Merge tag 'asoc-v4.19' of https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-linus

ASoC: Updates for v4.19

A fairly big update, including quite a bit of core activity this time
around (which is good to see) along with a fairly large set of new
drivers.

 - A new snd_pcm_stop_xrun() helper which is now used in several
   drivers.
 - Support for providing name prefixes to generic component nodes.
 - Quite a few fixes for DPCM as it gains a bit wider use and more
   robust testing.
 - Generalization of the DIO2125 support to a simple amplifier driver.
 - Accessory detection support for the audio graph card.
 - DT support for PXA AC'97 devices.
 - Quirks for a number of new x86 systems.
 - Support for AM Logic Meson, Everest ES7154, Intel systems with
   RT5682, Qualcomm QDSP6 and WCD9335, Realtek RT5682 and TI TAS5707.

99 files changed, 701 insertions, 571 deletions

diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 6e921754c8fc..c210a25dd6da 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1180,13 +1180,10 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
 SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
 		struct rusage32 __user *, ur)
 {
-	unsigned int status = 0;
 	struct rusage r;
-	long err = kernel_wait4(pid, &status, options, &r);
+	long err = kernel_wait4(pid, ustatus, options, &r);
 	if (err <= 0)
 		return err;
-	if (put_user(status, ustatus))
-		return -EFAULT;
 	if (!ur)
 		return err;
 	if (put_tv_to_tv32(&ur->ru_utime, &r.ru_utime))
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index e81bcd271be7..5151d81476a1 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -50,6 +50,9 @@ config ARC
 	select HAVE_KERNEL_LZMA
 	select ARCH_HAS_PTE_SPECIAL
 
+config ARCH_HAS_CACHE_LINE_SIZE
+	def_bool y
+
 config MIGHT_HAVE_PCI
 	bool
 
@@ -413,7 +416,7 @@ config ARC_HAS_DIV_REM
 
 config ARC_HAS_ACCL_REGS
 	bool "Reg Pair ACCL:ACCH (FPU and/or MPY > 6)"
-	default n
+	default y
 	help
 	  Depending on the configuration, CPU can contain accumulator reg-pair
 	  (also referred to as r58:r59). These can also be used by gcc as GPR so
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index d37f49d6a27f..6c1b20dd76ad 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -16,7 +16,7 @@ endif
 
 KBUILD_DEFCONFIG := nsim_700_defconfig
 
-cflags-y	+= -fno-common -pipe -fno-builtin -D__linux__
+cflags-y	+= -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__
 cflags-$(CONFIG_ISA_ARCOMPACT)	+= -mA7
 cflags-$(CONFIG_ISA_ARCV2)	+= -mcpu=archs
 
@@ -140,16 +140,3 @@ dtbs: scripts
 
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
-
-# Hacks to enable final link due to absence of link-time branch relexation
-# and gcc choosing optimal(shorter) branches at -O3
-#
-# vineetg Feb 2010: -mlong-calls switched off for overall kernel build
-# However lib/decompress_inflate.o (.init.text) calls
-# zlib_inflate_workspacesize (.text) causing relocation errors.
-# Thus forcing all exten calls in this file to be long calls
-export CFLAGS_decompress_inflate.o = -mmedium-calls
-export CFLAGS_initramfs.o = -mmedium-calls
-ifdef CONFIG_SMP
-export CFLAGS_core.o = -mmedium-calls
-endif
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index 09f85154c5a4..a635ea972304 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index 09fed3ef22b6..aa507e423075 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index ea2f6d817d1a..eba07f468654 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig
index ab231c040efe..098b19fbaa51 100644
--- a/arch/arc/configs/haps_hs_defconfig
+++ b/arch/arc/configs/haps_hs_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EXPERT=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig
index cf449cbf440d..0104c404d897 100644
--- a/arch/arc/configs/haps_hs_smp_defconfig
+++ b/arch/arc/configs/haps_hs_smp_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 1b54c72f4296..6491be0ddbc9 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -9,7 +9,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig
index 31c2c70b34a1..99e05cf63fca 100644
--- a/arch/arc/configs/nsim_700_defconfig
+++ b/arch/arc/configs/nsim_700_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig
index a578c721d50f..0dc4f9b737e7 100644
--- a/arch/arc/configs/nsim_hs_defconfig
+++ b/arch/arc/configs/nsim_hs_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig
index 37d7395f3272..be3c30a15e54 100644
--- a/arch/arc/configs/nsim_hs_smp_defconfig
+++ b/arch/arc/configs/nsim_hs_smp_defconfig
@@ -9,7 +9,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index 1e1470e2a7f0..3a74b9b21772 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
index 084a6e42685b..ea2834b4dc1d 100644
--- a/arch/arc/configs/nsimosci_hs_defconfig
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
index f36d47990415..80a5a1b4924b 100644
--- a/arch/arc/configs/nsimosci_hs_smp_defconfig
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -9,7 +9,6 @@ CONFIG_IKCONFIG_PROC=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
 CONFIG_PERF_EVENTS=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_KPROBES=y
diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig
index 1aca2e8fd1ba..2cc87f909747 100644
--- a/arch/arc/configs/tb10x_defconfig
+++ b/arch/arc/configs/tb10x_defconfig
@@ -56,7 +56,6 @@ CONFIG_STMMAC_ETH=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
-CONFIG_DEVPTS_MULTIPLE_INSTANCES=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 8486f328cc5d..ff7d3232764a 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -48,7 +48,9 @@
 })
 
 /* Largest line length for either L1 or L2 is 128 bytes */
-#define ARCH_DMA_MINALIGN      128
+#define SMP_CACHE_BYTES		128
+#define cache_line_size()	SMP_CACHE_BYTES
+#define ARCH_DMA_MINALIGN	SMP_CACHE_BYTES
 
 extern void arc_cache_init(void);
 extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
index d5da2115d78a..03d6bb0f4e13 100644
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -17,8 +17,11 @@
 #ifndef __ASM_ARC_UDELAY_H
 #define __ASM_ARC_UDELAY_H
 
+#include <asm-generic/types.h>
 #include <asm/param.h>		/* HZ */
 
+extern unsigned long loops_per_jiffy;
+
 static inline void __delay(unsigned long loops)
 {
 	__asm__ __volatile__(
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index ec36d5b6d435..29f3988c9424 100644
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -234,6 +234,9 @@
 	POP	gp
 	RESTORE_R12_TO_R0
 
+#ifdef CONFIG_ARC_CURR_IN_REG
+	ld	r25, [sp, 12]
+#endif
 	ld  sp, [sp] /* restore original sp */
 	/* orig_r0, ECR, user_r25 skipped automatically */
 .endm
@@ -315,6 +318,9 @@
 	POP	gp
 	RESTORE_R12_TO_R0
 
+#ifdef CONFIG_ARC_CURR_IN_REG
+	ld	r25, [sp, 12]
+#endif
 	ld  sp, [sp] /* restore original sp */
 	/* orig_r0, ECR, user_r25 skipped automatically */
 .endm
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index 51597f344a62..302b0db8ea2b 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -86,9 +86,6 @@
 	POP	r1
 	POP	r0
 
