AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-11-24 11:00:56 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm

Browse Source 
Pull ARM updates from Russell King:
 "Included in this series are:

   1. BE8 (modern big endian) changes for ARM from Ben Dooks
   2. big.Little support from Nicolas Pitre and Dave Martin
   3. support for LPAE systems with all system memory above 4GB
   4. Perf updates from Will Deacon
   5. Additional prefetching and other performance improvements from Will.
   6. Neon-optimised AES implementation fro Ard.
   7. A number of smaller fixes scattered around the place.

  There is a rather horrid merge conflict in tools/perf - I was never
  notified of the conflict because it originally occurred between Will's
  tree and other stuff.  Consequently I have a resolution which Will
  forwarded me, which I'll forward on immediately after sending this
  mail.

  The other notable thing is I'm expecting some build breakage in the
  crypto stuff on ARM only with Ard's AES patches.  These were merged
  into a stable git branch which others had already pulled, so there's
  little I can do about this.  The problem is caused because these
  patches have a dependency on some code in the crypto git tree - I
  tried requesting a branch I can pull to resolve these, and all I got
  each time from the crypto people was "we'll revert our patches then"
  which would only make things worse since I still don't have the
  dependent patches.  I've no idea what's going on there or how to
  resolve that, and since I can't split these patches from the rest of
  this pull request, I'm rather stuck with pushing this as-is or
  reverting Ard's patches.

  Since it should "come out in the wash" I've left them in - the only
  build problems they seem to cause at the moment are with randconfigs,
  and since it's a new feature anyway.  However, if by -rc1 the
  dependencies aren't in, I think it'd be best to revert Ard's patches"

I resolved the perf conflict roughly as per the patch sent by Russell,
but there may be some differences.  Any errors are likely mine.  Let's
see how the crypto issues work out..

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (110 commits)
  ARM: 7868/1: arm/arm64: remove atomic_clear_mask() in "include/asm/atomic.h"
  ARM: 7867/1: include: asm: use 'int' instead of 'unsigned long' for 'oldval' in atomic_cmpxchg().
  ARM: 7866/1: include: asm: use 'long long' instead of 'u64' within atomic.h
  ARM: 7871/1: amba: Extend number of IRQS
  ARM: 7887/1: Don't smp_cross_call() on UP devices in arch_irq_work_raise()
  ARM: 7872/1: Support arch_irq_work_raise() via self IPIs
  ARM: 7880/1: Clear the IT state independent of the Thumb-2 mode
  ARM: 7878/1: nommu: Implement dummy early_paging_init()
  ARM: 7876/1: clear Thumb-2 IT state on exception handling
  ARM: 7874/2: bL_switcher: Remove cpu_hotplug_driver_{lock,unlock}()
  ARM: footbridge: fix build warnings for netwinder
  ARM: 7873/1: vfp: clear vfp_current_hw_state for dying cpu
  ARM: fix misplaced arch_virt_to_idmap()
  ARM: 7848/1: mcpm: Implement cpu_kill() to synchronise on powerdown
  ARM: 7847/1: mcpm: Factor out logical-to-physical CPU translation
  ARM: 7869/1: remove unused XSCALE_PMU Kconfig param
  ARM: 7864/1: Handle 64-bit memory in case of 32-bit phys_addr_t
  ARM: 7863/1: Let arm_add_memory() always use 64-bit arguments
  ARM: 7862/1: pcpu: replace __get_cpu_var_uses
  ARM: 7861/1: cacheflush: consolidate single-CPU ARMv7 cache disabling code
  ...
This commit is contained in:
Linus Torvalds 2013-11-14 08:51:29 +09:00
commit f47671e2d8
121 changed files with 8137 additions and 628 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
arch/arm/Kconfig
View File

@ -5,6 +5,7 @@ config ARM
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
select ARCH_HAVE_CUSTOM_GPIO_H
select ARCH_USE_CMPXCHG_LOCKREF
select ARCH_WANT_IPC_PARSE_VERSION
select BUILDTIME_EXTABLE_SORT if MMU
select CLONE_BACKWARDS
@ -51,6 +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
@ -481,6 +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
@ -688,7 +692,6 @@ config ARCH_SA1100
select GENERIC_CLOCKEVENTS
select HAVE_IDE
select ISA
select NEED_MACH_GPIO_H
select NEED_MACH_MEMORY_H
select SPARSE_IRQ
help
@ -1064,11 +1067,6 @@ config IWMMXT
Enable support for iWMMXt context switching at run time if
running on a CPU that supports it.
config XSCALE_PMU
bool
depends on CPU_XSCALE
default y
config MULTI_IRQ_HANDLER
bool
help
@ -1516,6 +1514,32 @@ 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

41
arch/arm/Kconfig.debug
View File

@ -318,6 +318,7 @@ choice
config DEBUG_MSM_UART1
bool "Kernel low-level debugging messages via MSM UART1"
depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50
select DEBUG_MSM_UART
help
Say Y here if you want the debug print routines to direct
their output to the first serial port on MSM devices.
@ -325,6 +326,7 @@ choice
config DEBUG_MSM_UART2
bool "Kernel low-level debugging messages via MSM UART2"
depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50
select DEBUG_MSM_UART
help
Say Y here if you want the debug print routines to direct
their output to the second serial port on MSM devices.
@ -332,6 +334,7 @@ choice
config DEBUG_MSM_UART3
bool "Kernel low-level debugging messages via MSM UART3"
depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50
select DEBUG_MSM_UART
help
Say Y here if you want the debug print routines to direct
their output to the third serial port on MSM devices.
@ -340,6 +343,7 @@ choice
bool "Kernel low-level debugging messages via MSM 8660 UART"
depends on ARCH_MSM8X60
select MSM_HAS_DEBUG_UART_HS
select DEBUG_MSM_UART
help
Say Y here if you want the debug print routines to direct
their output to the serial port on MSM 8660 devices.
@ -348,10 +352,20 @@ choice
bool "Kernel low-level debugging messages via MSM 8960 UART"
depends on ARCH_MSM8960
select MSM_HAS_DEBUG_UART_HS
select DEBUG_MSM_UART
help
Say Y here if you want the debug print routines to direct
their output to the serial port on MSM 8960 devices.
config DEBUG_MSM8974_UART
bool "Kernel low-level debugging messages via MSM 8974 UART"
depends on ARCH_MSM8974
select MSM_HAS_DEBUG_UART_HS
select DEBUG_MSM_UART
help
Say Y here if you want the debug print routines to direct
their output to the serial port on MSM 8974 devices.
config DEBUG_MVEBU_UART
bool "Kernel low-level debugging messages via MVEBU UART (old bootloaders)"
depends on ARCH_MVEBU
@ -841,6 +855,20 @@ choice
options; the platform specific options are deprecated
and will be soon removed.
config DEBUG_LL_UART_EFM32
bool "Kernel low-level debugging via efm32 UART"
depends on ARCH_EFM32
help
Say Y here if you want the debug print routines to direct
their output to an UART or USART port on efm32 based
machines. Use the following addresses for DEBUG_UART_PHYS:
0x4000c000 | USART0
0x4000c400 | USART1
0x4000c800 | USART2
0x4000e000 | UART0
0x4000e400 | UART1
config DEBUG_LL_UART_PL01X
bool "Kernel low-level debugging via ARM Ltd PL01x Primecell UART"
help
@ -887,11 +915,16 @@ config DEBUG_STI_UART
bool
depends on ARCH_STI
config DEBUG_MSM_UART
bool
depends on ARCH_MSM
config DEBUG_LL_INCLUDE
string
default "debug/8250.S" if DEBUG_LL_UART_8250 || DEBUG_UART_8250
default "debug/pl01x.S" if DEBUG_LL_UART_PL01X || DEBUG_UART_PL01X
default "debug/exynos.S" if DEBUG_EXYNOS_UART
default "debug/efm32.S" if DEBUG_LL_UART_EFM32
default "debug/icedcc.S" if DEBUG_ICEDCC
default "debug/imx.S" if DEBUG_IMX1_UART || \
DEBUG_IMX25_UART || \
@ -902,11 +935,7 @@ config DEBUG_LL_INCLUDE
DEBUG_IMX53_UART ||\
DEBUG_IMX6Q_UART || \
DEBUG_IMX6SL_UART
default "debug/msm.S" if DEBUG_MSM_UART1 || \
DEBUG_MSM_UART2 || \
DEBUG_MSM_UART3 || \
DEBUG_MSM8660_UART || \
DEBUG_MSM8960_UART
default "debug/msm.S" if DEBUG_MSM_UART
default "debug/omap2plus.S" if DEBUG_OMAP2PLUS_UART
default "debug/sirf.S" if DEBUG_SIRFPRIMA2_UART1 || DEBUG_SIRFMARCO_UART1
default "debug/sti.S" if DEBUG_STI_UART
@ -959,6 +988,7 @@ config DEBUG_UART_PHYS
default 0x20064000 if DEBUG_RK29_UART1 || DEBUG_RK3X_UART2
default 0x20068000 if DEBUG_RK29_UART2 || DEBUG_RK3X_UART3
default 0x20201000 if DEBUG_BCM2835
default 0x4000e400 if DEBUG_LL_UART_EFM32
default 0x40090000 if ARCH_LPC32XX
default 0x40100000 if DEBUG_PXA_UART1
default 0x42000000 if ARCH_GEMINI
@ -989,6 +1019,7 @@ config DEBUG_UART_PHYS
default 0xfff36000 if DEBUG_HIGHBANK_UART
default 0xfffff700 if ARCH_IOP33X
depends on DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \
DEBUG_LL_UART_EFM32 || \
DEBUG_UART_8250 || DEBUG_UART_PL01X
config DEBUG_UART_VIRT

