Merge branch 'devel-stable' into for-next

Conflicts:
	arch/arm/include/asm/atomic.h
	arch/arm/include/asm/hardirq.h
	arch/arm/kernel/smp.c
This commit is contained in:
Russell King 2013-11-12 10:58:59 +00:00
Родитель ec1e20a02f 70d4212687
Коммит df762eccba
80 изменённых файлов: 7571 добавлений и 245 удалений

Просмотреть файл

@ -52,6 +52,8 @@ config ARM
select HAVE_MOD_ARCH_SPECIFIC if ARM_UNWIND
select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
select HAVE_PERF_EVENTS
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_UID16
@ -482,6 +484,7 @@ config ARCH_IXP4XX
bool "IXP4xx-based"
depends on MMU
select ARCH_HAS_DMA_SET_COHERENT_MASK
select ARCH_SUPPORTS_BIG_ENDIAN
select ARCH_REQUIRE_GPIOLIB
select CLKSRC_MMIO
select CPU_XSCALE
@ -1545,6 +1548,32 @@ config MCPM
for (multi-)cluster based systems, such as big.LITTLE based
systems.
config BIG_LITTLE
bool "big.LITTLE support (Experimental)"
depends on CPU_V7 && SMP
select MCPM
help
This option enables support selections for the big.LITTLE
system architecture.
config BL_SWITCHER
bool "big.LITTLE switcher support"
depends on BIG_LITTLE && MCPM && HOTPLUG_CPU
select CPU_PM
select ARM_CPU_SUSPEND
help
The big.LITTLE "switcher" provides the core functionality to
transparently handle transition between a cluster of A15's
and a cluster of A7's in a big.LITTLE system.
config BL_SWITCHER_DUMMY_IF
tristate "Simple big.LITTLE switcher user interface"
depends on BL_SWITCHER && DEBUG_KERNEL
help
This is a simple and dummy char dev interface to control
the big.LITTLE switcher core code. It is meant for
debugging purposes only.
choice
prompt "Memory split"
default VMSPLIT_3G

Просмотреть файл

@ -16,6 +16,7 @@ LDFLAGS :=
LDFLAGS_vmlinux :=-p --no-undefined -X
ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
LDFLAGS_vmlinux += --be8
LDFLAGS_MODULE += --be8
endif
OBJCOPYFLAGS :=-O binary -R .comment -S

Просмотреть файл

@ -135,6 +135,7 @@ start:
.word _edata @ zImage end address
THUMB( .thumb )
1:
ARM_BE8( setend be ) @ go BE8 if compiled for BE8
mrs r9, cpsr
#ifdef CONFIG_ARM_VIRT_EXT
bl __hyp_stub_install @ get into SVC mode, reversibly
@ -699,9 +700,7 @@ __armv4_mmu_cache_on:
mrc p15, 0, r0, c1, c0, 0 @ read control reg
orr r0, r0, #0x5000 @ I-cache enable, RR cache replacement
orr r0, r0, #0x0030
#ifdef CONFIG_CPU_ENDIAN_BE8
orr r0, r0, #1 << 25 @ big-endian page tables
#endif
ARM_BE8( orr r0, r0, #1 << 25 ) @ big-endian page tables
bl __common_mmu_cache_on
mov r0, #0
mcr p15, 0, r0, c8, c7, 0 @ flush I,D TLBs
@ -728,9 +727,7 @@ __armv7_mmu_cache_on:
orr r0, r0, #1 << 22 @ U (v6 unaligned access model)
@ (needed for ARM1176)
#ifdef CONFIG_MMU
#ifdef CONFIG_CPU_ENDIAN_BE8
orr r0, r0, #1 << 25 @ big-endian page tables
#endif
ARM_BE8( orr r0, r0, #1 << 25 ) @ big-endian page tables
mrcne p15, 0, r6, c2, c0, 2 @ read ttb control reg
orrne r0, r0, #1 @ MMU enabled
movne r1, #0xfffffffd @ domain 0 = client

Просмотреть файл

@ -17,3 +17,5 @@ obj-$(CONFIG_MCPM) += mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
AFLAGS_mcpm_head.o := -march=armv7-a
AFLAGS_vlock.o := -march=armv7-a
obj-$(CONFIG_TI_PRIV_EDMA) += edma.o
obj-$(CONFIG_BL_SWITCHER) += bL_switcher.o
obj-$(CONFIG_BL_SWITCHER_DUMMY_IF) += bL_switcher_dummy_if.o

Просмотреть файл

@ -0,0 +1,822 @@
/*
* arch/arm/common/bL_switcher.c -- big.LITTLE cluster switcher core driver
*
* Created by: Nicolas Pitre, March 2012
* Copyright: (C) 2012-2013 Linaro Limited
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/atomic.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/cpu_pm.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/kthread.h>
#include <linux/wait.h>
#include <linux/time.h>
#include <linux/clockchips.h>
#include <linux/hrtimer.h>
#include <linux/tick.h>
#include <linux/notifier.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/smp.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/sysfs.h>
#include <linux/irqchip/arm-gic.h>
#include <linux/moduleparam.h>
#include <asm/smp_plat.h>
#include <asm/cputype.h>
#include <asm/suspend.h>
#include <asm/mcpm.h>
#include <asm/bL_switcher.h>
#define CREATE_TRACE_POINTS
#include <trace/events/power_cpu_migrate.h>
/*
* Use our own MPIDR accessors as the generic ones in asm/cputype.h have
* __attribute_const__ and we don't want the compiler to assume any
* constness here as the value _does_ change along some code paths.
*/
static int read_mpidr(void)
{
unsigned int id;
asm volatile ("mrc p15, 0, %0, c0, c0, 5" : "=r" (id));
return id & MPIDR_HWID_BITMASK;
}
/*
* Get a global nanosecond time stamp for tracing.
*/
static s64 get_ns(void)
{
struct timespec ts;
getnstimeofday(&ts);
return timespec_to_ns(&ts);
}
/*
* bL switcher core code.
*/
static void bL_do_switch(void *_arg)
{
unsigned ib_mpidr, ib_cpu, ib_cluster;
long volatile handshake, **handshake_ptr = _arg;
pr_debug("%s\n", __func__);
ib_mpidr = cpu_logical_map(smp_processor_id());
ib_cpu = MPIDR_AFFINITY_LEVEL(ib_mpidr, 0);
ib_cluster = MPIDR_AFFINITY_LEVEL(ib_mpidr, 1);
/* Advertise our handshake location */
if (handshake_ptr) {
handshake = 0;
*handshake_ptr = &handshake;
} else
handshake = -1;
/*
* Our state has been saved at this point. Let's release our
* inbound CPU.
*/
mcpm_set_entry_vector(ib_cpu, ib_cluster, cpu_resume);
sev();
/*
* From this point, we must assume that our counterpart CPU might
* have taken over in its parallel world already, as if execution
* just returned from cpu_suspend(). It is therefore important to
* be very careful not to make any change the other guy is not
* expecting. This is why we need stack isolation.
*
* Fancy under cover tasks could be performed here. For now
* we have none.
*/
/*
* Let's wait until our inbound is alive.
*/
while (!handshake) {
wfe();
smp_mb();
}
/* Let's put ourself down. */
mcpm_cpu_power_down();
/* should never get here */
BUG();
}
/*
* Stack isolation. To ensure 'current' remains valid, we just use another
* piece of our thread's stack space which should be fairly lightly used.
* The selected area starts just above the thread_info structure located
* at the very bottom of the stack, aligned to a cache line, and indexed
* with the cluster number.
*/
#define STACK_SIZE 512
extern void call_with_stack(void (*fn)(void *), void *arg, void *sp);
static int bL_switchpoint(unsigned long _arg)
{
unsigned int mpidr = read_mpidr();
unsigned int clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1);
void *stack = current_thread_info() + 1;
stack = PTR_ALIGN(stack, L1_CACHE_BYTES);
stack += clusterid * STACK_SIZE + STACK_SIZE;
call_with_stack(bL_do_switch, (void *)_arg, stack);
BUG();
}
/*
* Generic switcher interface
*/
static unsigned int bL_gic_id[MAX_CPUS_PER_CLUSTER][MAX_NR_CLUSTERS];
static int bL_switcher_cpu_pairing[NR_CPUS];
/*
* bL_switch_to - Switch to a specific cluster for the current CPU
* @new_cluster_id: the ID of the cluster to switch to.
*
* This function must be called on the CPU to be switched.
* Returns 0 on success, else a negative status code.
*/
static int bL_switch_to(unsigned int new_cluster_id)
{
unsigned int mpidr, this_cpu, that_cpu;
unsigned int ob_mpidr, ob_cpu, ob_cluster, ib_mpidr, ib_cpu, ib_cluster;
struct completion inbound_alive;
struct tick_device *tdev;
enum clock_event_mode tdev_mode;
long volatile *handshake_ptr;
int ipi_nr, ret;
this_cpu = smp_processor_id();
ob_mpidr = read_mpidr();
ob_cpu = MPIDR_AFFINITY_LEVEL(ob_mpidr, 0);
ob_cluster = MPIDR_AFFINITY_LEVEL(ob_mpidr, 1);
BUG_ON(cpu_logical_map(this_cpu) != ob_mpidr);
if (new_cluster_id == ob_cluster)
return 0;
that_cpu = bL_switcher_cpu_pairing[this_cpu];
ib_mpidr = cpu_logical_map(that_cpu);
ib_cpu = MPIDR_AFFINITY_LEVEL(ib_mpidr, 0);
ib_cluster = MPIDR_AFFINITY_LEVEL(ib_mpidr, 1);
pr_debug("before switch: CPU %d MPIDR %#x -> %#x\n",
this_cpu, ob_mpidr, ib_mpidr);
this_cpu = smp_processor_id();
/* Close the gate for our entry vectors */
mcpm_set_entry_vector(ob_cpu, ob_cluster, NULL);
mcpm_set_entry_vector(ib_cpu, ib_cluster, NULL);
/* Install our "inbound alive" notifier. */
init_completion(&inbound_alive);
ipi_nr = register_ipi_completion(&inbound_alive, this_cpu);
ipi_nr |= ((1 << 16) << bL_gic_id[ob_cpu][ob_cluster]);
mcpm_set_early_poke(ib_cpu, ib_cluster, gic_get_sgir_physaddr(), ipi_nr);
/*
* Let's wake up the inbound CPU now in case it requires some delay
* to come online, but leave it gated in our entry vector code.
*/
ret = mcpm_cpu_power_up(ib_cpu, ib_cluster);
if (ret) {
pr_err("%s: mcpm_cpu_power_up() returned %d\n", __func__, ret);
return ret;
}
/*
* Raise a SGI on the inbound CPU to make sure it doesn't stall
* in a possible WFI, such as in bL_power_down().
*/
gic_send_sgi(bL_gic_id[ib_cpu][ib_cluster], 0);
/*
* Wait for the inbound to come up. This allows for other
* tasks to be scheduled in the mean time.
*/
wait_for_completion(&inbound_alive);
mcpm_set_early_poke(ib_cpu, ib_cluster, 0, 0);
/*
* From this point we are entering the switch critical zone
* and can't take any interrupts anymore.
*/
local_irq_disable();
local_fiq_disable();
trace_cpu_migrate_begin(get_ns(), ob_mpidr);
/* redirect GIC's SGIs to our counterpart */
gic_migrate_target(bL_gic_id[ib_cpu][ib_cluster]);
tdev = tick_get_device(this_cpu);
if (tdev && !cpumask_equal(tdev->evtdev->cpumask, cpumask_of(this_cpu)))
tdev = NULL;
if (tdev) {
tdev_mode = tdev->evtdev->mode;
clockevents_set_mode(tdev->evtdev, CLOCK_EVT_MODE_SHUTDOWN);
}
ret = cpu_pm_enter();
/* we can not tolerate errors at this point */
if (ret)
panic("%s: cpu_pm_enter() returned %d\n", __func__, ret);
/* Swap the physical CPUs in the logical map for this logical CPU. */
cpu_logical_map(this_cpu) = ib_mpidr;
cpu_logical_map(that_cpu) = ob_mpidr;
/* Let's do the actual CPU switch. */
ret = cpu_suspend((unsigned long)&handshake_ptr, bL_switchpoint);
if (ret > 0)
panic("%s: cpu_suspend() returned %d\n", __func__, ret);
/* We are executing on the inbound CPU at this point */
mpidr = read_mpidr();
pr_debug("after switch: CPU %d MPIDR %#x\n", this_cpu, mpidr);
BUG_ON(mpidr != ib_mpidr);
mcpm_cpu_powered_up();
ret = cpu_pm_exit();
if (tdev) {
clockevents_set_mode(tdev->evtdev, tdev_mode);
clockevents_program_event(tdev->evtdev,
tdev->evtdev->next_event, 1);
}
trace_cpu_migrate_finish(get_ns(), ib_mpidr);
local_fiq_enable();
local_irq_enable();
*handshake_ptr = 1;
dsb_sev();
if (ret)
pr_err("%s exiting with error %d\n", __func__, ret);
return ret;
}
struct bL_thread {
spinlock_t lock;
struct task_struct *task;
wait_queue_head_t wq;
int wanted_cluster;
struct completion started;
bL_switch_completion_handler completer;
void *completer_cookie;
};
static struct bL_thread bL_threads[NR_CPUS];
static int bL_switcher_thread(void *arg)
{
struct bL_thread *t = arg;
struct sched_param param = { .sched_priority = 1 };
int cluster;
bL_switch_completion_handler completer;
void *completer_cookie;
sched_setscheduler_nocheck(current, SCHED_FIFO, &param);
complete(&t->started);
do {
if (signal_pending(current))
flush_signals(current);
wait_event_interruptible(t->wq,
t->wanted_cluster != -1 ||
kthread_should_stop());
spin_lock(&t->lock);
cluster = t->wanted_cluster;
completer = t->completer;
completer_cookie = t->completer_cookie;
t->wanted_cluster = -1;
t->completer = NULL;
spin_unlock(&t->lock);
if (cluster != -1) {
bL_switch_to(cluster);
if (completer)
completer(completer_cookie);
}
} while (!kthread_should_stop());
return 0;
}
static struct task_struct *bL_switcher_thread_create(int cpu, void *arg)
{
struct task_struct *task;
task = kthread_create_on_node(bL_switcher_thread, arg,
cpu_to_node(cpu), "kswitcher_%d", cpu);
if (!IS_ERR(task)) {
kthread_bind(task, cpu);
wake_up_process(task);
} else
pr_err("%s failed for CPU %d\n", __func__, cpu);
return task;
}
/*
* bL_switch_request_cb - Switch to a specific cluster for the given CPU,
* with completion notification via a callback
*
* @cpu: the CPU to switch
* @new_cluster_id: the ID of the cluster to switch to.
* @completer: switch completion callback. if non-NULL,
* @completer(@completer_cookie) will be called on completion of
* the switch, in non-atomic context.
* @completer_cookie: opaque context argument for @completer.
*
* This function causes a cluster switch on the given CPU by waking up
* the appropriate switcher thread. This function may or may not return
* before the switch has occurred.
*
* If a @completer callback function is supplied, it will be called when
* the switch is complete. This can be used to determine asynchronously
* when the switch is complete, regardless of when bL_switch_request()
* returns. When @completer is supplied, no new switch request is permitted
* for the affected CPU until after the switch is complete, and @completer
* has returned.
*/
int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id,
bL_switch_completion_handler completer,
void *completer_cookie)
{
struct bL_thread *t;
if (cpu >= ARRAY_SIZE(bL_threads)) {
pr_err("%s: cpu %d out of bounds\n", __func__, cpu);
return -EINVAL;
}
t = &bL_threads[cpu];
if (IS_ERR(t->task))
return PTR_ERR(t->task);
if (!t->task)
return -ESRCH;
spin_lock(&t->lock);
if (t->completer) {
spin_unlock(&t->lock);
return -EBUSY;
}
t->completer = completer;
t->completer_cookie = completer_cookie;
t->wanted_cluster = new_cluster_id;
spin_unlock(&t->lock);
wake_up(&t->wq);
return 0;
}
EXPORT_SYMBOL_GPL(bL_switch_request_cb);
/*
* Activation and configuration code.
*/
static DEFINE_MUTEX(bL_switcher_activation_lock);
static BLOCKING_NOTIFIER_HEAD(bL_activation_notifier);
static unsigned int bL_switcher_active;
static unsigned int bL_switcher_cpu_original_cluster[NR_CPUS];
static cpumask_t bL_switcher_removed_logical_cpus;
int bL_switcher_register_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_register(&bL_activation_notifier, nb);
}
EXPORT_SYMBOL_GPL(bL_switcher_register_notifier);
int bL_switcher_unregister_notifier(struct notifier_block *nb)
{
return blocking_notifier_chain_unregister(&bL_activation_notifier, nb);
}
EXPORT_SYMBOL_GPL(bL_switcher_unregister_notifier);
static int bL_activation_notify(unsigned long val)
{
int ret;
ret = blocking_notifier_call_chain(&bL_activation_notifier, val, NULL);
if (ret & NOTIFY_STOP_MASK)
pr_err("%s: notifier chain failed with status 0x%x\n",
__func__, ret);
return notifier_to_errno(ret);
}
static void bL_switcher_restore_cpus(void)
{
int i;
for_each_cpu(i, &bL_switcher_removed_logical_cpus)
cpu_up(i);
}
static int bL_switcher_halve_cpus(void)
{
int i, j, cluster_0, gic_id, ret;
unsigned int cpu, cluster, mask;
cpumask_t available_cpus;
/* First pass to validate what we have */
mask = 0;
for_each_online_cpu(i) {
cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0);
cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1);
if (cluster >= 2) {
pr_err("%s: only dual cluster systems are supported\n", __func__);
return -EINVAL;
}
if (WARN_ON(cpu >= MAX_CPUS_PER_CLUSTER))
return -EINVAL;
mask |= (1 << cluster);
}
if (mask != 3) {
pr_err("%s: no CPU pairing possible\n", __func__);
return -EINVAL;
}
/*
* Now let's do the pairing. We match each CPU with another CPU
* from a different cluster. To get a uniform scheduling behavior
* without fiddling with CPU topology and compute capacity data,
* we'll use logical CPUs initially belonging to the same cluster.
*/
memset(bL_switcher_cpu_pairing, -1, sizeof(bL_switcher_cpu_pairing));
cpumask_copy(&available_cpus, cpu_online_mask);
cluster_0 = -1;
for_each_cpu(i, &available_cpus) {
int match = -1;
cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1);
if (cluster_0 == -1)
cluster_0 = cluster;
if (cluster != cluster_0)
continue;
cpumask_clear_cpu(i, &available_cpus);
for_each_cpu(j, &available_cpus) {
cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(j), 1);
/*
* Let's remember the last match to create "odd"
* pairings on purpose in order for other code not
* to assume any relation between physical and
* logical CPU numbers.
*/
if (cluster != cluster_0)
match = j;
}
if (match != -1) {
bL_switcher_cpu_pairing[i] = match;
cpumask_clear_cpu(match, &available_cpus);
pr_info("CPU%d paired with CPU%d\n", i, match);
}
}
/*
* Now we disable the unwanted CPUs i.e. everything that has no
* pairing information (that includes the pairing counterparts).
*/
cpumask_clear(&bL_switcher_removed_logical_cpus);
for_each_online_cpu(i) {
cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0);
cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1);
/* Let's take note of the GIC ID for this CPU */
gic_id = gic_get_cpu_id(i);
if (gic_id < 0) {
pr_err("%s: bad GIC ID for CPU %d\n", __func__, i);
bL_switcher_restore_cpus();
return -EINVAL;
}
bL_gic_id[cpu][cluster] = gic_id;
pr_info("GIC ID for CPU %u cluster %u is %u\n",
cpu, cluster, gic_id);
if (bL_switcher_cpu_pairing[i] != -1) {
bL_switcher_cpu_original_cluster[i] = cluster;
continue;
}
ret = cpu_down(i);
if (ret) {
bL_switcher_restore_cpus();
return ret;
}
cpumask_set_cpu(i, &bL_switcher_removed_logical_cpus);
}
return 0;
}
/* Determine the logical CPU a given physical CPU is grouped on. */
int bL_switcher_get_logical_index(u32 mpidr)
{
int cpu;
if (!bL_switcher_active)
return -EUNATCH;
mpidr &= MPIDR_HWID_BITMASK;
for_each_online_cpu(cpu) {
int pairing = bL_switcher_cpu_pairing[cpu];
if (pairing == -1)
continue;
if ((mpidr == cpu_logical_map(cpu)) ||
(mpidr == cpu_logical_map(pairing)))
return cpu;
}
return -EINVAL;
}
static void bL_switcher_trace_trigger_cpu(void *__always_unused info)
{
trace_cpu_migrate_current(get_ns(), read_mpidr());
}
int bL_switcher_trace_trigger(void)
{
int ret;
preempt_disable();
bL_switcher_trace_trigger_cpu(NULL);
ret = smp_call_function(bL_switcher_trace_trigger_cpu, NULL, true);
preempt_enable();
return ret;
}
EXPORT_SYMBOL_GPL(bL_switcher_trace_trigger);
static int bL_switcher_enable(void)
{
int cpu, ret;
mutex_lock(&bL_switcher_activation_lock);
lock_device_hotplug();
if (bL_switcher_active) {
unlock_device_hotplug();
mutex_unlock(&bL_switcher_activation_lock);
return 0;
}
pr_info("big.LITTLE switcher initializing\n");
ret = bL_activation_notify(BL_NOTIFY_PRE_ENABLE);
if (ret)
goto error;
ret = bL_switcher_halve_cpus();
if (ret)
goto error;
bL_switcher_trace_trigger();
for_each_online_cpu(cpu) {
struct bL_thread *t = &bL_threads[cpu];
spin_lock_init(&t->lock);
init_waitqueue_head(&t->wq);
init_completion(&t->started);
t->wanted_cluster = -1;
t->task = bL_switcher_thread_create(cpu, t);
}
bL_switcher_active = 1;
bL_activation_notify(BL_NOTIFY_POST_ENABLE);
pr_info("big.LITTLE switcher initialized\n");
goto out;
error:
pr_warn("big.LITTLE switcher initialization failed\n");
bL_activation_notify(BL_NOTIFY_POST_DISABLE);
out:
unlock_device_hotplug();
mutex_unlock(&bL_switcher_activation_lock);
return ret;
}
#ifdef CONFIG_SYSFS
static void bL_switcher_disable(void)
{
unsigned int cpu, cluster;
struct bL_thread *t;
struct task_struct *task;
mutex_lock(&bL_switcher_activation_lock);
lock_device_hotplug();
if (!bL_switcher_active)
goto out;
if (bL_activation_notify(BL_NOTIFY_PRE_DISABLE) != 0) {
bL_activation_notify(BL_NOTIFY_POST_ENABLE);
goto out;
}
bL_switcher_active = 0;
/*
* To deactivate the switcher, we must shut down the switcher
* threads to prevent any other requests from being accepted.
* Then, if the final cluster for given logical CPU is not the
* same as the original one, we'll recreate a switcher thread
* just for the purpose of switching the CPU back without any
* possibility for interference from external requests.
*/
for_each_online_cpu(cpu) {
t = &bL_threads[cpu];
task = t->task;
t->task = NULL;
if (!task || IS_ERR(task))
continue;
kthread_stop(task);
/* no more switch may happen on this CPU at this point */
cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1);
if (cluster == bL_switcher_cpu_original_cluster[cpu])
continue;
init_completion(&t->started);
t->wanted_cluster = bL_switcher_cpu_original_cluster[cpu];
task = bL_switcher_thread_create(cpu, t);
if (!IS_ERR(task)) {
wait_for_completion(&t->started);
kthread_stop(task);
cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1);
if (cluster == bL_switcher_cpu_original_cluster[cpu])
continue;
}
/* If execution gets here, we're in trouble. */
pr_crit("%s: unable to restore original cluster for CPU %d\n",
__func__, cpu);
pr_crit("%s: CPU %d can't be restored\n",
__func__, bL_switcher_cpu_pairing[cpu]);
cpumask_clear_cpu(bL_switcher_cpu_pairing[cpu],
&bL_switcher_removed_logical_cpus);
}
bL_switcher_restore_cpus();
bL_switcher_trace_trigger();
bL_activation_notify(BL_NOTIFY_POST_DISABLE);
out:
unlock_device_hotplug();
mutex_unlock(&bL_switcher_activation_lock);
}
static ssize_t bL_switcher_active_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return sprintf(buf, "%u\n", bL_switcher_active);
}
static ssize_t bL_switcher_active_store(struct kobject *kobj,
struct kobj_attribute *attr, const char *buf, size_t count)
{
int ret;
switch (buf[0]) {
case '0':
bL_switcher_disable();
ret = 0;
break;
case '1':
ret = bL_switcher_enable();
break;
default:
ret = -EINVAL;
}
return (ret >= 0) ? count : ret;
}
static ssize_t bL_switcher_trace_trigger_store(struct kobject *kobj,
struct kobj_attribute *attr, const char *buf, size_t count)
{
int ret = bL_switcher_trace_trigger();
return ret ? ret : count;
}
static struct kobj_attribute bL_switcher_active_attr =
__ATTR(active, 0644, bL_switcher_active_show, bL_switcher_active_store);
static struct kobj_attribute bL_switcher_trace_trigger_attr =
__ATTR(trace_trigger, 0200, NULL, bL_switcher_trace_trigger_store);
static struct attribute *bL_switcher_attrs[] = {
&bL_switcher_active_attr.attr,
&bL_switcher_trace_trigger_attr.attr,
NULL,
};
static struct attribute_group bL_switcher_attr_group = {
.attrs = bL_switcher_attrs,
};
static struct kobject *bL_switcher_kobj;
static int __init bL_switcher_sysfs_init(void)
{
int ret;
bL_switcher_kobj = kobject_create_and_add("bL_switcher", kernel_kobj);
if (!bL_switcher_kobj)
return -ENOMEM;
ret = sysfs_create_group(bL_switcher_kobj, &bL_switcher_attr_group);
if (ret)
kobject_put(bL_switcher_kobj);
return ret;
}
#endif /* CONFIG_SYSFS */
bool bL_switcher_get_enabled(void)
{
mutex_lock(&bL_switcher_activation_lock);
return bL_switcher_active;
}
EXPORT_SYMBOL_GPL(bL_switcher_get_enabled);
void bL_switcher_put_enabled(void)
{
mutex_unlock(&bL_switcher_activation_lock);
}
EXPORT_SYMBOL_GPL(bL_switcher_put_enabled);
/*
* Veto any CPU hotplug operation on those CPUs we've removed
* while the switcher is active.
* We're just not ready to deal with that given the trickery involved.
*/
static int bL_switcher_hotplug_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
if (bL_switcher_active) {
int pairing = bL_switcher_cpu_pairing[(unsigned long)hcpu];
switch (action & 0xf) {
case CPU_UP_PREPARE:
case CPU_DOWN_PREPARE:
if (pairing == -1)
return NOTIFY_BAD;
}
}
return NOTIFY_DONE;
}
static bool no_bL_switcher;
core_param(no_bL_switcher, no_bL_switcher, bool, 0644);
static int __init bL_switcher_init(void)
{
int ret;
if (MAX_NR_CLUSTERS != 2) {
pr_err("%s: only dual cluster systems are supported\n", __func__);
return -EINVAL;
}
cpu_notifier(bL_switcher_hotplug_callback, 0);
if (!no_bL_switcher) {
ret = bL_switcher_enable();
if (ret)
return ret;
}
#ifdef CONFIG_SYSFS
ret = bL_switcher_sysfs_init();
if (ret)
pr_err("%s: unable to create sysfs entry\n", __func__);
#endif
return 0;
}
late_initcall(bL_switcher_init);