-#ifdef CONFIG_ARC_CURR_IN_REG
-	ld	r25, [sp, 12]
-#endif
 .endm
 
 /*--------------------------------------------------------------
diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h
index c28e6c347b49..871f3cb16af9 100644
--- a/arch/arc/include/asm/mach_desc.h
+++ b/arch/arc/include/asm/mach_desc.h
@@ -34,9 +34,7 @@ struct machine_desc {
 	const char		*name;
 	const char		**dt_compat;
 	void			(*init_early)(void);
-#ifdef CONFIG_SMP
 	void			(*init_per_cpu)(unsigned int);
-#endif
 	void			(*init_machine)(void);
 	void			(*init_late)(void);
 
diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h
index 109baa06831c..09ddddf71cc5 100644
--- a/arch/arc/include/asm/page.h
+++ b/arch/arc/include/asm/page.h
@@ -105,7 +105,7 @@ typedef pte_t * pgtable_t;
 #define virt_addr_valid(kaddr)  pfn_valid(virt_to_pfn(kaddr))
 
 /* Default Permissions for stack/heaps pages (Non Executable) */
-#define VM_DATA_DEFAULT_FLAGS   (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE)
+#define VM_DATA_DEFAULT_FLAGS   (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
 #define WANT_PAGE_VIRTUAL   1
 
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 8ec5599a0957..cf4be70d5892 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -377,7 +377,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
 
 /* Decode a PTE containing swap "identifier "into constituents */
 #define __swp_type(pte_lookalike)	(((pte_lookalike).val) & 0x1f)
-#define __swp_offset(pte_lookalike)	((pte_lookalike).val << 13)
+#define __swp_offset(pte_lookalike)	((pte_lookalike).val >> 13)
 
 /* NOPs, to keep generic kernel happy */
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
index 538b36afe89e..62b185057c04 100644
--- a/arch/arc/kernel/irq.c
+++ b/arch/arc/kernel/irq.c
@@ -31,10 +31,10 @@ void __init init_IRQ(void)
 	/* a SMP H/w block could do IPI IRQ request here */
 	if (plat_smp_ops.init_per_cpu)
 		plat_smp_ops.init_per_cpu(smp_processor_id());
+#endif
 
 	if (machine_desc->init_per_cpu)
 		machine_desc->init_per_cpu(smp_processor_id());
-#endif
 }
 
 /*
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 5ac3b547453f..4674541eba3f 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -47,7 +47,8 @@ SYSCALL_DEFINE0(arc_gettls)
 SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
 {
 	struct pt_regs *regs = current_pt_regs();
-	int uval = -EFAULT;
+	u32 uval;
+	int ret;
 
 	/*
 	 * This is only for old cores lacking LLOCK/SCOND, which by defintion
@@ -60,23 +61,47 @@ SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
 	/* Z indicates to userspace if operation succeded */
 	regs->status32 &= ~STATUS_Z_MASK;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
-		return -EFAULT;
+	ret = access_ok(VERIFY_WRITE, uaddr, sizeof(*uaddr));
+	if (!ret)
+		 goto fail;
 
+again:
 	preempt_disable();
 
-	if (__get_user(uval, uaddr))
-		goto done;
+	ret = __get_user(uval, uaddr);
+	if (ret)
+		 goto fault;
 
-	if (uval == expected) {
-		if (!__put_user(new, uaddr))
-			regs->status32 |= STATUS_Z_MASK;
-	}
+	if (uval != expected)
+		 goto out;
 
-done:
-	preempt_enable();
+	ret = __put_user(new, uaddr);
+	if (ret)
+		 goto fault;
+
+	regs->status32 |= STATUS_Z_MASK;
 
+out:
+	preempt_enable();
 	return uval;
+
+fault:
+	preempt_enable();
+
+	if (unlikely(ret != -EFAULT))
+		 goto fail;
+
+	down_read(&current->mm->mmap_sem);
+	ret = fixup_user_fault(current, current->mm, (unsigned long) uaddr,
+			       FAULT_FLAG_WRITE, NULL);
+	up_read(&current->mm->mmap_sem);
+
+	if (likely(!ret))
+		 goto again;
+
+fail:
+	force_sig(SIGSEGV, current);
+	return ret;
 }
 
 #ifdef CONFIG_ISA_ARCV2
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 9dbe645ee127..25c631942500 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -1038,7 +1038,7 @@ void flush_cache_mm(struct mm_struct *mm)
 void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr,
 		      unsigned long pfn)
 {
-	unsigned int paddr = pfn << PAGE_SHIFT;
+	phys_addr_t paddr = pfn << PAGE_SHIFT;
 
 	u_vaddr &= PAGE_MASK;
 
@@ -1058,8 +1058,9 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page,
 		     unsigned long u_vaddr)
 {
 	/* TBD: do we really need to clear the kernel mapping */
-	__flush_dcache_page(page_address(page), u_vaddr);
-	__flush_dcache_page(page_address(page), page_address(page));
+	__flush_dcache_page((phys_addr_t)page_address(page), u_vaddr);
+	__flush_dcache_page((phys_addr_t)page_address(page),
+			    (phys_addr_t)page_address(page));
 
 }
 
@@ -1246,6 +1247,16 @@ void __init arc_cache_init_master(void)
 		}
 	}
 
+	/*
+	 * Check that SMP_CACHE_BYTES (and hence ARCH_DMA_MINALIGN) is larger
+	 * or equal to any cache line length.
+	 */
+	BUILD_BUG_ON_MSG(L1_CACHE_BYTES > SMP_CACHE_BYTES,
+			 "SMP_CACHE_BYTES must be >= any cache line length");
+	if (is_isa_arcv2() && (l2_line_sz > SMP_CACHE_BYTES))
+		panic("L2 Cache line [%d] > kernel Config [%d]\n",
+		      l2_line_sz, SMP_CACHE_BYTES);
+
 	/* Note that SLC disable not formally supported till HS 3.0 */
 	if (is_isa_arcv2() && l2_line_sz && !slc_enable)
 		arc_slc_disable();
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 8c1071840979..ec47e6079f5d 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -129,14 +129,59 @@ int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 	return ret;
 }
 
