629,12 @@ static void __init bhi_select_mitigation(void)
return;
/* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */
- if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) &&
- !(x86_read_arch_cap_msr() & ARCH_CAP_RRSBA))
- return;
+ if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
+ !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) {
+ spec_ctrl_disable_kernel_rrsba();
+ if (rrsba_disabled)
+ return;
+ }
if (spec_ctrl_bhi_dis())
return;
@@ -1649,9 +1646,6 @@ static void __init bhi_select_mitigation(void)
setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n");
- if (bhi_mitigation == BHI_MITIGATION_AUTO)
- return;
-
/* Mitigate syscalls when the mitigation is forced =on */
setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP);
pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n");
@@ -1884,8 +1878,6 @@ static void update_indir_branch_cond(void)
/* Update the static key controlling the MDS CPU buffer clear in idle */
static void update_mds_branch_idle(void)
{
- u64 ia32_cap = x86_read_arch_cap_msr();
-
/*
* Enable the idle clearing if SMT is active on CPUs which are
* affected only by MSBDS and not any other MDS variant.
@@ -1900,7 +1892,7 @@ static void update_mds_branch_idle(void)
if (sched_smt_active()) {
static_branch_enable(&mds_idle_clear);
} else if (mmio_mitigation == MMIO_MITIGATION_OFF ||
- (ia32_cap & ARCH_CAP_FBSDP_NO)) {
+ (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) {
static_branch_disable(&mds_idle_clear);
}
}
@@ -2788,21 +2780,22 @@ static char *pbrsb_eibrs_state(void)
}
}
-static const char * const spectre_bhi_state(void)
+static const char *spectre_bhi_state(void)
{
if (!boot_cpu_has_bug(X86_BUG_BHI))
return "; BHI: Not affected";
- else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW))
+ else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW))
return "; BHI: BHI_DIS_S";
- else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP))
+ else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP))
return "; BHI: SW loop, KVM: SW loop";
else if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
- !(x86_read_arch_cap_msr() & ARCH_CAP_RRSBA))
+ !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) &&
+ rrsba_disabled)
return "; BHI: Retpoline";
- else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT))
- return "; BHI: Syscall hardening, KVM: SW loop";
+ else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT))
+ return "; BHI: Vulnerable, KVM: SW loop";
- return "; BHI: Vulnerable (Syscall hardening enabled)";
+ return "; BHI: Vulnerable";
}
static ssize_t spectre_v2_show_state(char *buf)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 08fe77d2a..f2bc651c0 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1308,25 +1308,25 @@ static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long whi
u64 x86_read_arch_cap_msr(void)
{
- u64 ia32_cap = 0;
+ u64 x86_arch_cap_msr = 0;
if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
- rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
+ rdmsrl(MSR_IA32_ARCH_CAPABILITIES, x86_arch_cap_msr);
- return ia32_cap;
+ return x86_arch_cap_msr;
}
-static bool arch_cap_mmio_immune(u64 ia32_cap)
+static bool arch_cap_mmio_immune(u64 x86_arch_cap_msr)
{
- return (ia32_cap & ARCH_CAP_FBSDP_NO &&
- ia32_cap & ARCH_CAP_PSDP_NO &&
- ia32_cap & ARCH_CAP_SBDR_SSDP_NO);
+ return (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO &&
+ x86_arch_cap_msr & ARCH_CAP_PSDP_NO &&
+ x86_arch_cap_msr & ARCH_CAP_SBDR_SSDP_NO);
}
-static bool __init vulnerable_to_rfds(u64 ia32_cap)
+static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr)
{
/* The "immunity" bit trumps everything else: */
- if (ia32_cap & ARCH_CAP_RFDS_NO)
+ if (x86_arch_cap_msr & ARCH_CAP_RFDS_NO)
return false;
/*
@@ -1334,7 +1334,7 @@ static bool __init vulnerable_to_rfds(u64 ia32_cap)
* indicate that mitigation is needed because guest is running on a
* vulnerable hardware or may migrate to such hardware:
*/
- if (ia32_cap & ARCH_CAP_RFDS_CLEAR)
+ if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR)
return true;
/* Only consult the blacklist when there is no enumeration: */
@@ -1343,11 +1343,11 @@ static bool __init vulnerable_to_rfds(u64 ia32_cap)
static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
{
- u64 ia32_cap = x86_read_arch_cap_msr();
+ u64 x86_arch_cap_msr = x86_read_arch_cap_msr();
/* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */
if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) &&
- !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO))
+ !(x86_arch_cap_msr & ARCH_CAP_PSCHANGE_MC_NO))
setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT);
if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION))
@@ -1359,7 +1359,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) &&
- !(ia32_cap & ARCH_CAP_SSB_NO) &&
+ !(x86_arch_cap_msr & ARCH_CAP_SSB_NO) &&
!cpu_has(c, X86_FEATURE_AMD_SSB_NO))
setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
@@ -1367,15 +1367,15 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
* AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature
* flag and protect from vendor-specific bugs via the whitelist.