Просмотреть файл

@ -0,0 +1,71 @@
/*
* arch/arm/common/bL_switcher_dummy_if.c -- b.L switcher dummy interface
*
* Created by: Nicolas Pitre, November 2012
* Copyright: (C) 2012-2013 Linaro Limited
*
* Dummy interface to user space for debugging purpose only.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/init.h>
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/miscdevice.h>
#include <asm/uaccess.h>
#include <asm/bL_switcher.h>
static ssize_t bL_switcher_write(struct file *file, const char __user *buf,
size_t len, loff_t *pos)
{
unsigned char val[3];
unsigned int cpu, cluster;
int ret;
pr_debug("%s\n", __func__);
if (len < 3)
return -EINVAL;
if (copy_from_user(val, buf, 3))
return -EFAULT;
/* format: <cpu#>,<cluster#> */
if (val[0] < '0' || val[0] > '9' ||
val[1] != ',' ||
val[2] < '0' || val[2] > '1')
return -EINVAL;
cpu = val[0] - '0';
cluster = val[2] - '0';
ret = bL_switch_request(cpu, cluster);
return ret ? : len;
}
static const struct file_operations bL_switcher_fops = {
.write = bL_switcher_write,
.owner = THIS_MODULE,
};
static struct miscdevice bL_switcher_device = {
MISC_DYNAMIC_MINOR,
"b.L_switcher",
&bL_switcher_fops
};
static int __init bL_switcher_dummy_if_init(void)
{
return misc_register(&bL_switcher_device);
}
static void __exit bL_switcher_dummy_if_exit(void)
{
misc_deregister(&bL_switcher_device);
}
module_init(bL_switcher_dummy_if_init);
module_exit(bL_switcher_dummy_if_exit);

Просмотреть файл

@ -27,6 +27,18 @@ void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr)
sync_cache_w(&mcpm_entry_vectors[cluster][cpu]);
}
extern unsigned long mcpm_entry_early_pokes[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER][2];
void mcpm_set_early_poke(unsigned cpu, unsigned cluster,
unsigned long poke_phys_addr, unsigned long poke_val)
{
unsigned long *poke = &mcpm_entry_early_pokes[cluster][cpu][0];
poke[0] = poke_phys_addr;
poke[1] = poke_val;
__cpuc_flush_dcache_area((void *)poke, 8);
outer_clean_range(__pa(poke), __pa(poke + 2));
}
static const struct mcpm_platform_ops *platform_ops;
int __init mcpm_platform_register(const struct mcpm_platform_ops *ops)

Просмотреть файл

@ -15,6 +15,7 @@
#include <linux/linkage.h>
#include <asm/mcpm.h>
#include <asm/assembler.h>
#include "vlock.h"
@ -47,6 +48,7 @@
ENTRY(mcpm_entry_point)
ARM_BE8(setend be)
THUMB( adr r12, BSYM(1f) )
THUMB( bx r12 )
THUMB( .thumb )
@ -71,12 +73,19 @@ ENTRY(mcpm_entry_point)
* position independent way.
*/
adr r5, 3f
ldmia r5, {r6, r7, r8, r11}
ldmia r5, {r0, r6, r7, r8, r11}
add r0, r5, r0 @ r0 = mcpm_entry_early_pokes
add r6, r5, r6 @ r6 = mcpm_entry_vectors
ldr r7, [r5, r7] @ r7 = mcpm_power_up_setup_phys
add r8, r5, r8 @ r8 = mcpm_sync
add r11, r5, r11 @ r11 = first_man_locks
@ Perform an early poke, if any
add r0, r0, r4, lsl #3
ldmia r0, {r0, r1}
teq r0, #0
strne r1, [r0]
mov r0, #MCPM_SYNC_CLUSTER_SIZE
mla r8, r0, r10, r8 @ r8 = sync cluster base
@ -195,7 +204,8 @@ mcpm_entry_gated:
.align 2
3: .word mcpm_entry_vectors - .
3: .word mcpm_entry_early_pokes - .
.word mcpm_entry_vectors - 3b
.word mcpm_power_up_setup_phys - 3b
.word mcpm_sync - 3b
.word first_man_locks - 3b
@ -214,6 +224,10 @@ first_man_locks:
ENTRY(mcpm_entry_vectors)
.space 4 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER
.type mcpm_entry_early_pokes, #object
ENTRY(mcpm_entry_early_pokes)
.space 8 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER
.type mcpm_power_up_setup_phys, #object
ENTRY(mcpm_power_up_setup_phys)
.space 4 @ set by mcpm_sync_init()

1
arch/arm/crypto/.gitignore поставляемый Normal file
Просмотреть файл

@ -0,0 +1 @@
aesbs-core.S

Просмотреть файл

@ -3,7 +3,17 @@
#
obj-$(CONFIG_CRYPTO_AES_ARM) += aes-arm.o
obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
aes-arm-y := aes-armv4.o aes_glue.o
sha1-arm-y := sha1-armv4-large.o sha1_glue.o
aes-arm-y := aes-armv4.o aes_glue.o
aes-arm-bs-y := aesbs-core.o aesbs-glue.o
sha1-arm-y := sha1-armv4-large.o sha1_glue.o
quiet_cmd_perl = PERL $@
cmd_perl = $(PERL) $(<) > $(@)
$(src)/aesbs-core.S_shipped: $(src)/bsaes-armv7.pl
$(call cmd,perl)
.PRECIOUS: $(obj)/aesbs-core.S

