aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/vmlinux.lds.S
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/vmlinux.lds.S')
-rw-r--r--arch/x86/kernel/vmlinux.lds.S402
1 files changed, 171 insertions, 231 deletions
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 4c85b2e2bb6..49edf2dd361 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -41,16 +41,40 @@ ENTRY(phys_startup_64)
jiffies_64 = jiffies;
#endif
+#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+/*
+ * On 64-bit, align RODATA to 2MB so that even with CONFIG_DEBUG_RODATA
+ * we retain large page mappings for boundaries spanning kernel text, rodata
+ * and data sections.
+ *
+ * However, kernel identity mappings will have different RWX permissions
+ * to the pages mapping to text and to the pages padding (which are freed) the
+ * text section. Hence kernel identity mappings will be broken to smaller
+ * pages. For 64-bit, kernel text and kernel identity mappings are different,
+ * so we can enable protection checks that come with CONFIG_DEBUG_RODATA,
+ * as well as retain 2MB large page mappings for kernel text.
+ */
+#define X64_ALIGN_DEBUG_RODATA_BEGIN . = ALIGN(HPAGE_SIZE);
+
+#define X64_ALIGN_DEBUG_RODATA_END \
+ . = ALIGN(HPAGE_SIZE); \
+ __end_rodata_hpage_align = .;
+
+#else
+
+#define X64_ALIGN_DEBUG_RODATA_BEGIN
+#define X64_ALIGN_DEBUG_RODATA_END
+
+#endif
+
PHDRS {
text PT_LOAD FLAGS(5); /* R_E */
- data PT_LOAD FLAGS(7); /* RWE */
+ data PT_LOAD FLAGS(6); /* RW_ */
#ifdef CONFIG_X86_64
- user PT_LOAD FLAGS(7); /* RWE */
- data.init PT_LOAD FLAGS(7); /* RWE */
#ifdef CONFIG_SMP
- percpu PT_LOAD FLAGS(7); /* RWE */
+ percpu PT_LOAD FLAGS(6); /* RW_ */
#endif
- data.init2 PT_LOAD FLAGS(7); /* RWE */
+ init PT_LOAD FLAGS(7); /* RWE */
#endif
note PT_NOTE FLAGS(0); /* ___ */
}
@@ -66,26 +90,17 @@ SECTIONS
#endif
/* Text and read-only data */
-
- /* bootstrapping code */
- .text.head : AT(ADDR(.text.head) - LOAD_OFFSET) {
- _text = .;
- *(.text.head)
- } :text = 0x9090
-
- /* The rest of the text */
.text : AT(ADDR(.text) - LOAD_OFFSET) {
-#ifdef CONFIG_X86_32
- /* not really needed, already page aligned */
- . = ALIGN(PAGE_SIZE);
- *(.text.page_aligned)
-#endif
+ _text = .;
+ /* bootstrapping code */
+ HEAD_TEXT
. = ALIGN(8);
_stext = .;
TEXT_TEXT
SCHED_TEXT
LOCK_TEXT
KPROBES_TEXT
+ ENTRY_TEXT
IRQENTRY_TEXT
*(.fixup)
*(.gnu.warning)
@@ -95,194 +110,90 @@ SECTIONS
NOTES :text :note
- /* Exception table */
- . = ALIGN(16);
- __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
- __start___ex_table = .;
- *(__ex_table)
- __stop___ex_table = .;
- } :text = 0x9090
+ EXCEPTION_TABLE(16) :text = 0x9090
- RODATA
+#if defined(CONFIG_DEBUG_RODATA)
+ /* .text should occupy whole number of pages */
+ . = ALIGN(PAGE_SIZE);
+#endif
+ X64_ALIGN_DEBUG_RODATA_BEGIN
+ RO_DATA(PAGE_SIZE)
+ X64_ALIGN_DEBUG_RODATA_END
/* Data */
- . = ALIGN(PAGE_SIZE);
.data : AT(ADDR(.data) - LOAD_OFFSET) {
- DATA_DATA
- CONSTRUCTORS
+ /* Start of data section */
+ _sdata = .;
-#ifdef CONFIG_X86_64
- /* End of data section */
- _edata = .;
-#endif
- } :data
+ /* init_task */
+ INIT_TASK_DATA(THREAD_SIZE)
#ifdef CONFIG_X86_32
- /* 32 bit has nosave before _edata */
- . = ALIGN(PAGE_SIZE);
- .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
- __nosave_begin = .;
- *(.data.nosave)
- . = ALIGN(PAGE_SIZE);
- __nosave_end = .;
- }
+ /* 32 bit has nosave before _edata */
+ NOSAVE_DATA
#endif
- . = ALIGN(PAGE_SIZE);
- .data.page_aligned : AT(ADDR(.data.page_aligned) - LOAD_OFFSET) {
- *(.data.page_aligned)
- *(.data.idt)
