lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Date:	Mon, 26 Aug 2013 20:44:40 +0000
From:	Christoph Lameter <cl@...ux.com>
To:	Tejun Heo <tj@...nel.org>
Cc:	linux-kernel@...r.kernel.org
Subject: [guv v2 18/31] s390: Replace __get_cpu_var uses

__get_cpu_var() is used for multiple purposes in the kernel source. One of them is
address calculation via the form &__get_cpu_var(x). This calculates the address for
the instance of the percpu variable of the current processor based on an offset.

Others usage cases are for storing and retrieving data from the current processors percpu area.
__get_cpu_var() can be used as an lvalue when writing data or on the right side of an assignment.

__get_cpu_var() is defined as :


#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))



__get_cpu_var() always only does a address determination. However, store and retrieve operations
could use a segment prefix (or global register on other platforms) to avoid the address calculation.

this_cpu_write() and this_cpu_read() can directly take an offset into a percpu area and use
optimized assembly code to read and write per cpu variables.


This patch converts __get_cpu_var into either and explicit address calculation using this_cpu_ptr()
or into a use of this_cpu operations that use the offset. Thereby address calcualtions are avoided
and less registers are used when code is generated.

At the end of the patchset all uses of __get_cpu_var have been removed so the macro is removed too.

The patchset includes passes over all arches as well. Once these operations are used throughout then
specialized macros can be defined in non -x86 arches as well in order to optimize per cpu access by
f.e. using a global register that may be set to the per cpu base.




Transformations done to __get_cpu_var()


1. Determine the address of the percpu instance of the current processor.

	DEFINE_PER_CPU(int, y);
	int *x = &__get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(&y);


2. Same as #1 but this time an array structure is involved.

	DEFINE_PER_CPU(int, y[20]);
	int *x = __get_cpu_var(y);

    Converts to

	int *x = this_cpu_ptr(y);


3. Retrieve the content of the current processors instance of a per cpu variable.

	DEFINE_PER_CPU(int, u);
	int x = __get_cpu_var(y)

   Converts to

	int x = __this_cpu_read(y);


4. Retrieve the content of a percpu struct

	DEFINE_PER_CPU(struct mystruct, y);
	struct mystruct x = __get_cpu_var(y);

   Converts to

	memcpy(this_cpu_ptr(&y), x, sizeof(x));


5. Assignment to a per cpu variable

	DEFINE_PER_CPU(int, y)
	__get_cpu_var(y) = x;

   Converts to

	this_cpu_write(y, x);


6. Increment/Decrement etc of a per cpu variable

	DEFINE_PER_CPU(int, y);
	__get_cpu_var(y)++

   Converts to

	this_cpu_inc(y)



Signed-off-by: Christoph Lameter <cl@...ux.com>

Index: linux/arch/s390/include/asm/irq.h
===================================================================
--- linux.orig/arch/s390/include/asm/irq.h	2013-08-22 14:49:17.339583428 -0500
+++ linux/arch/s390/include/asm/irq.h	2013-08-22 14:49:17.327583548 -0500
@@ -55,7 +55,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct ir
 
 static __always_inline void inc_irq_stat(enum interruption_class irq)
 {
-	__get_cpu_var(irq_stat).irqs[irq]++;
+	__this_cpu_inc(irq_stat.irqs[irq]);
 }
 
 struct ext_code {
Index: linux/arch/s390/include/asm/cputime.h
===================================================================
--- linux.orig/arch/s390/include/asm/cputime.h	2013-08-22 14:49:17.339583428 -0500
+++ linux/arch/s390/include/asm/cputime.h	2013-08-22 14:49:17.327583548 -0500
@@ -187,7 +187,7 @@ cputime64_t s390_get_idle_time(int cpu);
 
 static inline int s390_nohz_delay(int cpu)
 {
-	return __get_cpu_var(s390_idle).nohz_delay != 0;
+	return __this_cpu_read(s390_idle.nohz_delay) != 0;
 }
 
 #define arch_needs_cpu(cpu) s390_nohz_delay(cpu)
Index: linux/arch/s390/kernel/kprobes.c
===================================================================
--- linux.orig/arch/s390/kernel/kprobes.c	2013-08-22 14:49:17.339583428 -0500
+++ linux/arch/s390/kernel/kprobes.c	2013-08-22 14:49:17.327583548 -0500
@@ -212,9 +212,9 @@ static void __kprobes disable_singlestep
  */
 static void __kprobes push_kprobe(struct kprobe_ctlblk *kcb, struct kprobe *p)
 {
-	kcb->prev_kprobe.kp = __get_cpu_var(current_kprobe);
+	kcb->prev_kprobe.kp = __this_cpu_read(current_kprobe);
 	kcb->prev_kprobe.status = kcb->kprobe_status;
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 }
 
 /*
@@ -224,7 +224,7 @@ static void __kprobes push_kprobe(struct
  */
 static void __kprobes pop_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 }
 