Просмотреть файл

@ -6,22 +6,12 @@
#include <linux/crypto.h>
#include <crypto/aes.h>
#define AES_MAXNR 14
#include "aes_glue.h"
typedef struct {
unsigned int rd_key[4 *(AES_MAXNR + 1)];
int rounds;
} AES_KEY;
struct AES_CTX {
AES_KEY enc_key;
AES_KEY dec_key;
};
asmlinkage void AES_encrypt(const u8 *in, u8 *out, AES_KEY *ctx);
asmlinkage void AES_decrypt(const u8 *in, u8 *out, AES_KEY *ctx);
asmlinkage int private_AES_set_decrypt_key(const unsigned char *userKey, const int bits, AES_KEY *key);
asmlinkage int private_AES_set_encrypt_key(const unsigned char *userKey, const int bits, AES_KEY *key);
EXPORT_SYMBOL(AES_encrypt);
EXPORT_SYMBOL(AES_decrypt);
EXPORT_SYMBOL(private_AES_set_encrypt_key);
EXPORT_SYMBOL(private_AES_set_decrypt_key);
static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
{
@ -81,7 +71,7 @@ static struct crypto_alg aes_alg = {
.cipher = {
.cia_min_keysize = AES_MIN_KEY_SIZE,
.cia_max_keysize = AES_MAX_KEY_SIZE,
.cia_setkey = aes_set_key,
.cia_setkey = aes_set_key,
.cia_encrypt = aes_encrypt,
.cia_decrypt = aes_decrypt
}

Просмотреть файл

@ -0,0 +1,19 @@
#define AES_MAXNR 14
struct AES_KEY {
unsigned int rd_key[4 * (AES_MAXNR + 1)];
int rounds;
};
struct AES_CTX {
struct AES_KEY enc_key;
struct AES_KEY dec_key;
};
asmlinkage void AES_encrypt(const u8 *in, u8 *out, struct AES_KEY *ctx);
asmlinkage void AES_decrypt(const u8 *in, u8 *out, struct AES_KEY *ctx);
asmlinkage int private_AES_set_decrypt_key(const unsigned char *userKey,
const int bits, struct AES_KEY *key);
asmlinkage int private_AES_set_encrypt_key(const unsigned char *userKey,
const int bits, struct AES_KEY *key);

Разница между файлами не показана из-за своего большого размера Загрузить разницу

Просмотреть файл

@ -0,0 +1,434 @@
/*
* linux/arch/arm/crypto/aesbs-glue.c - glue code for NEON bit sliced AES
*
* Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <asm/neon.h>
#include <crypto/aes.h>
#include <crypto/ablk_helper.h>
#include <crypto/algapi.h>
#include <linux/module.h>
#include "aes_glue.h"
#define BIT_SLICED_KEY_MAXSIZE (128 * (AES_MAXNR - 1) + 2 * AES_BLOCK_SIZE)
struct BS_KEY {
struct AES_KEY rk;
int converted;
u8 __aligned(8) bs[BIT_SLICED_KEY_MAXSIZE];
} __aligned(8);
asmlinkage void bsaes_enc_key_convert(u8 out[], struct AES_KEY const *in);
asmlinkage void bsaes_dec_key_convert(u8 out[], struct AES_KEY const *in);
asmlinkage void bsaes_cbc_encrypt(u8 const in[], u8 out[], u32 bytes,
struct BS_KEY *key, u8 iv[]);
asmlinkage void bsaes_ctr32_encrypt_blocks(u8 const in[], u8 out[], u32 blocks,
struct BS_KEY *key, u8 const iv[]);
asmlinkage void bsaes_xts_encrypt(u8 const in[], u8 out[], u32 bytes,
struct BS_KEY *key, u8 tweak[]);
asmlinkage void bsaes_xts_decrypt(u8 const in[], u8 out[], u32 bytes,
struct BS_KEY *key, u8 tweak[]);
struct aesbs_cbc_ctx {
struct AES_KEY enc;
struct BS_KEY dec;
};
struct aesbs_ctr_ctx {
struct BS_KEY enc;
};
struct aesbs_xts_ctx {
struct BS_KEY enc;
struct BS_KEY dec;
struct AES_KEY twkey;
};
static int aesbs_cbc_set_key(struct crypto_tfm *tfm, const u8 *in_key,
unsigned int key_len)
{
struct aesbs_cbc_ctx *ctx = crypto_tfm_ctx(tfm);
int bits = key_len * 8;
if (private_AES_set_encrypt_key(in_key, bits, &ctx->enc)) {
tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
return -EINVAL;
}
ctx->dec.rk = ctx->enc;
private_AES_set_decrypt_key(in_key, bits, &ctx->dec.rk);
ctx->dec.converted = 0;
return 0;
}
static int aesbs_ctr_set_key(struct crypto_tfm *tfm, const u8 *in_key,
unsigned int key_len)
{
struct aesbs_ctr_ctx *ctx = crypto_tfm_ctx(tfm);
int bits = key_len * 8;
if (private_AES_set_encrypt_key(in_key, bits, &ctx->enc.rk)) {
tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
return -EINVAL;
}
ctx->enc.converted = 0;
return 0;
}
static int aesbs_xts_set_key(struct crypto_tfm *tfm, const u8 *in_key,
unsigned int key_len)
{
struct aesbs_xts_ctx *ctx = crypto_tfm_ctx(tfm);
int bits = key_len * 4;
if (private_AES_set_encrypt_key(in_key, bits, &ctx->enc.rk)) {
tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
return -EINVAL;
}
ctx->dec.rk = ctx->enc.rk;
private_AES_set_decrypt_key(in_key, bits, &ctx->dec.rk);
private_AES_set_encrypt_key(in_key + key_len / 2, bits, &ctx->twkey);
ctx->enc.converted = ctx->dec.converted = 0;
return 0;
}
static int aesbs_cbc_encrypt(struct blkcipher_desc *desc,
struct scatterlist *dst,
struct scatterlist *src, unsigned int nbytes)
{
struct aesbs_cbc_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
int err;
blkcipher_walk_init(&walk, dst, src, nbytes);
err = blkcipher_walk_virt(desc, &walk);
while (walk.nbytes) {
u32 blocks = walk.nbytes / AES_BLOCK_SIZE;
u8 *src = walk.src.virt.addr;
if (walk.dst.virt.addr == walk.src.virt.addr) {
u8 *iv = walk.iv;
do {
crypto_xor(src, iv, AES_BLOCK_SIZE);
AES_encrypt(src, src, &ctx->enc);
iv = src;
src += AES_BLOCK_SIZE;
} while (--blocks);
memcpy(walk.iv, iv, AES_BLOCK_SIZE);
} else {
u8 *dst = walk.dst.virt.addr;
do {
crypto_xor(walk.iv, src, AES_BLOCK_SIZE);
AES_encrypt(walk.iv, dst, &ctx->enc);
memcpy(walk.iv, dst, AES_BLOCK_SIZE);
src += AES_BLOCK_SIZE;
dst += AES_BLOCK_SIZE;
} while (--blocks);
}
err = blkcipher_walk_done(desc, &walk, 0);
}
return err;
}
static int aesbs_cbc_decrypt(struct blkcipher_desc *desc,
struct scatterlist *dst,
struct scatterlist *src, unsigned int nbytes)
{
struct aesbs_cbc_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
int err;
blkcipher_walk_init(&walk, dst, src, nbytes);
err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE);
while ((walk.nbytes / AES_BLOCK_SIZE) >= 8) {
kernel_neon_begin();
bsaes_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
walk.nbytes, &ctx->dec, walk.iv);
kernel_neon_end();
err = blkcipher_walk_done(desc, &walk, 0);
}
while (walk.nbytes) {
u32 blocks = walk.nbytes / AES_BLOCK_SIZE;
u8 *dst = walk.dst.virt.addr;
u8 *src = walk.src.virt.addr;
u8 bk[2][AES_BLOCK_SIZE];
u8 *iv = walk.iv;
do {
if (walk.dst.virt.addr == walk.src.virt.addr)
memcpy(bk[blocks & 1], src, AES_BLOCK_SIZE);
AES_decrypt(src, dst, &ctx->dec.rk);
crypto_xor(dst, iv, AES_BLOCK_SIZE);
if (walk.dst.virt.addr == walk.src.virt.addr)
iv = bk[blocks & 1];
else
iv = src;
dst += AES_BLOCK_SIZE;
src += AES_BLOCK_SIZE;
} while (--blocks);
err = blkcipher_walk_done(desc, &walk, 0);
}
return err;
}
static void inc_be128_ctr(__be32 ctr[], u32 addend)
{
int i;
for (i = 3; i >= 0; i--, addend = 1) {
u32 n = be32_to_cpu(ctr[i]) + addend;
ctr[i] = cpu_to_be32(n);
if (n >= addend)
break;
}
}
static int aesbs_ctr_encrypt(struct blkcipher_desc *desc,
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes)
{
struct aesbs_ctr_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
u32 blocks;
int err;
blkcipher_walk_init(&walk, dst, src, nbytes);
err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE);
while ((blocks = walk.nbytes / AES_BLOCK_SIZE)) {
u32 tail = walk.nbytes % AES_BLOCK_SIZE;
__be32 *ctr = (__be32 *)walk.iv;
u32 headroom = UINT_MAX - be32_to_cpu(ctr[3]);
/* avoid 32 bit counter overflow in the NEON code */
if (unlikely(headroom < blocks)) {
blocks = headroom + 1;
tail = walk.nbytes - blocks * AES_BLOCK_SIZE;
}
kernel_neon_begin();
bsaes_ctr32_encrypt_blocks(walk.src.virt.addr,
walk.dst.virt.addr, blocks,
&ctx->enc, walk.iv);
kernel_neon_end();
inc_be128_ctr(ctr, blocks);
nbytes -= blocks * AES_BLOCK_SIZE;
if (nbytes && nbytes == tail && nbytes <= AES_BLOCK_SIZE)
break;
err = blkcipher_walk_done(desc, &walk, tail);
}
if (walk.nbytes) {
u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
u8 ks[AES_BLOCK_SIZE];
AES_encrypt(walk.iv, ks, &ctx->enc.rk);
if (tdst != tsrc)
memcpy(tdst, tsrc, nbytes);
crypto_xor(tdst, ks, nbytes);
err = blkcipher_walk_done(desc, &walk, 0);
}
return err;
}
static int aesbs_xts_encrypt(struct blkcipher_desc *desc,
struct scatterlist *dst,
struct scatterlist *src, unsigned int nbytes)
{
struct aesbs_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
int err;
blkcipher_walk_init(&walk, dst, src, nbytes);
err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE);
/* generate the initial tweak */
AES_encrypt(walk.iv, walk.iv, &ctx->twkey);
while (walk.nbytes) {
kernel_neon_begin();
bsaes_xts_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
walk.nbytes, &ctx->enc, walk.iv);
kernel_neon_end();
err = blkcipher_walk_done(desc, &walk, 0);
}
return err;
}
static int aesbs_xts_decrypt(struct blkcipher_desc *desc,
struct scatterlist *dst,
struct scatterlist *src, unsigned int nbytes)
{
struct aesbs_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
int err;
blkcipher_walk_init(&walk, dst, src, nbytes);
err = blkcipher_walk_virt_block(desc, &walk, 8 * AES_BLOCK_SIZE);
/* generate the initial tweak */
AES_encrypt(walk.iv, walk.iv, &ctx->twkey);
while (walk.nbytes) {
kernel_neon_begin();
bsaes_xts_decrypt(walk.src.virt.addr, walk.dst.virt.addr,
walk.nbytes, &ctx->dec, walk.iv);
kernel_neon_end();
err = blkcipher_walk_done(desc, &walk, 0);
}
return err;
}
static struct crypto_alg aesbs_algs[] = { {
.cra_name = "__cbc-aes-neonbs",
.cra_driver_name = "__driver-cbc-aes-neonbs",
.cra_priority = 0,
.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct aesbs_cbc_ctx),
.cra_alignmask = 7,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
.cra_blkcipher = {
.min_keysize = AES_MIN_KEY_SIZE,
.max_keysize = AES_MAX_KEY_SIZE,
.ivsize = AES_BLOCK_SIZE,
.setkey = aesbs_cbc_set_key,
.encrypt = aesbs_cbc_encrypt,
.decrypt = aesbs_cbc_decrypt,
},
}, {
.cra_name = "__ctr-aes-neonbs",
.cra_driver_name = "__driver-ctr-aes-neonbs",
.cra_priority = 0,
.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
.cra_blocksize = 1,
.cra_ctxsize = sizeof(struct aesbs_ctr_ctx),
.cra_alignmask = 7,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
.cra_blkcipher = {
.min_keysize = AES_MIN_KEY_SIZE,
.max_keysize = AES_MAX_KEY_SIZE,
.ivsize = AES_BLOCK_SIZE,
.setkey = aesbs_ctr_set_key,
.encrypt = aesbs_ctr_encrypt,
.decrypt = aesbs_ctr_encrypt,
},
}, {
.cra_name = "__xts-aes-neonbs",
.cra_driver_name = "__driver-xts-aes-neonbs",
.cra_priority = 0,
.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct aesbs_xts_ctx),
.cra_alignmask = 7,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
.cra_blkcipher = {
.min_keysize = 2 * AES_MIN_KEY_SIZE,
.max_keysize = 2 * AES_MAX_KEY_SIZE,
.ivsize = AES_BLOCK_SIZE,
.setkey = aesbs_xts_set_key,
.encrypt = aesbs_xts_encrypt,
.decrypt = aesbs_xts_decrypt,
},
}, {
.cra_name = "cbc(aes)",
.cra_driver_name = "cbc-aes-neonbs",
.cra_priority = 300,
.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct async_helper_ctx),
.cra_alignmask = 7,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_ablkcipher = {
.min_keysize = AES_MIN_KEY_SIZE,
.max_keysize = AES_MAX_KEY_SIZE,
.ivsize = AES_BLOCK_SIZE,
.setkey = ablk_set_key,
.encrypt = __ablk_encrypt,
.decrypt = ablk_decrypt,
}
}, {
.cra_name = "ctr(aes)",
.cra_driver_name = "ctr-aes-neonbs",
.cra_priority = 300,
.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
.cra_blocksize = 1,
.cra_ctxsize = sizeof(struct async_helper_ctx),
.cra_alignmask = 7,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_ablkcipher = {
.min_keysize = AES_MIN_KEY_SIZE,
.max_keysize = AES_MAX_KEY_SIZE,
.ivsize = AES_BLOCK_SIZE,
.setkey = ablk_set_key,
.encrypt = ablk_encrypt,
.decrypt = ablk_decrypt,
}
}, {
.cra_name = "xts(aes)",
.cra_driver_name = "xts-aes-neonbs",
.cra_priority = 300,
.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct async_helper_ctx),
.cra_alignmask = 7,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_ablkcipher = {
.min_keysize = 2 * AES_MIN_KEY_SIZE,
.max_keysize = 2 * AES_MAX_KEY_SIZE,
.ivsize = AES_BLOCK_SIZE,
.setkey = ablk_set_key,
.encrypt = ablk_encrypt,
.decrypt = ablk_decrypt,
}
} };
static int __init aesbs_mod_init(void)
{
if (!cpu_has_neon())
return -ENODEV;
return crypto_register_algs(aesbs_algs, ARRAY_SIZE(aesbs_algs));
}
static void __exit aesbs_mod_exit(void)
{
crypto_unregister_algs(aesbs_algs, ARRAY_SIZE(aesbs_algs));
}
module_init(aesbs_mod_init);
module_exit(aesbs_mod_exit);
MODULE_DESCRIPTION("Bit sliced AES in CBC/CTR/XTS modes using NEON");
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_LICENSE("GPL");

Разница между файлами не показана из-за своего большого размера Загрузить разницу

Просмотреть файл

@ -24,6 +24,7 @@ generic-y += sembuf.h
generic-y += serial.h
generic-y += shmbuf.h
generic-y += siginfo.h
generic-y += simd.h
generic-y += sizes.h
generic-y += socket.h
generic-y += sockios.h

Просмотреть файл

@ -53,6 +53,13 @@
#define put_byte_3 lsl #0
#endif
/* Select code for any configuration running in BE8 mode */
#ifdef CONFIG_CPU_ENDIAN_BE8
#define ARM_BE8(code...) code
#else
#define ARM_BE8(code...)
#endif
/*
* Data preload for architectures that support it
*/