+/*
+ * Cache operations depending on function and direction argument, inspired by
+ * https://lkml.org/lkml/2018/5/18/979
+ * "dma_sync_*_for_cpu and direction=TO_DEVICE (was Re: [PATCH 02/20]
+ * dma-mapping: provide a generic dma-noncoherent implementation)"
+ *
+ *          |   map          ==  for_device     |   unmap     ==  for_cpu
+ *          |----------------------------------------------------------------
+ * TO_DEV   |   writeback        writeback      |   none          none
+ * FROM_DEV |   invalidate       invalidate     |   invalidate*   invalidate*
+ * BIDIR    |   writeback+inv    writeback+inv  |   invalidate    invalidate
+ *
+ *     [*] needed for CPU speculative prefetches
+ *
+ * NOTE: we don't check the validity of direction argument as it is done in
+ * upper layer functions (in include/linux/dma-mapping.h)
+ */
+
 void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 		size_t size, enum dma_data_direction dir)
 {
-	dma_cache_wback(paddr, size);
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		dma_cache_wback(paddr, size);
+		break;
+
+	case DMA_FROM_DEVICE:
+		dma_cache_inv(paddr, size);
+		break;
+
+	case DMA_BIDIRECTIONAL:
+		dma_cache_wback_inv(paddr, size);
+		break;
+
+	default:
+		break;
+	}
 }
 
 void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
 		size_t size, enum dma_data_direction dir)
 {
-	dma_cache_inv(paddr, size);
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		break;
+
+	/* FROM_DEVICE invalidate needed if speculative CPU prefetch only */
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		dma_cache_inv(paddr, size);
+		break;
+
+	default:
+		break;
+	}
 }
diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h
index 0c7d11022d0f..4f6a1673b3a6 100644
--- a/arch/arc/plat-eznps/include/plat/ctop.h
+++ b/arch/arc/plat-eznps/include/plat/ctop.h
@@ -21,6 +21,7 @@
 #error "Incorrect ctop.h include"
 #endif
 
+#include <linux/types.h>
 #include <soc/nps/common.h>
 
 /* core auxiliary registers */
@@ -143,6 +144,15 @@ struct nps_host_reg_gim_p_int_dst {
 };
 
 /* AUX registers definition */
+struct nps_host_reg_aux_dpc {
+	union {
+		struct {
+			u32 ien:1, men:1, hen:1, reserved:29;
+		};
+		u32 value;
+	};
+};
+
 struct nps_host_reg_aux_udmc {
 	union {
 		struct {
diff --git a/arch/arc/plat-eznps/mtm.c b/arch/arc/plat-eznps/mtm.c
index 2388de3d09ef..ed0077ef666e 100644
--- a/arch/arc/plat-eznps/mtm.c
+++ b/arch/arc/plat-eznps/mtm.c
@@ -15,6 +15,8 @@
  */
 
 #include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/log2.h>
 #include <asm/arcregs.h>
@@ -157,10 +159,10 @@ void mtm_enable_core(unsigned int cpu)
 /* Verify and set the value of the mtm hs counter */
 static int __init set_mtm_hs_ctr(char *ctr_str)
 {
-	long hs_ctr;
+	int hs_ctr;
 	int ret;
 
-	ret = kstrtol(ctr_str, 0, &hs_ctr);
+	ret = kstrtoint(ctr_str, 0, &hs_ctr);
 
 	if (ret || hs_ctr > MT_HS_CNT_MAX || hs_ctr < MT_HS_CNT_MIN) {
 		pr_err("** Invalid @nps_mtm_hs_ctr [%d] needs to be [%d:%d] (incl)\n",
diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig
index 19ab3cf98f0f..9356753c2ed8 100644
--- a/arch/arc/plat-hsdk/Kconfig
+++ b/arch/arc/plat-hsdk/Kconfig
@@ -7,5 +7,8 @@
 
 menuconfig ARC_SOC_HSDK
 	bool "ARC HS Development Kit SOC"
+	depends on ISA_ARCV2
+	select ARC_HAS_ACCL_REGS
 	select CLK_HSDK
 	select RESET_HSDK
+	select MIGHT_HAVE_PCI
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
index 2958aedb649a..2588b842407c 100644
--- a/arch/arc/plat-hsdk/platform.c
+++ b/arch/arc/plat-hsdk/platform.c
@@ -42,6 +42,66 @@ static void __init hsdk_init_per_cpu(unsigned int cpu)
 #define SDIO_UHS_REG_EXT	(SDIO_BASE + 0x108)
 #define SDIO_UHS_REG_EXT_DIV_2	(2 << 30)
 
+#define HSDK_GPIO_INTC          (ARC_PERIPHERAL_BASE + 0x3000)
+
+static void __init hsdk_enable_gpio_intc_wire(void)
+{
+	/*
+	 * Peripherals on CPU Card are wired to cpu intc via intermediate
+	 * DW APB GPIO blocks (mainly for debouncing)
+	 *
+	 *         ---------------------
+	 *        |  snps,archs-intc  |
+	 *        ---------------------
+	 *                  |
+	 *        ----------------------
+	 *        | snps,archs-idu-intc |
+	 *        ----------------------
+	 *         |   |     |   |    |
+	 *         | [eth] [USB]    [... other peripherals]
+	 *         |
+	 * -------------------
+	 * | snps,dw-apb-intc |
+	 * -------------------
+	 *  |      |   |   |
+	 * [Bt] [HAPS]   [... other peripherals]
+	 *
+	 * Current implementation of "irq-dw-apb-ictl" driver doesn't work well
+	 * with stacked INTCs. In particular problem happens if its master INTC
+	 * not yet instantiated. See discussion here -
+	 * https://lkml.org/lkml/2015/3/4/755
+	 *
+	 * So setup the first gpio block as a passive pass thru and hide it from
+	 * DT hardware topology - connect intc directly to cpu intc
+	 * The GPIO "wire" needs to be init nevertheless (here)
+	 *
+	 * One side adv is that peripheral interrupt handling avoids one nested
+	 * intc ISR hop
+	 *
+	 * According to HSDK User's Manual [1], "Table 2 Interrupt Mapping"
+	 * we have the following GPIO input lines used as sources of interrupt:
+	 * - GPIO[0] - Bluetooth interrupt of RS9113 module
+	 * - GPIO[2] - HAPS interrupt (on HapsTrak 3 connector)
+	 * - GPIO[3] - Audio codec (MAX9880A) interrupt
+	 * - GPIO[8-23] - Available on Arduino and PMOD_x headers
+	 * For now there's no use of Arduino and PMOD_x headers in Linux
+	 * use-case so we only enable lines 0, 2 and 3.
+	 *
+	 * [1] https://github.com/foss-for-synopsys-dwc-arc-processors/ARC-Development-Systems-Forum/wiki/docs/ARC_HSDK_User_Guide.pdf
+	 */
+#define GPIO_INTEN              (HSDK_GPIO_INTC + 0x30)
+#define GPIO_INTMASK            (HSDK_GPIO_INTC + 0x34)
+#define GPIO_INTTYPE_LEVEL      (HSDK_GPIO_INTC + 0x38)
+#define GPIO_INT_POLARITY       (HSDK_GPIO_INTC + 0x3c)
+#define GPIO_INT_CONNECTED_MASK	0x0d
+
+	iowrite32(0xffffffff, (void __iomem *) GPIO_INTMASK);
+	iowrite32(~GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTMASK);
+	iowrite32(0x00000000, (void __iomem *) GPIO_INTTYPE_LEVEL);
+	iowrite32(0xffffffff, (void __iomem *) GPIO_INT_POLARITY);
+	iowrite32(GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTEN);
+}
+
 static void __init hsdk_init_early(void)
 {
 	/*
@@ -62,6 +122,8 @@ static void __init hsdk_init_early(void)
 	 * minimum possible div-by-2.
 	 */
 	iowrite32(SDIO_UHS_REG_EXT_DIV_2, (void __iomem *) SDIO_UHS_REG_EXT);
+
+	hsdk_enable_gpio_intc_wire();
 }
 
 static const char *hsdk_compat[] __initconst = {
diff --git a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
index 19a075aee19e..f14df0baf2ab 100644
--- a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
@@ -692,7 +692,7 @@
 			dsa,member = <0 0>;
 			eeprom-length = <512>;
 			interrupt-parent = <&gpio6>;
-			interrupts = <3 IRQ_TYPE_EDGE_FALLING>;
+			interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
 
diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts
index bdf73cbcec3a..e7c3c563ff8f 100644
--- a/arch/arm/boot/dts/omap4-droid4-xt894.dts
+++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts
@@ -159,13 +159,7 @@
 
 		dais = <&mcbsp2_port>, <&mcbsp3_port>;
 	};
-};
-
-&dss {
-	status = "okay";
-};
 
