lkml.org 
[lkml]   [2008]   [Jun]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[PATCH 4/4] x86: Replace xxx_pda() operations with x86_xx_percpu().
  * It is now possible to use percpu operations for pda access
since the pda is in the percpu area. Drop the pda operations.

Based on linux-2.6.tip

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Mike Travis <travis@sgi.com>
---
arch/x86/kernel/apic_64.c | 4 -
arch/x86/kernel/cpu/mcheck/mce_amd_64.c | 2
arch/x86/kernel/cpu/mcheck/mce_intel_64.c | 2
arch/x86/kernel/nmi.c | 5 +
arch/x86/kernel/process_64.c | 12 ++--
arch/x86/kernel/smp.c | 4 -
arch/x86/kernel/time_64.c | 2
arch/x86/kernel/tlb_64.c | 12 ++--
arch/x86/kernel/traps_64.c | 2
arch/x86/kernel/x8664_ksyms_64.c | 2
arch/x86/xen/smp.c | 2
include/asm-x86/current.h | 3 -
include/asm-x86/hardirq_64.h | 6 +-
include/asm-x86/mmu_context_64.h | 12 ++--
include/asm-x86/pda.h | 80 ++----------------------------
include/asm-x86/smp.h | 2
include/asm-x86/stackprotector.h | 2
include/asm-x86/thread_info.h | 3 -
include/asm-x86/topology.h | 2
19 files changed, 47 insertions(+), 112 deletions(-)
--- linux-2.6.tip.orig/arch/x86/kernel/apic_64.c
+++ linux-2.6.tip/arch/x86/kernel/apic_64.c
@@ -481,7 +481,7 @@ static void local_apic_timer_interrupt(v
/*
* the NMI deadlock-detector uses this.
*/
- add_pda(apic_timer_irqs, 1);
+ x86_inc_percpu(pda.apic_timer_irqs);

evt->event_handler(evt);
}
@@ -986,7 +986,7 @@ asmlinkage void smp_spurious_interrupt(v
if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
ack_APIC_irq();

- add_pda(irq_spurious_count, 1);
+ x86_inc_percpu(pda.irq_spurious_count);
irq_exit();
}

--- linux-2.6.tip.orig/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
+++ linux-2.6.tip/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
@@ -237,7 +237,7 @@ asmlinkage void mce_threshold_interrupt(
}
}
out:
- add_pda(irq_threshold_count, 1);
+ x86_inc_percpu(pda.irq_threshold_count);
irq_exit();
}

--- linux-2.6.tip.orig/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ linux-2.6.tip/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -26,7 +26,7 @@ asmlinkage void smp_thermal_interrupt(vo
if (therm_throt_process(msr_val & 1))
mce_log_therm_throt_event(smp_processor_id(), msr_val);

- add_pda(irq_thermal_count, 1);
+ x86_inc_percpu(pda.irq_thermal_count);
irq_exit();
}

--- linux-2.6.tip.orig/arch/x86/kernel/nmi.c
+++ linux-2.6.tip/arch/x86/kernel/nmi.c
@@ -56,7 +56,7 @@ static int endflag __initdata = 0;
static inline unsigned int get_nmi_count(int cpu)
{
#ifdef CONFIG_X86_64
- return cpu_pda(cpu)->__nmi_count;
+ return x86_read_percpu(pda.__nmi_count);
#else
return nmi_count(cpu);
#endif
@@ -77,7 +77,8 @@ static inline int mce_in_progress(void)
static inline unsigned int get_timer_irqs(int cpu)
{
#ifdef CONFIG_X86_64
- return read_pda(apic_timer_irqs) + read_pda(irq0_irqs);
+ return x86_read_percpu(pda.apic_timer_irqs) +
+ x86_read_percpu(pda.irq0_irqs);
#else
return per_cpu(irq_stat, cpu).apic_timer_irqs +
per_cpu(irq_stat, cpu).irq0_irqs;
--- linux-2.6.tip.orig/arch/x86/kernel/process_64.c
+++ linux-2.6.tip/arch/x86/kernel/process_64.c
@@ -75,7 +75,7 @@ void idle_notifier_register(struct notif

void enter_idle(void)
{
- write_pda(isidle, 1);
+ x86_write_percpu(pda.isidle, 1);
atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
}

