108 files changed, 1150 insertions, 560 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 358eb0105e00..88c09ca2584f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1186,7 +1186,7 @@ M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
 L:      linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:      Maintained
 F:      arch/arm/mach-mvebu/
-F:      drivers/rtc/armada38x-rtc
+F:      drivers/rtc/rtc-armada38x.c
 
 ARM/Marvell Berlin SoC support
 M:      Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
@@ -1675,8 +1675,8 @@ F:	drivers/misc/eeprom/at24.c
 F:      include/linux/platform_data/at24.h
 
 ATA OVER ETHERNET (AOE) DRIVER
-M:      "Ed L. Cashin" <ecashin@coraid.com>
-W:      http://support.coraid.com/support/linux
+M:      "Ed L. Cashin" <ed.cashin@acm.org>
+W:      http://www.openaoe.org/
 S:      Supported
 F:      Documentation/aoe/
 F:      drivers/block/aoe/
@@ -3252,6 +3252,13 @@ S:	Maintained
 F:      Documentation/hwmon/dme1737
 F:      drivers/hwmon/dme1737.c
 
+DMI/SMBIOS SUPPORT
+M:      Jean Delvare <jdelvare@suse.de>
+S:      Maintained
+F:      drivers/firmware/dmi-id.c
+F:      drivers/firmware/dmi_scan.c
+F:      include/linux/dmi.h
+
 DOCKING STATION DRIVER
 M:      Shaohua Li <shaohua.li@intel.com>
 L:      linux-acpi@vger.kernel.org
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 114234e83caa..edda76fae83f 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -67,7 +67,7 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs,
                sigset_t *set)
 {
         int err;
-        err = __copy_to_user(&(sf->uc.uc_mcontext.regs), regs,
+        err = __copy_to_user(&(sf->uc.uc_mcontext.regs.scratch), regs,
                              sizeof(sf->uc.uc_mcontext.regs.scratch));
         err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t));
 
@@ -83,7 +83,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
         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));
 
         return err;
@@ -131,6 +131,15 @@ SYSCALL_DEFINE0(rt_sigreturn)
         /* Don't restart from sigreturn */
         syscall_wont_restart(regs);
 
+        /*
+         * Ensure that sigreturn always returns to user mode (in case the
+         * regs saved on user stack got fudged between save and sigreturn)
+         * Otherwise it is easy to panic the kernel with a custom
+         * signal handler and/or restorer which clobberes the status32/ret
+         * to return to a bogus location in kernel mode.
+         */
+        regs->status32 |= STATUS_U_MASK;
+
         return regs->r0;
 
 badframe:
@@ -229,8 +238,11 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs)
 
         /*
          * handler returns using sigreturn stub provided already by userpsace
+         * If not, nuke the process right away
          */
-        BUG_ON(!(ksig->ka.sa.sa_flags & SA_RESTORER));
+        if(!(ksig->ka.sa.sa_flags & SA_RESTORER))
+                return 1;
+
         regs->blink = (unsigned long)ksig->ka.sa.sa_restorer;
 
         /* User Stack for signal handler will be above the frame just carved */
@@ -296,12 +308,12 @@ static void
 handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
         sigset_t *oldset = sigmask_to_save();
-        int ret;
+        int failed;
 
         /* Set up the stack frame */
-        ret = setup_rt_frame(ksig, oldset, regs);
+        failed = setup_rt_frame(ksig, oldset, regs);
 
-        signal_setup_done(ret, ksig, 0);
+        signal_setup_done(failed, ksig, 0);
 }
 
 void do_signal(struct pt_regs *regs)
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index cb9593079f29..d8c25b7b18fb 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -246,14 +246,30 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
         __ret; \
 })
 
-#define this_cpu_cmpxchg_1(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
-#define this_cpu_cmpxchg_2(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
-#define this_cpu_cmpxchg_4(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
-#define this_cpu_cmpxchg_8(ptr, o, n) cmpxchg_local(raw_cpu_ptr(&(ptr)), o, n)
-
-#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \
-        cmpxchg_double_local(raw_cpu_ptr(&(ptr1)), raw_cpu_ptr(&(ptr2)), \
-                                o1, o2, n1, n2)
+#define _protect_cmpxchg_local(pcp, o, n)                       \
+({                                                              \
+        typeof(*raw_cpu_ptr(&(pcp))) __ret;                     \
+        preempt_disable();                                      \
+        __ret = cmpxchg_local(raw_cpu_ptr(&(pcp)), o, n);       \
+        preempt_enable();                                       \
+        __ret;                                                  \
+})
+
+#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+#define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n)
+
+#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2)           \
+({                                                                      \
+        int __ret;                                                      \
+        preempt_disable();                                              \
+        __ret = cmpxchg_double_local(   raw_cpu_ptr(&(ptr1)),           \
+                                        raw_cpu_ptr(&(ptr2)),           \
+                                        o1, o2, n1, n2);                \
+        preempt_enable();                                               \
+        __ret;                                                          \
+})
 
 #define cmpxchg64(ptr,o,n)              cmpxchg((ptr),(o),(n))
 #define cmpxchg64_local(ptr,o,n)        cmpxchg_local((ptr),(o),(n))
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index a9eee33dfa62..101a42bde728 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -151,6 +151,15 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
         unsigned int cpu = smp_processor_id();
 
+        /*
+         * init_mm.pgd does not contain any user mappings and it is always
+         * active for kernel addresses in TTBR1. Just set the reserved TTBR0.
+         */
+        if (next == &init_mm) {
+                cpu_set_reserved_ttbr0();
+                return;
+        }
+
         if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
                 check_and_switch_context(next, tsk);
 }
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 09da25bc596f..4fde8c1df97f 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -204,25 +204,47 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
         return ret;
 }
 
+#define _percpu_read(pcp)                                               \
+({                                                                      \
+        typeof(pcp) __retval;                                           \
+        preempt_disable();                                              \
+        __retval = (typeof(pcp))__percpu_read(raw_cpu_ptr(&(pcp)),      \
+                                              sizeof(pcp));             \
+        preempt_enable();                                               \
+        __retval;                                                       \
+})
+
+#define _percpu_write(pcp, val)                                         \
+do {                                                                    \
+        preempt_disable();                                              \
+        __percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val),       \
+                                sizeof(pcp));                           \
+        preempt_enable();                                               \
+} while(0)                                                              \
+
+#define _pcp_protect(operation, pcp, val)                       \
+({                                                              \
+        typeof(pcp) __retval;                                   \
+        preempt_disable();                                      \
+        __retval = (typeof(pcp))operation(raw_cpu_ptr(&(pcp)),  \
+                                          (val), sizeof(pcp));  \
+        preempt_enable();                                       \
+        __retval;                                               \
+})
+
 #define _percpu_add(pcp, val) \
-        __percpu_add(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+        _pcp_protect(__percpu_add, pcp, val)
 
-#define _percpu_add_return(pcp, val) (typeof(pcp)) (_percpu_add(pcp, val))
+#define _percpu_add_return(pcp, val) _percpu_add(pcp, val)
 
 #define _percpu_and(pcp, val) \
-        __percpu_and(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
+        _pcp_protect(__percpu_and, pcp, val)
 
 #define _percpu_or(pcp, val) \
-        __percpu_or(raw_cpu_ptr(&(pcp)), val, sizeof(pcp))
-
-#define _percpu_read(pcp) (typeof(pcp)) \
-        (__percpu_read(raw_cpu_ptr(&(pcp)), sizeof(pcp)))
-
-#define _percpu_write(pcp, val) \
-        __percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp))
+        _pcp_protect(__percpu_or, pcp, val)
 
 #define _percpu_xchg(pcp, val) (typeof(pcp)) \
-        (__percpu_xchg(raw_cpu_ptr(&(pcp)), (unsigned long)(val), sizeof(pcp)))
+        _pcp_protect(__percpu_xchg, pcp, (unsigned long)(val))
 
 #define this_cpu_add_1(pcp, val) _percpu_add(pcp, val)
 #define this_cpu_add_2(pcp, val) _percpu_add(pcp, val)
diff --git a/arch/metag/include/asm/io.h b/arch/metag/include/asm/io.h
index 9359e5048442..d5779b0ec573 100644
--- a/arch/metag/include/asm/io.h
+++ b/arch/metag/include/asm/io.h
@@ -2,6 +2,7 @@
 #define _ASM_METAG_IO_H
 
 #include <linux/types.h>
+#include <asm/pgtable-bits.h>
 
 #define IO_SPACE_LIMIT  0
 
diff --git a/arch/metag/include/asm/pgtable-bits.h b/arch/metag/include/asm/pgtable-bits.h
new file mode 100644
index 000000000000..25ba6729f496
--- /dev/null
+++ b/arch/metag/include/asm/pgtable-bits.h
@@ -0,0 +1,104 @@
+/*
+ * Meta page table definitions.
+ */
+
+#ifndef _METAG_PGTABLE_BITS_H
+#define _METAG_PGTABLE_BITS_H
+
+#include <asm/metag_mem.h>
+
+/*
+ * Definitions for MMU descriptors
+ *
+ * These are the hardware bits in the MMCU pte entries.
+ * Derived from the Meta toolkit headers.
+ */
+#define _PAGE_PRESENT           MMCU_ENTRY_VAL_BIT
+#define _PAGE_WRITE             MMCU_ENTRY_WR_BIT
+#define _PAGE_PRIV              MMCU_ENTRY_PRIV_BIT
+/* Write combine bit - this can cause writes to occur out of order */
+#define _PAGE_WR_COMBINE        MMCU_ENTRY_WRC_BIT
+/* Sys coherent bit - this bit is never used by Linux */
+#define _PAGE_SYS_COHERENT      MMCU_ENTRY_SYS_BIT
+#define _PAGE_ALWAYS_ZERO_1     0x020
+#define _PAGE_CACHE_CTRL0       0x040
+#define _PAGE_CACHE_CTRL1       0x080
+#define _PAGE_ALWAYS_ZERO_2     0x100
+#define _PAGE_ALWAYS_ZERO_3     0x200
+#define _PAGE_ALWAYS_ZERO_4     0x400
+#define _PAGE_ALWAYS_ZERO_5     0x800
+
+/* These are software bits that we stuff into the gaps in the hardware
+ * pte entries that are not used.  Note, these DO get stored in the actual
+ * hardware, but the hardware just does not use them.
+ */
+#define _PAGE_ACCESSED          _PAGE_ALWAYS_ZERO_1
+#define _PAGE_DIRTY             _PAGE_ALWAYS_ZERO_2
+
+/* Pages owned, and protected by, the kernel. */
+#define _PAGE_KERNEL            _PAGE_PRIV
+
+/* No cacheing of this page */
+#define _PAGE_CACHE_WIN0        (MMCU_CWIN_UNCACHED << MMCU_ENTRY_CWIN_S)
+/* burst cacheing - good for data streaming */
+#define _PAGE_CACHE_WIN1        (MMCU_CWIN_BURST << MMCU_ENTRY_CWIN_S)
+/* One cache way per thread */
+#define _PAGE_CACHE_WIN2        (MMCU_CWIN_C1SET << MMCU_ENTRY_CWIN_S)
+/* Full on cacheing */
+#define _PAGE_CACHE_WIN3        (MMCU_CWIN_CACHED << MMCU_ENTRY_CWIN_S)
+
+#define _PAGE_CACHEABLE         (_PAGE_CACHE_WIN3 | _PAGE_WR_COMBINE)
+
+/* which bits are used for cache control ... */
+#define _PAGE_CACHE_MASK        (_PAGE_CACHE_CTRL0 | _PAGE_CACHE_CTRL1 | \
+                                 _PAGE_WR_COMBINE)
+
+/* This is a mask of the bits that pte_modify is allowed to change. */
+#define _PAGE_CHG_MASK          (PAGE_MASK)
+
+#define _PAGE_SZ_SHIFT          1
+#define _PAGE_SZ_4K             (0x0)
+#define _PAGE_SZ_8K             (0x1 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_16K            (0x2 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_32K            (0x3 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_64K            (0x4 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_128K           (0x5 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_256K           (0x6 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_512K           (0x7 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_1M             (0x8 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_2M             (0x9 << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_4M             (0xa << _PAGE_SZ_SHIFT)
+#define _PAGE_SZ_MASK           (0xf << _PAGE_SZ_SHIFT)
+
+#if defined(CONFIG_PAGE_SIZE_4K)
+#define _PAGE_SZ                (_PAGE_SZ_4K)
+#elif defined(CONFIG_PAGE_SIZE_8K)
+#define _PAGE_SZ                (_PAGE_SZ_8K)
+#elif defined(CONFIG_PAGE_SIZE_16K)
+#define _PAGE_SZ                (_PAGE_SZ_16K)
+#endif
+#define _PAGE_TABLE             (_PAGE_SZ | _PAGE_PRESENT)
+
+#if defined(CONFIG_HUGETLB_PAGE_SIZE_8K)
+# define _PAGE_SZHUGE           (_PAGE_SZ_8K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_16K)
+# define _PAGE_SZHUGE           (_PAGE_SZ_16K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_32K)
+# define _PAGE_SZHUGE           (_PAGE_SZ_32K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_64K)
+# define _PAGE_SZHUGE           (_PAGE_SZ_64K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_128K)
+# define _PAGE_SZHUGE           (_PAGE_SZ_128K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K)
+# define _PAGE_SZHUGE           (_PAGE_SZ_256K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512K)
+# define _PAGE_SZHUGE           (_PAGE_SZ_512K)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_1M)
+# define _PAGE_SZHUGE           (_PAGE_SZ_1M)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_2M)
+# define _PAGE_SZHUGE           (_PAGE_SZ_2M)
+#elif defined(CONFIG_HUGETLB_PAGE_SIZE_4M)
+# define _PAGE_SZHUGE           (_PAGE_SZ_4M)
+#endif
+
+#endif /* _METAG_PGTABLE_BITS_H */
diff --git a/arch/metag/include/asm/pgtable.h b/arch/metag/include/asm/pgtable.h
index d0604c0a8702..ffa3a3a2ecad 100644
--- a/arch/metag/include/asm/pgtable.h
+++ b/arch/metag/include/asm/pgtable.h
@@ -5,6 +5,7 @@
 #ifndef _METAG_PGTABLE_H
 #define _METAG_PGTABLE_H
 
+#include <asm/pgtable-bits.h>
 #include <asm-generic/pgtable-nopmd.h>
 
 /* Invalid regions on Meta: 0x00000000-0x001FFFFF and 0xFFFF0000-0xFFFFFFFF */
@@ -21,100 +22,6 @@
 #endif
 
 /*
- * Definitions for MMU descriptors
- *
- * These are the hardware bits in the MMCU pte entries.
- * Derived from the Meta toolkit headers.
- */
-#define _PAGE_PRESENT           MMCU_ENTRY_VAL_BIT
-#define _PAGE_WRITE             MMCU_ENTRY_WR_BIT
-#define _PAGE_PRIV              MMCU_ENTRY_PRIV_BIT
-/* Write combine bit - this can cause writes to occur out of order */
-#define _PAGE_WR_COMBINE        MMCU_ENTRY_WRC_BIT
-/* Sys coherent bit - this bit is never used by Linux */
-#define _PAGE_SYS_COHERENT      MMCU_ENTRY_SYS_BIT
-#define _PAGE_ALWAYS_ZERO_1     0x020
-#define _PAGE_CACHE_CTRL0       0x040
-#define _PAGE_CACHE_CTRL1       0x080
-#define _PAGE_ALWAYS_ZERO_2     0x100
-#define _PAGE_ALWAYS_ZERO_3     0x200
-#define _PAGE_ALWAYS_ZERO_4     0x400
-#define _PAGE_ALWAYS_ZERO_5     0x800
-
-/* These are software bits that we stuff into the gaps in the hardware
- * pte entries that are not used.  Note, these DO get stored in the actual
- * hardware, but the hardware just does not use them.
- */
-#define _PAGE_ACCESSED          _PAGE_ALWAYS_ZERO_1
-#define _PAGE_DIRTY             _PAGE_ALWAYS_ZERO_2
-
-/* Pages owned, and protected by, the kernel. */
-#define _PAGE_KERNEL            _PAGE_PRIV
-
-/* No cacheing of this page */
-#define _PAGE_CACHE_WIN0        (MMCU_CWIN_UNCACHED << MMCU_ENTRY_CWIN_S)
-/* burst cacheing - good for data streaming */
-#define _PAGE_CACHE_WIN1        (MMCU_CWIN_BURST << MMCU_ENTRY_CWIN_S)
-/* One cache way per thread */
-#define _PAGE_CACHE_WIN2        (MMCU_CWIN_C1SET << MMCU_ENTRY_CWIN_S)
-/* Full on cacheing */
-#define _PAGE_CACHE_WIN3        (MMCU_CWIN_CACHED << MMCU_ENTRY_CWIN_S)
-
-#define _PAGE_CACHEABLE         (_PAGE_CACHE_WIN3 | _PAGE_WR_COMBINE)
-
-/* which bits are used for cache control ... */
-#define _PAGE_CACHE_MASK        (_PAGE_CACHE_CTRL0 | _PAGE_CACHE_CTRL1 | \
-                                 _PAGE_WR_COMBINE)
-
-/* This is a mask of the bits that pte_modify is allowed to change. */
-#define _PAGE_CHG_MASK          (PAGE_MASK)
-
-#define _PAGE_SZ_SHIFT          1
-#define _PAGE_SZ_4K             (0x0)
-#define _PAGE_SZ_8K             (0x1 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_16K            (0x2 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_32K            (0x3 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_64K            (0x4 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_128K           (0x5 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_256K           (0x6 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_512K           (0x7 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_1M             (0x8 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_2M             (0x9 << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_4M             (0xa << _PAGE_SZ_SHIFT)
-#define _PAGE_SZ_MASK           (0xf << _PAGE_SZ_SHIFT)
-
-#if defined(CONFIG_PAGE_SIZE_4K)
-#define _PAGE_SZ                (_PAGE_SZ_4K)
-#elif defined(CONFIG_PAGE_SIZE_8K)
-#define _PAGE_SZ                (_PAGE_SZ_8K)
-#elif defined(CONFIG_PAGE_SIZE_16K)
-#define _PAGE_SZ                (_PAGE_SZ_16K)
-#endif
-#define _PAGE_TABLE             (_PAGE_SZ | _PAGE_PRESENT)
-
-#if defined(CONFIG_HUGETLB_PAGE_SIZE_8K)
-# define _PAGE_SZHUGE           (_PAGE_SZ_8K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_16K)
-# define _PAGE_SZHUGE           (_PAGE_SZ_16K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_32K)
-# define _PAGE_SZHUGE           (_PAGE_SZ_32K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_64K)
-# define _PAGE_SZHUGE           (_PAGE_SZ_64K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_128K)
-# define _PAGE_SZHUGE           (_PAGE_SZ_128K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_256K)
-# define _PAGE_SZHUGE           (_PAGE_SZ_256K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512K)
-# define _PAGE_SZHUGE           (_PAGE_SZ_512K)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_1M)
-# define _PAGE_SZHUGE           (_PAGE_SZ_1M)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_2M)
-# define _PAGE_SZHUGE           (_PAGE_SZ_2M)
-#elif defined(CONFIG_HUGETLB_PAGE_SIZE_4M)
-# define _PAGE_SZHUGE           (_PAGE_SZ_4M)
-#endif
-
-/*
  * The Linux memory management assumes a three-level page table setup. On
  * Meta, we use that, but "fold" the mid level into the top-level page
  * table.
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index f213f5b4c423..d17437238a2c 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -26,7 +26,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
         if (likely(pgd != NULL)) {
                 memset(pgd, 0, PAGE_SIZE<<PGD_ALLOC_ORDER);
-#ifdef CONFIG_64BIT
+#if PT_NLEVELS == 3
                 actual_pgd += PTRS_PER_PGD;
                 /* Populate first pmd with allocated memory.  We mark it
                  * with PxD_FLAG_ATTACHED as a signal to the system that this
@@ -45,7 +45,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-#ifdef CONFIG_64BIT
+#if PT_NLEVELS == 3
         pgd -= PTRS_PER_PGD;
 #endif
         free_pages((unsigned long)pgd, PGD_ALLOC_ORDER);
@@ -72,12 +72,15 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-#ifdef CONFIG_64BIT
         if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
-                /* This is the permanent pmd attached to the pgd;
-                 * cannot free it */
+                /*
+                 * This is the permanent pmd attached to the pgd;
+                 * cannot free it.
+                 * Increment the counter to compensate for the decrement
+                 * done by generic mm code.
+                 */
+                mm_inc_nr_pmds(mm);
                 return;
-#endif
         free_pages((unsigned long)pmd, PMD_ORDER);
 }
 
