summaryrefslogtreecommitdiff
path: root/arch/x86/boot/compressed
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/boot/compressed')
-rw-r--r--arch/x86/boot/compressed/Makefile54
-rw-r--r--arch/x86/boot/compressed/cpuflags.c4
-rw-r--r--arch/x86/boot/compressed/head_32.S99
-rw-r--r--arch/x86/boot/compressed/head_64.S198
-rw-r--r--arch/x86/boot/compressed/ident_map_64.c349
-rw-r--r--arch/x86/boot/compressed/idt_64.c54
-rw-r--r--arch/x86/boot/compressed/idt_handlers_64.S77
-rw-r--r--arch/x86/boot/compressed/kaslr.c266
-rw-r--r--arch/x86/boot/compressed/kaslr_64.c153
-rw-r--r--arch/x86/boot/compressed/misc.c7
-rw-r--r--arch/x86/boot/compressed/misc.h54
-rw-r--r--arch/x86/boot/compressed/mkpiggy.c6
-rw-r--r--arch/x86/boot/compressed/pgtable_64.c9
-rw-r--r--arch/x86/boot/compressed/sev-es.c214
-rw-r--r--arch/x86/boot/compressed/vmlinux.lds.S50
15 files changed, 1044 insertions, 550 deletions
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 3962f592633d..ee249088cbfe 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -29,10 +29,10 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4 vmlinux.bin.zst
KBUILD_CFLAGS := -m$(BITS) -O2
-KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC)
+KBUILD_CFLAGS += -fno-strict-aliasing -fPIE
KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
cflags-$(CONFIG_X86_32) := -march=i386
-cflags-$(CONFIG_X86_64) := -mcmodel=small
+cflags-$(CONFIG_X86_64) := -mcmodel=small -mno-red-zone
KBUILD_CFLAGS += $(cflags-y)
KBUILD_CFLAGS += -mno-mmx -mno-sse
KBUILD_CFLAGS += -ffreestanding
@@ -43,24 +43,26 @@ KBUILD_CFLAGS += -Wno-pointer-sign
KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
KBUILD_CFLAGS += -D__DISABLE_EXPORTS
+# Disable relocation relaxation in case the link is not PIE.
+KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no)
+KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h
+
+# sev-es.c indirectly inludes inat-table.h which is generated during
+# compilation and stored in $(objtree). Add the directory to the includes so
+# that the compiler finds it even with out-of-tree builds (make O=/some/path).
+CFLAGS_sev-es.o += -I$(objtree)/arch/x86/lib/
KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
GCOV_PROFILE := n
UBSAN_SANITIZE :=n
KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE)
+KBUILD_LDFLAGS += $(call ld-option,--no-ld-generated-unwind-info)
# Compressed kernel should be built as PIE since it may be loaded at any
# address by the bootloader.
-ifeq ($(CONFIG_X86_32),y)
-KBUILD_LDFLAGS += $(call ld-option, -pie) $(call ld-option, --no-dynamic-linker)
-else
-# To build 64-bit compressed kernel as PIE, we disable relocation
-# overflow check to avoid relocation overflow error with a new linker
-# command-line option, -z noreloc-overflow.
-KBUILD_LDFLAGS += $(shell $(LD) --help 2>&1 | grep -q "\-z noreloc-overflow" \
- && echo "-z noreloc-overflow -pie --no-dynamic-linker")
-endif
-LDFLAGS_vmlinux := -T
+LDFLAGS_vmlinux := -pie $(call ld-option, --no-dynamic-linker)
+LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
+LDFLAGS_vmlinux += -T
hostprogs := mkpiggy
HOST_EXTRACFLAGS += -I$(srctree)/tools/include
@@ -84,9 +86,11 @@ vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/kernel_info.o $(obj)/head_$(BITS).o
vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o
vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o
ifdef CONFIG_X86_64
- vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr_64.o
+ vmlinux-objs-y += $(obj)/ident_map_64.o
+ vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o
vmlinux-objs-y += $(obj)/mem_encrypt.o
vmlinux-objs-y += $(obj)/pgtable_64.o
+ vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev-es.o
endif
vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
@@ -94,30 +98,8 @@ vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a
-# The compressed kernel is built with -fPIC/-fPIE so that a boot loader
-# can place it anywhere in memory and it will still run. However, since
-# it is executed as-is without any ELF relocation processing performed
-# (and has already had all relocation sections stripped from the binary),
-# none of the code can use data relocations (e.g. static assignments of
-# pointer values), since they will be meaningless at runtime. This check
-# will refuse to link the vmlinux if any of these relocations are found.
-quiet_cmd_check_data_rel = DATAREL $@
-define cmd_check_data_rel
- for obj in $(filter %.o,$^); do \
- $(READELF) -S $$obj | grep -qF .rel.local && { \
- echo "error: $$obj has data relocations!" >&2; \
- exit 1; \
- } || true; \
- done
-endef
-
-# We need to run two commands under "if_changed", so merge them into a
-# single invocation.
-quiet_cmd_check-and-link-vmlinux = LD $@
- cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld)
-
$(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE
- $(call if_changed,check-and-link-vmlinux)
+ $(call if_changed,ld)
OBJCOPYFLAGS_vmlinux.bin := -R .comment -S
$(obj)/vmlinux.bin: vmlinux FORCE
diff --git a/arch/x86/boot/compressed/cpuflags.c b/arch/x86/boot/compressed/cpuflags.c
index 6448a8196d32..0cc1323896d1 100644
--- a/arch/x86/boot/compressed/cpuflags.c
+++ b/arch/x86/boot/compressed/cpuflags.c
@@ -1,6 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
-#ifdef CONFIG_RANDOMIZE_BASE
-
#include "../cpuflags.c"
bool has_cpuflag(int flag)
@@ -9,5 +7,3 @@ bool has_cpuflag(int flag)
return test_bit(flag, cpu.flags);
}
-
-#endif
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 03557f2174bf..659fad53ca82 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -33,32 +33,13 @@
#include <asm/bootparam.h>
/*
- * The 32-bit x86 assembler in binutils 2.26 will generate R_386_GOT32X
- * relocation to get the symbol address in PIC. When the compressed x86
- * kernel isn't built as PIC, the linker optimizes R_386_GOT32X
- * relocations to their fixed symbol addresses. However, when the
- * compressed x86 kernel is loaded at a different address, it leads
- * to the following load failure:
- *
- * Failed to allocate space for phdrs
- *
- * during the decompression stage.
- *
- * If the compressed x86 kernel is relocatable at run-time, it should be
- * compiled with -fPIE, instead of -fPIC, if possible and should be built as
- * Position Independent Executable (PIE) so that linker won't optimize
- * R_386_GOT32X relocation to its fixed symbol address. Older
- * linkers generate R_386_32 relocations against locally defined symbols,
- * _bss, _ebss, _got, _egot and _end, in PIE. It isn't wrong, just less
- * optimal than R_386_RELATIVE. But the x86 kernel fails to properly handle
- * R_386_32 relocations when relocating the kernel. To generate
- * R_386_RELATIVE relocations, we mark _bss, _ebss, _got, _egot and _end as
- * hidden:
+ * These symbols needed to be marked as .hidden to prevent the BFD linker from
+ * generating R_386_32 (rather than R_386_RELATIVE) relocations for them when
+ * the 32-bit compressed kernel is linked as PIE. This is no longer necessary,
+ * but it doesn't hurt to keep them .hidden.
*/
.hidden _bss
.hidden _ebss
- .hidden _got
- .hidden _egot
.hidden _end
__HEAD
@@ -77,10 +58,10 @@ SYM_FUNC_START(startup_32)
leal (BP_scratch+4)(%esi), %esp
call 1f
1: popl %edx
- subl $1b, %edx
+ addl $_GLOBAL_OFFSET_TABLE_+(.-1b), %edx
/* Load new GDT */
- leal gdt(%edx), %eax
+ leal gdt@GOTOFF(%edx), %eax
movl %eax, 2(%eax)
lgdt (%eax)
@@ -93,14 +74,16 @@ SYM_FUNC_START(startup_32)
movl %eax, %ss
/*
- * %edx contains the address we are loaded at by the boot loader and %ebx
- * contains the address where we should move the kernel image temporarily
- * for safe in-place decompression. %ebp contains the address that the kernel
- * will be decompressed to.
+ * %edx contains the address we are loaded at by the boot loader (plus the
+ * offset to the GOT). The below code calculates %ebx to be the address where
+ * we should move the kernel image temporarily for safe in-place decompression
+ * (again, plus the offset to the GOT).
+ *
+ * %ebp is calculated to be the address that the kernel will be decompressed to.
*/
#ifdef CONFIG_RELOCATABLE
- movl %edx, %ebx
+ leal startup_32@GOTOFF(%edx), %ebx
#ifdef CONFIG_EFI_STUB
/*
@@ -111,7 +94,7 @@ SYM_FUNC_START(startup_32)
* image_offset = startup_32 - image_base
* Otherwise image_offset will be zero and has no effect on the calculations.
*/
- subl image_offset(%edx), %ebx
+ subl image_offset@GOTOFF(%edx), %ebx
#endif
movl BP_kernel_alignment(%esi), %eax
@@ -128,10 +111,10 @@ SYM_FUNC_START(startup_32)
movl %ebx, %ebp // Save the output address for later
/* Target address to relocate to for decompression */
addl BP_init_size(%esi), %ebx
- subl $_end, %ebx
+ subl $_end@GOTOFF, %ebx
/* Set up the stack */
- leal boot_stack_end(%ebx), %esp
+ leal boot_stack_end@GOTOFF(%ebx), %esp
/* Zero EFLAGS */
pushl $0
@@ -142,8 +125,8 @@ SYM_FUNC_START(startup_32)
* where decompression in place becomes safe.
*/
pushl %esi
- leal (_bss-4)(%edx), %esi
- leal (_bss-4)(%ebx), %edi
+ leal (_bss@GOTOFF-4)(%edx), %esi
+ leal (_bss@GOTOFF-4)(%ebx), %edi
movl $(_bss - startup_32), %ecx
shrl $2, %ecx
std
@@ -156,14 +139,14 @@ SYM_FUNC_START(startup_32)
* during extract_kernel below. To avoid any issues, repoint the GDTR
* to the new copy of the GDT.