@@ -305,7 +305,7 @@ static int __kprobes kprobe_handler(stru
 		enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn);
 		return 1;
 	} else if (kprobe_running()) {
-		p = __get_cpu_var(current_kprobe);
+		p = __this_cpu_read(current_kprobe);
 		if (p->break_handler && p->break_handler(p, regs)) {
 			/*
 			 * Continuation after the jprobe completed and
Index: linux/arch/s390/kernel/nmi.c
===================================================================
--- linux.orig/arch/s390/kernel/nmi.c	2013-08-22 14:49:17.339583428 -0500
+++ linux/arch/s390/kernel/nmi.c	2013-08-22 14:49:17.327583548 -0500
@@ -53,8 +53,8 @@ void s390_handle_mcck(void)
 	 */
 	local_irq_save(flags);
 	local_mcck_disable();
-	mcck = __get_cpu_var(cpu_mcck);
-	memset(&__get_cpu_var(cpu_mcck), 0, sizeof(struct mcck_struct));
+	mcck = __this_cpu_read(cpu_mcck);
+	memset(this_cpu_ptr(&cpu_mcck), 0, sizeof(struct mcck_struct));
 	clear_thread_flag(TIF_MCCK_PENDING);
 	local_mcck_enable();
 	local_irq_restore(flags);
@@ -256,7 +256,7 @@ void notrace s390_do_machine_check(struc
 	nmi_enter();
 	inc_irq_stat(NMI_NMI);
 	mci = (struct mci *) &S390_lowcore.mcck_interruption_code;
-	mcck = &__get_cpu_var(cpu_mcck);
+	mcck = this_cpu_ptr(&cpu_mcck);
 	umode = user_mode(regs);
 
 	if (mci->sd) {
Index: linux/arch/s390/kernel/perf_cpum_cf.c
===================================================================
--- linux.orig/arch/s390/kernel/perf_cpum_cf.c	2013-08-22 14:49:17.339583428 -0500
+++ linux/arch/s390/kernel/perf_cpum_cf.c	2013-08-22 14:49:17.331583508 -0500
@@ -173,7 +173,7 @@ static int validate_ctr_auth(const struc
  */
 static void cpumf_pmu_enable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	int err;
 
 	if (cpuhw->flags & PMU_F_ENABLED)
@@ -196,7 +196,7 @@ static void cpumf_pmu_enable(struct pmu
  */
 static void cpumf_pmu_disable(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	int err;
 	u64 inactive;
 
@@ -230,7 +230,7 @@ static void cpumf_measurement_alert(stru
 		return;
 
 	inc_irq_stat(IRQEXT_CMC);
-	cpuhw = &__get_cpu_var(cpu_hw_events);
+	cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	/* Measurement alerts are shared and might happen when the PMU
 	 * is not reserved.  Ignore these alerts in this case. */
@@ -250,7 +250,7 @@ static void cpumf_measurement_alert(stru
 #define PMC_RELEASE   1
 static void setup_pmc_cpu(void *flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	switch (*((int *) flags)) {
 	case PMC_INIT:
@@ -481,7 +481,7 @@ static void cpumf_pmu_read(struct perf_e
 
 static void cpumf_pmu_start(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
@@ -512,7 +512,7 @@ static void cpumf_pmu_start(struct perf_
 
 static void cpumf_pmu_stop(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (!(hwc->state & PERF_HES_STOPPED)) {
@@ -533,7 +533,7 @@ static void cpumf_pmu_stop(struct perf_e
 
 static int cpumf_pmu_add(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	/* Check authorization for the counter set to which this
 	 * counter belongs.
@@ -557,7 +557,7 @@ static int cpumf_pmu_add(struct perf_eve
 
 static void cpumf_pmu_del(struct perf_event *event, int flags)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	cpumf_pmu_stop(event, PERF_EF_UPDATE);
 
@@ -581,7 +581,7 @@ static void cpumf_pmu_del(struct perf_ev
  */
 static void cpumf_pmu_start_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	perf_pmu_disable(pmu);
 	cpuhw->flags |= PERF_EVENT_TXN;
@@ -595,7 +595,7 @@ static void cpumf_pmu_start_txn(struct p
  */
 static void cpumf_pmu_cancel_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	WARN_ON(cpuhw->tx_state != cpuhw->state);
 
@@ -610,7 +610,7 @@ static void cpumf_pmu_cancel_txn(struct
  */
 static int cpumf_pmu_commit_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
+	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 	u64 state;
 
 	/* check if the updated state can be scheduled */
Index: linux/arch/s390/kernel/processor.c
===================================================================
--- linux.orig/arch/s390/kernel/processor.c	2013-08-22 14:49:17.339583428 -0500
+++ linux/arch/s390/kernel/processor.c	2013-08-22 14:49:17.331583508 -0500
@@ -23,8 +23,8 @@ static DEFINE_PER_CPU(struct cpuid, cpu_
  */
 void cpu_init(void)
 {
-	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);
-	struct cpuid *id = &__get_cpu_var(cpu_id);
+	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
+	struct cpuid *id = this_cpu_ptr(&cpu_id);
 
 	get_cpu_id(id);
 	atomic_inc(&init_mm.mm_count);
Index: linux/arch/s390/kernel/time.c
===================================================================
--- linux.orig/arch/s390/kernel/time.c	2013-08-22 14:49:17.339583428 -0500
+++ linux/arch/s390/kernel/time.c	2013-08-22 14:49:17.331583508 -0500
@@ -93,7 +93,7 @@ void clock_comparator_work(void)
 