@@ -99,7 +102,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 static inline void
 pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
 {
-#ifdef CONFIG_64BIT
+#if PT_NLEVELS == 3
         /* preserve the gateway marker if this is the beginning of
          * the permanent pmd */
         if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 5a8997d63899..8eefb12d1d33 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -55,8 +55,8 @@
 #define ENTRY_COMP(_name_) .word sys_##_name_
 #endif
 
-        ENTRY_SAME(restart_syscall)     /* 0 */
-        ENTRY_SAME(exit)
+90:     ENTRY_SAME(restart_syscall)     /* 0 */
+91:     ENTRY_SAME(exit)
         ENTRY_SAME(fork_wrapper)
         ENTRY_SAME(read)
         ENTRY_SAME(write)
@@ -439,7 +439,10 @@
         ENTRY_SAME(bpf)
         ENTRY_COMP(execveat)
 
-        /* Nothing yet */
+
+.ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b))
+.error "size of syscall table does not fit value of __NR_Linux_syscalls"
+.endif
 
 #undef ENTRY_SAME
 #undef ENTRY_DIFF
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 03cd858a401c..4cbe23af400a 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -153,6 +153,7 @@
 #define PPC_INST_MFSPR_PVR_MASK         0xfc1fffff
 #define PPC_INST_MFTMR                  0x7c0002dc
 #define PPC_INST_MSGSND                 0x7c00019c
+#define PPC_INST_MSGCLR                 0x7c0001dc
 #define PPC_INST_MSGSNDP                0x7c00011c
 #define PPC_INST_MTTMR                  0x7c0003dc
 #define PPC_INST_NOP                    0x60000000
@@ -309,6 +310,8 @@
                                         ___PPC_RB(b) | __PPC_EH(eh))
 #define PPC_MSGSND(b)           stringify_in_c(.long PPC_INST_MSGSND | \
                                         ___PPC_RB(b))
+#define PPC_MSGCLR(b)           stringify_in_c(.long PPC_INST_MSGCLR | \
+                                        ___PPC_RB(b))
 #define PPC_MSGSNDP(b)          stringify_in_c(.long PPC_INST_MSGSNDP | \
                                         ___PPC_RB(b))
 #define PPC_POPCNTB(a, s)       stringify_in_c(.long PPC_INST_POPCNTB | \
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 1c874fb533bb..af56b5c6c81a 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -608,13 +608,16 @@
 #define   SRR1_ISI_N_OR_G       0x10000000 /* ISI: Access is no-exec or G */
 #define   SRR1_ISI_PROT         0x08000000 /* ISI: Other protection fault */
 #define   SRR1_WAKEMASK         0x00380000 /* reason for wakeup */
+#define   SRR1_WAKEMASK_P8      0x003c0000 /* reason for wakeup on POWER8 */
 #define   SRR1_WAKESYSERR       0x00300000 /* System error */
 #define   SRR1_WAKEEE           0x00200000 /* External interrupt */
 #define   SRR1_WAKEMT           0x00280000 /* mtctrl */
 #define   SRR1_WAKEHMI          0x00280000 /* Hypervisor maintenance */
 #define   SRR1_WAKEDEC          0x00180000 /* Decrementer interrupt */
+#define   SRR1_WAKEDBELL        0x00140000 /* Privileged doorbell on P8 */
 #define   SRR1_WAKETHERM        0x00100000 /* Thermal management interrupt */
 #define   SRR1_WAKERESET        0x00100000 /* System reset */
+#define   SRR1_WAKEHDBELL       0x000c0000 /* Hypervisor doorbell on P8 */
 #define   SRR1_WAKESTATE        0x00030000 /* Powersave exit mask [46:47] */
 #define   SRR1_WS_DEEPEST       0x00030000 /* Some resources not maintained,
                                           * may not be recoverable */
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index f337666768a7..f83046878336 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -437,6 +437,26 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .machine_check_early    = __machine_check_early_realmode_p8,
                 .platform               = "power8",
         },
+        {       /* Power8NVL */
+                .pvr_mask               = 0xffff0000,
+                .pvr_value              = 0x004c0000,
+                .cpu_name               = "POWER8NVL (raw)",
+                .cpu_features           = CPU_FTRS_POWER8,
+                .cpu_user_features      = COMMON_USER_POWER8,
+                .cpu_user_features2     = COMMON_USER2_POWER8,
+                .mmu_features           = MMU_FTRS_POWER8,
+                .icache_bsize           = 128,
+                .dcache_bsize           = 128,
+                .num_pmcs               = 6,
+                .pmc_type               = PPC_PMC_IBM,
+                .oprofile_cpu_type      = "ppc64/power8",
+                .oprofile_type          = PPC_OPROFILE_INVALID,
+                .cpu_setup              = __setup_cpu_power8,
+                .cpu_restore            = __restore_cpu_power8,
+                .flush_tlb              = __flush_tlb_power8,
+                .machine_check_early    = __machine_check_early_realmode_p8,
+                .platform               = "power8",
+        },
         {       /* Power8 DD1: Does not support doorbell IPIs */
                 .pvr_mask               = 0xffffff00,
                 .pvr_value              = 0x004d0100,
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index f4217819cc31..2128f3a96c32 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -17,6 +17,7 @@
 
 #include <asm/dbell.h>
 #include <asm/irq_regs.h>
+#include <asm/kvm_ppc.h>
 
 #ifdef CONFIG_SMP
 void doorbell_setup_this_cpu(void)
@@ -41,6 +42,7 @@ void doorbell_exception(struct pt_regs *regs)
 
         may_hard_irq_enable();
 
+        kvmppc_set_host_ipi(smp_processor_id(), 0);
         __this_cpu_inc(irq_stat.doorbell_irqs);
 
         smp_ipi_demux();
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index c2df8150bd7a..9519e6bdc6d7 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1408,7 +1408,7 @@ machine_check_handle_early:
         bne     9f                      /* continue in V mode if we are. */
 
 5:
-#ifdef CONFIG_KVM_BOOK3S_64_HV
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
         /*
          * We are coming from kernel context. Check if we are coming from
          * guest. if yes, then we can continue. We will fall through
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index de4018a1bc4b..de747563d29d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -636,7 +636,7 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu)
         spin_lock(&vcpu->arch.vpa_update_lock);
         lppaca = (struct lppaca *)vcpu->arch.vpa.pinned_addr;
         if (lppaca)
-                yield_count = lppaca->yield_count;
+                yield_count = be32_to_cpu(lppaca->yield_count);
         spin_unlock(&vcpu->arch.vpa_update_lock);
         return yield_count;
 }
@@ -942,20 +942,20 @@ static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu,
 static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
                 bool preserve_top32)
 {
+        struct kvm *kvm = vcpu->kvm;
         struct kvmppc_vcore *vc = vcpu->arch.vcore;
         u64 mask;
 
+        mutex_lock(&kvm->lock);
         spin_lock(&vc->lock);
         /*
          * If ILE (interrupt little-endian) has changed, update the
          * MSR_LE bit in the intr_msr for each vcpu in this vcore.
          */
         if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) {
-                struct kvm *kvm = vcpu->kvm;
                 struct kvm_vcpu *vcpu;
                 int i;
 
-                mutex_lock(&kvm->lock);
                 kvm_for_each_vcpu(i, vcpu, kvm) {
                         if (vcpu->arch.vcore != vc)
                                 continue;
@@ -964,7 +964,6 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
                         else
                                 vcpu->arch.intr_msr &= ~MSR_LE;
                 }
-                mutex_unlock(&kvm->lock);
         }
 
         /*
@@ -981,6 +980,7 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
                 mask &= 0xFFFFFFFF;
         vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
         spin_unlock(&vc->lock);
+        mutex_unlock(&kvm->lock);
 }
 
 static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bb94e6f20c81..6cbf1630cb70 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1005,6 +1005,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
         /* Save HEIR (HV emulation assist reg) in emul_inst
            if this is an HEI (HV emulation interrupt, e40) */
         li      r3,KVM_INST_FETCH_FAILED
+        stw     r3,VCPU_LAST_INST(r9)
         cmpwi   r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST
         bne     11f
         mfspr   r3,SPRN_HEIR
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index fc34025ef822..38a45088f633 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -33,6 +33,8 @@
 #include <asm/runlatch.h>
 #include <asm/code-patching.h>
 #include <asm/dbell.h>
+#include <asm/kvm_ppc.h>
+#include <asm/ppc-opcode.h>
 
 #include "powernv.h"
 
@@ -149,7 +151,7 @@ static int pnv_smp_cpu_disable(void)
 static void pnv_smp_cpu_kill_self(void)
 {
         unsigned int cpu;
-        unsigned long srr1;
+        unsigned long srr1, wmask;
         u32 idle_states;
 
         /* Standard hot unplug procedure */
@@ -161,6 +163,10 @@ static void pnv_smp_cpu_kill_self(void)
         generic_set_cpu_dead(cpu);
         smp_wmb();
 
+        wmask = SRR1_WAKEMASK;
+        if (cpu_has_feature(CPU_FTR_ARCH_207S))
+                wmask = SRR1_WAKEMASK_P8;
+
         idle_states = pnv_get_supported_cpuidle_states();
         /* We don't want to take decrementer interrupts while we are offline,
          * so clear LPCR:PECE1. We keep PECE2 enabled.
@@ -191,10 +197,14 @@ static void pnv_smp_cpu_kill_self(void)
                  * having finished executing in a KVM guest, then srr1
                  * contains 0.
                  */
-                if ((srr1 & SRR1_WAKEMASK) == SRR1_WAKEEE) {
+                if ((srr1 & wmask) == SRR1_WAKEEE) {
                         icp_native_flush_interrupt();
                         local_paca->irq_happened &= PACA_IRQ_HARD_DIS;
                         smp_mb();
+                } else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
+                        unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+                        asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
+                        kvmppc_set_host_ipi(cpu, 0);
                 }
 
                 if (cpu_core_split_required())
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 90cf3dcbd9f2..8f35d525cede 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -25,10 +25,10 @@
 static struct kobject *mobility_kobj;
 
 struct update_props_workarea {
-        u32 phandle;
-        u32 state;
-        u64 reserved;
-        u32 nprops;
+        __be32 phandle;
+        __be32 state;
+        __be64 reserved;
+        __be32 nprops;
 } __packed;
 
 #define NODE_ACTION_MASK        0xff000000
@@ -54,11 +54,11 @@ static int mobility_rtas_call(int token, char *buf, s32 scope)
         return rc;
 }
 
-static int delete_dt_node(u32 phandle)
+static int delete_dt_node(__be32 phandle)
 {
         struct device_node *dn;
 
-        dn = of_find_node_by_phandle(phandle);
+        dn = of_find_node_by_phandle(be32_to_cpu(phandle));
         if (!dn)
                 return -ENOENT;
 
@@ -127,7 +127,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop,
         return 0;
 }
 
-static int update_dt_node(u32 phandle, s32 scope)
+static int update_dt_node(__be32 phandle, s32 scope)
 {
         struct update_props_workarea *upwa;
         struct device_node *dn;
@@ -136,6 +136,7 @@ static int update_dt_node(u32 phandle, s32 scope)
         char *prop_data;
         char *rtas_buf;
         int update_properties_token;
+        u32 nprops;
         u32 vd;
 
         update_properties_token = rtas_token("ibm,update-properties");
@@ -146,7 +147,7 @@ static int update_dt_node(u32 phandle, s32 scope)
         if (!rtas_buf)
                 return -ENOMEM;
 
-        dn = of_find_node_by_phandle(phandle);
+        dn = of_find_node_by_phandle(be32_to_cpu(phandle));
         if (!dn) {
                 kfree(rtas_buf);
                 return -ENOENT;
@@ -162,6 +163,7 @@ static int update_dt_node(u32 phandle, s32 scope)
                         break;
 
                 prop_data = rtas_buf + sizeof(*upwa);
+                nprops = be32_to_cpu(upwa->nprops);
 
                 /* On the first call to ibm,update-properties for a node the
                  * the first property value descriptor contains an empty
@@ -170,17 +172,17 @@ static int update_dt_node(u32 phandle, s32 scope)
                  */
                 if (*prop_data == 0) {
                         prop_data++;
-                        vd = *(u32 *)prop_data;
+                        vd = be32_to_cpu(*(__be32 *)prop_data);
                         prop_data += vd + sizeof(vd);
-                        upwa->nprops--;
+                        nprops--;
                 }
 
-                for (i = 0; i < upwa->nprops; i++) {
+                for (i = 0; i < nprops; i++) {
                         char *prop_name;
 
                         prop_name = prop_data;
                         prop_data += strlen(prop_name) + 1;
-                        vd = *(u32 *)prop_data;
+                        vd = be32_to_cpu(*(__be32 *)prop_data);
                         prop_data += sizeof(vd);
 
                         switch (vd) {
@@ -212,13 +214,13 @@ static int update_dt_node(u32 phandle, s32 scope)
         return 0;
 }
 
-static int add_dt_node(u32 parent_phandle, u32 drc_index)
+static int add_dt_node(__be32 parent_phandle, __be32 drc_index)
 {
         struct device_node *dn;
         struct device_node *parent_dn;
         int rc;
 
-        parent_dn = of_find_node_by_phandle(parent_phandle);
+        parent_dn = of_find_node_by_phandle(be32_to_cpu(parent_phandle));
         if (!parent_dn)
                 return -ENOENT;
 
@@ -237,7 +239,7 @@ static int add_dt_node(u32 parent_phandle, u32 drc_index)
 int pseries_devicetree_update(s32 scope)
 {
         char *rtas_buf;
-        u32 *data;
+        __be32 *data;
         int update_nodes_token;
         int rc;
 
@@ -254,17 +256,17 @@ int pseries_devicetree_update(s32 scope)
                 if (rc && rc != 1)
                         break;
 
-                data = (u32 *)rtas_buf + 4;
-                while (*data & NODE_ACTION_MASK) {
+                data = (__be32 *)rtas_buf + 4;
+                while (be32_to_cpu(*data) & NODE_ACTION_MASK) {
                         int i;
-                        u32 action = *data & NODE_ACTION_MASK;
-                        int node_count = *data & NODE_COUNT_MASK;
+                        u32 action = be32_to_cpu(*data) & NODE_ACTION_MASK;
+                        u32 node_count = be32_to_cpu(*data) & NODE_COUNT_MASK;
 
                         data++;
 
                         for (i = 0; i < node_count; i++) {
-                                u32 phandle = *data++;
-                                u32 drc_index;
+                                __be32 phandle = *data++;
+                                __be32 drc_index;
 
                                 switch (action) {
                                 case DELETE_DT_NODE:
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index c9df40b5c0ac..c9c875d9ed31 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -211,7 +211,7 @@ do {								\
 
 extern unsigned long mmap_rnd_mask;
 
-#define STACK_RND_MASK  (mmap_rnd_mask)
+#define STACK_RND_MASK  (test_thread_flag(TIF_31BIT) ? 0x7ff : mmap_rnd_mask)
 
 #define ARCH_DLINFO                                                         \
 do {                                                                        \
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 82c19899574f..6c79f1b44fe7 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -57,6 +57,44 @@
 
 unsigned long ftrace_plt;
 
+static inline void ftrace_generate_orig_insn(struct ftrace_insn *insn)
+{
+#ifdef CC_USING_HOTPATCH
+        /* brcl 0,0 */
+        insn->opc = 0xc004;
+        insn->disp = 0;
+#else
+        /* stg r14,8(r15) */
+        insn->opc = 0xe3e0;
+        insn->disp = 0xf0080024;
+#endif
+}
+
+static inline int is_kprobe_on_ftrace(struct ftrace_insn *insn)
+{
+#ifdef CONFIG_KPROBES
+        if (insn->opc == BREAKPOINT_INSTRUCTION)
+                return 1;
+#endif
+        return 0;
+}
+
+static inline void ftrace_generate_kprobe_nop_insn(struct ftrace_insn *insn)
+{
+#ifdef CONFIG_KPROBES
+        insn->opc = BREAKPOINT_INSTRUCTION;
+        insn->disp = KPROBE_ON_FTRACE_NOP;
+#endif
+}
+
+static inline void ftrace_generate_kprobe_call_insn(struct ftrace_insn *insn)
+{
+#ifdef CONFIG_KPROBES
+        insn->opc = BREAKPOINT_INSTRUCTION;
+        insn->disp = KPROBE_ON_FTRACE_CALL;
+#endif
+}
+
 int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
                        unsigned long addr)
 {
@@ -72,16 +110,9 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
                 return -EFAULT;
         if (addr == MCOUNT_ADDR) {
                 /* Initial code replacement */
-#ifdef CC_USING_HOTPATCH
-                /* We expect to see brcl 0,0 */
-                ftrace_generate_nop_insn(&orig);
-#else
-                /* We expect to see stg r14,8(r15) */
-                orig.opc = 0xe3e0;
-                orig.disp = 0xf0080024;
-#endif
+                ftrace_generate_orig_insn(&orig);
                 ftrace_generate_nop_insn(&new);
-        } else if (old.opc == BREAKPOINT_INSTRUCTION) {
+        } else if (is_kprobe_on_ftrace(&old)) {
                 /*
                  * If we find a breakpoint instruction, a kprobe has been
                  * placed at the beginning of the function. We write the
@@ -89,9 +120,8 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
                  * bytes of the original instruction so that the kprobes
                  * handler can execute a nop, if it reaches this breakpoint.
                  */
-                new.opc = orig.opc = BREAKPOINT_INSTRUCTION;
-                orig.disp = KPROBE_ON_FTRACE_CALL;
-                new.disp = KPROBE_ON_FTRACE_NOP;
+                ftrace_generate_kprobe_call_insn(&orig);
+                ftrace_generate_kprobe_nop_insn(&new);
         } else {
                 /* Replace ftrace call with a nop. */
                 ftrace_generate_call_insn(&orig, rec->ip);
@@ -111,7 +141,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
         if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old)))
                 return -EFAULT;
-        if (old.opc == BREAKPOINT_INSTRUCTION) {
+        if (is_kprobe_on_ftrace(&old)) {
                 /*
                  * If we find a breakpoint instruction, a kprobe has been
                  * placed at the beginning of the function. We write the
@@ -119,9 +149,8 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
                  * bytes of the original instruction so that the kprobes
                  * handler can execute a brasl if it reaches this breakpoint.
                  */
-                new.opc = orig.opc = BREAKPOINT_INSTRUCTION;
-                orig.disp = KPROBE_ON_FTRACE_NOP;
-                new.disp = KPROBE_ON_FTRACE_CALL;
+                ftrace_generate_kprobe_nop_insn(&orig);
+                ftrace_generate_kprobe_call_insn(&new);
         } else {
                 /* Replace nop with an ftrace call. */
                 ftrace_generate_nop_insn(&orig);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index c3f8d157cb0d..e6a1578fc000 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1415,7 +1415,7 @@ CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG);
 
 static struct attribute *cpumsf_pmu_events_attr[] = {
         CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC),
-        CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG),
+        NULL,
         NULL,
 };
 