1
arch/arm/Makefile
View File

@ -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

9
arch/arm/boot/compressed/head.S
View File

@ -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

2
arch/arm/common/Makefile
View File

@ -16,3 +16,5 @@ 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

822
arch/arm/common/bL_switcher.c Normal file
View File

@ -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);

71
arch/arm/common/bL_switcher_dummy_if.c Normal file
View File

@ -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);

27
arch/arm/common/mcpm_entry.c
View File

@ -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)
@ -90,6 +102,21 @@ void mcpm_cpu_power_down(void)
BUG();
}
int mcpm_cpu_power_down_finish(unsigned int cpu, unsigned int cluster)
{
int ret;
if (WARN_ON_ONCE(!platform_ops || !platform_ops->power_down_finish))
return -EUNATCH;
ret = platform_ops->power_down_finish(cpu, cluster);
if (ret)
pr_warn("%s: cpu %u, cluster %u failed to power down (%d)\n",
__func__, cpu, cluster, ret);
return ret;
}
void mcpm_cpu_suspend(u64 expected_residency)
{
phys_reset_t phys_reset;

18
arch/arm/common/mcpm_head.S
View File

@ -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()

29
arch/arm/common/mcpm_platsmp.c
View File

@ -19,14 +19,23 @@
#include <asm/smp.h>
#include <asm/smp_plat.h>
static int mcpm_boot_secondary(unsigned int cpu, struct task_struct *idle)
static void cpu_to_pcpu(unsigned int cpu,
unsigned int *pcpu, unsigned int *pcluster)
{
unsigned int mpidr, pcpu, pcluster, ret;
extern void secondary_startup(void);
unsigned int mpidr;
mpidr = cpu_logical_map(cpu);
pcpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
pcluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
*pcpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
*pcluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
}
static int mcpm_boot_secondary(unsigned int cpu, struct task_struct *idle)
{
unsigned int pcpu, pcluster, ret;
extern void secondary_startup(void);
cpu_to_pcpu(cpu, &pcpu, &pcluster);
pr_debug("%s: logical CPU %d is physical CPU %d cluster %d\n",
__func__, cpu, pcpu, pcluster);
@ -47,6 +56,15 @@ static void mcpm_secondary_init(unsigned int cpu)
#ifdef CONFIG_HOTPLUG_CPU
static int mcpm_cpu_kill(unsigned int cpu)
{
unsigned int pcpu, pcluster;
cpu_to_pcpu(cpu, &pcpu, &pcluster);
return !mcpm_cpu_power_down_finish(pcpu, pcluster);
}
static int mcpm_cpu_disable(unsigned int cpu)
{
/*
@ -73,6 +91,7 @@ static struct smp_operations __initdata mcpm_smp_ops = {
.smp_boot_secondary = mcpm_boot_secondary,
.smp_secondary_init = mcpm_secondary_init,
#ifdef CONFIG_HOTPLUG_CPU
.cpu_kill = mcpm_cpu_kill,
.cpu_disable = mcpm_cpu_disable,
.cpu_die = mcpm_cpu_die,
#endif

2
arch/arm/common/timer-sp.c
View File

@ -175,7 +175,7 @@ static struct clock_event_device sp804_clockevent = {
static struct irqaction sp804_timer_irq = {
.name = "timer",
.flags = IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
.flags = IRQF_TIMER | IRQF_IRQPOLL,
.handler = sp804_timer_interrupt,
.dev_id = &sp804_clockevent,
};

22
arch/arm/configs/h3600_defconfig
View File

@ -1,5 +1,6 @@
CONFIG_EXPERIMENTAL=y
CONFIG_SYSVIPC=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
CONFIG_LOG_BUF_SHIFT=14
CONFIG_BLK_DEV_INITRD=y
CONFIG_MODULES=y
@ -11,11 +12,11 @@ CONFIG_ARCH_SA1100=y
CONFIG_SA1100_H3600=y
CONFIG_PCCARD=y
CONFIG_PCMCIA_SA1100=y
CONFIG_PREEMPT=y
CONFIG_ZBOOT_ROM_TEXT=0x0
CONFIG_ZBOOT_ROM_BSS=0x0
# CONFIG_CPU_FREQ_STAT is not set
CONFIG_FPE_NWFPE=y
CONFIG_PM=y
CONFIG_NET=y
CONFIG_UNIX=y
CONFIG_INET=y
@ -24,13 +25,10 @@ CONFIG_IRDA=m
CONFIG_IRLAN=m
CONFIG_IRNET=m
CONFIG_IRCOMM=m
CONFIG_SA1100_FIR=m
# CONFIG_WIRELESS is not set
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_MTD=y
CONFIG_MTD_PARTITIONS=y
CONFIG_MTD_REDBOOT_PARTS=y
CONFIG_MTD_CHAR=y
CONFIG_MTD_BLOCK=y
CONFIG_MTD_CFI=y
CONFIG_MTD_CFI_ADV_OPTIONS=y
@ -41,19 +39,15 @@ CONFIG_MTD_SA1100=y
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=8192
# CONFIG_MISC_DEVICES is not set
CONFIG_IDE=y
CONFIG_BLK_DEV_IDECS=y
CONFIG_NETDEVICES=y
# CONFIG_NETDEV_1000 is not set
# CONFIG_NETDEV_10000 is not set
# CONFIG_WLAN is not set
CONFIG_NET_PCMCIA=y
CONFIG_PCMCIA_PCNET=y
CONFIG_PPP=m
CONFIG_PPP_ASYNC=m
CONFIG_PPP_DEFLATE=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
CONFIG_PPP_ASYNC=m
# CONFIG_WLAN is not set
# CONFIG_KEYBOARD_ATKBD is not set
CONFIG_KEYBOARD_GPIO=y
# CONFIG_INPUT_MOUSE is not set
@ -64,8 +58,6 @@ CONFIG_SERIAL_SA1100_CONSOLE=y
# CONFIG_HWMON is not set
CONFIG_FB=y
CONFIG_FB_SA1100=y
# CONFIG_VGA_CONSOLE is not set
# CONFIG_HID_SUPPORT is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_EXT2_FS=y
CONFIG_MSDOS_FS=m
@ -74,6 +66,4 @@ CONFIG_JFFS2_FS=y
CONFIG_CRAMFS=m
CONFIG_NFS_FS=y
CONFIG_NFSD=m
CONFIG_SMB_FS=m
CONFIG_NLS=y
# CONFIG_RCU_CPU_STALL_DETECTOR is not set