*/
- leal gdt(%ebx), %eax
+ leal gdt@GOTOFF(%ebx), %eax
movl %eax, 2(%eax)
lgdt (%eax)
/*
* Jump to the relocated address.
*/
- leal .Lrelocated(%ebx), %eax
+ leal .Lrelocated@GOTOFF(%ebx), %eax
jmp *%eax
SYM_FUNC_END(startup_32)
@@ -173,7 +156,7 @@ SYM_FUNC_START_ALIAS(efi_stub_entry)
add $0x4, %esp
movl 8(%esp), %esi /* save boot_params pointer */
call efi_main
- leal startup_32(%eax), %eax
+ /* efi_main returns the possibly relocated address of startup_32 */
jmp *%eax
SYM_FUNC_END(efi32_stub_entry)
SYM_FUNC_END_ALIAS(efi_stub_entry)
@@ -186,40 +169,26 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
* Clear BSS (stack is currently empty)
*/
xorl %eax, %eax
- leal _bss(%ebx), %edi
- leal _ebss(%ebx), %ecx
+ leal _bss@GOTOFF(%ebx), %edi
+ leal _ebss@GOTOFF(%ebx), %ecx
subl %edi, %ecx
shrl $2, %ecx
rep stosl
/*
- * Adjust our own GOT
- */
- leal _got(%ebx), %edx
- leal _egot(%ebx), %ecx
-1:
- cmpl %ecx, %edx
- jae 2f
- addl %ebx, (%edx)
- addl $4, %edx
- jmp 1b
-2:
-
-/*
* Do the extraction, and jump to the new kernel..
*/
- /* push arguments for extract_kernel: */
- pushl $z_output_len /* decompressed length, end of relocs */
-
- pushl %ebp /* output address */
-
- pushl $z_input_len /* input_len */
- leal input_data(%ebx), %eax
- pushl %eax /* input_data */
- leal boot_heap(%ebx), %eax
- pushl %eax /* heap area */
- pushl %esi /* real mode pointer */
- call extract_kernel /* returns kernel location in %eax */
+ /* push arguments for extract_kernel: */
+
+ pushl output_len@GOTOFF(%ebx) /* decompressed length, end of relocs */
+ pushl %ebp /* output address */
+ pushl input_len@GOTOFF(%ebx) /* input_len */
+ leal input_data@GOTOFF(%ebx), %eax
+ pushl %eax /* input_data */
+ leal boot_heap@GOTOFF(%ebx), %eax
+ pushl %eax /* heap area */
+ pushl %esi /* real mode pointer */
+ call extract_kernel /* returns kernel location in %eax */
addl $24, %esp
/*
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 97d37f0a34f5..1c80f1738fd9 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -33,6 +33,7 @@
#include <asm/processor-flags.h>
#include <asm/asm-offsets.h>
#include <asm/bootparam.h>
+#include <asm/desc_defs.h>
#include "pgtable.h"
/*
@@ -40,11 +41,35 @@
*/
.hidden _bss
.hidden _ebss
- .hidden _got
- .hidden _egot
.hidden _end
__HEAD
+
+/*
+ * This macro gives the relative virtual address of X, i.e. the offset of X
+ * from startup_32. This is the same as the link-time virtual address of X,
+ * since startup_32 is at 0, but defining it this way tells the
+ * assembler/linker that we do not want the actual run-time address of X. This
+ * prevents the linker from trying to create unwanted run-time relocation
+ * entries for the reference when the compressed kernel is linked as PIE.
+ *
+ * A reference X(%reg) will result in the link-time VA of X being stored with
+ * the instruction, and a run-time R_X86_64_RELATIVE relocation entry that
+ * adds the 64-bit base address where the kernel is loaded.
+ *
+ * Replacing it with (X-startup_32)(%reg) results in the offset being stored,
+ * and no run-time relocation.
+ *
+ * The macro should be used as a displacement with a base register containing
+ * the run-time address of startup_32 [i.e. rva(X)(%reg)], or as an immediate
+ * [$ rva(X)].
+ *
+ * This macro can only be used from within the .head.text section, since the
+ * expression requires startup_32 to be in the same section as the code being
+ * assembled.
+ */
+#define rva(X) ((X) - startup_32)
+
.code32
SYM_FUNC_START(startup_32)
/*
@@ -67,10 +92,10 @@ SYM_FUNC_START(startup_32)
leal (BP_scratch+4)(%esi), %esp
call 1f
1: popl %ebp
- subl $1b, %ebp
+ subl $ rva(1b), %ebp
/* Load new GDT with the 64bit segments using 32bit descriptor */
- leal gdt(%ebp), %eax
+ leal rva(gdt)(%ebp), %eax
movl %eax, 2(%eax)
lgdt (%eax)
@@ -83,7 +108,7 @@ SYM_FUNC_START(startup_32)
movl %eax, %ss
/* setup a stack and make sure cpu supports long mode. */
- leal boot_stack_end(%ebp), %esp
+ leal rva(boot_stack_end)(%ebp), %esp
call verify_cpu
testl %eax, %eax
@@ -110,7 +135,7 @@ SYM_FUNC_START(startup_32)
* image_offset = startup_32 - image_base
* Otherwise image_offset will be zero and has no effect on the calculations.
*/
- subl image_offset(%ebp), %ebx
+ subl rva(image_offset)(%ebp), %ebx
#endif
movl BP_kernel_alignment(%esi), %eax
@@ -126,7 +151,7 @@ SYM_FUNC_START(startup_32)
/* Target address to relocate to for decompression */
addl BP_init_size(%esi), %ebx
- subl $_end, %ebx
+ subl $ rva(_end), %ebx
/*
* Prepare for entering 64 bit mode
@@ -154,19 +179,19 @@ SYM_FUNC_START(startup_32)
1:
/* Initialize Page tables to 0 */
- leal pgtable(%ebx), %edi
+ leal rva(pgtable)(%ebx), %edi
xorl %eax, %eax
movl $(BOOT_INIT_PGT_SIZE/4), %ecx
rep stosl
/* Build Level 4 */
- leal pgtable + 0(%ebx), %edi
+ leal rva(pgtable + 0)(%ebx), %edi
leal 0x1007 (%edi), %eax
movl %eax, 0(%edi)
addl %edx, 4(%edi)
/* Build Level 3 */
- leal pgtable + 0x1000(%ebx), %edi
+ leal rva(pgtable + 0x1000)(%ebx), %edi
leal 0x1007(%edi), %eax
movl $4, %ecx
1: movl %eax, 0x00(%edi)
@@ -177,7 +202,7 @@ SYM_FUNC_START(startup_32)
jnz 1b
/* Build Level 2 */
- leal pgtable + 0x2000(%ebx), %edi
+ leal rva(pgtable + 0x2000)(%ebx), %edi
movl $0x00000183, %eax
movl $2048, %ecx
1: movl %eax, 0(%edi)
@@ -188,7 +213,7 @@ SYM_FUNC_START(startup_32)
jnz 1b
/* Enable the boot page tables */
- leal pgtable(%ebx), %eax
+ leal rva(pgtable)(%ebx), %eax
movl %eax, %cr3
/* Enable Long mode in EFER (Extended Feature Enable Register) */
@@ -213,14 +238,14 @@ SYM_FUNC_START(startup_32)
* We place all of the values on our mini stack so lret can
* used to perform that far jump.
*/
- leal startup_64(%ebp), %eax
+ leal rva(startup_64)(%ebp), %eax
#ifdef CONFIG_EFI_MIXED
- movl efi32_boot_args(%ebp), %edi
+ movl rva(efi32_boot_args)(%ebp), %edi
cmp $0, %edi
jz 1f
- leal efi64_stub_entry(%ebp), %eax
- movl efi32_boot_args+4(%ebp), %esi
- movl efi32_boot_args+8(%ebp), %edx // saved bootparams pointer
+ leal rva(efi64_stub_entry)(%ebp), %eax
+ movl rva(efi32_boot_args+4)(%ebp), %esi
+ movl rva(efi32_boot_args+8)(%ebp), %edx // saved bootparams pointer
cmpl $0, %edx
jnz 1f
/*
@@ -231,7 +256,7 @@ SYM_FUNC_START(startup_32)
* the correct stack alignment for entry.
*/
subl $40, %esp
- leal efi_pe_entry(%ebp), %eax
+ leal rva(efi_pe_entry)(%ebp), %eax
movl %edi, %ecx // MS calling convention
movl %esi, %edx
1:
@@ -257,18 +282,18 @@ SYM_FUNC_START(efi32_stub_entry)
call 1f
1: pop %ebp
- subl $1b, %ebp
+ subl $ rva(1b), %ebp
- movl %esi, efi32_boot_args+8(%ebp)
+ movl %esi, rva(efi32_boot_args+8)(%ebp)
SYM_INNER_LABEL(efi32_pe_stub_entry, SYM_L_LOCAL)
- movl %ecx, efi32_boot_args(%ebp)
- movl %edx, efi32_boot_args+4(%ebp)
- movb $0, efi_is64(%ebp)
+ movl %ecx, rva(efi32_boot_args)(%ebp)
+ movl %edx, rva(efi32_boot_args+4)(%ebp)
+ movb $0, rva(efi_is64)(%ebp)
/* Save firmware GDTR and code/data selectors */
- sgdtl efi32_boot_gdt(%ebp)
- movw %cs, efi32_boot_cs(%ebp)
- movw %ds, efi32_boot_ds(%ebp)
+ sgdtl rva(efi32_boot_gdt)(%ebp)
+ movw %cs, rva(efi32_boot_cs)(%ebp)
+ movw %ds, rva(efi32_boot_ds)(%ebp)
/* Disable paging */
movl %cr0, %eax
@@ -347,30 +372,11 @@ SYM_CODE_START(startup_64)
/* Target address to relocate to for decompression */
movl BP_init_size(%rsi), %ebx
- subl $_end, %ebx
+ subl $ rva(_end), %ebx
addq %rbp, %rbx
/* Set up the stack */
- leaq boot_stack_end(%rbx), %rsp
-
- /*
- * paging_prepare() and cleanup_trampoline() below can have GOT
- * references. Adjust the table with address we are running at.