@@ -1606,8 +1606,11 @@ static int __init init_cpum_sampling_pmu(void)
                 return -EINVAL;
         }
 
-        if (si.ad)
+        if (si.ad) {
                 sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB);
+                cpumsf_pmu_events_attr[1] =
+                        CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG);
+        }
 
         sfdbg = debug_register(KMSG_COMPONENT, 2, 1, 80);
         if (!sfdbg)
diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S
index 6b09fdffbd2f..ca6294645dd3 100644
--- a/arch/s390/kernel/swsusp_asm64.S
+++ b/arch/s390/kernel/swsusp_asm64.S
@@ -177,6 +177,17 @@ restart_entry:
         lhi     %r1,1
         sigp    %r1,%r0,SIGP_SET_ARCHITECTURE
         sam64
+#ifdef CONFIG_SMP
+        larl    %r1,smp_cpu_mt_shift
+        icm     %r1,15,0(%r1)
+        jz      smt_done
+        llgfr   %r1,%r1
+smt_loop:
+        sigp    %r1,%r0,SIGP_SET_MULTI_THREADING
+        brc     8,smt_done                      /* accepted */
+        brc     2,smt_loop                      /* busy, try again */
+smt_done:
+#endif
         larl    %r1,.Lnew_pgm_check_psw
         lpswe   0(%r1)
 pgm_check_entry:
diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h
index 4f6725ff4c33..f5b6537306f0 100644
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@@ -2957,6 +2957,17 @@ unsigned long sun4v_t5_set_perfreg(unsigned long reg_num,
                                    unsigned long reg_val);
 #endif
 
+
+#define HV_FAST_M7_GET_PERFREG  0x43
+#define HV_FAST_M7_SET_PERFREG  0x44
+
+#ifndef __ASSEMBLY__
+unsigned long sun4v_m7_get_perfreg(unsigned long reg_num,
+                                      unsigned long *reg_val);
+unsigned long sun4v_m7_set_perfreg(unsigned long reg_num,
+                                      unsigned long reg_val);
+#endif
+
 /* Function numbers for HV_CORE_TRAP.  */
 #define HV_CORE_SET_VER                 0x00
 #define HV_CORE_PUTCHAR                 0x01
@@ -2981,6 +2992,7 @@ unsigned long sun4v_t5_set_perfreg(unsigned long reg_num,
 #define HV_GRP_SDIO                     0x0108
 #define HV_GRP_SDIO_ERR                 0x0109
 #define HV_GRP_REBOOT_DATA              0x0110
+#define HV_GRP_M7_PERF                  0x0114
 #define HV_GRP_NIAG_PERF                0x0200
 #define HV_GRP_FIRE_PERF                0x0201
 #define HV_GRP_N2_CPU                   0x0202
diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c
index 5c55145bfbf0..662500fa555f 100644
--- a/arch/sparc/kernel/hvapi.c
+++ b/arch/sparc/kernel/hvapi.c
@@ -48,6 +48,7 @@ static struct api_info api_table[] = {
         { .group = HV_GRP_VT_CPU,                               },
         { .group = HV_GRP_T5_CPU,                               },
         { .group = HV_GRP_DIAG,         .flags = FLAG_PRE_API   },
+        { .group = HV_GRP_M7_PERF,                              },
 };
 
 static DEFINE_SPINLOCK(hvapi_lock);
diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S
index caedf8320416..afbaba52d2f1 100644
--- a/arch/sparc/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@@ -837,3 +837,19 @@ ENTRY(sun4v_t5_set_perfreg)
         retl
          nop
 ENDPROC(sun4v_t5_set_perfreg)
+
+ENTRY(sun4v_m7_get_perfreg)
+        mov     %o1, %o4
+        mov     HV_FAST_M7_GET_PERFREG, %o5
+        ta      HV_FAST_TRAP
+        stx     %o1, [%o4]
+        retl
+        nop
+ENDPROC(sun4v_m7_get_perfreg)
+
+ENTRY(sun4v_m7_set_perfreg)
+        mov     HV_FAST_M7_SET_PERFREG, %o5
+        ta      HV_FAST_TRAP
+        retl
+        nop
+ENDPROC(sun4v_m7_set_perfreg)
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index 7e967c8018c8..eb978c77c76a 100644
--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@@ -217,6 +217,31 @@ static const struct pcr_ops n5_pcr_ops = {
         .pcr_nmi_disable        = PCR_N4_PICNPT,
 };
 
+static u64 m7_pcr_read(unsigned long reg_num)
+{
+        unsigned long val;
+
+        (void) sun4v_m7_get_perfreg(reg_num, &val);
+
+        return val;
+}
+
+static void m7_pcr_write(unsigned long reg_num, u64 val)
+{
+        (void) sun4v_m7_set_perfreg(reg_num, val);
+}
+
+static const struct pcr_ops m7_pcr_ops = {
+        .read_pcr               = m7_pcr_read,
+        .write_pcr              = m7_pcr_write,
+        .read_pic               = n4_pic_read,
+        .write_pic              = n4_pic_write,
+        .nmi_picl_value         = n4_picl_value,
+        .pcr_nmi_enable         = (PCR_N4_PICNPT | PCR_N4_STRACE |
+                                   PCR_N4_UTRACE | PCR_N4_TOE |
+                                   (26 << PCR_N4_SL_SHIFT)),
+        .pcr_nmi_disable        = PCR_N4_PICNPT,
+};
 
 static unsigned long perf_hsvc_group;
 static unsigned long perf_hsvc_major;
@@ -248,6 +273,10 @@ static int __init register_perf_hsvc(void)
                         perf_hsvc_group = HV_GRP_T5_CPU;
                         break;
 
+                case SUN4V_CHIP_SPARC_M7:
+                        perf_hsvc_group = HV_GRP_M7_PERF;
+                        break;
+
                 default:
                         return -ENODEV;
                 }
@@ -293,6 +322,10 @@ static int __init setup_sun4v_pcr_ops(void)
                 pcr_ops = &n5_pcr_ops;
                 break;
 
+        case SUN4V_CHIP_SPARC_M7:
+                pcr_ops = &m7_pcr_ops;
+                break;
+
         default:
                 ret = -ENODEV;
                 break;
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 46a5e4508752..86eebfa3b158 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -792,6 +792,42 @@ static const struct sparc_pmu niagara4_pmu = {
         .num_pic_regs   = 4,
 };
 
+static void sparc_m7_write_pmc(int idx, u64 val)
+{
+        u64 pcr;
+
+        pcr = pcr_ops->read_pcr(idx);
+        /* ensure ov and ntc are reset */
+        pcr &= ~(PCR_N4_OV | PCR_N4_NTC);
+
+        pcr_ops->write_pic(idx, val & 0xffffffff);
+
+        pcr_ops->write_pcr(idx, pcr);
+}
+
+static const struct sparc_pmu sparc_m7_pmu = {
+        .event_map      = niagara4_event_map,
+        .cache_map      = &niagara4_cache_map,
+        .max_events     = ARRAY_SIZE(niagara4_perfmon_event_map),
+        .read_pmc       = sparc_vt_read_pmc,
+        .write_pmc      = sparc_m7_write_pmc,
+        .upper_shift    = 5,
+        .lower_shift    = 5,
+        .event_mask     = 0x7ff,
+        .user_bit       = PCR_N4_UTRACE,
+        .priv_bit       = PCR_N4_STRACE,
+
+        /* We explicitly don't support hypervisor tracing. */
+        .hv_bit         = 0,
+
+        .irq_bit        = PCR_N4_TOE,
+        .upper_nop      = 0,
+        .lower_nop      = 0,
+        .flags          = 0,
+        .max_hw_events  = 4,
+        .num_pcrs       = 4,
+        .num_pic_regs   = 4,
+};
 static const struct sparc_pmu *sparc_pmu __read_mostly;
 
 static u64 event_encoding(u64 event_id, int idx)
@@ -960,6 +996,8 @@ out:
         cpuc->pcr[0] |= cpuc->event[0]->hw.config_base;
 }
 
+static void sparc_pmu_start(struct perf_event *event, int flags);
+
 /* On this PMU each PIC has it's own PCR control register.  */
 static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc)
 {
@@ -972,20 +1010,13 @@ static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc)
                 struct perf_event *cp = cpuc->event[i];
                 struct hw_perf_event *hwc = &cp->hw;
                 int idx = hwc->idx;
-                u64 enc;
 
                 if (cpuc->current_idx[i] != PIC_NO_INDEX)
                         continue;
 
-                sparc_perf_event_set_period(cp, hwc, idx);
                 cpuc->current_idx[i] = idx;
 
-                enc = perf_event_get_enc(cpuc->events[i]);
-                cpuc->pcr[idx] &= ~mask_for_index(idx);
-                if (hwc->state & PERF_HES_STOPPED)
-                        cpuc->pcr[idx] |= nop_for_index(idx);
-                else
-                        cpuc->pcr[idx] |= event_encoding(enc, idx);
+                sparc_pmu_start(cp, PERF_EF_RELOAD);
         }
 out:
         for (i = 0; i < cpuc->n_events; i++) {
@@ -1101,7 +1132,6 @@ static void sparc_pmu_del(struct perf_event *event, int _flags)
         int i;
 
         local_irq_save(flags);
-        perf_pmu_disable(event->pmu);
 
         for (i = 0; i < cpuc->n_events; i++) {
                 if (event == cpuc->event[i]) {
@@ -1127,7 +1157,6 @@ static void sparc_pmu_del(struct perf_event *event, int _flags)
                 }
         }
 
-        perf_pmu_enable(event->pmu);
         local_irq_restore(flags);
 }
 
@@ -1361,7 +1390,6 @@ static int sparc_pmu_add(struct perf_event *event, int ef_flags)
         unsigned long flags;
 
         local_irq_save(flags);
-        perf_pmu_disable(event->pmu);
 
         n0 = cpuc->n_events;
         if (n0 >= sparc_pmu->max_hw_events)
@@ -1394,7 +1422,6 @@ nocheck:
 
         ret = 0;
 out:
-        perf_pmu_enable(event->pmu);
         local_irq_restore(flags);
         return ret;
 }
@@ -1667,6 +1694,10 @@ static bool __init supported_pmu(void)
                 sparc_pmu = &niagara4_pmu;
                 return true;
         }
+        if (!strcmp(sparc_pmu_type, "sparc-m7")) {
+                sparc_pmu = &sparc_m7_pmu;
+                return true;
+        }
         return false;
 }
 
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 0be7bf978cb1..46a59643bb1c 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -287,6 +287,8 @@ void arch_trigger_all_cpu_backtrace(bool include_self)
                         printk("             TPC[%lx] O7[%lx] I7[%lx] RPC[%lx]\n",
                                gp->tpc, gp->o7, gp->i7, gp->rpc);
                 }
+
+                touch_nmi_watchdog();
         }
 
         memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
@@ -362,6 +364,8 @@ static void pmu_snapshot_all_cpus(void)
                        (cpu == this_cpu ? '*' : ' '), cpu,
                        pp->pcr[0], pp->pcr[1], pp->pcr[2], pp->pcr[3],
                        pp->pic[0], pp->pic[1], pp->pic[2], pp->pic[3]);
+
+                touch_nmi_watchdog();
         }
 
         memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
diff --git a/arch/sparc/lib/memmove.S b/arch/sparc/lib/memmove.S
index b7f6334e159f..857ad4f8905f 100644
--- a/arch/sparc/lib/memmove.S
+++ b/arch/sparc/lib/memmove.S
@@ -8,9 +8,11 @@
 
         .text
 ENTRY(memmove) /* o0=dst o1=src o2=len */
-        mov             %o0, %g1
+        brz,pn          %o2, 99f
+         mov            %o0, %g1
+
         cmp             %o0, %o1
-        bleu,pt         %xcc, memcpy
+        bleu,pt         %xcc, 2f
          add            %o1, %o2, %g7
         cmp             %g7, %o0
         bleu,pt         %xcc, memcpy
@@ -24,7 +26,34 @@ ENTRY(memmove) /* o0=dst o1=src o2=len */
         stb             %g7, [%o0]
         bne,pt          %icc, 1b
          sub            %o0, 1, %o0
-
+99:
         retl
          mov            %g1, %o0
+
+        /* We can't just call memcpy for these memmove cases.  On some
+         * chips the memcpy uses cache initializing stores and when dst
+         * and src are close enough, those can clobber the source data
+         * before we've loaded it in.
+         */
+2:      or              %o0, %o1, %g7
+        or              %o2, %g7, %g7
+        andcc           %g7, 0x7, %g0
+        bne,pn          %xcc, 4f
+         nop
+
+3:      ldx             [%o1], %g7
+        add             %o1, 8, %o1
+        subcc           %o2, 8, %o2
+        add             %o0, 8, %o0
+        bne,pt          %icc, 3b
+         stx            %g7, [%o0 - 0x8]
+        ba,a,pt         %xcc, 99b
+
+4:      ldub            [%o1], %g7
+        add             %o1, 1, %o1
+        subcc           %o2, 1, %o2
+        add             %o0, 1, %o0
+        bne,pt          %icc, 4b
+         stb            %g7, [%o0 - 0x1]
+        ba,a,pt         %xcc, 99b
 ENDPROC(memmove)
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index b1947e0f3e10..46d4449772bc 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -422,6 +422,7 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
                         struct kvm_ioapic *ioapic, int vector, int trigger_mode)
 {
         int i;
+        struct kvm_lapic *apic = vcpu->arch.apic;
 
         for (i = 0; i < IOAPIC_NUM_PINS; i++) {
                 union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
@@ -443,7 +444,8 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
                 kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
                 spin_lock(&ioapic->lock);
 
-                if (trigger_mode != IOAPIC_LEVEL_TRIG)
+                if (trigger_mode != IOAPIC_LEVEL_TRIG ||
+                    kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)
                         continue;
 
                 ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index bd4e34de24c7..4ee827d7bf36 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -833,8 +833,7 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 
 static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
 {
-        if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
-            kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
+        if (kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
                 int trigger_mode;
                 if (apic_test_vector(vector, apic->regs + APIC_TMR))
                         trigger_mode = IOAPIC_LEVEL_TRIG;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 10a481b7674d..ae4f6d35d19c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2479,8 +2479,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
         if (enable_ept) {
                 /* nested EPT: emulate EPT also to L1 */
                 vmx->nested.nested_vmx_secondary_ctls_high |=
-                        SECONDARY_EXEC_ENABLE_EPT |
-                        SECONDARY_EXEC_UNRESTRICTED_GUEST;
+                        SECONDARY_EXEC_ENABLE_EPT;
                 vmx->nested.nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
                          VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT |
                          VMX_EPT_INVEPT_BIT;
@@ -2494,6 +2493,10 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
         } else
                 vmx->nested.nested_vmx_ept_caps = 0;
 
+        if (enable_unrestricted_guest)
+                vmx->nested.nested_vmx_secondary_ctls_high |=
+                        SECONDARY_EXEC_UNRESTRICTED_GUEST;
+
         /* miscellaneous data */
         rdmsr(MSR_IA32_VMX_MISC,
                 vmx->nested.nested_vmx_misc_low,
diff --git a/block/blk-merge.c b/block/blk-merge.c
index fc1ff3b1ea1f..fd3fee81c23c 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -592,7 +592,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
         if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS)) {
                 struct bio_vec *bprev;
 
-                bprev = &rq->biotail->bi_io_vec[bio->bi_vcnt - 1];
+                bprev = &rq->biotail->bi_io_vec[rq->biotail->bi_vcnt - 1];
                 if (bvec_gap_to_prev(bprev, bio->bi_io_vec[0].bv_offset))
                         return false;
         }
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index d53a764b05ea..be3290cc0644 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -278,9 +278,11 @@ static int bt_get(struct blk_mq_alloc_data *data,
                 /*
                  * We're out of tags on this hardware queue, kick any
                  * pending IO submits before going to sleep waiting for
-                 * some to complete.
+                 * some to complete. Note that hctx can be NULL here for
+                 * reserved tag allocation.
                  */
-                blk_mq_run_hw_queue(hctx, false);
+                if (hctx)
+                        blk_mq_run_hw_queue(hctx, false);
 
                 /*
                  * Retry tag allocation after running the hardware queue,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4f4bea21052e..b7b8933ec241 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1938,7 +1938,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
          */
         if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release,
                             PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
-                goto err_map;
+                goto err_mq_usage;
 
         setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
         blk_queue_rq_timeout(q, 30000);
@@ -1981,7 +1981,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
         blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 
         if (blk_mq_init_hw_queues(q, set))
-                goto err_hw;
+                goto err_mq_usage;
 
         mutex_lock(&all_q_mutex);
         list_add_tail(&q->all_q_node, &all_q_list);
@@ -1993,7 +1993,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 
         return q;
 
-err_hw:
+err_mq_usage:
         blk_cleanup_queue(q);
 err_hctxs:
         kfree(map);
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 4c35f0822d06..ef150ebb4c30 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4737,7 +4737,7 @@ struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag)
                 return NULL;
 
         /* libsas case */
-        if (!ap->scsi_host) {
+        if (ap->flags & ATA_FLAG_SAS_HOST) {
                 tag = ata_sas_allocate_tag(ap);
                 if (tag < 0)
                         return NULL;
@@ -4776,7 +4776,7 @@ void ata_qc_free(struct ata_queued_cmd *qc)
         tag = qc->tag;
         if (likely(ata_tag_valid(tag))) {
                 qc->tag = ATA_TAG_POISON;
-                if (!ap->scsi_host)
+                if (ap->flags & ATA_FLAG_SAS_HOST)
                         ata_sas_free_tag(tag, ap);
         }
 }
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index beb8b27d4621..a13587b5c2be 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -243,4 +243,12 @@ extern struct regcache_ops regcache_rbtree_ops;
 extern struct regcache_ops regcache_lzo_ops;
 extern struct regcache_ops regcache_flat_ops;
 
+static inline const char *regmap_name(const struct regmap *map)
+{
+        if (map->dev)
+                return dev_name(map->dev);
+
+        return map->name;
+}
+
 #endif
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index da84f544c544..87db9893b463 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -218,7 +218,7 @@ int regcache_read(struct regmap *map,
                 ret = map->cache_ops->read(map, reg, value);
 
                 if (ret == 0)
-                        trace_regmap_reg_read_cache(map->dev, reg, *value);
+                        trace_regmap_reg_read_cache(map, reg, *value);
 
                 return ret;
         }
@@ -311,7 +311,7 @@ int regcache_sync(struct regmap *map)
         dev_dbg(map->dev, "Syncing %s cache\n",
                 map->cache_ops->name);
         name = map->cache_ops->name;
-        trace_regcache_sync(map->dev, name, "start");
+        trace_regcache_sync(map, name, "start");
 
         if (!map->cache_dirty)
                 goto out;
@@ -346,7 +346,7 @@ out:
 
         regmap_async_complete(map);
 
-        trace_regcache_sync(map->dev, name, "stop");
+        trace_regcache_sync(map, name, "stop");
 
         return ret;
 }
@@ -381,7 +381,7 @@ int regcache_sync_region(struct regmap *map, unsigned int min,
         name = map->cache_ops->name;
         dev_dbg(map->dev, "Syncing %s cache from %d-%d\n", name, min, max);
 
