Merge branch '4.7-fixes' into mips-for-linux-next

Documentation/x86/intel_mpx.txt

@@ -45,7 +45,7 @@ is how we expect the compiler, application and kernel to work together.
    MPX-instrumented.
 3) The kernel detects that the CPU has MPX, allows the new prctl() to
    succeed, and notes the location of the bounds directory. Userspace is
-   expected to keep the bounds directory at that locationWe note it
+   expected to keep the bounds directory at that location. We note it
    instead of reading it each time because the 'xsave' operation needed
    to access the bounds directory register is an expensive operation.
 4) If the application needs to spill bounds out of the 4 registers, it
@@ -167,7 +167,7 @@ If a #BR is generated due to a bounds violation caused by MPX.
 We need to decode MPX instructions to get violation address and
 set this address into extended struct siginfo.
 
-The _sigfault feild of struct siginfo is extended as follow:
+The _sigfault field of struct siginfo is extended as follow:
 
 87		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
 88		struct {
@@ -240,5 +240,5 @@ them at the same bounds table.
 This is allowed architecturally.  See more information "Intel(R) Architecture
 Instruction Set Extensions Programming Reference" (9.3.4).
 
-However, if users did this, the kernel might be fooled in to unmaping an
+However, if users did this, the kernel might be fooled in to unmapping an
 in-use bounds table since it does not recognize sharing.

Documentation/x86/tlb.txt

@@ -5,7 +5,7 @@ memory, it has two choices:
     from areas other than the one we are trying to flush will be
     destroyed and must be refilled later, at some cost.
  2. Use the invlpg instruction to invalidate a single page at a
-    time.  This could potentialy cost many more instructions, but
+    time.  This could potentially cost many more instructions, but
     it is a much more precise operation, causing no collateral
     damage to other TLB entries.
 
@@ -19,7 +19,7 @@ Which method to do depends on a few things:
     work.
  3. The size of the TLB.  The larger the TLB, the more collateral
     damage we do with a full flush.  So, the larger the TLB, the
-    more attrative an individual flush looks.  Data and
+    more attractive an individual flush looks.  Data and
     instructions have separate TLBs, as do different page sizes.
  4. The microarchitecture.  The TLB has become a multi-level
     cache on modern CPUs, and the global flushes have become more

Documentation/x86/x86_64/machinecheck

@@ -36,7 +36,7 @@ between all CPUs.
 
 check_interval
 	How often to poll for corrected machine check errors, in seconds
-	(Note output is hexademical). Default 5 minutes.  When the poller
+	(Note output is hexadecimal). Default 5 minutes.  When the poller
 	finds MCEs it triggers an exponential speedup (poll more often) on
 	the polling interval.  When the poller stops finding MCEs, it
 	triggers an exponential backoff (poll less often) on the polling

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 7
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Psychotic Stoned Sheep
 
 # *DOCUMENTATION*

arch/arm64/include/asm/cputype.h

@@ -80,12 +80,14 @@
 #define APM_CPU_PART_POTENZA		0x000
 
 #define CAVIUM_CPU_PART_THUNDERX	0x0A1
+#define CAVIUM_CPU_PART_THUNDERX_81XX	0x0A2
 
 #define BRCM_CPU_PART_VULCAN		0x516
 
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
+#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 
 #ifndef __ASSEMBLY__
 

arch/arm64/include/asm/ptrace.h

@@ -117,6 +117,8 @@ struct pt_regs {
 	};
 	u64 orig_x0;
 	u64 syscallno;
+	u64 orig_addr_limit;
+	u64 unused;	// maintain 16 byte alignment
 };
 
 #define arch_has_single_step()	(1)

arch/arm64/kernel/asm-offsets.c

@@ -60,6 +60,7 @@ int main(void)
   DEFINE(S_PC,			offsetof(struct pt_regs, pc));
   DEFINE(S_ORIG_X0,		offsetof(struct pt_regs, orig_x0));
   DEFINE(S_SYSCALLNO,		offsetof(struct pt_regs, syscallno));
+  DEFINE(S_ORIG_ADDR_LIMIT,	offsetof(struct pt_regs, orig_addr_limit));
   DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
   BLANK();
   DEFINE(MM_CONTEXT_ID,		offsetof(struct mm_struct, context.id.counter));

arch/arm64/kernel/cpu_errata.c

@@ -98,6 +98,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		MIDR_RANGE(MIDR_THUNDERX, 0x00,
 			   (1 << MIDR_VARIANT_SHIFT) | 1),
 	},
+	{
+	/* Cavium ThunderX, T81 pass 1.0 */
+		.desc = "Cavium erratum 27456",
+		.capability = ARM64_WORKAROUND_CAVIUM_27456,
+		MIDR_RANGE(MIDR_THUNDERX_81XX, 0x00, 0x00),
+	},
 #endif
 	{
 	}

arch/arm64/kernel/entry.S

@@ -28,6 +28,7 @@
 #include <asm/errno.h>
 #include <asm/esr.h>
 #include <asm/irq.h>
+#include <asm/memory.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
 