- }
+ PAGE_ALIGNED_DATA(PAGE_SIZE)
-#ifdef CONFIG_X86_32
- . = ALIGN(32);
-#else
- . = ALIGN(PAGE_SIZE);
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
-#endif
- .data.cacheline_aligned :
- AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) {
- *(.data.cacheline_aligned)
- }
+ CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
- /* rarely changed data like cpu maps */
-#ifdef CONFIG_X86_32
- . = ALIGN(32);
-#else
- . = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES);
-#endif
- .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) {
- *(.data.read_mostly)
+ DATA_DATA
+ CONSTRUCTORS
+
+ /* rarely changed data like cpu maps */
+ READ_MOSTLY_DATA(INTERNODE_CACHE_BYTES)
-#ifdef CONFIG_X86_32
/* End of data section */
_edata = .;
-#endif
- }
-
-#ifdef CONFIG_X86_64
-
-#define VSYSCALL_ADDR (-10*1024*1024)
-#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data.read_mostly) + \
- SIZEOF(.data.read_mostly) + 4095) & ~(4095))
-#define VSYSCALL_VIRT_ADDR ((ADDR(.data.read_mostly) + \
- SIZEOF(.data.read_mostly) + 4095) & ~(4095))
-
-#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR)
-#define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
-
-#define VVIRT_OFFSET (VSYSCALL_ADDR - VSYSCALL_VIRT_ADDR)
-#define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
-
- . = VSYSCALL_ADDR;
- .vsyscall_0 : AT(VSYSCALL_PHYS_ADDR) {
- *(.vsyscall_0)
- } :user
-
- __vsyscall_0 = VSYSCALL_VIRT_ADDR;
-
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
- .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) {
- *(.vsyscall_fn)
- }
-
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
- .vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data)) {
- *(.vsyscall_gtod_data)
- }
-
- vsyscall_gtod_data = VVIRT(.vsyscall_gtod_data);
- .vsyscall_clock : AT(VLOAD(.vsyscall_clock)) {
- *(.vsyscall_clock)
- }
- vsyscall_clock = VVIRT(.vsyscall_clock);
-
-
- .vsyscall_1 ADDR(.vsyscall_0) + 1024: AT(VLOAD(.vsyscall_1)) {
- *(.vsyscall_1)
- }
- .vsyscall_2 ADDR(.vsyscall_0) + 2048: AT(VLOAD(.vsyscall_2)) {
- *(.vsyscall_2)
- }
-
- .vgetcpu_mode : AT(VLOAD(.vgetcpu_mode)) {
- *(.vgetcpu_mode)
- }
- vgetcpu_mode = VVIRT(.vgetcpu_mode);
-
- . = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
- .jiffies : AT(VLOAD(.jiffies)) {
- *(.jiffies)
- }
- jiffies = VVIRT(.jiffies);
-
- .vsyscall_3 ADDR(.vsyscall_0) + 3072: AT(VLOAD(.vsyscall_3)) {
- *(.vsyscall_3)
- }
-
- . = VSYSCALL_VIRT_ADDR + PAGE_SIZE;
-
-#undef VSYSCALL_ADDR
-#undef VSYSCALL_PHYS_ADDR
-#undef VSYSCALL_VIRT_ADDR
-#undef VLOAD_OFFSET
-#undef VLOAD
-#undef VVIRT_OFFSET
-#undef VVIRT
-
-#endif /* CONFIG_X86_64 */
+ } :data
- /* init_task */
- . = ALIGN(THREAD_SIZE);
- .data.init_task : AT(ADDR(.data.init_task) - LOAD_OFFSET) {
- *(.data.init_task)
- }
-#ifdef CONFIG_X86_64
- :data.init
-#endif
- /*
- * smp_locks might be freed after init
- * start/end must be page aligned
- */
. = ALIGN(PAGE_SIZE);
- .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
- __smp_locks = .;
- *(.smp_locks)
- __smp_locks_end = .;
- . = ALIGN(PAGE_SIZE);
- }
+ __vvar_page = .;
+
+ .vvar : AT(ADDR(.vvar) - LOAD_OFFSET) {
+ /* work around gold bug 13023 */
+ __vvar_beginning_hack = .;
+
+ /* Place all vvars at the offsets in asm/vvar.h. */
+#define EMIT_VVAR(name, offset) \
+ . = __vvar_beginning_hack + offset; \
+ *(.vvar_ ## name)
+#define __VVAR_KERNEL_LDS
+#include <asm/vvar.h>
+#undef __VVAR_KERNEL_LDS
+#undef EMIT_VVAR
+
+ /*
+ * Pad the rest of the page with zeros. Otherwise the loader
+ * can leave garbage here.