1
arch/arm/crypto/.gitignore vendored Normal file
View File

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

14
arch/arm/crypto/Makefile
View File

@ -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

22
arch/arm/crypto/aes_glue.c
View File

@ -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
}

19
arch/arm/crypto/aes_glue.h Normal file
View File

@ -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);

2544
arch/arm/crypto/aesbs-core.S_shipped Normal file
View File

File diff suppressed because it is too large Load Diff

434
arch/arm/crypto/aesbs-glue.c Normal file
View File

@ -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");

2467
arch/arm/crypto/bsaes-armv7.pl Normal file
View File

File diff suppressed because it is too large Load Diff

1
arch/arm/include/asm/Kbuild
View File

@ -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

7
arch/arm/include/asm/assembler.h
View File

@ -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
*/

108
arch/arm/include/asm/atomic.h
View File

@ -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"
@ -114,7 +117,8 @@ static inline int atomic_sub_return(int i, atomic_t *v)
static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
{
unsigned long oldval, res;
int oldval;
unsigned long res;
smp_mb();
@ -134,21 +138,6 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
return oldval;
}
static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
{
unsigned long tmp, tmp2;
__asm__ __volatile__("@ atomic_clear_mask\n"
"1: ldrex %0, [%3]\n"
" bic %0, %0, %4\n"
" strex %1, %0, [%3]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (tmp), "=&r" (tmp2), "+Qo" (*addr)
: "r" (addr), "Ir" (mask)
: "cc");
}
#else /* ARM_ARCH_6 */
#ifdef CONFIG_SMP
@ -197,15 +186,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
return ret;
}
static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
{
unsigned long flags;
raw_local_irq_save(flags);
*addr &= ~mask;
raw_local_irq_restore(flags);
}
#endif /* __LINUX_ARM_ARCH__ */
#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
@ -238,15 +218,15 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
#ifndef CONFIG_GENERIC_ATOMIC64
typedef struct {
u64 __aligned(8) counter;
long long counter;
} atomic64_t;
#define ATOMIC64_INIT(i) { (i) }
#ifdef CONFIG_ARM_LPAE
static inline u64 atomic64_read(const atomic64_t *v)
static inline long long atomic64_read(const atomic64_t *v)
{
u64 result;
long long result;
__asm__ __volatile__("@ atomic64_read\n"
" ldrd %0, %H0, [%1]"
@ -257,7 +237,7 @@ static inline u64 atomic64_read(const atomic64_t *v)
return result;
}
static inline void atomic64_set(atomic64_t *v, u64 i)
static inline void atomic64_set(atomic64_t *v, long long i)
{
__asm__ __volatile__("@ atomic64_set\n"
" strd %2, %H2, [%1]"
@ -266,9 +246,9 @@ static inline void atomic64_set(atomic64_t *v, u64 i)
);
}
#else
static inline u64 atomic64_read(const atomic64_t *v)
static inline long long atomic64_read(const atomic64_t *v)
{
u64 result;
long long result;
__asm__ __volatile__("@ atomic64_read\n"
" ldrexd %0, %H0, [%1]"
@ -279,10 +259,11 @@ static inline u64 atomic64_read(const atomic64_t *v)
return result;
}
static inline void atomic64_set(atomic64_t *v, u64 i)
static inline void atomic64_set(atomic64_t *v, long long i)
{
u64 tmp;
long long tmp;
prefetchw(&v->counter);
__asm__ __volatile__("@ atomic64_set\n"
"1: ldrexd %0, %H0, [%2]\n"
" strexd %0, %3, %H3, [%2]\n"
@ -294,15 +275,16 @@ static inline void atomic64_set(atomic64_t *v, u64 i)
}
#endif
static inline void atomic64_add(u64 i, atomic64_t *v)
static inline void atomic64_add(long long i, atomic64_t *v)
{
u64 result;
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"
@ -311,17 +293,17 @@ static inline void atomic64_add(u64 i, atomic64_t *v)
: "cc");
}
static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
static inline long long atomic64_add_return(long long i, atomic64_t *v)
{
u64 result;
long long result;
unsigned long tmp;
smp_mb();
__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"
@ -334,15 +316,16 @@ static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
return result;
}
static inline void atomic64_sub(u64 i, atomic64_t *v)
static inline void atomic64_sub(long long i, atomic64_t *v)
{
u64 result;
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"
@ -351,17 +334,17 @@ static inline void atomic64_sub(u64 i, atomic64_t *v)
: "cc");
}
static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
static inline long long atomic64_sub_return(long long i, atomic64_t *v)
{
u64 result;
long long result;
unsigned long tmp;
smp_mb();
__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"
@ -374,9 +357,10 @@ static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
return result;
}
static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new)
static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old,
long long new)
{
u64 oldval;
long long oldval;
unsigned long res;
smp_mb();
@ -398,9 +382,9 @@ static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new)
return oldval;
}
static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new)
static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
{
u64 result;
long long result;
unsigned long tmp;
smp_mb();
@ -419,18 +403,18 @@ static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new)
return result;
}
static inline u64 atomic64_dec_if_positive(atomic64_t *v)
static inline long long atomic64_dec_if_positive(atomic64_t *v)
{
u64 result;
long long result;
unsigned long tmp;
smp_mb();
__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"
@ -445,9 +429,9 @@ static inline u64 atomic64_dec_if_positive(atomic64_t *v)
return result;
}
static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
{
u64 val;
long long val;
unsigned long tmp;
int ret = 1;
@ -459,8 +443,8 @@ static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 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"

77
arch/arm/include/asm/bL_switcher.h Normal file
View File

@ -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

10
arch/arm/include/asm/bug.h
View File

@ -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 */

46
arch/arm/include/asm/cacheflush.h
View File

@ -435,4 +435,50 @@ static inline void __sync_cache_range_r(volatile void *p, size_t size)
#define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr))
#define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr))
/*
* Disabling cache access for one CPU in an ARMv7 SMP system is tricky.
* To do so we must:
*
* - Clear the SCTLR.C bit to prevent further cache allocations
* - Flush the desired level of cache
* - Clear the ACTLR "SMP" bit to disable local coherency
*
* ... and so without any intervening memory access in between those steps,
* not even to the stack.
*
* WARNING -- After this has been called:
*
* - No ldrex/strex (and similar) instructions must be used.
* - The CPU is obviously no longer coherent with the other CPUs.
* - This is unlikely to work as expected if Linux is running non-secure.
*
* Note:
*
* - This is known to apply to several ARMv7 processor implementations,
* however some exceptions may exist. Caveat emptor.
*
* - The clobber list is dictated by the call to v7_flush_dcache_*.
* fp is preserved to the stack explicitly prior disabling the cache
* since adding it to the clobber list is incompatible with having
* CONFIG_FRAME_POINTER=y. ip is saved as well if ever r12-clobbering
* trampoline are inserted by the linker and to keep sp 64-bit aligned.
*/
#define v7_exit_coherency_flush(level) \
asm volatile( \
"stmfd sp!, {fp, ip} \n\t" \
"mrc p15, 0, r0, c1, c0, 0 @ get SCTLR \n\t" \
"bic r0, r0, #"__stringify(CR_C)" \n\t" \
"mcr p15, 0, r0, c1, c0, 0 @ set SCTLR \n\t" \
"isb \n\t" \
"bl v7_flush_dcache_"__stringify(level)" \n\t" \
"clrex \n\t" \
"mrc p15, 0, r0, c1, c0, 1 @ get ACTLR \n\t" \
"bic r0, r0, #(1 << 6) @ disable local coherency \n\t" \
"mcr p15, 0, r0, c1, c0, 1 @ set ACTLR \n\t" \
"isb \n\t" \
"dsb \n\t" \
"ldmfd sp!, {fp, ip}" \
: : : "r0","r1","r2","r3","r4","r5","r6","r7", \
"r9","r10","lr","memory" )
#endif