Просмотреть файл

@ -12,6 +12,7 @@
#define __ASM_ARM_ATOMIC_H
#include <linux/compiler.h>
#include <linux/prefetch.h>
#include <linux/types.h>
#include <linux/irqflags.h>
#include <asm/barrier.h>
@ -41,6 +42,7 @@ static inline void atomic_add(int i, atomic_t *v)
unsigned long tmp;
int result;
prefetchw(&v->counter);
__asm__ __volatile__("@ atomic_add\n"
"1: ldrex %0, [%3]\n"
" add %0, %0, %4\n"
@ -79,6 +81,7 @@ static inline void atomic_sub(int i, atomic_t *v)
unsigned long tmp;
int result;
prefetchw(&v->counter);
__asm__ __volatile__("@ atomic_sub\n"
"1: ldrex %0, [%3]\n"
" sub %0, %0, %4\n"
@ -260,6 +263,7 @@ static inline void atomic64_set(atomic64_t *v, long long i)
{
long long tmp;
prefetchw(&v->counter);
__asm__ __volatile__("@ atomic64_set\n"
"1: ldrexd %0, %H0, [%2]\n"
" strexd %0, %3, %H3, [%2]\n"
@ -276,10 +280,11 @@ static inline void atomic64_add(long long i, atomic64_t *v)
long long result;
unsigned long tmp;
prefetchw(&v->counter);
__asm__ __volatile__("@ atomic64_add\n"
"1: ldrexd %0, %H0, [%3]\n"
" adds %0, %0, %4\n"
" adc %H0, %H0, %H4\n"
" adds %Q0, %Q0, %Q4\n"
" adc %R0, %R0, %R4\n"
" strexd %1, %0, %H0, [%3]\n"
" teq %1, #0\n"
" bne 1b"
@ -297,8 +302,8 @@ static inline long long atomic64_add_return(long long i, atomic64_t *v)
__asm__ __volatile__("@ atomic64_add_return\n"
"1: ldrexd %0, %H0, [%3]\n"
" adds %0, %0, %4\n"
" adc %H0, %H0, %H4\n"
" adds %Q0, %Q0, %Q4\n"
" adc %R0, %R0, %R4\n"
" strexd %1, %0, %H0, [%3]\n"
" teq %1, #0\n"
" bne 1b"
@ -316,10 +321,11 @@ static inline void atomic64_sub(long long i, atomic64_t *v)
long long result;
unsigned long tmp;
prefetchw(&v->counter);
__asm__ __volatile__("@ atomic64_sub\n"
"1: ldrexd %0, %H0, [%3]\n"
" subs %0, %0, %4\n"
" sbc %H0, %H0, %H4\n"
" subs %Q0, %Q0, %Q4\n"
" sbc %R0, %R0, %R4\n"
" strexd %1, %0, %H0, [%3]\n"
" teq %1, #0\n"
" bne 1b"
@ -337,8 +343,8 @@ static inline long long atomic64_sub_return(long long i, atomic64_t *v)
__asm__ __volatile__("@ atomic64_sub_return\n"
"1: ldrexd %0, %H0, [%3]\n"
" subs %0, %0, %4\n"
" sbc %H0, %H0, %H4\n"
" subs %Q0, %Q0, %Q4\n"
" sbc %R0, %R0, %R4\n"
" strexd %1, %0, %H0, [%3]\n"
" teq %1, #0\n"
" bne 1b"
@ -406,9 +412,9 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
__asm__ __volatile__("@ atomic64_dec_if_positive\n"
"1: ldrexd %0, %H0, [%3]\n"
" subs %0, %0, #1\n"
" sbc %H0, %H0, #0\n"
" teq %H0, #0\n"
" subs %Q0, %Q0, #1\n"
" sbc %R0, %R0, #0\n"
" teq %R0, #0\n"
" bmi 2f\n"
" strexd %1, %0, %H0, [%3]\n"
" teq %1, #0\n"
@ -437,8 +443,8 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
" teqeq %H0, %H5\n"
" moveq %1, #0\n"
" beq 2f\n"
" adds %0, %0, %6\n"
" adc %H0, %H0, %H6\n"
" adds %Q0, %Q0, %Q6\n"
" adc %R0, %R0, %R6\n"
" strexd %2, %0, %H0, [%4]\n"
" teq %2, #0\n"
" bne 1b\n"

Просмотреть файл

@ -0,0 +1,77 @@
/*
* arch/arm/include/asm/bL_switcher.h
*
* Created by: Nicolas Pitre, April 2012
* Copyright: (C) 2012-2013 Linaro Limited
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#ifndef ASM_BL_SWITCHER_H
#define ASM_BL_SWITCHER_H
#include <linux/compiler.h>
#include <linux/types.h>
typedef void (*bL_switch_completion_handler)(void *cookie);
int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id,
bL_switch_completion_handler completer,
void *completer_cookie);
static inline int bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
{
return bL_switch_request_cb(cpu, new_cluster_id, NULL, NULL);
}
/*
* Register here to be notified about runtime enabling/disabling of
* the switcher.
*
* The notifier chain is called with the switcher activation lock held:
* the switcher will not be enabled or disabled during callbacks.
* Callbacks must not call bL_switcher_{get,put}_enabled().
*/
#define BL_NOTIFY_PRE_ENABLE 0
#define BL_NOTIFY_POST_ENABLE 1
#define BL_NOTIFY_PRE_DISABLE 2
#define BL_NOTIFY_POST_DISABLE 3
#ifdef CONFIG_BL_SWITCHER
int bL_switcher_register_notifier(struct notifier_block *nb);
int bL_switcher_unregister_notifier(struct notifier_block *nb);
/*
* Use these functions to temporarily prevent enabling/disabling of
* the switcher.
* bL_switcher_get_enabled() returns true if the switcher is currently
* enabled. Each call to bL_switcher_get_enabled() must be followed
* by a call to bL_switcher_put_enabled(). These functions are not
* recursive.
*/
bool bL_switcher_get_enabled(void);
void bL_switcher_put_enabled(void);
int bL_switcher_trace_trigger(void);
int bL_switcher_get_logical_index(u32 mpidr);
#else
static inline int bL_switcher_register_notifier(struct notifier_block *nb)
{
return 0;
}
static inline int bL_switcher_unregister_notifier(struct notifier_block *nb)
{
return 0;
}
static inline bool bL_switcher_get_enabled(void) { return false; }
static inline void bL_switcher_put_enabled(void) { }
static inline int bL_switcher_trace_trigger(void) { return 0; }
static inline int bL_switcher_get_logical_index(u32 mpidr) { return -EUNATCH; }
#endif /* CONFIG_BL_SWITCHER */
#endif

Просмотреть файл

@ -2,6 +2,8 @@
#define _ASMARM_BUG_H
#include <linux/linkage.h>
#include <linux/types.h>
#include <asm/opcodes.h>
#ifdef CONFIG_BUG
@ -12,10 +14,10 @@
*/
#ifdef CONFIG_THUMB2_KERNEL
#define BUG_INSTR_VALUE 0xde02
#define BUG_INSTR_TYPE ".hword "
#define BUG_INSTR(__value) __inst_thumb16(__value)
#else
#define BUG_INSTR_VALUE 0xe7f001f2
#define BUG_INSTR_TYPE ".word "
#define BUG_INSTR(__value) __inst_arm(__value)
#endif
@ -33,7 +35,7 @@
#define __BUG(__file, __line, __value) \
do { \
asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n" \
asm volatile("1:\t" BUG_INSTR(__value) "\n" \
".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \
"2:\t.asciz " #__file "\n" \
".popsection\n" \
@ -48,7 +50,7 @@ do { \
#define __BUG(__file, __line, __value) \
do { \
asm volatile(BUG_INSTR_TYPE #__value); \
asm volatile(BUG_INSTR(__value) "\n"); \
unreachable(); \
} while (0)
#endif /* CONFIG_DEBUG_BUGVERBOSE */

Просмотреть файл

@ -5,7 +5,7 @@
#include <linux/threads.h>
#include <asm/irq.h>
#define NR_IPI 7
#define NR_IPI 8
typedef struct {
unsigned int __softirq_pending;

Просмотреть файл

@ -24,8 +24,8 @@
#define TRACER_TIMEOUT 10000
#define etm_writel(t, v, x) \
(__raw_writel((v), (t)->etm_regs + (x)))
#define etm_readl(t, x) (__raw_readl((t)->etm_regs + (x)))
(writel_relaxed((v), (t)->etm_regs + (x)))
#define etm_readl(t, x) (readl_relaxed((t)->etm_regs + (x)))
/* CoreSight Management Registers */
#define CSMR_LOCKACCESS 0xfb0
@ -142,8 +142,8 @@
#define ETBFF_TRIGFL BIT(10)
#define etb_writel(t, v, x) \
(__raw_writel((v), (t)->etb_regs + (x)))
#define etb_readl(t, x) (__raw_readl((t)->etb_regs + (x)))
(writel_relaxed((v), (t)->etb_regs + (x)))
#define etb_readl(t, x) (readl_relaxed((t)->etb_regs + (x)))
#define etm_lock(t) do { etm_writel((t), 0, CSMR_LOCKACCESS); } while (0)
#define etm_unlock(t) \

Просмотреть файл

@ -11,6 +11,7 @@
#define __ARM_KGDB_H__
#include <linux/ptrace.h>
#include <asm/opcodes.h>
/*
* GDB assumes that we're a user process being debugged, so
@ -41,7 +42,7 @@
static inline void arch_kgdb_breakpoint(void)
{
asm(".word 0xe7ffdeff");
asm(__inst_arm(0xe7ffdeff));
}
extern void kgdb_handle_bus_error(void);

Просмотреть файл

@ -49,6 +49,7 @@ struct machine_desc {
bool (*smp_init)(void);
void (*fixup)(struct tag *, char **,
struct meminfo *);
void (*init_meminfo)(void);
void (*reserve)(void);/* reserve mem blocks */
void (*map_io)(void);/* IO mapping function */
void (*init_early)(void);

Просмотреть файл

@ -41,6 +41,14 @@ extern void mcpm_entry_point(void);
*/
void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr);
/*
* This sets an early poke i.e a value to be poked into some address
* from very early assembly code before the CPU is ungated. The
* address must be physical, and if 0 then nothing will happen.
*/
void mcpm_set_early_poke(unsigned cpu, unsigned cluster,
unsigned long poke_phys_addr, unsigned long poke_val);
/*
* CPU/cluster power operations API for higher subsystems to use.
*/

Просмотреть файл

@ -172,8 +172,13 @@
* so that all we need to do is modify the 8-bit constant field.
*/
#define __PV_BITS_31_24 0x81000000
#define __PV_BITS_7_0 0x81
extern u64 __pv_phys_offset;
extern u64 __pv_offset;
extern void fixup_pv_table(const void *, unsigned long);
extern const void *__pv_table_begin, *__pv_table_end;
extern unsigned long __pv_phys_offset;
#define PHYS_OFFSET __pv_phys_offset
#define __pv_stub(from,to,instr,type) \
@ -185,22 +190,58 @@ extern unsigned long __pv_phys_offset;
: "=r" (to) \
: "r" (from), "I" (type))
static inline unsigned long __virt_to_phys(unsigned long x)
#define __pv_stub_mov_hi(t) \
__asm__ volatile("@ __pv_stub_mov\n" \
"1: mov %R0, %1\n" \
" .pushsection .pv_table,\"a\"\n" \
" .long 1b\n" \
" .popsection\n" \
: "=r" (t) \
: "I" (__PV_BITS_7_0))
#define __pv_add_carry_stub(x, y) \
__asm__ volatile("@ __pv_add_carry_stub\n" \
"1: adds %Q0, %1, %2\n" \
" adc %R0, %R0, #0\n" \
" .pushsection .pv_table,\"a\"\n" \
" .long 1b\n" \
" .popsection\n" \
: "+r" (y) \
: "r" (x), "I" (__PV_BITS_31_24) \
: "cc")
static inline phys_addr_t __virt_to_phys(unsigned long x)
{
unsigned long t;
__pv_stub(x, t, "add", __PV_BITS_31_24);
phys_addr_t t;
if (sizeof(phys_addr_t) == 4) {
__pv_stub(x, t, "add", __PV_BITS_31_24);
} else {
__pv_stub_mov_hi(t);
__pv_add_carry_stub(x, t);
}
return t;
}
static inline unsigned long __phys_to_virt(unsigned long x)
static inline unsigned long __phys_to_virt(phys_addr_t x)
{
unsigned long t;
__pv_stub(x, t, "sub", __PV_BITS_31_24);
return t;
}
#else
#define __virt_to_phys(x) ((x) - PAGE_OFFSET + PHYS_OFFSET)
#define __phys_to_virt(x) ((x) - PHYS_OFFSET + PAGE_OFFSET)
static inline phys_addr_t __virt_to_phys(unsigned long x)
{
return (phys_addr_t)x - PAGE_OFFSET + PHYS_OFFSET;
}
static inline unsigned long __phys_to_virt(phys_addr_t x)
{
return x - PHYS_OFFSET + PAGE_OFFSET;
}
#endif
#endif
#endif /* __ASSEMBLY__ */
@ -238,16 +279,33 @@ static inline phys_addr_t virt_to_phys(const volatile void *x)
static inline void *phys_to_virt(phys_addr_t x)
{
return (void *)(__phys_to_virt((unsigned long)(x)));
return (void *)__phys_to_virt(x);
}
/*
* Drivers should NOT use these either.
*/
#define __pa(x) __virt_to_phys((unsigned long)(x))
#define __va(x) ((void *)__phys_to_virt((unsigned long)(x)))
#define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x)))
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x);
/*
* These are for systems that have a hardware interconnect supported alias of
* physical memory for idmap purposes. Most cases should leave these
* untouched.
*/
static inline phys_addr_t __virt_to_idmap(unsigned long x)
{
if (arch_virt_to_idmap)
return arch_virt_to_idmap(x);
else
return __virt_to_phys(x);
}
#define virt_to_idmap(x) __virt_to_idmap((unsigned long)(x))
/*
* Virtual <-> DMA view memory address translations
* Again, these are *only* valid on the kernel direct mapped RAM

Просмотреть файл

@ -16,7 +16,7 @@ typedef struct {
#ifdef CONFIG_CPU_HAS_ASID
#define ASID_BITS 8
#define ASID_MASK ((~0ULL) << ASID_BITS)
#define ASID(mm) ((mm)->context.id.counter & ~ASID_MASK)
#define ASID(mm) ((unsigned int)((mm)->context.id.counter & ~ASID_MASK))
#else
#define ASID(mm) (0)
#endif

Просмотреть файл

@ -22,6 +22,7 @@
#include <asm/hw_breakpoint.h>
#include <asm/ptrace.h>
#include <asm/types.h>
#include <asm/unified.h>
#ifdef __KERNEL__
#define STACK_TOP ((current->personality & ADDR_LIMIT_32BIT) ? \
@ -87,6 +88,17 @@ unsigned long get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) task_pt_regs(tsk)->ARM_pc
#define KSTK_ESP(tsk) task_pt_regs(tsk)->ARM_sp
#ifdef CONFIG_SMP
#define __ALT_SMP_ASM(smp, up) \
"9998: " smp "\n" \
" .pushsection \".alt.smp.init\", \"a\"\n" \
" .long 9998b\n" \
" " up "\n" \
" .popsection\n"
#else
#define __ALT_SMP_ASM(smp, up) up
#endif
/*
* Prefetching support - only ARMv5.
*/
@ -97,17 +109,22 @@ static inline void prefetch(const void *ptr)
{
__asm__ __volatile__(
"pld\t%a0"
:
: "p" (ptr)
: "cc");
:: "p" (ptr));
}
#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
#define ARCH_HAS_PREFETCHW
#define prefetchw(ptr) prefetch(ptr)
#define ARCH_HAS_SPINLOCK_PREFETCH
#define spin_lock_prefetch(x) do { } while (0)
static inline void prefetchw(const void *ptr)
{
__asm__ __volatile__(
".arch_extension mp\n"
__ALT_SMP_ASM(
WASM(pldw) "\t%a0",
WASM(pld) "\t%a0"
)
:: "p" (ptr));
}
#endif
#endif
#define HAVE_ARCH_PICK_MMAP_LAYOUT

Просмотреть файл

@ -84,6 +84,8 @@ extern void arch_send_call_function_single_ipi(int cpu);
extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask);
extern int register_ipi_completion(struct completion *completion, int cpu);
struct smp_operations {
#ifdef CONFIG_SMP
/*