@@ -438,7 +438,7 @@ start_thread(struct pt_regs *regs, unsig
load_gs_index(0);
regs->ip = new_ip;
regs->sp = new_sp;
- write_pda(oldrsp, new_sp);
+ x86_write_percpu(pda.oldrsp, new_sp);
regs->cs = __USER_CS;
regs->ss = __USER_DS;
regs->flags = 0x200;
@@ -674,11 +674,11 @@ __switch_to(struct task_struct *prev_p,
/*
* Switch the PDA and FPU contexts.
*/
- prev->usersp = read_pda(oldrsp);
- write_pda(oldrsp, next->usersp);
- write_pda(pcurrent, next_p);
+ prev->usersp = x86_read_percpu(pda.oldrsp);
+ x86_write_percpu(pda.oldrsp, next->usersp);
+ x86_write_percpu(pda.pcurrent, next_p);

- write_pda(kernelstack,
+ x86_write_percpu(pda.kernelstack,
(unsigned long)task_stack_page(next_p) + THREAD_SIZE - PDA_STACKOFFSET);
#ifdef CONFIG_CC_STACKPROTECTOR
/*
--- linux-2.6.tip.orig/arch/x86/kernel/smp.c
+++ linux-2.6.tip/arch/x86/kernel/smp.c
@@ -295,7 +295,7 @@ void smp_reschedule_interrupt(struct pt_
#ifdef CONFIG_X86_32
__get_cpu_var(irq_stat).irq_resched_count++;
#else
- add_pda(irq_resched_count, 1);
+ x86_inc_percpu(pda.irq_resched_count);
#endif
}

@@ -320,7 +320,7 @@ void smp_call_function_interrupt(struct
#ifdef CONFIG_X86_32
__get_cpu_var(irq_stat).irq_call_count++;
#else
- add_pda(irq_call_count, 1);
+ x86_inc_percpu(pda.irq_call_count);
#endif
irq_exit();

--- linux-2.6.tip.orig/arch/x86/kernel/time_64.c
+++ linux-2.6.tip/arch/x86/kernel/time_64.c
@@ -46,7 +46,7 @@ EXPORT_SYMBOL(profile_pc);

static irqreturn_t timer_event_interrupt(int irq, void *dev_id)
{
- add_pda(irq0_irqs, 1);
+ x86_inc_percpu(pda.irq0_irqs);

global_clock_event->event_handler(global_clock_event);

--- linux-2.6.tip.orig/arch/x86/kernel/tlb_64.c
+++ linux-2.6.tip/arch/x86/kernel/tlb_64.c
@@ -60,9 +60,9 @@ static DEFINE_PER_CPU(union smp_flush_st
*/
void leave_mm(int cpu)
{
- if (read_pda(mmu_state) == TLBSTATE_OK)
+ if (x86_read_percpu(pda.mmu_state) == TLBSTATE_OK)
BUG();
- cpu_clear(cpu, read_pda(active_mm)->cpu_vm_mask);
+ cpu_clear(cpu, x86_read_percpu(pda.active_mm)->cpu_vm_mask);
load_cr3(swapper_pg_dir);
}
EXPORT_SYMBOL_GPL(leave_mm);
@@ -140,8 +140,8 @@ asmlinkage void smp_invalidate_interrupt
* BUG();
*/