+ */
+ . = __vvar_beginning_hack + PAGE_SIZE;
+ } :data
+
+ . = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE);
/* Init code and data - will be freed after init */
. = ALIGN(PAGE_SIZE);
- .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
+ .init.begin : AT(ADDR(.init.begin) - LOAD_OFFSET) {
__init_begin = .; /* paired with __init_end */
- _sinittext = .;
- INIT_TEXT
- _einittext = .;
}
- .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
- INIT_DATA
- }
+#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
+ /*
+ * percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the
+ * output PHDR, so the next output section - .init.text - should
+ * start another segment - init.
+ */
+ PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu)
+#endif
- . = ALIGN(16);
- .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
- __setup_start = .;
- *(.init.setup)
- __setup_end = .;
- }
- .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
- __initcall_start = .;
- INITCALLS
- __initcall_end = .;
- }
+ INIT_TEXT_SECTION(PAGE_SIZE)
+#ifdef CONFIG_X86_64
+ :init
+#endif
- .con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
- __con_initcall_start = .;
- *(.con_initcall.init)
- __con_initcall_end = .;
- }
+ INIT_DATA_SECTION(16)
.x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
__x86_cpu_dev_start = .;
@@ -290,8 +201,21 @@ SECTIONS
__x86_cpu_dev_end = .;
}
- SECURITY_INIT
+#ifdef CONFIG_X86_INTEL_MID
+ .x86_intel_mid_dev.init : AT(ADDR(.x86_intel_mid_dev.init) - \
+ LOAD_OFFSET) {
+ __x86_intel_mid_dev_start = .;
+ *(.x86_intel_mid_dev.init)
+ __x86_intel_mid_dev_end = .;
+ }
+#endif
+ /*
+ * start address and size of operations which during runtime
+ * can be patched with virtualization friendly instructions or
+ * baremetal native ones. Think page table operations.
+ * Details in paravirt_types.h
+ */
. = ALIGN(8);
.parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
__parainstructions = .;
@@ -299,6 +223,11 @@ SECTIONS
__parainstructions_end = .;
}
+ /*
+ * struct alt_inst entries. From the header (alternative.h):
+ * "Alternative instructions for different CPU types or capabilities"
+ * Think locking instructions on spinlocks.
+ */
. = ALIGN(8);
.altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
__alt_instructions = .;
@@ -306,11 +235,36 @@ SECTIONS
__alt_instructions_end = .;
}
+ /*
+ * And here are the replacement instructions. The linker sticks
+ * them as binary blobs. The .altinstructions has enough data to
+ * get the address and the length of them to patch the kernel safely.
+ */
.altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
*(.altinstr_replacement)
}
/*
+ * struct iommu_table_entry entries are injected in this section.
+ * It is an array of IOMMUs which during run time gets sorted depending
+ * on its dependency order. After rootfs_initcall is complete
+ * this section can be safely removed.