Просмотреть файл

@ -5,21 +5,13 @@
#error SMP not supported on pre-ARMv6 CPUs
#endif
#include <asm/processor.h>
#include <linux/prefetch.h>
/*
* sev and wfe are ARMv6K extensions. Uniprocessor ARMv6 may not have the K
* extensions, so when running on UP, we have to patch these instructions away.
*/
#define ALT_SMP(smp, up) \
"9998: " smp "\n" \
" .pushsection \".alt.smp.init\", \"a\"\n" \
" .long 9998b\n" \
" " up "\n" \
" .popsection\n"
#ifdef CONFIG_THUMB2_KERNEL
#define SEV ALT_SMP("sev.w", "nop.w")
/*
* For Thumb-2, special care is needed to ensure that the conditional WFE
* instruction really does assemble to exactly 4 bytes (as required by
@ -31,17 +23,18 @@
* the assembler won't change IT instructions which are explicitly present
* in the input.
*/
#define WFE(cond) ALT_SMP( \
#define WFE(cond) __ALT_SMP_ASM( \
"it " cond "\n\t" \
"wfe" cond ".n", \
\
"nop.w" \
)
#else
#define SEV ALT_SMP("sev", "nop")
#define WFE(cond) ALT_SMP("wfe" cond, "nop")
#define WFE(cond) __ALT_SMP_ASM("wfe" cond, "nop")
#endif
#define SEV __ALT_SMP_ASM(WASM(sev), WASM(nop))
static inline void dsb_sev(void)
{
#if __LINUX_ARM_ARCH__ >= 7
@ -77,6 +70,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
u32 newval;
arch_spinlock_t lockval;
prefetchw(&lock->slock);
__asm__ __volatile__(
"1: ldrex %0, [%3]\n"
" add %1, %0, %4\n"
@ -100,6 +94,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
unsigned long contended, res;
u32 slock;
prefetchw(&lock->slock);
do {
__asm__ __volatile__(
" ldrex %0, [%3]\n"
@ -156,6 +151,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
{
unsigned long tmp;
prefetchw(&rw->lock);
__asm__ __volatile__(
"1: ldrex %0, [%1]\n"
" teq %0, #0\n"
@ -174,6 +170,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
{
unsigned long contended, res;
prefetchw(&rw->lock);
do {
__asm__ __volatile__(
" ldrex %0, [%2]\n"
@ -207,7 +204,7 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
}
/* write_can_lock - would write_trylock() succeed? */
#define arch_write_can_lock(x) ((x)->lock == 0)
#define arch_write_can_lock(x) (ACCESS_ONCE((x)->lock) == 0)
/*
* Read locks are a bit more hairy:
@ -225,6 +222,7 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
{
unsigned long tmp, tmp2;
prefetchw(&rw->lock);
__asm__ __volatile__(
"1: ldrex %0, [%2]\n"
" adds %0, %0, #1\n"
@ -245,6 +243,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
smp_mb();
prefetchw(&rw->lock);
__asm__ __volatile__(
"1: ldrex %0, [%2]\n"
" sub %0, %0, #1\n"
@ -263,6 +262,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
{
unsigned long contended, res;
prefetchw(&rw->lock);
do {
__asm__ __volatile__(
" ldrex %0, [%2]\n"
@ -284,7 +284,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
}
/* read_can_lock - would read_trylock() succeed? */
#define arch_read_can_lock(x) ((x)->lock < 0x80000000)
#define arch_read_can_lock(x) (ACCESS_ONCE((x)->lock) < 0x80000000)
#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)

Просмотреть файл

@ -25,7 +25,7 @@ typedef struct {
#define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } }
typedef struct {
volatile unsigned int lock;
u32 lock;
} arch_rwlock_t;
#define __ARCH_RW_LOCK_UNLOCKED { 0 }

Просмотреть файл

@ -38,6 +38,8 @@
#ifdef __ASSEMBLY__
#define W(instr) instr.w
#define BSYM(sym) sym + 1
#else
#define WASM(instr) #instr ".w"
#endif
#else /* !CONFIG_THUMB2_KERNEL */
@ -50,6 +52,8 @@
#ifdef __ASSEMBLY__
#define W(instr) instr
#define BSYM(sym) sym
#else
#define WASM(instr) #instr
#endif
#endif /* CONFIG_THUMB2_KERNEL */

Просмотреть файл

@ -25,12 +25,14 @@
.macro waituart,rd,rx
1001: ldr \rd, [\rx, #UART01x_FR]
ARM_BE8( rev \rd, \rd )
tst \rd, #UART01x_FR_TXFF
bne 1001b
.endm
.macro busyuart,rd,rx
1001: ldr \rd, [\rx, #UART01x_FR]
ARM_BE8( rev \rd, \rd )
tst \rd, #UART01x_FR_BUSY
bne 1001b
.endm

Просмотреть файл

@ -7,6 +7,7 @@ header-y += hwcap.h
header-y += ioctls.h
header-y += kvm_para.h
header-y += mman.h
header-y += perf_regs.h
header-y += posix_types.h
header-y += ptrace.h
header-y += setup.h

Просмотреть файл

@ -0,0 +1,23 @@
#ifndef _ASM_ARM_PERF_REGS_H
#define _ASM_ARM_PERF_REGS_H
enum perf_event_arm_regs {
PERF_REG_ARM_R0,
PERF_REG_ARM_R1,
PERF_REG_ARM_R2,
PERF_REG_ARM_R3,
PERF_REG_ARM_R4,
PERF_REG_ARM_R5,
PERF_REG_ARM_R6,
PERF_REG_ARM_R7,
PERF_REG_ARM_R8,
PERF_REG_ARM_R9,
PERF_REG_ARM_R10,
PERF_REG_ARM_FP,
PERF_REG_ARM_IP,
PERF_REG_ARM_SP,
PERF_REG_ARM_LR,
PERF_REG_ARM_PC,
PERF_REG_ARM_MAX,
};
#endif /* _ASM_ARM_PERF_REGS_H */

Просмотреть файл

@ -17,7 +17,8 @@ CFLAGS_REMOVE_return_address.o = -pg
obj-y := elf.o entry-common.o irq.o opcodes.o \
process.o ptrace.o return_address.o \
setup.o signal.o stacktrace.o sys_arm.o time.o traps.o
setup.o signal.o sigreturn_codes.o \
stacktrace.o sys_arm.o time.o traps.o
obj-$(CONFIG_ATAGS) += atags_parse.o
obj-$(CONFIG_ATAGS_PROC) += atags_proc.o
@ -78,6 +79,7 @@ obj-$(CONFIG_CPU_XSC3) += xscale-cp0.o
obj-$(CONFIG_CPU_MOHAWK) += xscale-cp0.o
obj-$(CONFIG_CPU_PJ4) += pj4-cp0.o
obj-$(CONFIG_IWMMXT) += iwmmxt.o
obj-$(CONFIG_PERF_EVENTS) += perf_regs.o
obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o perf_event_cpu.o
AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt
obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o

Просмотреть файл

@ -155,4 +155,5 @@ EXPORT_SYMBOL(__gnu_mcount_nc);
#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
EXPORT_SYMBOL(__pv_phys_offset);
EXPORT_SYMBOL(__pv_offset);
#endif

Просмотреть файл

@ -416,9 +416,8 @@ __und_usr:
bne __und_usr_thumb
sub r4, r2, #4 @ ARM instr at LR - 4
1: ldrt r0, [r4]
#ifdef CONFIG_CPU_ENDIAN_BE8
rev r0, r0 @ little endian instruction
#endif
ARM_BE8(rev r0, r0) @ little endian instruction
@ r0 = 32-bit ARM instruction which caused the exception
@ r2 = PC value for the following instruction (:= regs->ARM_pc)
@ r4 = PC value for the faulting instruction

Просмотреть файл

@ -393,9 +393,7 @@ ENTRY(vector_swi)
#else
USER( ldr r10, [lr, #-4] ) @ get SWI instruction
#endif
#ifdef CONFIG_CPU_ENDIAN_BE8
rev r10, r10 @ little endian instruction
#endif
ARM_BE8(rev r10, r10) @ little endian instruction
#elif defined(CONFIG_AEABI)

Просмотреть файл

@ -77,6 +77,7 @@
__HEAD
ENTRY(stext)
ARM_BE8(setend be ) @ ensure we are in BE8 mode
THUMB( adr r9, BSYM(1f) ) @ Kernel is always entered in ARM.
THUMB( bx r9 ) @ If this is a Thumb-2 kernel,
@ -352,6 +353,9 @@ ENTRY(secondary_startup)
* the processor type - there is no need to check the machine type
* as it has already been validated by the primary processor.
*/
ARM_BE8(setend be) @ ensure we are in BE8 mode
#ifdef CONFIG_ARM_VIRT_EXT
bl __hyp_stub_install_secondary
#endif
@ -555,6 +559,14 @@ ENTRY(fixup_smp)
ldmfd sp!, {r4 - r6, pc}
ENDPROC(fixup_smp)
#ifdef __ARMEB__
#define LOW_OFFSET 0x4
#define HIGH_OFFSET 0x0
#else
#define LOW_OFFSET 0x0
#define HIGH_OFFSET 0x4
#endif
#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
/* __fixup_pv_table - patch the stub instructions with the delta between
@ -565,17 +577,20 @@ ENDPROC(fixup_smp)
__HEAD
__fixup_pv_table:
adr r0, 1f
ldmia r0, {r3-r5, r7}
sub r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET
ldmia r0, {r3-r7}
mvn ip, #0
subs r3, r0, r3 @ PHYS_OFFSET - PAGE_OFFSET
add r4, r4, r3 @ adjust table start address
add r5, r5, r3 @ adjust table end address
add r7, r7, r3 @ adjust __pv_phys_offset address
str r8, [r7] @ save computed PHYS_OFFSET to __pv_phys_offset
add r6, r6, r3 @ adjust __pv_phys_offset address
add r7, r7, r3 @ adjust __pv_offset address
str r8, [r6, #LOW_OFFSET] @ save computed PHYS_OFFSET to __pv_phys_offset
strcc ip, [r7, #HIGH_OFFSET] @ save to __pv_offset high bits
mov r6, r3, lsr #24 @ constant for add/sub instructions
teq r3, r6, lsl #24 @ must be 16MiB aligned
THUMB( it ne @ cross section branch )
bne __error
str r6, [r7, #4] @ save to __pv_offset
str r3, [r7, #LOW_OFFSET] @ save to __pv_offset low bits
b __fixup_a_pv_table
ENDPROC(__fixup_pv_table)
@ -584,10 +599,19 @@ ENDPROC(__fixup_pv_table)
.long __pv_table_begin
.long __pv_table_end
2: .long __pv_phys_offset
.long __pv_offset
.text
__fixup_a_pv_table:
adr r0, 3f
ldr r6, [r0]
add r6, r6, r3
ldr r0, [r6, #HIGH_OFFSET] @ pv_offset high word
ldr r6, [r6, #LOW_OFFSET] @ pv_offset low word
mov r6, r6, lsr #24
cmn r0, #1
#ifdef CONFIG_THUMB2_KERNEL
moveq r0, #0x200000 @ set bit 21, mov to mvn instruction
lsls r6, #24
beq 2f
clz r7, r6
@ -601,18 +625,42 @@ __fixup_a_pv_table:
b 2f
1: add r7, r3
ldrh ip, [r7, #2]
and ip, 0x8f00
orr ip, r6 @ mask in offset bits 31-24
ARM_BE8(rev16 ip, ip)
tst ip, #0x4000
and ip, #0x8f00
orrne ip, r6 @ mask in offset bits 31-24
orreq ip, r0 @ mask in offset bits 7-0
ARM_BE8(rev16 ip, ip)
strh ip, [r7, #2]
bne 2f
ldrh ip, [r7]
ARM_BE8(rev16 ip, ip)
bic ip, #0x20
orr ip, ip, r0, lsr #16
ARM_BE8(rev16 ip, ip)
strh ip, [r7]
2: cmp r4, r5
ldrcc r7, [r4], #4 @ use branch for delay slot
bcc 1b
bx lr
#else
moveq r0, #0x400000 @ set bit 22, mov to mvn instruction
b 2f
1: ldr ip, [r7, r3]
#ifdef CONFIG_CPU_ENDIAN_BE8
@ in BE8, we load data in BE, but instructions still in LE
bic ip, ip, #0xff000000
tst ip, #0x000f0000 @ check the rotation field
orrne ip, ip, r6, lsl #24 @ mask in offset bits 31-24
biceq ip, ip, #0x00004000 @ clear bit 22
orreq ip, ip, r0, lsl #24 @ mask in offset bits 7-0
#else
bic ip, ip, #0x000000ff
orr ip, ip, r6 @ mask in offset bits 31-24
tst ip, #0xf00 @ check the rotation field
orrne ip, ip, r6 @ mask in offset bits 31-24
biceq ip, ip, #0x400000 @ clear bit 22
orreq ip, ip, r0 @ mask in offset bits 7-0
#endif
str ip, [r7, r3]
2: cmp r4, r5
ldrcc r7, [r4], #4 @ use branch for delay slot
@ -621,28 +669,30 @@ __fixup_a_pv_table:
#endif
ENDPROC(__fixup_a_pv_table)
.align
3: .long __pv_offset
ENTRY(fixup_pv_table)
stmfd sp!, {r4 - r7, lr}
ldr r2, 2f @ get address of __pv_phys_offset
mov r3, #0 @ no offset
mov r4, r0 @ r0 = table start
add r5, r0, r1 @ r1 = table size
ldr r6, [r2, #4] @ get __pv_offset
bl __fixup_a_pv_table
ldmfd sp!, {r4 - r7, pc}
ENDPROC(fixup_pv_table)
.align
2: .long __pv_phys_offset
.data
.globl __pv_phys_offset
.type __pv_phys_offset, %object
__pv_phys_offset:
.long 0
.size __pv_phys_offset, . - __pv_phys_offset
.quad 0
.size __pv_phys_offset, . -__pv_phys_offset
.globl __pv_offset
.type __pv_offset, %object
__pv_offset:
.long 0
.quad 0
.size __pv_offset, . -__pv_offset
#endif
#include "head-common.S"

Просмотреть файл

@ -24,6 +24,7 @@
#include <asm/sections.h>
#include <asm/smp_plat.h>
#include <asm/unwind.h>
#include <asm/opcodes.h>
#ifdef CONFIG_XIP_KERNEL
/*
@ -60,6 +61,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
Elf32_Sym *sym;
const char *symname;
s32 offset;
u32 tmp;
#ifdef CONFIG_THUMB2_KERNEL
u32 upper, lower, sign, j1, j2;
#endif
@ -95,7 +97,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
case R_ARM_PC24:
case R_ARM_CALL:
case R_ARM_JUMP24:
offset = (*(u32 *)loc & 0x00ffffff) << 2;
offset = __mem_to_opcode_arm(*(u32 *)loc);
offset = (offset & 0x00ffffff) << 2;
if (offset & 0x02000000)
offset -= 0x04000000;
@ -111,9 +114,10 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
}
offset >>= 2;
offset &= 0x00ffffff;
*(u32 *)loc &= 0xff000000;
*(u32 *)loc |= offset & 0x00ffffff;
*(u32 *)loc &= __opcode_to_mem_arm(0xff000000);
*(u32 *)loc |= __opcode_to_mem_arm(offset);
break;
case R_ARM_V4BX:
@ -121,8 +125,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
* other bits to re-code instruction as
* MOV PC,Rm.
*/
*(u32 *)loc &= 0xf000000f;
*(u32 *)loc |= 0x01a0f000;
*(u32 *)loc &= __opcode_to_mem_arm(0xf000000f);
*(u32 *)loc |= __opcode_to_mem_arm(0x01a0f000);
break;
case R_ARM_PREL31:
@ -132,7 +136,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
case R_ARM_MOVW_ABS_NC:
case R_ARM_MOVT_ABS:
offset = *(u32 *)loc;
offset = tmp = __mem_to_opcode_arm(*(u32 *)loc);
offset = ((offset & 0xf0000) >> 4) | (offset & 0xfff);
offset = (offset ^ 0x8000) - 0x8000;
@ -140,16 +144,18 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS)
offset >>= 16;
*(u32 *)loc &= 0xfff0f000;
*(u32 *)loc |= ((offset & 0xf000) << 4) |
(offset & 0x0fff);
tmp &= 0xfff0f000;
tmp |= ((offset & 0xf000) << 4) |
(offset & 0x0fff);
*(u32 *)loc = __opcode_to_mem_arm(tmp);
break;
#ifdef CONFIG_THUMB2_KERNEL
case R_ARM_THM_CALL:
case R_ARM_THM_JUMP24:
upper = *(u16 *)loc;
lower = *(u16 *)(loc + 2);
upper = __mem_to_opcode_thumb16(*(u16 *)loc);
lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
/*
* 25 bit signed address range (Thumb-2 BL and B.W
@ -198,17 +204,20 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
sign = (offset >> 24) & 1;
j1 = sign ^ (~(offset >> 23) & 1);
j2 = sign ^ (~(offset >> 22) & 1);
*(u16 *)loc = (u16)((upper & 0xf800) | (sign << 10) |
upper = (u16)((upper & 0xf800) | (sign << 10) |
((offset >> 12) & 0x03ff));
*(u16 *)(loc + 2) = (u16)((lower & 0xd000) |
(j1 << 13) | (j2 << 11) |
((offset >> 1) & 0x07ff));
lower = (u16)((lower & 0xd000) |
(j1 << 13) | (j2 << 11) |
((offset >> 1) & 0x07ff));
*(u16 *)loc = __opcode_to_mem_thumb16(upper);
*(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower);
break;
case R_ARM_THM_MOVW_ABS_NC:
case R_ARM_THM_MOVT_ABS:
upper = *(u16 *)loc;
lower = *(u16 *)(loc + 2);
upper = __mem_to_opcode_thumb16(*(u16 *)loc);
lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
/*
* MOVT/MOVW instructions encoding in Thumb-2:
@ -229,12 +238,14 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS)
offset >>= 16;
*(u16 *)loc = (u16)((upper & 0xfbf0) |
((offset & 0xf000) >> 12) |
((offset & 0x0800) >> 1));
*(u16 *)(loc + 2) = (u16)((lower & 0x8f00) |
((offset & 0x0700) << 4) |
(offset & 0x00ff));
upper = (u16)((upper & 0xfbf0) |
((offset & 0xf000) >> 12) |
((offset & 0x0800) >> 1));
lower = (u16)((lower & 0x8f00) |
((offset & 0x0700) << 4) |
(offset & 0x00ff));
*(u16 *)loc = __opcode_to_mem_thumb16(upper);
*(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower);
break;
#endif