- *
- * Zero RAX for adjust_got: the GOT was not adjusted before;
- * there's no adjustment to undo.
- */
- xorq %rax, %rax
-
- /*
- * Calculate the address the binary is loaded at and use it as
- * a GOT adjustment.
- */
- call 1f
-1: popq %rdi
- subq $1b, %rdi
-
- call .Ladjust_got
+ leaq rva(boot_stack_end)(%rbx), %rsp
/*
* At this point we are in long mode with 4-level paging enabled,
@@ -410,6 +416,10 @@ SYM_CODE_START(startup_64)
.Lon_kernel_cs:
+ pushq %rsi
+ call load_stage1_idt
+ popq %rsi
+
/*
* paging_prepare() sets up the trampoline and checks if we need to
* enable 5-level paging.
@@ -444,7 +454,7 @@ SYM_CODE_START(startup_64)
lretq
trampoline_return:
/* Restore the stack, the 32-bit trampoline uses its own stack */
- leaq boot_stack_end(%rbx), %rsp
+ leaq rva(boot_stack_end)(%rbx), %rsp
/*
* cleanup_trampoline() would restore trampoline memory.
@@ -456,7 +466,7 @@ trampoline_return:
* this function call.
*/
pushq %rsi
- leaq top_pgtable(%rbx), %rdi
+ leaq rva(top_pgtable)(%rbx), %rdi
call cleanup_trampoline
popq %rsi
@@ -464,30 +474,15 @@ trampoline_return:
pushq $0
popfq
- /*
- * Previously we've adjusted the GOT with address the binary was
- * loaded at. Now we need to re-adjust for relocation address.
- *
- * Calculate the address the binary is loaded at, so that we can
- * undo the previous GOT adjustment.
- */
- call 1f
-1: popq %rax
- subq $1b, %rax
-
- /* The new adjustment is the relocation address */
- movq %rbx, %rdi
- call .Ladjust_got
-
/*
* Copy the compressed kernel to the end of our buffer
* where decompression in place becomes safe.
*/
pushq %rsi
leaq (_bss-8)(%rip), %rsi
- leaq (_bss-8)(%rbx), %rdi
- movq $_bss /* - $startup_32 */, %rcx
- shrq $3, %rcx
+ leaq rva(_bss-8)(%rbx), %rdi
+ movl $(_bss - startup_32), %ecx
+ shrl $3, %ecx
std
rep movsq
cld
@@ -498,15 +493,15 @@ trampoline_return:
* during extract_kernel below. To avoid any issues, repoint the GDTR
* to the new copy of the GDT.
*/
- leaq gdt64(%rbx), %rax
- leaq gdt(%rbx), %rdx
+ leaq rva(gdt64)(%rbx), %rax
+ leaq rva(gdt)(%rbx), %rdx
movq %rdx, 2(%rax)
lgdt (%rax)
/*
* Jump to the relocated address.
*/
- leaq .Lrelocated(%rbx), %rax
+ leaq rva(.Lrelocated)(%rbx), %rax
jmp *%rax
SYM_CODE_END(startup_64)
@@ -518,7 +513,7 @@ SYM_FUNC_START_ALIAS(efi_stub_entry)
movq %rdx, %rbx /* save boot_params pointer */
call efi_main
movq %rbx,%rsi
- leaq startup_64(%rax), %rax
+ leaq rva(startup_64)(%rax), %rax
jmp *%rax
SYM_FUNC_END(efi64_stub_entry)
SYM_FUNC_END_ALIAS(efi_stub_entry)
@@ -538,15 +533,30 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
rep stosq
/*
+ * If running as an SEV guest, the encryption mask is required in the
+ * page-table setup code below. When the guest also has SEV-ES enabled
+ * set_sev_encryption_mask() will cause #VC exceptions, but the stage2
+ * handler can't map its GHCB because the page-table is not set up yet.
+ * So set up the encryption mask here while still on the stage1 #VC
+ * handler. Then load stage2 IDT and switch to the kernel's own
+ * page-table.
+ */
+ pushq %rsi
+ call set_sev_encryption_mask
+ call load_stage2_idt
+ call initialize_identity_maps
+ popq %rsi
+
+/*
* Do the extraction, and jump to the new kernel..
*/
pushq %rsi /* Save the real mode argument */
movq %rsi, %rdi /* real mode address */
leaq boot_heap(%rip), %rsi /* malloc area for uncompression */
leaq input_data(%rip), %rdx /* input_data */
- movl $z_input_len, %ecx /* input_len */
+ movl input_len(%rip), %ecx /* input_len */
movq %rbp, %r8 /* output target address */
- movl $z_output_len, %r9d /* decompressed length, end of relocs */
+ movl output_len(%rip), %r9d /* decompressed length, end of relocs */
call extract_kernel /* returns kernel location in %rax */
popq %rsi
@@ -556,27 +566,6 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated)
jmp *%rax
SYM_FUNC_END(.Lrelocated)
-/*
- * Adjust the global offset table
- *
- * RAX is the previous adjustment of the table to undo (use 0 if it's the
- * first time we touch GOT).
- * RDI is the new adjustment to apply.
- */
-.Ladjust_got:
- /* Walk through the GOT adding the address to the entries */
- leaq _got(%rip), %rdx
- leaq _egot(%rip), %rcx
-1:
- cmpq %rcx, %rdx
- jae 2f
- subq %rax, (%rdx) /* Undo previous adjustment */
- addq %rdi, (%rdx) /* Apply the new adjustment */
- addq $8, %rdx
- jmp 1b
-2:
- ret
-
.code32
/*
* This is the 32-bit trampoline that will be copied over to low memory.
@@ -690,10 +679,21 @@ SYM_DATA_START_LOCAL(gdt)
.quad 0x0000000000000000 /* TS continued */
SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end)
+SYM_DATA_START(boot_idt_desc)
+ .word boot_idt_end - boot_idt - 1
+ .quad 0
+SYM_DATA_END(boot_idt_desc)
+ .balign 8
+SYM_DATA_START(boot_idt)
+ .rept BOOT_IDT_ENTRIES
+ .quad 0
+ .quad 0
+ .endr
+SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end)
+
#ifdef CONFIG_EFI_STUB
SYM_DATA(image_offset, .long 0)
#endif
-
#ifdef CONFIG_EFI_MIXED
SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0)
SYM_DATA(efi_is64, .byte 1)
@@ -702,7 +702,7 @@ SYM_DATA(efi_is64, .byte 1)
#define BS32_handle_protocol 88 // offsetof(efi_boot_services_32_t, handle_protocol)
#define LI32_image_base 32 // offsetof(efi_loaded_image_32_t, image_base)
- .text
+ __HEAD
.code32
SYM_FUNC_START(efi32_pe_entry)
/*
@@ -724,12 +724,12 @@ SYM_FUNC_START(efi32_pe_entry)
call 1f
1: pop %ebx
- subl $1b, %ebx
+ subl $ rva(1b), %ebx
/* Get the loaded image protocol pointer from the image handle */
leal -4(%ebp), %eax
pushl %eax // &loaded_image
- leal loaded_image_proto(%ebx), %eax
+ leal rva(loaded_image_proto)(%ebx), %eax
pushl %eax // pass the GUID address
pushl 8(%ebp) // pass the image handle
@@ -764,7 +764,7 @@ SYM_FUNC_START(efi32_pe_entry)
* use it before we get to the 64-bit efi_pe_entry() in C code.
*/
subl %esi, %ebx
- movl %ebx, image_offset(%ebp) // save image_offset
+ movl %ebx, rva(image_offset)(%ebp) // save image_offset
jmp efi32_pe_stub_entry
2: popl %edi // restore callee-save registers
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
new file mode 100644
index 000000000000..063a60edcf99
--- /dev/null
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -0,0 +1,349 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This code is used on x86_64 to create page table identity mappings on
+ * demand by building up a new set of page tables (or appending to the
+ * existing ones), and then switching over to them when ready.
+ *
+ * Copyright (C) 2015-2016 Yinghai Lu
+ * Copyright (C) 2016 Kees Cook
+ */
+
+/*
+ * Since we're dealing with identity mappings, physical and virtual
+ * addresses are the same, so override these defines which are ultimately
+ * used by the headers in misc.h.
+ */
+#define __pa(x) ((unsigned long)(x))
+#define __va(x) ((void *)((unsigned long)(x)))
+
+/* No PAGE_TABLE_ISOLATION support needed either: */
+#undef CONFIG_PAGE_TABLE_ISOLATION
+
+#include "error.h"
+#include "misc.h"
+
+/* These actually do the work of building the kernel identity maps. */
+#include <linux/pgtable.h>
+#include <asm/cmpxchg.h>
+#include <asm/trap_pf.h>
+#include <asm/trapnr.h>
+#include <asm/init.h>
+/* Use the static base for this part of the boot process */
+#undef __PAGE_OFFSET
+#define __PAGE_OFFSET __PAGE_OFFSET_BASE
+#include "../../mm/ident_map.c"
+
+#ifdef CONFIG_X86_5LEVEL
+unsigned int __pgtable_l5_enabled;
+unsigned int pgdir_shift = 39;
+unsigned int ptrs_per_p4d = 1;
+#endif
+
+/* Used by PAGE_KERN* macros: */
+pteval_t __default_kernel_pte_mask __read_mostly = ~0;
+
+/* Used to track our page table allocation area. */
+struct alloc_pgt_data {
+ unsigned char *pgt_buf;
+ unsigned long pgt_buf_size;
+ unsigned long pgt_buf_offset;
+};
+
+/*
+ * Allocates space for a page table entry, using struct alloc_pgt_data
+ * above. Besides the local callers, this is used as the allocation
+ * callback in mapping_info below.