@@ -97,7 +98,14 @@
 	mov	x29, xzr			// fp pointed to user-space
 	.else
 	add	x21, sp, #S_FRAME_SIZE
-	.endif
+	get_thread_info tsk
+	/* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+	ldr	x20, [tsk, #TI_ADDR_LIMIT]
+	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	mov	x20, #TASK_SIZE_64
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+	ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO)
+	.endif /* \el == 0 */
 	mrs	x22, elr_el1
 	mrs	x23, spsr_el1
 	stp	lr, x21, [sp, #S_LR]
@@ -128,6 +136,14 @@
 	.endm
 
 	.macro	kernel_exit, el
+	.if	\el != 0
+	/* Restore the task's original addr_limit. */
+	ldr	x20, [sp, #S_ORIG_ADDR_LIMIT]
+	str	x20, [tsk, #TI_ADDR_LIMIT]
+
+	/* No need to restore UAO, it will be restored from SPSR_EL1 */
+	.endif
+
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
 	ct_user_enter
@@ -406,7 +422,6 @@ el1_irq:
 	bl	trace_hardirqs_off
 #endif
 
-	get_thread_info tsk
 	irq_handler
 
 #ifdef CONFIG_PREEMPT

arch/arm64/mm/fault.c

@@ -280,7 +280,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	}
 
 	if (permission_fault(esr) && (addr < USER_DS)) {
-		if (get_fs() == KERNEL_DS)
+		/* regs->orig_addr_limit may be 0 if we entered from EL0 */
+		if (regs->orig_addr_limit == KERNEL_DS)
 			die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
 
 		if (!search_exception_tables(regs->pc))

arch/mips/cavium-octeon/octeon-irq.c

@@ -1260,7 +1260,7 @@ static int octeon_irq_gpio_map(struct irq_domain *d,
 
 	line = (hw + gpiod->base_hwirq) >> 6;
 	bit = (hw + gpiod->base_hwirq) & 63;
-	if (line > ARRAY_SIZE(octeon_irq_ciu_to_irq) ||
+	if (line >= ARRAY_SIZE(octeon_irq_ciu_to_irq) ||
 		octeon_irq_ciu_to_irq[line][bit] != 0)
 		return -EINVAL;
 

arch/mips/include/asm/msa.h

@@ -168,6 +168,7 @@ static inline unsigned int read_msa_##name(void)		\
 	unsigned int reg;					\
 	__asm__ __volatile__(					\
 	"	.set	push\n"					\
+	"	.set	fp=64\n"				\
 	"	.set	msa\n"					\
 	"	cfcmsa	%0, $" #cs "\n"				\
 	"	.set	pop\n"					\
@@ -179,6 +180,7 @@ static inline void write_msa_##name(unsigned int val)		\
 {								\
 	__asm__ __volatile__(					\
 	"	.set	push\n"					\
+	"	.set	fp=64\n"				\
 	"	.set	msa\n"					\
 	"	ctcmsa	$" #cs ", %0\n"				\
 	"	.set	pop\n"					\

arch/mips/kernel/cevt-r4k.c

@@ -276,20 +276,15 @@ int r4k_clockevent_init(void)
 				  CLOCK_EVT_FEAT_C3STOP |
 				  CLOCK_EVT_FEAT_PERCPU;
 
-	clockevent_set_clock(cd, mips_hpt_frequency);
-
-	/* Calculate the min / max delta */
-	cd->max_delta_ns	= clockevent_delta2ns(0x7fffffff, cd);
 	min_delta		= calculate_min_delta();
-	cd->min_delta_ns	= clockevent_delta2ns(min_delta, cd);
 
 	cd->rating		= 300;
 	cd->irq			= irq;
 	cd->cpumask		= cpumask_of(cpu);
 	cd->set_next_event	= mips_next_event;
 	cd->event_handler	= mips_event_handler;
 
-	clockevents_register_device(cd);
+	clockevents_config_and_register(cd, mips_hpt_frequency, min_delta, 0x7fffffff);
 
 	if (cp0_timer_irq_installed)
 		return 0;

arch/mips/kernel/csrc-r4k.c

@@ -23,7 +23,7 @@ static struct clocksource clocksource_mips = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static u64 notrace r4k_read_sched_clock(void)
+static u64 __maybe_unused notrace r4k_read_sched_clock(void)
 {
 	return read_c0_count();
 }
@@ -82,7 +82,9 @@ int __init init_r4k_clocksource(void)
 
 	clocksource_register_hz(&clocksource_mips, mips_hpt_frequency);
 