+ */
+ .iommu_table : AT(ADDR(.iommu_table) - LOAD_OFFSET) {
+ __iommu_table = .;
+ *(.iommu_table)
+ __iommu_table_end = .;
+ }
+
+ . = ALIGN(8);
+ .apicdrivers : AT(ADDR(.apicdrivers) - LOAD_OFFSET) {
+ __apicdrivers = .;
+ *(.apicdrivers);
+ __apicdrivers_end = .;
+ }
+
+ . = ALIGN(8);
+ /*
* .exit.text is discard at runtime, not link time, to deal with
* references from .altinstructions and .eh_frame
*/
@@ -322,27 +276,8 @@ SECTIONS
EXIT_DATA
}
-#ifdef CONFIG_BLK_DEV_INITRD
- . = ALIGN(PAGE_SIZE);
- .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
- __initramfs_start = .;
- *(.init.ramfs)
- __initramfs_end = .;
- }
-#endif
-
-#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
- /*
- * percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the
- * output PHDR, so the next output section - __data_nosave - should
- * start another section data.init2. Also, pda should be at the head of
- * percpu area. Preallocate it and define the percpu offset symbol
- * so that it can be accessed as a percpu variable.
- */
- . = ALIGN(PAGE_SIZE);
- PERCPU_VADDR(0, :percpu)
-#else
- PERCPU(PAGE_SIZE)
+#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
+ PERCPU_SECTION(INTERNODE_CACHE_BYTES)
#endif
. = ALIGN(PAGE_SIZE);
@@ -352,24 +287,31 @@ SECTIONS
__init_end = .;
}
+ /*
+ * smp_locks might be freed after init
+ * start/end must be page aligned
+ */
+ . = ALIGN(PAGE_SIZE);
+ .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
+ __smp_locks = .;
+ *(.smp_locks)
+ . = ALIGN(PAGE_SIZE);
+ __smp_locks_end = .;
+ }
+
#ifdef CONFIG_X86_64
.data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
- . = ALIGN(PAGE_SIZE);
- __nosave_begin = .;
- *(.data.nosave)
- . = ALIGN(PAGE_SIZE);
- __nosave_end = .;
- } :data.init2
- /* use another section data.init2, see PERCPU_VADDR() above */
+ NOSAVE_DATA
+ }
#endif
/* BSS */
. = ALIGN(PAGE_SIZE);
.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
__bss_start = .;
- *(.bss.page_aligned)
+ *(.bss..page_aligned)
*(.bss)
- . = ALIGN(4);
+ . = ALIGN(PAGE_SIZE);
__bss_stop = .;
}
@@ -381,43 +323,41 @@ SECTIONS
__brk_limit = .;
}
- .end : AT(ADDR(.end) - LOAD_OFFSET) {
- _end = .;
- }
-
- /* Sections to be discarded */
- /DISCARD/ : {
- *(.exitcall.exit)
- *(.eh_frame)
- *(.discard)
- }
+ _end = .;
STABS_DEBUG
DWARF_DEBUG
+
+ /* Sections to be discarded */
+ DISCARDS
+ /DISCARD/ : { *(.eh_frame) }
}
#ifdef CONFIG_X86_32
-ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
- "kernel image bigger than KERNEL_IMAGE_SIZE")
+/*
+ * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+ */
+. = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
+ "kernel image bigger than KERNEL_IMAGE_SIZE");
#else
/*
* Per-cpu symbols which need to be offset from __per_cpu_load
* for the boot processor.
*/
-#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load
+#define INIT_PER_CPU(x) init_per_cpu__##x = x + __per_cpu_load
INIT_PER_CPU(gdt_page);
INIT_PER_CPU(irq_stack_union);
/*
* Build-time check on the image size:
*/
-ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
- "kernel image bigger than KERNEL_IMAGE_SIZE")
+. = ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
+ "kernel image bigger than KERNEL_IMAGE_SIZE");
#ifdef CONFIG_SMP
-ASSERT((per_cpu__irq_stack_union == 0),
- "irq_stack_union is not at start of per-cpu area");
+. = ASSERT((irq_stack_union == 0),
+ "irq_stack_union is not at start of per-cpu area");
#endif
#endif /* CONFIG_X86_32 */
@@ -425,7 +365,7 @@ ASSERT((per_cpu__irq_stack_union == 0),
#ifdef CONFIG_KEXEC
#include <asm/kexec.h>
-ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
- "kexec control code size is too big")
+. = ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
+ "kexec control code size is too big");
#endif
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-05 23:11:09 +0000