-&gpio6 {
 	pwm8: dmtimer-pwm-8 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&vibrator_direction_pin>;
@@ -192,7 +186,10 @@
 		pwm-names = "enable", "direction";
 		direction-duty-cycle-ns = <10000000>;
 	};
+};
 
+&dss {
+	status = "okay";
 };
 
 &dsi1 {
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 106a1466518d..746565a876dc 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -48,6 +48,7 @@ saved_pc	.req	lr
  * from those features make this path too inefficient.
  */
 ret_fast_syscall:
+__ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
 	disable_irq_notrace			@ disable interrupts
@@ -78,6 +79,7 @@ fast_work_pending:
  * call.
  */
 ret_fast_syscall:
+__ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
 	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
@@ -255,7 +257,7 @@ local_restart:
 	tst	r10, #_TIF_SYSCALL_WORK		@ are we tracing syscalls?
 	bne	__sys_trace
 
-	invoke_syscall tbl, scno, r10, ret_fast_syscall
+	invoke_syscall tbl, scno, r10, __ret_fast_syscall
 
 	add	r1, sp, #S_OFF
 2:	cmp	scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE)
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 225d1c58d2de..d9c299133111 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -338,6 +338,7 @@ static struct vm_area_struct gate_vma = {
 
 static int __init gate_vma_init(void)
 {
+	vma_init(&gate_vma, NULL);
 	gate_vma.vm_page_prot = PAGE_READONLY_EXEC;
 	return 0;
 }
diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index d7c9a8476d57..5a16ea74e28a 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -4,6 +4,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
 #include <linux/spi/pxa2xx_spi.h>
 #include <linux/platform_data/i2c-pxa.h>
 
@@ -59,16 +60,6 @@ static struct resource pxamci_resources[] = {
 		.end	= IRQ_MMC,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		.start	= 21,
-		.end	= 21,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		.start	= 22,
-		.end	= 22,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 static u64 pxamci_dmamask = 0xffffffffUL;
@@ -406,16 +397,6 @@ static struct resource pxa_ir_resources[] = {
 		.end	= 0x40700023,
 		.flags  = IORESOURCE_MEM,
 	},
-	[5] = {
-		.start  = 17,
-		.end	= 17,
-		.flags  = IORESOURCE_DMA,
-	},
-	[6] = {
-		.start  = 18,
-		.end	= 18,
-		.flags  = IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa_device_ficp = {
@@ -544,18 +525,6 @@ static struct resource pxa25x_resource_ssp[] = {
 		.end	= IRQ_SSP,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 13,
-		.end	= 13,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 14,
-		.end	= 14,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa25x_device_ssp = {
@@ -582,18 +551,6 @@ static struct resource pxa25x_resource_nssp[] = {
 		.end	= IRQ_NSSP,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 15,
-		.end	= 15,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 16,
-		.end	= 16,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa25x_device_nssp = {
@@ -620,18 +577,6 @@ static struct resource pxa25x_resource_assp[] = {
 		.end	= IRQ_ASSP,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 23,
-		.end	= 23,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 24,
-		.end	= 24,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa25x_device_assp = {
@@ -750,18 +695,6 @@ static struct resource pxa27x_resource_ssp1[] = {
 		.end	= IRQ_SSP,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 13,
-		.end	= 13,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 14,
-		.end	= 14,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa27x_device_ssp1 = {
@@ -788,18 +721,6 @@ static struct resource pxa27x_resource_ssp2[] = {
 		.end	= IRQ_SSP2,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 15,
-		.end	= 15,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 16,
-		.end	= 16,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa27x_device_ssp2 = {
@@ -826,18 +747,6 @@ static struct resource pxa27x_resource_ssp3[] = {
 		.end	= IRQ_SSP3,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 66,
-		.end	= 66,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 67,
-		.end	= 67,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa27x_device_ssp3 = {
@@ -894,16 +803,6 @@ static struct resource pxa3xx_resources_mci2[] = {
 		.end	= IRQ_MMC2,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		.start	= 93,
-		.end	= 93,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		.start	= 94,
-		.end	= 94,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa3xx_device_mci2 = {
@@ -933,16 +832,6 @@ static struct resource pxa3xx_resources_mci3[] = {
 		.end	= IRQ_MMC3,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		.start	= 100,
-		.end	= 100,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		.start	= 101,
-		.end	= 101,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa3xx_device_mci3 = {
@@ -1020,18 +909,6 @@ static struct resource pxa3xx_resources_nand[] = {
 		.end	= IRQ_NAND,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for Data DMA */
-		.start	= 97,
-		.end	= 97,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for Command DMA */
-		.start	= 99,
-		.end	= 99,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 static u64 pxa3xx_nand_dma_mask = DMA_BIT_MASK(32);
@@ -1065,18 +942,6 @@ static struct resource pxa3xx_resource_ssp4[] = {
 		.end	= IRQ_SSP4,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 2,
-		.end	= 2,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 3,
-		.end	= 3,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 /*
@@ -1202,11 +1067,6 @@ void __init pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_master *info)
 	platform_device_add(pd);
 }
 
-static struct mmp_dma_platdata pxa_dma_pdata = {
-	.dma_channels	= 0,
-	.nb_requestors	= 0,
-};
-
 static struct resource pxa_dma_resource[] = {
 	[0] = {
 		.start	= 0x40000000,
@@ -1233,9 +1093,7 @@ static struct platform_device pxa2xx_pxa_dma = {
 	.resource	= pxa_dma_resource,
 };
 