*/
- if ((ia32_cap & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) {
+ if ((x86_arch_cap_msr & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) {
setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) &&
- !(ia32_cap & ARCH_CAP_PBRSB_NO))
+ !(x86_arch_cap_msr & ARCH_CAP_PBRSB_NO))
setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB);
}
if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) &&
- !(ia32_cap & ARCH_CAP_MDS_NO)) {
+ !(x86_arch_cap_msr & ARCH_CAP_MDS_NO)) {
setup_force_cpu_bug(X86_BUG_MDS);
if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY))
setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
@@ -1394,9 +1394,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
* TSX_CTRL check alone is not sufficient for cases when the microcode
* update is not present or running as guest that don't get TSX_CTRL.
*/
- if (!(ia32_cap & ARCH_CAP_TAA_NO) &&
+ if (!(x86_arch_cap_msr & ARCH_CAP_TAA_NO) &&
(cpu_has(c, X86_FEATURE_RTM) ||
- (ia32_cap & ARCH_CAP_TSX_CTRL_MSR)))
+ (x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR)))
setup_force_cpu_bug(X86_BUG_TAA);
/*
@@ -1422,7 +1422,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
* Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist,
* nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits.
*/
- if (!arch_cap_mmio_immune(ia32_cap)) {
+ if (!arch_cap_mmio_immune(x86_arch_cap_msr)) {
if (cpu_matches(cpu_vuln_blacklist, MMIO))
setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO))
@@ -1430,7 +1430,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
}
if (!cpu_has(c, X86_FEATURE_BTC_NO)) {
- if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA))
+ if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (x86_arch_cap_msr & ARCH_CAP_RSBA))
setup_force_cpu_bug(X86_BUG_RETBLEED);
}
@@ -1443,7 +1443,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
* disabling AVX2. The only way to do this in HW is to clear XCR0[2],
* which means that AVX will be disabled.
*/
- if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) &&
+ if (cpu_matches(cpu_vuln_blacklist, GDS) && !(x86_arch_cap_msr & ARCH_CAP_GDS_NO) &&
boot_cpu_has(X86_FEATURE_AVX))
setup_force_cpu_bug(X86_BUG_GDS);
@@ -1452,11 +1452,11 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
setup_force_cpu_bug(X86_BUG_SRSO);
}
- if (vulnerable_to_rfds(ia32_cap))
+ if (vulnerable_to_rfds(x86_arch_cap_msr))
setup_force_cpu_bug(X86_BUG_RFDS);
/* When virtualized, eIBRS could be hidden, assume vulnerable */
- if (!(ia32_cap & ARCH_CAP_BHI_NO) &&
+ if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) &&
!cpu_matches(cpu_vuln_whitelist, NO_BHI) &&
(boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) ||
boot_cpu_has(X86_FEATURE_HYPERVISOR)))
@@ -1466,7 +1466,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
return;
/* Rogue Data Cache Load? No! */
- if (ia32_cap & ARCH_CAP_RDCL_NO)
+ if (x86_arch_cap_msr & ARCH_CAP_RDCL_NO)
return;
setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index c881bcafb..9c19f40b1 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -44,7 +44,10 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_F16C, X86_FEATURE_XMM2, },
{ X86_FEATURE_AES, X86_FEATURE_XMM2 },
{ X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 },
+ { X86_FEATURE_GFNI, X86_FEATURE_XMM2 },
{ X86_FEATURE_FMA, X86_FEATURE_AVX },
+ { X86_FEATURE_VAES, X86_FEATURE_AVX },
+ { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX },
{ X86_FEATURE_AVX2, X86_FEATURE_AVX, },
{ X86_FEATURE_AVX512F, X86_FEATURE_AVX, },
{ X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F },
@@ -56,9 +59,6 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F },
{ X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F },
{ X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL },
- { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL },
- { X86_FEATURE_VAES, X86_FEATURE_AVX512VL },
- { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL },
{ X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL },
{ X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL },
{ X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F },
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 84adf12a7..4fae511b2 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -41,6 +41,7 @@
#include <asm/trapnr.h>
#include <asm/sev.h>
#include <asm/tdx.h>
+#include <asm/init.h>
/*
* Manage page tables very early on.