-        trace_regcache_sync(map->dev, name, "start region");
+        trace_regcache_sync(map, name, "start region");
 
         if (!map->cache_dirty)
                 goto out;
@@ -401,7 +401,7 @@ out:
 
         regmap_async_complete(map);
 
-        trace_regcache_sync(map->dev, name, "stop region");
+        trace_regcache_sync(map, name, "stop region");
 
         return ret;
 }
@@ -428,7 +428,7 @@ int regcache_drop_region(struct regmap *map, unsigned int min,
 
         map->lock(map->lock_arg);
 
-        trace_regcache_drop_region(map->dev, min, max);
+        trace_regcache_drop_region(map, min, max);
 
         ret = map->cache_ops->drop(map, min, max);
 
@@ -455,7 +455,7 @@ void regcache_cache_only(struct regmap *map, bool enable)
         map->lock(map->lock_arg);
         WARN_ON(map->cache_bypass && enable);
         map->cache_only = enable;
-        trace_regmap_cache_only(map->dev, enable);
+        trace_regmap_cache_only(map, enable);
         map->unlock(map->lock_arg);
 }
 EXPORT_SYMBOL_GPL(regcache_cache_only);
@@ -493,7 +493,7 @@ void regcache_cache_bypass(struct regmap *map, bool enable)
         map->lock(map->lock_arg);
         WARN_ON(map->cache_only && enable);
         map->cache_bypass = enable;
-        trace_regmap_cache_bypass(map->dev, enable);
+        trace_regmap_cache_bypass(map, enable);
         map->unlock(map->lock_arg);
 }
 EXPORT_SYMBOL_GPL(regcache_cache_bypass);
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index f99b098ddabf..dbfe6a69c3da 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1281,7 +1281,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg,
         if (map->async && map->bus->async_write) {
                 struct regmap_async *async;
 
-                trace_regmap_async_write_start(map->dev, reg, val_len);
+                trace_regmap_async_write_start(map, reg, val_len);
 
                 spin_lock_irqsave(&map->async_lock, flags);
                 async = list_first_entry_or_null(&map->async_free,
@@ -1339,8 +1339,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg,
                 return ret;
         }
 
-        trace_regmap_hw_write_start(map->dev, reg,
-                                    val_len / map->format.val_bytes);
+        trace_regmap_hw_write_start(map, reg, val_len / map->format.val_bytes);
 
         /* If we're doing a single register write we can probably just
          * send the work_buf directly, otherwise try to do a gather
@@ -1372,8 +1371,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg,
                 kfree(buf);
         }
 
-        trace_regmap_hw_write_done(map->dev, reg,
-                                   val_len / map->format.val_bytes);
+        trace_regmap_hw_write_done(map, reg, val_len / map->format.val_bytes);
 
         return ret;
 }
@@ -1407,12 +1405,12 @@ static int _regmap_bus_formatted_write(void *context, unsigned int reg,
 
         map->format.format_write(map, reg, val);
 
-        trace_regmap_hw_write_start(map->dev, reg, 1);
+        trace_regmap_hw_write_start(map, reg, 1);
 
         ret = map->bus->write(map->bus_context, map->work_buf,
                               map->format.buf_size);
 
-        trace_regmap_hw_write_done(map->dev, reg, 1);
+        trace_regmap_hw_write_done(map, reg, 1);
 
         return ret;
 }
@@ -1470,7 +1468,7 @@ int _regmap_write(struct regmap *map, unsigned int reg,
                 dev_info(map->dev, "%x <= %x\n", reg, val);
 #endif
 
-        trace_regmap_reg_write(map->dev, reg, val);
+        trace_regmap_reg_write(map, reg, val);
 
         return map->reg_write(context, reg, val);
 }
@@ -1773,7 +1771,7 @@ static int _regmap_raw_multi_reg_write(struct regmap *map,
         for (i = 0; i < num_regs; i++) {
                 int reg = regs[i].reg;
                 int val = regs[i].def;
-                trace_regmap_hw_write_start(map->dev, reg, 1);
+                trace_regmap_hw_write_start(map, reg, 1);
                 map->format.format_reg(u8, reg, map->reg_shift);
                 u8 += reg_bytes + pad_bytes;
                 map->format.format_val(u8, val, 0);
@@ -1788,7 +1786,7 @@ static int _regmap_raw_multi_reg_write(struct regmap *map,
 
         for (i = 0; i < num_regs; i++) {
                 int reg = regs[i].reg;
-                trace_regmap_hw_write_done(map->dev, reg, 1);
+                trace_regmap_hw_write_done(map, reg, 1);
         }
         return ret;
 }
@@ -2059,15 +2057,13 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
          */
         u8[0] |= map->read_flag_mask;
 
-        trace_regmap_hw_read_start(map->dev, reg,
-                                   val_len / map->format.val_bytes);
+        trace_regmap_hw_read_start(map, reg, val_len / map->format.val_bytes);
 
         ret = map->bus->read(map->bus_context, map->work_buf,
                              map->format.reg_bytes + map->format.pad_bytes,
                              val, val_len);
 
-        trace_regmap_hw_read_done(map->dev, reg,
-                                  val_len / map->format.val_bytes);
+        trace_regmap_hw_read_done(map, reg, val_len / map->format.val_bytes);
 
         return ret;
 }
@@ -2123,7 +2119,7 @@ static int _regmap_read(struct regmap *map, unsigned int reg,
                         dev_info(map->dev, "%x => %x\n", reg, *val);
 #endif
 
-                trace_regmap_reg_read(map->dev, reg, *val);
+                trace_regmap_reg_read(map, reg, *val);
 
                 if (!map->cache_bypass)
                         regcache_write(map, reg, *val);
@@ -2480,7 +2476,7 @@ void regmap_async_complete_cb(struct regmap_async *async, int ret)
         struct regmap *map = async->map;
         bool wake;
 
-        trace_regmap_async_io_complete(map->dev);
+        trace_regmap_async_io_complete(map);
 
         spin_lock(&map->async_lock);
         list_move(&async->list, &map->async_free);
@@ -2525,7 +2521,7 @@ int regmap_async_complete(struct regmap *map)
         if (!map->bus || !map->bus->async_write)
                 return 0;
 
-        trace_regmap_async_complete_start(map->dev);
+        trace_regmap_async_complete_start(map);
 
         wait_event(map->async_waitq, regmap_async_is_done(map));
 
@@ -2534,7 +2530,7 @@ int regmap_async_complete(struct regmap *map)
         map->async_ret = 0;
         spin_unlock_irqrestore(&map->async_lock, flags);
 
-        trace_regmap_async_complete_done(map->dev);
+        trace_regmap_async_complete_done(map);
 
         return ret;
 }
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 4bc2a5cb9935..a98c41f72c63 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -803,10 +803,6 @@ static int __init nbd_init(void)
                 return -EINVAL;
         }
 
-        nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
-        if (!nbd_dev)
-                return -ENOMEM;
-
         part_shift = 0;
         if (max_part > 0) {
                 part_shift = fls(max_part);
@@ -828,6 +824,10 @@ static int __init nbd_init(void)
         if (nbds_max > 1UL << (MINORBITS - part_shift))
                 return -EINVAL;
 
+        nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
+        if (!nbd_dev)
+                return -ENOMEM;
+
         for (i = 0; i < nbds_max; i++) {
                 struct gendisk *disk = alloc_disk(1 << part_shift);
                 if (!disk)
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index ceb32dd52a6c..e23be20a3417 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -3003,6 +3003,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
         }
         get_device(dev->device);
 
+        INIT_LIST_HEAD(&dev->node);
         INIT_WORK(&dev->probe_work, nvme_async_probe);
         schedule_work(&dev->probe_work);
         return 0;
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 68161f7a07d6..a0b036ccb118 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -192,6 +192,7 @@ config SYS_SUPPORTS_EM_STI
 config SH_TIMER_CMT
         bool "Renesas CMT timer driver" if COMPILE_TEST
         depends on GENERIC_CLOCKEVENTS
+        depends on HAS_IOMEM
         default SYS_SUPPORTS_SH_CMT
         help
           This enables build of a clocksource and clockevent driver for
@@ -201,6 +202,7 @@ config SH_TIMER_CMT
 config SH_TIMER_MTU2
         bool "Renesas MTU2 timer driver" if COMPILE_TEST
         depends on GENERIC_CLOCKEVENTS
+        depends on HAS_IOMEM
         default SYS_SUPPORTS_SH_MTU2
         help
           This enables build of a clockevent driver for the Multi-Function
@@ -210,6 +212,7 @@ config SH_TIMER_MTU2
 config SH_TIMER_TMU
         bool "Renesas TMU timer driver" if COMPILE_TEST
         depends on GENERIC_CLOCKEVENTS
+        depends on HAS_IOMEM
         default SYS_SUPPORTS_SH_TMU
         help
           This enables build of a clocksource and clockevent driver for
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index 5dcbf90b8015..58597fbcc046 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -17,7 +17,6 @@
 #include <linux/irq.h>
 #include <linux/irqreturn.h>
 #include <linux/reset.h>
-#include <linux/sched_clock.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -137,11 +136,6 @@ static struct irqaction sun5i_timer_irq = {
         .dev_id = &sun5i_clockevent,
 };
 
-static u64 sun5i_timer_sched_read(void)
-{
-        return ~readl(timer_base + TIMER_CNTVAL_LO_REG(1));
-}
-
 static void __init sun5i_timer_init(struct device_node *node)
 {
         struct reset_control *rstc;
@@ -172,7 +166,6 @@ static void __init sun5i_timer_init(struct device_node *node)
         writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD,
                timer_base + TIMER_CTL_REG(1));
 
-        sched_clock_register(sun5i_timer_sched_read, 32, rate);
         clocksource_mmio_init(timer_base + TIMER_CNTVAL_LO_REG(1), node->name,
                               rate, 340, 32, clocksource_mmio_readl_down);
 
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index f6d04c7b5115..679b10e34fb5 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -525,17 +525,6 @@ void drm_framebuffer_reference(struct drm_framebuffer *fb)
 }
 EXPORT_SYMBOL(drm_framebuffer_reference);
 
-static void drm_framebuffer_free_bug(struct kref *kref)
-{
-        BUG();
-}
-
-static void __drm_framebuffer_unreference(struct drm_framebuffer *fb)
-{
-        DRM_DEBUG("%p: FB ID: %d (%d)\n", fb, fb->base.id, atomic_read(&fb->refcount.refcount));
-        kref_put(&fb->refcount, drm_framebuffer_free_bug);
-}
-
 /**
  * drm_framebuffer_unregister_private - unregister a private fb from the lookup idr
  * @fb: fb to unregister
@@ -1320,7 +1309,7 @@ void drm_plane_force_disable(struct drm_plane *plane)
                 return;
         }
         /* disconnect the plane from the fb and crtc: */
-        __drm_framebuffer_unreference(plane->old_fb);
+        drm_framebuffer_unreference(plane->old_fb);
         plane->old_fb = NULL;
         plane->fb = NULL;
         plane->crtc = NULL;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5b205863b659..27ea6bdebce7 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2737,24 +2737,11 @@ i915_gem_retire_requests_ring(struct intel_engine_cs *ring)
 
         WARN_ON(i915_verify_lists(ring->dev));
 
-        /* Move any buffers on the active list that are no longer referenced
-         * by the ringbuffer to the flushing/inactive lists as appropriate,
-         * before we free the context associated with the requests.
+        /* Retire requests first as we use it above for the early return.
+         * If we retire requests last, we may use a later seqno and so clear
+         * the requests lists without clearing the active list, leading to
+         * confusion.
          */
-        while (!list_empty(&ring->active_list)) {
-                struct drm_i915_gem_object *obj;
-
-                obj = list_first_entry(&ring->active_list,
-                                      struct drm_i915_gem_object,
-                                      ring_list);
-
-                if (!i915_gem_request_completed(obj->last_read_req, true))
-                        break;
-
-                i915_gem_object_move_to_inactive(obj);
-        }
-
-
         while (!list_empty(&ring->request_list)) {
                 struct drm_i915_gem_request *request;
                 struct intel_ringbuffer *ringbuf;
@@ -2789,6 +2776,23 @@ i915_gem_retire_requests_ring(struct intel_engine_cs *ring)
                 i915_gem_free_request(request);
         }
 
+        /* Move any buffers on the active list that are no longer referenced
+         * by the ringbuffer to the flushing/inactive lists as appropriate,
+         * before we free the context associated with the requests.
+         */
+        while (!list_empty(&ring->active_list)) {
+                struct drm_i915_gem_object *obj;
+
+                obj = list_first_entry(&ring->active_list,
+                                      struct drm_i915_gem_object,
+                                      ring_list);
+
+                if (!i915_gem_request_completed(obj->last_read_req, true))
+                        break;
+
+                i915_gem_object_move_to_inactive(obj);
+        }
+
         if (unlikely(ring->trace_irq_req &&
                      i915_gem_request_completed(ring->trace_irq_req, true))) {
                 ring->irq_put(ring);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 6d22128d97b1..f75173c20f47 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2438,8 +2438,15 @@ intel_find_plane_obj(struct intel_crtc *intel_crtc,
         if (!intel_crtc->base.primary->fb)
                 return;
 
-        if (intel_alloc_plane_obj(intel_crtc, plane_config))
+        if (intel_alloc_plane_obj(intel_crtc, plane_config)) {
+                struct drm_plane *primary = intel_crtc->base.primary;
+
+                primary->state->crtc = &intel_crtc->base;
+                primary->crtc = &intel_crtc->base;
+                update_state_fb(primary);
+
                 return;
+        }
 
         kfree(intel_crtc->base.primary->fb);
         intel_crtc->base.primary->fb = NULL;
@@ -2462,11 +2469,15 @@ intel_find_plane_obj(struct intel_crtc *intel_crtc,
                         continue;
 
                 if (i915_gem_obj_ggtt_offset(obj) == plane_config->base) {
+                        struct drm_plane *primary = intel_crtc->base.primary;
+
                         if (obj->tiling_mode != I915_TILING_NONE)
                                 dev_priv->preserve_bios_swizzle = true;
 
                         drm_framebuffer_reference(c->primary->fb);
-                        intel_crtc->base.primary->fb = c->primary->fb;
+                        primary->fb = c->primary->fb;
+                        primary->state->crtc = &intel_crtc->base;
+                        primary->crtc = &intel_crtc->base;
                         obj->frontbuffer_bits |= INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe);
                         break;
                 }
@@ -6663,7 +6674,6 @@ i9xx_get_initial_plane_config(struct intel_crtc *crtc,
                       plane_config->size);
 
         crtc->base.primary->fb = fb;
-        update_state_fb(crtc->base.primary);
 }
 
 static void chv_crtc_clock_get(struct intel_crtc *crtc,
@@ -7704,7 +7714,6 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc,
                       plane_config->size);
 
         crtc->base.primary->fb = fb;
-        update_state_fb(crtc->base.primary);
         return;
 
 error:
@@ -7798,7 +7807,6 @@ ironlake_get_initial_plane_config(struct intel_crtc *crtc,
                       plane_config->size);
 
         crtc->base.primary->fb = fb;
-        update_state_fb(crtc->base.primary);
 }
 
 static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 9b641b38b857..8001fe9e3434 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -433,7 +433,6 @@ static int dm_blk_open(struct block_device *bdev, fmode_t mode)
 
         dm_get(md);
         atomic_inc(&md->open_count);
-
 out:
         spin_unlock(&_minor_lock);
 
@@ -442,16 +441,20 @@ out:
 
 static void dm_blk_close(struct gendisk *disk, fmode_t mode)
 {
-        struct mapped_device *md = disk->private_data;
+        struct mapped_device *md;
 
         spin_lock(&_minor_lock);
 
+        md = disk->private_data;
+        if (WARN_ON(!md))
+                goto out;
+
         if (atomic_dec_and_test(&md->open_count) &&
             (test_bit(DMF_DEFERRED_REMOVE, &md->flags)))
                 queue_work(deferred_remove_workqueue, &deferred_remove_work);
 
         dm_put(md);
-
+out:
         spin_unlock(&_minor_lock);
 }
 
@@ -2241,7 +2244,6 @@ static void free_dev(struct mapped_device *md)
         int minor = MINOR(disk_devt(md->disk));
 
         unlock_fs(md);
-        bdput(md->bdev);
         destroy_workqueue(md->wq);
 
         if (md->kworker_task)
@@ -2252,19 +2254,22 @@ static void free_dev(struct mapped_device *md)
                 mempool_destroy(md->rq_pool);
         if (md->bs)
                 bioset_free(md->bs);
-        blk_integrity_unregister(md->disk);
-        del_gendisk(md->disk);
+
         cleanup_srcu_struct(&md->io_barrier);
         free_table_devices(&md->table_devices);
-        free_minor(minor);
+        dm_stats_cleanup(&md->stats);
 
         spin_lock(&_minor_lock);
         md->disk->private_data = NULL;
         spin_unlock(&_minor_lock);
-
+        if (blk_get_integrity(md->disk))
+                blk_integrity_unregister(md->disk);
+        del_gendisk(md->disk);
         put_disk(md->disk);
         blk_cleanup_queue(md->queue);
-        dm_stats_cleanup(&md->stats);
+        bdput(md->bdev);
+        free_minor(minor);
+
         module_put(THIS_MODULE);
         kfree(md);
 }
@@ -2642,8 +2647,9 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
 
         might_sleep();
 
-        spin_lock(&_minor_lock);
         map = dm_get_live_table(md, &srcu_idx);
+
+        spin_lock(&_minor_lock);
         idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md))));
         set_bit(DMF_FREEING, &md->flags);
         spin_unlock(&_minor_lock);
diff --git a/drivers/mfd/kempld-core.c b/drivers/mfd/kempld-core.c
index f38ec424872e..5615522f8d62 100644
--- a/drivers/mfd/kempld-core.c
+++ b/drivers/mfd/kempld-core.c
@@ -739,7 +739,7 @@ static int __init kempld_init(void)
                 for (id = kempld_dmi_table;
                      id->matches[0].slot != DMI_NONE; id++)
                         if (strstr(id->ident, force_device_id))
-                                if (id->callback && id->callback(id))
+                                if (id->callback && !id->callback(id))
                                         break;
                 if (id->matches[0].slot == DMI_NONE)
                         return -ENODEV;
diff --git a/drivers/mfd/rtsx_usb.c b/drivers/mfd/rtsx_usb.c
index ede50244f265..dbd907d7170e 100644
--- a/drivers/mfd/rtsx_usb.c
+++ b/drivers/mfd/rtsx_usb.c
@@ -196,18 +196,27 @@ EXPORT_SYMBOL_GPL(rtsx_usb_ep0_write_register);
 int rtsx_usb_ep0_read_register(struct rtsx_ucr *ucr, u16 addr, u8 *data)
 {
         u16 value;
+        u8 *buf;
+        int ret;
 
         if (!data)
                 return -EINVAL;
-        *data = 0;
+
+        buf = kzalloc(sizeof(u8), GFP_KERNEL);
+        if (!buf)
+                return -ENOMEM;
 
         addr |= EP0_READ_REG_CMD << EP0_OP_SHIFT;
         value = swab16(addr);
 
-        return usb_control_msg(ucr->pusb_dev,
+        ret = usb_control_msg(ucr->pusb_dev,
                         usb_rcvctrlpipe(ucr->pusb_dev, 0), RTSX_USB_REQ_REG_OP,
                         USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-                        value, 0, data, 1, 100);
+                        value, 0, buf, 1, 100);
+        *data = *buf;
+
+        kfree(buf);
+        return ret;
 }
 EXPORT_SYMBOL_GPL(rtsx_usb_ep0_read_register);
 