Просмотреть файл

@ -256,12 +256,11 @@ validate_event(struct pmu_hw_events *hw_events,
struct perf_event *event)
{
struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
struct pmu *leader_pmu = event->group_leader->pmu;
if (is_software_event(event))
return 1;
if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
if (event->state < PERF_EVENT_STATE_OFF)
return 1;
if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)

Просмотреть файл

@ -0,0 +1,30 @@
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/perf_event.h>
#include <linux/bug.h>
#include <asm/perf_regs.h>
#include <asm/ptrace.h>
u64 perf_reg_value(struct pt_regs *regs, int idx)
{
if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM_MAX))
return 0;
return regs->uregs[idx];
}
#define REG_RESERVED (~((1ULL << PERF_REG_ARM_MAX) - 1))
int perf_reg_validate(u64 mask)
{
if (!mask || mask & REG_RESERVED)
return -EINVAL;
return 0;
}
u64 perf_reg_abi(struct task_struct *task)
{
return PERF_SAMPLE_REGS_ABI_32;
}

Просмотреть файл

@ -73,6 +73,8 @@ __setup("fpe=", fpe_setup);
#endif
extern void paging_init(const struct machine_desc *desc);
extern void early_paging_init(const struct machine_desc *,
struct proc_info_list *);
extern void sanity_check_meminfo(void);
extern enum reboot_mode reboot_mode;
extern void setup_dma_zone(const struct machine_desc *desc);
@ -888,6 +890,8 @@ void __init setup_arch(char **cmdline_p)
parse_early_param();
sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL);
early_paging_init(mdesc, lookup_processor_type(read_cpuid_id()));
sanity_check_meminfo();
arm_memblock_init(&meminfo, mdesc);

Просмотреть файл

@ -21,29 +21,7 @@
#include <asm/unistd.h>
#include <asm/vfp.h>
/*
* For ARM syscalls, we encode the syscall number into the instruction.
*/
#define SWI_SYS_SIGRETURN (0xef000000|(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE))
#define SWI_SYS_RT_SIGRETURN (0xef000000|(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE))
/*
* With EABI, the syscall number has to be loaded into r7.
*/
#define MOV_R7_NR_SIGRETURN (0xe3a07000 | (__NR_sigreturn - __NR_SYSCALL_BASE))
#define MOV_R7_NR_RT_SIGRETURN (0xe3a07000 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE))
/*
* For Thumb syscalls, we pass the syscall number via r7. We therefore
* need two 16-bit instructions.
*/
#define SWI_THUMB_SIGRETURN (0xdf00 << 16 | 0x2700 | (__NR_sigreturn - __NR_SYSCALL_BASE))
#define SWI_THUMB_RT_SIGRETURN (0xdf00 << 16 | 0x2700 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE))
static const unsigned long sigreturn_codes[7] = {
MOV_R7_NR_SIGRETURN, SWI_SYS_SIGRETURN, SWI_THUMB_SIGRETURN,
MOV_R7_NR_RT_SIGRETURN, SWI_SYS_RT_SIGRETURN, SWI_THUMB_RT_SIGRETURN,
};
extern const unsigned long sigreturn_codes[7];
static unsigned long signal_return_offset;

Просмотреть файл

@ -0,0 +1,80 @@
/*
* sigreturn_codes.S - code sinpets for sigreturn syscalls
*
* Created by: Victor Kamensky, 2013-08-13
* Copyright: (C) 2013 Linaro Limited
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
#include <asm/unistd.h>
/*
* For ARM syscalls, we encode the syscall number into the instruction.
* With EABI, the syscall number has to be loaded into r7. As result
* ARM syscall sequence snippet will have move and svc in .arm encoding
*
* For Thumb syscalls, we pass the syscall number via r7. We therefore
* need two 16-bit instructions in .thumb encoding
*
* Please note sigreturn_codes code are not executed in place. Instead
* they just copied by kernel into appropriate places. Code inside of
* arch/arm/kernel/signal.c is very sensitive to layout of these code
* snippets.
*/
#if __LINUX_ARM_ARCH__ <= 4
/*
* Note we manually set minimally required arch that supports
* required thumb opcodes for early arch versions. It is OK
* for this file to be used in combination with other
* lower arch variants, since these code snippets are only
* used as input data.
*/
.arch armv4t
#endif
.section .rodata
.global sigreturn_codes
.type sigreturn_codes, #object
.arm
sigreturn_codes:
/* ARM sigreturn syscall code snippet */
mov r7, #(__NR_sigreturn - __NR_SYSCALL_BASE)
swi #(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE)
/* Thumb sigreturn syscall code snippet */
.thumb
movs r7, #(__NR_sigreturn - __NR_SYSCALL_BASE)
swi #0
/* ARM sigreturn_rt syscall code snippet */
.arm
mov r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE)
swi #(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE)
/* Thumb sigreturn_rt syscall code snippet */
.thumb
movs r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE)
swi #0
/*
* Note on addtional space: setup_return in signal.c
* algorithm uses two words copy regardless whether
* it is thumb case or not, so we need additional
* word after real last entry.
*/
.arm
.space 4
.size sigreturn_codes, . - sigreturn_codes

Просмотреть файл

@ -55,6 +55,7 @@
* specific registers and some other data for resume.
* r0 = suspend function arg0
* r1 = suspend function
* r2 = MPIDR value the resuming CPU will use
*/
ENTRY(__cpu_suspend)
stmfd sp!, {r4 - r11, lr}
@ -67,23 +68,18 @@ ENTRY(__cpu_suspend)
mov r5, sp @ current virtual SP
add r4, r4, #12 @ Space for pgd, virt sp, phys resume fn
sub sp, sp, r4 @ allocate CPU state on stack
stmfd sp!, {r0, r1} @ save suspend func arg and pointer
add r0, sp, #8 @ save pointer to save block
mov r1, r4 @ size of save block
mov r2, r5 @ virtual SP
ldr r3, =sleep_save_sp
stmfd sp!, {r0, r1} @ save suspend func arg and pointer
ldr r3, [r3, #SLEEP_SAVE_SP_VIRT]
ALT_SMP(mrc p15, 0, r9, c0, c0, 5)
ALT_UP_B(1f)
ldr r8, =mpidr_hash
/*
* This ldmia relies on the memory layout of the mpidr_hash
* struct mpidr_hash.
*/
ldmia r8, {r4-r7} @ r4 = mpidr mask (r5,r6,r7) = l[0,1,2] shifts
compute_mpidr_hash lr, r5, r6, r7, r9, r4
add r3, r3, lr, lsl #2
1:
ALT_SMP(ldr r0, =mpidr_hash)
ALT_UP_B(1f)
/* This ldmia relies on the memory layout of the mpidr_hash struct */
ldmia r0, {r1, r6-r8} @ r1 = mpidr mask (r6,r7,r8) = l[0,1,2] shifts
compute_mpidr_hash r0, r6, r7, r8, r2, r1
add r3, r3, r0, lsl #2
1: mov r2, r5 @ virtual SP
mov r1, r4 @ size of save block
add r0, sp, #8 @ pointer to save block
bl __cpu_suspend_save
adr lr, BSYM(cpu_suspend_abort)
ldmfd sp!, {r0, pc} @ call suspend fn
@ -130,6 +126,7 @@ ENDPROC(cpu_resume_after_mmu)
.data
.align
ENTRY(cpu_resume)
ARM_BE8(setend be) @ ensure we are in BE mode
mov r1, #0
ALT_SMP(mrc p15, 0, r0, c0, c0, 5)
ALT_UP_B(1f)

Просмотреть файл

@ -68,6 +68,7 @@ enum ipi_msg_type {
IPI_CALL_FUNC_SINGLE,
IPI_CPU_STOP,
IPI_IRQ_WORK,
IPI_COMPLETION,
};
static DECLARE_COMPLETION(cpu_running);
@ -82,7 +83,7 @@ void __init smp_set_ops(struct smp_operations *ops)
static unsigned long get_arch_pgd(pgd_t *pgd)
{
phys_addr_t pgdir = virt_to_phys(pgd);
phys_addr_t pgdir = virt_to_idmap(pgd);
BUG_ON(pgdir & ARCH_PGD_MASK);
return pgdir >> ARCH_PGD_SHIFT;
}
@ -467,6 +468,7 @@ static const char *ipi_types[NR_IPI] = {
S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
S(IPI_CPU_STOP, "CPU stop interrupts"),
S(IPI_IRQ_WORK, "IRQ work interrupts"),
S(IPI_COMPLETION, "completion interrupts"),
};
void show_ipi_list(struct seq_file *p, int prec)
@ -526,6 +528,19 @@ static void ipi_cpu_stop(unsigned int cpu)
cpu_relax();
}
static DEFINE_PER_CPU(struct completion *, cpu_completion);
int register_ipi_completion(struct completion *completion, int cpu)
{
per_cpu(cpu_completion, cpu) = completion;
return IPI_COMPLETION;
}
static void ipi_complete(unsigned int cpu)
{
complete(per_cpu(cpu_completion, cpu));
}
/*
* Main handler for inter-processor interrupts
*/
@ -584,6 +599,12 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
break;
#endif
case IPI_COMPLETION:
irq_enter();
ipi_complete(cpu);
irq_exit();
break;
default:
printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
cpu, ipinr);

Просмотреть файл

@ -28,7 +28,7 @@
*/
unsigned int __init scu_get_core_count(void __iomem *scu_base)
{
unsigned int ncores = __raw_readl(scu_base + SCU_CONFIG);
unsigned int ncores = readl_relaxed(scu_base + SCU_CONFIG);
return (ncores & 0x03) + 1;
}
@ -42,19 +42,19 @@ void scu_enable(void __iomem *scu_base)
#ifdef CONFIG_ARM_ERRATA_764369
/* Cortex-A9 only */
if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090) {
scu_ctrl = __raw_readl(scu_base + 0x30);
scu_ctrl = readl_relaxed(scu_base + 0x30);
if (!(scu_ctrl & 1))
__raw_writel(scu_ctrl | 0x1, scu_base + 0x30);
writel_relaxed(scu_ctrl | 0x1, scu_base + 0x30);
}
#endif
scu_ctrl = __raw_readl(scu_base + SCU_CTRL);
scu_ctrl = readl_relaxed(scu_base + SCU_CTRL);
/* already enabled? */
if (scu_ctrl & 1)
return;
scu_ctrl |= 1;
__raw_writel(scu_ctrl, scu_base + SCU_CTRL);
writel_relaxed(scu_ctrl, scu_base + SCU_CTRL);
/*
* Ensure that the data accessed by CPU0 before the SCU was
@ -80,9 +80,9 @@ int scu_power_mode(void __iomem *scu_base, unsigned int mode)
if (mode > 3 || mode == 1 || cpu > 3)
return -EINVAL;
val = __raw_readb(scu_base + SCU_CPU_STATUS + cpu) & ~0x03;
val = readb_relaxed(scu_base + SCU_CPU_STATUS + cpu) & ~0x03;
val |= mode;
__raw_writeb(val, scu_base + SCU_CPU_STATUS + cpu);
writeb_relaxed(val, scu_base + SCU_CPU_STATUS + cpu);
return 0;
}

Просмотреть файл

@ -45,7 +45,7 @@ static void twd_set_mode(enum clock_event_mode mode,
case CLOCK_EVT_MODE_PERIODIC:
ctrl = TWD_TIMER_CONTROL_ENABLE | TWD_TIMER_CONTROL_IT_ENABLE
| TWD_TIMER_CONTROL_PERIODIC;
__raw_writel(DIV_ROUND_CLOSEST(twd_timer_rate, HZ),
writel_relaxed(DIV_ROUND_CLOSEST(twd_timer_rate, HZ),
twd_base + TWD_TIMER_LOAD);
break;
case CLOCK_EVT_MODE_ONESHOT:
@ -58,18 +58,18 @@ static void twd_set_mode(enum clock_event_mode mode,
ctrl = 0;
}
__raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL);
writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL);
}
static int twd_set_next_event(unsigned long evt,
struct clock_event_device *unused)
{
unsigned long ctrl = __raw_readl(twd_base + TWD_TIMER_CONTROL);
unsigned long ctrl = readl_relaxed(twd_base + TWD_TIMER_CONTROL);
ctrl |= TWD_TIMER_CONTROL_ENABLE;
__raw_writel(evt, twd_base + TWD_TIMER_COUNTER);
__raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL);
writel_relaxed(evt, twd_base + TWD_TIMER_COUNTER);
writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL);
return 0;
}
@ -82,8 +82,8 @@ static int twd_set_next_event(unsigned long evt,
*/
static int twd_timer_ack(void)
{
if (__raw_readl(twd_base + TWD_TIMER_INTSTAT)) {
__raw_writel(1, twd_base + TWD_TIMER_INTSTAT);
if (readl_relaxed(twd_base + TWD_TIMER_INTSTAT)) {
writel_relaxed(1, twd_base + TWD_TIMER_INTSTAT);
return 1;
}
@ -211,15 +211,15 @@ static void twd_calibrate_rate(void)
waitjiffies += 5;
/* enable, no interrupt or reload */
__raw_writel(0x1, twd_base + TWD_TIMER_CONTROL);
writel_relaxed(0x1, twd_base + TWD_TIMER_CONTROL);
/* maximum value */
__raw_writel(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER);
writel_relaxed(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER);
while (get_jiffies_64() < waitjiffies)
udelay(10);
count = __raw_readl(twd_base + TWD_TIMER_COUNTER);
count = readl_relaxed(twd_base + TWD_TIMER_COUNTER);
twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5);
@ -277,7 +277,7 @@ static void twd_timer_setup(void)
* bother with the below.
*/
if (per_cpu(percpu_setup_called, cpu)) {
__raw_writel(0, twd_base + TWD_TIMER_CONTROL);
writel_relaxed(0, twd_base + TWD_TIMER_CONTROL);
clockevents_register_device(clk);
enable_percpu_irq(clk->irq, 0);
return;
@ -290,7 +290,7 @@ static void twd_timer_setup(void)
* The following is done once per CPU the first time .setup() is
* called.
*/
__raw_writel(0, twd_base + TWD_TIMER_CONTROL);
writel_relaxed(0, twd_base + TWD_TIMER_CONTROL);
clk->name = "local_timer";
clk->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT |

Просмотреть файл

@ -10,7 +10,7 @@
#include <asm/suspend.h>
#include <asm/tlbflush.h>
extern int __cpu_suspend(unsigned long, int (*)(unsigned long));
extern int __cpu_suspend(unsigned long, int (*)(unsigned long), u32 cpuid);
extern void cpu_resume_mmu(void);
#ifdef CONFIG_MMU
@ -21,6 +21,7 @@ extern void cpu_resume_mmu(void);
int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
{
struct mm_struct *mm = current->active_mm;
u32 __mpidr = cpu_logical_map(smp_processor_id());
int ret;
if (!idmap_pgd)
@ -32,7 +33,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
* resume (indicated by a zero return code), we need to switch
* back to the correct page tables.
*/
ret = __cpu_suspend(arg, fn);
ret = __cpu_suspend(arg, fn, __mpidr);
if (ret == 0) {
cpu_switch_mm(mm->pgd, mm);
local_flush_bp_all();
@ -44,7 +45,8 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
#else
int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
{
return __cpu_suspend(arg, fn);
u32 __mpidr = cpu_logical_map(smp_processor_id());
return __cpu_suspend(arg, fn, __mpidr);
}
#define idmap_pgd NULL
#endif

