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 for Android: free password hash cracker in your pocket
[<prev] [next>] [day] [month] [year] [list]
Message-ID: <00000140bc5f0931-53fcf3dd-0664-4c09-a08b-3ce72d4d5f5b-000000@email.amazonses.com>
Date:	Mon, 26 Aug 2013 20:44:39 +0000
From:	Christoph Lameter <cl@...ux.com>
To:	Tejun Heo <tj@...nel.org>
Cc:	linux-kernel@...r.kernel.org
Subject: [guv v2 14/31] drivers: 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/drivers/char/random.c
===================================================================
--- linux.orig/drivers/char/random.c	2013-08-22 14:16:11.335913933 -0500
+++ linux/drivers/char/random.c	2013-08-22 14:16:11.319914096 -0500
@@ -744,7 +744,7 @@ static DEFINE_PER_CPU(struct fast_pool,
 void add_interrupt_randomness(int irq, int irq_flags)
 {
 	struct entropy_store	*r;
-	struct fast_pool	*fast_pool = &__get_cpu_var(irq_randomness);
+	struct fast_pool	*fast_pool = this_cpu_ptr(&irq_randomness);
 	struct pt_regs		*regs = get_irq_regs();
 	unsigned long		now = jiffies;
 	__u32			input[4], cycles = get_cycles();
Index: linux/drivers/clocksource/metag_generic.c
===================================================================
--- linux.orig/drivers/clocksource/metag_generic.c	2013-08-22 14:16:11.335913933 -0500
+++ linux/drivers/clocksource/metag_generic.c	2013-08-22 14:16:11.323914055 -0500
@@ -90,7 +90,7 @@ static struct clocksource clocksource_me
 
 static irqreturn_t metag_timer_interrupt(int irq, void *dummy)
 {
-	struct clock_event_device *evt = &__get_cpu_var(local_clockevent);
+	struct clock_event_device *evt = this_cpu_ptr(&local_clockevent);
 
 	evt->event_handler(evt);
 
Index: linux/drivers/cpuidle/governors/ladder.c
===================================================================
--- linux.orig/drivers/cpuidle/governors/ladder.c	2013-08-22 14:16:11.335913933 -0500
+++ linux/drivers/cpuidle/governors/ladder.c	2013-08-22 14:16:11.323914055 -0500
@@ -66,7 +66,7 @@ static inline void ladder_do_selection(s
 static int ladder_select_state(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev)
 {
-	struct ladder_device *ldev = &__get_cpu_var(ladder_devices);
+	struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
 	struct ladder_device_state *last_state;
 	int last_residency, last_idx = ldev->last_state_idx;
 	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
@@ -170,7 +170,7 @@ static int ladder_enable_device(struct c
  */
 static void ladder_reflect(struct cpuidle_device *dev, int index)
 {
-	struct ladder_device *ldev = &__get_cpu_var(ladder_devices);
+	struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
 	if (index > 0)
 		ldev->last_state_idx = index;
 }
Index: linux/drivers/cpuidle/governors/menu.c
===================================================================
--- linux.orig/drivers/cpuidle/governors/menu.c	2013-08-22 14:16:11.335913933 -0500
+++ linux/drivers/cpuidle/governors/menu.c	2013-08-22 14:16:11.323914055 -0500
@@ -258,7 +258,7 @@ again:
  */
 static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
-	struct menu_device *data = &__get_cpu_var(menu_devices);
+	struct menu_device *data = this_cpu_ptr(&menu_devices);
 	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
 	int i;
 	int multiplier;
@@ -342,7 +342,7 @@ static int menu_select(struct cpuidle_dr
  */
 static void menu_reflect(struct cpuidle_device *dev, int index)
 {
-	struct menu_device *data = &__get_cpu_var(menu_devices);
+	struct menu_device *data = this_cpu_ptr(&menu_devices);
 	data->last_state_idx = index;
 	if (index >= 0)
 		data->needs_update = 1;
@@ -355,7 +355,7 @@ static void menu_reflect(struct cpuidle_
  */
 static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
-	struct menu_device *data = &__get_cpu_var(menu_devices);
+	struct menu_device *data = this_cpu_ptr(&menu_devices);
 	int last_idx = data->last_state_idx;
 	unsigned int last_idle_us = cpuidle_get_last_residency(dev);
 	struct cpuidle_state *target = &drv->states[last_idx];
Index: linux/drivers/leds/trigger/ledtrig-cpu.c
===================================================================
--- linux.orig/drivers/leds/trigger/ledtrig-cpu.c	2013-08-22 14:16:11.335913933 -0500
+++ linux/drivers/leds/trigger/ledtrig-cpu.c	2013-08-22 14:16:11.323914055 -0500
@@ -46,7 +46,7 @@ static DEFINE_PER_CPU(struct led_trigger
  */
 void ledtrig_cpu(enum cpu_led_event ledevt)
 {
-	struct led_trigger_cpu *trig = &__get_cpu_var(cpu_trig);
+	struct led_trigger_cpu *trig = this_cpu_ptr(&cpu_trig);
 
