Merge tag 'v3.10.105' into update

This is the 3.10.105 stable release
2018-03-21 23:00:38 +01:00
parent c8df40eb3e ec55e7c2bf
commit ad957d335c
293 changed files with 2952 additions and 1165 deletions
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 10
-SUBLEVEL = 104
+SUBLEVEL = 105
 EXTRAVERSION =
 NAME = TOSSUG Baby Fish

@@ -371,14 +371,6 @@ __copy_tofrom_user_nocheck(void *to, const void *from, long len)
 	return __cu_len;
 }

-extern inline long
-__copy_tofrom_user(void *to, const void *from, long len, const void __user *validate)
-{
-	if (__access_ok((unsigned long)validate, len, get_fs()))
-		len = __copy_tofrom_user_nocheck(to, from, len);
-	return len;
-}
-
 #define __copy_to_user(to,from,n)					\
 ({									\
 	__chk_user_ptr(to);						\
@@ -393,17 +385,22 @@ __copy_tofrom_user(void *to, const void *from, long len, const void __user *vali
 #define __copy_to_user_inatomic __copy_to_user
 #define __copy_from_user_inatomic __copy_from_user

-
 extern inline long
 copy_to_user(void __user *to, const void *from, long n)
 {
-	return __copy_tofrom_user((__force void *)to, from, n, to);
+	if (likely(__access_ok((unsigned long)to, n, get_fs())))
+		n = __copy_tofrom_user_nocheck((__force void *)to, from, n);
+	return n;
 }

 extern inline long
 copy_from_user(void *to, const void __user *from, long n)
 {
-	return __copy_tofrom_user(to, (__force void *)from, n, from);
+	if (likely(__access_ok((unsigned long)from, n, get_fs())))
+		n = __copy_tofrom_user_nocheck(to, (__force void *)from, n);
+	else
+		memset(to, 0, n);
+	return n;
 }

 extern void __do_clear_user(void);
@@ -83,7 +83,10 @@
 	"2:	;nop\n"				\
 	"	.section .fixup, \"ax\"\n"	\
 	"	.align 4\n"			\
-	"3:	mov %0, %3\n"			\
+	"3:	# return -EFAULT\n"		\
+	"	mov %0, %3\n"			\
+	"	# zero out dst ptr\n"		\
+	"	mov %1,  0\n"			\
 	"	j   2b\n"			\
 	"	.previous\n"			\
 	"	.section __ex_table, \"a\"\n"	\
@@ -101,7 +104,11 @@
 	"2:	;nop\n"				\
 	"	.section .fixup, \"ax\"\n"	\
 	"	.align 4\n"			\
-	"3:	mov %0, %3\n"			\
+	"3:	# return -EFAULT\n"		\
+	"	mov %0, %3\n"			\
+	"	# zero out dst ptr\n"		\
+	"	mov %1,  0\n"			\
+	"	mov %R1, 0\n"			\
 	"	j   2b\n"			\
 	"	.previous\n"			\
 	"	.section __ex_table, \"a\"\n"	\
@@ -80,13 +80,14 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
 	int err;

 	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
-	if (!err)
-		set_current_blocked(&set);
-
-	err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs),
+	err |= __copy_from_user(regs, &(sf->uc.uc_mcontext.regs.scratch),
 				sizeof(sf->uc.uc_mcontext.regs.scratch));
+	if (err)
+		return err;

-	return err;
+	set_current_blocked(&set);
+
+	return 0;
 }

 static inline int is_do_ss_needed(unsigned int magic)
@@ -715,7 +715,7 @@ __armv7_mmu_cache_on:
 		orrne	r0, r0, #1		@ MMU enabled
 		movne	r1, #0xfffffffd		@ domain 0 = client
 		bic     r6, r6, #1 << 31        @ 32-bit translation system
-		bic     r6, r6, #3 << 0         @ use only ttbr0
+		bic     r6, r6, #(7 << 0) | (1 << 4)	@ use only ttbr0
 		mcrne	p15, 0, r3, c2, c0, 0	@ load page table pointer
 		mcrne	p15, 0, r0, c8, c7, 0	@ flush I,D TLBs
 		mcr	p15, 0, r0, c7, c5, 4	@ ISB
@@ -872,9 +872,9 @@ struct sa1111_save_data {

 #ifdef CONFIG_PM

-static int sa1111_suspend(struct platform_device *dev, pm_message_t state)
+static int sa1111_suspend_noirq(struct device *dev)
 {
-	struct sa1111 *sachip = platform_get_drvdata(dev);
+	struct sa1111 *sachip = dev_get_drvdata(dev);
 	struct sa1111_save_data *save;
 	unsigned long flags;
 	unsigned int val;
@@ -937,9 +937,9 @@ static int sa1111_suspend(struct platform_device *dev, pm_message_t state)
 *	restored by their respective drivers, and must be called
 *	via LDM after this function.
 */
-static int sa1111_resume(struct platform_device *dev)
+static int sa1111_resume_noirq(struct device *dev)
 {
-	struct sa1111 *sachip = platform_get_drvdata(dev);
+	struct sa1111 *sachip = dev_get_drvdata(dev);
 	struct sa1111_save_data *save;
 	unsigned long flags, id;
 	void __iomem *base;
@@ -955,7 +955,7 @@ static int sa1111_resume(struct platform_device *dev)
 	id = sa1111_readl(sachip->base + SA1111_SKID);
 	if ((id & SKID_ID_MASK) != SKID_SA1111_ID) {
 		__sa1111_remove(sachip);
-		platform_set_drvdata(dev, NULL);
+		dev_set_drvdata(dev, NULL);
 		kfree(save);
 		return 0;
 	}
@@ -1006,8 +1006,8 @@ static int sa1111_resume(struct platform_device *dev)
 }

 #else
-#define sa1111_suspend NULL
-#define sa1111_resume  NULL
+#define sa1111_suspend_noirq NULL
+#define sa1111_resume_noirq  NULL
 #endif

 static int sa1111_probe(struct platform_device *pdev)
@@ -1041,6 +1041,11 @@ static int sa1111_remove(struct platform_device *pdev)
 	return 0;
 }

+static struct dev_pm_ops sa1111_pm_ops = {
+	.suspend_noirq = sa1111_suspend_noirq,
+	.resume_noirq = sa1111_resume_noirq,
+};
+
 /*
 *	Not sure if this should be on the system bus or not yet.
 *	We really want some way to register a system device at
@@ -1053,11 +1058,10 @@ static int sa1111_remove(struct platform_device *pdev)
 static struct platform_driver sa1111_device_driver = {
 	.probe		= sa1111_probe,
 	.remove		= sa1111_remove,
-	.suspend	= sa1111_suspend,
-	.resume		= sa1111_resume,
 	.driver		= {
 		.name	= "sa1111",
 		.owner	= THIS_MODULE,
+		.pm	= &sa1111_pm_ops,
 	},
 };

@@ -92,6 +92,8 @@ void __init arm_dt_init_cpu_maps(void)
 		return;

 	for_each_child_of_node(cpus, cpu) {
+		const __be32 *cell;
+		int prop_bytes;
 		u32 hwid;

 		if (of_node_cmp(cpu->type, "cpu"))
@@ -103,17 +105,23 @@ void __init arm_dt_init_cpu_maps(void)
 		 * properties is considered invalid to build the
 		 * cpu_logical_map.
 		 */
-		if (of_property_read_u32(cpu, "reg", &hwid)) {
+		cell = of_get_property(cpu, "reg", &prop_bytes);
+		if (!cell || prop_bytes < sizeof(*cell)) {
 			pr_debug(" * %s missing reg property\n",
 				     cpu->full_name);
 			return;
 		}

 		/*
-		 * 8 MSBs must be set to 0 in the DT since the reg property
+		 * Bits n:24 must be set to 0 in the DT since the reg property
 		 * defines the MPIDR[23:0].
 		 */
-		if (hwid & ~MPIDR_HWID_BITMASK)
+		do {
+			hwid = be32_to_cpu(*cell++);
+			prop_bytes -= sizeof(*cell);
+		} while (!hwid && prop_bytes > 0);
+
+		if (prop_bytes || (hwid & ~MPIDR_HWID_BITMASK))
 			return;

 		/*
@@ -30,6 +30,7 @@

 #include <mach/hardware.h>
 #include <mach/irqs.h>
+#include <mach/reset.h>

 #include "generic.h"

@@ -133,6 +134,7 @@ static void sa1100_power_off(void)

 void sa11x0_restart(char mode, const char *cmd)
 {
+	clear_reset_status(RESET_STATUS_ALL);
 	if (mode == 's') {
 		/* Jump into ROM at address 0 */
 		soft_restart(0);
@@ -124,6 +124,7 @@ extern unsigned long randomize_et_dyn(unsigned long base);

 #define SET_PERSONALITY(ex)		clear_thread_flag(TIF_32BIT);

+/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
 #define ARCH_DLINFO							\
 do {									\
 	NEW_AUX_ENT(AT_SYSINFO_EHDR,					\
@@ -200,4 +200,14 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 #define arch_read_relax(lock)	cpu_relax()
 #define arch_write_relax(lock)	cpu_relax()

+/*
+ * Accesses appearing in program order before a spin_lock() operation
+ * can be reordered with accesses inside the critical section, by virtue
+ * of arch_spin_lock being constructed using acquire semantics.
+ *
+ * In cases where this is problematic (e.g. try_to_wake_up), an
+ * smp_mb__before_spinlock() can restore the required ordering.
+ */
+#define smp_mb__before_spinlock()	smp_mb()
+
 #endif /* __ASM_SPINLOCK_H */
@@ -19,4 +19,6 @@
 /* vDSO location */
 #define AT_SYSINFO_EHDR	33

+#define AT_VECTOR_SIZE_ARCH 1 /* entries in ARCH_DLINFO */
+
 #endif
@@ -421,8 +421,10 @@ int kernel_active_single_step(void)
 /* ptrace API */
 void user_enable_single_step(struct task_struct *task)
 {
-	set_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP);
-	set_regs_spsr_ss(task_pt_regs(task));
+	struct thread_info *ti = task_thread_info(task);
+
+	if (!test_and_set_ti_thread_flag(ti, TIF_SINGLESTEP))
+		set_regs_spsr_ss(task_pt_regs(task));
 }

 void user_disable_single_step(struct task_struct *task)
@@ -600,7 +600,7 @@ el0_inv:
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
 	mrs	x2, esr_el1
-	b	bad_mode
+	b	bad_el0_sync
 ENDPROC(el0_sync)

 	.align	6
@@ -424,12 +424,11 @@ int register_async_abort_handler(void (*fn)(struct pt_regs *regs, void *), void
 #endif

 /*
- * bad_mode handles the impossible case in the exception vector.
+ * bad_mode handles the impossible case in the exception vector. This is always
+ * fatal.
 */
 asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 {
-	siginfo_t info;
-	void __user *pc = (void __user *)instruction_pointer(regs);
 	console_verbose();

 #ifdef CONFIG_MEDIATEK_SOLUTION
@@ -443,6 +442,24 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 #endif
 	pr_crit("Bad mode in %s handler detected, code 0x%08x\n",
 		handler[reason], esr);
+
+	die("Oops - bad mode", regs, 0);
+	local_irq_disable();
+	panic("bad mode");
+}
+
+/*
+ * bad_el0_sync handles unexpected, but potentially recoverable synchronous
+ * exceptions taken from EL0. Unlike bad_mode, this returns.
+ */
+asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
+{
+	siginfo_t info;
+	void __user *pc = (void __user *)instruction_pointer(regs);
+	console_verbose();
+
+	pr_crit("Bad EL0 synchronous exception detected on CPU%d, code 0x%08x\n",
+		smp_processor_id(), esr);
 	__show_regs(regs);

 	info.si_signo = SIGILL;
@@ -450,7 +467,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 	info.si_code  = ILL_ILLOPC;
 	info.si_addr  = pc;

-	arm64_notify_die("Oops - bad mode", regs, &info, 0);
+	force_sig_info(info.si_signo, &info, current);
 }

 void __pte_error(const char *file, int line, unsigned long val)
@@ -74,7 +74,7 @@ extern __kernel_size_t __copy_user(void *to, const void *from,

 extern __kernel_size_t copy_to_user(void __user *to, const void *from,
 				    __kernel_size_t n);
-extern __kernel_size_t copy_from_user(void *to, const void __user *from,
+extern __kernel_size_t ___copy_from_user(void *to, const void __user *from,
 				      __kernel_size_t n);

 static inline __kernel_size_t __copy_to_user(void __user *to, const void *from,
@@ -88,6 +88,15 @@ static inline __kernel_size_t __copy_from_user(void *to,
 {
 	return __copy_user(to, (const void __force *)from, n);
 }
+static inline __kernel_size_t copy_from_user(void *to,
+					       const void __user *from,
+					       __kernel_size_t n)
+{
+	size_t res = ___copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
+}

 #define __copy_to_user_inatomic __copy_to_user
 #define __copy_from_user_inatomic __copy_from_user
@@ -36,7 +36,7 @@ EXPORT_SYMBOL(copy_page);
 /*
 * Userspace access stuff.
 */
-EXPORT_SYMBOL(copy_from_user);
+EXPORT_SYMBOL(___copy_from_user);
 EXPORT_SYMBOL(copy_to_user);
 EXPORT_SYMBOL(__copy_user);
 EXPORT_SYMBOL(strncpy_from_user);
@@ -23,13 +23,13 @@
 	 */
 	.text
 	.align	1
-	.global	copy_from_user
-	.type	copy_from_user, @function
-copy_from_user:
+	.global	___copy_from_user
+	.type	___copy_from_user, @function
+___copy_from_user:
 	branch_if_kernel r8, __copy_user
 	ret_if_privileged r8, r11, r10, r10
 	rjmp	__copy_user
-	.size	copy_from_user, . - copy_from_user
+	.size	___copy_from_user, . - ___copy_from_user

 	.global	copy_to_user
 	.type	copy_to_user, @function
@@ -435,7 +435,7 @@ void __init at32_init_pio(struct platform_device *pdev)
 	struct resource *regs;
 	struct pio_device *pio;

-	if (pdev->id > MAX_NR_PIO_DEVICES) {
+	if (pdev->id >= MAX_NR_PIO_DEVICES) {
 		dev_err(&pdev->dev, "only %d PIO devices supported\n",
 			MAX_NR_PIO_DEVICES);
 		return;
@@ -177,11 +177,12 @@ static inline int bad_user_access_length(void)
 static inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	if (access_ok(VERIFY_READ, from, n))
+	if (likely(access_ok(VERIFY_READ, from, n))) {
 		memcpy(to, (const void __force *)from, n);
-	else
-		return n;
-	return 0;
+		return 0;
+	}
+	memset(to, 0, n);
+	return n;
 }

 static inline unsigned long __must_check
@@ -176,30 +176,6 @@ extern unsigned long __copy_user(void __user *to, const void *from, unsigned lon
 extern unsigned long __copy_user_zeroing(void *to, const void __user *from, unsigned long n);
 extern unsigned long __do_clear_user(void __user *to, unsigned long n);