56
arch/arm/include/asm/cmpxchg.h
View File

@ -223,6 +223,42 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
return ret;
}
static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
unsigned long long old,
unsigned long long new)
{
unsigned long long oldval;
unsigned long res;
__asm__ __volatile__(
"1: ldrexd %1, %H1, [%3]\n"
" teq %1, %4\n"
" teqeq %H1, %H4\n"
" bne 2f\n"
" strexd %0, %5, %H5, [%3]\n"
" teq %0, #0\n"
" bne 1b\n"
"2:"
: "=&r" (res), "=&r" (oldval), "+Qo" (*ptr)
: "r" (ptr), "r" (old), "r" (new)
: "cc");
return oldval;
}
static inline unsigned long long __cmpxchg64_mb(unsigned long long *ptr,
unsigned long long old,
unsigned long long new)
{
unsigned long long ret;
smp_mb();
ret = __cmpxchg64(ptr, old, new);
smp_mb();
return ret;
}
#define cmpxchg_local(ptr,o,n) \
((__typeof__(*(ptr)))__cmpxchg_local((ptr), \
(unsigned long)(o), \
@ -230,18 +266,16 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
sizeof(*(ptr))))
#define cmpxchg64(ptr, o, n) \
((__typeof__(*(ptr)))atomic64_cmpxchg(container_of((ptr), \
atomic64_t, \
counter), \
(unsigned long long)(o), \
(unsigned long long)(n)))
((__typeof__(*(ptr)))__cmpxchg64_mb((ptr), \
(unsigned long long)(o), \
(unsigned long long)(n)))
#define cmpxchg64_local(ptr, o, n) \
((__typeof__(*(ptr)))local64_cmpxchg(container_of((ptr), \
local64_t, \
a), \
(unsigned long long)(o), \
(unsigned long long)(n)))
#define cmpxchg64_relaxed(ptr, o, n) \
((__typeof__(*(ptr)))__cmpxchg64((ptr), \
(unsigned long long)(o), \
(unsigned long long)(n)))
#define cmpxchg64_local(ptr, o, n) cmpxchg64_relaxed((ptr), (o), (n))
#endif /* __LINUX_ARM_ARCH__ >= 6 */

1
arch/arm/include/asm/cputype.h
View File

@ -10,6 +10,7 @@
#define CPUID_TLBTYPE 3
#define CPUID_MPUIR 4
#define CPUID_MPIDR 5
#define CPUID_REVIDR 6
#ifdef CONFIG_CPU_V7M
#define CPUID_EXT_PFR0 0x40

2
arch/arm/include/asm/hardirq.h
View File

@ -5,7 +5,7 @@
#include <linux/threads.h>
#include <asm/irq.h>
#define NR_IPI 6
#define NR_IPI 8
typedef struct {
unsigned int __softirq_pending;

8
arch/arm/include/asm/hardware/coresight.h
View File

@ -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) \

3
arch/arm/include/asm/kgdb.h
View File

@ -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);

1
arch/arm/include/asm/mach/arch.h
View File

@ -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);

39
arch/arm/include/asm/mcpm.h
View File

@ -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.
*/
@ -81,9 +89,39 @@ int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster);
*
* This will return if mcpm_platform_register() has not been called
* previously in which case the caller should take appropriate action.
*
* On success, the CPU is not guaranteed to be truly halted until
* mcpm_cpu_power_down_finish() subsequently returns non-zero for the
* specified cpu. Until then, other CPUs should make sure they do not
* trash memory the target CPU might be executing/accessing.
*/
void mcpm_cpu_power_down(void);
/**
* mcpm_cpu_power_down_finish - wait for a specified CPU to halt, and
* make sure it is powered off
*
* @cpu: CPU number within given cluster
* @cluster: cluster number for the CPU
*
* Call this function to ensure that a pending powerdown has taken
* effect and the CPU is safely parked before performing non-mcpm
* operations that may affect the CPU (such as kexec trashing the
* kernel text).
*
* It is *not* necessary to call this function if you only need to
* serialise a pending powerdown with mcpm_cpu_power_up() or a wakeup
* event.
*
* Do not call this function unless the specified CPU has already
* called mcpm_cpu_power_down() or has committed to doing so.
*
* @return:
* - zero if the CPU is in a safely parked state
* - nonzero otherwise (e.g., timeout)
*/
int mcpm_cpu_power_down_finish(unsigned int cpu, unsigned int cluster);
/**
* mcpm_cpu_suspend - bring the calling CPU in a suspended state
*
@ -126,6 +164,7 @@ int mcpm_cpu_powered_up(void);
struct mcpm_platform_ops {
int (*power_up)(unsigned int cpu, unsigned int cluster);
void (*power_down)(void);
int (*power_down_finish)(unsigned int cpu, unsigned int cluster);
void (*suspend)(u64);
void (*powered_up)(void);
};

76
arch/arm/include/asm/memory.h
View File

@ -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

2
arch/arm/include/asm/mmu.h
View File

@ -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

7
arch/arm/include/asm/pgtable-2level.h
View File

@ -181,6 +181,13 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
/*
* We don't have huge page support for short descriptors, for the moment
* define empty stubs for use by pin_page_for_write.
*/
#define pmd_hugewillfault(pmd) (0)
#define pmd_thp_or_huge(pmd) (0)
#endif /* __ASSEMBLY__ */
#endif /* _ASM_PGTABLE_2LEVEL_H */

3
arch/arm/include/asm/pgtable-3level.h
View File

@ -206,6 +206,9 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) (!(pmd_val(pmd) & PMD_SECT_RDONLY))
#define pmd_hugewillfault(pmd) (!pmd_young(pmd) || !pmd_write(pmd))
#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd))
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define pmd_trans_huge(pmd) (pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)

33
arch/arm/include/asm/processor.h
View File

@ -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

2
arch/arm/include/asm/setup.h
View File

@ -49,7 +49,7 @@ extern struct meminfo meminfo;
#define bank_phys_end(bank) ((bank)->start + (bank)->size)
#define bank_phys_size(bank) (bank)->size
extern int arm_add_memory(phys_addr_t start, phys_addr_t size);
extern int arm_add_memory(u64 start, u64 size);
extern void early_print(const char *str, ...);
extern void dump_machine_table(void);

2
arch/arm/include/asm/smp.h
View File

@ -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
/*

36
arch/arm/include/asm/spinlock.h
View File

@ -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"
@ -127,10 +122,14 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
dsb_sev();
}
static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
{
return lock.tickets.owner == lock.tickets.next;
}
static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
struct __raw_tickets tickets = ACCESS_ONCE(lock->tickets);
return tickets.owner != tickets.next;
return !arch_spin_value_unlocked(ACCESS_ONCE(*lock));
}
static inline int arch_spin_is_contended(arch_spinlock_t *lock)
@ -152,6 +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"
@ -170,6 +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"
@ -203,7 +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:
@ -221,6 +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"
@ -241,6 +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"
@ -259,6 +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"
@ -280,7 +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)