- if (f->flush_mm == read_pda(active_mm)) {
- if (read_pda(mmu_state) == TLBSTATE_OK) {
+ if (f->flush_mm == x86_read_percpu(pda.active_mm)) {
+ if (x86_read_percpu(pda.mmu_state) == TLBSTATE_OK) {
if (f->flush_va == TLB_FLUSH_ALL)
local_flush_tlb();
else
@@ -152,7 +152,7 @@ asmlinkage void smp_invalidate_interrupt
out:
ack_APIC_irq();
cpu_clear(cpu, f->flush_cpumask);
- add_pda(irq_tlb_count, 1);
+ x86_inc_percpu(pda.irq_tlb_count);
}

void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
@@ -264,7 +264,7 @@ static void do_flush_tlb_all(void *info)
unsigned long cpu = smp_processor_id();

__flush_tlb_all();
- if (read_pda(mmu_state) == TLBSTATE_LAZY)
+ if (x86_read_percpu(pda.mmu_state) == TLBSTATE_LAZY)
leave_mm(cpu);
}

--- linux-2.6.tip.orig/arch/x86/kernel/traps_64.c
+++ linux-2.6.tip/arch/x86/kernel/traps_64.c
@@ -878,7 +878,7 @@ asmlinkage notrace __kprobes void
do_nmi(struct pt_regs *regs, long error_code)
{
nmi_enter();
- add_pda(__nmi_count, 1);
+ x86_inc_percpu(pda.__nmi_count);
if (!ignore_nmis)
default_do_nmi(regs);
nmi_exit();
--- linux-2.6.tip.orig/arch/x86/kernel/x8664_ksyms_64.c
+++ linux-2.6.tip/arch/x86/kernel/x8664_ksyms_64.c
@@ -59,8 +59,6 @@ EXPORT_SYMBOL(empty_zero_page);
EXPORT_SYMBOL(init_level4_pgt);
EXPORT_SYMBOL(load_gs_index);

-EXPORT_SYMBOL(_proxy_pda);
-
#ifdef CONFIG_PARAVIRT
/* Virtualized guests may want to use it */
EXPORT_SYMBOL_GPL(cpu_gdt_descr);
--- linux-2.6.tip.orig/arch/x86/xen/smp.c
+++ linux-2.6.tip/arch/x86/xen/smp.c
@@ -68,7 +68,7 @@ static irqreturn_t xen_reschedule_interr
#ifdef CONFIG_X86_32
__get_cpu_var(irq_stat).irq_resched_count++;
#else
- add_pda(irq_resched_count, 1);
+ x86_inc_percpu(pda.irq_resched_count);
#endif

return IRQ_HANDLED;
--- linux-2.6.tip.orig/include/asm-x86/current.h
+++ linux-2.6.tip/include/asm-x86/current.h
@@ -17,12 +17,13 @@ static __always_inline struct task_struc

#ifndef __ASSEMBLY__
#include <asm/pda.h>
+#include <asm/percpu.h>

struct task_struct;

static __always_inline struct task_struct *get_current(void)
{
- return read_pda(pcurrent);
+ return x86_read_percpu(pda.pcurrent);
}

#else /* __ASSEMBLY__ */
--- linux-2.6.tip.orig/include/asm-x86/hardirq_64.h
+++ linux-2.6.tip/include/asm-x86/hardirq_64.h
@@ -11,12 +11,12 @@

#define __ARCH_IRQ_STAT 1

-#define local_softirq_pending() read_pda(__softirq_pending)
+#define local_softirq_pending() x86_read_percpu(pda.__softirq_pending)

#define __ARCH_SET_SOFTIRQ_PENDING 1

-#define set_softirq_pending(x) write_pda(__softirq_pending, (x))
-#define or_softirq_pending(x) or_pda(__softirq_pending, (x))
+#define set_softirq_pending(x) x86_write_percpu(pda.__softirq_pending, (x))
+#define or_softirq_pending(x) x86_or_percpu(pda.__softirq_pending, (x))

extern void ack_bad_irq(unsigned int irq);

