#define ARM_CPU_KEEP(x)
#endif
+#if defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK)
+#define ARM_EXIT_KEEP(x) x
+#else
+#define ARM_EXIT_KEEP(x)
+#endif
+
OUTPUT_ARCH(arm)
ENTRY(stext)
_sinittext = .;
HEAD_TEXT
INIT_TEXT
+ ARM_EXIT_KEEP(EXIT_TEXT)
_einittext = .;
ARM_CPU_DISCARD(PROC_INFO)
__arch_info_begin = .;
#ifndef CONFIG_XIP_KERNEL
__init_begin = _stext;
INIT_DATA
+ ARM_EXIT_KEEP(EXIT_DATA)
#endif
}
- PERCPU(PAGE_SIZE)
+ PERCPU(32, PAGE_SIZE)
#ifndef CONFIG_XIP_KERNEL
. = ALIGN(PAGE_SIZE);
. = ALIGN(PAGE_SIZE);
__init_begin = .;
INIT_DATA
+ ARM_EXIT_KEEP(EXIT_DATA)
. = ALIGN(PAGE_SIZE);
__init_end = .;
#endif
}
#endif
+ NOTES
+
BSS_SECTION(0, 0, 0)
_end = .;
INIT_TEXT_SECTION(PAGE_SIZE)
.init.data : { INIT_DATA }
.init.setup : { INIT_SETUP(16) }
-#ifdef CONFIG_ETRAX_ARCH_V32
- __start___param = .;
- __param : { *(__param) }
- __stop___param = .;
-#endif
.initcall.init : {
INIT_CALLS
}
#endif
__vmlinux_end = .; /* Last address of the physical file. */
#ifdef CONFIG_ETRAX_ARCH_V32
- PERCPU(PAGE_SIZE)
+ PERCPU(32, PAGE_SIZE)
.init.ramfs : {
INIT_RAM_FS
typeof(var) pxo_new__ = (nval); \
switch (sizeof(var)) { \
case 1: \
- asm("\n1:mov "__percpu_arg(1)",%%al" \
- "\n\tcmpxchgb %2, "__percpu_arg(1) \
+ asm("\n\tmov "__percpu_arg(1)",%%al" \
+ "\n1:\tcmpxchgb %2, "__percpu_arg(1) \
"\n\tjnz 1b" \
- : "=a" (pxo_ret__), "+m" (var) \
+ : "=&a" (pxo_ret__), "+m" (var) \
: "q" (pxo_new__) \
: "memory"); \
break; \
case 2: \
- asm("\n1:mov "__percpu_arg(1)",%%ax" \
- "\n\tcmpxchgw %2, "__percpu_arg(1) \
+ asm("\n\tmov "__percpu_arg(1)",%%ax" \
+ "\n1:\tcmpxchgw %2, "__percpu_arg(1) \
"\n\tjnz 1b" \
- : "=a" (pxo_ret__), "+m" (var) \
+ : "=&a" (pxo_ret__), "+m" (var) \
: "r" (pxo_new__) \
: "memory"); \
break; \
case 4: \
- asm("\n1:mov "__percpu_arg(1)",%%eax" \
- "\n\tcmpxchgl %2, "__percpu_arg(1) \
+ asm("\n\tmov "__percpu_arg(1)",%%eax" \
+ "\n1:\tcmpxchgl %2, "__percpu_arg(1) \
"\n\tjnz 1b" \
- : "=a" (pxo_ret__), "+m" (var) \
+ : "=&a" (pxo_ret__), "+m" (var) \
: "r" (pxo_new__) \
: "memory"); \
break; \
case 8: \
- asm("\n1:mov "__percpu_arg(1)",%%rax" \
- "\n\tcmpxchgq %2, "__percpu_arg(1) \
+ asm("\n\tmov "__percpu_arg(1)",%%rax" \
+ "\n1:\tcmpxchgq %2, "__percpu_arg(1) \
"\n\tjnz 1b" \
- : "=a" (pxo_ret__), "+m" (var) \
+ : "=&a" (pxo_ret__), "+m" (var) \
: "r" (pxo_new__) \
: "memory"); \
break; \
#define irqsafe_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval)
#endif /* !CONFIG_M386 */
+ #ifdef CONFIG_X86_CMPXCHG64
+ #define percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2) \
+ ({ \
+ char __ret; \
+ typeof(o1) __o1 = o1; \
+ typeof(o1) __n1 = n1; \
+ typeof(o2) __o2 = o2; \
+ typeof(o2) __n2 = n2; \
+ typeof(o2) __dummy = n2; \
+ asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t" \
+ : "=a"(__ret), "=m" (pcp1), "=d"(__dummy) \
+ : "b"(__n1), "c"(__n2), "a"(__o1), "d"(__o2)); \
+ __ret; \
+ })
+
+ #define __this_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2)
+ #define this_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2)
+ #define irqsafe_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2)
+ #endif /* CONFIG_X86_CMPXCHG64 */
+
/*
* Per cpu atomic 64 bit operations are only available under 64 bit.