2
arch/arm/include/asm/spinlock_types.h
View File

@ -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 }

48
arch/arm/include/asm/tlbflush.h
View File

@ -560,37 +560,6 @@ static inline void __flush_bp_all(void)
asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero));
}
#include <asm/cputype.h>
#ifdef CONFIG_ARM_ERRATA_798181
static inline int erratum_a15_798181(void)
{
unsigned int midr = read_cpuid_id();
/* Cortex-A15 r0p0..r3p2 affected */
if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2)
return 0;
return 1;
}
static inline void dummy_flush_tlb_a15_erratum(void)
{
/*
* Dummy TLBIMVAIS. Using the unmapped address 0 and ASID 0.
*/
asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0));
dsb(ish);
}
#else
static inline int erratum_a15_798181(void)
{
return 0;
}
static inline void dummy_flush_tlb_a15_erratum(void)
{
}
#endif
/*
* flush_pmd_entry
*
@ -697,4 +666,21 @@ extern void flush_bp_all(void);
#endif
#ifndef __ASSEMBLY__
#ifdef CONFIG_ARM_ERRATA_798181
extern void erratum_a15_798181_init(void);
#else
static inline void erratum_a15_798181_init(void) {}
#endif
extern bool (*erratum_a15_798181_handler)(void);
static inline bool erratum_a15_798181(void)
{
if (unlikely(IS_ENABLED(CONFIG_ARM_ERRATA_798181) &&
erratum_a15_798181_handler))
return erratum_a15_798181_handler();
return false;
}
#endif
#endif

4
arch/arm/include/asm/unified.h
View File

@ -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 */

45
arch/arm/include/debug/efm32.S Normal file
View File

@ -0,0 +1,45 @@
/*
* Copyright (C) 2013 Pengutronix
* Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>
*
* 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.
*/
#define UARTn_CMD 0x000c
#define UARTn_CMD_TXEN 0x0004
#define UARTn_STATUS 0x0010
#define UARTn_STATUS_TXC 0x0020
#define UARTn_STATUS_TXBL 0x0040
#define UARTn_TXDATA 0x0034
.macro addruart, rx, tmp
ldr \rx, =(CONFIG_DEBUG_UART_PHYS)
/*
* enable TX. The driver might disable it to save energy. We
* don't care about disabling at the end as during debug power
* consumption isn't that important.
*/
ldr \tmp, =(UARTn_CMD_TXEN)
str \tmp, [\rx, #UARTn_CMD]
.endm
.macro senduart,rd,rx
strb \rd, [\rx, #UARTn_TXDATA]
.endm
.macro waituart,rd,rx
1001: ldr \rd, [\rx, #UARTn_STATUS]
tst \rd, #UARTn_STATUS_TXBL
beq 1001b
.endm
.macro busyuart,rd,rx
1001: ldr \rd, [\rx, UARTn_STATUS]
tst \rd, #UARTn_STATUS_TXC
bne 1001b
.endm

5
arch/arm/include/debug/msm.S
View File

@ -44,6 +44,11 @@
#ifdef CONFIG_DEBUG_MSM8960_UART
#define MSM_DEBUG_UART_BASE 0xF0040000
#define MSM_DEBUG_UART_PHYS 0x16440000
#endif
#ifdef CONFIG_DEBUG_MSM8974_UART
#define MSM_DEBUG_UART_BASE 0xFA71E000
#define MSM_DEBUG_UART_PHYS 0xF991E000
#endif
.macro addruart, rp, rv, tmp

2
arch/arm/include/debug/pl01x.S
View File

@ -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

1
arch/arm/include/uapi/asm/Kbuild
View File

@ -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

23
arch/arm/include/uapi/asm/perf_regs.h Normal file
View File

@ -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 */

4
arch/arm/kernel/Makefile
View File

@ -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

1
arch/arm/kernel/armksyms.c
View File

@ -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

6
arch/arm/kernel/entry-armv.S
View File

@ -192,6 +192,7 @@ __dabt_svc:
svc_entry
mov r2, sp
dabt_helper
THUMB( ldr r5, [sp, #S_PSR] ) @ potentially updated CPSR
svc_exit r5 @ return from exception
UNWIND(.fnend )
ENDPROC(__dabt_svc)
@ -416,9 +417,8 @@ __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

4
arch/arm/kernel/entry-common.S
View File

@ -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)

82
arch/arm/kernel/head.S
View File

@ -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"

14
arch/arm/kernel/hw_breakpoint.c
View File

@ -344,13 +344,13 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
/* Breakpoint */
ctrl_base = ARM_BASE_BCR;
val_base = ARM_BASE_BVR;
slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
slots = this_cpu_ptr(bp_on_reg);
max_slots = core_num_brps;
} else {
/* Watchpoint */
ctrl_base = ARM_BASE_WCR;
val_base = ARM_BASE_WVR;
slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
slots = this_cpu_ptr(wp_on_reg);
max_slots = core_num_wrps;
}
@ -396,12 +396,12 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
/* Breakpoint */
base = ARM_BASE_BCR;
slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
slots = this_cpu_ptr(bp_on_reg);
max_slots = core_num_brps;
} else {
/* Watchpoint */
base = ARM_BASE_WCR;
slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
slots = this_cpu_ptr(wp_on_reg);
max_slots = core_num_wrps;
}
@ -697,7 +697,7 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr,
struct arch_hw_breakpoint *info;
struct arch_hw_breakpoint_ctrl ctrl;
slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
slots = this_cpu_ptr(wp_on_reg);
for (i = 0; i < core_num_wrps; ++i) {
rcu_read_lock();
@ -768,7 +768,7 @@ static void watchpoint_single_step_handler(unsigned long pc)
struct perf_event *wp, **slots;
struct arch_hw_breakpoint *info;
slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
slots = this_cpu_ptr(wp_on_reg);
for (i = 0; i < core_num_wrps; ++i) {
rcu_read_lock();
@ -802,7 +802,7 @@ static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs)
struct arch_hw_breakpoint *info;
struct arch_hw_breakpoint_ctrl ctrl;
slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
slots = this_cpu_ptr(bp_on_reg);
/* The exception entry code places the amended lr in the PC. */
addr = regs->ARM_pc;

8
arch/arm/kernel/kprobes.c
View File

@ -171,13 +171,13 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
{
__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
kcb->kprobe_status = kcb->prev_kprobe.status;
}
static void __kprobes set_current_kprobe(struct kprobe *p)
{
__get_cpu_var(current_kprobe) = p;
__this_cpu_write(current_kprobe, p);
}
static void __kprobes
@ -421,10 +421,10 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
continue;
if (ri->rp && ri->rp->handler) {
__get_cpu_var(current_kprobe) = &ri->rp->kp;
__this_cpu_write(current_kprobe, &ri->rp->kp);
get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
ri->rp->handler(ri, regs);
__get_cpu_var(current_kprobe) = NULL;
__this_cpu_write(current_kprobe, NULL);
}
orig_ret_address = (unsigned long)ri->ret_addr;

57
arch/arm/kernel/module.c
View File

@ -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

3
arch/arm/kernel/perf_event.c
View File

@ -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)

2
arch/arm/kernel/perf_event_cpu.c
View File

@ -68,7 +68,7 @@ EXPORT_SYMBOL_GPL(perf_num_counters);
static struct pmu_hw_events *cpu_pmu_get_cpu_events(void)
{
return &__get_cpu_var(cpu_hw_events);
return this_cpu_ptr(&cpu_hw_events);
}
static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)