@@ -84,8 +85,6 @@ static struct desc_ptr startup_gdt_descr = {
.address = 0,
};
-#define __head __section(".head.text")
-
static void __head *fixup_pointer(void *ptr, unsigned long physaddr)
{
return ptr - (void *)_text + (void *)physaddr;
@@ -203,7 +202,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
load_delta = physaddr - (unsigned long)(_text - __START_KERNEL_map);
/* Is the address not 2M aligned? */
- if (load_delta & ~PMD_PAGE_MASK)
+ if (load_delta & ~PMD_MASK)
for (;;);
/* Include the SME encryption mask in the fixup value */
@@ -588,7 +587,7 @@ static void set_bringup_idt_handler(gate_desc *idt, int n, void *handler)
}
/* This runs while still in the direct mapping */
-static void startup_64_load_idt(unsigned long physbase)
+static void __head startup_64_load_idt(unsigned long physbase)
{
struct desc_ptr *desc = fixup_pointer(&bringup_idt_descr, physbase);
gate_desc *idt = fixup_pointer(bringup_idt_table, physbase);
diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c
index b348a672f..b525fe6d6 100644
--- a/arch/x86/kernel/platform-quirks.c
+++ b/arch/x86/kernel/platform-quirks.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/init.h>
+#include <linux/pnp.h>
#include <asm/setup.h>
#include <asm/bios_ebda.h>
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 7f94dbbc3..a0d3059be 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -137,7 +137,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
log_lvl, d3, d6, d7);
}
- if (cpu_feature_enabled(X86_FEATURE_OSPKE))
+ if (cr4 & X86_CR4_PKE)
printk("%sPKRU: %08x\n", log_lvl, read_pkru());
}
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index 271e70d57..3fe76bf17 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -86,7 +86,8 @@ static bool __init sev_es_check_cpu_features(void)
return true;
}
-static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason)
+static void __head __noreturn
+sev_es_terminate(unsigned int set, unsigned int reason)
{
u64 val = GHCB_MSR_TERM_REQ;
@@ -323,13 +324,7 @@ static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid
*/
static const struct snp_cpuid_table *snp_cpuid_get_table(void)
{
- void *ptr;
-
- asm ("lea cpuid_table_copy(%%rip), %0"
- : "=r" (ptr)
- : "p" (&cpuid_table_copy));
-
- return ptr;
+ return &RIP_REL_REF(cpuid_table_copy);
}
/*
@@ -388,7 +383,7 @@ static u32 snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted)
return xsave_size;
}
-static bool
+static bool __head
snp_cpuid_get_validated_func(struct cpuid_leaf *leaf)
{
const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
@@ -525,7 +520,8 @@ static int snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
* Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value
* should be treated as fatal by caller.
*/
-static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
+static int __head
+snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
{
const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
@@ -567,7 +563,7 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le
* page yet, so it only supports the MSR based communication with the
* hypervisor and only the CPUID exit-code.
*/
-void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
+void __head do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
{
unsigned int subfn = lower_bits(regs->cx, 32);
unsigned int fn = lower_bits(regs->ax, 32);
@@ -1013,7 +1009,8 @@ struct cc_setup_data {
* Search for a Confidential Computing blob passed in as a setup_data entry
* via the Linux Boot Protocol.
*/
-static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp)
+static __head
+struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp)
{
struct cc_setup_data *sd = NULL;
struct setup_data *hdr;
@@ -1040,7 +1037,7 @@ static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp)
* mapping needs to be updated in sync with all the changes to virtual memory
* layout and related mapping facilities throughout the boot process.