Просмотреть файл

@ -34,6 +34,7 @@
#include <asm/unwind.h>
#include <asm/tls.h>
#include <asm/system_misc.h>
#include <asm/opcodes.h>
static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
@ -341,15 +342,17 @@ void arm_notify_die(const char *str, struct pt_regs *regs,
int is_valid_bugaddr(unsigned long pc)
{
#ifdef CONFIG_THUMB2_KERNEL
unsigned short bkpt;
u16 bkpt;
u16 insn = __opcode_to_mem_thumb16(BUG_INSTR_VALUE);
#else
unsigned long bkpt;
u32 bkpt;
u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE);
#endif
if (probe_kernel_address((unsigned *)pc, bkpt))
return 0;
return bkpt == BUG_INSTR_VALUE;
return bkpt == insn;
}
#endif
@ -402,25 +405,28 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
if (processor_mode(regs) == SVC_MODE) {
#ifdef CONFIG_THUMB2_KERNEL
if (thumb_mode(regs)) {
instr = ((u16 *)pc)[0];
instr = __mem_to_opcode_thumb16(((u16 *)pc)[0]);
if (is_wide_instruction(instr)) {
instr <<= 16;
instr |= ((u16 *)pc)[1];
u16 inst2;
inst2 = __mem_to_opcode_thumb16(((u16 *)pc)[1]);
instr = __opcode_thumb32_compose(instr, inst2);
}
} else
#endif
instr = *(u32 *) pc;
instr = __mem_to_opcode_arm(*(u32 *) pc);
} else if (thumb_mode(regs)) {
if (get_user(instr, (u16 __user *)pc))
goto die_sig;
instr = __mem_to_opcode_thumb16(instr);
if (is_wide_instruction(instr)) {
unsigned int instr2;
if (get_user(instr2, (u16 __user *)pc+1))
goto die_sig;
instr <<= 16;
instr |= instr2;
instr2 = __mem_to_opcode_thumb16(instr2);
instr = __opcode_thumb32_compose(instr, instr2);
}
} else if (get_user(instr, (u32 __user *)pc)) {
instr = __mem_to_opcode_arm(instr);
goto die_sig;
}

Просмотреть файл

@ -10,6 +10,11 @@ UNWIND( .fnstart )
and r3, r0, #31 @ Get bit offset
mov r0, r0, lsr #5
add r1, r1, r0, lsl #2 @ Get word offset
#if __LINUX_ARM_ARCH__ >= 7
.arch_extension mp
ALT_SMP(W(pldw) [r1])
ALT_UP(W(nop))
#endif
mov r3, r2, lsl r3
1: ldrex r2, [r1]
\instr r2, r2, r3

Просмотреть файл

@ -4,6 +4,7 @@ config ARCH_HIGHBANK
select ARCH_HAS_CPUFREQ
select ARCH_HAS_HOLES_MEMORYMODEL
select ARCH_HAS_OPP
select ARCH_SUPPORTS_BIG_ENDIAN
select ARCH_WANT_OPTIONAL_GPIOLIB
select ARM_AMBA
select ARM_ERRATA_764369

Просмотреть файл

@ -1,9 +1,5 @@
if ARCH_IXP4XX
config ARCH_SUPPORTS_BIG_ENDIAN
bool
default y
menu "Intel IXP4xx Implementation Options"
comment "IXP4xx Platforms"

Просмотреть файл

@ -1,5 +1,6 @@
config ARCH_MVEBU
bool "Marvell SOCs with Device Tree support" if ARCH_MULTI_V7
select ARCH_SUPPORTS_BIG_ENDIAN
select CLKSRC_MMIO
select COMMON_CLK
select GENERIC_CLOCKEVENTS

Просмотреть файл

@ -20,6 +20,8 @@
#define ARMADA_XP_CFB_CTL_REG_OFFSET 0x0
#define ARMADA_XP_CFB_CFG_REG_OFFSET 0x4
#include <asm/assembler.h>
.text
/*
* r0: Coherency fabric base register address
@ -29,6 +31,7 @@ ENTRY(ll_set_cpu_coherent)
/* Create bit by cpu index */
mov r3, #(1 << 24)
lsl r1, r3, r1
ARM_BE8(rev r1, r1)
/* Add CPU to SMP group - Atomic */
add r3, r0, #ARMADA_XP_CFB_CTL_REG_OFFSET

Просмотреть файл

@ -21,12 +21,16 @@
#include <linux/linkage.h>
#include <linux/init.h>
#include <asm/assembler.h>
/*
* Armada XP specific entry point for secondary CPUs.
* We add the CPU to the coherency fabric and then jump to secondary
* startup
*/
ENTRY(armada_xp_secondary_startup)
ARM_BE8(setend be ) @ go BE8 if entered LE
/* Get coherency fabric base physical address */
adr r0, 1f
ldr r1, [r0]

Просмотреть файл

@ -1,6 +1,7 @@
config ARCH_VEXPRESS
bool "ARM Ltd. Versatile Express family" if ARCH_MULTI_V7
select ARCH_REQUIRE_GPIOLIB
select ARCH_SUPPORTS_BIG_ENDIAN
select ARM_AMBA
select ARM_GIC
select ARM_TIMER_SP804

Просмотреть файл

@ -952,3 +952,9 @@ config ARCH_HAS_BARRIERS
help
This option allows the use of custom mandatory barriers
included via the mach/barriers.h file.
config ARCH_SUPPORTS_BIG_ENDIAN
bool
help
This option specifies the architecture can support big endian
operation.

Просмотреть файл

@ -38,9 +38,8 @@ ENTRY(v6_early_abort)
bne do_DataAbort
bic r1, r1, #1 << 11 @ clear bit 11 of FSR
ldr r3, [r4] @ read aborted ARM instruction
#ifdef CONFIG_CPU_ENDIAN_BE8
rev r3, r3
#endif
ARM_BE8(rev r3, r3)
do_ldrd_abort tmp=ip, insn=r3
tst r3, #1 << 20 @ L = 0 -> write
orreq r1, r1, #1 << 11 @ yes.

Просмотреть файл

@ -25,6 +25,7 @@
#include <asm/cp15.h>
#include <asm/system_info.h>
#include <asm/unaligned.h>
#include <asm/opcodes.h>
#include "fault.h"
@ -762,21 +763,25 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
if (thumb_mode(regs)) {
u16 *ptr = (u16 *)(instrptr & ~1);
fault = probe_kernel_address(ptr, tinstr);
tinstr = __mem_to_opcode_thumb16(tinstr);
if (!fault) {
if (cpu_architecture() >= CPU_ARCH_ARMv7 &&
IS_T32(tinstr)) {
/* Thumb-2 32-bit */
u16 tinst2 = 0;
fault = probe_kernel_address(ptr + 1, tinst2);
instr = (tinstr << 16) | tinst2;
tinst2 = __mem_to_opcode_thumb16(tinst2);
instr = __opcode_thumb32_compose(tinstr, tinst2);
thumb2_32b = 1;
} else {
isize = 2;
instr = thumb2arm(tinstr);
}
}
} else
} else {
fault = probe_kernel_address(instrptr, instr);
instr = __mem_to_opcode_arm(instr);
}
if (fault) {
type = TYPE_FAULT;

Просмотреть файл

@ -10,6 +10,7 @@
#include <asm/system_info.h>
pgd_t *idmap_pgd;
phys_addr_t (*arch_virt_to_idmap) (unsigned long x);
#ifdef CONFIG_ARM_LPAE
static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
@ -67,8 +68,9 @@ static void identity_mapping_add(pgd_t *pgd, const char *text_start,
unsigned long addr, end;
unsigned long next;
addr = virt_to_phys(text_start);
end = virt_to_phys(text_end);
addr = virt_to_idmap(text_start);
end = virt_to_idmap(text_end);
pr_info("Setting up static identity map for 0x%lx - 0x%lx\n", addr, end);
prot |= PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF;
@ -90,8 +92,6 @@ static int __init init_static_idmap(void)
if (!idmap_pgd)
return -ENOMEM;
pr_info("Setting up static identity map for 0x%p - 0x%p\n",
__idmap_text_start, __idmap_text_end);
identity_mapping_add(idmap_pgd, __idmap_text_start,
__idmap_text_end, 0);

Просмотреть файл

@ -28,6 +28,8 @@
#include <asm/highmem.h>
#include <asm/system_info.h>
#include <asm/traps.h>
#include <asm/procinfo.h>
#include <asm/memory.h>
#include <asm/mach/arch.h>
#include <asm/mach/map.h>
@ -1315,6 +1317,86 @@ static void __init map_lowmem(void)
}
}
#ifdef CONFIG_ARM_LPAE
/*
* early_paging_init() recreates boot time page table setup, allowing machines
* to switch over to a high (>4G) address space on LPAE systems
*/
void __init early_paging_init(const struct machine_desc *mdesc,
struct proc_info_list *procinfo)
{
pmdval_t pmdprot = procinfo->__cpu_mm_mmu_flags;
unsigned long map_start, map_end;
pgd_t *pgd0, *pgdk;
pud_t *pud0, *pudk, *pud_start;
pmd_t *pmd0, *pmdk;
phys_addr_t phys;
int i;
if (!(mdesc->init_meminfo))
return;
/* remap kernel code and data */
map_start = init_mm.start_code;
map_end = init_mm.brk;
/* get a handle on things... */
pgd0 = pgd_offset_k(0);
pud_start = pud0 = pud_offset(pgd0, 0);
pmd0 = pmd_offset(pud0, 0);
pgdk = pgd_offset_k(map_start);
pudk = pud_offset(pgdk, map_start);
pmdk = pmd_offset(pudk, map_start);
mdesc->init_meminfo();
/* Run the patch stub to update the constants */
fixup_pv_table(&__pv_table_begin,
(&__pv_table_end - &__pv_table_begin) << 2);
/*
* Cache cleaning operations for self-modifying code
* We should clean the entries by MVA but running a
* for loop over every pv_table entry pointer would
* just complicate the code.
*/
flush_cache_louis();
dsb();
isb();
/* remap level 1 table */
for (i = 0; i < PTRS_PER_PGD; pud0++, i++) {
set_pud(pud0,
__pud(__pa(pmd0) | PMD_TYPE_TABLE | L_PGD_SWAPPER));
pmd0 += PTRS_PER_PMD;
}
/* remap pmds for kernel mapping */
phys = __pa(map_start) & PMD_MASK;
do {
*pmdk++ = __pmd(phys | pmdprot);
phys += PMD_SIZE;
} while (phys < map_end);
flush_cache_all();
cpu_switch_mm(pgd0, &init_mm);
cpu_set_ttbr(1, __pa(pgd0) + TTBR1_OFFSET);
local_flush_bp_all();
local_flush_tlb_all();
}
#else
void __init early_paging_init(const struct machine_desc *mdesc,
struct proc_info_list *procinfo)
{
if (mdesc->init_meminfo)
mdesc->init_meminfo();
}
#endif
/*
* paging_init() sets up the page tables, initialises the zone memory
* maps, and sets up the zero page, bad page and bad page tables.

Просмотреть файл

@ -295,6 +295,15 @@ void __init sanity_check_meminfo(void)
high_memory = __va(end - 1) + 1;
}
/*
* early_paging_init() recreates boot time page table setup, allowing machines
* to switch over to a high (>4G) address space on LPAE systems
*/
void __init early_paging_init(const struct machine_desc *mdesc,
struct proc_info_list *procinfo)
{
}
/*
* paging_init() sets up the page tables, initialises the zone memory
* maps, and sets up the zero page, bad page and bad page tables.

Просмотреть файл

@ -220,9 +220,7 @@ __v6_setup:
#endif /* CONFIG_MMU */
adr r5, v6_crval
ldmia r5, {r5, r6}
#ifdef CONFIG_CPU_ENDIAN_BE8
orr r6, r6, #1 << 25 @ big-endian page tables
#endif
ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables
mrc p15, 0, r0, c1, c0, 0 @ read control register
bic r0, r0, r5 @ clear bits them
orr r0, r0, r6 @ set them

Просмотреть файл

@ -367,9 +367,7 @@ __v7_setup:
#endif
adr r5, v7_crval
ldmia r5, {r5, r6}
#ifdef CONFIG_CPU_ENDIAN_BE8
orr r6, r6, #1 << 25 @ big-endian page tables
#endif
ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables
#ifdef CONFIG_SWP_EMULATE
orr r5, r5, #(1 << 10) @ set SW bit in "clear"
bic r6, r6, #(1 << 10) @ clear it in "mmuset"

Просмотреть файл

@ -19,6 +19,7 @@
#include <linux/if_vlan.h>
#include <asm/cacheflush.h>
#include <asm/hwcap.h>
#include <asm/opcodes.h>
#include "bpf_jit_32.h"
@ -113,8 +114,11 @@ static u32 jit_udiv(u32 dividend, u32 divisor)
static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx)
{
inst |= (cond << 28);
inst = __opcode_to_mem_arm(inst);
if (ctx->target != NULL)
ctx->target[ctx->idx] = inst | (cond << 28);
ctx->target[ctx->idx] = inst;
ctx->idx++;
}

Просмотреть файл

@ -10,6 +10,7 @@
*/
#include <linux/linkage.h>
#include <linux/init.h>
#include <asm/assembler.h>
/*
* Realview/Versatile Express specific entry point for secondary CPUs.
@ -17,6 +18,7 @@
* until we're ready for them to initialise.
*/
ENTRY(versatile_secondary_startup)
ARM_BE8(setend be)
mrc p15, 0, r0, c0, c0, 5
bic r0, #0xff000000
adr r4, 1f

Просмотреть файл

@ -776,6 +776,22 @@ config CRYPTO_AES_ARM
See <http://csrc.nist.gov/encryption/aes/> for more information.
config CRYPTO_AES_ARM_BS
tristate "Bit sliced AES using NEON instructions"
depends on ARM && KERNEL_MODE_NEON
select CRYPTO_ALGAPI
select CRYPTO_AES_ARM
select CRYPTO_ABLK_HELPER
help
Use a faster and more secure NEON based implementation of AES in CBC,
CTR and XTS modes
Bit sliced AES gives around 45% speedup on Cortex-A15 for CTR mode
and for XTS mode encryption, CBC and XTS mode decryption speedup is
around 25%. (CBC encryption speed is not affected by this driver.)
This implementation does not rely on any lookup tables so it is
believed to be invulnerable to cache timing attacks.
config CRYPTO_ANUBIS
tristate "Anubis cipher algorithm"
select CRYPTO_ALGAPI

Просмотреть файл

@ -280,7 +280,7 @@ asmlinkage void __naked cci_enable_port_for_self(void)
/* Enable the CCI port */
" ldr r0, [r0, %[offsetof_port_phys]] \n"
" mov r3, #"__stringify(CCI_ENABLE_REQ)" \n"
" mov r3, %[cci_enable_req]\n"
" str r3, [r0, #"__stringify(CCI_PORT_CTRL)"] \n"
/* poll the status reg for completion */
@ -288,7 +288,7 @@ asmlinkage void __naked cci_enable_port_for_self(void)
" ldr r0, [r1] \n"
" ldr r0, [r0, r1] @ cci_ctrl_base \n"
"4: ldr r1, [r0, #"__stringify(CCI_CTRL_STATUS)"] \n"
" tst r1, #1 \n"
" tst r1, %[cci_control_status_bits] \n"
" bne 4b \n"
" mov r0, #0 \n"
@ -301,6 +301,8 @@ asmlinkage void __naked cci_enable_port_for_self(void)
"7: .word cci_ctrl_phys - . \n"
: :
[sizeof_cpu_port] "i" (sizeof(cpu_port)),
[cci_enable_req] "i" cpu_to_le32(CCI_ENABLE_REQ),
[cci_control_status_bits] "i" cpu_to_le32(1),
#ifndef __ARMEB__
[offsetof_cpu_port_mpidr_lsb] "i" (offsetof(struct cpu_port, mpidr)),
#else