-void __init pxa2xx_set_dmac_info(int nb_channels, int nb_requestors)
+void __init pxa2xx_set_dmac_info(struct mmp_dma_platdata *dma_pdata)
 {
-	pxa_dma_pdata.dma_channels = nb_channels;
-	pxa_dma_pdata.nb_requestors = nb_requestors;
-	pxa_register_device(&pxa2xx_pxa_dma, &pxa_dma_pdata);
+	pxa_register_device(&pxa2xx_pxa_dma, dma_pdata);
 }
diff --git a/arch/arm/mach-pxa/devices.h b/arch/arm/mach-pxa/devices.h
index 11263f7c455b..498b07bc6a3e 100644
--- a/arch/arm/mach-pxa/devices.h
+++ b/arch/arm/mach-pxa/devices.h
@@ -1,4 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#define PDMA_FILTER_PARAM(_prio, _requestor) (&(struct pxad_param) { \
+	.prio = PXAD_PRIO_##_prio, .drcmr = _requestor })
+struct mmp_dma_platdata;
+
 extern struct platform_device pxa_device_pmu;
 extern struct platform_device pxa_device_mci;
 extern struct platform_device pxa3xx_device_mci2;
@@ -55,7 +59,7 @@ extern struct platform_device pxa3xx_device_gpio;
 extern struct platform_device pxa93x_device_gpio;
 
 void __init pxa_register_device(struct platform_device *dev, void *data);
-void __init pxa2xx_set_dmac_info(int nb_channels, int nb_requestors);
+void __init pxa2xx_set_dmac_info(struct mmp_dma_platdata *dma_pdata);
 
 struct i2c_pxa_platform_data;
 extern void pxa_set_i2c_info(struct i2c_pxa_platform_data *info);
diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c
index ba431fad5c47..ab8808ce7e21 100644
--- a/arch/arm/mach-pxa/pxa25x.c
+++ b/arch/arm/mach-pxa/pxa25x.c
@@ -16,6 +16,8 @@
  * initialization stuff for PXA machines which can be overridden later if
  * need be.
  */
+#include <linux/dmaengine.h>
+#include <linux/dma/pxa-dma.h>
 #include <linux/gpio.h>
 #include <linux/gpio-pxa.h>
 #include <linux/module.h>
@@ -26,6 +28,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/irq.h>
 #include <linux/irqchip.h>
+#include <linux/platform_data/mmp_dma.h>
 
 #include <asm/mach/map.h>
 #include <asm/suspend.h>
@@ -201,6 +204,39 @@ static struct platform_device *pxa25x_devices[] __initdata = {
 	&pxa_device_asoc_platform,
 };
 
+static const struct dma_slave_map pxa25x_slave_map[] = {
+	/* PXA25x, PXA27x and PXA3xx common entries */
+	{ "pxa2xx-ac97", "pcm_pcm_mic_mono", PDMA_FILTER_PARAM(LOWEST, 8) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_in", PDMA_FILTER_PARAM(LOWEST, 9) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_out",
+	  PDMA_FILTER_PARAM(LOWEST, 10) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_in", PDMA_FILTER_PARAM(LOWEST, 11) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_out", PDMA_FILTER_PARAM(LOWEST, 12) },
+	{ "pxa-ssp-dai.1", "rx", PDMA_FILTER_PARAM(LOWEST, 13) },
+	{ "pxa-ssp-dai.1", "tx", PDMA_FILTER_PARAM(LOWEST, 14) },
+	{ "pxa-ssp-dai.2", "rx", PDMA_FILTER_PARAM(LOWEST, 15) },
+	{ "pxa-ssp-dai.2", "tx", PDMA_FILTER_PARAM(LOWEST, 16) },
+	{ "pxa2xx-ir", "rx", PDMA_FILTER_PARAM(LOWEST, 17) },
+	{ "pxa2xx-ir", "tx", PDMA_FILTER_PARAM(LOWEST, 18) },
+	{ "pxa2xx-mci.0", "rx", PDMA_FILTER_PARAM(LOWEST, 21) },
+	{ "pxa2xx-mci.0", "tx", PDMA_FILTER_PARAM(LOWEST, 22) },
+
+	/* PXA25x specific map */
+	{ "pxa25x-ssp.0", "rx", PDMA_FILTER_PARAM(LOWEST, 13) },
+	{ "pxa25x-ssp.0", "tx", PDMA_FILTER_PARAM(LOWEST, 14) },
+	{ "pxa25x-nssp.1", "rx", PDMA_FILTER_PARAM(LOWEST, 15) },
+	{ "pxa25x-nssp.1", "tx", PDMA_FILTER_PARAM(LOWEST, 16) },
+	{ "pxa25x-nssp.2", "rx", PDMA_FILTER_PARAM(LOWEST, 23) },
+	{ "pxa25x-nssp.2", "tx", PDMA_FILTER_PARAM(LOWEST, 24) },
+};
+
+static struct mmp_dma_platdata pxa25x_dma_pdata = {
+	.dma_channels	= 16,
+	.nb_requestors	= 40,
+	.slave_map	= pxa25x_slave_map,
+	.slave_map_cnt	= ARRAY_SIZE(pxa25x_slave_map),
+};
+
 static int __init pxa25x_init(void)
 {
 	int ret = 0;
@@ -215,7 +251,7 @@ static int __init pxa25x_init(void)
 		register_syscore_ops(&pxa2xx_mfp_syscore_ops);
 
 		if (!of_have_populated_dt()) {
-			pxa2xx_set_dmac_info(16, 40);
+			pxa2xx_set_dmac_info(&pxa25x_dma_pdata);
 			pxa_register_device(&pxa25x_device_gpio, &pxa25x_gpio_info);
 			ret = platform_add_devices(pxa25x_devices,
 						   ARRAY_SIZE(pxa25x_devices));
diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c
index 0c06f383ad52..5a8990a9313d 100644
--- a/arch/arm/mach-pxa/pxa27x.c
+++ b/arch/arm/mach-pxa/pxa27x.c
@@ -11,6 +11,8 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/dmaengine.h>
+#include <linux/dma/pxa-dma.h>
 #include <linux/gpio.h>
 #include <linux/gpio-pxa.h>
 #include <linux/module.h>
@@ -23,6 +25,7 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/platform_data/i2c-pxa.h>
+#include <linux/platform_data/mmp_dma.h>
 
 #include <asm/mach/map.h>
 #include <mach/hardware.h>
@@ -297,6 +300,40 @@ static struct platform_device *devices[] __initdata = {
 	&pxa27x_device_pwm1,
 };
 