+ */
+static void *alloc_pgt_page(void *context)
+{
+ struct alloc_pgt_data *pages = (struct alloc_pgt_data *)context;
+ unsigned char *entry;
+
+ /* Validate there is space available for a new page. */
+ if (pages->pgt_buf_offset >= pages->pgt_buf_size) {
+ debug_putstr("out of pgt_buf in " __FILE__ "!?\n");
+ debug_putaddr(pages->pgt_buf_offset);
+ debug_putaddr(pages->pgt_buf_size);
+ return NULL;
+ }
+
+ entry = pages->pgt_buf + pages->pgt_buf_offset;
+ pages->pgt_buf_offset += PAGE_SIZE;
+
+ return entry;
+}
+
+/* Used to track our allocated page tables. */
+static struct alloc_pgt_data pgt_data;
+
+/* The top level page table entry pointer. */
+static unsigned long top_level_pgt;
+
+phys_addr_t physical_mask = (1ULL << __PHYSICAL_MASK_SHIFT) - 1;
+
+/*
+ * Mapping information structure passed to kernel_ident_mapping_init().
+ * Due to relocation, pointers must be assigned at run time not build time.
+ */
+static struct x86_mapping_info mapping_info;
+
+/*
+ * Adds the specified range to the identity mappings.
+ */
+static void add_identity_map(unsigned long start, unsigned long end)
+{
+ int ret;
+
+ /* Align boundary to 2M. */
+ start = round_down(start, PMD_SIZE);
+ end = round_up(end, PMD_SIZE);
+ if (start >= end)
+ return;
+
+ /* Build the mapping. */
+ ret = kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, start, end);
+ if (ret)
+ error("Error: kernel_ident_mapping_init() failed\n");
+}
+
+/* Locates and clears a region for a new top level page table. */
+void initialize_identity_maps(void)
+{
+ /* Exclude the encryption mask from __PHYSICAL_MASK */
+ physical_mask &= ~sme_me_mask;
+
+ /* Init mapping_info with run-time function/buffer pointers. */
+ mapping_info.alloc_pgt_page = alloc_pgt_page;
+ mapping_info.context = &pgt_data;
+ mapping_info.page_flag = __PAGE_KERNEL_LARGE_EXEC | sme_me_mask;
+ mapping_info.kernpg_flag = _KERNPG_TABLE;
+
+ /*
+ * It should be impossible for this not to already be true,
+ * but since calling this a second time would rewind the other
+ * counters, let's just make sure this is reset too.
+ */
+ pgt_data.pgt_buf_offset = 0;
+
+ /*
+ * If we came here via startup_32(), cr3 will be _pgtable already
+ * and we must append to the existing area instead of entirely
+ * overwriting it.
+ *
+ * With 5-level paging, we use '_pgtable' to allocate the p4d page table,
+ * the top-level page table is allocated separately.
+ *
+ * p4d_offset(top_level_pgt, 0) would cover both the 4- and 5-level
+ * cases. On 4-level paging it's equal to 'top_level_pgt'.
+ */
+ top_level_pgt = read_cr3_pa();
+ if (p4d_offset((pgd_t *)top_level_pgt, 0) == (p4d_t *)_pgtable) {
+ pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE;
+ pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE;
+ memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
+ } else {
+ pgt_data.pgt_buf = _pgtable;
+ pgt_data.pgt_buf_size = BOOT_PGT_SIZE;
+ memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
+ top_level_pgt = (unsigned long)alloc_pgt_page(&pgt_data);
+ }
+
+ /*
+ * New page-table is set up - map the kernel image and load it
+ * into cr3.
+ */
+ add_identity_map((unsigned long)_head, (unsigned long)_end);
+ write_cr3(top_level_pgt);
+}
+
+/*
+ * This switches the page tables to the new level4 that has been built
+ * via calls to add_identity_map() above. If booted via startup_32(),
+ * this is effectively a no-op.
+ */
+void finalize_identity_maps(void)
+{
+ write_cr3(top_level_pgt);
+}
+
+static pte_t *split_large_pmd(struct x86_mapping_info *info,
+ pmd_t *pmdp, unsigned long __address)
+{
+ unsigned long page_flags;
+ unsigned long address;
+ pte_t *pte;
+ pmd_t pmd;
+ int i;
+
+ pte = (pte_t *)info->alloc_pgt_page(info->context);
+ if (!pte)
+ return NULL;
+
+ address = __address & PMD_MASK;
+ /* No large page - clear PSE flag */
+ page_flags = info->page_flag & ~_PAGE_PSE;
+
+ /* Populate the PTEs */
+ for (i = 0; i < PTRS_PER_PMD; i++) {
+ set_pte(&pte[i], __pte(address | page_flags));
+ address += PAGE_SIZE;
+ }
+
+ /*
+ * Ideally we need to clear the large PMD first and do a TLB
+ * flush before we write the new PMD. But the 2M range of the
+ * PMD might contain the code we execute and/or the stack
+ * we are on, so we can't do that. But that should be safe here
+ * because we are going from large to small mappings and we are
+ * also the only user of the page-table, so there is no chance
+ * of a TLB multihit.
+ */
+ pmd = __pmd((unsigned long)pte | info->kernpg_flag);
+ set_pmd(pmdp, pmd);
+ /* Flush TLB to establish the new PMD */
+ write_cr3(top_level_pgt);
+
+ return pte + pte_index(__address);
+}
+
+static void clflush_page(unsigned long address)
+{
+ unsigned int flush_size;
+ char *cl, *start, *end;
+
+ /*
+ * Hardcode cl-size to 64 - CPUID can't be used here because that might
+ * cause another #VC exception and the GHCB is not ready to use yet.
+ */
+ flush_size = 64;
+ start = (char *)(address & PAGE_MASK);
+ end = start + PAGE_SIZE;
+
+ /*
+ * First make sure there are no pending writes on the cache-lines to
+ * flush.
+ */
+ asm volatile("mfence" : : : "memory");
+
+ for (cl = start; cl != end; cl += flush_size)
+ clflush(cl);
+}
+
+static int set_clr_page_flags(struct x86_mapping_info *info,
+ unsigned long address,
+ pteval_t set, pteval_t clr)
+{
+ pgd_t *pgdp = (pgd_t *)top_level_pgt;
+ p4d_t *p4dp;
+ pud_t *pudp;
+ pmd_t *pmdp;
+ pte_t *ptep, pte;
+
+ /*
+ * First make sure there is a PMD mapping for 'address'.
+ * It should already exist, but keep things generic.
+ *
+ * To map the page just read from it and fault it in if there is no
+ * mapping yet. add_identity_map() can't be called here because that
+ * would unconditionally map the address on PMD level, destroying any
+ * PTE-level mappings that might already exist. Use assembly here so
+ * the access won't be optimized away.
+ */
+ asm volatile("mov %[address], %%r9"
+ :: [address] "g" (*(unsigned long *)address)
+ : "r9", "memory");
+
+ /*
+ * The page is mapped at least with PMD size - so skip checks and walk
+ * directly to the PMD.
+ */
+ p4dp = p4d_offset(pgdp, address);
+ pudp = pud_offset(p4dp, address);
+ pmdp = pmd_offset(pudp, address);
+
+ if (pmd_large(*pmdp))
+ ptep = split_large_pmd(info, pmdp, address);
+ else
+ ptep = pte_offset_kernel(pmdp, address);
+
+ if (!ptep)
+ return -ENOMEM;
+
+ /*
+ * Changing encryption attributes of a page requires to flush it from
+ * the caches.
+ */
+ if ((set | clr) & _PAGE_ENC)
+ clflush_page(address);
+
+ /* Update PTE */
+ pte = *ptep;
+ pte = pte_set_flags(pte, set);
+ pte = pte_clear_flags(pte, clr);
+ set_pte(ptep, pte);
+
+ /* Flush TLB after changing encryption attribute */
+ write_cr3(top_level_pgt);
+
+ return 0;
+}
+
+int set_page_decrypted(unsigned long address)
+{
+ return set_clr_page_flags(&mapping_info, address, 0, _PAGE_ENC);
+}
+
+int set_page_encrypted(unsigned long address)
+{
+ return set_clr_page_flags(&mapping_info, address, _PAGE_ENC, 0);
+}
+
+int set_page_non_present(unsigned long address)
+{
+ return set_clr_page_flags(&mapping_info, address, 0, _PAGE_PRESENT);
+}
+
+static void do_pf_error(const char *msg, unsigned long error_code,
+ unsigned long address, unsigned long ip)
+{
+ error_putstr(msg);
+
+ error_putstr("\nError Code: ");
+ error_puthex(error_code);
+ error_putstr("\nCR2: 0x");
+ error_puthex(address);
+ error_putstr("\nRIP relative to _head: 0x");
+ error_puthex(ip - (unsigned long)_head);
+ error_putstr("\n");
+
+ error("Stopping.\n");
+}
+
+void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code)
+{
+ unsigned long address = native_read_cr2();
+ unsigned long end;
+ bool ghcb_fault;
+
+ ghcb_fault = sev_es_check_ghcb_fault(address);
+
+ address &= PMD_MASK;
+ end = address + PMD_SIZE;
+
+ /*
+ * Check for unexpected error codes. Unexpected are:
+ * - Faults on present pages
+ * - User faults
+ * - Reserved bits set
+ */
+ if (error_code & (X86_PF_PROT | X86_PF_USER | X86_PF_RSVD))
+ do_pf_error("Unexpected page-fault:", error_code, address, regs->ip);
+ else if (ghcb_fault)
+ do_pf_error("Page-fault on GHCB page:", error_code, address, regs->ip);
+
+ /*
+ * Error code is sane - now identity map the 2M region around
+ * the faulting address.
