Merge branch 'master' into for-next

10 files changed, 124 insertions, 14 deletions

diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 7e9ed1eea40..d93f976fb38 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -102,6 +102,8 @@
 	.else
 	ldmdb	sp, {r0 - lr}^			@ get calling r0 - lr
 	.endif
+	mov	r0, r0				@ ARMv5T and earlier require a nop
+						@ after ldm {}^
 	add	sp, sp, #S_FRAME_SIZE - S_PC
 	movs	pc, lr				@ return & move spsr_svc into cpsr
 	.endm
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index b7cb45bb91e..3b3d2c80509 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -27,7 +27,6 @@
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
-#include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/smp.h>
 #include <linux/init.h>
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index ba8ccfede96..a5b846b9895 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -9,6 +9,7 @@
  * Authors:  George Davis <davis_g@mvista.com>
  *           Deepak Saxena <dsaxena@plexity.net>
  */
+#include <linux/irq.h>
 #include <linux/kgdb.h>
 #include <asm/traps.h>
 
@@ -158,6 +159,18 @@ static struct undef_hook kgdb_compiled_brkpt_hook = {
 	.fn			= kgdb_compiled_brk_fn
 };
 
+static void kgdb_call_nmi_hook(void *ignored)
+{
+       kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs());
+}
+
+void kgdb_roundup_cpus(unsigned long flags)
+{
+       local_irq_enable();
+       smp_call_function(kgdb_call_nmi_hook, NULL, 0);
+       local_irq_disable();
+}
+
 /**
  *	kgdb_arch_init - Perform any architecture specific initalization.
  *
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index 60c62c377fa..2ba7deb3072 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -22,6 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/stop_machine.h>
 #include <linux/stringify.h>
 #include <asm/traps.h>
@@ -393,6 +394,14 @@ void __kprobes jprobe_return(void)
 		/*
 		 * Setup an empty pt_regs. Fill SP and PC fields as
 		 * they're needed by longjmp_break_handler.
+		 *
+		 * We allocate some slack between the original SP and start of
+		 * our fabricated regs. To be precise we want to have worst case
+		 * covered which is STMFD with all 16 regs so we allocate 2 *
+		 * sizeof(struct_pt_regs)).
+		 *
+		 * This is to prevent any simulated instruction from writing
+		 * over the regs when they are accessing the stack.
 		 */
 		"sub    sp, %0, %1		\n\t"
 		"ldr    r0, ="__stringify(JPROBE_MAGIC_ADDR)"\n\t"
@@ -410,7 +419,7 @@ void __kprobes jprobe_return(void)
 		"ldmia	sp, {r0 - pc}		\n\t"
 		:
 		: "r" (kcb->jprobe_saved_regs.ARM_sp),
-		  "I" (sizeof(struct pt_regs)),
+		  "I" (sizeof(struct pt_regs) * 2),
 		  "J" (offsetof(struct pt_regs, ARM_sp)),
 		  "J" (offsetof(struct pt_regs, ARM_pc)),
 		  "J" (offsetof(struct pt_regs, ARM_cpsr))
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index f28c5e9c51e..c628bdf6c43 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -16,9 +16,9 @@
 #include <linux/mm.h>
 #include <linux/elf.h>
 #include <linux/vmalloc.h>
-#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/string.h>
+#include <linux/gfp.h>
 
 #include <asm/pgtable.h>
 #include <asm/sections.h>
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index c54ceb3d1f9..9e70f2053f9 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -332,7 +332,8 @@ armpmu_reserve_hardware(void)
 
 	for (i = 0; i < pmu_irqs->num_irqs; ++i) {
 		err = request_irq(pmu_irqs->irqs[i], armpmu->handle_irq,
-				  IRQF_DISABLED, "armpmu", NULL);
+				  IRQF_DISABLED | IRQF_NOBALANCING,
+				  "armpmu", NULL);
 		if (err) {
 			pr_warning("unable to request IRQ%d for ARM "
 				   "perf counters\n", pmu_irqs->irqs[i]);
@@ -965,7 +966,7 @@ armv6pmu_handle_irq(int irq_num,
 	 */
 	armv6_pmcr_write(pmcr);
 
-	data.addr = 0;
+	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 	for (idx = 0; idx <= armpmu->num_events; ++idx) {
@@ -1624,7 +1625,7 @@ enum armv7_counters {
 /*
  * EVTSEL: Event selection reg
  */
-#define	ARMV7_EVTSEL_MASK	0x7f		/* Mask for writable bits */
+#define	ARMV7_EVTSEL_MASK	0xff		/* Mask for writable bits */
 
 /*
  * SELECT: Counter selection reg
@@ -1945,7 +1946,7 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 	 */
 	regs = get_irq_regs();
 
-	data.addr = 0;
+	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 	for (idx = 0; idx <= armpmu->num_events; ++idx) {
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index ba2adefa53f..0e12e0acbf2 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -16,7 +16,6 @@
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
-#include <linux/slab.h>
 #include <linux/user.h>
 #include <linux/delay.h>
 #include <linux/reboot.h>
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index e7714f367eb..907d5a620bc 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -18,6 +18,7 @@
 #include <asm/cacheflush.h>
 #include <asm/ucontext.h>
 #include <asm/unistd.h>
+#include <asm/vfp.h>
 
 #include "ptrace.h"
 #include "signal.h"
@@ -175,6 +176,90 @@ static int restore_iwmmxt_context(struct iwmmxt_sigframe *frame)
 