-static inline unsigned long
-__generic_copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-	if (access_ok(VERIFY_WRITE, to, n))
-		return __copy_user(to,from,n);
-	return n;
-}
-
-static inline unsigned long
-__generic_copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	if (access_ok(VERIFY_READ, from, n))
-		return __copy_user_zeroing(to,from,n);
-	return n;
-}
-
-static inline unsigned long
-__generic_clear_user(void __user *to, unsigned long n)
-{
-	if (access_ok(VERIFY_WRITE, to, n))
-		return __do_clear_user(to,n);
-	return n;
-}
-
 static inline long
 __strncpy_from_user(char *dst, const char __user *src, long count)
 {
@@ -262,7 +238,7 @@ __constant_copy_from_user(void *to, const void __user *from, unsigned long n)
 	else if (n == 24)
 		__asm_copy_from_user_24(to, from, ret);
 	else
-		ret = __generic_copy_from_user(to, from, n);
+		ret = __copy_user_zeroing(to, from, n);

 	return ret;
 }
@@ -312,7 +288,7 @@ __constant_copy_to_user(void __user *to, const void *from, unsigned long n)
 	else if (n == 24)
 		__asm_copy_to_user_24(to, from, ret);
 	else
-		ret = __generic_copy_to_user(to, from, n);
+		ret = __copy_user(to, from, n);

 	return ret;
 }
@@ -344,26 +320,43 @@ __constant_clear_user(void __user *to, unsigned long n)
 	else if (n == 24)
 		__asm_clear_24(to, ret);
 	else
-		ret = __generic_clear_user(to, n);
+		ret = __do_clear_user(to, n);

 	return ret;
 }


-#define clear_user(to, n)			\
-(__builtin_constant_p(n) ?			\
- __constant_clear_user(to, n) :			\
- __generic_clear_user(to, n))
+static inline size_t clear_user(void __user *to, size_t n)
+{
+	if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+		return n;
+	if (__builtin_constant_p(n))
+		return __constant_clear_user(to, n);
+	else
+		return __do_clear_user(to, n);
+}

-#define copy_from_user(to, from, n)		\
-(__builtin_constant_p(n) ?			\
- __constant_copy_from_user(to, from, n) :	\
- __generic_copy_from_user(to, from, n))
+static inline size_t copy_from_user(void *to, const void __user *from, size_t n)
+{
+	if (unlikely(!access_ok(VERIFY_READ, from, n))) {
+		memset(to, 0, n);
+		return n;
+	}
+	if (__builtin_constant_p(n))
+		return __constant_copy_from_user(to, from, n);
+	else
+		return __copy_user_zeroing(to, from, n);
+}

-#define copy_to_user(to, from, n)		\
-(__builtin_constant_p(n) ?			\
- __constant_copy_to_user(to, from, n) :		\
- __generic_copy_to_user(to, from, n))
+static inline size_t copy_to_user(void __user *to, const void *from, size_t n)
+{
+	if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+		return n;
+	if (__builtin_constant_p(n))
+		return __constant_copy_to_user(to, from, n);
+	else
+		return __copy_user(to, from, n);
+}

 /* We let the __ versions of copy_from/to_user inline, because they're often
 * used in fast paths and have only a small space overhead.
@@ -263,19 +263,25 @@ do {							\
 extern long __memset_user(void *dst, unsigned long count);
 extern long __memcpy_user(void *dst, const void *src, unsigned long count);

-#define clear_user(dst,count)			__memset_user(____force(dst), (count))
+#define __clear_user(dst,count)			__memset_user(____force(dst), (count))
 #define __copy_from_user_inatomic(to, from, n)	__memcpy_user((to), ____force(from), (n))
 #define __copy_to_user_inatomic(to, from, n)	__memcpy_user(____force(to), (from), (n))

 #else

-#define clear_user(dst,count)			(memset(____force(dst), 0, (count)), 0)
+#define __clear_user(dst,count)			(memset(____force(dst), 0, (count)), 0)
 #define __copy_from_user_inatomic(to, from, n)	(memcpy((to), ____force(from), (n)), 0)
 #define __copy_to_user_inatomic(to, from, n)	(memcpy(____force(to), (from), (n)), 0)

 #endif

-#define __clear_user clear_user
+static inline unsigned long __must_check
+clear_user(void __user *to, unsigned long n)
+{
+	if (likely(__access_ok(to, n)))
+		n = __clear_user(to, n);
+	return n;
+}

 static inline unsigned long __must_check
 __copy_to_user(void __user *to, const void *from, unsigned long n)
@@ -102,7 +102,8 @@ static inline long hexagon_strncpy_from_user(char *dst, const char __user *src,
 {
 	long res = __strnlen_user(src, n);

-	/* return from strnlen can't be zero -- that would be rubbish. */
+	if (unlikely(!res))
+		return -EFAULT;

 	if (res > n) {
 		copy_from_user(dst, src, n);
@@ -262,17 +262,15 @@ __copy_from_user (void *to, const void __user *from, unsigned long count)
 	__cu_len;									\
 })

-#define copy_from_user(to, from, n)							\
-({											\
-	void *__cu_to = (to);								\
-	const void __user *__cu_from = (from);						\
-	long __cu_len = (n);								\
-											\
-	__chk_user_ptr(__cu_from);							\
-	if (__access_ok(__cu_from, __cu_len, get_fs()))					\
-		__cu_len = __copy_user((__force void __user *) __cu_to, __cu_from, __cu_len);	\
-	__cu_len;									\
-})
+static inline unsigned long
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	if (likely(__access_ok(from, n, get_fs())))
+		n = __copy_user((__force void __user *) to, from, n);
+	else
+		memset(to, 0, n);
+	return n;
+}

 #define __copy_in_user(to, from, size)	__copy_user((to), (from), (size))

@@ -215,7 +215,7 @@ extern int fixup_exception(struct pt_regs *regs);
 #define __get_user_nocheck(x,ptr,size)					\
 ({									\
 	long __gu_err = 0;						\
-	unsigned long __gu_val;						\
+	unsigned long __gu_val = 0;					\
 	might_sleep();							\
 	__get_user_size(__gu_val,(ptr),(size),__gu_err);		\
 	(x) = (__typeof__(*(ptr)))__gu_val;				\
@@ -38,6 +38,7 @@
 #define atomic_dec(v) atomic_sub(1, (v))

 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
+#define atomic_dec_if_positive(v)       atomic_sub_if_positive(1, v)

 #define smp_mb__before_atomic_dec()	barrier()
 #define smp_mb__after_atomic_dec()	barrier()
@@ -46,8 +47,6 @@

 #endif

-#define atomic_dec_if_positive(v)       atomic_sub_if_positive(1, v)
-
 #include <asm-generic/atomic64.h>

 #endif /* __ASM_METAG_ATOMIC_H */
@@ -199,8 +199,9 @@ extern unsigned long __must_check __copy_user_zeroing(void *to,
 static inline unsigned long
 copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	if (access_ok(VERIFY_READ, from, n))
+	if (likely(access_ok(VERIFY_READ, from, n)))
 		return __copy_user_zeroing(to, from, n);
+	memset(to, 0, n);
 	return n;
 }

@@ -226,7 +226,7 @@ extern long __user_bad(void);

 #define __get_user(x, ptr)						\
 ({									\
-	unsigned long __gu_val;						\
+	unsigned long __gu_val = 0;					\
 	/*unsigned long __gu_ptr = (unsigned long)(ptr);*/		\
 	long __gu_err;							\
 	switch (sizeof(*(ptr))) {					\
@@ -371,10 +371,13 @@ extern long __user_bad(void);
 static inline long copy_from_user(void *to,
 		const void __user *from, unsigned long n)
 {
+	unsigned long res = n;
 	might_sleep();
-	if (access_ok(VERIFY_READ, from, n))
-		return __copy_from_user(to, from, n);
-	return n;
+	if (likely(access_ok(VERIFY_READ, from, n)))
+		res = __copy_from_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }

 #define __copy_to_user(to, from, n)	\
@@ -375,7 +375,10 @@ struct kvm_vcpu_arch {
 	/* Host KSEG0 address of the EI/DI offset */
 	void *kseg0_commpage;

-	u32 io_gpr;		/* GPR used as IO source/target */
+	/* Resume PC after MMIO completion */
+	unsigned long io_pc;
+	/* GPR used as IO source/target */
+	u32 io_gpr;

 	/* Used to calibrate the virutal count register for the guest */
 	int32_t host_cp0_count;
@@ -386,8 +389,6 @@ struct kvm_vcpu_arch {
 	/* Bitmask of pending exceptions to be cleared */
 	unsigned long pending_exceptions_clr;

-	unsigned long pending_load_cause;
-
 	/* Save/Restore the entryhi register when are are preempted/scheduled back in */
 	unsigned long preempt_entryhi;

@@ -73,7 +73,7 @@ static inline int is_syscall_success(struct pt_regs *regs)

 static inline long regs_return_value(struct pt_regs *regs)
 {
-	if (is_syscall_success(regs))
+	if (is_syscall_success(regs) || !user_mode(regs))
 		return regs->regs[2];
 	else
 		return -regs->regs[2];
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/thread_info.h>
+#include <linux/string.h>

 /*
 * The fs value determines whether argument validity checking should be
@@ -938,6 +939,8 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
 		might_fault();						\
 		__cu_len = __invoke_copy_from_user(__cu_to, __cu_from,	\
 						   __cu_len);		\
+	} else {							\
+		memset(__cu_to, 0, __cu_len);				\
 	}								\
 	__cu_len;							\
 })
@@ -254,15 +254,15 @@ enum emulation_result kvm_mips_emul_eret(struct kvm_vcpu *vcpu)
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	enum emulation_result er = EMULATE_DONE;

-	if (kvm_read_c0_guest_status(cop0) & ST0_EXL) {
+	if (kvm_read_c0_guest_status(cop0) & ST0_ERL) {
+		kvm_clear_c0_guest_status(cop0, ST0_ERL);
+		vcpu->arch.pc = kvm_read_c0_guest_errorepc(cop0);
+	} else if (kvm_read_c0_guest_status(cop0) & ST0_EXL) {
 		kvm_debug("[%#lx] ERET to %#lx\n", vcpu->arch.pc,
 			  kvm_read_c0_guest_epc(cop0));
 		kvm_clear_c0_guest_status(cop0, ST0_EXL);
 		vcpu->arch.pc = kvm_read_c0_guest_epc(cop0);

-	} else if (kvm_read_c0_guest_status(cop0) & ST0_ERL) {
-		kvm_clear_c0_guest_status(cop0, ST0_ERL);
-		vcpu->arch.pc = kvm_read_c0_guest_errorepc(cop0);
 	} else {
 		printk("[%#lx] ERET when MIPS_SR_EXL|MIPS_SR_ERL == 0\n",
 		       vcpu->arch.pc);
@@ -310,6 +310,47 @@ enum emulation_result kvm_mips_emul_tlbr(struct kvm_vcpu *vcpu)
 	return er;
 }

+/**
+ * kvm_mips_invalidate_guest_tlb() - Indicates a change in guest MMU map.
+ * @vcpu:	VCPU with changed mappings.
+ * @tlb:	TLB entry being removed.
+ *
+ * This is called to indicate a single change in guest MMU mappings, so that we
+ * can arrange TLB flushes on this and other CPUs.
+ */
+static void kvm_mips_invalidate_guest_tlb(struct kvm_vcpu *vcpu,
+					  struct kvm_mips_tlb *tlb)
+{
+	int cpu, i;
+	bool user;
+
+	/* No need to flush for entries which are already invalid */
+	if (!((tlb->tlb_lo0 | tlb->tlb_lo1) & MIPS3_PG_V))
+		return;
+	/* User address space doesn't need flushing for KSeg2/3 changes */
+	user = tlb->tlb_hi < KVM_GUEST_KSEG0;
+
+	preempt_disable();
+
+	/*
+	 * Probe the shadow host TLB for the entry being overwritten, if one
+	 * matches, invalidate it
+	 */
+	kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi);
+
+	/* Invalidate the whole ASID on other CPUs */
+	cpu = smp_processor_id();
+	for_each_possible_cpu(i) {
+		if (i == cpu)
+			continue;
+		if (user)
+			vcpu->arch.guest_user_asid[i] = 0;
+		vcpu->arch.guest_kernel_asid[i] = 0;
+	}
+
+	preempt_enable();
+}
+
 /* Write Guest TLB Entry @ Index */
 enum emulation_result kvm_mips_emul_tlbwi(struct kvm_vcpu *vcpu)
 {
@@ -331,10 +372,8 @@ enum emulation_result kvm_mips_emul_tlbwi(struct kvm_vcpu *vcpu)
 	}

 	tlb = &vcpu->arch.guest_tlb[index];
-#if 1
-	/* Probe the shadow host TLB for the entry being overwritten, if one matches, invalidate it */
-	kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi);
-#endif
+
+	kvm_mips_invalidate_guest_tlb(vcpu, tlb);

 	tlb->tlb_mask = kvm_read_c0_guest_pagemask(cop0);
 	tlb->tlb_hi = kvm_read_c0_guest_entryhi(cop0);
@@ -373,10 +412,7 @@ enum emulation_result kvm_mips_emul_tlbwr(struct kvm_vcpu *vcpu)

 	tlb = &vcpu->arch.guest_tlb[index];

-#if 1
-	/* Probe the shadow host TLB for the entry being overwritten, if one matches, invalidate it */
-	kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi);
-#endif
+	kvm_mips_invalidate_guest_tlb(vcpu, tlb);

 	tlb->tlb_mask = kvm_read_c0_guest_pagemask(cop0);
 	tlb->tlb_hi = kvm_read_c0_guest_entryhi(cop0);
@@ -419,6 +455,7 @@ kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause,
 	int32_t rt, rd, copz, sel, co_bit, op;
 	uint32_t pc = vcpu->arch.pc;
 	unsigned long curr_pc;
+	int cpu, i;

 	/*
 	 * Update PC and hold onto current PC in case there is
@@ -538,8 +575,16 @@ kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause,
 					     ASID_MASK,
 					     vcpu->arch.gprs[rt] & ASID_MASK);

+					preempt_disable();
 					/* Blow away the shadow host TLBs */
 					kvm_mips_flush_host_tlb(1);
+					cpu = smp_processor_id();
+					for_each_possible_cpu(i)
+						if (i != cpu) {
+							vcpu->arch.guest_user_asid[i] = 0;
+							vcpu->arch.guest_kernel_asid[i] = 0;
+						}
+					preempt_enable();
 				}
 				kvm_write_c0_guest_entryhi(cop0,
 							   vcpu->arch.gprs[rt]);
@@ -773,6 +818,7 @@ kvm_mips_emulate_load(uint32_t inst, uint32_t cause,
 		      struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DO_MMIO;
+	unsigned long curr_pc;
 	int32_t op, base, rt, offset;
 	uint32_t bytes;

@@ -781,7 +827,18 @@ kvm_mips_emulate_load(uint32_t inst, uint32_t cause,
 	offset = inst & 0xffff;
 	op = (inst >> 26) & 0x3f;