*/
-static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
+static void __head setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
{
const struct snp_cpuid_table *cpuid_table_fw, *cpuid_table;
int i;
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index e35fcc8d4..f8a8249ae 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -26,6 +26,7 @@
#include <linux/dmi.h>
#include <uapi/linux/sev-guest.h>
+#include <asm/init.h>
#include <asm/cpu_entry_area.h>
#include <asm/stacktrace.h>
#include <asm/sev.h>
@@ -690,7 +691,7 @@ static void pvalidate_pages(unsigned long vaddr, unsigned long npages, bool vali
}
}
-static void __init early_set_pages_state(unsigned long paddr, unsigned long npages, enum psc_op op)
+static void __head early_set_pages_state(unsigned long paddr, unsigned long npages, enum psc_op op)
{
unsigned long paddr_end;
u64 val;
@@ -728,7 +729,7 @@ e_term:
sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
}
-void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
+void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
unsigned long npages)
{
/*
@@ -2085,7 +2086,7 @@ fail:
*
* Scan for the blob in that order.
*/
-static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
+static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
{
struct cc_blob_sev_info *cc_info;
@@ -2111,7 +2112,7 @@ found_cc_info:
return cc_info;
}
-bool __init snp_init(struct boot_params *bp)
+bool __head snp_init(struct boot_params *bp)
{
struct cc_blob_sev_info *cc_info;
@@ -2133,7 +2134,7 @@ bool __init snp_init(struct boot_params *bp)
return true;
}
-void __init __noreturn snp_abort(void)
+void __head __noreturn snp_abort(void)
{
sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
}
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 62a44455c..f02961cbb 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -340,6 +340,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
kvm_update_pv_runtime(vcpu);
+ vcpu->arch.is_amd_compatible = guest_cpuid_is_amd_or_hygon(vcpu);
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu);
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index b1658c0de..18fd2e845 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -125,6 +125,16 @@ static inline bool guest_cpuid_is_intel(struct kvm_vcpu *vcpu)
return best && is_guest_vendor_intel(best->ebx, best->ecx, best->edx);
}
+static inline bool guest_cpuid_is_amd_compatible(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.is_amd_compatible;
+}
+
+static inline bool guest_cpuid_is_intel_compatible(struct kvm_vcpu *vcpu)
+{
+ return !guest_cpuid_is_amd_compatible(vcpu);
+}
+
static inline int guest_cpuid_family(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index bfeafe485..c90fef025 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2548,7 +2548,8 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type)
trig_mode = reg & APIC_LVT_LEVEL_TRIGGER;
r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL);
- if (r && lvt_type == APIC_LVTPC)
+ if (r && lvt_type == APIC_LVTPC &&
+ guest_cpuid_is_intel_compatible(apic->vcpu))
kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED);
return r;
}
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d30325e29..13134954e 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4649,7 +4649,7 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu,
context->cpu_role.base.level, is_efer_nx(context),
guest_can_use_gbpages(vcpu),
is_cr4_pse(context),
- guest_cpuid_is_amd_or_hygon(vcpu));
+ guest_cpuid_is_amd_compatible(vcpu));
}
static void
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 5c1590855..10aff2c9a 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7742,8 +7742,28 @@ static u64 vmx_get_perf_capabilities(void)
if (vmx_pebs_supported()) {
perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK;
- if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4)
- perf_cap &= ~PERF_CAP_PEBS_BASELINE;
+
+ /*
+ * Disallow adaptive PEBS as it is functionally broken, can be
+ * used by the guest to read *host* LBRs, and can be used to
+ * bypass userspace event filters. To correctly and safely
+ * support adaptive PEBS, KVM needs to:
+ *
+ * 1. Account for the ADAPTIVE flag when (re)programming fixed
+ * counters.
+ *
+ * 2. Gain support from perf (or take direct control of counter
+ * programming) to support events without adaptive PEBS
+ * enabled for the hardware counter.
+ *
+ * 3. Ensure LBR MSRs cannot hold host data on VM-Entry with
+ * adaptive PEBS enabled and MSR_PEBS_DATA_CFG.LBRS=1.
+ *
+ * 4. Document which PMU events are effectively exposed to the
+ * guest via adaptive PEBS, and make adaptive PEBS mutually
+ * exclusive with KVM_SET_PMU_EVENT_FILTER if necessary.
+ */
+ perf_cap &= ~PERF_CAP_PEBS_BASELINE;
}
return perf_cap;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f72476503..a2ea636a2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3278,7 +3278,7 @@ static bool is_mci_status_msr(u32 msr)
static bool can_set_mci_status(struct kvm_vcpu *vcpu)
{
/* McStatusWrEn enabled? */
- if (guest_cpuid_is_amd_or_hygon(vcpu))
+ if (guest_cpuid_is_amd_compatible(vcpu))
return !!(vcpu->arch.msr_hwcr & BIT_ULL(18));
return false;
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index 9de3d900b..e25288ee3 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -26,7 +26,7 @@ SYM_FUNC_START(sme_encrypt_execute)
* RCX - virtual address of the encryption workarea, including:
* - stack page (PAGE_SIZE)
* - encryption routine page (PAGE_SIZE)
- * - intermediate copy buffer (PMD_PAGE_SIZE)
+ * - intermediate copy buffer (PMD_SIZE)
* R8 - physical address of the pagetables to use for encryption
*/
@@ -123,7 +123,7 @@ SYM_FUNC_START(__enc_copy)
wbinvd /* Invalidate any cache entries */
/* Copy/encrypt up to 2MB at a time */
- movq $PMD_PAGE_SIZE, %r12
+ movq $PMD_SIZE, %r12
1:
cmpq %r12, %r9
jnb 2f
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 06ccbd36e..f17609884 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -41,6 +41,7 @@
#include <linux/mem_encrypt.h>
#include <linux/cc_platform.h>
+#include <asm/init.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/cmdline.h>
@@ -93,12 +94,12 @@ struct sme_populate_pgd_data {
* section is 2MB aligned to allow for simple pagetable setup using only
* PMD entries (see vmlinux.lds.S).
*/
-static char sme_workarea[2 * PMD_PAGE_SIZE] __section(".init.scratch");
+static char sme_workarea[2 * PMD_SIZE] __section(".init.scratch");
static char sme_cmdline_arg[] __initdata = "mem_encrypt";
static char sme_cmdline_on[] __initdata = "on";
-static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
+static void __head sme_clear_pgd(struct sme_populate_pgd_data *ppd)
{
unsigned long pgd_start, pgd_end, pgd_size;
pgd_t *pgd_p;
@@ -113,7 +114,7 @@ static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
memset(pgd_p, 0, pgd_size);
}
-static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
+static pud_t __head *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
{
pgd_t *pgd;
p4d_t *p4d;
@@ -150,7 +151,7 @@ static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
return pud;
}
-static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
+static void __head sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
{
pud_t *pud;
pmd_t *pmd;
@@ -166,7 +167,7 @@ static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
set_pmd(pmd, __pmd(ppd->paddr | ppd->pmd_flags));
}
-static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
+static void __head sme_populate_pgd(struct sme_populate_pgd_data *ppd)
{
pud_t *pud;
pmd_t *pmd;
@@ -192,17 +193,17 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
set_pte(pte, __pte(ppd->paddr | ppd->pte_flags));
}
-static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
+static void __head __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
{
while (ppd->vaddr < ppd->vaddr_end) {
sme_populate_pgd_large(ppd);
- ppd->vaddr += PMD_PAGE_SIZE;
- ppd->paddr += PMD_PAGE_SIZE;
+ ppd->vaddr += PMD_SIZE;
+ ppd->paddr += PMD_SIZE;
}
}
-static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
+static void __head __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
{
while (ppd->vaddr < ppd->vaddr_end) {
sme_populate_pgd(ppd);
@@ -212,7 +213,7 @@ static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
}
}
-static void __init __sme_map_range(struct sme_populate_pgd_data *ppd,
+static void __head __sme_map_range(struct sme_populate_pgd_data *ppd,
pmdval_t pmd_flags, pteval_t pte_flags)
{
unsigned long vaddr_end;
@@ -224,11 +225,11 @@ static void __init __sme_map_range(struct sme_populate_pgd_data *ppd,
vaddr_end = ppd->vaddr_end;
/* If start is not 2MB aligned, create PTE entries */
- ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE);
+ ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_SIZE);
__sme_map_range_pte(ppd);
/* Create PMD entries */
- ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK;
+ ppd->vaddr_end = vaddr_end & PMD_MASK;
__sme_map_range_pmd(ppd);
/* If end is not 2MB aligned, create PTE entries */
@@ -236,22 +237,22 @@ static void __init __sme_map_range(struct sme_populate_pgd_data *ppd,
__sme_map_range_pte(ppd);
}
-static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd)
+static void __head sme_map_range_encrypted(struct sme_populate_pgd_data *ppd)
{
__sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC);
}
-static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd)
+static void __head sme_map_range_decrypted(struct sme_populate_pgd_data *ppd)
{
__sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC);
}
-static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd)
+static void __head sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd)
{
__sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP);
}
-static unsigned long __init sme_pgtable_calc(unsigned long len)
+static unsigned long __head sme_pgtable_calc(unsigned long len)
{
unsigned long entries = 0, tables = 0;
@@ -288,7 +289,7 @@ static unsigned long __init sme_pgtable_calc(unsigned long len)
return entries + tables;
}
-void __init sme_encrypt_kernel(struct boot_params *bp)
+void __head sme_encrypt_kernel(struct boot_params *bp)
{
unsigned long workarea_start, workarea_end, workarea_len;
unsigned long execute_start, execute_end, execute_len;
@@ -323,9 +324,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
* memory from being cached.