 	/* Locate the correct CPU LED */
 	switch (ledevt) {
Index: linux/drivers/net/ethernet/tile/tilegx.c
===================================================================
--- linux.orig/drivers/net/ethernet/tile/tilegx.c	2013-08-22 14:16:11.335913933 -0500
+++ linux/drivers/net/ethernet/tile/tilegx.c	2013-08-22 14:16:11.323914055 -0500
@@ -368,7 +368,7 @@ static void tile_net_pop_all_buffers(int
 /* Provide linux buffers to mPIPE. */
 static void tile_net_provide_needed_buffers(void)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 
 	while (info->num_needed_small_buffers != 0) {
 		if (!tile_net_provide_buffer(true))
@@ -407,7 +407,7 @@ static inline bool filter_packet(struct
 static void tile_net_receive_skb(struct net_device *dev, struct sk_buff *skb,
 				 gxio_mpipe_idesc_t *idesc, unsigned long len)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	struct tile_net_priv *priv = netdev_priv(dev);
 
 	/* Encode the actual packet length. */
@@ -435,7 +435,7 @@ static void tile_net_receive_skb(struct
 /* Handle a packet.  Return true if "processed", false if "filtered". */
 static bool tile_net_handle_packet(gxio_mpipe_idesc_t *idesc)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	struct net_device *dev = tile_net_devs_for_channel[idesc->channel];
 	uint8_t l2_offset;
 	void *va;
@@ -498,7 +498,7 @@ static bool tile_net_handle_packet(gxio_
  */
 static int tile_net_poll(struct napi_struct *napi, int budget)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	unsigned int work = 0;
 	gxio_mpipe_idesc_t *idesc;
 	int i, n;
@@ -536,7 +536,7 @@ done:
 /* Handle an ingress interrupt on the current cpu. */
 static irqreturn_t tile_net_handle_ingress_irq(int irq, void *unused)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	napi_schedule(&info->napi);
 	return IRQ_HANDLED;
 }
@@ -597,7 +597,7 @@ static enum hrtimer_restart tile_net_han
 /* Make sure the egress timer is scheduled. */
 static void tile_net_schedule_egress_timer(void)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 
 	if (!info->egress_timer_scheduled) {
 		hrtimer_start(&info->egress_timer,
@@ -614,7 +614,7 @@ static void tile_net_schedule_egress_tim
  */
 static enum hrtimer_restart tile_net_handle_egress_timer(struct hrtimer *t)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	unsigned long irqflags;
 	bool pending = false;
 	int i;
@@ -649,7 +649,7 @@ static enum hrtimer_restart tile_net_han
  */
 static void tile_net_update_cpu(void *arg)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	struct net_device *dev = arg;
 