-	vcpu->arch.pending_load_cause = cause;
+	/*
+	 * Find the resume PC now while we have safe and easy access to the
+	 * prior branch instruction, and save it for
+	 * kvm_mips_complete_mmio_load() to restore later.
+	 */
+	curr_pc = vcpu->arch.pc;
+	er = update_pc(vcpu, cause);
+	if (er == EMULATE_FAIL)
+		return er;
+	vcpu->arch.io_pc = vcpu->arch.pc;
+	vcpu->arch.pc = curr_pc;
+
 	vcpu->arch.io_gpr = rt;

 	switch (op) {
@@ -1610,7 +1667,6 @@ kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	unsigned long *gpr = &vcpu->arch.gprs[vcpu->arch.io_gpr];
 	enum emulation_result er = EMULATE_DONE;
-	unsigned long curr_pc;

 	if (run->mmio.len > sizeof(*gpr)) {
 		printk("Bad MMIO length: %d", run->mmio.len);
@@ -1618,14 +1674,8 @@ kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		goto done;
 	}

-	/*
-	 * Update PC and hold onto current PC in case there is
-	 * an error and we want to rollback the PC
-	 */
-	curr_pc = vcpu->arch.pc;
-	er = update_pc(vcpu, vcpu->arch.pending_load_cause);
-	if (er == EMULATE_FAIL)
-		return er;
+	/* Restore saved resume PC */
+	vcpu->arch.pc = vcpu->arch.io_pc;

 	switch (run->mmio.len) {
 	case 4:
@@ -1647,12 +1697,6 @@ kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		break;
 	}

-	if (vcpu->arch.pending_load_cause & CAUSEF_BD)
-		kvm_debug
-		    ("[%#lx] Completing %d byte BD Load to gpr %d (0x%08lx) type %d\n",
-		     vcpu->arch.pc, run->mmio.len, vcpu->arch.io_gpr, *gpr,
-		     vcpu->mmio_needed);
-
 done:
 	return er;
 }
@@ -36,6 +36,9 @@
 #include <linux/console.h>
 #endif

+#define ROCIT_CONFIG_GEN0		0x1f403000
+#define  ROCIT_CONFIG_GEN0_PCI_IOCU	BIT(7)
+
 extern void malta_be_init(void);
 extern int malta_be_handler(struct pt_regs *regs, int is_fixup);

@@ -108,6 +111,8 @@ static void __init fd_activate(void)
 static int __init plat_enable_iocoherency(void)
 {
 	int supported = 0;
+	u32 cfg;
+
 	if (mips_revision_sconid == MIPS_REVISION_SCON_BONITO) {
 		if (BONITO_PCICACHECTRL & BONITO_PCICACHECTRL_CPUCOH_PRES) {
 			BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_CPUCOH_EN;
@@ -130,7 +135,8 @@ static int __init plat_enable_iocoherency(void)
 	} else if (gcmp_niocu() != 0) {
 		/* Nothing special needs to be done to enable coherency */
 		pr_info("CMP IOCU detected\n");
-		if ((*(unsigned int *)0xbf403000 & 0x81) != 0x81) {
+		cfg = __raw_readl((u32 *)CKSEG1ADDR(ROCIT_CONFIG_GEN0));
+		if (!(cfg & ROCIT_CONFIG_GEN0_PCI_IOCU)) {
 			pr_crit("IOCU OPERATION DISABLED BY SWITCH - DEFAULTING TO SW IO COHERENCY\n");
 			return 0;
 		}
@@ -181,6 +181,7 @@ struct __large_struct { unsigned long buf[100]; };
 		"2:\n"						\
 		"	.section	.fixup,\"ax\"\n"	\
 		"3:\n\t"					\
+		"	mov		0,%1\n"			\
 		"	mov		%3,%0\n"		\
 		"	jmp		2b\n"			\
 		"	.previous\n"				\
@@ -9,7 +9,7 @@
 * as published by the Free Software Foundation; either version
 * 2 of the Licence, or (at your option) any later version.
 */
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>

 unsigned long
 __generic_copy_to_user(void *to, const void *from, unsigned long n)
@@ -24,6 +24,8 @@ __generic_copy_from_user(void *to, const void *from, unsigned long n)
 {
 	if (access_ok(VERIFY_READ, from, n))
 		__copy_user_zeroing(to, from, n);
+	else
+		memset(to, 0, n);
 	return n;
 }

@@ -273,28 +273,20 @@ __copy_tofrom_user(void *to, const void *from, unsigned long size);
 static inline unsigned long
 copy_from_user(void *to, const void *from, unsigned long n)
 {
-	unsigned long over;
+	unsigned long res = n;

-	if (access_ok(VERIFY_READ, from, n))
-		return __copy_tofrom_user(to, from, n);
-	if ((unsigned long)from < TASK_SIZE) {
-		over = (unsigned long)from + n - TASK_SIZE;
-		return __copy_tofrom_user(to, from, n - over) + over;
-	}
-	return n;
+	if (likely(access_ok(VERIFY_READ, from, n)))
+		res = __copy_tofrom_user(to, from, n);
+	if (unlikely(res))
+		memset(to + (n - res), 0, res);
+	return res;
 }

 static inline unsigned long
 copy_to_user(void *to, const void *from, unsigned long n)
 {
-	unsigned long over;
-
-	if (access_ok(VERIFY_WRITE, to, n))
-		return __copy_tofrom_user(to, from, n);
-	if ((unsigned long)to < TASK_SIZE) {
-		over = (unsigned long)to + n - TASK_SIZE;
-		return __copy_tofrom_user(to, from, n - over) + over;
-	}
+	if (likely(access_ok(VERIFY_WRITE, to, n)))
+		n = __copy_tofrom_user(to, from, n);
 	return n;
 }

@@ -303,13 +295,8 @@ extern unsigned long __clear_user(void *addr, unsigned long size);
 static inline __must_check unsigned long
 clear_user(void *addr, unsigned long size)
 {
-
-	if (access_ok(VERIFY_WRITE, addr, size))
-		return __clear_user(addr, size);
-	if ((unsigned long)addr < TASK_SIZE) {
-		unsigned long over = (unsigned long)addr + size - TASK_SIZE;
-		return __clear_user(addr, size - over) + over;
-	}
+	if (likely(access_ok(VERIFY_WRITE, addr, size)))
+		size = __clear_user(addr, size);
 	return size;
 }

@@ -9,6 +9,8 @@
 #include <asm/errno.h>
 #include <asm-generic/uaccess-unaligned.h>

+#include <linux/string.h>
+
 #define VERIFY_READ 0
 #define VERIFY_WRITE 1

@@ -246,13 +248,14 @@ static inline unsigned long __must_check copy_from_user(void *to,
                                          unsigned long n)
 {
        int sz = __compiletime_object_size(to);
-        int ret = -EFAULT;
+        unsigned long ret = n;

        if (likely(sz == -1 || !__builtin_constant_p(n) || sz >= n))
                ret = __copy_from_user(to, from, n);
        else
                copy_from_user_overflow();
-
+	if (unlikely(ret))
+		memset(to + (n - ret), 0, ret);
        return ret;
 }

@@ -106,8 +106,6 @@ linux_gateway_entry:
 	mtsp	%r0,%sr4			/* get kernel space into sr4 */
 	mtsp	%r0,%sr5			/* get kernel space into sr5 */
 	mtsp	%r0,%sr6			/* get kernel space into sr6 */
-	mfsp    %sr7,%r1                        /* save user sr7 */
-	mtsp    %r1,%sr3                        /* and store it in sr3 */

 #ifdef CONFIG_64BIT
 	/* for now we can *always* set the W bit on entry to the syscall
@@ -133,6 +131,14 @@ linux_gateway_entry:
 	depdi	0, 31, 32, %r21
 1:	
 #endif
+
+	/* We use a rsm/ssm pair to prevent sr3 from being clobbered
+	 * by external interrupts.
+	 */
+	mfsp    %sr7,%r1                        /* save user sr7 */
+	rsm	PSW_SM_I, %r0			/* disable interrupts */
+	mtsp    %r1,%sr3                        /* and store it in sr3 */
+
 	mfctl   %cr30,%r1
 	xor     %r1,%r30,%r30                   /* ye olde xor trick */
 	xor     %r1,%r30,%r1
@@ -147,6 +153,7 @@ linux_gateway_entry:
 	 */

 	mtsp	%r0,%sr7			/* get kernel space into sr7 */
+	ssm	PSW_SM_I, %r0			/* enable interrupts */
 	STREGM	%r1,FRAME_SIZE(%r30)		/* save r1 (usp) here for now */
 	mfctl	%cr30,%r1			/* get task ptr in %r1 */
 	LDREG	TI_TASK(%r1),%r1
@@ -323,30 +323,17 @@ extern unsigned long __copy_tofrom_user(void __user *to,
 static inline unsigned long copy_from_user(void *to,
 		const void __user *from, unsigned long n)
 {
-	unsigned long over;
-
-	if (access_ok(VERIFY_READ, from, n))
+	if (likely(access_ok(VERIFY_READ, from, n)))
 		return __copy_tofrom_user((__force void __user *)to, from, n);
-	if ((unsigned long)from < TASK_SIZE) {
-		over = (unsigned long)from + n - TASK_SIZE;
-		return __copy_tofrom_user((__force void __user *)to, from,
-				n - over) + over;
-	}
+	memset(to, 0, n);
 	return n;
 }

 static inline unsigned long copy_to_user(void __user *to,
 		const void *from, unsigned long n)
 {
-	unsigned long over;
-
 	if (access_ok(VERIFY_WRITE, to, n))
 		return __copy_tofrom_user(to, (__force void __user *)from, n);
-	if ((unsigned long)to < TASK_SIZE) {
-		over = (unsigned long)to + n - TASK_SIZE;
-		return __copy_tofrom_user(to, (__force void __user *)from,
-				n - over) + over;
-	}
 	return n;
 }

@@ -437,10 +424,6 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size)
 	might_sleep();
 	if (likely(access_ok(VERIFY_WRITE, addr, size)))
 		return __clear_user(addr, size);
-	if ((unsigned long)addr < TASK_SIZE) {
-		unsigned long over = (unsigned long)addr + size - TASK_SIZE;
-		return __clear_user(addr, size - over) + over;
-	}
 	return size;
 }

@@ -280,7 +280,7 @@ int __init nvram_remove_partition(const char *name, int sig,

 		/* Make partition a free partition */
 		part->header.signature = NVRAM_SIG_FREE;
-		strncpy(part->header.name, "wwwwwwwwwwww", 12);
+		memset(part->header.name, 'w', 12);
 		part->header.checksum = nvram_checksum(&part->header);
 		rc = nvram_write_header(part);
 		if (rc <= 0) {
@@ -298,8 +298,8 @@ int __init nvram_remove_partition(const char *name, int sig,
 		}
 		if (prev) {
 			prev->header.length += part->header.length;
-			prev->header.checksum = nvram_checksum(&part->header);
-			rc = nvram_write_header(part);
+			prev->header.checksum = nvram_checksum(&prev->header);
+			rc = nvram_write_header(prev);
 			if (rc <= 0) {
 				printk(KERN_ERR "nvram_remove_partition: nvram_write failed (%d)\n", rc);
 				return rc;
@@ -57,7 +57,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
 	bl	V_LOCAL_FUNC(__get_datapage)
 	mtlr	r12
 	addi	r3,r3,CFG_SYSCALL_MAP64
-	cmpli	cr0,r4,0
+	cmpldi	cr0,r4,0
 	crclr	cr0*4+so
 	beqlr
 	li	r0,__NR_syscalls
@@ -145,7 +145,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
 	bne	cr0,99f

 	li	r3,0
-	cmpli	cr0,r4,0
+	cmpldi	cr0,r4,0
 	crclr	cr0*4+so
 	beqlr
 	lis	r5,CLOCK_REALTIME_RES@h
@@ -336,6 +336,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	addi	r3,r3,8
 171:
 177:
+179:
 	addi	r3,r3,8
 370:
 372:
@@ -350,7 +351,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 173:
 174:
 175:
-179:
 181:
 184:
 186:
@@ -110,7 +110,12 @@ BEGIN_FTR_SECTION
 END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
 	b	slb_finish_load_1T

-0:
+0:	/*
+	 * For userspace addresses, make sure this is region 0.
+	 */
+	cmpdi	r9, 0
+	bne	8f
+
 	/* when using slices, we extract the psize off the slice bitmaps
 	 * and then we need to get the sllp encoding off the mmu_psize_defs
 	 * array.
@@ -176,8 +176,8 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pnv_phb *phb)
 	pr_info("  dma1ErrorLog1        = 0x%016llx\n", data->dma1ErrorLog1);

 	for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
-		if ((data->pestA[i] >> 63) == 0 &&
-		    (data->pestB[i] >> 63) == 0)
+		if ((be64_to_cpu(data->pestA[i]) >> 63) == 0 &&
+		    (be64_to_cpu(data->pestB[i]) >> 63) == 0)
 			continue;
 		pr_info("  PE[%3d] PESTA        = 0x%016llx\n", i, data->pestA[i]);
 		pr_info("          PESTB        = 0x%016llx\n", data->pestB[i]);
@@ -164,28 +164,28 @@ extern int __put_user_bad(void) __attribute__((noreturn));
 	__chk_user_ptr(ptr);					\
 	switch (sizeof(*(ptr))) {				\
 	case 1: {						\
-		unsigned char __x;				\
+		unsigned char __x = 0;				\
 		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
 					 ptr, &__x);		\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 2: {						\
-		unsigned short __x;				\
+		unsigned short __x = 0;				\
 		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
 					 ptr, &__x);		\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 4: {						\
-		unsigned int __x;				\
+		unsigned int __x = 0;				\
 		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
 					 ptr, &__x);		\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
 		break;						\
 	};							\
 	case 8: {						\
-		unsigned long long __x;				\
+		unsigned long long __x = 0;			\
 		__gu_err = __get_user_fn(sizeof (*(ptr)),	\
 					 ptr, &__x);		\
 		(x) = *(__force __typeof__(*(ptr)) *) &__x;	\
@@ -158,7 +158,7 @@ do {									\
 		__get_user_asm(val, "lw", ptr);				\
 		 break;							\
 	case 8: 							\
-		if ((copy_from_user((void *)&val, ptr, 8)) == 0)	\
+		if (__copy_from_user((void *)&val, ptr, 8) == 0)	\
 			__gu_err = 0;					\
 		else							\
 			__gu_err = -EFAULT;				\
@@ -183,6 +183,8 @@ do {									\
 									\
 	if (likely(access_ok(VERIFY_READ, __gu_ptr, size)))		\
 		__get_user_common((x), size, __gu_ptr);			\
+	else								\
+		(x) = 0;						\
 									\
 	__gu_err;							\
 })
@@ -196,6 +198,7 @@ do {									\
 		"2:\n"							\
 		".section .fixup,\"ax\"\n"				\
 		"3:li	%0, %4\n"					\
+		"li	%1, 0\n"					\
 		"j	2b\n"						\
 		".previous\n"						\
 		".section __ex_table,\"a\"\n"				\
@@ -293,35 +296,34 @@ extern int __copy_tofrom_user(void *to, const void *from, unsigned long len);
 static inline unsigned long
 copy_from_user(void *to, const void *from, unsigned long len)
 {
-	unsigned long over;
+	unsigned long res = len;

-	if (access_ok(VERIFY_READ, from, len))
-		return __copy_tofrom_user(to, from, len);
+	if (likely(access_ok(VERIFY_READ, from, len)))
+		res = __copy_tofrom_user(to, from, len);

-	if ((unsigned long)from < TASK_SIZE) {
-		over = (unsigned long)from + len - TASK_SIZE;
-		return __copy_tofrom_user(to, from, len - over) + over;
-	}
-	return len;
+	if (unlikely(res))
+		memset(to + (len - res), 0, res);
+
+	return res;
 }

 static inline unsigned long
 copy_to_user(void *to, const void *from, unsigned long len)
 {
-	unsigned long over;
+	if (likely(access_ok(VERIFY_WRITE, to, len)))
+		len = __copy_tofrom_user(to, from, len);

-	if (access_ok(VERIFY_WRITE, to, len))
-		return __copy_tofrom_user(to, from, len);
-
-	if ((unsigned long)to < TASK_SIZE) {
-		over = (unsigned long)to + len - TASK_SIZE;
-		return __copy_tofrom_user(to, from, len - over) + over;
-	}
 	return len;
 }

-#define __copy_from_user(to, from, len)	\
-		__copy_tofrom_user((to), (from), (len))
+static inline unsigned long
+__copy_from_user(void *to, const void *from, unsigned long len)
+{
+	unsigned long left = __copy_tofrom_user(to, from, len);
+	if (unlikely(left))
+		memset(to + (len - left), 0, left);
+	return left;
+}

 #define __copy_to_user(to, from, len)		\
 		__copy_tofrom_user((to), (from), (len))
@@ -335,17 +337,17 @@ __copy_to_user_inatomic(void *to, const void *from, unsigned long len)
 static inline unsigned long
 __copy_from_user_inatomic(void *to, const void *from, unsigned long len)
 {
-	return __copy_from_user(to, from, len);
+	return __copy_tofrom_user(to, from, len);
 }

-#define __copy_in_user(to, from, len)	__copy_from_user(to, from, len)
+#define __copy_in_user(to, from, len)	__copy_tofrom_user(to, from, len)

 static inline unsigned long
 copy_in_user(void *to, const void *from, unsigned long len)
 {
 	if (access_ok(VERIFY_READ, from, len) &&
 		      access_ok(VERFITY_WRITE, to, len))
-		return copy_from_user(to, from, len);
+		return __copy_tofrom_user(to, from, len);
 }

 /*
@@ -151,7 +151,10 @@ copy_from_user(void *to, const void __user *from, unsigned long n)
 	__kernel_size_t __copy_size = (__kernel_size_t) n;

 	if (__copy_size && __access_ok(__copy_from, __copy_size))
-		return __copy_user(to, from, __copy_size);
+		__copy_size = __copy_user(to, from, __copy_size);
+
+	if (unlikely(__copy_size))
+		memset(to + (n - __copy_size), 0, __copy_size);

 	return __copy_size;
 }
@@ -24,6 +24,7 @@
 #define __get_user_size(x,ptr,size,retval)			\
 do {								\
 	retval = 0;						\
+	x = 0;							\
 	switch (size) {						\
 	case 1:							\
 		retval = __get_user_asm_b((void *)&x,		\
@@ -265,8 +265,10 @@ static inline unsigned long copy_from_user(void *to, const void __user *from, un
 {
 	if (n && __access_ok((unsigned long) from, n))
 		return __copy_user((__force void __user *) to, from, n);
-	else
+	else {
+		memset(to, 0, n);
 		return n;
+	}
 }

 static inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
@@ -215,8 +215,8 @@ void do_timer_interrupt(struct pt_regs *regs, int fault_num)
 */
 unsigned long long sched_clock(void)
 {
-	return clocksource_cyc2ns(get_cycles(),
-				  sched_clock_mult, SCHED_CLOCK_SHIFT);
+	return mult_frac(get_cycles(),
+			 sched_clock_mult, 1ULL << SCHED_CLOCK_SHIFT);
 }

 int setup_profiling_timer(unsigned int multiplier)
@@ -7,7 +7,7 @@
 targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo

 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
-KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
+KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC)
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 cflags-$(CONFIG_X86_32) := -march=i386
 cflags-$(CONFIG_X86_64) := -mcmodel=small
@@ -20,6 +20,18 @@ KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n

 LDFLAGS := -m elf_$(UTS_MACHINE)
+ifeq ($(CONFIG_RELOCATABLE),y)
+# If kernel is relocatable, build compressed kernel as PIE.
+ifeq ($(CONFIG_X86_32),y)
+LDFLAGS += $(call ld-option, -pie) $(call ld-option, --no-dynamic-linker)
+else
+# To build 64-bit compressed kernel as PIE, we disable relocation
+# overflow check to avoid relocation overflow error with a new linker
+# command-line option, -z noreloc-overflow.
+LDFLAGS += $(shell $(LD) --help 2>&1 | grep -q "\-z noreloc-overflow" \
+	&& echo "-z noreloc-overflow -pie --no-dynamic-linker")
+endif
+endif
 LDFLAGS_vmlinux := -T

 hostprogs-y	:= mkpiggy
@@ -30,6 +30,34 @@
 #include <asm/boot.h>
 #include <asm/asm-offsets.h>

+/*
+ * The 32-bit x86 assembler in binutils 2.26 will generate R_386_GOT32X
+ * relocation to get the symbol address in PIC.  When the compressed x86
+ * kernel isn't built as PIC, the linker optimizes R_386_GOT32X
+ * relocations to their fixed symbol addresses.  However, when the
+ * compressed x86 kernel is loaded at a different address, it leads
+ * to the following load failure:
+ *
+ *   Failed to allocate space for phdrs
+ *
+ * during the decompression stage.
+ *
+ * If the compressed x86 kernel is relocatable at run-time, it should be
+ * compiled with -fPIE, instead of -fPIC, if possible and should be built as
+ * Position Independent Executable (PIE) so that linker won't optimize
+ * R_386_GOT32X relocation to its fixed symbol address.  Older
+ * linkers generate R_386_32 relocations against locally defined symbols,
+ * _bss, _ebss, _got and _egot, in PIE.  It isn't wrong, just less
+ * optimal than R_386_RELATIVE.  But the x86 kernel fails to properly handle
+ * R_386_32 relocations when relocating the kernel.  To generate
+ * R_386_RELATIVE relocations, we mark _bss, _ebss, _got and _egot as
+ * hidden:
+ */
+	.hidden _bss
+	.hidden _ebss
+	.hidden _got
+	.hidden _egot
+
 	__HEAD
 ENTRY(startup_32)
 #ifdef CONFIG_EFI_STUB
@@ -34,6 +34,14 @@
 #include <asm/processor-flags.h>
 #include <asm/asm-offsets.h>

+/*
+ * Locally defined symbols should be marked hidden:
+ */
+	.hidden _bss
+	.hidden _ebss
+	.hidden _got
+	.hidden _egot
+
 	__HEAD
 	.code32
 ENTRY(startup_32)
@@ -4,6 +4,7 @@
 #include <asm/page.h>
 #include <asm-generic/hugetlb.h>

+#define hugepages_supported() cpu_has_pse

 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,
@@ -17,7 +17,14 @@

 static inline void __native_flush_tlb(void)
 {
+	/*
+	 * If current->mm == NULL then we borrow a mm which may change during a
+	 * task switch and therefore we must not be preempted while we write CR3
+	 * back:
+	 */
+	preempt_disable();
 	native_write_cr3(native_read_cr3());
+	preempt_enable();
 }

 static inline void __native_flush_tlb_global_irq_disabled(void)
@@ -381,7 +381,7 @@ do {									\
 	asm volatile("1:	mov"itype" %1,%"rtype"0\n"		\
 		     "2:\n"						\
 		     _ASM_EXTABLE_EX(1b, 2b)				\
-		     : ltype(x) : "m" (__m(addr)))
+		     : ltype(x) : "m" (__m(addr)), "0" (0))

 #define __put_user_nocheck(x, ptr, size)			\
 ({								\
@@ -1581,6 +1581,9 @@ void __init enable_IR_x2apic(void)
 	int ret, x2apic_enabled = 0;
 	int hardware_init_ret;

+	if (skip_ioapic_setup)
+		return;
+
 	/* Make sure irq_remap_ops are initialized */
 	setup_irq_remapping_ops();

@@ -586,7 +586,7 @@ early_idt_handler_common:
 	movl %eax,%ds
 	movl %eax,%es

-	cmpl $(__KERNEL_CS),32(%esp)
+	cmpw $(__KERNEL_CS),32(%esp)
 	jne 10f

 	leal 28(%esp),%eax	# Pointer to %eip
@@ -46,12 +46,12 @@ void _paravirt_nop(void)
 }

 /* identity function, which can be inlined */
-u32 _paravirt_ident_32(u32 x)
+u32 notrace _paravirt_ident_32(u32 x)
 {
 	return x;
 }

-u64 _paravirt_ident_64(u64 x)
+u64 notrace _paravirt_ident_64(u64 x)
 {
 	return x;
 }
@@ -366,6 +366,7 @@ struct nested_vmx {
 	struct list_head vmcs02_pool;
 	int vmcs02_num;
 	u64 vmcs01_tsc_offset;
+	bool change_vmcs01_virtual_x2apic_mode;
 	/* L2 must run next, and mustn't decide to exit to L1. */
 	bool nested_run_pending;
 	/*
@@ -6702,6 +6703,12 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 {
 	u32 sec_exec_control;

+	/* Postpone execution until vmcs01 is the current VMCS. */
+	if (is_guest_mode(vcpu)) {
+		to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true;
+		return;
+	}
+
 	/*
 	 * There is not point to enable virtualize x2apic without enable
 	 * apicv
@@ -8085,6 +8092,12 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu)
 	/* Update TSC_OFFSET if TSC was changed while L2 ran */
 	vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);

+	if (vmx->nested.change_vmcs01_virtual_x2apic_mode) {
+		vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
+		vmx_set_virtual_x2apic_mode(vcpu,
+				vcpu->arch.apic_base & X2APIC_ENABLE);
+	}
+
 	/* This is needed for same reason as it was needed in prepare_vmcs02 */
 	vmx->host_rsp = 0;

@@ -178,7 +178,18 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	struct kvm_shared_msrs *locals
 		= container_of(urn, struct kvm_shared_msrs, urn);
 	struct kvm_shared_msr_values *values;
+	unsigned long flags;

+	/*
+	 * Disabling irqs at this point since the following code could be
+	 * interrupted and executed through kvm_arch_hardware_disable()
+	 */
+	local_irq_save(flags);
+	if (locals->registered) {
+		locals->registered = false;
+		user_return_notifier_unregister(urn);
+	}
+	local_irq_restore(flags);
 	for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
 		values = &locals->values[slot];
 		if (values->host != values->curr) {
@@ -186,8 +197,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 			values->curr = values->host;
 		}
 	}
-	locals->registered = false;
-	user_return_notifier_unregister(urn);
 }

 static void shared_msr_update(unsigned slot, u32 msr)
@@ -3182,6 +3191,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	};
 	case KVM_SET_VAPIC_ADDR: {
 		struct kvm_vapic_addr va;
+		int idx;

 		r = -EINVAL;
 		if (!irqchip_in_kernel(vcpu->kvm))
@@ -3189,7 +3199,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&va, argp, sizeof va))
 			goto out;
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_X86_SETUP_MCE: {
@@ -6509,11 +6521,13 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)

 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
+	void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
+
 	kvmclock_reset(vcpu);

-	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
 	fx_free(vcpu);
 	kvm_x86_ops->vcpu_free(vcpu);
+	free_cpumask_var(wbinvd_dirty_mask);
 }

 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
@@ -505,11 +505,8 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 		return 1;

 	while (cursor < to) {
-		if (!devmem_is_allowed(pfn)) {
-			printk(KERN_INFO "Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx]\n",
-				current->comm, from, to - 1);
+		if (!devmem_is_allowed(pfn))
 			return 0;
-		}
 		cursor += PAGE_SIZE;
 		pfn++;
 	}
@@ -51,11 +51,7 @@

 #else /* CONFIG_SMP */

-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#include <asm-generic/barrier.h>

 #endif /* CONFIG_SMP */

@@ -1187,7 +1187,7 @@ static void __init xen_cleanhighmap(unsigned long vaddr,

 	/* NOTE: The loop is more greedy than the cleanup_highmap variant.
 	 * We include the PMD passed in on _both_ boundaries. */
-	for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE));
+	for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PTRS_PER_PMD));
 			pmd++, vaddr += PMD_SIZE) {
 		if (pmd_none(*pmd))
 			continue;
@@ -2812,7 +2812,6 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
 	if (time_before(jiffies, rq_fifo_time(rq)))
 		rq = NULL;

-	cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
 	return rq;
 }

@@ -3186,6 +3185,9 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
 	unsigned int max_dispatch;

+	if (cfq_cfqq_must_dispatch(cfqq))
+		return true;
+
 	/*
 	 * Drain async requests before we start sync IO
 	 */
@@ -3277,15 +3279,20 @@ static bool cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)

 	BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));

+	rq = cfq_check_fifo(cfqq);
+	if (rq)
+		cfq_mark_cfqq_must_dispatch(cfqq);
+
 	if (!cfq_may_dispatch(cfqd, cfqq))
 		return false;

 	/*
 	 * follow expired path, else get first next available
 	 */
-	rq = cfq_check_fifo(cfqq);
 	if (!rq)
 		rq = cfqq->next_rq;
+	else
+		cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);

 	/*
 	 * insert request into driver dispatch list
@@ -3794,7 +3801,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	 * if the new request is sync, but the currently running queue is
 	 * not, let the sync request have priority.
 	 */
-	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
+	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq) && !cfq_cfqq_must_dispatch(cfqq))
 		return true;

 	if (new_cfqq->cfqg != cfqq->cfqg)
@@ -379,6 +379,7 @@ static int crypto_init_ablkcipher_ops(struct crypto_tfm *tfm, u32 type,
 	}
 	crt->base = __crypto_ablkcipher_cast(tfm);
 	crt->ivsize = alg->ivsize;
+	crt->has_setkey = alg->max_keysize;

 	return 0;
 }
@@ -460,6 +461,7 @@ static int crypto_init_givcipher_ops(struct crypto_tfm *tfm, u32 type,
 	crt->givdecrypt = alg->givdecrypt ?: no_givdecrypt;
 	crt->base = __crypto_ablkcipher_cast(tfm);
 	crt->ivsize = alg->ivsize;
+	crt->has_setkey = alg->max_keysize;

 	return 0;
 }
@@ -76,6 +76,8 @@ int af_alg_register_type(const struct af_alg_type *type)
 		goto unlock;

 	type->ops->owner = THIS_MODULE;
+	if (type->ops_nokey)
+		type->ops_nokey->owner = THIS_MODULE;
 	node->type = type;
 	list_add(&node->list, &alg_types);
 	err = 0;
@@ -125,6 +127,26 @@ int af_alg_release(struct socket *sock)
 }
 EXPORT_SYMBOL_GPL(af_alg_release);

+void af_alg_release_parent(struct sock *sk)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	unsigned int nokey = ask->nokey_refcnt;
+	bool last = nokey && !ask->refcnt;
+
+	sk = ask->parent;
+	ask = alg_sk(sk);
+
+	lock_sock(sk);
+	ask->nokey_refcnt -= nokey;
+	if (!last)
+		last = !--ask->refcnt;
+	release_sock(sk);
+
+	if (last)
+		sock_put(sk);
+}
+EXPORT_SYMBOL_GPL(af_alg_release_parent);
+
 static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
 	struct sock *sk = sock->sk;
@@ -132,6 +154,7 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct sockaddr_alg *sa = (void *)uaddr;
 	const struct af_alg_type *type;
 	void *private;
+	int err;

 	if (sock->state == SS_CONNECTED)
 		return -EINVAL;
@@ -157,16 +180,22 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		return PTR_ERR(private);
 	}

+	err = -EBUSY;
 	lock_sock(sk);
+	if (ask->refcnt | ask->nokey_refcnt)
+		goto unlock;

 	swap(ask->type, type);
 	swap(ask->private, private);

+	err = 0;
+
+unlock:
 	release_sock(sk);

 	alg_do_release(type, private);

-	return 0;
+	return err;
 }

 static int alg_setkey(struct sock *sk, char __user *ukey,
@@ -199,11 +228,15 @@ static int alg_setsockopt(struct socket *sock, int level, int optname,
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 	const struct af_alg_type *type;
-	int err = -ENOPROTOOPT;
+	int err = -EBUSY;

 	lock_sock(sk);
+	if (ask->refcnt)
+		goto unlock;
+
 	type = ask->type;

+	err = -ENOPROTOOPT;
 	if (level != SOL_ALG || !type)
 		goto unlock;

@@ -228,6 +261,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock)
 	struct alg_sock *ask = alg_sk(sk);
 	const struct af_alg_type *type;
 	struct sock *sk2;
+	unsigned int nokey;
 	int err;

 	lock_sock(sk);
@@ -247,18 +281,29 @@ int af_alg_accept(struct sock *sk, struct socket *newsock)
 	security_sk_clone(sk, sk2);

 	err = type->accept(ask->private, sk2);
+
+	nokey = err == -ENOKEY;
+	if (nokey && type->accept_nokey)
+		err = type->accept_nokey(ask->private, sk2);
+
 	if (err)
 		goto unlock;

 	sk2->sk_family = PF_ALG;

-	sock_hold(sk);
+	if (nokey || !ask->refcnt++)
+		sock_hold(sk);
+	ask->nokey_refcnt += nokey;
 	alg_sk(sk2)->parent = sk;
 	alg_sk(sk2)->type = type;
+	alg_sk(sk2)->nokey_refcnt = nokey;

 	newsock->ops = type->ops;
 	newsock->state = SS_CONNECTED;

+	if (nokey)
+		newsock->ops = type->ops_nokey;
+
 	err = 0;

 unlock:
@@ -370,6 +370,7 @@ static int crypto_ahash_init_tfm(struct crypto_tfm *tfm)
 	struct ahash_alg *alg = crypto_ahash_alg(hash);

 	hash->setkey = ahash_nosetkey;
+	hash->has_setkey = false;
 	hash->export = ahash_no_export;
 	hash->import = ahash_no_import;

@@ -382,8 +383,10 @@ static int crypto_ahash_init_tfm(struct crypto_tfm *tfm)
 	hash->finup = alg->finup ?: ahash_def_finup;
 	hash->digest = alg->digest;

-	if (alg->setkey)
+	if (alg->setkey) {
 		hash->setkey = alg->setkey;
+		hash->has_setkey = true;
+	}
 	if (alg->export)
 		hash->export = alg->export;
 	if (alg->import)
@@ -34,6 +34,11 @@ struct hash_ctx {
 	struct ahash_request req;
 };

+struct algif_hash_tfm {
+	struct crypto_ahash *hash;
+	bool has_key;
+};
+
 static int hash_sendmsg(struct kiocb *unused, struct socket *sock,
 			struct msghdr *msg, size_t ignored)
 {
@@ -248,19 +253,151 @@ static struct proto_ops algif_hash_ops = {
 	.accept		=	hash_accept,
 };

+static int hash_check_key(struct socket *sock)
+{
+	int err = 0;
+	struct sock *psk;
+	struct alg_sock *pask;
+	struct algif_hash_tfm *tfm;
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+
+	lock_sock(sk);
+	if (ask->refcnt)
+		goto unlock_child;
+
+	psk = ask->parent;
+	pask = alg_sk(ask->parent);
+	tfm = pask->private;
+
+	err = -ENOKEY;
+	lock_sock_nested(psk, SINGLE_DEPTH_NESTING);
+	if (!tfm->has_key)
+		goto unlock;
+
+	if (!pask->refcnt++)
+		sock_hold(psk);
+
+	ask->refcnt = 1;
+	sock_put(psk);
+
+	err = 0;
+
+unlock:
+	release_sock(psk);
+unlock_child:
+	release_sock(sk);
+
+	return err;
+}
+
+static int hash_sendmsg_nokey(struct kiocb *unused, struct socket *sock,
+			      struct msghdr *msg, size_t size)
+{
+	int err;
+
+	err = hash_check_key(sock);
+	if (err)
+		return err;
+
+	return hash_sendmsg(unused, sock, msg, size);
+}
+
+static ssize_t hash_sendpage_nokey(struct socket *sock, struct page *page,
+				   int offset, size_t size, int flags)
+{
+	int err;
+
+	err = hash_check_key(sock);
+	if (err)
+		return err;
+
+	return hash_sendpage(sock, page, offset, size, flags);
+}
+
+static int hash_recvmsg_nokey(struct kiocb *unused, struct socket *sock,
+			      struct msghdr *msg, size_t ignored, int flags)
+{
+	int err;
+
+	err = hash_check_key(sock);
+	if (err)
+		return err;
+
+	return hash_recvmsg(unused, sock, msg, ignored, flags);
+}
+
+static int hash_accept_nokey(struct socket *sock, struct socket *newsock,
+			     int flags)
+{
+	int err;
+
+	err = hash_check_key(sock);
+	if (err)
+		return err;
+
+	return hash_accept(sock, newsock, flags);
+}
+
+static struct proto_ops algif_hash_ops_nokey = {
+	.family		=	PF_ALG,
+
+	.connect	=	sock_no_connect,
+	.socketpair	=	sock_no_socketpair,
+	.getname	=	sock_no_getname,
+	.ioctl		=	sock_no_ioctl,
+	.listen		=	sock_no_listen,
+	.shutdown	=	sock_no_shutdown,
+	.getsockopt	=	sock_no_getsockopt,
+	.mmap		=	sock_no_mmap,
+	.bind		=	sock_no_bind,
+	.setsockopt	=	sock_no_setsockopt,
+	.poll		=	sock_no_poll,
+
+	.release	=	af_alg_release,
+	.sendmsg	=	hash_sendmsg_nokey,
+	.sendpage	=	hash_sendpage_nokey,
+	.recvmsg	=	hash_recvmsg_nokey,
+	.accept		=	hash_accept_nokey,
+};
+
 static void *hash_bind(const char *name, u32 type, u32 mask)
 {
-	return crypto_alloc_ahash(name, type, mask);
+	struct algif_hash_tfm *tfm;
+	struct crypto_ahash *hash;
+
+	tfm = kzalloc(sizeof(*tfm), GFP_KERNEL);
+	if (!tfm)
+		return ERR_PTR(-ENOMEM);
+
+	hash = crypto_alloc_ahash(name, type, mask);
+	if (IS_ERR(hash)) {
+		kfree(tfm);
+		return ERR_CAST(hash);
+	}
+
+	tfm->hash = hash;
+
+	return tfm;
 }

 static void hash_release(void *private)
 {
-	crypto_free_ahash(private);
+	struct algif_hash_tfm *tfm = private;
+
+	crypto_free_ahash(tfm->hash);
+	kfree(tfm);
 }

 static int hash_setkey(void *private, const u8 *key, unsigned int keylen)
 {
-	return crypto_ahash_setkey(private, key, keylen);
+	struct algif_hash_tfm *tfm = private;
+	int err;
+
+	err = crypto_ahash_setkey(tfm->hash, key, keylen);
+	tfm->has_key = !err;
+
+	return err;
 }

 static void hash_sock_destruct(struct sock *sk)
@@ -274,12 +411,14 @@ static void hash_sock_destruct(struct sock *sk)
 	af_alg_release_parent(sk);
 }

-static int hash_accept_parent(void *private, struct sock *sk)
+static int hash_accept_parent_nokey(void *private, struct sock *sk)
 {
 	struct hash_ctx *ctx;
 	struct alg_sock *ask = alg_sk(sk);
-	unsigned len = sizeof(*ctx) + crypto_ahash_reqsize(private);
-	unsigned ds = crypto_ahash_digestsize(private);
+	struct algif_hash_tfm *tfm = private;
+	struct crypto_ahash *hash = tfm->hash;
+	unsigned len = sizeof(*ctx) + crypto_ahash_reqsize(hash);
+	unsigned ds = crypto_ahash_digestsize(hash);

 	ctx = sock_kmalloc(sk, len, GFP_KERNEL);
 	if (!ctx)
@@ -299,7 +438,7 @@ static int hash_accept_parent(void *private, struct sock *sk)

 	ask->private = ctx;

-	ahash_request_set_tfm(&ctx->req, private);
+	ahash_request_set_tfm(&ctx->req, hash);
 	ahash_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				   af_alg_complete, &ctx->completion);

@@ -308,12 +447,24 @@ static int hash_accept_parent(void *private, struct sock *sk)
 	return 0;
 }

+static int hash_accept_parent(void *private, struct sock *sk)
+{
+	struct algif_hash_tfm *tfm = private;
+
+	if (!tfm->has_key && crypto_ahash_has_setkey(tfm->hash))
+		return -ENOKEY;
+
+	return hash_accept_parent_nokey(private, sk);
+}
+
 static const struct af_alg_type algif_type_hash = {
 	.bind		=	hash_bind,
 	.release	=	hash_release,
 	.setkey		=	hash_setkey,
 	.accept		=	hash_accept_parent,
+	.accept_nokey	=	hash_accept_parent_nokey,
 	.ops		=	&algif_hash_ops,
+	.ops_nokey	=	&algif_hash_ops_nokey,
 	.name		=	"hash",
 	.owner		=	THIS_MODULE
 };
@@ -31,6 +31,11 @@ struct skcipher_sg_list {
 	struct scatterlist sg[0];
 };

+struct skcipher_tfm {
+	struct crypto_ablkcipher *skcipher;
+	bool has_key;
+};
+
 struct skcipher_ctx {
 	struct list_head tsgl;
 	struct af_alg_sgl rsgl;
@@ -441,13 +446,6 @@ static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock,
 		char __user *from = iov->iov_base;

 		while (seglen) {
-			sgl = list_first_entry(&ctx->tsgl,
-					       struct skcipher_sg_list, list);
-			sg = sgl->sg;
-
-			while (!sg->length)
-				sg++;
-
 			used = ctx->used;
 			if (!used) {
 				err = skcipher_wait_for_data(sk, flags);
@@ -469,6 +467,13 @@ static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock,
 			if (!used)
 				goto free;

+			sgl = list_first_entry(&ctx->tsgl,
+					       struct skcipher_sg_list, list);
+			sg = sgl->sg;
+
+			while (!sg->length)
+				sg++;
+
 			ablkcipher_request_set_crypt(&ctx->req, sg,
 						     ctx->rsgl.sg, used,
 						     ctx->iv);
@@ -544,19 +549,139 @@ static struct proto_ops algif_skcipher_ops = {
 	.poll		=	skcipher_poll,
 };

+static int skcipher_check_key(struct socket *sock)
+{
+	int err = 0;
+	struct sock *psk;
+	struct alg_sock *pask;
+	struct skcipher_tfm *tfm;
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+
+	lock_sock(sk);
+	if (ask->refcnt)
+		goto unlock_child;
+
+	psk = ask->parent;
+	pask = alg_sk(ask->parent);
+	tfm = pask->private;
+
+	err = -ENOKEY;
+	lock_sock_nested(psk, SINGLE_DEPTH_NESTING);
+	if (!tfm->has_key)
+		goto unlock;
+
+	if (!pask->refcnt++)
+		sock_hold(psk);
+
+	ask->refcnt = 1;
+	sock_put(psk);
+
+	err = 0;
+
+unlock:
+	release_sock(psk);
+unlock_child:
+	release_sock(sk);
+
+	return err;
+}
+
+static int skcipher_sendmsg_nokey(struct kiocb *unused, struct socket *sock,
+				  struct msghdr *msg, size_t size)
+{
+	int err;
+
+	err = skcipher_check_key(sock);
+	if (err)
+		return err;
+
+	return skcipher_sendmsg(unused, sock, msg, size);
+}
+
+static ssize_t skcipher_sendpage_nokey(struct socket *sock, struct page *page,
+				       int offset, size_t size, int flags)
+{
+	int err;
+
+	err = skcipher_check_key(sock);
+	if (err)
+		return err;
+
+	return skcipher_sendpage(sock, page, offset, size, flags);
+}
+
+static int skcipher_recvmsg_nokey(struct kiocb *unused, struct socket *sock,
+				  struct msghdr *msg, size_t ignored, int flags)
+{
+	int err;
+
+	err = skcipher_check_key(sock);
+	if (err)
+		return err;
+
+	return skcipher_recvmsg(unused, sock, msg, ignored, flags);
+}
+
+static struct proto_ops algif_skcipher_ops_nokey = {
+	.family		=	PF_ALG,
+
+	.connect	=	sock_no_connect,
+	.socketpair	=	sock_no_socketpair,
+	.getname	=	sock_no_getname,
+	.ioctl		=	sock_no_ioctl,
+	.listen		=	sock_no_listen,
+	.shutdown	=	sock_no_shutdown,
+	.getsockopt	=	sock_no_getsockopt,
+	.mmap		=	sock_no_mmap,
+	.bind		=	sock_no_bind,
+	.accept		=	sock_no_accept,
+	.setsockopt	=	sock_no_setsockopt,
+
+	.release	=	af_alg_release,
+	.sendmsg	=	skcipher_sendmsg_nokey,
+	.sendpage	=	skcipher_sendpage_nokey,
+	.recvmsg	=	skcipher_recvmsg_nokey,
+	.poll		=	skcipher_poll,
+};
+
 static void *skcipher_bind(const char *name, u32 type, u32 mask)
 {
-	return crypto_alloc_ablkcipher(name, type, mask);
+	struct skcipher_tfm *tfm;
+	struct crypto_ablkcipher *skcipher;
+
+	tfm = kzalloc(sizeof(*tfm), GFP_KERNEL);
+	if (!tfm)
+		return ERR_PTR(-ENOMEM);
+
+	skcipher = crypto_alloc_ablkcipher(name, type, mask);
+	if (IS_ERR(skcipher)) {
+		kfree(tfm);
+		return ERR_CAST(skcipher);
+	}
+
+	tfm->skcipher = skcipher;
+
+	return tfm;
 }

 static void skcipher_release(void *private)
 {
-	crypto_free_ablkcipher(private);
+	struct skcipher_tfm *tfm = private;
+
+	crypto_free_ablkcipher(tfm->skcipher);
+	kfree(tfm);
 }

 static int skcipher_setkey(void *private, const u8 *key, unsigned int keylen)
 {
-	return crypto_ablkcipher_setkey(private, key, keylen);
+	struct skcipher_tfm *tfm = private;
+	int err;
+
+	err = crypto_ablkcipher_setkey(tfm->skcipher, key, keylen);
+	tfm->has_key = !err;
+
+	return err;
 }

 static void skcipher_sock_destruct(struct sock *sk)
@@ -571,24 +696,25 @@ static void skcipher_sock_destruct(struct sock *sk)
 	af_alg_release_parent(sk);
 }

-static int skcipher_accept_parent(void *private, struct sock *sk)
+static int skcipher_accept_parent_nokey(void *private, struct sock *sk)
 {
 	struct skcipher_ctx *ctx;
 	struct alg_sock *ask = alg_sk(sk);
-	unsigned int len = sizeof(*ctx) + crypto_ablkcipher_reqsize(private);
+	struct skcipher_tfm *tfm = private;
+	struct crypto_ablkcipher *skcipher = tfm->skcipher;
+	unsigned int len = sizeof(*ctx) + crypto_ablkcipher_reqsize(skcipher);

 	ctx = sock_kmalloc(sk, len, GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
-
-	ctx->iv = sock_kmalloc(sk, crypto_ablkcipher_ivsize(private),
+	ctx->iv = sock_kmalloc(sk, crypto_ablkcipher_ivsize(skcipher),
 			       GFP_KERNEL);
 	if (!ctx->iv) {
 		sock_kfree_s(sk, ctx, len);
 		return -ENOMEM;
 	}

-	memset(ctx->iv, 0, crypto_ablkcipher_ivsize(private));
+	memset(ctx->iv, 0, crypto_ablkcipher_ivsize(skcipher));

 	INIT_LIST_HEAD(&ctx->tsgl);
 	ctx->len = len;
@@ -600,21 +726,33 @@ static int skcipher_accept_parent(void *private, struct sock *sk)

 	ask->private = ctx;

-	ablkcipher_request_set_tfm(&ctx->req, private);
+	ablkcipher_request_set_tfm(&ctx->req, skcipher);
 	ablkcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG,
-					af_alg_complete, &ctx->completion);
+				      af_alg_complete, &ctx->completion);

 	sk->sk_destruct = skcipher_sock_destruct;

 	return 0;
 }

+static int skcipher_accept_parent(void *private, struct sock *sk)
+{
+	struct skcipher_tfm *tfm = private;
+
+	if (!tfm->has_key && crypto_ablkcipher_has_setkey(tfm->skcipher))
+		return -ENOKEY;
+
+	return skcipher_accept_parent_nokey(private, sk);
+}
+
 static const struct af_alg_type algif_type_skcipher = {
 	.bind		=	skcipher_bind,
 	.release	=	skcipher_release,
 	.setkey		=	skcipher_setkey,
 	.accept		=	skcipher_accept_parent,
+	.accept_nokey	=	skcipher_accept_parent_nokey,
 	.ops		=	&algif_skcipher_ops,
+	.ops_nokey	=	&algif_skcipher_ops_nokey,
 	.name		=	"skcipher",
 	.owner		=	THIS_MODULE
 };
@@ -233,6 +233,8 @@ static int blkcipher_walk_next(struct blkcipher_desc *desc,
 		return blkcipher_walk_done(desc, walk, -EINVAL);
 	}

+	bsize = min(walk->blocksize, n);
+
 	walk->flags &= ~(BLKCIPHER_WALK_SLOW | BLKCIPHER_WALK_COPY |
 			 BLKCIPHER_WALK_DIFF);
 	if (!scatterwalk_aligned(&walk->in, walk->alignmask) ||
@@ -471,6 +473,7 @@ static int crypto_init_blkcipher_ops_async(struct crypto_tfm *tfm)
 	}
 	crt->base = __crypto_ablkcipher_cast(tfm);
 	crt->ivsize = alg->ivsize;
+	crt->has_setkey = alg->max_keysize;

 	return 0;
 }
@@ -565,9 +565,14 @@ static int cryptd_hash_export(struct ahash_request *req, void *out)

 static int cryptd_hash_import(struct ahash_request *req, const void *in)
 {
-	struct cryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct shash_desc *desc = cryptd_shash_desc(req);

-	return crypto_shash_import(&rctx->desc, in);
+	desc->tfm = ctx->child;
+	desc->flags = req->base.flags;
+
+	return crypto_shash_import(desc, in);
 }

 static int cryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
@@ -109,7 +109,7 @@ static int crypto_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 	struct crypto_ablkcipher *ctr = ctx->ctr;
 	struct {
 		be128 hash;
-		u8 iv[8];
+		u8 iv[16];

 		struct crypto_gcm_setkey_result result;

@@ -353,9 +353,10 @@ int crypto_init_shash_ops_async(struct crypto_tfm *tfm)
 	crt->final = shash_async_final;
 	crt->finup = shash_async_finup;
 	crt->digest = shash_async_digest;
+	crt->setkey = shash_async_setkey;
+
+	crt->has_setkey = alg->setkey != shash_no_setkey;

-	if (alg->setkey)
-		crt->setkey = shash_async_setkey;
 	if (alg->export)
 		crt->export = shash_async_export;
 	if (alg->import)
@@ -647,7 +647,7 @@ static int ghes_proc(struct ghes *ghes)
 	ghes_do_proc(ghes, ghes->estatus);
 out:
 	ghes_clear_estatus(ghes);
-	return 0;
+	return rc;
 }

 static void ghes_add_timer(struct ghes *ghes)
@@ -827,11 +827,29 @@ static struct kobject *get_device_parent(struct device *dev,
 	return NULL;
 }

+static inline bool live_in_glue_dir(struct kobject *kobj,
+				    struct device *dev)
+{
+	if (!kobj || !dev->class ||
+	    kobj->kset != &dev->class->p->glue_dirs)
+		return false;
+	return true;
+}
+
+static inline struct kobject *get_glue_dir(struct device *dev)
+{
+	return dev->kobj.parent;
+}
+
+/*
+ * make sure cleaning up dir as the last step, we need to make
+ * sure .release handler of kobject is run with holding the
+ * global lock
+ */
 static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir)
 {
 	/* see if we live in a "glue" directory */
-	if (!glue_dir || !dev->class ||
-	    glue_dir->kset != &dev->class->p->glue_dirs)
+	if (!live_in_glue_dir(glue_dir, dev))
 		return;

 	mutex_lock(&gdp_mutex);
@@ -839,11 +857,6 @@ static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir)
 	mutex_unlock(&gdp_mutex);
 }

-static void cleanup_device_parent(struct device *dev)
-{
-	cleanup_glue_dir(dev, dev->kobj.parent);
-}
-
 static int device_add_class_symlinks(struct device *dev)
 {
 	int error;
@@ -1007,6 +1020,7 @@ int device_add(struct device *dev)
 	struct kobject *kobj;
 	struct class_interface *class_intf;
 	int error = -EINVAL;
+	struct kobject *glue_dir = NULL;

 	dev = get_device(dev);
 	if (!dev)
@@ -1051,8 +1065,10 @@ int device_add(struct device *dev)
 	/* first, register with generic layer. */
 	/* we require the name to be set before, and pass NULL */
 	error = kobject_add(&dev->kobj, dev->kobj.parent, NULL);
-	if (error)
+	if (error) {
+		glue_dir = get_glue_dir(dev);
 		goto Error;
+	}

 	/* notify platform of device entry */
 	if (platform_notify)
@@ -1135,11 +1151,11 @@ done:
 	device_remove_file(dev, &uevent_attr);
 attrError:
 	kobject_uevent(&dev->kobj, KOBJ_REMOVE);
+	glue_dir = get_glue_dir(dev);
 	kobject_del(&dev->kobj);
 Error:
-	cleanup_device_parent(dev);
-	if (parent)
-		put_device(parent);
+	cleanup_glue_dir(dev, glue_dir);
+	put_device(parent);
 name_error:
 	kfree(dev->p);
 	dev->p = NULL;
@@ -1210,6 +1226,7 @@ void put_device(struct device *dev)
 void device_del(struct device *dev)
 {
 	struct device *parent = dev->parent;
+	struct kobject *glue_dir = NULL;
 	struct class_interface *class_intf;

 	/* Notify clients of device removal.  This call must come
@@ -1251,8 +1268,9 @@ void device_del(struct device *dev)
 	if (platform_notify_remove)
 		platform_notify_remove(dev);
 	kobject_uevent(&dev->kobj, KOBJ_REMOVE);
-	cleanup_device_parent(dev);
+	glue_dir = get_glue_dir(dev);
 	kobject_del(&dev->kobj);
+	cleanup_glue_dir(dev, glue_dir);
 	put_device(parent);
 }

@@ -1771,7 +1771,7 @@ int drbd_send(struct drbd_tconn *tconn, struct socket *sock,
 * do we need to block DRBD_SIG if sock == &meta.socket ??
 * otherwise wake_asender() might interrupt some send_*Ack !
 */
-		rv = kernel_sendmsg(sock, &msg, &iov, 1, size);
+		rv = kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len);
 		if (rv == -EAGAIN) {
 			if (we_should_drop_the_connection(tconn, sock))
 				break;
@@ -269,8 +269,8 @@ static inline void blkif_get_x86_32_req(struct blkif_request *dst,
 					struct blkif_x86_32_request *src)
 {
 	int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST;
-	dst->operation = src->operation;
-	switch (src->operation) {
+	dst->operation = ACCESS_ONCE(src->operation);
+	switch (dst->operation) {
 	case BLKIF_OP_READ:
 	case BLKIF_OP_WRITE:
 	case BLKIF_OP_WRITE_BARRIER:
@@ -305,8 +305,8 @@ static inline void blkif_get_x86_64_req(struct blkif_request *dst,
 					struct blkif_x86_64_request *src)
 {
 	int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST;
-	dst->operation = src->operation;
-	switch (src->operation) {
+	dst->operation = ACCESS_ONCE(src->operation);
+	switch (dst->operation) {
 	case BLKIF_OP_READ:
 	case BLKIF_OP_WRITE:
 	case BLKIF_OP_WRITE_BARRIER:
@@ -105,6 +105,7 @@ static int exynos_rng_probe(struct platform_device *pdev)
 {
 	struct exynos_rng *exynos_rng;
 	struct resource *res;
+	int ret;

 	exynos_rng = devm_kzalloc(&pdev->dev, sizeof(struct exynos_rng),
 					GFP_KERNEL);
@@ -132,7 +133,13 @@ static int exynos_rng_probe(struct platform_device *pdev)
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);

-	return hwrng_register(&exynos_rng->rng);
+	ret = hwrng_register(&exynos_rng->rng);
+	if (ret) {
+		pm_runtime_dont_use_autosuspend(&pdev->dev);
+		pm_runtime_disable(&pdev->dev);
+	}
+
+	return ret;
 }

 static int exynos_rng_remove(struct platform_device *pdev)
@@ -127,7 +127,12 @@ static int omap_rng_probe(struct platform_device *pdev)
 	dev_set_drvdata(&pdev->dev, priv);

 	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to runtime_get device: %d\n", ret);
+		pm_runtime_put_noidle(&pdev->dev);
+		goto err_ioremap;
+	}

 	ret = hwrng_register(&omap_rng_ops);
 	if (ret)
@@ -182,8 +187,15 @@ static int omap_rng_suspend(struct device *dev)
 static int omap_rng_resume(struct device *dev)
 {
 	struct omap_rng_private_data *priv = dev_get_drvdata(dev);
+	int ret;
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "Failed to runtime_get device: %d\n", ret);
+		pm_runtime_put_noidle(dev);
+		return ret;
+	}

-	pm_runtime_get_sync(dev);
 	omap_rng_write_reg(priv, RNG_MASK_REG, 0x1);

 	return 0;
@@ -69,12 +69,8 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 	u64 cursor = from;

 	while (cursor < to) {
-		if (!devmem_is_allowed(pfn)) {
-			printk(KERN_INFO
-		"Program %s tried to access /dev/mem between %Lx->%Lx.\n",
-				current->comm, from, to);
+		if (!devmem_is_allowed(pfn))
 			return 0;
-		}
 		cursor += PAGE_SIZE;
 		pfn++;
 	}
@@ -472,7 +472,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 						devfreq->profile->max_state *
 						devfreq->profile->max_state,
 						GFP_KERNEL);
-	devfreq->time_in_state = devm_kzalloc(dev, sizeof(unsigned int) *
+	devfreq->time_in_state = devm_kzalloc(dev, sizeof(unsigned long) *
 						devfreq->profile->max_state,
 						GFP_KERNEL);
 	devfreq->last_stat_updated = jiffies;
@@ -968,7 +968,7 @@ static void edac_inc_ue_error(struct mem_ctl_info *mci,
 	mci->ue_mc += count;

 	if (!enable_per_layer_report) {
-		mci->ce_noinfo_count += count;
+		mci->ue_noinfo_count += count;
 		return;
 	}

@@ -73,13 +73,13 @@ struct rfc2734_header {

 #define fwnet_get_hdr_lf(h)		(((h)->w0 & 0xc0000000) >> 30)
 #define fwnet_get_hdr_ether_type(h)	(((h)->w0 & 0x0000ffff))
-#define fwnet_get_hdr_dg_size(h)	(((h)->w0 & 0x0fff0000) >> 16)
+#define fwnet_get_hdr_dg_size(h)	((((h)->w0 & 0x0fff0000) >> 16) + 1)
 #define fwnet_get_hdr_fg_off(h)		(((h)->w0 & 0x00000fff))
 #define fwnet_get_hdr_dgl(h)		(((h)->w1 & 0xffff0000) >> 16)

-#define fwnet_set_hdr_lf(lf)		((lf)  << 30)
+#define fwnet_set_hdr_lf(lf)		((lf) << 30)
 #define fwnet_set_hdr_ether_type(et)	(et)
-#define fwnet_set_hdr_dg_size(dgs)	((dgs) << 16)
+#define fwnet_set_hdr_dg_size(dgs)	(((dgs) - 1) << 16)
 #define fwnet_set_hdr_fg_off(fgo)	(fgo)

 #define fwnet_set_hdr_dgl(dgl)		((dgl) << 16)
@@ -591,6 +591,9 @@ static int fwnet_incoming_packet(struct fwnet_device *dev, __be32 *buf, int len,
 	int retval;
 	u16 ether_type;