*/
- /* Physical addresses gives us the identity mapped virtual addresses */
- kernel_start = __pa_symbol(_text);
- kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE);
+ kernel_start = (unsigned long)RIP_REL_REF(_text);
+ kernel_end = ALIGN((unsigned long)RIP_REL_REF(_end), PMD_SIZE);
kernel_len = kernel_end - kernel_start;
initrd_start = 0;
@@ -343,24 +343,16 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
#endif
/*
- * We're running identity mapped, so we must obtain the address to the
- * SME encryption workarea using rip-relative addressing.
- */
- asm ("lea sme_workarea(%%rip), %0"
- : "=r" (workarea_start)
- : "p" (sme_workarea));
-
- /*
* Calculate required number of workarea bytes needed:
* executable encryption area size:
* stack page (PAGE_SIZE)
* encryption routine page (PAGE_SIZE)
- * intermediate copy buffer (PMD_PAGE_SIZE)
+ * intermediate copy buffer (PMD_SIZE)
* pagetable structures for the encryption of the kernel
* pagetable structures for workarea (in case not currently mapped)
*/
- execute_start = workarea_start;
- execute_end = execute_start + (PAGE_SIZE * 2) + PMD_PAGE_SIZE;
+ execute_start = workarea_start = (unsigned long)RIP_REL_REF(sme_workarea);
+ execute_end = execute_start + (PAGE_SIZE * 2) + PMD_SIZE;
execute_len = execute_end - execute_start;
/*
@@ -383,7 +375,7 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
* before it is mapped.
*/
workarea_len = execute_len + pgtable_area_len;
- workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE);
+ workarea_end = ALIGN(workarea_start + workarea_len, PMD_SIZE);
/*
* Set the address to the start of where newly created pagetable
@@ -502,7 +494,7 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
native_write_cr3(__native_read_cr3());
}
-void __init sme_enable(struct boot_params *bp)
+void __head sme_enable(struct boot_params *bp)
{
const char *cmdline_ptr, *cmdline_arg, *cmdline_on;
unsigned int eax, ebx, ecx, edx;
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 5f0ce77a2..68d4f328f 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -747,11 +747,11 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr)
switch (level) {
case PG_LEVEL_1G:
phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT;
- offset = virt_addr & ~PUD_PAGE_MASK;
+ offset = virt_addr & ~PUD_MASK;
break;
case PG_LEVEL_2M:
phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT;
- offset = virt_addr & ~PMD_PAGE_MASK;
+ offset = virt_addr & ~PMD_MASK;
break;
default:
phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
@@ -1041,7 +1041,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
case PG_LEVEL_1G:
ref_prot = pud_pgprot(*(pud_t *)kpte);
ref_pfn = pud_pfn(*(pud_t *)kpte);
- pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT;
+ pfninc = PMD_SIZE >> PAGE_SHIFT;
lpaddr = address & PUD_MASK;
lpinc = PMD_SIZE;
/*
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index ffe3b3a08..78414c6d1 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -592,7 +592,7 @@ static void pti_set_kernel_image_nonglobal(void)
* of the image.
*/
unsigned long start = PFN_ALIGN(_text);
- unsigned long end = ALIGN((unsigned long)_end, PMD_PAGE_SIZE);
+ unsigned long end = ALIGN((unsigned long)_end, PMD_SIZE);
/*
* This clears _PAGE_GLOBAL from the entire kernel image.