@@ -288,18 +297,27 @@ static int rtsx_usb_get_status_with_bulk(struct rtsx_ucr *ucr, u16 *status)
 int rtsx_usb_get_card_status(struct rtsx_ucr *ucr, u16 *status)
 {
         int ret;
+        u16 *buf;
 
         if (!status)
                 return -EINVAL;
 
-        if (polling_pipe == 0)
+        if (polling_pipe == 0) {
+                buf = kzalloc(sizeof(u16), GFP_KERNEL);
+                if (!buf)
+                        return -ENOMEM;
+
                 ret = usb_control_msg(ucr->pusb_dev,
                                 usb_rcvctrlpipe(ucr->pusb_dev, 0),
                                 RTSX_USB_REQ_POLL,
                                 USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-                                0, 0, status, 2, 100);
-        else
+                                0, 0, buf, 2, 100);
+                *status = *buf;
+
+                kfree(buf);
+        } else {
                 ret = rtsx_usb_get_status_with_bulk(ucr, status);
+        }
 
         /* usb_control_msg may return positive when success */
         if (ret < 0)
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index 11d6e6561df1..15a8190a6f75 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -1543,7 +1543,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
 {
         struct pcnet32_private *lp;
         int i, media;
-        int fdx, mii, fset, dxsuflo;
+        int fdx, mii, fset, dxsuflo, sram;
         int chip_version;
         char *chipname;
         struct net_device *dev;
@@ -1580,7 +1580,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
         }
 
         /* initialize variables */
-        fdx = mii = fset = dxsuflo = 0;
+        fdx = mii = fset = dxsuflo = sram = 0;
         chip_version = (chip_version >> 12) & 0xffff;
 
         switch (chip_version) {
@@ -1613,6 +1613,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
                 chipname = "PCnet/FAST III 79C973";     /* PCI */
                 fdx = 1;
                 mii = 1;
+                sram = 1;
                 break;
         case 0x2626:
                 chipname = "PCnet/Home 79C978"; /* PCI */
@@ -1636,6 +1637,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
                 chipname = "PCnet/FAST III 79C975";     /* PCI */
                 fdx = 1;
                 mii = 1;
+                sram = 1;
                 break;
         case 0x2628:
                 chipname = "PCnet/PRO 79C976";
@@ -1664,6 +1666,31 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev)
                 dxsuflo = 1;
         }
 
+        /*
+         * The Am79C973/Am79C975 controllers come with 12K of SRAM
+         * which we can use for the Tx/Rx buffers but most importantly,
+         * the use of SRAM allow us to use the BCR18:NOUFLO bit to avoid
+         * Tx fifo underflows.
+         */
+        if (sram) {
+                /*
+                 * The SRAM is being configured in two steps. First we
+                 * set the SRAM size in the BCR25:SRAM_SIZE bits. According
+                 * to the datasheet, each bit corresponds to a 512-byte
+                 * page so we can have at most 24 pages. The SRAM_SIZE
+                 * holds the value of the upper 8 bits of the 16-bit SRAM size.
+                 * The low 8-bits start at 0x00 and end at 0xff. So the
+                 * address range is from 0x0000 up to 0x17ff. Therefore,
+                 * the SRAM_SIZE is set to 0x17. The next step is to set
+                 * the BCR26:SRAM_BND midway through so the Tx and Rx
+                 * buffers can share the SRAM equally.
+                 */
+                a->write_bcr(ioaddr, 25, 0x17);
+                a->write_bcr(ioaddr, 26, 0xc);
+                /* And finally enable the NOUFLO bit */
+                a->write_bcr(ioaddr, 18, a->read_bcr(ioaddr, 18) | (1 << 11));
+        }
+
         dev = alloc_etherdev(sizeof(*lp));
         if (!dev) {
                 ret = -ENOMEM;
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 27de37aa90af..27b9fe99a9bd 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -354,6 +354,7 @@ struct be_vf_cfg {
         u16 vlan_tag;
         u32 tx_rate;
         u32 plink_tracking;
+        u32 privileges;
 };
 
 enum vf_state {
@@ -423,6 +424,7 @@ struct be_adapter {
 
         u8 __iomem *csr;        /* CSR BAR used only for BE2/3 */
         u8 __iomem *db;         /* Door Bell */
+        u8 __iomem *pcicfg;     /* On SH,BEx only. Shadow of PCI config space */
 
         struct mutex mbox_lock; /* For serializing mbox cmds to BE card */
         struct be_dma_mem mbox_mem;
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 36916cfa70f9..7f05f309e935 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1902,15 +1902,11 @@ int be_cmd_modify_eqd(struct be_adapter *adapter, struct be_set_eqd *set_eqd,
 {
         int num_eqs, i = 0;
 
-        if (lancer_chip(adapter) && num > 8) {
-                while (num) {
-                        num_eqs = min(num, 8);
-                        __be_cmd_modify_eqd(adapter, &set_eqd[i], num_eqs);
-                        i += num_eqs;
-                        num -= num_eqs;
-                }
-        } else {
-                __be_cmd_modify_eqd(adapter, set_eqd, num);
+        while (num) {
+                num_eqs = min(num, 8);
+                __be_cmd_modify_eqd(adapter, &set_eqd[i], num_eqs);
+                i += num_eqs;
+                num -= num_eqs;
         }
 
         return 0;
@@ -1918,7 +1914,7 @@ int be_cmd_modify_eqd(struct be_adapter *adapter, struct be_set_eqd *set_eqd,
 
 /* Uses sycnhronous mcc */
 int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
-                       u32 num)
+                       u32 num, u32 domain)
 {
         struct be_mcc_wrb *wrb;
         struct be_cmd_req_vlan_config *req;
@@ -1936,6 +1932,7 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
         be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
                                OPCODE_COMMON_NTWK_VLAN_CONFIG, sizeof(*req),
                                wrb, NULL);
+        req->hdr.domain = domain;
 
         req->interface_id = if_id;
         req->untagged = BE_IF_FLAGS_UNTAGGED & be_if_cap_flags(adapter) ? 1 : 0;
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index db761e8e42a3..a7634a3f052a 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -2256,7 +2256,7 @@ int lancer_cmd_get_pport_stats(struct be_adapter *adapter,
 int be_cmd_get_fw_ver(struct be_adapter *adapter);
 int be_cmd_modify_eqd(struct be_adapter *adapter, struct be_set_eqd *, int num);
 int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
-                       u32 num);
+                       u32 num, u32 domain);
 int be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 status);
 int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc);
 int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc);
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 0a816859aca5..e6b790f0d9dc 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1171,7 +1171,7 @@ static int be_vid_config(struct be_adapter *adapter)
         for_each_set_bit(i, adapter->vids, VLAN_N_VID)
                 vids[num++] = cpu_to_le16(i);
 
-        status = be_cmd_vlan_config(adapter, adapter->if_handle, vids, num);
+        status = be_cmd_vlan_config(adapter, adapter->if_handle, vids, num, 0);
         if (status) {
                 dev_err(dev, "Setting HW VLAN filtering failed\n");
                 /* Set to VLAN promisc mode as setting VLAN filter failed */
@@ -1380,11 +1380,67 @@ static int be_get_vf_config(struct net_device *netdev, int vf,
         return 0;
 }
 
+static int be_set_vf_tvt(struct be_adapter *adapter, int vf, u16 vlan)
+{
+        struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf];
+        u16 vids[BE_NUM_VLANS_SUPPORTED];
+        int vf_if_id = vf_cfg->if_handle;
+        int status;
+
+        /* Enable Transparent VLAN Tagging */
+        status = be_cmd_set_hsw_config(adapter, vlan, vf + 1, vf_if_id, 0);
+        if (status)
+                return status;
+
+        /* Clear pre-programmed VLAN filters on VF if any, if TVT is enabled */
+        vids[0] = 0;
+        status = be_cmd_vlan_config(adapter, vf_if_id, vids, 1, vf + 1);
+        if (!status)
+                dev_info(&adapter->pdev->dev,
+                         "Cleared guest VLANs on VF%d", vf);
+
+        /* After TVT is enabled, disallow VFs to program VLAN filters */
+        if (vf_cfg->privileges & BE_PRIV_FILTMGMT) {
+                status = be_cmd_set_fn_privileges(adapter, vf_cfg->privileges &
+                                                  ~BE_PRIV_FILTMGMT, vf + 1);
+                if (!status)
+                        vf_cfg->privileges &= ~BE_PRIV_FILTMGMT;
+        }
+        return 0;
+}
+
+static int be_clear_vf_tvt(struct be_adapter *adapter, int vf)
+{
+        struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf];
+        struct device *dev = &adapter->pdev->dev;
+        int status;
+
+        /* Reset Transparent VLAN Tagging. */
+        status = be_cmd_set_hsw_config(adapter, BE_RESET_VLAN_TAG_ID, vf + 1,
+                                       vf_cfg->if_handle, 0);
+        if (status)
+                return status;
+
+        /* Allow VFs to program VLAN filtering */
+        if (!(vf_cfg->privileges & BE_PRIV_FILTMGMT)) {
+                status = be_cmd_set_fn_privileges(adapter, vf_cfg->privileges |
+                                                  BE_PRIV_FILTMGMT, vf + 1);
+                if (!status) {
+                        vf_cfg->privileges |= BE_PRIV_FILTMGMT;
+                        dev_info(dev, "VF%d: FILTMGMT priv enabled", vf);
+                }
+        }
+
+        dev_info(dev,
+                 "Disable/re-enable i/f in VM to clear Transparent VLAN tag");
+        return 0;
+}
+
 static int be_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos)
 {
         struct be_adapter *adapter = netdev_priv(netdev);
         struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf];
-        int status = 0;
+        int status;
 
         if (!sriov_enabled(adapter))
                 return -EPERM;
@@ -1394,24 +1450,19 @@ static int be_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos)
 
         if (vlan || qos) {
                 vlan |= qos << VLAN_PRIO_SHIFT;
-                if (vf_cfg->vlan_tag != vlan)
-                        status = be_cmd_set_hsw_config(adapter, vlan, vf + 1,
-                                                       vf_cfg->if_handle, 0);
+                status = be_set_vf_tvt(adapter, vf, vlan);
         } else {
-                /* Reset Transparent Vlan Tagging. */
-                status = be_cmd_set_hsw_config(adapter, BE_RESET_VLAN_TAG_ID,
-                                               vf + 1, vf_cfg->if_handle, 0);
+                status = be_clear_vf_tvt(adapter, vf);
         }
 
         if (status) {
                 dev_err(&adapter->pdev->dev,
-                        "VLAN %d config on VF %d failed : %#x\n", vlan,
-                        vf, status);
+                        "VLAN %d config on VF %d failed : %#x\n", vlan, vf,
+                        status);
                 return be_cmd_status(status);
         }
 
         vf_cfg->vlan_tag = vlan;
-
         return 0;
 }
 
@@ -2772,14 +2823,12 @@ void be_detect_error(struct be_adapter *adapter)
                         }
                 }
         } else {
-                pci_read_config_dword(adapter->pdev,
-                                      PCICFG_UE_STATUS_LOW, &ue_lo);
-                pci_read_config_dword(adapter->pdev,
-                                      PCICFG_UE_STATUS_HIGH, &ue_hi);
-                pci_read_config_dword(adapter->pdev,
-                                      PCICFG_UE_STATUS_LOW_MASK, &ue_lo_mask);
-                pci_read_config_dword(adapter->pdev,
-                                      PCICFG_UE_STATUS_HI_MASK, &ue_hi_mask);
+                ue_lo = ioread32(adapter->pcicfg + PCICFG_UE_STATUS_LOW);
+                ue_hi = ioread32(adapter->pcicfg + PCICFG_UE_STATUS_HIGH);
+                ue_lo_mask = ioread32(adapter->pcicfg +
+                                      PCICFG_UE_STATUS_LOW_MASK);
+                ue_hi_mask = ioread32(adapter->pcicfg +
+                                      PCICFG_UE_STATUS_HI_MASK);
 
                 ue_lo = (ue_lo & ~ue_lo_mask);
                 ue_hi = (ue_hi & ~ue_hi_mask);
@@ -3339,7 +3388,6 @@ static int be_if_create(struct be_adapter *adapter, u32 *if_handle,
                         u32 cap_flags, u32 vf)
 {
         u32 en_flags;
-        int status;
 
         en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
                    BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS |
@@ -3347,10 +3395,7 @@ static int be_if_create(struct be_adapter *adapter, u32 *if_handle,
 
         en_flags &= cap_flags;
 
-        status = be_cmd_if_create(adapter, cap_flags, en_flags,
-                                  if_handle, vf);
-
-        return status;
+        return be_cmd_if_create(adapter, cap_flags, en_flags, if_handle, vf);
 }
 
 static int be_vfs_if_create(struct be_adapter *adapter)
@@ -3368,8 +3413,13 @@ static int be_vfs_if_create(struct be_adapter *adapter)
                 if (!BE3_chip(adapter)) {
                         status = be_cmd_get_profile_config(adapter, &res,
                                                            vf + 1);
-                        if (!status)
+                        if (!status) {
                                 cap_flags = res.if_cap_flags;
+                                /* Prevent VFs from enabling VLAN promiscuous
+                                 * mode
+                                 */
+                                cap_flags &= ~BE_IF_FLAGS_VLAN_PROMISCUOUS;
+                        }
                 }
 
                 status = be_if_create(adapter, &vf_cfg->if_handle,
@@ -3403,7 +3453,6 @@ static int be_vf_setup(struct be_adapter *adapter)
         struct device *dev = &adapter->pdev->dev;
         struct be_vf_cfg *vf_cfg;
         int status, old_vfs, vf;
-        u32 privileges;
 
         old_vfs = pci_num_vf(adapter->pdev);
 
@@ -3433,15 +3482,18 @@ static int be_vf_setup(struct be_adapter *adapter)
 
         for_all_vfs(adapter, vf_cfg, vf) {
                 /* Allow VFs to programs MAC/VLAN filters */
-                status = be_cmd_get_fn_privileges(adapter, &privileges, vf + 1);
-                if (!status && !(privileges & BE_PRIV_FILTMGMT)) {
+                status = be_cmd_get_fn_privileges(adapter, &vf_cfg->privileges,
+                                                  vf + 1);
+                if (!status && !(vf_cfg->privileges & BE_PRIV_FILTMGMT)) {
                         status = be_cmd_set_fn_privileges(adapter,
-                                                          privileges |
+                                                          vf_cfg->privileges |
                                                           BE_PRIV_FILTMGMT,
                                                           vf + 1);
-                        if (!status)
+                        if (!status) {
+                                vf_cfg->privileges |= BE_PRIV_FILTMGMT;
                                 dev_info(dev, "VF%d has FILTMGMT privilege\n",
                                          vf);
+                        }
                 }
 
                 /* Allow full available bandwidth */
@@ -4820,24 +4872,37 @@ static int be_roce_map_pci_bars(struct be_adapter *adapter)
 
 static int be_map_pci_bars(struct be_adapter *adapter)
 {
+        struct pci_dev *pdev = adapter->pdev;
         u8 __iomem *addr;
 
         if (BEx_chip(adapter) && be_physfn(adapter)) {
-                adapter->csr = pci_iomap(adapter->pdev, 2, 0);
+                adapter->csr = pci_iomap(pdev, 2, 0);
                 if (!adapter->csr)
                         return -ENOMEM;
         }
 
-        addr = pci_iomap(adapter->pdev, db_bar(adapter), 0);
+        addr = pci_iomap(pdev, db_bar(adapter), 0);
         if (!addr)
                 goto pci_map_err;
         adapter->db = addr;
 
+        if (skyhawk_chip(adapter) || BEx_chip(adapter)) {
+                if (be_physfn(adapter)) {
+                        /* PCICFG is the 2nd BAR in BE2 */
+                        addr = pci_iomap(pdev, BE2_chip(adapter) ? 1 : 0, 0);
+                        if (!addr)
+                                goto pci_map_err;
+                        adapter->pcicfg = addr;
+                } else {
+                        adapter->pcicfg = adapter->db + SRIOV_VF_PCICFG_OFFSET;
+                }
+        }
+
         be_roce_map_pci_bars(adapter);
         return 0;
 
 pci_map_err:
-        dev_err(&adapter->pdev->dev, "Error in mapping PCI BARs\n");
+        dev_err(&pdev->dev, "Error in mapping PCI BARs\n");
         be_unmap_pci_bars(adapter);
         return -ENOMEM;
 }
diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c
index fe48f4c51373..1762ad3910b2 100644
--- a/drivers/net/usb/cx82310_eth.c
+++ b/drivers/net/usb/cx82310_eth.c
@@ -46,8 +46,7 @@ enum cx82310_status {
 };
 
 #define CMD_PACKET_SIZE 64
-/* first command after power on can take around 8 seconds */
-#define CMD_TIMEOUT     15000
+#define CMD_TIMEOUT     100
 #define CMD_REPLY_RETRY 5
 
 #define CX82310_MTU     1514
@@ -78,8 +77,9 @@ static int cx82310_cmd(struct usbnet *dev, enum cx82310_cmd cmd, bool reply,
         ret = usb_bulk_msg(udev, usb_sndbulkpipe(udev, CMD_EP), buf,
                            CMD_PACKET_SIZE, &actual_len, CMD_TIMEOUT);
         if (ret < 0) {
-                dev_err(&dev->udev->dev, "send command %#x: error %d\n",
-                        cmd, ret);
+                if (cmd != CMD_GET_LINK_STATUS)
+                        dev_err(&dev->udev->dev, "send command %#x: error %d\n",
+                                cmd, ret);
                 goto end;
         }
 
@@ -90,8 +90,10 @@ static int cx82310_cmd(struct usbnet *dev, enum cx82310_cmd cmd, bool reply,
                                            buf, CMD_PACKET_SIZE, &actual_len,
                                            CMD_TIMEOUT);
                         if (ret < 0) {
-                                dev_err(&dev->udev->dev,
-                                        "reply receive error %d\n", ret);
+                                if (cmd != CMD_GET_LINK_STATUS)
+                                        dev_err(&dev->udev->dev,
+                                                "reply receive error %d\n",
+                                                ret);
                                 goto end;
                         }
                         if (actual_len > 0)
@@ -134,6 +136,8 @@ static int cx82310_bind(struct usbnet *dev, struct usb_interface *intf)
         int ret;
         char buf[15];
         struct usb_device *udev = dev->udev;
+        u8 link[3];
+        int timeout = 50;
 
         /* avoid ADSL modems - continue only if iProduct is "USB NET CARD" */
         if (usb_string(udev, udev->descriptor.iProduct, buf, sizeof(buf)) > 0
@@ -160,6 +164,20 @@ static int cx82310_bind(struct usbnet *dev, struct usb_interface *intf)
         if (!dev->partial_data)
                 return -ENOMEM;
 
+        /* wait for firmware to become ready (indicated by the link being up) */
+        while (--timeout) {
+                ret = cx82310_cmd(dev, CMD_GET_LINK_STATUS, true, NULL, 0,
+                                  link, sizeof(link));
+                /* the command can time out during boot - it's not an error */
+                if (!ret && link[0] == 1 && link[2] == 1)
+                        break;
+                msleep(500);
+        };
+        if (!timeout) {
+                dev_err(&udev->dev, "firmware not ready in time\n");
+                return -ETIMEDOUT;
+        }
+
         /* enable ethernet mode (?) */
         ret = cx82310_cmd(dev, CMD_ETHERNET_MODE, true, "\x01", 1, NULL, 0);
         if (ret) {
diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c
index 9205f433573c..18198316b6cf 100644
--- a/drivers/regulator/palmas-regulator.c
+++ b/drivers/regulator/palmas-regulator.c
@@ -1572,6 +1572,10 @@ static int palmas_regulators_probe(struct platform_device *pdev)
         if (!pmic)
                 return -ENOMEM;
 