+ */
+ add_identity_map(address, end);
+}
diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c
new file mode 100644
index 000000000000..804a502ee0d2
--- /dev/null
+++ b/arch/x86/boot/compressed/idt_64.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <asm/trap_pf.h>
+#include <asm/segment.h>
+#include <asm/trapnr.h>
+#include "misc.h"
+
+static void set_idt_entry(int vector, void (*handler)(void))
+{
+ unsigned long address = (unsigned long)handler;
+ gate_desc entry;
+
+ memset(&entry, 0, sizeof(entry));
+
+ entry.offset_low = (u16)(address & 0xffff);
+ entry.segment = __KERNEL_CS;
+ entry.bits.type = GATE_TRAP;
+ entry.bits.p = 1;
+ entry.offset_middle = (u16)((address >> 16) & 0xffff);
+ entry.offset_high = (u32)(address >> 32);
+
+ memcpy(&boot_idt[vector], &entry, sizeof(entry));
+}
+
+/* Have this here so we don't need to include <asm/desc.h> */
+static void load_boot_idt(const struct desc_ptr *dtr)
+{
+ asm volatile("lidt %0"::"m" (*dtr));
+}
+
+/* Setup IDT before kernel jumping to .Lrelocated */
+void load_stage1_idt(void)
+{
+ boot_idt_desc.address = (unsigned long)boot_idt;
+
+
+ if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT))
+ set_idt_entry(X86_TRAP_VC, boot_stage1_vc);
+
+ load_boot_idt(&boot_idt_desc);
+}
+
+/* Setup IDT after kernel jumping to .Lrelocated */
+void load_stage2_idt(void)
+{
+ boot_idt_desc.address = (unsigned long)boot_idt;
+
+ set_idt_entry(X86_TRAP_PF, boot_page_fault);
+
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+ set_idt_entry(X86_TRAP_VC, boot_stage2_vc);
+#endif
+
+ load_boot_idt(&boot_idt_desc);
+}
diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S
new file mode 100644
index 000000000000..22890e199f5b
--- /dev/null
+++ b/arch/x86/boot/compressed/idt_handlers_64.S
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Early IDT handler entry points
+ *
+ * Copyright (C) 2019 SUSE
+ *
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#include <asm/segment.h>
+
+/* For ORIG_RAX */
+#include "../../entry/calling.h"
+
+.macro EXCEPTION_HANDLER name function error_code=0
+SYM_FUNC_START(\name)
+
+ /* Build pt_regs */
+ .if \error_code == 0
+ pushq $0
+ .endif
+
+ pushq %rdi
+ pushq %rsi
+ pushq %rdx
+ pushq %rcx
+ pushq %rax
+ pushq %r8
+ pushq %r9
+ pushq %r10
+ pushq %r11
+ pushq %rbx
+ pushq %rbp
+ pushq %r12
+ pushq %r13
+ pushq %r14
+ pushq %r15
+
+ /* Call handler with pt_regs */
+ movq %rsp, %rdi
+ /* Error code is second parameter */
+ movq ORIG_RAX(%rsp), %rsi
+ call \function
+
+ /* Restore regs */
+ popq %r15
+ popq %r14
+ popq %r13
+ popq %r12
+ popq %rbp
+ popq %rbx
+ popq %r11
+ popq %r10
+ popq %r9
+ popq %r8
+ popq %rax
+ popq %rcx
+ popq %rdx
+ popq %rsi
+ popq %rdi
+
+ /* Remove error code and return */
+ addq $8, %rsp
+
+ iretq
+SYM_FUNC_END(\name)
+ .endm
+
+ .text
+ .code64
+
+EXCEPTION_HANDLER boot_page_fault do_boot_page_fault error_code=1
+
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+EXCEPTION_HANDLER boot_stage1_vc do_vc_no_ghcb error_code=1
+EXCEPTION_HANDLER boot_stage2_vc do_boot_stage2_vc error_code=1
+#endif
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index dde7cb3724df..b59547ce5b19 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -36,17 +36,12 @@
#define STATIC
#include <linux/decompress/mm.h>
-#ifdef CONFIG_X86_5LEVEL
-unsigned int __pgtable_l5_enabled;
-unsigned int pgdir_shift __ro_after_init = 39;
-unsigned int ptrs_per_p4d __ro_after_init = 1;
-#endif
+#define _SETUP
+#include <asm/setup.h> /* For COMMAND_LINE_SIZE */
+#undef _SETUP
extern unsigned long get_cmd_line_ptr(void);
-/* Used by PAGE_KERN* macros: */
-pteval_t __default_kernel_pte_mask __read_mostly = ~0;
-
/* Simplified build-specific string for starting entropy. */
static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
@@ -87,8 +82,11 @@ static unsigned long get_boot_seed(void)
static bool memmap_too_large;
-/* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */
-static unsigned long long mem_limit = ULLONG_MAX;
+/*
+ * Store memory limit: MAXMEM on 64-bit and KERNEL_IMAGE_SIZE on 32-bit.
+ * It may be reduced by "mem=nn[KMG]" or "memmap=nn[KMG]" command line options.
+ */
+static u64 mem_limit;
/* Number of immovable memory regions */
static int num_immovable_mem;
@@ -131,8 +129,7 @@ enum parse_mode {
};
static int
-parse_memmap(char *p, unsigned long long *start, unsigned long long *size,
- enum parse_mode mode)
+parse_memmap(char *p, u64 *start, u64 *size, enum parse_mode mode)
{
char *oldp;
@@ -162,7 +159,7 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size,
*/
*size = 0;
} else {
- unsigned long long flags;
+ u64 flags;
/*
* efi_fake_mem=nn@ss:attr the attr specifies
@@ -201,7 +198,7 @@ static void mem_avoid_memmap(enum parse_mode mode, char *str)
while (str && (i < MAX_MEMMAP_REGIONS)) {
int rc;
- unsigned long long start, size;
+ u64 start, size;
char *k = strchr(str, ',');
if (k)
@@ -214,7 +211,7 @@ static void mem_avoid_memmap(enum parse_mode mode, char *str)
if (start == 0) {
/* Store the specified memory limit if size > 0 */
- if (size > 0)
+ if (size > 0 && size < mem_limit)
mem_limit = size;
continue;
@@ -261,15 +258,15 @@ static void parse_gb_huge_pages(char *param, char *val)
static void handle_mem_options(void)
{
char *args = (char *)get_cmd_line_ptr();
- size_t len = strlen((char *)args);
+ size_t len;
char *tmp_cmdline;
char *param, *val;
u64 mem_size;
- if (!strstr(args, "memmap=") && !strstr(args, "mem=") &&
- !strstr(args, "hugepages"))
+ if (!args)
return;
+ len = strnlen(args, COMMAND_LINE_SIZE-1);
tmp_cmdline = malloc(len + 1);
if (!tmp_cmdline)
error("Failed to allocate space for tmp_cmdline");
@@ -284,14 +281,12 @@ static void handle_mem_options(void)
while (*args) {
args = next_arg(args, &param, &val);
/* Stop at -- */
- if (!val && strcmp(param, "--") == 0) {
- warn("Only '--' specified in cmdline");
- goto out;
- }
+ if (!val && strcmp(param, "--") == 0)
+ break;
if (!strcmp(param, "memmap")) {
mem_avoid_memmap(PARSE_MEMMAP, val);
- } else if (strstr(param, "hugepages")) {
+ } else if (IS_ENABLED(CONFIG_X86_64) && strstr(param, "hugepages")) {
parse_gb_huge_pages(param, val);
} else if (!strcmp(param, "mem")) {
char *p = val;
@@ -300,21 +295,23 @@ static void handle_mem_options(void)
continue;
mem_size = memparse(p, &p);
if (mem_size == 0)
- goto out;
+ break;
- mem_limit = mem_size;
+ if (mem_size < mem_limit)
+ mem_limit = mem_size;
} else if (!strcmp(param, "efi_fake_mem")) {
mem_avoid_memmap(PARSE_EFI, val);
}
}
-out:
free(tmp_cmdline);
return;
}
/*
- * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T).
+ * In theory, KASLR can put the kernel anywhere in the range of [16M, MAXMEM)
+ * on 64-bit, and [16M, KERNEL_IMAGE_SIZE) on 32-bit.
+ *
* The mem_avoid array is used to store the ranges that need to be avoided
* when KASLR searches for an appropriate random address. We must avoid any
* regions that are unsafe to overlap with during decompression, and other
@@ -392,8 +389,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
{
unsigned long init_size = boot_params->hdr.init_size;
u64 initrd_start, initrd_size;
- u64 cmd_line, cmd_line_size;
- char *ptr;
+ unsigned long cmd_line, cmd_line_size;
/*
* Avoid the region that is unsafe to overlap during
@@ -401,8 +397,6 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
*/
mem_avoid[MEM_AVOID_ZO_RANGE].start = input;
mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input;
- add_identity_map(mem_avoid[MEM_AVOID_ZO_RANGE].start,
- mem_avoid[MEM_AVOID_ZO_RANGE].size);
/* Avoid initrd. */
initrd_start = (u64)boot_params->ext_ramdisk_image << 32;
@@ -414,22 +408,17 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
/* No need to set mapping for initrd, it will be handled in VO. */
/* Avoid kernel command line. */
- cmd_line = (u64)boot_params->ext_cmd_line_ptr << 32;
- cmd_line |= boot_params->hdr.cmd_line_ptr;
+ cmd_line = get_cmd_line_ptr();
/* Calculate size of cmd_line. */
- ptr = (char *)(unsigned long)cmd_line;
- for (cmd_line_size = 0; ptr[cmd_line_size++];)
- ;
- mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line;
- mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size;
- add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start,
- mem_avoid[MEM_AVOID_CMDLINE].size);
+ if (cmd_line) {
+ cmd_line_size = strnlen((char *)cmd_line, COMMAND_LINE_SIZE-1) + 1;
+ mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line;
+ mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size;
+ }
/* Avoid boot parameters. */
mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params;
mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params);
- add_identity_map(mem_avoid[MEM_AVOID_BOOTPARAMS].start,
- mem_avoid[MEM_AVOID_BOOTPARAMS].size);
/* We don't need to set a mapping for setup_data. */
@@ -438,11 +427,6 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
/* Enumerate the immovable memory regions */
num_immovable_mem = count_immovable_mem_regions();
-
-#ifdef CONFIG_X86_VERBOSE_BOOTUP
- /* Make sure video RAM can be used. */
- add_identity_map(0, PMD_SIZE);
-#endif
}
/*
@@ -454,7 +438,7 @@ static bool mem_avoid_overlap(struct mem_vector *img,
{
int i;
struct setup_data *ptr;
- unsigned long earliest = img->start + img->size;
+ u64 earliest = img->start + img->size;
bool is_overlapping = false;
for (i = 0; i < MEM_AVOID_MAX; i++) {
@@ -499,18 +483,16 @@ static bool mem_avoid_overlap(struct mem_vector *img,
}
struct slot_area {
- unsigned long addr;
- int num;
+ u64 addr;
+ unsigned long num;
};
#define MAX_SLOT_AREA 100
static struct slot_area slot_areas[MAX_SLOT_AREA];
-
+static unsigned int slot_area_index;
static unsigned long slot_max;
-static unsigned long slot_area_index;
-
static void store_slot_info(struct mem_vector *region, unsigned long image_size)
{
struct slot_area slot_area;
@@ -519,13 +501,10 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size)
return;
slot_area.addr = region->start;
- slot_area.num = (region->size - image_size) /
- CONFIG_PHYSICAL_ALIGN + 1;
+ slot_area.num = 1 + (region->size - image_size) / CONFIG_PHYSICAL_ALIGN;
- if (slot_area.num > 0) {
- slot_areas[slot_area_index++] = slot_area;
- slot_max += slot_area.num;
- }
+ slot_areas[slot_area_index++] = slot_area;
+ slot_max += slot_area.num;
}
/*
@@ -535,57 +514,53 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size)
static void
process_gb_huge_pages(struct mem_vector *region, unsigned long image_size)
{
- unsigned long addr, size = 0;
+ u64 pud_start, pud_end;
+ unsigned long gb_huge_pages;
struct mem_vector tmp;
- int i = 0;
- if (!max_gb_huge_pages) {
+ if (!IS_ENABLED(CONFIG_X86_64) || !max_gb_huge_pages) {
store_slot_info(region, image_size);
return;
}
- addr = ALIGN(region->start, PUD_SIZE);
- /* Did we raise the address above the passed in memory entry? */
- if (addr < region->start + region->size)
- size = region->size - (addr - region->start);
-
- /* Check how many 1GB huge pages can be filtered out: */
- while (size > PUD_SIZE && max_gb_huge_pages) {
- size -= PUD_SIZE;
- max_gb_huge_pages--;
- i++;
- }
+ /* Are there any 1GB pages in the region? */
+ pud_start = ALIGN(region->start, PUD_SIZE);
+ pud_end = ALIGN_DOWN(region->start + region->size, PUD_SIZE);
/* No good 1GB huge pages found: */
- if (!i) {
+ if (pud_start >= pud_end) {
store_slot_info(region, image_size);
return;
}
- /*
- * Skip those 'i'*1GB good huge pages, and continue checking and
- * processing the remaining head or tail part of the passed region
- * if available.
- */
-
- if (addr >= region->start + image_size) {
+ /* Check if the head part of the region is usable. */
+ if (pud_start >= region->start + image_size) {
tmp.start = region->start;
- tmp.size = addr - region->start;
+ tmp.size = pud_start - region->start;
store_slot_info(&tmp, image_size);
}
- size = region->size - (addr - region->start) - i * PUD_SIZE;
- if (size >= image_size) {
- tmp.start = addr + i * PUD_SIZE;
- tmp.size = size;
+ /* Skip the good 1GB pages. */
+ gb_huge_pages = (pud_end - pud_start) >> PUD_SHIFT;
+ if (gb_huge_pages > max_gb_huge_pages) {
+ pud_end = pud_start + (max_gb_huge_pages << PUD_SHIFT);
+ max_gb_huge_pages = 0;
+ } else {
+ max_gb_huge_pages -= gb_huge_pages;
+ }
+
+ /* Check if the tail part of the region is usable. */
+ if (region->start + region->size >= pud_end + image_size) {
+ tmp.start = pud_end;
+ tmp.size = region->start + region->size - pud_end;
store_slot_info(&tmp, image_size);
}
}
-static unsigned long slots_fetch_random(void)
+static u64 slots_fetch_random(void)
{
unsigned long slot;
- int i;
+ unsigned int i;
/* Handle case of no slots stored. */
if (slot_max == 0)
@@ -598,7 +573,7 @@ static unsigned long slots_fetch_random(void)
slot -= slot_areas[i].num;
continue;
}
- return slot_areas[i].addr + slot * CONFIG_PHYSICAL_ALIGN;
+ return slot_areas[i].addr + ((u64)slot * CONFIG_PHYSICAL_ALIGN);
}
if (i == slot_area_index)
@@ -611,49 +586,23 @@ static void __process_mem_region(struct mem_vector *entry,
unsigned long image_size)
{
struct mem_vector region, overlap;
- unsigned long start_orig, end;
- struct mem_vector cur_entry;
+ u64 region_end;
- /* On 32-bit, ignore entries entirely above our maximum. */
- if (IS_ENABLED(CONFIG_X86_32) && entry->start >= KERNEL_IMAGE_SIZE)
- return;
-
- /* Ignore entries entirely below our minimum. */
- if (entry->start + entry->size < minimum)
- return;
-
- /* Ignore entries above memory limit */
- end = min(entry->size + entry->start, mem_limit);
- if (entry->start >= end)
- return;
- cur_entry.start = entry->start;
- cur_entry.size = end - entry->start;
-
- region.start = cur_entry.start;
- region.size = cur_entry.size;
+ /* Enforce minimum and memory limit. */
+ region.start = max_t(u64, entry->start, minimum);
+ region_end = min(entry->start + entry->size, mem_limit);
/* Give up if slot area array is full. */
while (slot_area_index < MAX_SLOT_AREA) {
- start_orig = region.start;
-
- /* Potentially raise address to minimum location. */
- if (region.start < minimum)
- region.start = minimum;
-
/* Potentially raise address to meet alignment needs. */
region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);
/* Did we raise the address above the passed in memory entry? */
- if (region.start > cur_entry.start + cur_entry.size)
+ if (region.start > region_end)
return;
/* Reduce size by any delta from the original address. */
- region.size -= region.start - start_orig;
-
- /* On 32-bit, reduce region size to fit within max size. */
- if (IS_ENABLED(CONFIG_X86_32) &&
- region.start + region.size > KERNEL_IMAGE_SIZE)
- region.size = KERNEL_IMAGE_SIZE - region.start;
+ region.size = region_end - region.start;
/* Return if region can't contain decompressed kernel */
if (region.size < image_size)
@@ -666,27 +615,19 @@ static void __process_mem_region(struct mem_vector *entry,
}
/* Store beginning of region if holds at least image_size. */
- if (overlap.start > region.start + image_size) {
- struct mem_vector beginning;
-
- beginning.start = region.start;
- beginning.size = overlap.start - region.start;
- process_gb_huge_pages(&beginning, image_size);
+ if (overlap.start >= region.start + image_size) {
+ region.size = overlap.start - region.start;
+ process_gb_huge_pages(&region, image_size);
}
- /* Return if overlap extends to or past end of region. */
- if (overlap.start + overlap.size >= region.start + region.size)
- return;
-
/* Clip off the overlapping region and start over. */
- region.size -= overlap.start - region.start + overlap.size;
region.start = overlap.start + overlap.size;
}
}
static bool process_mem_region(struct mem_vector *region,
- unsigned long long minimum,
- unsigned long long image_size)
+ unsigned long minimum,
+ unsigned long image_size)
{
int i;
/*
@@ -709,7 +650,7 @@ static bool process_mem_region(struct mem_vector *region,
* immovable memory and @region.
*/
for (i = 0; i < num_immovable_mem; i++) {
- unsigned long long start, end, entry_end, region_end;
+ u64 start, end, entry_end, region_end;
struct mem_vector entry;
if (!mem_overlaps(region, &immovable_mem[i]))
@@ -736,8 +677,8 @@ static bool process_mem_region(struct mem_vector *region,
#ifdef CONFIG_EFI
/*
- * Returns true if mirror region found (and must have been processed
- * for slots adding)
+ * Returns true if we processed the EFI memmap, which we prefer over the E820
+ * table if it is available.
*/
static bool
process_efi_entries(unsigned long minimum, unsigned long image_size)
@@ -839,20 +780,30 @@ static void process_e820_entries(unsigned long minimum,
static unsigned long find_random_phys_addr(unsigned long minimum,
unsigned long image_size)
{
+ u64 phys_addr;
+
+ /* Bail out early if it's impossible to succeed. */
+ if (minimum + image_size > mem_limit)
+ return 0;
+
/* Check if we had too many memmaps. */
if (memmap_too_large) {
debug_putstr("Aborted memory entries scan (more than 4 memmap= args)!\n");
return 0;
}
- /* Make sure minimum is aligned. */
- minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
+ if (!process_efi_entries(minimum, image_size))
+ process_e820_entries(minimum, image_size);
+
+ phys_addr = slots_fetch_random();
- if (process_efi_entries(minimum, image_size))
- return slots_fetch_random();
+ /* Perform a final check to make sure the address is in range. */
+ if (phys_addr < minimum || phys_addr + image_size > mem_limit) {
+ warn("Invalid physical address chosen!\n");
+ return 0;
+ }
- process_e820_entries(minimum, image_size);
- return slots_fetch_random();
+ return (unsigned long)phys_addr;
}
static unsigned long find_random_virt_addr(unsigned long minimum,
@@ -860,18 +811,12 @@ static unsigned long find_random_virt_addr(unsigned long minimum,
{
unsigned long slots, random_addr;
- /* Make sure minimum is aligned. */
- minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
- /* Align image_size for easy slot calculations. */
- image_size = ALIGN(image_size, CONFIG_PHYSICAL_ALIGN);
-
/*
* There are how many CONFIG_PHYSICAL_ALIGN-sized slots
* that can hold image_size within the range of minimum to
* KERNEL_IMAGE_SIZE?