--- linux-2.6.tip.orig/include/asm-x86/mmu_context_64.h
+++ linux-2.6.tip/include/asm-x86/mmu_context_64.h
@@ -20,8 +20,8 @@ void destroy_context(struct mm_struct *m
static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
{
#ifdef CONFIG_SMP
- if (read_pda(mmu_state) == TLBSTATE_OK)
- write_pda(mmu_state, TLBSTATE_LAZY);
+ if (x86_read_percpu(pda.mmu_state) == TLBSTATE_OK)
+ x86_write_percpu(pda.mmu_state, TLBSTATE_LAZY);
#endif
}

@@ -33,8 +33,8 @@ static inline void switch_mm(struct mm_s
/* stop flush ipis for the previous mm */
cpu_clear(cpu, prev->cpu_vm_mask);
#ifdef CONFIG_SMP
- write_pda(mmu_state, TLBSTATE_OK);
- write_pda(active_mm, next);
+ x86_write_percpu(pda.mmu_state, TLBSTATE_OK);
+ x86_write_percpu(pda.active_mm, next);
#endif
cpu_set(cpu, next->cpu_vm_mask);
load_cr3(next->pgd);
@@ -44,8 +44,8 @@ static inline void switch_mm(struct mm_s
}
#ifdef CONFIG_SMP
else {
- write_pda(mmu_state, TLBSTATE_OK);
- if (read_pda(active_mm) != next)
+ x86_write_percpu(pda.mmu_state, TLBSTATE_OK);
+ if (x86_read_percpu(pda.active_mm) != next)
BUG();
if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
/* We were in lazy tlb mode and leave_mm disabled
--- linux-2.6.tip.orig/include/asm-x86/pda.h
+++ linux-2.6.tip/include/asm-x86/pda.h
@@ -21,7 +21,7 @@ struct x8664_pda {
offset 40!!! */
char *irqstackptr;
short nodenumber; /* number of current node (32k max) */
- short in_bootmem; /* pda lives in bootmem */
+ short unused1; /* unused */
unsigned int __softirq_pending;
unsigned int __nmi_count; /* number of NMI on this CPUs */
short mmu_state;
@@ -37,17 +37,8 @@ struct x8664_pda {
unsigned irq_spurious_count;
} ____cacheline_aligned_in_smp;

-extern struct x8664_pda **_cpu_pda;
extern void pda_init(int);

-#define cpu_pda(i) (_cpu_pda[i])
-
-/*
- * There is no fast way to get the base address of the PDA, all the accesses
- * have to mention %fs/%gs. So it needs to be done this Torvaldian way.
- */
-extern void __bad_pda_field(void) __attribute__((noreturn));
-
/*
* proxy_pda doesn't actually exist, but tell gcc it is accessed for
* all PDA accesses so it gets read/write dependencies right.
@@ -56,69 +47,11 @@ extern struct x8664_pda _proxy_pda;

#define pda_offset(field) offsetof(struct x8664_pda, field)

-#define pda_to_op(op, field, val) \
-do { \
- typedef typeof(_proxy_pda.field) T__; \
- if (0) { T__ tmp__; tmp__ = (val); } /* type checking */ \
- switch (sizeof(_proxy_pda.field)) { \
- case 2: \
- asm(op "w %1,%%gs:%c2" : \
- "+m" (_proxy_pda.field) : \
- "ri" ((T__)val), \
- "i"(pda_offset(field))); \
- break; \
- case 4: \
- asm(op "l %1,%%gs:%c2" : \
- "+m" (_proxy_pda.field) : \
- "ri" ((T__)val), \
- "i" (pda_offset(field))); \
- break; \
- case 8: \
- asm(op "q %1,%%gs:%c2": \
- "+m" (_proxy_pda.field) : \
- "ri" ((T__)val), \
- "i"(pda_offset(field))); \
- break; \
- default: \
- __bad_pda_field(); \
- } \
-} while (0)
-
-#define pda_from_op(op, field) \
-({ \
- typeof(_proxy_pda.field) ret__; \
- switch (sizeof(_proxy_pda.field)) { \
- case 2: \
- asm(op "w %%gs:%c1,%0" : \
- "=r" (ret__) : \
- "i" (pda_offset(field)), \
- "m" (_proxy_pda.field)); \
- break; \
- case 4: \
- asm(op "l %%gs:%c1,%0": \
- "=r" (ret__): \
- "i" (pda_offset(field)), \
- "m" (_proxy_pda.field)); \
- break; \
- case 8: \
- asm(op "q %%gs:%c1,%0": \
- "=r" (ret__) : \
- "i" (pda_offset(field)), \
- "m" (_proxy_pda.field)); \
- break; \
- default: \
- __bad_pda_field(); \
- } \
- ret__; \
-})
-
-#define read_pda(field) pda_from_op("mov", field)
-#define write_pda(field, val) pda_to_op("mov", field, val)
-#define add_pda(field, val) pda_to_op("add", field, val)
-#define sub_pda(field, val) pda_to_op("sub", field, val)
-#define or_pda(field, val) pda_to_op("or", field, val)
-
-/* This is not atomic against other CPUs -- CPU preemption needs to be off */
+/*
+ * This is not atomic against other CPUs -- CPU preemption needs to be off
+ * NOTE: This relies on the fact that the cpu_pda is the *first* field in
+ * the per cpu area. Move it and you'll need to change this.
+ */
#define test_and_clear_bit_pda(bit, field) \
({ \
int old__; \
@@ -128,6 +61,7 @@ do { \
old__; \
})

+
#endif

#define PDA_STACKOFFSET (5*8)
--- linux-2.6.tip.orig/include/asm-x86/smp.h
+++ linux-2.6.tip/include/asm-x86/smp.h
@@ -134,7 +134,7 @@ DECLARE_PER_CPU(int, cpu_number);
extern int safe_smp_processor_id(void);

#elif defined(CONFIG_X86_64_SMP)
-#define raw_smp_processor_id() read_pda(cpunumber)
+#define raw_smp_processor_id() x86_read_percpu(pda.cpunumber)

#define stack_smp_processor_id() \
({ \
--- linux-2.6.tip.orig/include/asm-x86/stackprotector.h
+++ linux-2.6.tip/include/asm-x86/stackprotector.h
@@ -32,7 +32,7 @@ static __always_inline void boot_init_st
canary += tsc + (tsc << 32UL);

current->stack_canary = canary;
- write_pda(stack_canary, canary);
+ x86_write_percpu(pda.stack_canary, canary);
}

#endif
--- linux-2.6.tip.orig/include/asm-x86/thread_info.h
+++ linux-2.6.tip/include/asm-x86/thread_info.h
@@ -200,7 +200,8 @@ static inline struct thread_info *curren
static inline struct thread_info *current_thread_info(void)
{
struct thread_info *ti;
- ti = (void *)(read_pda(kernelstack) + PDA_STACKOFFSET - THREAD_SIZE);
+ ti = (void *)(x86_read_percpu(pda.kernelstack) +
+ PDA_STACKOFFSET - THREAD_SIZE);
return ti;
}

--- linux-2.6.tip.orig/include/asm-x86/topology.h
+++ linux-2.6.tip/include/asm-x86/topology.h
@@ -72,7 +72,7 @@ extern cpumask_t *node_to_cpumask_map;
DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);

/* Returns the number of the current Node. */
-#define numa_node_id() read_pda(nodenumber)
+#define numa_node_id() x86_read_percpu(pda.nodenumber)

#ifdef CONFIG_DEBUG_PER_CPU_MAPS
extern int cpu_to_node(int cpu);
--


\
 
 \ /
  Last update: 2008-06-04 02:33    [from the cache]
©2003-2011 Jasper Spaans