30
arch/arm/kernel/perf_regs.c Normal file
View File

@ -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;
}

28
arch/arm/kernel/setup.c
View File

@ -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);
@ -599,6 +601,8 @@ static void __init setup_processor(void)
elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT);
#endif
erratum_a15_798181_init();
feat_v6_fixup();
cacheid_init();
@ -619,9 +623,10 @@ void __init dump_machine_table(void)
/* can't use cpu_relax() here as it may require MMU setup */;
}
int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
int __init arm_add_memory(u64 start, u64 size)
{
struct membank *bank = &meminfo.bank[meminfo.nr_banks];
u64 aligned_start;
if (meminfo.nr_banks >= NR_BANKS) {
printk(KERN_CRIT "NR_BANKS too low, "
@ -634,10 +639,16 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
* Size is appropriately rounded down, start is rounded up.
*/
size -= start & ~PAGE_MASK;
bank->start = PAGE_ALIGN(start);
aligned_start = PAGE_ALIGN(start);
#ifndef CONFIG_ARM_LPAE
if (bank->start + size < bank->start) {
#ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT
if (aligned_start > ULONG_MAX) {
printk(KERN_CRIT "Ignoring memory at 0x%08llx outside "
"32-bit physical address space\n", (long long)start);
return -EINVAL;
}
if (aligned_start + size > ULONG_MAX) {
printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in "
"32-bit physical address space\n", (long long)start);
/*
@ -645,10 +656,11 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
* 32 bits, we use ULONG_MAX as the upper limit rather than 4GB.
* This means we lose a page after masking.
*/
size = ULONG_MAX - bank->start;
size = ULONG_MAX - aligned_start;
}
#endif
bank->start = aligned_start;
bank->size = size & ~(phys_addr_t)(PAGE_SIZE - 1);
/*
@ -669,8 +681,8 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
static int __init early_mem(char *p)
{
static int usermem __initdata = 0;
phys_addr_t size;
phys_addr_t start;
u64 size;
u64 start;
char *endp;
/*
@ -878,6 +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);

38
arch/arm/kernel/signal.c
View File

@ -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;
@ -375,12 +353,18 @@ setup_return(struct pt_regs *regs, struct ksignal *ksig,
*/
thumb = handler & 1;
#if __LINUX_ARM_ARCH__ >= 7
/*
* Clear the If-Then Thumb-2 execution state
* ARM spec requires this to be all 000s in ARM mode
* Snapdragon S4/Krait misbehaves on a Thumb=>ARM
* signal transition without this.
*/
cpsr &= ~PSR_IT_MASK;
#endif
if (thumb) {
cpsr |= PSR_T_BIT;
#if __LINUX_ARM_ARCH__ >= 7
/* clear the If-Then Thumb-2 execution state */
cpsr &= ~PSR_IT_MASK;
#endif
} else
cpsr &= ~PSR_T_BIT;
}

80
arch/arm/kernel/sigreturn_codes.S Normal file
View File

@ -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

27
arch/arm/kernel/sleep.S
View File

@ -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)

42
arch/arm/kernel/smp.c
View File

@ -25,6 +25,7 @@
#include <linux/clockchips.h>
#include <linux/completion.h>
#include <linux/cpufreq.h>
#include <linux/irq_work.h>
#include <linux/atomic.h>
#include <asm/smp.h>
@ -66,6 +67,8 @@ enum ipi_msg_type {
IPI_CALL_FUNC,
IPI_CALL_FUNC_SINGLE,
IPI_CPU_STOP,
IPI_IRQ_WORK,
IPI_COMPLETION,
};
static DECLARE_COMPLETION(cpu_running);
@ -80,7 +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;
}
@ -448,6 +451,14 @@ void arch_send_call_function_single_ipi(int cpu)
smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
}
#ifdef CONFIG_IRQ_WORK
void arch_irq_work_raise(void)
{
if (is_smp())
smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
}
#endif
static const char *ipi_types[NR_IPI] = {
#define S(x,s) [x] = s
S(IPI_WAKEUP, "CPU wakeup interrupts"),
@ -456,6 +467,8 @@ static const char *ipi_types[NR_IPI] = {
S(IPI_CALL_FUNC, "Function call interrupts"),
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)
@ -515,6 +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
*/
@ -565,6 +591,20 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
irq_exit();
break;
#ifdef CONFIG_IRQ_WORK
case IPI_IRQ_WORK:
irq_enter();
irq_work_run();
irq_exit();
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);

14
arch/arm/kernel/smp_scu.c
View File

@ -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;
}

36
arch/arm/kernel/smp_tlb.c
View File

@ -70,6 +70,40 @@ static inline void ipi_flush_bp_all(void *ignored)
local_flush_bp_all();
}
#ifdef CONFIG_ARM_ERRATA_798181
bool (*erratum_a15_798181_handler)(void);
static bool erratum_a15_798181_partial(void)
{
asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0));
dsb(ish);
return false;
}
static bool erratum_a15_798181_broadcast(void)
{
asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0));
dsb(ish);
return true;
}
void erratum_a15_798181_init(void)
{
unsigned int midr = read_cpuid_id();
unsigned int revidr = read_cpuid(CPUID_REVIDR);
/* Cortex-A15 r0p0..r3p2 w/o ECO fix affected */
if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2 ||
(revidr & 0x210) == 0x210) {
return;
}
if (revidr & 0x10)
erratum_a15_798181_handler = erratum_a15_798181_partial;
else
erratum_a15_798181_handler = erratum_a15_798181_broadcast;
}
#endif
static void ipi_flush_tlb_a15_erratum(void *arg)
{
dmb();
@ -80,7 +114,6 @@ static void broadcast_tlb_a15_erratum(void)
if (!erratum_a15_798181())
return;
dummy_flush_tlb_a15_erratum();
smp_call_function(ipi_flush_tlb_a15_erratum, NULL, 1);
}
@ -92,7 +125,6 @@ static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm)
if (!erratum_a15_798181())
return;
dummy_flush_tlb_a15_erratum();
this_cpu = get_cpu();
a15_erratum_get_cpumask(this_cpu, mm, &mask);
smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1);

24
arch/arm/kernel/smp_twd.c
View File

@ -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 |

8
arch/arm/kernel/suspend.c
View File

@ -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

24
arch/arm/kernel/traps.c
View File

@ -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;
}

6
arch/arm/kvm/arm.c
View File

@ -65,7 +65,7 @@ static bool vgic_present;
static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
{
BUG_ON(preemptible());
__get_cpu_var(kvm_arm_running_vcpu) = vcpu;
__this_cpu_write(kvm_arm_running_vcpu, vcpu);
}
/**
@ -75,7 +75,7 @@ static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
struct kvm_vcpu *kvm_arm_get_running_vcpu(void)
{
BUG_ON(preemptible());
return __get_cpu_var(kvm_arm_running_vcpu);
return __this_cpu_read(kvm_arm_running_vcpu);
}
/**
@ -815,7 +815,7 @@ static void cpu_init_hyp_mode(void *dummy)
boot_pgd_ptr = kvm_mmu_get_boot_httbr();
pgd_ptr = kvm_mmu_get_httbr();
stack_page = __get_cpu_var(kvm_arm_hyp_stack_page);
stack_page = __this_cpu_read(kvm_arm_hyp_stack_page);
hyp_stack_ptr = stack_page + PAGE_SIZE;
vector_ptr = (unsigned long)__kvm_hyp_vector;