+static const struct dma_slave_map pxa27x_slave_map[] = {
+	/* PXA25x, PXA27x and PXA3xx common entries */
+	{ "pxa2xx-ac97", "pcm_pcm_mic_mono", PDMA_FILTER_PARAM(LOWEST, 8) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_in", PDMA_FILTER_PARAM(LOWEST, 9) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_out",
+	  PDMA_FILTER_PARAM(LOWEST, 10) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_in", PDMA_FILTER_PARAM(LOWEST, 11) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_out", PDMA_FILTER_PARAM(LOWEST, 12) },
+	{ "pxa-ssp-dai.0", "rx", PDMA_FILTER_PARAM(LOWEST, 13) },
+	{ "pxa-ssp-dai.0", "tx", PDMA_FILTER_PARAM(LOWEST, 14) },
+	{ "pxa-ssp-dai.1", "rx", PDMA_FILTER_PARAM(LOWEST, 15) },
+	{ "pxa-ssp-dai.1", "tx", PDMA_FILTER_PARAM(LOWEST, 16) },
+	{ "pxa2xx-ir", "rx", PDMA_FILTER_PARAM(LOWEST, 17) },
+	{ "pxa2xx-ir", "tx", PDMA_FILTER_PARAM(LOWEST, 18) },
+	{ "pxa2xx-mci.0", "rx", PDMA_FILTER_PARAM(LOWEST, 21) },
+	{ "pxa2xx-mci.0", "tx", PDMA_FILTER_PARAM(LOWEST, 22) },
+	{ "pxa-ssp-dai.2", "rx", PDMA_FILTER_PARAM(LOWEST, 66) },
+	{ "pxa-ssp-dai.2", "tx", PDMA_FILTER_PARAM(LOWEST, 67) },
+
+	/* PXA27x specific map */
+	{ "pxa2xx-i2s", "rx", PDMA_FILTER_PARAM(LOWEST, 2) },
+	{ "pxa2xx-i2s", "tx", PDMA_FILTER_PARAM(LOWEST, 3) },
+	{ "pxa27x-camera.0", "CI_Y", PDMA_FILTER_PARAM(HIGHEST, 68) },
+	{ "pxa27x-camera.0", "CI_U", PDMA_FILTER_PARAM(HIGHEST, 69) },
+	{ "pxa27x-camera.0", "CI_V", PDMA_FILTER_PARAM(HIGHEST, 70) },
+};
+
+static struct mmp_dma_platdata pxa27x_dma_pdata = {
+	.dma_channels	= 32,
+	.nb_requestors	= 75,
+	.slave_map	= pxa27x_slave_map,
+	.slave_map_cnt	= ARRAY_SIZE(pxa27x_slave_map),
+};
+
 static int __init pxa27x_init(void)
 {
 	int ret = 0;
@@ -313,7 +350,7 @@ static int __init pxa27x_init(void)
 		if (!of_have_populated_dt()) {
 			pxa_register_device(&pxa27x_device_gpio,
 					    &pxa27x_gpio_info);
-			pxa2xx_set_dmac_info(32, 75);
+			pxa2xx_set_dmac_info(&pxa27x_dma_pdata);
 			ret = platform_add_devices(devices,
 						   ARRAY_SIZE(devices));
 		}
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index 8c64f93b669b..df9c8970adcf 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -12,6 +12,8 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/dmaengine.h>
+#include <linux/dma/pxa-dma.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -24,6 +26,7 @@
 #include <linux/of.h>
 #include <linux/syscore_ops.h>
 #include <linux/platform_data/i2c-pxa.h>
+#include <linux/platform_data/mmp_dma.h>
 
 #include <asm/mach/map.h>
 #include <asm/suspend.h>
@@ -421,6 +424,42 @@ static struct platform_device *devices[] __initdata = {
 	&pxa27x_device_pwm1,
 };
 
+static const struct dma_slave_map pxa3xx_slave_map[] = {
+	/* PXA25x, PXA27x and PXA3xx common entries */
+	{ "pxa2xx-ac97", "pcm_pcm_mic_mono", PDMA_FILTER_PARAM(LOWEST, 8) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_in", PDMA_FILTER_PARAM(LOWEST, 9) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_out",
+	  PDMA_FILTER_PARAM(LOWEST, 10) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_in", PDMA_FILTER_PARAM(LOWEST, 11) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_out", PDMA_FILTER_PARAM(LOWEST, 12) },
+	{ "pxa-ssp-dai.0", "rx", PDMA_FILTER_PARAM(LOWEST, 13) },
+	{ "pxa-ssp-dai.0", "tx", PDMA_FILTER_PARAM(LOWEST, 14) },
+	{ "pxa-ssp-dai.1", "rx", PDMA_FILTER_PARAM(LOWEST, 15) },
+	{ "pxa-ssp-dai.1", "tx", PDMA_FILTER_PARAM(LOWEST, 16) },
+	{ "pxa2xx-ir", "rx", PDMA_FILTER_PARAM(LOWEST, 17) },
+	{ "pxa2xx-ir", "tx", PDMA_FILTER_PARAM(LOWEST, 18) },
+	{ "pxa2xx-mci.0", "rx", PDMA_FILTER_PARAM(LOWEST, 21) },
+	{ "pxa2xx-mci.0", "tx", PDMA_FILTER_PARAM(LOWEST, 22) },
+	{ "pxa-ssp-dai.2", "rx", PDMA_FILTER_PARAM(LOWEST, 66) },
+	{ "pxa-ssp-dai.2", "tx", PDMA_FILTER_PARAM(LOWEST, 67) },
+
+	/* PXA3xx specific map */
+	{ "pxa-ssp-dai.3", "rx", PDMA_FILTER_PARAM(LOWEST, 2) },
+	{ "pxa-ssp-dai.3", "tx", PDMA_FILTER_PARAM(LOWEST, 3) },
+	{ "pxa2xx-mci.1", "rx", PDMA_FILTER_PARAM(LOWEST, 93) },
+	{ "pxa2xx-mci.1", "tx", PDMA_FILTER_PARAM(LOWEST, 94) },
+	{ "pxa3xx-nand", "data", PDMA_FILTER_PARAM(LOWEST, 97) },
+	{ "pxa2xx-mci.2", "rx", PDMA_FILTER_PARAM(LOWEST, 100) },
+	{ "pxa2xx-mci.2", "tx", PDMA_FILTER_PARAM(LOWEST, 101) },
+};
+
+static struct mmp_dma_platdata pxa3xx_dma_pdata = {
+	.dma_channels	= 32,
+	.nb_requestors	= 100,
+	.slave_map	= pxa3xx_slave_map,
+	.slave_map_cnt	= ARRAY_SIZE(pxa3xx_slave_map),
+};
+
 static int __init pxa3xx_init(void)
 {
 	int ret = 0;
@@ -456,7 +495,7 @@ static int __init pxa3xx_init(void)
 		if (of_have_populated_dt())
 			return 0;
 
-		pxa2xx_set_dmac_info(32, 100);
+		pxa2xx_set_dmac_info(&pxa3xx_dma_pdata);
 		ret = platform_add_devices(devices, ARRAY_SIZE(devices));
 		if (ret)
 			return ret;
diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c
index 39aef4876ed4..04b2f22c2739 100644
--- a/arch/arm/mach-rpc/ecard.c
+++ b/arch/arm/mach-rpc/ecard.c
@@ -212,7 +212,7 @@ static DEFINE_MUTEX(ecard_mutex);
  */
 static void ecard_init_pgtables(struct mm_struct *mm)
 {
-	struct vm_area_struct vma;
+	struct vm_area_struct vma = TLB_FLUSH_VMA(mm, VM_EXEC);
 
 	/* We want to set up the page tables for the following mapping:
 	 *  Virtual	Physical
@@ -237,9 +237,6 @@ static void ecard_init_pgtables(struct mm_struct *mm)
 
 	memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE));
 