+	if (len <= RFC2374_UNFRAG_HDR_SIZE)
+		return 0;
+
 	hdr.w0 = be32_to_cpu(buf[0]);
 	lf = fwnet_get_hdr_lf(&hdr);
 	if (lf == RFC2374_HDR_UNFRAG) {
@@ -615,7 +618,12 @@ static int fwnet_incoming_packet(struct fwnet_device *dev, __be32 *buf, int len,
 		return fwnet_finish_incoming_packet(net, skb, source_node_id,
 						    is_broadcast, ether_type);
 	}
+
 	/* A datagram fragment has been received, now the fun begins. */
+
+	if (len <= RFC2374_FRAG_HDR_SIZE)
+		return 0;
+
 	hdr.w1 = ntohl(buf[1]);
 	buf += 2;
 	len -= RFC2374_FRAG_HDR_SIZE;
@@ -627,7 +635,10 @@ static int fwnet_incoming_packet(struct fwnet_device *dev, __be32 *buf, int len,
 		fg_off = fwnet_get_hdr_fg_off(&hdr);
 	}
 	datagram_label = fwnet_get_hdr_dgl(&hdr);
-	dg_size = fwnet_get_hdr_dg_size(&hdr); /* ??? + 1 */
+	dg_size = fwnet_get_hdr_dg_size(&hdr);
+
+	if (fg_off + len > dg_size)
+		return 0;

 	spin_lock_irqsave(&dev->lock, flags);

@@ -735,6 +746,22 @@ static void fwnet_receive_packet(struct fw_card *card, struct fw_request *r,
 	fw_send_response(card, r, rcode);
 }

+static int gasp_source_id(__be32 *p)
+{
+	return be32_to_cpu(p[0]) >> 16;
+}
+
+static u32 gasp_specifier_id(__be32 *p)
+{
+	return (be32_to_cpu(p[0]) & 0xffff) << 8 |
+	       (be32_to_cpu(p[1]) & 0xff000000) >> 24;
+}
+
+static u32 gasp_version(__be32 *p)
+{
+	return be32_to_cpu(p[1]) & 0xffffff;
+}
+
 static void fwnet_receive_broadcast(struct fw_iso_context *context,
 		u32 cycle, size_t header_length, void *header, void *data)
 {
@@ -744,9 +771,6 @@ static void fwnet_receive_broadcast(struct fw_iso_context *context,
 	__be32 *buf_ptr;
 	int retval;
 	u32 length;
-	u16 source_node_id;
-	u32 specifier_id;
-	u32 ver;
 	unsigned long offset;
 	unsigned long flags;

@@ -763,22 +787,17 @@ static void fwnet_receive_broadcast(struct fw_iso_context *context,

 	spin_unlock_irqrestore(&dev->lock, flags);

-	specifier_id =    (be32_to_cpu(buf_ptr[0]) & 0xffff) << 8
-			| (be32_to_cpu(buf_ptr[1]) & 0xff000000) >> 24;
-	ver = be32_to_cpu(buf_ptr[1]) & 0xffffff;
-	source_node_id = be32_to_cpu(buf_ptr[0]) >> 16;
-
-	if (specifier_id == IANA_SPECIFIER_ID &&
-	    (ver == RFC2734_SW_VERSION
+	if (length > IEEE1394_GASP_HDR_SIZE &&
+	    gasp_specifier_id(buf_ptr) == IANA_SPECIFIER_ID &&
+	    (gasp_version(buf_ptr) == RFC2734_SW_VERSION
 #if IS_ENABLED(CONFIG_IPV6)
-	     || ver == RFC3146_SW_VERSION
+	     || gasp_version(buf_ptr) == RFC3146_SW_VERSION
 #endif
-	    )) {
-		buf_ptr += 2;
-		length -= IEEE1394_GASP_HDR_SIZE;
-		fwnet_incoming_packet(dev, buf_ptr, length, source_node_id,
+	    ))
+		fwnet_incoming_packet(dev, buf_ptr + 2,
+				      length - IEEE1394_GASP_HDR_SIZE,
+				      gasp_source_id(buf_ptr),
 				      context->card->generation, true);
-	}

 	packet.payload_length = dev->rcv_buffer_size;
 	packet.interrupt = 1;
@@ -295,7 +295,7 @@ static int mpc8xxx_gpio_irq_map(struct irq_domain *h, unsigned int virq,
 		mpc8xxx_irq_chip.irq_set_type = mpc8xxx_gc->of_dev_id_data;

 	irq_set_chip_data(virq, h->host_data);
-	irq_set_chip_and_handler(virq, &mpc8xxx_irq_chip, handle_level_irq);
+	irq_set_chip_and_handler(virq, &mpc8xxx_irq_chip, handle_edge_irq);

 	return 0;
 }
@@ -3422,6 +3422,9 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 	int hdisplay, vdisplay;
 	int ret = -EINVAL;

+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
 	if (page_flip->flags & ~DRM_MODE_PAGE_FLIP_FLAGS ||
 	    page_flip->reserved != 0)
 		return -EINVAL;
@@ -114,6 +114,8 @@ static int qxl_palette_create_1bit(struct qxl_bo **palette_bo,
 				    palette_bo);

 	ret = qxl_bo_kmap(*palette_bo, (void **)&pal);
+	if (ret)
+		return ret;
 	pal->num_ents = 2;
 	pal->unique = unique++;
 	if (visual == FB_VISUAL_TRUECOLOR || visual == FB_VISUAL_DIRECTCOLOR) {
@@ -257,6 +257,8 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode)
 			atombios_enable_crtc_memreq(crtc, ATOM_ENABLE);
 		atombios_blank_crtc(crtc, ATOM_DISABLE);
 		drm_vblank_post_modeset(dev, radeon_crtc->crtc_id);
+		/* Make sure vblank interrupt is still enabled if needed */
+		radeon_irq_set(rdev);
 		radeon_crtc_load_lut(crtc);
 		break;
 	case DRM_MODE_DPMS_STANDBY:
@@ -331,6 +331,8 @@ static void radeon_crtc_dpms(struct drm_crtc *crtc, int mode)
 			WREG32_P(RADEON_CRTC_EXT_CNTL, crtc_ext_cntl, ~(mask | crtc_ext_cntl));
 		}
 		drm_vblank_post_modeset(dev, radeon_crtc->crtc_id);
+		/* Make sure vblank interrupt is still enabled if needed */
+		radeon_irq_set(rdev);
 		radeon_crtc_load_lut(crtc);
 		break;
 	case DRM_MODE_DPMS_STANDBY:
@@ -228,8 +228,8 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,

 	rdev = radeon_get_rdev(bo->bdev);
 	ridx = radeon_copy_ring_index(rdev);
-	old_start = old_mem->start << PAGE_SHIFT;
-	new_start = new_mem->start << PAGE_SHIFT;
+	old_start = (u64)old_mem->start << PAGE_SHIFT;
+	new_start = (u64)new_mem->start << PAGE_SHIFT;

 	switch (old_mem->mem_type) {
 	case TTM_PL_VRAM:
@@ -244,10 +244,14 @@ static void heartbeat_onchannelcallback(void *context)
 	struct heartbeat_msg_data *heartbeat_msg;
 	u8 *hbeat_txf_buf = util_heartbeat.recv_buffer;

-	vmbus_recvpacket(channel, hbeat_txf_buf,
-			 PAGE_SIZE, &recvlen, &requestid);
+	while (1) {
+
+		vmbus_recvpacket(channel, hbeat_txf_buf,
+				 PAGE_SIZE, &recvlen, &requestid);
+
+		if (!recvlen)
+			break;

-	if (recvlen > 0) {
 		icmsghdrp = (struct icmsg_hdr *)&hbeat_txf_buf[
 				sizeof(struct vmbuspipe_hdr)];

@@ -30,6 +30,7 @@

 #define ADT7411_REG_CFG1			0x18
 #define ADT7411_CFG1_START_MONITOR		(1 << 0)
+#define ADT7411_CFG1_RESERVED_BIT3		(1 << 3)

 #define ADT7411_REG_CFG2			0x19
 #define ADT7411_CFG2_DISABLE_AVG		(1 << 5)
@@ -292,8 +293,10 @@ static int adt7411_probe(struct i2c_client *client,
 	mutex_init(&data->device_lock);
 	mutex_init(&data->update_lock);

+	/* According to the datasheet, we must only write 1 to bit 3 */
 	ret = adt7411_modify_bit(client, ADT7411_REG_CFG1,
-				 ADT7411_CFG1_START_MONITOR, 1);
+				 ADT7411_CFG1_RESERVED_BIT3
+				 | ADT7411_CFG1_START_MONITOR, 1);
 	if (ret < 0)
 		return ret;

@@ -371,19 +371,57 @@ static irqreturn_t atmel_twi_interrupt(int irq, void *dev_id)

 	if (!irqstatus)
 		return IRQ_NONE;
-	else if (irqstatus & AT91_TWI_RXRDY)
-		at91_twi_read_next_byte(dev);
-	else if (irqstatus & AT91_TWI_TXRDY)
-		at91_twi_write_next_byte(dev);
-
-	/* catch error flags */
-	dev->transfer_status |= status;

+	/*
+	 * When a NACK condition is detected, the I2C controller sets the NACK,
+	 * TXCOMP and TXRDY bits all together in the Status Register (SR).
+	 *
+	 * 1 - Handling NACK errors with CPU write transfer.
+	 *
+	 * In such case, we should not write the next byte into the Transmit
+	 * Holding Register (THR) otherwise the I2C controller would start a new
+	 * transfer and the I2C slave is likely to reply by another NACK.
+	 *
+	 * 2 - Handling NACK errors with DMA write transfer.
+	 *
+	 * By setting the TXRDY bit in the SR, the I2C controller also triggers
+	 * the DMA controller to write the next data into the THR. Then the
+	 * result depends on the hardware version of the I2C controller.
+	 *
+	 * 2a - Without support of the Alternative Command mode.
+	 *
+	 * This is the worst case: the DMA controller is triggered to write the
+	 * next data into the THR, hence starting a new transfer: the I2C slave
+	 * is likely to reply by another NACK.
+	 * Concurrently, this interrupt handler is likely to be called to manage
+	 * the first NACK before the I2C controller detects the second NACK and
+	 * sets once again the NACK bit into the SR.
+	 * When handling the first NACK, this interrupt handler disables the I2C
+	 * controller interruptions, especially the NACK interrupt.
+	 * Hence, the NACK bit is pending into the SR. This is why we should
+	 * read the SR to clear all pending interrupts at the beginning of
+	 * at91_do_twi_transfer() before actually starting a new transfer.
+	 *
+	 * 2b - With support of the Alternative Command mode.
+	 *
+	 * When a NACK condition is detected, the I2C controller also locks the
+	 * THR (and sets the LOCK bit in the SR): even though the DMA controller
+	 * is triggered by the TXRDY bit to write the next data into the THR,
+	 * this data actually won't go on the I2C bus hence a second NACK is not
+	 * generated.
+	 */
 	if (irqstatus & (AT91_TWI_TXCOMP | AT91_TWI_NACK)) {
 		at91_disable_twi_interrupts(dev);
 		complete(&dev->cmd_complete);
+	} else if (irqstatus & AT91_TWI_RXRDY) {
+		at91_twi_read_next_byte(dev);
+	} else if (irqstatus & AT91_TWI_TXRDY) {
+		at91_twi_write_next_byte(dev);
 	}

+	/* catch error flags */
+	dev->transfer_status |= status;
+
 	return IRQ_HANDLED;
 }

@@ -391,6 +429,7 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev)
 {
 	int ret;
 	bool has_unre_flag = dev->pdata->has_unre_flag;
+	unsigned sr;

 	/*
 	 * WARNING: the TXCOMP bit in the Status Register is NOT a clear on
@@ -426,13 +465,16 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev)
 	INIT_COMPLETION(dev->cmd_complete);
 	dev->transfer_status = 0;

+	/* Clear pending interrupts, such as NACK. */
+	sr = at91_twi_read(dev, AT91_TWI_SR);
+
 	if (!dev->buf_len) {
 		at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_QUICK);
 		at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_TXCOMP);
 	} else if (dev->msg->flags & I2C_M_RD) {
 		unsigned start_flags = AT91_TWI_START;

-		if (at91_twi_read(dev, AT91_TWI_SR) & AT91_TWI_RXRDY) {
+		if (sr & AT91_TWI_RXRDY) {
 			dev_err(dev->dev, "RXRDY still set!");
 			at91_twi_read(dev, AT91_TWI_RHR);
 		}
@@ -798,13 +798,6 @@ static int pch_i2c_probe(struct pci_dev *pdev,
 	/* Set the number of I2C channel instance */
 	adap_info->ch_num = id->driver_data;

-	ret = request_irq(pdev->irq, pch_i2c_handler, IRQF_SHARED,
-		  KBUILD_MODNAME, adap_info);
-	if (ret) {
-		pch_pci_err(pdev, "request_irq FAILED\n");
-		goto err_request_irq;
-	}
-
 	for (i = 0; i < adap_info->ch_num; i++) {
 		pch_adap = &adap_info->pch_data[i].pch_adapter;
 		adap_info->pch_i2c_suspended = false;
@@ -821,6 +814,17 @@ static int pch_i2c_probe(struct pci_dev *pdev,
 		adap_info->pch_data[i].pch_base_address = base_addr + 0x100 * i;

 		pch_adap->dev.parent = &pdev->dev;
+	}
+
+	ret = request_irq(pdev->irq, pch_i2c_handler, IRQF_SHARED,
+		  KBUILD_MODNAME, adap_info);
+	if (ret) {
+		pch_pci_err(pdev, "request_irq FAILED\n");
+		goto err_request_irq;
+	}
+
+	for (i = 0; i < adap_info->ch_num; i++) {
+		pch_adap = &adap_info->pch_data[i].pch_adapter;

 		pch_i2c_init(&adap_info->pch_data[i]);

@@ -1323,6 +1323,7 @@ int i2c_register_driver(struct module *owner, struct i2c_driver *driver)
 	/* add the driver to the list of i2c drivers in the driver core */
 	driver->driver.owner = owner;
 	driver->driver.bus = &i2c_bus_type;
+	INIT_LIST_HEAD(&driver->clients);

 	/* When registration returns, the driver core
 	 * will have called probe() for all matching-but-unbound devices.
@@ -1341,7 +1342,6 @@ int i2c_register_driver(struct module *owner, struct i2c_driver *driver)

 	pr_debug("i2c-core: driver [%s] registered\n", driver->driver.name);

-	INIT_LIST_HEAD(&driver->clients);
 	/* Walk the adapters that are already present */
 	i2c_for_each_dev(driver, __process_new_driver);

@@ -160,11 +160,13 @@ static int kxsd9_read_raw(struct iio_dev *indio_dev,
 		if (ret < 0)
 			goto error_ret;
 		*val = ret;
+		ret = IIO_VAL_INT;
 		break;
 	case IIO_CHAN_INFO_SCALE:
 		ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C));
 		if (ret < 0)
 			goto error_ret;
+		*val = 0;
 		*val2 = kxsd9_micro_scales[ret & KXSD9_FS_MASK];
 		ret = IIO_VAL_INT_PLUS_MICRO;
 		break;
@@ -79,6 +79,8 @@ static struct ib_cm {
 	__be32 random_id_operand;
 	struct list_head timewait_list;
 	struct workqueue_struct *wq;
+	/* Sync on cm change port state */
+	spinlock_t state_lock;
 } cm;