5
arch/arm/lib/bitops.h
View File

@ -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

41
arch/arm/lib/uaccess_with_memcpy.c
View File

@ -18,6 +18,7 @@
#include <linux/hardirq.h> /* for in_atomic() */
#include <linux/gfp.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <asm/current.h>
#include <asm/page.h>
@ -40,7 +41,35 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp)
return 0;
pmd = pmd_offset(pud, addr);
if (unlikely(pmd_none(*pmd) || pmd_bad(*pmd)))
if (unlikely(pmd_none(*pmd)))
return 0;
/*
* A pmd can be bad if it refers to a HugeTLB or THP page.
*
* Both THP and HugeTLB pages have the same pmd layout
* and should not be manipulated by the pte functions.
*
* Lock the page table for the destination and check
* to see that it's still huge and whether or not we will
* need to fault on write, or if we have a splitting THP.
*/
if (unlikely(pmd_thp_or_huge(*pmd))) {
ptl = &current->mm->page_table_lock;
spin_lock(ptl);
if (unlikely(!pmd_thp_or_huge(*pmd)
|| pmd_hugewillfault(*pmd)
|| pmd_trans_splitting(*pmd))) {
spin_unlock(ptl);
return 0;
}
*ptep = NULL;
*ptlp = ptl;
return 1;
}
if (unlikely(pmd_bad(*pmd)))
return 0;
pte = pte_offset_map_lock(current->mm, pmd, addr, &ptl);
@ -94,7 +123,10 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
from += tocopy;
n -= tocopy;
pte_unmap_unlock(pte, ptl);
if (pte)
pte_unmap_unlock(pte, ptl);
else
spin_unlock(ptl);
}
if (!atomic)
up_read(&current->mm->mmap_sem);
@ -147,7 +179,10 @@ __clear_user_memset(void __user *addr, unsigned long n)
addr += tocopy;
n -= tocopy;
pte_unmap_unlock(pte, ptl);
if (pte)
pte_unmap_unlock(pte, ptl);
else
spin_unlock(ptl);
}
up_read(&current->mm->mmap_sem);

8
arch/arm/mach-footbridge/netwinder-hw.c
View File

@ -692,14 +692,14 @@ static void netwinder_led_set(struct led_classdev *cdev,
unsigned long flags;
u32 reg;
spin_lock_irqsave(&nw_gpio_lock, flags);
raw_spin_lock_irqsave(&nw_gpio_lock, flags);
reg = nw_gpio_read();
if (b != LED_OFF)
reg &= ~led->mask;
else
reg |= led->mask;
nw_gpio_modify_op(led->mask, reg);
spin_unlock_irqrestore(&nw_gpio_lock, flags);
raw_spin_unlock_irqrestore(&nw_gpio_lock, flags);
}
static enum led_brightness netwinder_led_get(struct led_classdev *cdev)
@ -709,9 +709,9 @@ static enum led_brightness netwinder_led_get(struct led_classdev *cdev)
unsigned long flags;
u32 reg;
spin_lock_irqsave(&nw_gpio_lock, flags);
raw_spin_lock_irqsave(&nw_gpio_lock, flags);
reg = nw_gpio_read();
spin_unlock_irqrestore(&nw_gpio_lock, flags);
raw_spin_unlock_irqrestore(&nw_gpio_lock, flags);
return (reg & led->mask) ? LED_OFF : LED_FULL;
}

3
arch/arm/mach-highbank/Kconfig
View File

@ -4,11 +4,12 @@ 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
select ARM_ERRATA_775420
select ARM_ERRATA_798181
select ARM_ERRATA_798181 if SMP
select ARM_GIC
select ARM_PSCI
select ARM_TIMER_SP804

4
arch/arm/mach-ixp4xx/Kconfig
View File

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

1
arch/arm/mach-mvebu/Kconfig
View File

@ -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

3
arch/arm/mach-mvebu/coherency_ll.S
View File

@ -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

4
arch/arm/mach-mvebu/headsmp.S
View File

@ -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]

3
arch/arm/mach-sa1100/assabet.c
View File

@ -512,6 +512,9 @@ static void __init assabet_map_io(void)
* Its called GPCLKR0 in my SA1110 manual.
*/
Ser1SDCR0 |= SDCR0_SUS;
MSC1 = (MSC1 & ~0xffff) |
MSC_NonBrst | MSC_32BitStMem |
MSC_RdAcc(2) | MSC_WrAcc(2) | MSC_Rec(0);
if (!machine_has_neponset())
sa1100_register_uart_fns(&assabet_port_fns);

55
arch/arm/mach-sa1100/include/mach/gpio.h
View File

@ -1,55 +0,0 @@
/*
* arch/arm/mach-sa1100/include/mach/gpio.h
*
* SA1100 GPIO wrappers for arch-neutral GPIO calls
*
* Written by Philipp Zabel <philipp.zabel@gmail.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* 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.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
*/
#ifndef __ASM_ARCH_SA1100_GPIO_H
#define __ASM_ARCH_SA1100_GPIO_H
#include <linux/io.h>
#include <mach/hardware.h>
#include <asm/irq.h>
#include <asm-generic/gpio.h>
#define __ARM_GPIOLIB_COMPLEX
static inline int gpio_get_value(unsigned gpio)
{
if (__builtin_constant_p(gpio) && (gpio <= GPIO_MAX))
return GPLR & GPIO_GPIO(gpio);
else
return __gpio_get_value(gpio);
}
static inline void gpio_set_value(unsigned gpio, int value)
{
if (__builtin_constant_p(gpio) && (gpio <= GPIO_MAX))
if (value)
GPSR = GPIO_GPIO(gpio);
else
GPCR = GPIO_GPIO(gpio);
else
__gpio_set_value(gpio, value);
}
#define gpio_cansleep __gpio_cansleep
#endif

2
arch/arm/mach-sa1100/include/mach/h3xxx.h
View File

@ -13,6 +13,8 @@
#ifndef _INCLUDE_H3XXX_H_
#define _INCLUDE_H3XXX_H_
#include "hardware.h" /* Gives GPIO_MAX */
/* Physical memory regions corresponding to chip selects */
#define H3600_EGPIO_PHYS (SA1100_CS5_PHYS + 0x01000000)
#define H3600_BANK_2_PHYS SA1100_CS2_PHYS

1
arch/arm/mach-sa1100/simpad.c
View File

@ -19,6 +19,7 @@
#include <mach/hardware.h>
#include <asm/setup.h>
#include <asm/irq.h>
#include <asm/mach-types.h>
#include <asm/mach/arch.h>

2
arch/arm/mach-tegra/Kconfig
View File

@ -51,7 +51,7 @@ config ARCH_TEGRA_3x_SOC
config ARCH_TEGRA_114_SOC
bool "Enable support for Tegra114 family"
select ARM_ERRATA_798181
select ARM_ERRATA_798181 if SMP
select ARM_L1_CACHE_SHIFT_6
select HAVE_ARM_ARCH_TIMER
select PINCTRL_TEGRA114