 #endif
 
+#ifdef CONFIG_VFP
+
+static int preserve_vfp_context(struct vfp_sigframe __user *frame)
+{
+	struct thread_info *thread = current_thread_info();
+	struct vfp_hard_struct *h = &thread->vfpstate.hard;
+	const unsigned long magic = VFP_MAGIC;
+	const unsigned long size = VFP_STORAGE_SIZE;
+	int err = 0;
+
+	vfp_sync_hwstate(thread);
+	__put_user_error(magic, &frame->magic, err);
+	__put_user_error(size, &frame->size, err);
+
+	/*
+	 * Copy the floating point registers. There can be unused
+	 * registers see asm/hwcap.h for details.
+	 */
+	err |= __copy_to_user(&frame->ufp.fpregs, &h->fpregs,
+			      sizeof(h->fpregs));
+	/*
+	 * Copy the status and control register.
+	 */
+	__put_user_error(h->fpscr, &frame->ufp.fpscr, err);
+
+	/*
+	 * Copy the exception registers.
+	 */
+	__put_user_error(h->fpexc, &frame->ufp_exc.fpexc, err);
+	__put_user_error(h->fpinst, &frame->ufp_exc.fpinst, err);
+	__put_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err);
+
+	return err ? -EFAULT : 0;
+}
+
+static int restore_vfp_context(struct vfp_sigframe __user *frame)
+{
+	struct thread_info *thread = current_thread_info();
+	struct vfp_hard_struct *h = &thread->vfpstate.hard;
+	unsigned long magic;
+	unsigned long size;
+	unsigned long fpexc;
+	int err = 0;
+
+	__get_user_error(magic, &frame->magic, err);
+	__get_user_error(size, &frame->size, err);
+
+	if (err)
+		return -EFAULT;
+	if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE)
+		return -EINVAL;
+
+	/*
+	 * Copy the floating point registers. There can be unused
+	 * registers see asm/hwcap.h for details.
+	 */
+	err |= __copy_from_user(&h->fpregs, &frame->ufp.fpregs,
+				sizeof(h->fpregs));
+	/*
+	 * Copy the status and control register.
+	 */
+	__get_user_error(h->fpscr, &frame->ufp.fpscr, err);
+
+	/*
+	 * Sanitise and restore the exception registers.
+	 */
+	__get_user_error(fpexc, &frame->ufp_exc.fpexc, err);
+	/* Ensure the VFP is enabled. */
+	fpexc |= FPEXC_EN;
+	/* Ensure FPINST2 is invalid and the exception flag is cleared. */
+	fpexc &= ~(FPEXC_EX | FPEXC_FP2V);
+	h->fpexc = fpexc;
+
+	__get_user_error(h->fpinst, &frame->ufp_exc.fpinst, err);
+	__get_user_error(h->fpinst2, &frame->ufp_exc.fpinst2, err);
+
+	if (!err)
+		vfp_flush_hwstate(thread);
+
+	return err ? -EFAULT : 0;
+}
+
+#endif
+
 /*
  * Do a signal return; undo the signal stack.  These are aligned to 64-bit.
  */
@@ -233,8 +318,8 @@ static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf)
 		err |= restore_iwmmxt_context(&aux->iwmmxt);
 #endif
 #ifdef CONFIG_VFP
-//	if (err == 0)
-//		err |= vfp_restore_state(&sf->aux.vfp);
+	if (err == 0)
+		err |= restore_vfp_context(&aux->vfp);
 #endif
 
 	return err;
@@ -348,8 +433,8 @@ setup_sigframe(struct sigframe __user *sf, struct pt_regs *regs, sigset_t *set)
 		err |= preserve_iwmmxt_context(&aux->iwmmxt);
 #endif
 #ifdef CONFIG_VFP
-//	if (err == 0)
-//		err |= vfp_save_state(&sf->aux.vfp);
+	if (err == 0)
+		err |= preserve_vfp_context(&aux->vfp);
 #endif
 	__put_user_error(0, &aux->end_magic, err);
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 57162af53dc..577543f3857 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -99,6 +99,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	*pmd = __pmd((PHYS_OFFSET & PGDIR_MASK) |
 		     PMD_TYPE_SECT | PMD_SECT_AP_WRITE);
 	flush_pmd_entry(pmd);
+	outer_clean_range(__pa(pmd), __pa(pmd + 1));
 
 	/*
 	 * We need to tell the secondary core where to find
@@ -106,7 +107,8 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	 */
 	secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
 	secondary_data.pgdir = virt_to_phys(pgd);
-	wmb();
+	__cpuc_flush_dcache_area(&secondary_data, sizeof(secondary_data));
+	outer_clean_range(__pa(&secondary_data), __pa(&secondary_data + 1));
 
 	/*
 	 * Now bring the CPU into our world.
diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c
index 4350f75e578..c23501842b9 100644
--- a/arch/arm/kernel/sys_arm.c
+++ b/arch/arm/kernel/sys_arm.c
@@ -15,7 +15,6 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/sem.h>
 #include <linux/msg.h>
@@ -27,6 +26,7 @@
 #include <linux/file.h>
 #include <linux/ipc.h>
 #include <linux/uaccess.h>
+#include <linux/slab.h>
 
 /* Fork a new task - this creates a new program thread.
  * This is called indirectly via a small wrapper