+        if (of_device_is_compatible(node, "ti,tps659038-pmic"))
+                palmas_generic_regs_info[PALMAS_REG_REGEN2].ctrl_addr =
+                                                        TPS659038_REGEN2_CTRL;
+
         pmic->dev = &pdev->dev;
         pmic->palmas = palmas;
         palmas->pmic = pmic;
diff --git a/drivers/rtc/rtc-mrst.c b/drivers/rtc/rtc-mrst.c
index e2436d140175..3a6fd3a8a2ec 100644
--- a/drivers/rtc/rtc-mrst.c
+++ b/drivers/rtc/rtc-mrst.c
@@ -413,8 +413,8 @@ static void rtc_mrst_do_remove(struct device *dev)
         mrst->dev = NULL;
 }
 
-#ifdef  CONFIG_PM
-static int mrst_suspend(struct device *dev, pm_message_t mesg)
+#ifdef CONFIG_PM_SLEEP
+static int mrst_suspend(struct device *dev)
 {
         struct mrst_rtc *mrst = dev_get_drvdata(dev);
         unsigned char   tmp;
@@ -453,7 +453,7 @@ static int mrst_suspend(struct device *dev, pm_message_t mesg)
  */
 static inline int mrst_poweroff(struct device *dev)
 {
-        return mrst_suspend(dev, PMSG_HIBERNATE);
+        return mrst_suspend(dev);
 }
 
 static int mrst_resume(struct device *dev)
@@ -490,9 +490,11 @@ static int mrst_resume(struct device *dev)
         return 0;
 }
 
+static SIMPLE_DEV_PM_OPS(mrst_pm_ops, mrst_suspend, mrst_resume);
+#define MRST_PM_OPS (&mrst_pm_ops)
+
 #else
-#define mrst_suspend    NULL
-#define mrst_resume     NULL
+#define MRST_PM_OPS NULL
 
 static inline int mrst_poweroff(struct device *dev)
 {
@@ -529,9 +531,8 @@ static struct platform_driver vrtc_mrst_platform_driver = {
         .remove         = vrtc_mrst_platform_remove,
         .shutdown       = vrtc_mrst_platform_shutdown,
         .driver = {
-                .name           = (char *) driver_name,
-                .suspend        = mrst_suspend,
-                .resume         = mrst_resume,
+                .name   = driver_name,
+                .pm     = MRST_PM_OPS,
         }
 };
 
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 9219953ee949..d9afc51af7d3 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -6815,7 +6815,8 @@ static struct ata_port_operations ipr_sata_ops = {
 };
 
 static struct ata_port_info sata_port_info = {
-        .flags          = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA,
+        .flags          = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA |
+                          ATA_FLAG_SAS_HOST,
         .pio_mask       = ATA_PIO4_ONLY,
         .mwdma_mask     = ATA_MWDMA2,
         .udma_mask      = ATA_UDMA6,
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 932d9cc98d2f..9c706d8c1441 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -547,7 +547,8 @@ static struct ata_port_operations sas_sata_ops = {
 };
 
 static struct ata_port_info sata_port_info = {
-        .flags = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ,
+        .flags = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | ATA_FLAG_NCQ |
+                 ATA_FLAG_SAS_HOST,
         .pio_mask = ATA_PIO4,
         .mwdma_mask = ATA_MWDMA2,
         .udma_mask = ATA_UDMA6,
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index 3ce39d10fafb..4f8c798e0633 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -108,7 +108,8 @@ static void dw_spi_dma_tx_done(void *arg)
 {
         struct dw_spi *dws = arg;
 
-        if (test_and_clear_bit(TX_BUSY, &dws->dma_chan_busy) & BIT(RX_BUSY))
+        clear_bit(TX_BUSY, &dws->dma_chan_busy);
+        if (test_bit(RX_BUSY, &dws->dma_chan_busy))
                 return;
         dw_spi_xfer_done(dws);
 }
@@ -156,7 +157,8 @@ static void dw_spi_dma_rx_done(void *arg)
 {
         struct dw_spi *dws = arg;
 
-        if (test_and_clear_bit(RX_BUSY, &dws->dma_chan_busy) & BIT(TX_BUSY))
+        clear_bit(RX_BUSY, &dws->dma_chan_busy);
+        if (test_bit(TX_BUSY, &dws->dma_chan_busy))
                 return;
         dw_spi_xfer_done(dws);
 }
diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c
index ff9cdbdb6672..2b2c359f5a50 100644
--- a/drivers/spi/spi-qup.c
+++ b/drivers/spi/spi-qup.c
@@ -498,7 +498,7 @@ static int spi_qup_probe(struct platform_device *pdev)
         struct resource *res;
         struct device *dev;
         void __iomem *base;
-        u32 max_freq, iomode;
+        u32 max_freq, iomode, num_cs;
         int ret, irq, size;
 
         dev = &pdev->dev;
@@ -550,10 +550,11 @@ static int spi_qup_probe(struct platform_device *pdev)
         }
 
         /* use num-cs unless not present or out of range */
-        if (of_property_read_u16(dev->of_node, "num-cs",
-                        &master->num_chipselect) ||
-                        (master->num_chipselect > SPI_NUM_CHIPSELECTS))
+        if (of_property_read_u32(dev->of_node, "num-cs", &num_cs) ||
+            num_cs > SPI_NUM_CHIPSELECTS)
                 master->num_chipselect = SPI_NUM_CHIPSELECTS;
+        else
+                master->num_chipselect = num_cs;
 
         master->bus_num = pdev->id;
         master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LOOP;
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index c64a3e59fce3..57a195041dc7 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1105,13 +1105,14 @@ void spi_finalize_current_message(struct spi_master *master)
                                 "failed to unprepare message: %d\n", ret);
                 }
         }
+
+        trace_spi_message_done(mesg);
+
         master->cur_msg_prepared = false;
 
         mesg->state = NULL;
         if (mesg->complete)
                 mesg->complete(mesg->context);
-
-        trace_spi_message_done(mesg);
 }
 EXPORT_SYMBOL_GPL(spi_finalize_current_message);
 
diff --git a/drivers/watchdog/imgpdc_wdt.c b/drivers/watchdog/imgpdc_wdt.c
index c8def68d9e4c..0deaa4f971f5 100644
--- a/drivers/watchdog/imgpdc_wdt.c
+++ b/drivers/watchdog/imgpdc_wdt.c
@@ -42,10 +42,10 @@
 #define PDC_WDT_MIN_TIMEOUT             1
 #define PDC_WDT_DEF_TIMEOUT             64
 
-static int heartbeat;
+static int heartbeat = PDC_WDT_DEF_TIMEOUT;
 module_param(heartbeat, int, 0);
-MODULE_PARM_DESC(heartbeat, "Watchdog heartbeats in seconds. "
-        "(default = " __MODULE_STRING(PDC_WDT_DEF_TIMEOUT) ")");
+MODULE_PARM_DESC(heartbeat, "Watchdog heartbeats in seconds "
+        "(default=" __MODULE_STRING(PDC_WDT_DEF_TIMEOUT) ")");
 
 static bool nowayout = WATCHDOG_NOWAYOUT;
 module_param(nowayout, bool, 0);
@@ -191,6 +191,7 @@ static int pdc_wdt_probe(struct platform_device *pdev)
         pdc_wdt->wdt_dev.ops = &pdc_wdt_ops;
         pdc_wdt->wdt_dev.max_timeout = 1 << PDC_WDT_CONFIG_DELAY_MASK;
         pdc_wdt->wdt_dev.parent = &pdev->dev;
+        watchdog_set_drvdata(&pdc_wdt->wdt_dev, pdc_wdt);
 
         ret = watchdog_init_timeout(&pdc_wdt->wdt_dev, heartbeat, &pdev->dev);
         if (ret < 0) {
@@ -232,7 +233,6 @@ static int pdc_wdt_probe(struct platform_device *pdev)
         watchdog_set_nowayout(&pdc_wdt->wdt_dev, nowayout);
 
         platform_set_drvdata(pdev, pdc_wdt);
-        watchdog_set_drvdata(&pdc_wdt->wdt_dev, pdc_wdt);
 
         ret = watchdog_register_device(&pdc_wdt->wdt_dev);
         if (ret)
diff --git a/drivers/watchdog/mtk_wdt.c b/drivers/watchdog/mtk_wdt.c
index a87f6df6e85f..938b987de551 100644
--- a/drivers/watchdog/mtk_wdt.c
+++ b/drivers/watchdog/mtk_wdt.c
@@ -133,7 +133,7 @@ static int mtk_wdt_start(struct watchdog_device *wdt_dev)
         u32 reg;
         struct mtk_wdt_dev *mtk_wdt = watchdog_get_drvdata(wdt_dev);
         void __iomem *wdt_base = mtk_wdt->wdt_base;
-        u32 ret;
+        int ret;
 
         ret = mtk_wdt_set_timeout(wdt_dev, wdt_dev->timeout);
         if (ret < 0)
diff --git a/fs/affs/file.c b/fs/affs/file.c
index d2468bf95669..a91795e01a7f 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -699,8 +699,10 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
         boff = tmp % bsize;
         if (boff) {
                 bh = affs_bread_ino(inode, bidx, 0);
-                if (IS_ERR(bh))
-                        return PTR_ERR(bh);
+                if (IS_ERR(bh)) {
+                        written = PTR_ERR(bh);
+                        goto err_first_bh;
+                }
                 tmp = min(bsize - boff, to - from);
                 BUG_ON(boff + tmp > bsize || tmp > bsize);
                 memcpy(AFFS_DATA(bh) + boff, data + from, tmp);
@@ -712,14 +714,16 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
                 bidx++;
         } else if (bidx) {
                 bh = affs_bread_ino(inode, bidx - 1, 0);
-                if (IS_ERR(bh))
-                        return PTR_ERR(bh);
+                if (IS_ERR(bh)) {
+                        written = PTR_ERR(bh);
+                        goto err_first_bh;
+                }
         }
         while (from + bsize <= to) {
                 prev_bh = bh;
                 bh = affs_getemptyblk_ino(inode, bidx);
                 if (IS_ERR(bh))
-                        goto out;
+                        goto err_bh;
                 memcpy(AFFS_DATA(bh), data + from, bsize);
                 if (buffer_new(bh)) {
                         AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
@@ -751,7 +755,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
                 prev_bh = bh;
                 bh = affs_bread_ino(inode, bidx, 1);
                 if (IS_ERR(bh))
-                        goto out;
+                        goto err_bh;
                 tmp = min(bsize, to - from);
                 BUG_ON(tmp > bsize);
                 memcpy(AFFS_DATA(bh), data + from, tmp);
@@ -790,12 +794,13 @@ done:
         if (tmp > inode->i_size)
                 inode->i_size = AFFS_I(inode)->mmu_private = tmp;
 
+err_first_bh:
         unlock_page(page);
         page_cache_release(page);
 
         return written;
 
-out:
+err_bh:
         bh = prev_bh;
         if (!written)
                 written = PTR_ERR(bh);
diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c
index 6e560d56094b..754fdf8c6356 100644
--- a/fs/hfsplus/brec.c
+++ b/fs/hfsplus/brec.c
@@ -131,13 +131,16 @@ skip:
         hfs_bnode_write(node, entry, data_off + key_len, entry_len);
         hfs_bnode_dump(node);
 
-        if (new_node) {
-                /* update parent key if we inserted a key
-                 * at the start of the first node
-                 */
-                if (!rec && new_node != node)
-                        hfs_brec_update_parent(fd);
+        /*
+         * update parent key if we inserted a key
+         * at the start of the node and it is not the new node
+         */
+        if (!rec && new_node != node) {
+                hfs_bnode_read_key(node, fd->search_key, data_off + size);
+                hfs_brec_update_parent(fd);
+        }
 
+        if (new_node) {
                 hfs_bnode_put(fd->bnode);
                 if (!new_node->parent) {
                         hfs_btree_inc_height(tree);
@@ -168,9 +171,6 @@ skip:
                 goto again;
         }
 
-        if (!rec)
-                hfs_brec_update_parent(fd);
-
         return 0;
 }
 
@@ -370,6 +370,8 @@ again:
         if (IS_ERR(parent))
                 return PTR_ERR(parent);
         __hfs_brec_find(parent, fd, hfs_find_rec_by_key);
+        if (fd->record < 0)
+                return -ENOENT;
         hfs_bnode_dump(parent);
         rec = fd->record;
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index fc03efa64ffe..6b08cc106c21 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -232,6 +232,7 @@ enum {
                                               * led */
         ATA_FLAG_NO_DIPM        = (1 << 23), /* host not happy with DIPM */
         ATA_FLAG_LOWTAG         = (1 << 24), /* host wants lowest available tag */
+        ATA_FLAG_SAS_HOST       = (1 << 25), /* SAS host */
 
         /* bits 24:31 of ap->flags are reserved for LLD specific flags */
 
diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h
index fb0390a1a498..ee7b1ce7a6f8 100644
--- a/include/linux/mfd/palmas.h
+++ b/include/linux/mfd/palmas.h
@@ -2999,6 +2999,9 @@ enum usb_irq_events {
 #define PALMAS_GPADC_TRIM15                                     0x0E
 #define PALMAS_GPADC_TRIM16                                     0x0F
 
+/* TPS659038 regen2_ctrl offset iss different from palmas */
+#define TPS659038_REGEN2_CTRL                                   0x12
+
 /* TPS65917 Interrupt registers */
 
 /* Registers for function INTERRUPT */
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index d4ad5b5a02bb..045f709cb89b 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -316,7 +316,7 @@ struct regulator_desc {
  * @driver_data: private regulator data
  * @of_node: OpenFirmware node to parse for device tree bindings (may be
  *           NULL).
- * @regmap: regmap to use for core regmap helpers if dev_get_regulator() is
+ * @regmap: regmap to use for core regmap helpers if dev_get_regmap() is
  *          insufficient.
  * @ena_gpio_initialized: GPIO controlling regulator enable was properly
  *                        initialized, meaning that >= 0 is a valid gpio
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6d77432e14ff..a419b65770d6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1625,11 +1625,11 @@ struct task_struct {
 
         /*
          * numa_faults_locality tracks if faults recorded during the last
-         * scan window were remote/local. The task scan period is adapted
-         * based on the locality of the faults with different weights
-         * depending on whether they were shared or private faults
+         * scan window were remote/local or failed to migrate. The task scan
+         * period is adapted based on the locality of the faults with different
+         * weights depending on whether they were shared or private faults
          */
-        unsigned long numa_faults_locality[2];
+        unsigned long numa_faults_locality[3];
 
         unsigned long numa_pages_migrated;
 #endif /* CONFIG_NUMA_BALANCING */
@@ -1719,6 +1719,7 @@ struct task_struct {
 #define TNF_NO_GROUP    0x02
 #define TNF_SHARED      0x04
 #define TNF_FAULT_LOCAL 0x08
+#define TNF_MIGRATE_FAIL 0x10
 
 #ifdef CONFIG_NUMA_BALANCING
 extern void task_numa_fault(int last_node, int node, int pages, int flags);
diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h
index 534e1f2ac4fc..57639fca223a 100644
--- a/include/net/netfilter/nf_log.h
+++ b/include/net/netfilter/nf_log.h
@@ -79,6 +79,16 @@ void nf_log_packet(struct net *net,
                    const struct nf_loginfo *li,
                    const char *fmt, ...);
 
+__printf(8, 9)
+void nf_log_trace(struct net *net,
+                  u_int8_t pf,
+                  unsigned int hooknum,
+                  const struct sk_buff *skb,
+                  const struct net_device *in,
+                  const struct net_device *out,
+                  const struct nf_loginfo *li,
+                  const char *fmt, ...);
+
 struct nf_log_buf;
 
 struct nf_log_buf *nf_log_buf_open(void);
diff --git a/include/trace/events/regmap.h b/include/trace/events/regmap.h
index 23d561512f64..22317d2b52ab 100644
--- a/include/trace/events/regmap.h
+++ b/include/trace/events/regmap.h
@@ -7,27 +7,26 @@
 #include <linux/ktime.h>
 #include <linux/tracepoint.h>
 
-struct device;
-struct regmap;
+#include "../../../drivers/base/regmap/internal.h"
 
 /*
  * Log register events
  */
 DECLARE_EVENT_CLASS(regmap_reg,
 
-        TP_PROTO(struct device *dev, unsigned int reg,
+        TP_PROTO(struct regmap *map, unsigned int reg,
                  unsigned int val),
 
-        TP_ARGS(dev, reg, val),
+        TP_ARGS(map, reg, val),
 
         TP_STRUCT__entry(
-                __string(       name,           dev_name(dev)   )
-                __field(        unsigned int,   reg             )
-                __field(        unsigned int,   val             )
+                __string(       name,           regmap_name(map)        )
+                __field(        unsigned int,   reg                     )
+                __field(        unsigned int,   val                     )
         ),
 
         TP_fast_assign(
-                __assign_str(name, dev_name(dev));
+                __assign_str(name, regmap_name(map));
                 __entry->reg = reg;
                 __entry->val = val;
         ),
@@ -39,45 +38,45 @@ DECLARE_EVENT_CLASS(regmap_reg,
 
 DEFINE_EVENT(regmap_reg, regmap_reg_write,
 
-        TP_PROTO(struct device *dev, unsigned int reg,
+        TP_PROTO(struct regmap *map, unsigned int reg,
                  unsigned int val),
 
-        TP_ARGS(dev, reg, val)
+        TP_ARGS(map, reg, val)
 
 );
 
 DEFINE_EVENT(regmap_reg, regmap_reg_read,
 
-        TP_PROTO(struct device *dev, unsigned int reg,
+        TP_PROTO(struct regmap *map, unsigned int reg,
                  unsigned int val),
 
-        TP_ARGS(dev, reg, val)
+        TP_ARGS(map, reg, val)
 
 );
 
 DEFINE_EVENT(regmap_reg, regmap_reg_read_cache,
 
-        TP_PROTO(struct device *dev, unsigned int reg,
+        TP_PROTO(struct regmap *map, unsigned int reg,
                  unsigned int val),
 
-        TP_ARGS(dev, reg, val)
+        TP_ARGS(map, reg, val)
 
 );
 
 DECLARE_EVENT_CLASS(regmap_block,
 
-        TP_PROTO(struct device *dev, unsigned int reg, int count),
+        TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-        TP_ARGS(dev, reg, count),
+        TP_ARGS(map, reg, count),
 
         TP_STRUCT__entry(
-                __string(       name,           dev_name(dev)   )
-                __field(        unsigned int,   reg             )
-                __field(        int,            count           )
+                __string(       name,           regmap_name(map)        )
+                __field(        unsigned int,   reg                     )
+                __field(        int,            count                   )
         ),
 
         TP_fast_assign(
-                __assign_str(name, dev_name(dev));
+                __assign_str(name, regmap_name(map));
                 __entry->reg = reg;
                 __entry->count = count;
         ),
@@ -89,48 +88,48 @@ DECLARE_EVENT_CLASS(regmap_block,
 
 DEFINE_EVENT(regmap_block, regmap_hw_read_start,
 
-        TP_PROTO(struct device *dev, unsigned int reg, int count),
+        TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-        TP_ARGS(dev, reg, count)
+        TP_ARGS(map, reg, count)
 );
 