 	S390_lowcore.clock_comparator = -1ULL;
 	set_clock_comparator(S390_lowcore.clock_comparator);
-	cd = &__get_cpu_var(comparators);
+	cd = this_cpu_ptr(&comparators);
 	cd->event_handler(cd);
 }
 
@@ -363,7 +363,7 @@ EXPORT_SYMBOL(get_sync_clock);
  */
 static void disable_sync_clock(void *dummy)
 {
-	atomic_t *sw_ptr = &__get_cpu_var(clock_sync_word);
+	atomic_t *sw_ptr = this_cpu_ptr(&clock_sync_word);
 	/*
 	 * Clear the in-sync bit 2^31. All get_sync_clock calls will
 	 * fail until the sync bit is turned back on. In addition
@@ -380,7 +380,7 @@ static void disable_sync_clock(void *dum
  */
 static void enable_sync_clock(void)
 {
-	atomic_t *sw_ptr = &__get_cpu_var(clock_sync_word);
+	atomic_t *sw_ptr = this_cpu_ptr(&clock_sync_word);
 	atomic_set_mask(0x80000000, sw_ptr);
 }
 
Index: linux/arch/s390/kernel/vtime.c
===================================================================
--- linux.orig/arch/s390/kernel/vtime.c	2013-08-22 14:49:17.339583428 -0500
+++ linux/arch/s390/kernel/vtime.c	2013-08-22 14:49:17.331583508 -0500
@@ -153,7 +153,7 @@ EXPORT_SYMBOL_GPL(vtime_account_system);
 
 void __kprobes vtime_stop_cpu(void)
 {
-	struct s390_idle_data *idle = &__get_cpu_var(s390_idle);
+	struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
 	unsigned long long idle_time;
 	unsigned long psw_mask;
 
Index: linux/arch/s390/oprofile/hwsampler.c
===================================================================
--- linux.orig/arch/s390/oprofile/hwsampler.c	2013-08-22 14:49:17.339583428 -0500
+++ linux/arch/s390/oprofile/hwsampler.c	2013-08-22 14:49:17.331583508 -0500
@@ -228,7 +228,7 @@ static inline unsigned long *trailer_ent
 static void hws_ext_handler(struct ext_code ext_code,
 			    unsigned int param32, unsigned long param64)
 {
-	struct hws_cpu_buffer *cb = &__get_cpu_var(sampler_cpu_buffer);
+	struct hws_cpu_buffer *cb = this_cpu_ptr(&sampler_cpu_buffer);
 
 	if (!(param32 & CPU_MF_INT_SF_MASK))
 		return;
Index: linux/arch/s390/pci/pci.c
===================================================================
--- linux.orig/arch/s390/pci/pci.c	2013-08-22 14:49:17.339583428 -0500
+++ linux/arch/s390/pci/pci.c	2013-08-22 14:49:17.335583467 -0500
@@ -409,7 +409,7 @@ static DEFINE_PER_CPU(unsigned long, nex
 
 static void zpci_irq_handler(struct airq_struct *airq)
 {
-	unsigned long sbit, mbit, last = 0, start = __get_cpu_var(next_sbit);
+	unsigned long sbit, mbit, last = 0, start = __this_cpu_read(next_sbit);
 	int rescan = 0, max = aisb_max;
 	struct zdev_irq_map *imap;
 
@@ -460,7 +460,7 @@ scan:
 	}
 out:
 	/* store next device bit to scan */
-	__get_cpu_var(next_sbit) = (++last >= aisb_max) ? 0 : last;
+	__this_cpu_write(next_sbit, (++last >= aisb_max) ? 0 : last);
 }
 
 /* msi_vecs - number of requested interrupts, 0 place function to error state */
Index: linux/arch/s390/kernel/irq.c
===================================================================
--- linux.orig/arch/s390/kernel/irq.c	2013-08-08 02:54:34.344984334 -0500
+++ linux/arch/s390/kernel/irq.c	2013-08-22 14:53:32.025028108 -0500
@@ -250,7 +250,7 @@ void __irq_entry do_extint(struct pt_reg
 	kstat_incr_irqs_this_cpu(EXTERNAL_INTERRUPT, NULL);
 	ext_code = *(struct ext_code *) &regs->int_code;
 	if (ext_code.code != 0x1004)
-		__get_cpu_var(s390_idle).nohz_delay = 1;
+		__this_cpu_write(s390_idle.nohz_delay, 1);
 
 	index = ext_hash(ext_code.code);
 	rcu_read_lock();

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