 	if (!info->has_iqueue)
@@ -1572,7 +1572,7 @@ static void tso_egress(struct net_device
  */
 static int tile_net_tx_tso(struct sk_buff *skb, struct net_device *dev)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	struct tile_net_priv *priv = netdev_priv(dev);
 	int channel = priv->echannel;
 	struct tile_net_egress *egress = &egress_for_echannel[channel];
@@ -1638,7 +1638,7 @@ static unsigned int tile_net_tx_frags(st
 /* Help the kernel transmit a packet. */
 static int tile_net_tx(struct sk_buff *skb, struct net_device *dev)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	struct tile_net_priv *priv = netdev_priv(dev);
 	struct tile_net_egress *egress = &egress_for_echannel[priv->echannel];
 	gxio_mpipe_equeue_t *equeue = egress->equeue;
@@ -1869,7 +1869,7 @@ static void tile_net_dev_init(const char
 /* Per-cpu module initialization. */
 static void tile_net_init_module_percpu(void *unused)
 {
-	struct tile_net_info *info = &__get_cpu_var(per_cpu_info);
+	struct tile_net_info *info = this_cpu_ptr(&per_cpu_info);
 	int my_cpu = smp_processor_id();
 
 	info->has_iqueue = false;
Index: linux/drivers/net/ethernet/tile/tilepro.c
===================================================================
--- linux.orig/drivers/net/ethernet/tile/tilepro.c	2013-08-22 14:16:11.335913933 -0500
+++ linux/drivers/net/ethernet/tile/tilepro.c	2013-08-22 14:16:11.327914014 -0500
@@ -1078,13 +1078,13 @@ static void tile_net_register(void *dev_
 	PDEBUG("tile_net_register(queue_id %d)\n", queue_id);
 
 	if (!strcmp(dev->name, "xgbe0"))
-		info = &__get_cpu_var(hv_xgbe0);
+		info = this_cpu_ptr(&hv_xgbe0);
 	else if (!strcmp(dev->name, "xgbe1"))
-		info = &__get_cpu_var(hv_xgbe1);
+		info = this_cpu_ptr(&hv_xgbe1);
 	else if (!strcmp(dev->name, "gbe0"))
-		info = &__get_cpu_var(hv_gbe0);
+		info = this_cpu_ptr(&hv_gbe0);
 	else if (!strcmp(dev->name, "gbe1"))
-		info = &__get_cpu_var(hv_gbe1);
+		info = this_cpu_ptr(&hv_gbe1);
 	else
 		BUG();
 
Index: linux/drivers/oprofile/cpu_buffer.c
===================================================================
--- linux.orig/drivers/oprofile/cpu_buffer.c	2013-08-22 14:16:11.335913933 -0500
+++ linux/drivers/oprofile/cpu_buffer.c	2013-08-22 14:16:11.327914014 -0500
@@ -45,7 +45,7 @@ unsigned long oprofile_get_cpu_buffer_si
 
 void oprofile_cpu_buffer_inc_smpl_lost(void)
 {
-	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
 
 	cpu_buf->sample_lost_overflow++;
 }
@@ -297,7 +297,7 @@ __oprofile_add_ext_sample(unsigned long
 			  unsigned long event, int is_kernel,
 			  struct task_struct *task)
 {
-	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
 	unsigned long backtrace = oprofile_backtrace_depth;
 
 	/*
@@ -357,7 +357,7 @@ oprofile_write_reserve(struct op_entry *
 {
 	struct op_sample *sample;
 	int is_kernel = !user_mode(regs);
-	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
 
 	cpu_buf->sample_received++;
 
@@ -412,13 +412,13 @@ int oprofile_write_commit(struct op_entr
 
 void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
 {
-	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
 	log_sample(cpu_buf, pc, 0, is_kernel, event, NULL);
 }
 
 void oprofile_add_trace(unsigned long pc)
 {
-	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(op_cpu_buffer);
+	struct oprofile_cpu_buffer *cpu_buf = this_cpu_ptr(&op_cpu_buffer);
 
 	if (!cpu_buf->tracing)
 		return;
Index: linux/drivers/oprofile/timer_int.c
===================================================================
--- linux.orig/drivers/oprofile/timer_int.c	2013-08-22 14:16:11.335913933 -0500
+++ linux/drivers/oprofile/timer_int.c	2013-08-22 14:16:11.327914014 -0500
@@ -32,7 +32,7 @@ static enum hrtimer_restart oprofile_hrt
 
 static void __oprofile_hrtimer_start(void *unused)
 {
-	struct hrtimer *hrtimer = &__get_cpu_var(oprofile_hrtimer);
+	struct hrtimer *hrtimer = this_cpu_ptr(&oprofile_hrtimer);
 
 	if (!ctr_running)
 		return;

--
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