1
arch/arm/mach-vexpress/Kconfig
View File

@ -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

56
arch/arm/mach-vexpress/dcscb.c
View File

@ -133,38 +133,8 @@ static void dcscb_power_down(void)
if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
arch_spin_unlock(&dcscb_lock);
/*
* Flush all cache levels for this cluster.
*
* To do so we do:
* - Clear the SCTLR.C bit to prevent further cache allocations
* - Flush the whole cache
* - Clear the ACTLR "SMP" bit to disable local coherency
*
* Let's do it in the safest possible way i.e. with
* no memory access within the following sequence
* including to the stack.
*
* Note: fp is preserved to the stack explicitly prior doing
* this since adding it to the clobber list is incompatible
* with having CONFIG_FRAME_POINTER=y.
*/
asm volatile(
"str fp, [sp, #-4]! \n\t"
"mrc p15, 0, r0, c1, c0, 0 @ get CR \n\t"
"bic r0, r0, #"__stringify(CR_C)" \n\t"
"mcr p15, 0, r0, c1, c0, 0 @ set CR \n\t"
"isb \n\t"
"bl v7_flush_dcache_all \n\t"
"clrex \n\t"
"mrc p15, 0, r0, c1, c0, 1 @ get AUXCR \n\t"
"bic r0, r0, #(1 << 6) @ disable local coherency \n\t"
"mcr p15, 0, r0, c1, c0, 1 @ set AUXCR \n\t"
"isb \n\t"
"dsb \n\t"
"ldr fp, [sp], #4"
: : : "r0","r1","r2","r3","r4","r5","r6","r7",
"r9","r10","lr","memory");
/* Flush all cache levels for this cluster. */
v7_exit_coherency_flush(all);
/*
* This is a harmless no-op. On platforms with a real
@ -183,26 +153,8 @@ static void dcscb_power_down(void)
} else {
arch_spin_unlock(&dcscb_lock);
/*
* Flush the local CPU cache.
* Let's do it in the safest possible way as above.
*/
asm volatile(
"str fp, [sp, #-4]! \n\t"
"mrc p15, 0, r0, c1, c0, 0 @ get CR \n\t"
"bic r0, r0, #"__stringify(CR_C)" \n\t"
"mcr p15, 0, r0, c1, c0, 0 @ set CR \n\t"
"isb \n\t"
"bl v7_flush_dcache_louis \n\t"
"clrex \n\t"
"mrc p15, 0, r0, c1, c0, 1 @ get AUXCR \n\t"
"bic r0, r0, #(1 << 6) @ disable local coherency \n\t"
"mcr p15, 0, r0, c1, c0, 1 @ set AUXCR \n\t"
"isb \n\t"
"dsb \n\t"
"ldr fp, [sp], #4"
: : : "r0","r1","r2","r3","r4","r5","r6","r7",
"r9","r10","lr","memory");
/* Disable and flush the local CPU cache. */
v7_exit_coherency_flush(louis);
}
__mcpm_cpu_down(cpu, cluster);

48
arch/arm/mach-vexpress/tc2_pm.c
View File

@ -156,32 +156,7 @@ static void tc2_pm_down(u64 residency)
: : "r" (0x400) );
}
/*
* We need to disable and flush the whole (L1 and L2) cache.
* Let's do it in the safest possible way i.e. with
* no memory access within the following sequence
* including the stack.
*
* Note: fp is preserved to the stack explicitly prior doing
* this since adding it to the clobber list is incompatible
* with having CONFIG_FRAME_POINTER=y.
*/
asm volatile(
"str fp, [sp, #-4]! \n\t"
"mrc p15, 0, r0, c1, c0, 0 @ get CR \n\t"
"bic r0, r0, #"__stringify(CR_C)" \n\t"
"mcr p15, 0, r0, c1, c0, 0 @ set CR \n\t"
"isb \n\t"
"bl v7_flush_dcache_all \n\t"
"clrex \n\t"
"mrc p15, 0, r0, c1, c0, 1 @ get AUXCR \n\t"
"bic r0, r0, #(1 << 6) @ disable local coherency \n\t"
"mcr p15, 0, r0, c1, c0, 1 @ set AUXCR \n\t"
"isb \n\t"
"dsb \n\t"
"ldr fp, [sp], #4"
: : : "r0","r1","r2","r3","r4","r5","r6","r7",
"r9","r10","lr","memory");
v7_exit_coherency_flush(all);
cci_disable_port_by_cpu(mpidr);
@ -197,26 +172,7 @@ static void tc2_pm_down(u64 residency)
arch_spin_unlock(&tc2_pm_lock);
/*
* We need to disable and flush only the L1 cache.
* Let's do it in the safest possible way as above.
*/
asm volatile(
"str fp, [sp, #-4]! \n\t"
"mrc p15, 0, r0, c1, c0, 0 @ get CR \n\t"
"bic r0, r0, #"__stringify(CR_C)" \n\t"
"mcr p15, 0, r0, c1, c0, 0 @ set CR \n\t"
"isb \n\t"
"bl v7_flush_dcache_louis \n\t"
"clrex \n\t"
"mrc p15, 0, r0, c1, c0, 1 @ get AUXCR \n\t"
"bic r0, r0, #(1 << 6) @ disable local coherency \n\t"
"mcr p15, 0, r0, c1, c0, 1 @ set AUXCR \n\t"
"isb \n\t"
"dsb \n\t"
"ldr fp, [sp], #4"
: : : "r0","r1","r2","r3","r4","r5","r6","r7",
"r9","r10","lr","memory");
v7_exit_coherency_flush(louis);
}
__mcpm_cpu_down(cpu, cluster);

6
arch/arm/mm/Kconfig
View File

@ -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.

5
arch/arm/mm/abort-ev6.S
View File

@ -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.

9
arch/arm/mm/alignment.c
View File

@ -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;

4
arch/arm/mm/dma-mapping.c
View File

@ -707,7 +707,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
gfp_t gfp, struct dma_attrs *attrs)
{
pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel);
pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
void *memory;
if (dma_alloc_from_coherent(dev, size, handle, &memory))
@ -720,7 +720,7 @@ void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
{
pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel);
pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
void *memory;
if (dma_alloc_from_coherent(dev, size, handle, &memory))

7
arch/arm/mm/extable.c
View File

@ -9,8 +9,13 @@ int fixup_exception(struct pt_regs *regs)
const struct exception_table_entry *fixup;
fixup = search_exception_tables(instruction_pointer(regs));
if (fixup)
if (fixup) {
regs->ARM_pc = fixup->fixup;
#ifdef CONFIG_THUMB2_KERNEL
/* Clear the IT state to avoid nasty surprises in the fixup */
regs->ARM_cpsr &= ~PSR_IT_MASK;
#endif
}
return fixup != NULL;
}

8
arch/arm/mm/idmap.c
View File

@ -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);

6
arch/arm/mm/mmap.c
View File

@ -202,13 +202,11 @@ int valid_phys_addr_range(phys_addr_t addr, size_t size)
}
/*
* We don't use supersection mappings for mmap() on /dev/mem, which
* means that we can't map the memory area above the 4G barrier into
* userspace.
* Do not allow /dev/mem mappings beyond the supported physical range.
*/
int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
{
return !(pfn + (size >> PAGE_SHIFT) > 0x00100000);
return (pfn + (size >> PAGE_SHIFT)) <= (1 + (PHYS_MASK >> PAGE_SHIFT));
}
#ifdef CONFIG_STRICT_DEVMEM

82
arch/arm/mm/mmu.c
View File

@ -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.

9
arch/arm/mm/nommu.c
View File

@ -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.

4
arch/arm/mm/proc-v6.S
View File

@ -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

4
arch/arm/mm/proc-v7.S
View File

@ -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"

6
arch/arm/net/bpf_jit_32.c
View File

@ -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++;
}

2
arch/arm/plat-versatile/headsmp.S
View File

@ -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

6
arch/arm/vfp/vfpmodule.c
View File

@ -642,9 +642,9 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
static int vfp_hotplug(struct notifier_block *b, unsigned long action,
void *hcpu)
{
if (action == CPU_DYING || action == CPU_DYING_FROZEN) {
vfp_force_reload((long)hcpu, current_thread_info());
} else if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
if (action == CPU_DYING || action == CPU_DYING_FROZEN)
vfp_current_hw_state[(long)hcpu] = NULL;
else if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
vfp_enable(NULL);
return NOTIFY_OK;
}

Some files were not shown because too many files have changed in this diff Show More