-	vma.vm_flags = VM_EXEC;
-	vma.vm_mm = mm;
-
 	flush_tlb_range(&vma, IO_START, IO_START + IO_SIZE);
 	flush_tlb_range(&vma, EASI_START, EASI_START + EASI_SIZE);
 }
diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c
index ba13f793fbce..ed36dcab80f1 100644
--- a/arch/arm/plat-pxa/ssp.c
+++ b/arch/arm/plat-pxa/ssp.c
@@ -127,53 +127,6 @@ static int pxa_ssp_probe(struct platform_device *pdev)
 	if (IS_ERR(ssp->clk))
 		return PTR_ERR(ssp->clk);
 
-	if (dev->of_node) {
-		struct of_phandle_args dma_spec;
-		struct device_node *np = dev->of_node;
-		int ret;
-
-		/*
-		 * FIXME: we should allocate the DMA channel from this
-		 * context and pass the channel down to the ssp users.
-		 * For now, we lookup the rx and tx indices manually
-		 */
-
-		/* rx */
-		ret = of_parse_phandle_with_args(np, "dmas", "#dma-cells",
-						 0, &dma_spec);
-
-		if (ret) {
-			dev_err(dev, "Can't parse dmas property\n");
-			return -ENODEV;
-		}
-		ssp->drcmr_rx = dma_spec.args[0];
-		of_node_put(dma_spec.np);
-
-		/* tx */
-		ret = of_parse_phandle_with_args(np, "dmas", "#dma-cells",
-						 1, &dma_spec);
-		if (ret) {
-			dev_err(dev, "Can't parse dmas property\n");
-			return -ENODEV;
-		}
-		ssp->drcmr_tx = dma_spec.args[0];
-		of_node_put(dma_spec.np);
-	} else {
-		res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-		if (res == NULL) {
-			dev_err(dev, "no SSP RX DRCMR defined\n");
-			return -ENODEV;
-		}
-		ssp->drcmr_rx = res->start;
-
-		res = platform_get_resource(pdev, IORESOURCE_DMA, 1);
-		if (res == NULL) {
-			dev_err(dev, "no SSP TX DRCMR defined\n");
-			return -ENODEV;
-		}
-		ssp->drcmr_tx = res->start;
-	}
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (res == NULL) {
 		dev_err(dev, "no memory resource defined\n");
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 7cf0b1aa6ea8..8a10f1d7199a 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -488,9 +488,13 @@ static int gcm_decrypt(struct aead_request *req)
 			err = skcipher_walk_done(&walk,
 						 walk.nbytes % AES_BLOCK_SIZE);
 		}
-		if (walk.nbytes)
-			pmull_gcm_encrypt_block(iv, iv, NULL,
+		if (walk.nbytes) {
+			kernel_neon_begin();
+			pmull_gcm_encrypt_block(iv, iv, ctx->aes_key.key_enc,
 						num_rounds(&ctx->aes_key));
+			kernel_neon_end();
+		}
+
 	} else {
 		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv,
 				    num_rounds(&ctx->aes_key));
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index ffdaea7954bb..0ad1cf233470 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -37,7 +37,7 @@ static inline void __tlb_remove_table(void *_table)
 
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
-	struct vm_area_struct vma = { .vm_mm = tlb->mm, };
+	struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
 
 	/*
 	 * The ASID allocator will either invalidate the ASID or mark
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index f24892a40d2c..c6d80743f4ed 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1351,9 +1351,9 @@ static void __update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 
 static void update_cpu_capabilities(u16 scope_mask)
 {
-	__update_cpu_capabilities(arm64_features, scope_mask, "detected:");
 	__update_cpu_capabilities(arm64_errata, scope_mask,
 				  "enabling workaround for");
+	__update_cpu_capabilities(arm64_features, scope_mask, "detected:");
 }
 
 static int __enable_cpu_capability(void *arg)
@@ -1408,8 +1408,8 @@ __enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 
 static void __init enable_cpu_capabilities(u16 scope_mask)
 {
-	__enable_cpu_capabilities(arm64_features, scope_mask);
 	__enable_cpu_capabilities(arm64_errata, scope_mask);
+	__enable_cpu_capabilities(arm64_features, scope_mask);
 }
 
 /*
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index ecc6818191df..192b3ba07075 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -108,7 +108,6 @@ static pte_t get_clear_flush(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	struct vm_area_struct vma = { .vm_mm = mm };
 	pte_t orig_pte = huge_ptep_get(ptep);
 	bool valid = pte_valid(orig_pte);
 	unsigned long i, saddr = addr;
@@ -125,8 +124,10 @@ static pte_t get_clear_flush(struct mm_struct *mm,
 			orig_pte = pte_mkdirty(orig_pte);
 	}
 
-	if (valid)
+	if (valid) {
+		struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
 		flush_tlb_range(&vma, saddr, addr);
+	}
 	return orig_pte;
 }
 
@@ -145,7 +146,7 @@ static void clear_flush(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	struct vm_area_struct vma = { .vm_mm = mm };
+	struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
 	unsigned long i, saddr = addr;
 
 	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 325cfb3b858a..9abf8a1e7b25 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -611,11 +611,13 @@ void __init mem_init(void)
 	BUILD_BUG_ON(TASK_SIZE_32			> TASK_SIZE_64);
 #endif
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
 	/*
 	 * Make sure we chose the upper bound of sizeof(struct page)
-	 * correctly.
+	 * correctly when sizing the VMEMMAP array.
 	 */
 	BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT));
+#endif
 
 	if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) {
 		extern int sysctl_overcommit_memory;
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index 44f0ac0df308..516355a774bf 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -115,12 +115,11 @@ ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned
 		flush_tlb_all();
 	} else {
 		/*
-		 * XXX fix me: flush_tlb_range() should take an mm pointer instead of a
-		 * vma pointer.
+		 * flush_tlb_range() takes a vma instead of a mm pointer because
+		 * some architectures want the vm_flags for ITLB/DTLB flush.
 		 */
-		struct vm_area_struct vma;
+		struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
 
-		vma.vm_mm = tlb->mm;
 		/* flush the address range from the tlb: */
 		flush_tlb_range(&vma, start, end);
 		/* now flush the virt. page-table area mapping the address range: */
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 3b38c717008a..46bff1661836 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -2278,17 +2278,15 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 	DPRINT(("smpl_buf @%p\n", smpl_buf));
 
 	/* allocate vma */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (!vma) {
 		DPRINT(("Cannot allocate vma\n"));
 		goto error_kmem;
 	}
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
 	/*
 	 * partially initialize the vma for the sampling buffer
 	 */
-	vma->vm_mm	     = mm;
 	vma->vm_file	     = get_file(filp);
 	vma->vm_flags	     = VM_READ|VM_MAYREAD|VM_DONTEXPAND|VM_DONTDUMP;
 	vma->vm_page_prot    = PAGE_READONLY; /* XXX may need to change */
@@ -2346,7 +2344,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 	return 0;
 
 error:
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 error_kmem:
 	pfm_rvfree(smpl_buf, size);
 