 /* Counter indexes ordered by attribute ID */
@@ -160,6 +162,8 @@ struct cm_port {
 	struct ib_mad_agent *mad_agent;
 	struct kobject port_obj;
 	u8 port_num;
+	struct list_head cm_priv_prim_list;
+	struct list_head cm_priv_altr_list;
 	struct cm_counter_group counter_group[CM_COUNTER_GROUPS];
 };

@@ -237,6 +241,12 @@ struct cm_id_private {
 	u8 service_timeout;
 	u8 target_ack_delay;

+	struct list_head prim_list;
+	struct list_head altr_list;
+	/* Indicates that the send port mad is registered and av is set */
+	int prim_send_port_not_ready;
+	int altr_send_port_not_ready;
+
 	struct list_head work_list;
 	atomic_t work_count;
 };
@@ -255,19 +265,46 @@ static int cm_alloc_msg(struct cm_id_private *cm_id_priv,
 	struct ib_mad_agent *mad_agent;
 	struct ib_mad_send_buf *m;
 	struct ib_ah *ah;
+	struct cm_av *av;
+	unsigned long flags, flags2;
+	int ret = 0;

+	/* don't let the port to be released till the agent is down */
+	spin_lock_irqsave(&cm.state_lock, flags2);
+	spin_lock_irqsave(&cm.lock, flags);
+	if (!cm_id_priv->prim_send_port_not_ready)
+		av = &cm_id_priv->av;
+	else if (!cm_id_priv->altr_send_port_not_ready &&
+		 (cm_id_priv->alt_av.port))
+		av = &cm_id_priv->alt_av;
+	else {
+		pr_info("%s: not valid CM id\n", __func__);
+		ret = -ENODEV;
+		spin_unlock_irqrestore(&cm.lock, flags);
+		goto out;
+	}
+	spin_unlock_irqrestore(&cm.lock, flags);
+	/* Make sure the port haven't released the mad yet */
 	mad_agent = cm_id_priv->av.port->mad_agent;
-	ah = ib_create_ah(mad_agent->qp->pd, &cm_id_priv->av.ah_attr);
-	if (IS_ERR(ah))
-		return PTR_ERR(ah);
+	if (!mad_agent) {
+		pr_info("%s: not a valid MAD agent\n", __func__);
+		ret = -ENODEV;
+		goto out;
+	}
+	ah = ib_create_ah(mad_agent->qp->pd, &av->ah_attr);
+	if (IS_ERR(ah)) {
+		ret = PTR_ERR(ah);
+		goto out;
+	}

 	m = ib_create_send_mad(mad_agent, cm_id_priv->id.remote_cm_qpn,
-			       cm_id_priv->av.pkey_index,
+			       av->pkey_index,
 			       0, IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
 			       GFP_ATOMIC);
 	if (IS_ERR(m)) {
 		ib_destroy_ah(ah);
-		return PTR_ERR(m);
+		ret = PTR_ERR(m);
+		goto out;
 	}

 	/* Timeout set by caller if response is expected. */
@@ -277,7 +314,10 @@ static int cm_alloc_msg(struct cm_id_private *cm_id_priv,
 	atomic_inc(&cm_id_priv->refcount);
 	m->context[0] = cm_id_priv;
 	*msg = m;
-	return 0;
+
+out:
+	spin_unlock_irqrestore(&cm.state_lock, flags2);
+	return ret;
 }

 static int cm_alloc_response_msg(struct cm_port *port,
@@ -346,7 +386,8 @@ static void cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc,
 			   grh, &av->ah_attr);
 }

-static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)
+static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av,
+			      struct cm_id_private *cm_id_priv)
 {
 	struct cm_device *cm_dev;
 	struct cm_port *port = NULL;
@@ -376,7 +417,18 @@ static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)
 	ib_init_ah_from_path(cm_dev->ib_device, port->port_num, path,
 			     &av->ah_attr);
 	av->timeout = path->packet_life_time + 1;
-	return 0;
+
+	spin_lock_irqsave(&cm.lock, flags);
+	if (&cm_id_priv->av == av)
+		list_add_tail(&cm_id_priv->prim_list, &port->cm_priv_prim_list);
+	else if (&cm_id_priv->alt_av == av)
+		list_add_tail(&cm_id_priv->altr_list, &port->cm_priv_altr_list);
+	else
+		ret = -EINVAL;
+
+	spin_unlock_irqrestore(&cm.lock, flags);
+
+	return ret;
 }

 static int cm_alloc_id(struct cm_id_private *cm_id_priv)
@@ -716,6 +768,8 @@ struct ib_cm_id *ib_create_cm_id(struct ib_device *device,
 	spin_lock_init(&cm_id_priv->lock);
 	init_completion(&cm_id_priv->comp);
 	INIT_LIST_HEAD(&cm_id_priv->work_list);
+	INIT_LIST_HEAD(&cm_id_priv->prim_list);
+	INIT_LIST_HEAD(&cm_id_priv->altr_list);
 	atomic_set(&cm_id_priv->work_count, -1);
 	atomic_set(&cm_id_priv->refcount, 1);
 	return &cm_id_priv->id;
@@ -914,6 +968,15 @@ retest:
 		break;
 	}

+	spin_lock_irq(&cm.lock);
+	if (!list_empty(&cm_id_priv->altr_list) &&
+	    (!cm_id_priv->altr_send_port_not_ready))
+		list_del(&cm_id_priv->altr_list);
+	if (!list_empty(&cm_id_priv->prim_list) &&
+	    (!cm_id_priv->prim_send_port_not_ready))
+		list_del(&cm_id_priv->prim_list);
+	spin_unlock_irq(&cm.lock);
+
 	cm_free_id(cm_id->local_id);
 	cm_deref_id(cm_id_priv);
 	wait_for_completion(&cm_id_priv->comp);
@@ -1137,12 +1200,13 @@ int ib_send_cm_req(struct ib_cm_id *cm_id,
 		goto out;
 	}

-	ret = cm_init_av_by_path(param->primary_path, &cm_id_priv->av);
+	ret = cm_init_av_by_path(param->primary_path, &cm_id_priv->av,
+				 cm_id_priv);
 	if (ret)
 		goto error1;
 	if (param->alternate_path) {
 		ret = cm_init_av_by_path(param->alternate_path,
-					 &cm_id_priv->alt_av);
+					 &cm_id_priv->alt_av, cm_id_priv);
 		if (ret)
 			goto error1;
 	}
@@ -1562,7 +1626,8 @@ static int cm_req_handler(struct cm_work *work)

 	cm_process_routed_req(req_msg, work->mad_recv_wc->wc);
 	cm_format_paths_from_req(req_msg, &work->path[0], &work->path[1]);
-	ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av);
+	ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av,
+				 cm_id_priv);
 	if (ret) {
 		ib_get_cached_gid(work->port->cm_dev->ib_device,
 				  work->port->port_num, 0, &work->path[0].sgid);
@@ -1572,7 +1637,8 @@ static int cm_req_handler(struct cm_work *work)
 		goto rejected;
 	}
 	if (req_msg->alt_local_lid) {
-		ret = cm_init_av_by_path(&work->path[1], &cm_id_priv->alt_av);
+		ret = cm_init_av_by_path(&work->path[1], &cm_id_priv->alt_av,
+					 cm_id_priv);
 		if (ret) {
 			ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_ALT_GID,
 				       &work->path[0].sgid,
@@ -2627,7 +2693,8 @@ int ib_send_cm_lap(struct ib_cm_id *cm_id,
 		goto out;
 	}

-	ret = cm_init_av_by_path(alternate_path, &cm_id_priv->alt_av);
+	ret = cm_init_av_by_path(alternate_path, &cm_id_priv->alt_av,
+				 cm_id_priv);
 	if (ret)
 		goto out;
 	cm_id_priv->alt_av.timeout =
@@ -2739,7 +2806,8 @@ static int cm_lap_handler(struct cm_work *work)
 	cm_init_av_for_response(work->port, work->mad_recv_wc->wc,
 				work->mad_recv_wc->recv_buf.grh,
 				&cm_id_priv->av);
-	cm_init_av_by_path(param->alternate_path, &cm_id_priv->alt_av);
+	cm_init_av_by_path(param->alternate_path, &cm_id_priv->alt_av,
+			   cm_id_priv);
 	ret = atomic_inc_and_test(&cm_id_priv->work_count);
 	if (!ret)
 		list_add_tail(&work->list, &cm_id_priv->work_list);
@@ -2931,7 +2999,7 @@ int ib_send_cm_sidr_req(struct ib_cm_id *cm_id,
 		return -EINVAL;

 	cm_id_priv = container_of(cm_id, struct cm_id_private, id);
-	ret = cm_init_av_by_path(param->path, &cm_id_priv->av);
+	ret = cm_init_av_by_path(param->path, &cm_id_priv->av, cm_id_priv);
 	if (ret)
 		goto out;

@@ -3352,7 +3420,9 @@ out:
 static int cm_migrate(struct ib_cm_id *cm_id)
 {
 	struct cm_id_private *cm_id_priv;
+	struct cm_av tmp_av;
 	unsigned long flags;
+	int tmp_send_port_not_ready;
 	int ret = 0;

 	cm_id_priv = container_of(cm_id, struct cm_id_private, id);
@@ -3361,7 +3431,14 @@ static int cm_migrate(struct ib_cm_id *cm_id)
 	    (cm_id->lap_state == IB_CM_LAP_UNINIT ||
 	     cm_id->lap_state == IB_CM_LAP_IDLE)) {
 		cm_id->lap_state = IB_CM_LAP_IDLE;
+		/* Swap address vector */
+		tmp_av = cm_id_priv->av;
 		cm_id_priv->av = cm_id_priv->alt_av;
+		cm_id_priv->alt_av = tmp_av;
+		/* Swap port send ready state */
+		tmp_send_port_not_ready = cm_id_priv->prim_send_port_not_ready;
+		cm_id_priv->prim_send_port_not_ready = cm_id_priv->altr_send_port_not_ready;
+		cm_id_priv->altr_send_port_not_ready = tmp_send_port_not_ready;
 	} else
 		ret = -EINVAL;
 	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
@@ -3767,6 +3844,9 @@ static void cm_add_one(struct ib_device *ib_device)
 		port->cm_dev = cm_dev;
 		port->port_num = i;

+		INIT_LIST_HEAD(&port->cm_priv_prim_list);
+		INIT_LIST_HEAD(&port->cm_priv_altr_list);
+
 		ret = cm_create_port_fs(port);
 		if (ret)
 			goto error1;
@@ -3813,6 +3893,8 @@ static void cm_remove_one(struct ib_device *ib_device)
 {
 	struct cm_device *cm_dev;
 	struct cm_port *port;
+	struct cm_id_private *cm_id_priv;
+	struct ib_mad_agent *cur_mad_agent;
 	struct ib_port_modify port_modify = {
 		.clr_port_cap_mask = IB_PORT_CM_SUP
 	};
@@ -3830,10 +3912,22 @@ static void cm_remove_one(struct ib_device *ib_device)
 	for (i = 1; i <= ib_device->phys_port_cnt; i++) {
 		port = cm_dev->port[i-1];
 		ib_modify_port(ib_device, port->port_num, 0, &port_modify);
-		ib_unregister_mad_agent(port->mad_agent);
+		/* Mark all the cm_id's as not valid */
+		spin_lock_irq(&cm.lock);
+		list_for_each_entry(cm_id_priv, &port->cm_priv_altr_list, altr_list)
+			cm_id_priv->altr_send_port_not_ready = 1;
+		list_for_each_entry(cm_id_priv, &port->cm_priv_prim_list, prim_list)
+			cm_id_priv->prim_send_port_not_ready = 1;
+		spin_unlock_irq(&cm.lock);
 		flush_workqueue(cm.wq);
+		spin_lock_irq(&cm.state_lock);
+		cur_mad_agent = port->mad_agent;
+		port->mad_agent = NULL;
+		spin_unlock_irq(&cm.state_lock);
+		ib_unregister_mad_agent(cur_mad_agent);
 		cm_remove_port_fs(port);
 	}
+
 	device_unregister(cm_dev->device);
 	kfree(cm_dev);
 }
@@ -3846,6 +3940,7 @@ static int __init ib_cm_init(void)
 	INIT_LIST_HEAD(&cm.device_list);
 	rwlock_init(&cm.device_lock);
 	spin_lock_init(&cm.lock);
+	spin_lock_init(&cm.state_lock);
 	cm.listen_service_table = RB_ROOT;
 	cm.listen_service_id = be64_to_cpu(IB_CM_ASSIGN_SERVICE_ID);
 	cm.remote_id_table = RB_ROOT;
@@ -106,7 +106,6 @@ struct mcast_group {
 	atomic_t		refcount;
 	enum mcast_group_state	state;
 	struct ib_sa_query	*query;
-	int			query_id;
 	u16			pkey_index;
 	u8			leave_state;
 	int			retries;
@@ -339,11 +338,7 @@ static int send_join(struct mcast_group *group, struct mcast_member *member)
 				       member->multicast.comp_mask,
 				       3000, GFP_KERNEL, join_handler, group,
 				       &group->query);
-	if (ret >= 0) {
-		group->query_id = ret;
-		ret = 0;
-	}
-	return ret;
+	return (ret > 0) ? 0 : ret;
 }

 static int send_leave(struct mcast_group *group, u8 leave_state)
@@ -363,11 +358,7 @@ static int send_leave(struct mcast_group *group, u8 leave_state)
 				       IB_SA_MCMEMBER_REC_JOIN_STATE,
 				       3000, GFP_KERNEL, leave_handler,
 				       group, &group->query);
-	if (ret >= 0) {
-		group->query_id = ret;
-		ret = 0;
-	}
-	return ret;
+	return (ret > 0) ? 0 : ret;
 }

 static void join_group(struct mcast_group *group, struct mcast_member *member,
@@ -224,12 +224,9 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file,
 			container_of(uobj, struct ib_uqp_object, uevent.uobject);

 		idr_remove_uobj(&ib_uverbs_qp_idr, uobj);
-		if (qp != qp->real_qp) {
-			ib_close_qp(qp);
-		} else {
+		if (qp == qp->real_qp)
 			ib_uverbs_detach_umcast(qp, uqp);
-			ib_destroy_qp(qp);
-		}
+		ib_destroy_qp(qp);
 		ib_uverbs_release_uevent(file, &uqp->uevent);
 		kfree(uqp);
 	}
@@ -239,11 +239,14 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 	if (context)
 		if (ib_copy_to_udata(udata, &cq->mcq.cqn, sizeof (__u32))) {
 			err = -EFAULT;
-			goto err_dbmap;
+			goto err_cq_free;
 		}

 	return &cq->ibcq;

+err_cq_free:
+	mlx4_cq_free(dev->dev, &cq->mcq);
+
 err_dbmap:
 	if (context)
 		mlx4_ib_db_unmap_user(to_mucontext(context), &cq->db);
--- a/Show More
+++ b/Show More