 DEFINE_EVENT(regmap_block, regmap_hw_read_done,
 
-        TP_PROTO(struct device *dev, unsigned int reg, int count),
+        TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-        TP_ARGS(dev, reg, count)
+        TP_ARGS(map, reg, count)
 );
 
 DEFINE_EVENT(regmap_block, regmap_hw_write_start,
 
-        TP_PROTO(struct device *dev, unsigned int reg, int count),
+        TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-        TP_ARGS(dev, reg, count)
+        TP_ARGS(map, reg, count)
 );
 
 DEFINE_EVENT(regmap_block, regmap_hw_write_done,
 
-        TP_PROTO(struct device *dev, unsigned int reg, int count),
+        TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-        TP_ARGS(dev, reg, count)
+        TP_ARGS(map, reg, count)
 );
 
 TRACE_EVENT(regcache_sync,
 
-        TP_PROTO(struct device *dev, const char *type,
+        TP_PROTO(struct regmap *map, const char *type,
                  const char *status),
 
-        TP_ARGS(dev, type, status),
+        TP_ARGS(map, type, status),
 
         TP_STRUCT__entry(
-                __string(       name,           dev_name(dev)   )
-                __string(       status,         status          )
-                __string(       type,           type            )
-                __field(        int,            type            )
+                __string(       name,           regmap_name(map)        )
+                __string(       status,         status                  )
+                __string(       type,           type                    )
+                __field(        int,            type                    )
         ),
 
         TP_fast_assign(
-                __assign_str(name, dev_name(dev));
+                __assign_str(name, regmap_name(map));
                 __assign_str(status, status);
                 __assign_str(type, type);
         ),
@@ -141,17 +140,17 @@ TRACE_EVENT(regcache_sync,
 
 DECLARE_EVENT_CLASS(regmap_bool,
 
-        TP_PROTO(struct device *dev, bool flag),
+        TP_PROTO(struct regmap *map, bool flag),
 
-        TP_ARGS(dev, flag),
+        TP_ARGS(map, flag),
 
         TP_STRUCT__entry(
-                __string(       name,           dev_name(dev)   )
-                __field(        int,            flag            )
+                __string(       name,           regmap_name(map)        )
+                __field(        int,            flag                    )
         ),
 
         TP_fast_assign(
-                __assign_str(name, dev_name(dev));
+                __assign_str(name, regmap_name(map));
                 __entry->flag = flag;
         ),
 
@@ -161,32 +160,32 @@ DECLARE_EVENT_CLASS(regmap_bool,
 
 DEFINE_EVENT(regmap_bool, regmap_cache_only,
 
-        TP_PROTO(struct device *dev, bool flag),
+        TP_PROTO(struct regmap *map, bool flag),
 
-        TP_ARGS(dev, flag)
+        TP_ARGS(map, flag)
 
 );
 
 DEFINE_EVENT(regmap_bool, regmap_cache_bypass,
 
-        TP_PROTO(struct device *dev, bool flag),
+        TP_PROTO(struct regmap *map, bool flag),
 
-        TP_ARGS(dev, flag)
+        TP_ARGS(map, flag)
 
 );
 
 DECLARE_EVENT_CLASS(regmap_async,
 
-        TP_PROTO(struct device *dev),
+        TP_PROTO(struct regmap *map),
 
-        TP_ARGS(dev),
+        TP_ARGS(map),
 
         TP_STRUCT__entry(
-                __string(       name,           dev_name(dev)   )
+                __string(       name,           regmap_name(map)        )
         ),
 
         TP_fast_assign(
-                __assign_str(name, dev_name(dev));
+                __assign_str(name, regmap_name(map));
         ),
 
         TP_printk("%s", __get_str(name))
@@ -194,50 +193,50 @@ DECLARE_EVENT_CLASS(regmap_async,
 
 DEFINE_EVENT(regmap_block, regmap_async_write_start,
 
-        TP_PROTO(struct device *dev, unsigned int reg, int count),
+        TP_PROTO(struct regmap *map, unsigned int reg, int count),
 
-        TP_ARGS(dev, reg, count)
+        TP_ARGS(map, reg, count)
 );
 
 DEFINE_EVENT(regmap_async, regmap_async_io_complete,
 
-        TP_PROTO(struct device *dev),
+        TP_PROTO(struct regmap *map),
 
-        TP_ARGS(dev)
+        TP_ARGS(map)
 
 );
 
 DEFINE_EVENT(regmap_async, regmap_async_complete_start,
 
-        TP_PROTO(struct device *dev),
+        TP_PROTO(struct regmap *map),
 
-        TP_ARGS(dev)
+        TP_ARGS(map)
 
 );
 
 DEFINE_EVENT(regmap_async, regmap_async_complete_done,
 
-        TP_PROTO(struct device *dev),
+        TP_PROTO(struct regmap *map),
 
-        TP_ARGS(dev)
+        TP_ARGS(map)
 
 );
 
 TRACE_EVENT(regcache_drop_region,
 
-        TP_PROTO(struct device *dev, unsigned int from,
+        TP_PROTO(struct regmap *map, unsigned int from,
                  unsigned int to),
 
-        TP_ARGS(dev, from, to),
+        TP_ARGS(map, from, to),
 
         TP_STRUCT__entry(
-                __string(       name,           dev_name(dev)   )
-                __field(        unsigned int,   from            )
-                __field(        unsigned int,   to              )
+                __string(       name,           regmap_name(map)        )
+                __field(        unsigned int,   from                    )
+                __field(        unsigned int,   to                      )
         ),
 
         TP_fast_assign(
-                __assign_str(name, dev_name(dev));
+                __assign_str(name, regmap_name(map));
                 __entry->from = from;
                 __entry->to = to;
         ),
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 453ef61311d4..2fabc0627165 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4574,6 +4574,13 @@ static void perf_pending_event(struct irq_work *entry)
 {
         struct perf_event *event = container_of(entry,
                         struct perf_event, pending);
+        int rctx;
+
+        rctx = perf_swevent_get_recursion_context();
+        /*
+         * If we 'fail' here, that's OK, it means recursion is already disabled
+         * and we won't recurse 'further'.
+         */
 
         if (event->pending_disable) {
                 event->pending_disable = 0;
@@ -4584,6 +4591,9 @@ static void perf_pending_event(struct irq_work *entry)
                 event->pending_wakeup = 0;
                 perf_event_wakeup(event);
         }
+
+        if (rctx >= 0)
+                perf_swevent_put_recursion_context(rctx);
 }
 
 /*
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 88d0d4420ad2..ba77ab5f64dd 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -633,7 +633,7 @@ static int count_matching_names(struct lock_class *new_class)
         if (!new_class->name)
                 return 0;
 
-        list_for_each_entry(class, &all_lock_classes, lock_entry) {
+        list_for_each_entry_rcu(class, &all_lock_classes, lock_entry) {
                 if (new_class->key - new_class->subclass == class->key)
                         return class->name_version;
                 if (class->name && !strcmp(class->name, new_class->name))
@@ -700,10 +700,12 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
         hash_head = classhashentry(key);
 
         /*
-         * We can walk the hash lockfree, because the hash only
-         * grows, and we are careful when adding entries to the end:
+         * We do an RCU walk of the hash, see lockdep_free_key_range().
          */
-        list_for_each_entry(class, hash_head, hash_entry) {
+        if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
+                return NULL;
+
+        list_for_each_entry_rcu(class, hash_head, hash_entry) {
                 if (class->key == key) {
                         /*
                          * Huh! same key, different name? Did someone trample
@@ -728,7 +730,8 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
         struct lockdep_subclass_key *key;
         struct list_head *hash_head;
         struct lock_class *class;
-        unsigned long flags;
+
+        DEBUG_LOCKS_WARN_ON(!irqs_disabled());
 
         class = look_up_lock_class(lock, subclass);
         if (likely(class))
@@ -750,28 +753,26 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
         key = lock->key->subkeys + subclass;
         hash_head = classhashentry(key);
 
-        raw_local_irq_save(flags);
         if (!graph_lock()) {
-                raw_local_irq_restore(flags);
                 return NULL;
         }
         /*
          * We have to do the hash-walk again, to avoid races
          * with another CPU:
          */
-        list_for_each_entry(class, hash_head, hash_entry)
+        list_for_each_entry_rcu(class, hash_head, hash_entry) {
                 if (class->key == key)
                         goto out_unlock_set;
+        }
+
         /*
          * Allocate a new key from the static array, and add it to
          * the hash:
          */
         if (nr_lock_classes >= MAX_LOCKDEP_KEYS) {
                 if (!debug_locks_off_graph_unlock()) {
-                        raw_local_irq_restore(flags);
                         return NULL;
                 }
-                raw_local_irq_restore(flags);
 
                 print_lockdep_off("BUG: MAX_LOCKDEP_KEYS too low!");
                 dump_stack();
@@ -798,7 +799,6 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 
         if (verbose(class)) {
                 graph_unlock();
-                raw_local_irq_restore(flags);
 
                 printk("\nnew class %p: %s", class->key, class->name);
                 if (class->name_version > 1)
@@ -806,15 +806,12 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
                 printk("\n");
                 dump_stack();
 
-                raw_local_irq_save(flags);
                 if (!graph_lock()) {
-                        raw_local_irq_restore(flags);
                         return NULL;
                 }
         }
 out_unlock_set:
         graph_unlock();
-        raw_local_irq_restore(flags);
 
 out_set_class_cache:
         if (!subclass || force)
@@ -870,11 +867,9 @@ static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
         entry->distance = distance;
         entry->trace = *trace;
         /*
-         * Since we never remove from the dependency list, the list can
-         * be walked lockless by other CPUs, it's only allocation
-         * that must be protected by the spinlock. But this also means
-         * we must make new entries visible only once writes to the
-         * entry become visible - hence the RCU op:
+         * Both allocation and removal are done under the graph lock; but
+         * iteration is under RCU-sched; see look_up_lock_class() and
+         * lockdep_free_key_range().
          */
         list_add_tail_rcu(&entry->entry, head);
 
@@ -1025,7 +1020,9 @@ static int __bfs(struct lock_list *source_entry,
                 else
                         head = &lock->class->locks_before;
 
-                list_for_each_entry(entry, head, entry) {
+                DEBUG_LOCKS_WARN_ON(!irqs_disabled());
+
+                list_for_each_entry_rcu(entry, head, entry) {
                         if (!lock_accessed(entry)) {
                                 unsigned int cq_depth;
                                 mark_lock_accessed(entry, lock);
@@ -2022,7 +2019,7 @@ static inline int lookup_chain_cache(struct task_struct *curr,
          * We can walk it lock-free, because entries only get added
          * to the hash:
          */
-        list_for_each_entry(chain, hash_head, entry) {
+        list_for_each_entry_rcu(chain, hash_head, entry) {
                 if (chain->chain_key == chain_key) {
 cache_hit:
                         debug_atomic_inc(chain_lookup_hits);
@@ -2996,8 +2993,18 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
         if (unlikely(!debug_locks))
                 return;
 
-        if (subclass)
+        if (subclass) {
+                unsigned long flags;
+
+                if (DEBUG_LOCKS_WARN_ON(current->lockdep_recursion))
+                        return;
+
+                raw_local_irq_save(flags);
+                current->lockdep_recursion = 1;
                 register_lock_class(lock, subclass, 1);
+                current->lockdep_recursion = 0;
+                raw_local_irq_restore(flags);
+        }
 }
 EXPORT_SYMBOL_GPL(lockdep_init_map);
 
@@ -3887,9 +3894,17 @@ static inline int within(const void *addr, void *start, unsigned long size)
         return addr >= start && addr < start + size;
 }
 
+/*
+ * Used in module.c to remove lock classes from memory that is going to be
+ * freed; and possibly re-used by other modules.
+ *
+ * We will have had one sync_sched() before getting here, so we're guaranteed
+ * nobody will look up these exact classes -- they're properly dead but still
+ * allocated.
+ */
 void lockdep_free_key_range(void *start, unsigned long size)
 {
-        struct lock_class *class, *next;
+        struct lock_class *class;
         struct list_head *head;
         unsigned long flags;
         int i;
@@ -3905,7 +3920,7 @@ void lockdep_free_key_range(void *start, unsigned long size)
                 head = classhash_table + i;
                 if (list_empty(head))
                         continue;
-                list_for_each_entry_safe(class, next, head, hash_entry) {
+                list_for_each_entry_rcu(class, head, hash_entry) {
                         if (within(class->key, start, size))
                                 zap_class(class);
                         else if (within(class->name, start, size))
@@ -3916,11 +3931,25 @@ void lockdep_free_key_range(void *start, unsigned long size)
         if (locked)
                 graph_unlock();
         raw_local_irq_restore(flags);
+
+        /*
+         * Wait for any possible iterators from look_up_lock_class() to pass
+         * before continuing to free the memory they refer to.
+         *
+         * sync_sched() is sufficient because the read-side is IRQ disable.
+         */
+        synchronize_sched();
+
+        /*
+         * XXX at this point we could return the resources to the pool;
+         * instead we leak them. We would need to change to bitmap allocators
+         * instead of the linear allocators we have now.
+         */
 }
 
 void lockdep_reset_lock(struct lockdep_map *lock)
 {
-        struct lock_class *class, *next;
+        struct lock_class *class;
         struct list_head *head;
         unsigned long flags;
         int i, j;
@@ -3948,7 +3977,7 @@ void lockdep_reset_lock(struct lockdep_map *lock)
                 head = classhash_table + i;
                 if (list_empty(head))
                         continue;
-                list_for_each_entry_safe(class, next, head, hash_entry) {
+                list_for_each_entry_rcu(class, head, hash_entry) {
                         int match = 0;
 
                         for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
diff --git a/kernel/module.c b/kernel/module.c
index b3d634ed06c9..99fdf94efce8 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1865,7 +1865,7 @@ static void free_module(struct module *mod)
         kfree(mod->args);
         percpu_modfree(mod);
 
-        /* Free lock-classes: */
+        /* Free lock-classes; relies on the preceding sync_rcu(). */
         lockdep_free_key_range(mod->module_core, mod->core_size);
 
         /* Finally, free the core (containing the module structure) */
@@ -3349,9 +3349,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
         module_bug_cleanup(mod);
         mutex_unlock(&module_mutex);
 
-        /* Free lock-classes: */
-        lockdep_free_key_range(mod->module_core, mod->core_size);
-
         /* we can't deallocate the module until we clear memory protection */
         unset_module_init_ro_nx(mod);
         unset_module_core_ro_nx(mod);
@@ -3375,6 +3372,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
         synchronize_rcu();
         mutex_unlock(&module_mutex);
  free_module:
+        /* Free lock-classes; relies on the preceding sync_rcu() */
+        lockdep_free_key_range(mod->module_core, mod->core_size);
+
         module_deallocate(mod, info);
  free_copy:
         free_copy(info);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f0f831e8a345..62671f53202a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3034,6 +3034,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
         } else {
                 if (dl_prio(oldprio))
                         p->dl.dl_boosted = 0;
+                if (rt_prio(oldprio))
+                        p->rt.timeout = 0;
                 p->sched_class = &fair_sched_class;
         }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7ce18f3c097a..bcfe32088b37 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1609,9 +1609,11 @@ static void update_task_scan_period(struct task_struct *p,
         /*
          * If there were no record hinting faults then either the task is
          * completely idle or all activity is areas that are not of interest
-         * to automatic numa balancing. Scan slower
+         * to automatic numa balancing. Related to that, if there were failed
+         * migration then it implies we are migrating too quickly or the local
+         * node is overloaded. In either case, scan slower
          */
-        if (local + shared == 0) {
+        if (local + shared == 0 || p->numa_faults_locality[2]) {
                 p->numa_scan_period = min(p->numa_scan_period_max,
                         p->numa_scan_period << 1);
 
@@ -2080,6 +2082,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 
         if (migrated)
                 p->numa_pages_migrated += pages;
+        if (flags & TNF_MIGRATE_FAIL)
+                p->numa_faults_locality[2] += pages;
 
         p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages;
         p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages;
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index eb682d5c697c..6aac4beedbbe 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -49,6 +49,7 @@ static void bc_set_mode(enum clock_event_mode mode,
  */
 static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 {
+        int bc_moved;
         /*
          * We try to cancel the timer first. If the callback is on
          * flight on some other cpu then we let it handle it. If we
@@ -60,9 +61,15 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
          * restart the timer because we are in the callback, but we
          * can set the expiry time and let the callback return
          * HRTIMER_RESTART.
+         *
+         * Since we are in the idle loop at this point and because
+         * hrtimer_{start/cancel} functions call into tracing,
+         * calls to these functions must be bound within RCU_NONIDLE.
          */
-        if (hrtimer_try_to_cancel(&bctimer) >= 0) {
-                hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+        RCU_NONIDLE(bc_moved = (hrtimer_try_to_cancel(&bctimer) >= 0) ?
+                !hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED) :
+                        0);
+        if (bc_moved) {
                 /* Bind the "device" to the cpu */
                 bc->bound_on = smp_processor_id();
         } else if (bc->bound_on == smp_processor_id()) {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 626e93db28ba..6817b0350c71 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1260,6 +1260,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
         int target_nid, last_cpupid = -1;
         bool page_locked;
         bool migrated = false;
+        bool was_writable;
         int flags = 0;
 
         /* A PROT_NONE fault should not end up here */
@@ -1291,17 +1292,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 flags |= TNF_FAULT_LOCAL;
         }
 
-        /*
-         * Avoid grouping on DSO/COW pages in specific and RO pages
-         * in general, RO pages shouldn't hurt as much anyway since
-         * they can be in shared cache state.
-         *
-         * FIXME! This checks "pmd_dirty()" as an approximation of
-         * "is this a read-only page", since checking "pmd_write()"
-         * is even more broken. We haven't actually turned this into
-         * a writable page, so pmd_write() will always be false.
-         */
-        if (!pmd_dirty(pmd))
+        /* See similar comment in do_numa_page for explanation */
+        if (!(vma->vm_flags & VM_WRITE))
                 flags |= TNF_NO_GROUP;
 
         /*
@@ -1358,12 +1350,17 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
         if (migrated) {
                 flags |= TNF_MIGRATED;
                 page_nid = target_nid;
-        }
+        } else
+                flags |= TNF_MIGRATE_FAIL;
 
         goto out;
 clear_pmdnuma:
         BUG_ON(!PageLocked(page));
+        was_writable = pmd_write(pmd);
         pmd = pmd_modify(pmd, vma->vm_page_prot);
+        pmd = pmd_mkyoung(pmd);
+        if (was_writable)
+                pmd = pmd_mkwrite(pmd);
         set_pmd_at(mm, haddr, pmdp, pmd);
         update_mmu_cache_pmd(vma, addr, pmdp);
         unlock_page(page);
@@ -1487,6 +1484,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 
         if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
                 pmd_t entry;
+                bool preserve_write = prot_numa && pmd_write(*pmd);
                 ret = 1;
 
                 /*
@@ -1502,9 +1500,11 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
                 if (!prot_numa || !pmd_protnone(*pmd)) {
                         entry = pmdp_get_and_clear_notify(mm, addr, pmd);
                         entry = pmd_modify(entry, newprot);
+                        if (preserve_write)
+                                entry = pmd_mkwrite(entry);
                         ret = HPAGE_PMD_NR;
                         set_pmd_at(mm, addr, pmd, entry);
-                        BUG_ON(pmd_write(entry));
+                        BUG_ON(!preserve_write && pmd_write(entry));
                 }
                 spin_unlock(ptl);
         }
diff --git a/mm/memory.c b/mm/memory.c
index 411144f977b1..97839f5c8c30 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3035,6 +3035,7 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
         int last_cpupid;
         int target_nid;
         bool migrated = false;
+        bool was_writable = pte_write(pte);
         int flags = 0;
 