*/
- slots = (KERNEL_IMAGE_SIZE - minimum - image_size) /
- CONFIG_PHYSICAL_ALIGN + 1;
+ slots = 1 + (KERNEL_IMAGE_SIZE - minimum - image_size) / CONFIG_PHYSICAL_ALIGN;
random_addr = kaslr_get_random_long("Virtual") % slots;
@@ -905,8 +850,10 @@ void choose_random_location(unsigned long input,
boot_params->hdr.loadflags |= KASLR_FLAG;
- /* Prepare to add new identity pagetables on demand. */
- initialize_identity_maps();
+ if (IS_ENABLED(CONFIG_X86_32))
+ mem_limit = KERNEL_IMAGE_SIZE;
+ else
+ mem_limit = MAXMEM;
/* Record the various known unsafe memory ranges. */
mem_avoid_init(input, input_size, *output);
@@ -917,6 +864,8 @@ void choose_random_location(unsigned long input,
* location:
*/
min_addr = min(*output, 512UL << 20);
+ /* Make sure minimum is aligned. */
+ min_addr = ALIGN(min_addr, CONFIG_PHYSICAL_ALIGN);
/* Walk available memory entries to find a random address. */
random_addr = find_random_phys_addr(min_addr, output_size);
@@ -924,19 +873,8 @@ void choose_random_location(unsigned long input,
warn("Physical KASLR disabled: no suitable memory region!");
} else {
/* Update the new physical address location. */
- if (*output != random_addr) {
- add_identity_map(random_addr, output_size);
+ if (*output != random_addr)
*output = random_addr;
- }
-
- /*
- * This loads the identity mapping page table.
- * This should only be done if a new physical address
- * is found for the kernel, otherwise we should keep
- * the old page table to make it be like the "nokaslr"
- * case.
- */
- finalize_identity_maps();
}
diff --git a/arch/x86/boot/compressed/kaslr_64.c b/arch/x86/boot/compressed/kaslr_64.c
deleted file mode 100644
index f9c5c13d979b..000000000000
--- a/arch/x86/boot/compressed/kaslr_64.c
+++ /dev/null
@@ -1,153 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * This code is used on x86_64 to create page table identity mappings on
- * demand by building up a new set of page tables (or appending to the
- * existing ones), and then switching over to them when ready.
- *
- * Copyright (C) 2015-2016 Yinghai Lu
- * Copyright (C) 2016 Kees Cook
- */
-
-/*
- * Since we're dealing with identity mappings, physical and virtual
- * addresses are the same, so override these defines which are ultimately
- * used by the headers in misc.h.
- */
-#define __pa(x) ((unsigned long)(x))
-#define __va(x) ((void *)((unsigned long)(x)))
-
-/* No PAGE_TABLE_ISOLATION support needed either: */
-#undef CONFIG_PAGE_TABLE_ISOLATION
-
-#include "misc.h"
-
-/* These actually do the work of building the kernel identity maps. */
-#include <linux/pgtable.h>
-#include <asm/init.h>
-/* Use the static base for this part of the boot process */
-#undef __PAGE_OFFSET
-#define __PAGE_OFFSET __PAGE_OFFSET_BASE
-#include "../../mm/ident_map.c"
-
-/* Used to track our page table allocation area. */
-struct alloc_pgt_data {
- unsigned char *pgt_buf;
- unsigned long pgt_buf_size;
- unsigned long pgt_buf_offset;
-};
-
-/*
- * Allocates space for a page table entry, using struct alloc_pgt_data
- * above. Besides the local callers, this is used as the allocation
- * callback in mapping_info below.
- */
-static void *alloc_pgt_page(void *context)
-{
- struct alloc_pgt_data *pages = (struct alloc_pgt_data *)context;
- unsigned char *entry;
-
- /* Validate there is space available for a new page. */
- if (pages->pgt_buf_offset >= pages->pgt_buf_size) {
- debug_putstr("out of pgt_buf in " __FILE__ "!?\n");
- debug_putaddr(pages->pgt_buf_offset);
- debug_putaddr(pages->pgt_buf_size);
- return NULL;
- }
-
- entry = pages->pgt_buf + pages->pgt_buf_offset;
- pages->pgt_buf_offset += PAGE_SIZE;
-
- return entry;
-}
-
-/* Used to track our allocated page tables. */
-static struct alloc_pgt_data pgt_data;
-
-/* The top level page table entry pointer. */
-static unsigned long top_level_pgt;
-
-phys_addr_t physical_mask = (1ULL << __PHYSICAL_MASK_SHIFT) - 1;
-
-/*
- * Mapping information structure passed to kernel_ident_mapping_init().
- * Due to relocation, pointers must be assigned at run time not build time.
- */
-static struct x86_mapping_info mapping_info;
-
-/* Locates and clears a region for a new top level page table. */
-void initialize_identity_maps(void)
-{
- /* If running as an SEV guest, the encryption mask is required. */
- set_sev_encryption_mask();
-
- /* Exclude the encryption mask from __PHYSICAL_MASK */
- physical_mask &= ~sme_me_mask;
-
- /* Init mapping_info with run-time function/buffer pointers. */
- mapping_info.alloc_pgt_page = alloc_pgt_page;
- mapping_info.context = &pgt_data;
- mapping_info.page_flag = __PAGE_KERNEL_LARGE_EXEC | sme_me_mask;
- mapping_info.kernpg_flag = _KERNPG_TABLE;
-
- /*
- * It should be impossible for this not to already be true,
- * but since calling this a second time would rewind the other
- * counters, let's just make sure this is reset too.
- */
- pgt_data.pgt_buf_offset = 0;
-
- /*
- * If we came here via startup_32(), cr3 will be _pgtable already
- * and we must append to the existing area instead of entirely
- * overwriting it.
- *
- * With 5-level paging, we use '_pgtable' to allocate the p4d page table,
- * the top-level page table is allocated separately.
- *
- * p4d_offset(top_level_pgt, 0) would cover both the 4- and 5-level
- * cases. On 4-level paging it's equal to 'top_level_pgt'.
- */
- top_level_pgt = read_cr3_pa();
- if (p4d_offset((pgd_t *)top_level_pgt, 0) == (p4d_t *)_pgtable) {
- debug_putstr("booted via startup_32()\n");
- pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE;
- pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE;
- memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
- } else {
- debug_putstr("booted via startup_64()\n");
- pgt_data.pgt_buf = _pgtable;
- pgt_data.pgt_buf_size = BOOT_PGT_SIZE;
- memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size);
- top_level_pgt = (unsigned long)alloc_pgt_page(&pgt_data);
- }
-}
-
-/*
- * Adds the specified range to what will become the new identity mappings.
- * Once all ranges have been added, the new mapping is activated by calling
- * finalize_identity_maps() below.
- */
-void add_identity_map(unsigned long start, unsigned long size)
-{
- unsigned long end = start + size;
-
- /* Align boundary to 2M. */
- start = round_down(start, PMD_SIZE);
- end = round_up(end, PMD_SIZE);
- if (start >= end)
- return;
-
- /* Build the mapping. */
- kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt,
- start, end);
-}
-
-/*
- * This switches the page tables to the new level4 that has been built
- * via calls to add_identity_map() above. If booted via startup_32(),
- * this is effectively a no-op.
- */
-void finalize_identity_maps(void)
-{
- write_cr3(top_level_pgt);
-}
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index e478e40fbe5a..267e7f93050e 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -442,6 +442,13 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
parse_elf(output);
handle_relocations(output, output_len, virt_addr);
debug_putstr("done.\nBooting the kernel.\n");
+
+ /*
+ * Flush GHCB from cache and map it encrypted again when running as
+ * SEV-ES guest.
+ */
+ sev_es_shutdown_ghcb();
+
return output;
}
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 726e264410ff..6d31f1b4c4d1 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -23,6 +23,7 @@
#include <asm/page.h>
#include <asm/boot.h>
#include <asm/bootparam.h>
+#include <asm/desc_defs.h>
#define BOOT_CTYPE_H
#include <linux/acpi.h>
@@ -36,6 +37,9 @@
#define memptr unsigned
#endif
+/* boot/compressed/vmlinux start and end markers */
+extern char _head[], _end[];
+
/* misc.c */
extern memptr free_mem_ptr;
extern memptr free_mem_end_ptr;
@@ -70,8 +74,8 @@ int cmdline_find_option(const char *option, char *buffer, int bufsize);
int cmdline_find_option_bool(const char *option);
struct mem_vector {
- unsigned long long start;
- unsigned long long size;
+ u64 start;
+ u64 size;
};
#if CONFIG_RANDOMIZE_BASE
@@ -81,8 +85,6 @@ void choose_random_location(unsigned long input,
unsigned long *output,
unsigned long output_size,
unsigned long *virt_addr);
-/* cpuflags.c */
-bool has_cpuflag(int flag);
#else
static inline void choose_random_location(unsigned long input,
unsigned long input_size,
@@ -93,18 +95,14 @@ static inline void choose_random_location(unsigned long input,
}
#endif
+/* cpuflags.c */
+bool has_cpuflag(int flag);
+
#ifdef CONFIG_X86_64
-void initialize_identity_maps(void);
-void add_identity_map(unsigned long start, unsigned long size);
-void finalize_identity_maps(void);
+extern int set_page_decrypted(unsigned long address);
+extern int set_page_encrypted(unsigned long address);
+extern int set_page_non_present(unsigned long address);
extern unsigned char _pgtable[];
-#else
-static inline void initialize_identity_maps(void)
-{ }
-static inline void add_identity_map(unsigned long start, unsigned long size)
-{ }
-static inline void finalize_identity_maps(void)
-{ }
#endif
#ifdef CONFIG_EARLY_PRINTK
@@ -119,6 +117,17 @@ static inline void console_init(void)
void set_sev_encryption_mask(void);
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+void sev_es_shutdown_ghcb(void);
+extern bool sev_es_check_ghcb_fault(unsigned long address);
+#else
+static inline void sev_es_shutdown_ghcb(void) { }
+static inline bool sev_es_check_ghcb_fault(unsigned long address)
+{
+ return false;
+}
+#endif
+
/* acpi.c */
#ifdef CONFIG_ACPI
acpi_physical_address get_rsdp_addr(void);
@@ -133,4 +142,21 @@ int count_immovable_mem_regions(void);
static inline int count_immovable_mem_regions(void) { return 0; }
#endif
+/* ident_map_64.c */
+#ifdef CONFIG_X86_5LEVEL
+extern unsigned int __pgtable_l5_enabled, pgdir_shift, ptrs_per_p4d;
+#endif
+
+/* Used by PAGE_KERN* macros: */
+extern pteval_t __default_kernel_pte_mask;
+
+/* idt_64.c */
+extern gate_desc boot_idt[BOOT_IDT_ENTRIES];
+extern struct desc_ptr boot_idt_desc;
+
+/* IDT Entry Points */
+void boot_page_fault(void);
+void boot_stage1_vc(void);
+void boot_stage2_vc(void);
+
#endif /* BOOT_COMPRESSED_MISC_H */
diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c
index 7e01248765b2..52aa56cdbacc 100644
--- a/arch/x86/boot/compressed/mkpiggy.c
+++ b/arch/x86/boot/compressed/mkpiggy.c
@@ -60,6 +60,12 @@ int main(int argc, char *argv[])
printf(".incbin \"%s\"\n", argv[1]);
printf("input_data_end:\n");
+ printf(".section \".rodata\",\"a\",@progbits\n");
+ printf(".globl input_len\n");
+ printf("input_len:\n\t.long %lu\n", ilen);
+ printf(".globl output_len\n");
+ printf("output_len:\n\t.long %lu\n", (unsigned long)olen);
+
retval = 0;
bail:
if (f)
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index c8862696a47b..7d0394f4ebf9 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -5,15 +5,6 @@
#include "pgtable.h"
#include "../string.h"
-/*
- * __force_order is used by special_insns.h asm code to force instruction
- * serialization.