* 32 bit must fall back to generic operations.
#define irqsafe_cpu_xor_8(pcp, val) percpu_to_op("xor", (pcp), val)
#define irqsafe_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval)
#define irqsafe_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval)
+
+ /*
+ * Pretty complex macro to generate cmpxchg16 instruction. The instruction
+ * is not supported on early AMD64 processors so we must be able to emulate
+ * it in software. The address used in the cmpxchg16 instruction must be
+ * aligned to a 16 byte boundary.
+ */
+ #define percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2) \
+ ({ \
+ char __ret; \
+ typeof(o1) __o1 = o1; \
+ typeof(o1) __n1 = n1; \
+ typeof(o2) __o2 = o2; \
+ typeof(o2) __n2 = n2; \
+ typeof(o2) __dummy; \
+ alternative_io("call this_cpu_cmpxchg16b_emu\n\t" P6_NOP4, \
+ "cmpxchg16b %%gs:(%%rsi)\n\tsetz %0\n\t", \
+ X86_FEATURE_CX16, \
+ ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)), \
+ "S" (&pcp1), "b"(__n1), "c"(__n2), \
+ "a"(__o1), "d"(__o2)); \
+ __ret; \
+ })
+
+ #define __this_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)
+ #define this_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)
+ #define irqsafe_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2) percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)
+
#endif
/* This is not atomic against other CPUs -- CPU preemption needs to be off */
SCHED_TEXT
LOCK_TEXT
KPROBES_TEXT
+ ENTRY_TEXT
IRQENTRY_TEXT
*(.fixup)
*(.gnu.warning)
* output PHDR, so the next output section - .init.text - should
* start another segment - init.
*/
- PERCPU_VADDR(0, :percpu)
+ PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu)
#endif
INIT_TEXT_SECTION(PAGE_SIZE)
}
#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
- PERCPU(PAGE_SIZE)
- PERCPU(INTERNODE_CACHE_BYTES, THREAD_SIZE)
++ PERCPU(INTERNODE_CACHE_BYTES, PAGE_SIZE)
#endif
. = ALIGN(PAGE_SIZE);
* HEAD_TEXT_SECTION
* INIT_TEXT_SECTION(PAGE_SIZE)
* INIT_DATA_SECTION(...)
- * PERCPU(PAGE_SIZE)
+ * PERCPU(CACHELINE_SIZE, PAGE_SIZE)
* __init_end = .;
*
* _stext = .;
#endif
#ifdef CONFIG_EVENT_TRACING
-#define FTRACE_EVENTS() VMLINUX_SYMBOL(__start_ftrace_events) = .; \
+#define FTRACE_EVENTS() . = ALIGN(8); \
+ VMLINUX_SYMBOL(__start_ftrace_events) = .; \
*(_ftrace_events) \
VMLINUX_SYMBOL(__stop_ftrace_events) = .;
#else
#endif
#ifdef CONFIG_FTRACE_SYSCALLS
-#define TRACE_SYSCALLS() VMLINUX_SYMBOL(__start_syscalls_metadata) = .; \
+#define TRACE_SYSCALLS() . = ALIGN(8); \
+ VMLINUX_SYMBOL(__start_syscalls_metadata) = .; \
*(__syscalls_metadata) \
VMLINUX_SYMBOL(__stop_syscalls_metadata) = .;
#else
CPU_KEEP(exit.data) \
MEM_KEEP(init.data) \
MEM_KEEP(exit.data) \
- . = ALIGN(32); \
- VMLINUX_SYMBOL(__start___tracepoints) = .; \
+ STRUCT_ALIGN(); \
*(__tracepoints) \
- VMLINUX_SYMBOL(__stop___tracepoints) = .; \
/* implement dynamic printk debug */ \
. = ALIGN(8); \
VMLINUX_SYMBOL(__start___verbose) = .; \
VMLINUX_SYMBOL(__stop___verbose) = .; \
LIKELY_PROFILE() \
BRANCH_PROFILE() \
- TRACE_PRINTKS() \
- \
- STRUCT_ALIGN(); \
- FTRACE_EVENTS() \
- \
- STRUCT_ALIGN(); \
- TRACE_SYSCALLS()
+ TRACE_PRINTKS()
/*
* Data section helpers
VMLINUX_SYMBOL(__start_rodata) = .; \
*(.rodata) *(.rodata.*) \
*(__vermagic) /* Kernel version magic */ \
+ . = ALIGN(8); \
+ VMLINUX_SYMBOL(__start___tracepoints_ptrs) = .; \
+ *(__tracepoints_ptrs) /* Tracepoints: pointer array */\
+ VMLINUX_SYMBOL(__stop___tracepoints_ptrs) = .; \
*(__markers_strings) /* Markers: strings */ \
*(__tracepoints_strings)/* Tracepoints: strings */ \
} \
*(.kprobes.text) \
VMLINUX_SYMBOL(__kprobes_text_end) = .;
+#define ENTRY_TEXT \
+ ALIGN_FUNCTION(); \
+ VMLINUX_SYMBOL(__entry_text_start) = .; \
+ *(.entry.text) \
+ VMLINUX_SYMBOL(__entry_text_end) = .;
+
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
#define IRQENTRY_TEXT \
ALIGN_FUNCTION(); \
KERNEL_CTORS() \
*(.init.rodata) \
MCOUNT_REC() \
+ FTRACE_EVENTS() \
+ TRACE_SYSCALLS() \
DEV_DISCARD(init.rodata) \
CPU_DISCARD(init.rodata) \
MEM_DISCARD(init.rodata) \
/**
* PERCPU_VADDR - define output section for percpu area
+ * @cacheline: cacheline size
* @vaddr: explicit base address (optional)
* @phdr: destination PHDR (optional)
*
- * Macro which expands to output section for percpu area. If @vaddr
- * is not blank, it specifies explicit base address and all percpu
- * symbols will be offset from the given address. If blank, @vaddr
- * always equals @laddr + LOAD_OFFSET.
+ * Macro which expands to output section for percpu area.
+ *
+ * @cacheline is used to align subsections to avoid false cacheline
+ * sharing between subsections for different purposes.
+ *
+ * If @vaddr is not blank, it specifies explicit base address and all
+ * percpu symbols will be offset from the given address. If blank,
+ * @vaddr always equals @laddr + LOAD_OFFSET.
*
* @phdr defines the output PHDR to use if not blank. Be warned that
* output PHDR is sticky. If @phdr is specified, the next output
* If there is no need to put the percpu section at a predetermined
* address, use PERCPU().
*/
- #define PERCPU_VADDR(vaddr, phdr) \
+ #define PERCPU_VADDR(cacheline, vaddr, phdr) \
VMLINUX_SYMBOL(__per_cpu_load) = .; \
.data..percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load) \
- LOAD_OFFSET) { \
*(.data..percpu..first) \
. = ALIGN(PAGE_SIZE); \
*(.data..percpu..page_aligned) \
+ . = ALIGN(cacheline); \
*(.data..percpu..readmostly) \
+ . = ALIGN(cacheline); \
*(.data..percpu) \
*(.data..percpu..shared_aligned) \
VMLINUX_SYMBOL(__per_cpu_end) = .; \
/**
* PERCPU - define output section for percpu area, simple version
+ * @cacheline: cacheline size
* @align: required alignment
*
- * Align to @align and outputs output section for percpu area. This
- * macro doesn't maniuplate @vaddr or @phdr and __per_cpu_load and
+ * Align to @align and outputs output section for percpu area. This macro
+ * doesn't manipulate @vaddr or @phdr and __per_cpu_load and
* __per_cpu_start will be identical.
*
- * This macro is equivalent to ALIGN(align); PERCPU_VADDR( , ) except
- * that __per_cpu_load is defined as a relative symbol against
- * .data..percpu which is required for relocatable x86_32
- * configuration.
+ * This macro is equivalent to ALIGN(@align); PERCPU_VADDR(@cacheline,,)
+ * except that __per_cpu_load is defined as a relative symbol against
+ * .data..percpu which is required for relocatable x86_32 configuration.
*/
- #define PERCPU(align) \
+ #define PERCPU(cacheline, align) \
. = ALIGN(align); \
.data..percpu : AT(ADDR(.data..percpu) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__per_cpu_load) = .; \
*(.data..percpu..first) \
. = ALIGN(PAGE_SIZE); \
*(.data..percpu..page_aligned) \
+ . = ALIGN(cacheline); \
*(.data..percpu..readmostly) \
+ . = ALIGN(cacheline); \
*(.data..percpu) \
*(.data..percpu..shared_aligned) \
VMLINUX_SYMBOL(__per_cpu_end) = .; \