+#ifndef CONFIG_CPU_FREQ
 	sched_clock_register(r4k_read_sched_clock, 32, mips_hpt_frequency);
+#endif
 
 	return 0;
 }

arch/mips/kernel/traps.c

@@ -704,6 +704,7 @@ asmlinkage void do_ov(struct pt_regs *regs)
 int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
 {
 	struct siginfo si = { 0 };
+	struct vm_area_struct *vma;
 
 	switch (sig) {
 	case 0:
@@ -744,7 +745,8 @@ int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31)
 		si.si_addr = fault_addr;
 		si.si_signo = sig;
 		down_read(&current->mm->mmap_sem);
-		if (find_vma(current->mm, (unsigned long)fault_addr))
+		vma = find_vma(current->mm, (unsigned long)fault_addr);
+		if (vma && (vma->vm_start <= (unsigned long)fault_addr))
 			si.si_code = SEGV_ACCERR;
 		else
 			si.si_code = SEGV_MAPERR;

arch/mips/lantiq/irq.c

@@ -344,7 +344,7 @@ static int icu_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw)
 		if (hw == ltq_eiu_irq[i])
 			chip = &ltq_eiu_type;
 
-	irq_set_chip_and_handler(hw, chip, handle_level_irq);
+	irq_set_chip_and_handler(irq, chip, handle_level_irq);
 
 	return 0;
 }

arch/mips/loongson64/loongson-3/hpet.c

@@ -13,8 +13,8 @@
 #define SMBUS_PCI_REG64		0x64
 #define SMBUS_PCI_REGB4		0xb4
 
-#define HPET_MIN_CYCLES		64
-#define HPET_MIN_PROG_DELTA	(HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1))
+#define HPET_MIN_CYCLES		16
+#define HPET_MIN_PROG_DELTA	(HPET_MIN_CYCLES * 12)
 
 static DEFINE_SPINLOCK(hpet_lock);
 DEFINE_PER_CPU(struct clock_event_device, hpet_clockevent_device);
@@ -157,14 +157,14 @@ static int hpet_tick_resume(struct clock_event_device *evt)
 static int hpet_next_event(unsigned long delta,
 		struct clock_event_device *evt)
 {
-	unsigned int cnt;
-	int res;
+	u32 cnt;
+	s32 res;
 
 	cnt = hpet_read(HPET_COUNTER);
-	cnt += delta;
+	cnt += (u32) delta;
 	hpet_write(HPET_T0_CMP, cnt);
 
-	res = (int)(cnt - hpet_read(HPET_COUNTER));
+	res = (s32)(cnt - hpet_read(HPET_COUNTER));
 
 	return res < HPET_MIN_CYCLES ? -ETIME : 0;
 }
@@ -230,7 +230,7 @@ void __init setup_hpet_timer(void)
 
 	cd = &per_cpu(hpet_clockevent_device, cpu);
 	cd->name = "hpet";
-	cd->rating = 320;
+	cd->rating = 100;
 	cd->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 	cd->set_state_shutdown = hpet_set_state_shutdown;
 	cd->set_state_periodic = hpet_set_state_periodic;

arch/mips/mm/sc-rm7k.c

@@ -161,7 +161,7 @@ static void rm7k_tc_disable(void)
 	local_irq_save(flags);
 	blast_rm7k_tcache();
 	clear_c0_config(RM7K_CONF_TE);
-	local_irq_save(flags);
+	local_irq_restore(flags);
 }
 
 static void rm7k_sc_disable(void)

arch/mips/net/bpf_jit.c

@@ -1199,7 +1199,7 @@ void bpf_jit_compile(struct bpf_prog *fp)
 
 	memset(&ctx, 0, sizeof(ctx));
 
-	ctx.offsets = kcalloc(fp->len, sizeof(*ctx.offsets), GFP_KERNEL);
+	ctx.offsets = kcalloc(fp->len + 1, sizeof(*ctx.offsets), GFP_KERNEL);
 	if (ctx.offsets == NULL)
 		return;
 

arch/x86/events/core.c

@@ -2319,7 +2319,7 @@ void
 perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	struct stack_frame frame;
-	const void __user *fp;
+	const unsigned long __user *fp;
 
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* TODO: We don't support guest os callchain now */
@@ -2332,7 +2332,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 	if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM))
 		return;
 
-	fp = (void __user *)regs->bp;
+	fp = (unsigned long __user *)regs->bp;
 
 	perf_callchain_store(entry, regs->ip);
 
@@ -2345,16 +2345,17 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 	pagefault_disable();
 	while (entry->nr < entry->max_stack) {
 		unsigned long bytes;
+
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
-		if (!access_ok(VERIFY_READ, fp, 16))
+		if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2))
 			break;
 
-		bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8);
+		bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp));
 		if (bytes != 0)
 			break;
-		bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8);
+		bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp));
 		if (bytes != 0)
 			break;
 

arch/x86/events/intel/Makefile

@@ -1,8 +1,8 @@
 obj-$(CONFIG_CPU_SUP_INTEL)		+= core.o bts.o cqm.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= ds.o knc.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= lbr.o p4.o p6.o pt.o
-obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl.o
-intel-rapl-objs				:= rapl.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl-perf.o
+intel-rapl-perf-objs			:= rapl.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel-uncore.o
 intel-uncore-objs			:= uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE)	+= intel-cstate.o