         /* A PROT_NONE fault should not end up here */
@@ -3059,6 +3060,8 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
         /* Make it present again */
         pte = pte_modify(pte, vma->vm_page_prot);
         pte = pte_mkyoung(pte);
+        if (was_writable)
+                pte = pte_mkwrite(pte);
         set_pte_at(mm, addr, ptep, pte);
         update_mmu_cache(vma, addr, ptep);
 
@@ -3069,16 +3072,14 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
         }
 
         /*
-         * Avoid grouping on DSO/COW pages in specific and RO pages
-         * in general, RO pages shouldn't hurt as much anyway since
-         * they can be in shared cache state.
-         *
-         * FIXME! This checks "pmd_dirty()" as an approximation of
-         * "is this a read-only page", since checking "pmd_write()"
-         * is even more broken. We haven't actually turned this into
-         * a writable page, so pmd_write() will always be false.
+         * Avoid grouping on RO pages in general. RO pages shouldn't hurt as
+         * much anyway since they can be in shared cache state. This misses
+         * the case where a mapping is writable but the process never writes
+         * to it but pte_write gets cleared during protection updates and
+         * pte_dirty has unpredictable behaviour between PTE scan updates,
+         * background writeback, dirty balancing and application behaviour.
          */
-        if (!pte_dirty(pte))
+        if (!(vma->vm_flags & VM_WRITE))
                 flags |= TNF_NO_GROUP;
 
         /*
@@ -3102,7 +3103,8 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
         if (migrated) {
                 page_nid = target_nid;
                 flags |= TNF_MIGRATED;
-        }
+        } else
+                flags |= TNF_MIGRATE_FAIL;
 
 out:
         if (page_nid != -1)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9fab10795bea..65842d688b7c 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1092,6 +1092,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
                         return NULL;
 
                 arch_refresh_nodedata(nid, pgdat);
+        } else {
+                /* Reset the nr_zones and classzone_idx to 0 before reuse */
+                pgdat->nr_zones = 0;
+                pgdat->classzone_idx = 0;
         }
 
         /* we can use NODE_DATA(nid) from here */
@@ -1977,15 +1981,6 @@ void try_offline_node(int nid)
                 if (is_vmalloc_addr(zone->wait_table))
                         vfree(zone->wait_table);
         }
-
-        /*
-         * Since there is no way to guarentee the address of pgdat/zone is not
-         * on stack of any kernel threads or used by other kernel objects
-         * without reference counting or other symchronizing method, do not
-         * reset node_data and free pgdat here. Just reset it to 0 and reuse
-         * the memory when the node is online again.
-         */
-        memset(pgdat, 0, sizeof(*pgdat));
 }
 EXPORT_SYMBOL(try_offline_node);
 
diff --git a/mm/mmap.c b/mm/mmap.c
index da9990acc08b..9ec50a368634 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -774,10 +774,8 @@ again:			remove_next = 1 + (end > next->vm_end);
 
                         importer->anon_vma = exporter->anon_vma;
                         error = anon_vma_clone(importer, exporter);
-                        if (error) {
-                                importer->anon_vma = NULL;
+                        if (error)
                                 return error;
-                        }
                 }
         }
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 44727811bf4c..88584838e704 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -75,6 +75,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                 oldpte = *pte;
                 if (pte_present(oldpte)) {
                         pte_t ptent;
+                        bool preserve_write = prot_numa && pte_write(oldpte);
 
                         /*
                          * Avoid trapping faults against the zero or KSM
@@ -94,6 +95,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
                         ptent = ptep_modify_prot_start(mm, addr, pte);
                         ptent = pte_modify(ptent, newprot);
+                        if (preserve_write)
+                                ptent = pte_mkwrite(ptent);
 
                         /* Avoid taking write faults for known dirty pages */
                         if (dirty_accountable && pte_dirty(ptent) &&
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 45e187b2d971..644bcb665773 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -857,8 +857,11 @@ static void bdi_update_write_bandwidth(struct backing_dev_info *bdi,
          *                   bw * elapsed + write_bandwidth * (period - elapsed)
          * write_bandwidth = ---------------------------------------------------
          *                                          period
+         *
+         * @written may have decreased due to account_page_redirty().
+         * Avoid underflowing @bw calculation.
          */
-        bw = written - bdi->written_stamp;
+        bw = written - min(written, bdi->written_stamp);
         bw *= HZ;
         if (unlikely(elapsed > period)) {
                 do_div(bw, elapsed);
@@ -922,7 +925,7 @@ static void global_update_bandwidth(unsigned long thresh,
                                     unsigned long now)
 {
         static DEFINE_SPINLOCK(dirty_lock);
-        static unsigned long update_time;
+        static unsigned long update_time = INITIAL_JIFFIES;
 
         /*
          * check locklessly first to optimize away locking for the most time
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 72f5ac381ab3..755a42c76eb4 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -103,6 +103,7 @@ void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 
                         if (!is_migrate_isolate_page(buddy)) {
                                 __isolate_free_page(page, order);
+                                kernel_map_pages(page, (1 << order), 1);
                                 set_page_refcounted(page);
                                 isolated_page = page;
                         }
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 75c1f2878519..29f2f8b853ae 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -265,8 +265,15 @@ int walk_page_range(unsigned long start, unsigned long end,
                         vma = vma->vm_next;
 
                         err = walk_page_test(start, next, walk);
-                        if (err > 0)
+                        if (err > 0) {
+                                /*
+                                 * positive return values are purely for
+                                 * controlling the pagewalk, so should never
+                                 * be passed to the callers.
+                                 */
+                                err = 0;
                                 continue;
+                        }
                         if (err < 0)
                                 break;
                 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 5e3e09081164..c161a14b6a8f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -287,6 +287,13 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
         return 0;
 
  enomem_failure:
+        /*
+         * dst->anon_vma is dropped here otherwise its degree can be incorrectly
+         * decremented in unlink_anon_vmas().
+         * We can safely do this because callers of anon_vma_clone() don't care
+         * about dst->anon_vma if anon_vma_clone() failed.
+         */
+        dst->anon_vma = NULL;
         unlink_anon_vmas(dst);
         return -ENOMEM;
 }
diff --git a/mm/slub.c b/mm/slub.c
index 6832c4eab104..82c473780c91 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2449,7 +2449,8 @@ redo:
         do {
                 tid = this_cpu_read(s->cpu_slab->tid);
                 c = raw_cpu_ptr(s->cpu_slab);
-        } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid));
+        } while (IS_ENABLED(CONFIG_PREEMPT) &&
+                 unlikely(tid != READ_ONCE(c->tid)));
 
         /*
          * Irqless object alloc/free algorithm used here depends on sequence
@@ -2718,7 +2719,8 @@ redo:
         do {
                 tid = this_cpu_read(s->cpu_slab->tid);
                 c = raw_cpu_ptr(s->cpu_slab);
-        } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid));
+        } while (IS_ENABLED(CONFIG_PREEMPT) &&
+                 unlikely(tid != READ_ONCE(c->tid)));
 
         /* Same with comment on barrier() in slab_alloc_node() */
         barrier();
diff --git a/net/compat.c b/net/compat.c
index 94d3d5e97883..f7bd286a8280 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -49,6 +49,13 @@ ssize_t get_compat_msghdr(struct msghdr *kmsg,
             __get_user(kmsg->msg_controllen, &umsg->msg_controllen) ||
             __get_user(kmsg->msg_flags, &umsg->msg_flags))
                 return -EFAULT;
+
+        if (!uaddr)
+                kmsg->msg_namelen = 0;
+
+        if (kmsg->msg_namelen < 0)
+                return -EINVAL;
+
         if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
                 kmsg->msg_namelen = sizeof(struct sockaddr_storage);
         kmsg->msg_control = compat_ptr(tmp3);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 99e810f84671..cf5e82f39d3b 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -272,9 +272,9 @@ static void trace_packet(const struct sk_buff *skb,
                     &chainname, &comment, &rulenum) != 0)
                         break;
 
-        nf_log_packet(net, AF_INET, hook, skb, in, out, &trace_loginfo,
-                      "TRACE: %s:%s:%s:%u ",
-                      tablename, chainname, comment, rulenum);
+        nf_log_trace(net, AF_INET, hook, skb, in, out, &trace_loginfo,
+                     "TRACE: %s:%s:%s:%u ",
+                     tablename, chainname, comment, rulenum);
 }
 #endif
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a2a796c5536b..1db253e36045 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2773,15 +2773,11 @@ void tcp_send_fin(struct sock *sk)
         } else {
                 /* Socket is locked, keep trying until memory is available. */
                 for (;;) {
-                        skb = alloc_skb_fclone(MAX_TCP_HEADER,
-                                               sk->sk_allocation);
+                        skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
                         if (skb)
                                 break;
                         yield();
                 }
-
-                /* Reserve space for headers and prepare control bits. */
-                skb_reserve(skb, MAX_TCP_HEADER);
                 /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
                 tcp_init_nondata_skb(skb, tp->write_seq,
                                      TCPHDR_ACK | TCPHDR_FIN);
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index b4d5e1d97c1b..27ca79682efb 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -104,6 +104,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
                                 goto again;
                         flp6->saddr = saddr;
                 }
+                err = rt->dst.error;
                 goto out;
         }
 again:
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index e080fbbbc0e5..bb00c6f2a885 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -298,9 +298,9 @@ static void trace_packet(const struct sk_buff *skb,
                     &chainname, &comment, &rulenum) != 0)
                         break;
 
-        nf_log_packet(net, AF_INET6, hook, skb, in, out, &trace_loginfo,
-                      "TRACE: %s:%s:%s:%u ",
-                      tablename, chainname, comment, rulenum);
+        nf_log_trace(net, AF_INET6, hook, skb, in, out, &trace_loginfo,
+                     "TRACE: %s:%s:%s:%u ",
+                     tablename, chainname, comment, rulenum);
 }
 #endif
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index ab889bb16b3c..be2c0ba82c85 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -112,11 +112,9 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
                 fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
                 fptr->nexthdr = nexthdr;
                 fptr->reserved = 0;
-                if (skb_shinfo(skb)->ip6_frag_id)
-                        fptr->identification = skb_shinfo(skb)->ip6_frag_id;
-                else
-                        ipv6_select_ident(fptr,
-                                          (struct rt6_info *)skb_dst(skb));
+                if (!skb_shinfo(skb)->ip6_frag_id)
+                        ipv6_proxy_select_ident(skb);
+                fptr->identification = skb_shinfo(skb)->ip6_frag_id;
 
                 /* Fragment the skb. ipv6 header and the remaining fields of the
                  * fragment header are updated in ipv6_gso_segment()
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 0d8448f19dfe..675d12c69e32 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -212,6 +212,30 @@ void nf_log_packet(struct net *net,
 }
 EXPORT_SYMBOL(nf_log_packet);
 
+void nf_log_trace(struct net *net,
+                  u_int8_t pf,
+                  unsigned int hooknum,
+                  const struct sk_buff *skb,
+                  const struct net_device *in,
+                  const struct net_device *out,
+                  const struct nf_loginfo *loginfo, const char *fmt, ...)
+{
+        va_list args;
+        char prefix[NF_LOG_PREFIXLEN];
+        const struct nf_logger *logger;
+
+        rcu_read_lock();
+        logger = rcu_dereference(net->nf.nf_loggers[pf]);
+        if (logger) {
+                va_start(args, fmt);
+                vsnprintf(prefix, sizeof(prefix), fmt, args);
+                va_end(args);
+                logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix);
+        }
+        rcu_read_unlock();
+}
+EXPORT_SYMBOL(nf_log_trace);
+
 #define S_SIZE (1024 - (sizeof(unsigned int) + 1))
 
 struct nf_log_buf {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 6ab777912237..ac1a9528dbf2 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1225,7 +1225,10 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 
         if (nla[NFTA_CHAIN_POLICY]) {
                 if ((chain != NULL &&
-                    !(chain->flags & NFT_BASE_CHAIN)) ||
+                    !(chain->flags & NFT_BASE_CHAIN)))
+                        return -EOPNOTSUPP;
+
+                if (chain == NULL &&
                     nla[NFTA_CHAIN_HOOK] == NULL)
                         return -EOPNOTSUPP;
 
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 3b90eb2b2c55..2d298dccb6dd 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -94,10 +94,10 @@ static void nft_trace_packet(const struct nft_pktinfo *pkt,
 {
         struct net *net = dev_net(pkt->in ? pkt->in : pkt->out);
 
-        nf_log_packet(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in,
-                      pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ",
-                      chain->table->name, chain->name, comments[type],
-                      rulenum);
+        nf_log_trace(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in,
+                     pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ",
+                     chain->table->name, chain->name, comments[type],
+                     rulenum);
 }
 
 unsigned int
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index a5599fc51a6f..54330fb5efaf 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -77,6 +77,9 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
         if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM])
                 return -EINVAL;
 
+        /* Not all fields are initialized so first zero the tuple */
+        memset(tuple, 0, sizeof(struct nf_conntrack_tuple));
+
         tuple->src.l3num = ntohs(nla_get_be16(tb[NFCTH_TUPLE_L3PROTONUM]));
         tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]);
 
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 213584cf04b3..65f3e2b6be44 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -133,6 +133,9 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par,
                 entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
                 break;
         case AF_INET6:
+                if (proto)
+                        entry->e6.ipv6.flags |= IP6T_F_PROTO;
+
                 entry->e6.ipv6.proto = proto;
                 entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0;
                 break;
@@ -344,6 +347,9 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx,
                 entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0;
                 break;
         case AF_INET6:
+                if (proto)
+                        entry->e6.ipv6.flags |= IP6T_F_PROTO;
+
                 entry->e6.ipv6.proto = proto;
                 entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0;
                 break;
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index c82df0a48fcd..37c15e674884 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -153,6 +153,8 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
                                 iter->err = err;
                                 goto out;
                         }
+
+                        continue;
                 }
 
                 if (iter->count < iter->skip)
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index ef8a926752a9..50e1e5aaf4ce 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -513,8 +513,8 @@ static int tproxy_tg6_check(const struct xt_tgchk_param *par)
 {
         const struct ip6t_ip6 *i = par->entryinfo;
 
-        if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP)
-            && !(i->flags & IP6T_INV_PROTO))
+        if ((i->proto == IPPROTO_TCP || i->proto == IPPROTO_UDP) &&
+            !(i->invflags & IP6T_INV_PROTO))
                 return 0;
 
         pr_info("Can be used only in combination with "
diff --git a/net/socket.c b/net/socket.c
index bbedbfcb42c2..245330ca0015 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1702,6 +1702,8 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len,
 
         if (len > INT_MAX)
                 len = INT_MAX;
+        if (unlikely(!access_ok(VERIFY_READ, buff, len)))
+                return -EFAULT;
         sock = sockfd_lookup_light(fd, &err, &fput_needed);
         if (!sock)
                 goto out;
@@ -1760,6 +1762,8 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size,
 
         if (size > INT_MAX)
                 size = INT_MAX;
+        if (unlikely(!access_ok(VERIFY_WRITE, ubuf, size)))
+                return -EFAULT;
         sock = sockfd_lookup_light(fd, &err, &fput_needed);
         if (!sock)
                 goto out;
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 1684bcc78b34..5fde34326dcf 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -152,7 +152,7 @@ static ssize_t sel_write_enforce(struct file *file, const char __user *buf,
                 goto out;
 
         /* No partial writes. */
-        length = EINVAL;
+        length = -EINVAL;
         if (*ppos != 0)
                 goto out;
 
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 4ca3d5d02436..a8a1e14272a1 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1989,7 +1989,7 @@ static const struct pci_device_id azx_ids[] = {
           .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
         /* Sunrise Point */
         { PCI_DEVICE(0x8086, 0xa170),
-          .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
+          .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
         /* Sunrise Point-LP */
         { PCI_DEVICE(0x8086, 0x9d70),
           .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 526398a4a442..74382137b9f5 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -396,7 +396,7 @@ static void alc_auto_setup_eapd(struct hda_codec *codec, bool on)
 {
         /* We currently only handle front, HP */
         static hda_nid_t pins[] = {
-                0x0f, 0x10, 0x14, 0x15, 0
+                0x0f, 0x10, 0x14, 0x15, 0x17, 0
         };
         hda_nid_t *p;
         for (p = pins; *p; p++)
@@ -5036,6 +5036,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
         SND_PCI_QUIRK(0x17aa, 0x501a, "Thinkpad", ALC283_FIXUP_INT_MIC),
         SND_PCI_QUIRK(0x17aa, 0x501e, "Thinkpad L440", ALC292_FIXUP_TPT440_DOCK),
         SND_PCI_QUIRK(0x17aa, 0x5026, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+        SND_PCI_QUIRK(0x17aa, 0x5036, "Thinkpad T450s", ALC292_FIXUP_TPT440_DOCK),
         SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
         SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
         SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD),
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 4e511221a0c1..0db571340edb 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -22,6 +22,14 @@ TARGETS += vm
 TARGETS_HOTPLUG = cpu-hotplug
 TARGETS_HOTPLUG += memory-hotplug
 
+# Clear LDFLAGS and MAKEFLAGS if called from main
+# Makefile to avoid test build failures when test
+# Makefile doesn't have explicit build rules.
+ifeq (1,$(MAKELEVEL))
+undefine LDFLAGS
+override MAKEFLAGS =
+endif
+
 all:
         for TARGET in $(TARGETS); do \
                 make -C $$TARGET; \
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a2214d9609bd..cc6a25d95fbf 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -471,7 +471,7 @@ static struct kvm *kvm_create_vm(unsigned long type)
         BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
 
         r = -ENOMEM;
-        kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
+        kvm->memslots = kvm_kvzalloc(sizeof(struct kvm_memslots));
         if (!kvm->memslots)
                 goto out_err_no_srcu;
 
@@ -522,7 +522,7 @@ out_err_no_srcu:
 out_err_no_disable:
         for (i = 0; i < KVM_NR_BUSES; i++)
                 kfree(kvm->buses[i]);
-        kfree(kvm->memslots);
+        kvfree(kvm->memslots);
         kvm_arch_free_vm(kvm);
         return ERR_PTR(r);
 }
@@ -578,7 +578,7 @@ static void kvm_free_physmem(struct kvm *kvm)
         kvm_for_each_memslot(memslot, slots)
                 kvm_free_physmem_slot(kvm, memslot, NULL);
 
-        kfree(kvm->memslots);
+        kvfree(kvm->memslots);
 }
 
 static void kvm_destroy_devices(struct kvm *kvm)
@@ -871,10 +871,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
                         goto out_free;
         }
 
-        slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
-                        GFP_KERNEL);
+        slots = kvm_kvzalloc(sizeof(struct kvm_memslots));
         if (!slots)
                 goto out_free;
+        memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
 
         if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) {
                 slot = id_to_memslot(slots, mem->slot);
@@ -917,7 +917,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
         kvm_arch_commit_memory_region(kvm, mem, &old, change);
 
         kvm_free_physmem_slot(kvm, &old, &new);
-        kfree(old_memslots);
+        kvfree(old_memslots);
 
         /*
          * IOMMU mapping:  New slots need to be mapped.  Old slots need to be
@@ -936,7 +936,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
         return 0;
 
 out_slots:
-        kfree(slots);
+        kvfree(slots);
 out_free:
         kvm_free_physmem_slot(kvm, &new, &old);
 out: