x86: merge 64 and 32 SMP percpu handling
Now that pda is allocated as part of percpu, percpu doesn't need to be
accessed through pda. Unify x86_64 SMP percpu access with x86_32 SMP
one. Other than the segment register, operand size and the base of
percpu symbols, they behave identical now.
This patch replaces now unnecessary pda->data_offset with a dummy
field which is necessary to keep stack_canary at its place. This
patch also moves per_cpu_offset initialization out of init_gdt() into
setup_per_cpu_areas(). Note that this change also necessitates
explicit per_cpu_offset initializations in voyager_smp.c.
With this change, x86_OP_percpu()'s are as efficient on x86_64 as on
x86_32 and also x86_64 can use assembly PER_CPU macros.
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index f8d1b04..f4cc81b 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -55,7 +55,6 @@
ENTRY(irqcount);
ENTRY(cpunumber);
ENTRY(irqstackptr);
- ENTRY(data_offset);
DEFINE(pda_size, sizeof(struct x8664_pda));
BLANK();
#undef ENTRY
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e28c7a9..4833f3a 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -52,6 +52,7 @@
#include <asm/irqflags.h>
#include <asm/paravirt.h>
#include <asm/ftrace.h>
+#include <asm/percpu.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
#include <linux/elf-em.h>
@@ -1072,10 +1073,10 @@
TRACE_IRQS_OFF
movq %rsp,%rdi /* pt_regs pointer */
xorl %esi,%esi /* no error code */
- movq %gs:pda_data_offset, %rbp
- subq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+ PER_CPU(init_tss, %rbp)
+ subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
call \do_sym
- addq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+ addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
jmp paranoid_exit /* %ebx: no swapgs flag */
CFI_ENDPROC
END(\sym)
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 1a31129..e99b661 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -38,8 +38,6 @@
#else
cpu_pda(0) = &_boot_cpu_pda;
#endif
- cpu_pda(0)->data_offset =
- (unsigned long)(__per_cpu_load - __per_cpu_start);
pda_init(0);
}
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 63d4628..be1ff34 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -125,14 +125,14 @@
#endif
}
-#ifdef CONFIG_X86_32
-/*
- * Great future not-so-futuristic plan: make i386 and x86_64 do it
- * the same way
- */
+#ifdef CONFIG_X86_64
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
+ [0] = (unsigned long)__per_cpu_load,
+};
+#else
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(__per_cpu_offset);
#endif
+EXPORT_SYMBOL(__per_cpu_offset);
/*
* Great future plan:
@@ -178,6 +178,7 @@
#endif
memcpy(ptr, __per_cpu_load, __per_cpu_end - __per_cpu_start);
+ per_cpu_offset(cpu) = ptr - __per_cpu_start;
#ifdef CONFIG_X86_64
cpu_pda(cpu) = (void *)ptr;
@@ -190,7 +191,7 @@
else
memset(cpu_pda(cpu), 0, sizeof(*cpu_pda(cpu)));
#endif
- per_cpu_offset(cpu) = ptr - __per_cpu_start;
+ per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
DBG("PERCPU: cpu %4d %p\n", cpu, ptr);
}
diff --git a/arch/x86/kernel/smpcommon.c b/arch/x86/kernel/smpcommon.c
index 397e309..84395fa 100644
--- a/arch/x86/kernel/smpcommon.c
+++ b/arch/x86/kernel/smpcommon.c
@@ -4,10 +4,10 @@
#include <linux/module.h>
#include <asm/smp.h>
-#ifdef CONFIG_X86_32
DEFINE_PER_CPU(unsigned long, this_cpu_off);
EXPORT_PER_CPU_SYMBOL(this_cpu_off);
+#ifdef CONFIG_X86_32
/*
* Initialize the CPU's GDT. This is either the boot CPU doing itself
* (still using the master per-cpu area), or a CPU doing it for a
@@ -24,7 +24,6 @@
write_gdt_entry(get_cpu_gdt_table(cpu),
GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S);
- per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu];
per_cpu(cpu_number, cpu) = cpu;
}
#endif