- *
- * It is not referenced from the code, but GCC < 5 with -fPIE would fail
- * due to an undefined symbol. Define it to make these ancient GCCs work.
- */
-unsigned long __force_order;
-
#define BIOS_START_MIN 0x20000U /* 128K, less than this is insane */
#define BIOS_START_MAX 0x9f000U /* 640K, absolute maximum */
diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c
new file mode 100644
index 000000000000..954cb2702e23
--- /dev/null
+++ b/arch/x86/boot/compressed/sev-es.c
@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AMD Encrypted Register State Support
+ *
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+/*
+ * misc.h needs to be first because it knows how to include the other kernel
+ * headers in the pre-decompression code in a way that does not break
+ * compilation.
+ */
+#include "misc.h"
+
+#include <asm/pgtable_types.h>
+#include <asm/sev-es.h>
+#include <asm/trapnr.h>
+#include <asm/trap_pf.h>
+#include <asm/msr-index.h>
+#include <asm/fpu/xcr.h>
+#include <asm/ptrace.h>
+#include <asm/svm.h>
+
+#include "error.h"
+
+struct ghcb boot_ghcb_page __aligned(PAGE_SIZE);
+struct ghcb *boot_ghcb;
+
+/*
+ * Copy a version of this function here - insn-eval.c can't be used in
+ * pre-decompression code.
+ */
+static bool insn_has_rep_prefix(struct insn *insn)
+{
+ int i;
+
+ insn_get_prefixes(insn);
+
+ for (i = 0; i < insn->prefixes.nbytes; i++) {
+ insn_byte_t p = insn->prefixes.bytes[i];
+
+ if (p == 0xf2 || p == 0xf3)
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Only a dummy for insn_get_seg_base() - Early boot-code is 64bit only and
+ * doesn't use segments.
+ */
+static unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx)
+{
+ return 0UL;
+}
+
+static inline u64 sev_es_rd_ghcb_msr(void)
+{
+ unsigned long low, high;
+
+ asm volatile("rdmsr" : "=a" (low), "=d" (high) :
+ "c" (MSR_AMD64_SEV_ES_GHCB));
+
+ return ((high << 32) | low);
+}
+
+static inline void sev_es_wr_ghcb_msr(u64 val)
+{
+ u32 low, high;
+
+ low = val & 0xffffffffUL;
+ high = val >> 32;
+
+ asm volatile("wrmsr" : : "c" (MSR_AMD64_SEV_ES_GHCB),
+ "a"(low), "d" (high) : "memory");
+}
+
+static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+{
+ char buffer[MAX_INSN_SIZE];
+ enum es_result ret;
+
+ memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
+
+ insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE, 1);
+ insn_get_length(&ctxt->insn);
+
+ ret = ctxt->insn.immediate.got ? ES_OK : ES_DECODE_FAILED;
+
+ return ret;
+}
+
+static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
+ void *dst, char *buf, size_t size)
+{
+ memcpy(dst, buf, size);
+
+ return ES_OK;
+}
+
+static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
+ void *src, char *buf, size_t size)
+{
+ memcpy(buf, src, size);
+
+ return ES_OK;
+}
+
+#undef __init
+#undef __pa
+#define __init
+#define __pa(x) ((unsigned long)(x))
+
+#define __BOOT_COMPRESSED
+
+/* Basic instruction decoding support needed */
+#include "../../lib/inat.c"
+#include "../../lib/insn.c"
+
+/* Include code for early handlers */
+#include "../../kernel/sev-es-shared.c"
+
+static bool early_setup_sev_es(void)
+{
+ if (!sev_es_negotiate_protocol())
+ sev_es_terminate(GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED);
+
+ if (set_page_decrypted((unsigned long)&boot_ghcb_page))
+ return false;
+
+ /* Page is now mapped decrypted, clear it */
+ memset(&boot_ghcb_page, 0, sizeof(boot_ghcb_page));
+
+ boot_ghcb = &boot_ghcb_page;
+
+ /* Initialize lookup tables for the instruction decoder */
+ inat_init_tables();
+
+ return true;
+}
+
+void sev_es_shutdown_ghcb(void)
+{
+ if (!boot_ghcb)
+ return;
+
+ if (!sev_es_check_cpu_features())
+ error("SEV-ES CPU Features missing.");
+
+ /*
+ * GHCB Page must be flushed from the cache and mapped encrypted again.
+ * Otherwise the running kernel will see strange cache effects when
+ * trying to use that page.
+ */
+ if (set_page_encrypted((unsigned long)&boot_ghcb_page))
+ error("Can't map GHCB page encrypted");
+
+ /*
+ * GHCB page is mapped encrypted again and flushed from the cache.
+ * Mark it non-present now to catch bugs when #VC exceptions trigger
+ * after this point.
+ */
+ if (set_page_non_present((unsigned long)&boot_ghcb_page))
+ error("Can't unmap GHCB page");
+}
+
+bool sev_es_check_ghcb_fault(unsigned long address)
+{
+ /* Check whether the fault was on the GHCB page */
+ return ((address & PAGE_MASK) == (unsigned long)&boot_ghcb_page);
+}
+
+void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
+{
+ struct es_em_ctxt ctxt;
+ enum es_result result;
+
+ if (!boot_ghcb && !early_setup_sev_es())
+ sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
+
+ vc_ghcb_invalidate(boot_ghcb);
+ result = vc_init_em_ctxt(&ctxt, regs, exit_code);
+ if (result != ES_OK)
+ goto finish;
+
+ switch (exit_code) {
+ case SVM_EXIT_RDTSC:
+ case SVM_EXIT_RDTSCP:
+ result = vc_handle_rdtsc(boot_ghcb, &ctxt, exit_code);
+ break;
+ case SVM_EXIT_IOIO:
+ result = vc_handle_ioio(boot_ghcb, &ctxt);
+ break;
+ case SVM_EXIT_CPUID:
+ result = vc_handle_cpuid(boot_ghcb, &ctxt);
+ break;
+ default:
+ result = ES_UNSUPPORTED;
+ break;
+ }
+
+finish:
+ if (result == ES_OK) {
+ vc_finish_insn(&ctxt);
+ } else if (result != ES_RETRY) {
+ /*
+ * For now, just halt the machine. That makes debugging easier,
+ * later we just call sev_es_terminate() here.
+ */
+ while (true)
+ asm volatile("hlt\n");
+ }
+}
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index 8f1025d1f681..112b2375d021 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -42,12 +42,6 @@ SECTIONS
*(.rodata.*)
_erodata = . ;
}
- .got : {
- _got = .;
- KEEP(*(.got.plt))
- KEEP(*(.got))
- _egot = .;
- }
.data : {
_data = . ;
*(.data)
@@ -75,5 +69,49 @@ SECTIONS
. = ALIGN(PAGE_SIZE); /* keep ZO size page aligned */
_end = .;
+ STABS_DEBUG
+ DWARF_DEBUG
+ ELF_DETAILS
+
DISCARDS
+ /DISCARD/ : {
+ *(.dynamic) *(.dynsym) *(.dynstr) *(.dynbss)
+ *(.hash) *(.gnu.hash)
+ *(.note.*)
+ }
+
+ .got.plt (INFO) : {
+ *(.got.plt)
+ }
+ ASSERT(SIZEOF(.got.plt) == 0 ||
+#ifdef CONFIG_X86_64
+ SIZEOF(.got.plt) == 0x18,
+#else
+ SIZEOF(.got.plt) == 0xc,
+#endif
+ "Unexpected GOT/PLT entries detected!")
+
+ /*
+ * Sections that should stay zero sized, which is safer to
+ * explicitly check instead of blindly discarding.
+ */
+ .got : {
+ *(.got)
+ }
+ ASSERT(SIZEOF(.got) == 0, "Unexpected GOT entries detected!")
+
+ .plt : {
+ *(.plt) *(.plt.*)
+ }
+ ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!")
+
+ .rel.dyn : {
+ *(.rel.*) *(.rel_*)
+ }
+ ASSERT(SIZEOF(.rel.dyn) == 0, "Unexpected run-time relocations (.rel) detected!")
+
+ .rela.dyn : {
+ *(.rela.*) *(.rela_*)
+ }
+ ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!")
}
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-13 02:16:39 +0300