Просмотреть файл

@ -253,10 +253,9 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
return -EINVAL;
raw_spin_lock(&irq_controller_lock);
mask = 0xff << shift;
bit = gic_cpu_map[cpu] << shift;
raw_spin_lock(&irq_controller_lock);
val = readl_relaxed(reg) & ~mask;
writel_relaxed(val | bit, reg);
raw_spin_unlock(&irq_controller_lock);
@ -652,7 +651,9 @@ static void __init gic_pm_init(struct gic_chip_data *gic)
void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
{
int cpu;
unsigned long map = 0;
unsigned long flags, map = 0;
raw_spin_lock_irqsave(&irq_controller_lock, flags);
/* Convert our logical CPU mask into a physical one. */
for_each_cpu(cpu, mask)
@ -666,9 +667,151 @@ void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
/* this always happens on GIC0 */
writel_relaxed(map << 16 | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
}
#endif
#ifdef CONFIG_BL_SWITCHER
/*
* gic_send_sgi - send a SGI directly to given CPU interface number
*
* cpu_id: the ID for the destination CPU interface
* irq: the IPI number to send a SGI for
*/
void gic_send_sgi(unsigned int cpu_id, unsigned int irq)
{
BUG_ON(cpu_id >= NR_GIC_CPU_IF);
cpu_id = 1 << cpu_id;
/* this always happens on GIC0 */
writel_relaxed((cpu_id << 16) | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
}
/*
* gic_get_cpu_id - get the CPU interface ID for the specified CPU
*
* @cpu: the logical CPU number to get the GIC ID for.
*
* Return the CPU interface ID for the given logical CPU number,
* or -1 if the CPU number is too large or the interface ID is
* unknown (more than one bit set).
*/
int gic_get_cpu_id(unsigned int cpu)
{
unsigned int cpu_bit;
if (cpu >= NR_GIC_CPU_IF)
return -1;
cpu_bit = gic_cpu_map[cpu];
if (cpu_bit & (cpu_bit - 1))
return -1;
return __ffs(cpu_bit);
}
/*
* gic_migrate_target - migrate IRQs to another CPU interface
*
* @new_cpu_id: the CPU target ID to migrate IRQs to
*
* Migrate all peripheral interrupts with a target matching the current CPU
* to the interface corresponding to @new_cpu_id. The CPU interface mapping
* is also updated. Targets to other CPU interfaces are unchanged.
* This must be called with IRQs locally disabled.
*/
void gic_migrate_target(unsigned int new_cpu_id)
{
unsigned int cur_cpu_id, gic_irqs, gic_nr = 0;
void __iomem *dist_base;
int i, ror_val, cpu = smp_processor_id();
u32 val, cur_target_mask, active_mask;
if (gic_nr >= MAX_GIC_NR)
BUG();
dist_base = gic_data_dist_base(&gic_data[gic_nr]);
if (!dist_base)
return;
gic_irqs = gic_data[gic_nr].gic_irqs;
cur_cpu_id = __ffs(gic_cpu_map[cpu]);
cur_target_mask = 0x01010101 << cur_cpu_id;
ror_val = (cur_cpu_id - new_cpu_id) & 31;
raw_spin_lock(&irq_controller_lock);
/* Update the target interface for this logical CPU */
gic_cpu_map[cpu] = 1 << new_cpu_id;
/*
* Find all the peripheral interrupts targetting the current
* CPU interface and migrate them to the new CPU interface.
* We skip DIST_TARGET 0 to 7 as they are read-only.
*/
for (i = 8; i < DIV_ROUND_UP(gic_irqs, 4); i++) {
val = readl_relaxed(dist_base + GIC_DIST_TARGET + i * 4);
active_mask = val & cur_target_mask;
if (active_mask) {
val &= ~active_mask;
val |= ror32(active_mask, ror_val);
writel_relaxed(val, dist_base + GIC_DIST_TARGET + i*4);
}
}
raw_spin_unlock(&irq_controller_lock);
/*
* Now let's migrate and clear any potential SGIs that might be
* pending for us (cur_cpu_id). Since GIC_DIST_SGI_PENDING_SET
* is a banked register, we can only forward the SGI using
* GIC_DIST_SOFTINT. The original SGI source is lost but Linux
* doesn't use that information anyway.
*
* For the same reason we do not adjust SGI source information
* for previously sent SGIs by us to other CPUs either.
*/
for (i = 0; i < 16; i += 4) {
int j;
val = readl_relaxed(dist_base + GIC_DIST_SGI_PENDING_SET + i);
if (!val)
continue;
writel_relaxed(val, dist_base + GIC_DIST_SGI_PENDING_CLEAR + i);
for (j = i; j < i + 4; j++) {
if (val & 0xff)
writel_relaxed((1 << (new_cpu_id + 16)) | j,
dist_base + GIC_DIST_SOFTINT);
val >>= 8;
}
}
}
/*
* gic_get_sgir_physaddr - get the physical address for the SGI register
*
* REturn the physical address of the SGI register to be used
* by some early assembly code when the kernel is not yet available.
*/
static unsigned long gic_dist_physaddr;
unsigned long gic_get_sgir_physaddr(void)
{
if (!gic_dist_physaddr)
return 0;
return gic_dist_physaddr + GIC_DIST_SOFTINT;
}
void __init gic_init_physaddr(struct device_node *node)
{
struct resource res;
if (of_address_to_resource(node, 0, &res) == 0) {
gic_dist_physaddr = res.start;
pr_info("GIC physical location is %#lx\n", gic_dist_physaddr);
}
}
#else
#define gic_init_physaddr(node) do { } while (0)
#endif
static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
irq_hw_number_t hw)
{
@ -850,6 +993,8 @@ int __init gic_of_init(struct device_node *node, struct device_node *parent)
percpu_offset = 0;
gic_init_bases(gic_cnt, -1, dist_base, cpu_base, percpu_offset, node);
if (!gic_cnt)
gic_init_physaddr(node);
if (parent) {
irq = irq_of_parse_and_map(node, 0);

Просмотреть файл

@ -31,6 +31,8 @@
#define GIC_DIST_TARGET 0x800
#define GIC_DIST_CONFIG 0xc00
#define GIC_DIST_SOFTINT 0xf00
#define GIC_DIST_SGI_PENDING_CLEAR 0xf10
#define GIC_DIST_SGI_PENDING_SET 0xf20
#define GICH_HCR 0x0
#define GICH_VTR 0x4
@ -74,6 +76,11 @@ static inline void gic_init(unsigned int nr, int start,
gic_init_bases(nr, start, dist, cpu, 0, NULL);
}
void gic_send_sgi(unsigned int cpu_id, unsigned int irq);
int gic_get_cpu_id(unsigned int cpu);
void gic_migrate_target(unsigned int new_cpu_id);
unsigned long gic_get_sgir_physaddr(void);
#endif /* __ASSEMBLY */
#endif

Просмотреть файл

@ -0,0 +1,67 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM power
#if !defined(_TRACE_POWER_CPU_MIGRATE_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_POWER_CPU_MIGRATE_H
#include <linux/tracepoint.h>
#define __cpu_migrate_proto \
TP_PROTO(u64 timestamp, \
u32 cpu_hwid)
#define __cpu_migrate_args \
TP_ARGS(timestamp, \
cpu_hwid)
DECLARE_EVENT_CLASS(cpu_migrate,
__cpu_migrate_proto,
__cpu_migrate_args,
TP_STRUCT__entry(
__field(u64, timestamp )
__field(u32, cpu_hwid )
),
TP_fast_assign(
__entry->timestamp = timestamp;
__entry->cpu_hwid = cpu_hwid;
),
TP_printk("timestamp=%llu cpu_hwid=0x%08lX",
(unsigned long long)__entry->timestamp,
(unsigned long)__entry->cpu_hwid
)
);
#define __define_cpu_migrate_event(name) \
DEFINE_EVENT(cpu_migrate, cpu_migrate_##name, \
__cpu_migrate_proto, \
__cpu_migrate_args \
)
__define_cpu_migrate_event(begin);
__define_cpu_migrate_event(finish);
__define_cpu_migrate_event(current);
#undef __define_cpu_migrate
#undef __cpu_migrate_proto
#undef __cpu_migrate_args
/* This file can get included multiple times, TRACE_HEADER_MULTI_READ at top */
#ifndef _PWR_CPU_MIGRATE_EVENT_AVOID_DOUBLE_DEFINING
#define _PWR_CPU_MIGRATE_EVENT_AVOID_DOUBLE_DEFINING
/*
* Set from_phys_cpu and to_phys_cpu to CPU_MIGRATE_ALL_CPUS to indicate
* a whole-cluster migration:
*/
#define CPU_MIGRATE_ALL_CPUS 0x80000000U
#endif
#endif /* _TRACE_POWER_CPU_MIGRATE_H */
/* This part must be outside protection */
#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_FILE power_cpu_migrate
#include <trace/define_trace.h>

Просмотреть файл

@ -2,3 +2,6 @@ ifndef NO_DWARF
PERF_HAVE_DWARF_REGS := 1
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
endif
ifndef NO_LIBUNWIND
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o
endif

Просмотреть файл

@ -0,0 +1,54 @@
#ifndef ARCH_PERF_REGS_H
#define ARCH_PERF_REGS_H
#include <stdlib.h>
#include "../../util/types.h"
#include <asm/perf_regs.h>
#define PERF_REGS_MASK ((1ULL << PERF_REG_ARM_MAX) - 1)
#define PERF_REG_IP PERF_REG_ARM_PC
#define PERF_REG_SP PERF_REG_ARM_SP
static inline const char *perf_reg_name(int id)
{
switch (id) {
case PERF_REG_ARM_R0:
return "r0";
case PERF_REG_ARM_R1:
return "r1";
case PERF_REG_ARM_R2:
return "r2";
case PERF_REG_ARM_R3:
return "r3";
case PERF_REG_ARM_R4:
return "r4";
case PERF_REG_ARM_R5:
return "r5";
case PERF_REG_ARM_R6:
return "r6";
case PERF_REG_ARM_R7:
return "r7";
case PERF_REG_ARM_R8:
return "r8";
case PERF_REG_ARM_R9:
return "r9";
case PERF_REG_ARM_R10:
return "r10";
case PERF_REG_ARM_FP:
return "fp";
case PERF_REG_ARM_IP:
return "ip";
case PERF_REG_ARM_SP:
return "sp";
case PERF_REG_ARM_LR:
return "lr";
case PERF_REG_ARM_PC:
return "pc";
default:
return NULL;
}
return NULL;
}
#endif /* ARCH_PERF_REGS_H */

Просмотреть файл

@ -0,0 +1,48 @@
#include <errno.h>
#include <libunwind.h>
#include "perf_regs.h"
#include "../../util/unwind.h"
int unwind__arch_reg_id(int regnum)
{
switch (regnum) {
case UNW_ARM_R0:
return PERF_REG_ARM_R0;
case UNW_ARM_R1:
return PERF_REG_ARM_R1;
case UNW_ARM_R2:
return PERF_REG_ARM_R2;
case UNW_ARM_R3:
return PERF_REG_ARM_R3;
case UNW_ARM_R4:
return PERF_REG_ARM_R4;
case UNW_ARM_R5:
return PERF_REG_ARM_R5;
case UNW_ARM_R6:
return PERF_REG_ARM_R6;
case UNW_ARM_R7:
return PERF_REG_ARM_R7;
case UNW_ARM_R8:
return PERF_REG_ARM_R8;
case UNW_ARM_R9:
return PERF_REG_ARM_R9;
case UNW_ARM_R10:
return PERF_REG_ARM_R10;
case UNW_ARM_R11:
return PERF_REG_ARM_FP;
case UNW_ARM_R12:
return PERF_REG_ARM_IP;
case UNW_ARM_R13:
return PERF_REG_ARM_SP;
case UNW_ARM_R14:
return PERF_REG_ARM_LR;
case UNW_ARM_R15:
return PERF_REG_ARM_PC;
default:
pr_err("unwind: invalid reg id %d\n", regnum);
return -EINVAL;
}
return -EINVAL;
}

Просмотреть файл

@ -29,6 +29,10 @@ ifeq ($(ARCH),x86_64)
NO_PERF_REGS := 0
LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
endif
ifeq ($(ARCH),arm)
NO_PERF_REGS := 0
LIBUNWIND_LIBS = -lunwind -lunwind-arm
endif
ifeq ($(NO_PERF_REGS),0)
CFLAGS += -DHAVE_PERF_REGS
@ -208,8 +212,7 @@ ifeq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_LIBELF),-DLIBELF_MMAP),y)
endif # try-cc
endif # NO_LIBELF
# There's only x86 (both 32 and 64) support for CFI unwind so far
ifneq ($(ARCH),x86)
ifeq ($(LIBUNWIND_LIBS),)
NO_LIBUNWIND := 1
endif
@ -223,9 +226,13 @@ endif
FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(CFLAGS) $(LIBUNWIND_LDFLAGS) $(LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS)
ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND),libunwind),y)
msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99);
msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 1.1);
NO_LIBUNWIND := 1
endif # Libunwind support
ifneq ($(call try-cc,$(SOURCE_LIBUNWIND_DEBUG_FRAME),$(FLAGS_UNWIND),libunwind debug_frame),y)
msg := $(warning No debug_frame support found in libunwind);
CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME
endif # debug_frame support in libunwind
endif # NO_LIBUNWIND
ifndef NO_LIBUNWIND

Просмотреть файл

@ -185,7 +185,6 @@ extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
unw_proc_info_t *pi,
int need_unwind_info, void *arg);
#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
int main(void)
@ -197,6 +196,26 @@ int main(void)
return 0;
}
endef
define SOURCE_LIBUNWIND_DEBUG_FRAME
#include <libunwind.h>
#include <stdlib.h>
extern int
UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug,
unw_word_t ip, unw_word_t segbase,
const char *obj_name, unw_word_t start,
unw_word_t end);
#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame)
int main(void)
{
dwarf_find_debug_frame(0, NULL, 0, 0, NULL, 0, 0);
return 0;
}
endef
endif
ifndef NO_BACKTRACE

Просмотреть файл

@ -39,6 +39,15 @@ UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
extern int
UNW_OBJ(dwarf_find_debug_frame) (int found, unw_dyn_info_t *di_debug,
unw_word_t ip,
unw_word_t segbase,
const char *obj_name, unw_word_t start,
unw_word_t end);
#define dwarf_find_debug_frame UNW_OBJ(dwarf_find_debug_frame)
#define DW_EH_PE_FORMAT_MASK 0x0f /* format of the encoded value */
#define DW_EH_PE_APPL_MASK 0x70 /* how the value is to be applied */
@ -245,8 +254,9 @@ static int unwind_spec_ehframe(struct dso *dso, struct machine *machine,
return 0;
}
static int read_unwind_spec(struct dso *dso, struct machine *machine,
u64 *table_data, u64 *segbase, u64 *fde_count)
static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
u64 *table_data, u64 *segbase,
u64 *fde_count)
{
int ret = -EINVAL, fd;
u64 offset;
@ -255,6 +265,7 @@ static int read_unwind_spec(struct dso *dso, struct machine *machine,
if (fd < 0)
return -EINVAL;
/* Check the .eh_frame section for unwinding info */
offset = elf_section_offset(fd, ".eh_frame_hdr");
close(fd);
@ -263,10 +274,29 @@ static int read_unwind_spec(struct dso *dso, struct machine *machine,
table_data, segbase,
fde_count);
/* TODO .debug_frame check if eh_frame_hdr fails */
return ret;
}
#ifndef NO_LIBUNWIND_DEBUG_FRAME
static int read_unwind_spec_debug_frame(struct dso *dso,
struct machine *machine, u64 *offset)
{
int fd = dso__data_fd(dso, machine);
if (fd < 0)
return -EINVAL;
/* Check the .debug_frame section for unwinding info */
*offset = elf_section_offset(fd, ".debug_frame");
close(fd);
if (*offset)
return 0;
return -EINVAL;
}
#endif
static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
{
struct addr_location al;
@ -291,20 +321,33 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
pr_debug("unwind: find_proc_info dso %s\n", map->dso->name);
if (read_unwind_spec(map->dso, ui->machine,
&table_data, &segbase, &fde_count))
return -EINVAL;
/* Check the .eh_frame section for unwinding info */
if (!read_unwind_spec_eh_frame(map->dso, ui->machine,
&table_data, &segbase, &fde_count)) {
memset(&di, 0, sizeof(di));
di.format = UNW_INFO_FORMAT_REMOTE_TABLE;
di.start_ip = map->start;
di.end_ip = map->end;
di.u.rti.segbase = map->start + segbase;
di.u.rti.table_data = map->start + table_data;
di.u.rti.table_len = fde_count * sizeof(struct table_entry)
/ sizeof(unw_word_t);
return dwarf_search_unwind_table(as, ip, &di, pi,
need_unwind_info, arg);
}
memset(&di, 0, sizeof(di));
di.format = UNW_INFO_FORMAT_REMOTE_TABLE;
di.start_ip = map->start;
di.end_ip = map->end;
di.u.rti.segbase = map->start + segbase;
di.u.rti.table_data = map->start + table_data;
di.u.rti.table_len = fde_count * sizeof(struct table_entry)
/ sizeof(unw_word_t);
return dwarf_search_unwind_table(as, ip, &di, pi,
need_unwind_info, arg);
#ifndef NO_LIBUNWIND_DEBUG_FRAME
/* Check the .debug_frame section for unwinding info */
if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
memset(&di, 0, sizeof(di));
dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name,
map->start, map->end);
return dwarf_search_unwind_table(as, ip, &di, pi,
need_unwind_info, arg);
}
#endif
return -EINVAL;
}
static int access_fpreg(unw_addr_space_t __maybe_unused as,