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 18278b448530..3b85c3ecac38 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -114,10 +114,9 @@ ia64_init_addr_space (void)
 	 * the problem.  When the process attempts to write to the register backing store
 	 * for the first time, it will get a SEGFAULT in this case.
 	 */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(current->mm);
 	if (vma) {
-		INIT_LIST_HEAD(&vma->anon_vma_chain);
-		vma->vm_mm = current->mm;
+		vma_set_anonymous(vma);
 		vma->vm_start = current->thread.rbs_bot & PAGE_MASK;
 		vma->vm_end = vma->vm_start + PAGE_SIZE;
 		vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT;
@@ -125,7 +124,7 @@ ia64_init_addr_space (void)
 		down_write(&current->mm->mmap_sem);
 		if (insert_vm_struct(current->mm, vma)) {
 			up_write(&current->mm->mmap_sem);
-			kmem_cache_free(vm_area_cachep, vma);
+			vm_area_free(vma);
 			return;
 		}
 		up_write(&current->mm->mmap_sem);
@@ -133,10 +132,9 @@ ia64_init_addr_space (void)
 
 	/* map NaT-page at address zero to speed up speculative dereferencing of NULL: */
 	if (!(current->personality & MMAP_PAGE_ZERO)) {
-		vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+		vma = vm_area_alloc(current->mm);
 		if (vma) {
-			INIT_LIST_HEAD(&vma->anon_vma_chain);
-			vma->vm_mm = current->mm;
+			vma_set_anonymous(vma);
 			vma->vm_end = PAGE_SIZE;
 			vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT);
 			vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO |
@@ -144,7 +142,7 @@ ia64_init_addr_space (void)
 			down_write(&current->mm->mmap_sem);
 			if (insert_vm_struct(current->mm, vma)) {
 				up_write(&current->mm->mmap_sem);
-				kmem_cache_free(vm_area_cachep, vma);
+				vm_area_free(vma);
 				return;
 			}
 			up_write(&current->mm->mmap_sem);
@@ -277,7 +275,7 @@ static struct vm_area_struct gate_vma;
 
 static int __init gate_vma_init(void)
 {
-	gate_vma.vm_mm = NULL;
+	vma_init(&gate_vma, NULL);
 	gate_vma.vm_start = FIXADDR_USER_START;
 	gate_vma.vm_end = FIXADDR_USER_END;
 	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c
index 10a405d593df..c782b10ddf50 100644
--- a/arch/mips/ath79/common.c
+++ b/arch/mips/ath79/common.c
@@ -58,7 +58,7 @@ EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init);
 
 void ath79_ddr_wb_flush(u32 reg)
 {
-	void __iomem *flush_reg = ath79_ddr_wb_flush_base + reg;
+	void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4);
 
 	/* Flush the DDR write buffer. */
 	__raw_writel(0x1, flush_reg);
diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c
index 8c9cbf13d32a..6054d49e608e 100644
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -212,12 +212,6 @@ static int __init bcm47xx_cpu_fixes(void)
 		 */
 		if (bcm47xx_bus.bcma.bus.chipinfo.id == BCMA_CHIP_ID_BCM4706)
 			cpu_wait = NULL;
-
-		/*
-		 * BCM47XX Erratum "R10: PCIe Transactions Periodically Fail"
-		 * Enable ExternalSync for sync instruction to take effect
-		 */
-		set_c0_config7(MIPS_CONF7_ES);
 		break;
 #endif
 	}
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 0bc270806ec5..ae461d91cd1f 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -681,8 +681,6 @@
 #define MIPS_CONF7_WII		(_ULCAST_(1) << 31)
 
 #define MIPS_CONF7_RPS		(_ULCAST_(1) << 2)
-/* ExternalSync */
-#define MIPS_CONF7_ES		(_ULCAST_(1) << 8)
 
 #define MIPS_CONF7_IAR		(_ULCAST_(1) << 10)
 #define MIPS_CONF7_AR		(_ULCAST_(1) << 16)
@@ -2767,7 +2765,6 @@ __BUILD_SET_C0(status)
 __BUILD_SET_C0(cause)
 __BUILD_SET_C0(config)
 __BUILD_SET_C0(config5)
-__BUILD_SET_C0(config7)
 __BUILD_SET_C0(intcontrol)
 __BUILD_SET_C0(intctl)
 __BUILD_SET_C0(srsmap)
diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c
index 9632436d74d7..c2e94cf5ecda 100644
--- a/arch/mips/pci/pci.c
+++ b/arch/mips/pci/pci.c
@@ -54,5 +54,5 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
 	phys_addr_t size = resource_size(rsrc);
 
 	*start = fixup_bigphys_addr(rsrc->start, size);
-	*end = rsrc->start + size;
+	*end = rsrc->start + size - 1;
 }
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index 6aed974276d8..34f7222c5efe 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -12,17 +12,17 @@ config NDS32
 	select CLONE_BACKWARDS
 	select COMMON_CLK
 	select DMA_NONCOHERENT_OPS
-	select GENERIC_ASHLDI3
-	select GENERIC_ASHRDI3
-	select GENERIC_LSHRDI3
-	select GENERIC_CMPDI2
-	select GENERIC_MULDI3
-	select GENERIC_UCMPDI2
 	select GENERIC_ATOMIC64
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IRQ_CHIP
 	select GENERIC_IRQ_SHOW
+	select GENERIC_LIB_ASHLDI3
+	select GENERIC_LIB_ASHRDI3
+	select GENERIC_LIB_CMPDI2
+	select GENERIC_LIB_LSHRDI3
+	select GENERIC_LIB_MULDI3
+	select GENERIC_LIB_UCMPDI2
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile
index 513bb2e9baf9..031c676821ff 100644
--- a/arch/nds32/Makefile
+++ b/arch/nds32/Makefile
@@ -34,10 +34,12 @@ ifdef CONFIG_CPU_LITTLE_ENDIAN
 KBUILD_CFLAGS   += $(call cc-option, -EL)
 KBUILD_AFLAGS   += $(call cc-option, -EL)
 LDFLAGS         += $(call cc-option, -EL)
+CHECKFLAGS      += -D__NDS32_EL__
 else
 KBUILD_CFLAGS   += $(call cc-option, -EB)
 KBUILD_AFLAGS   += $(call cc-option, -EB)
 LDFLAGS         += $(call cc-option, -EB)
+CHECKFLAGS      += -D__NDS32_EB__
 endif
 
 boot := arch/nds32/boot
diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h
index 10b48f0d8e85..8b26198d51bb 100644
--- a/arch/nds32/include/asm/cacheflush.h
+++ b/arch/nds32/include/asm/cacheflush.h
@@ -8,6 +8,8 @@
 
 #define PG_dcache_dirty PG_arch_1
 
+void flush_icache_range(unsigned long start, unsigned long end);
+void flush_icache_page(struct vm_area_struct *vma, struct page *page);
 #ifdef CONFIG_CPU_CACHE_ALIASING
 void flush_cache_mm(struct mm_struct *mm);
 void flush_cache_dup_mm(struct mm_struct *mm);
@@ -34,13 +36,16 @@ void flush_anon_page(struct vm_area_struct *vma,
 void flush_kernel_dcache_page(struct page *page);
 void flush_kernel_vmap_range(void *addr, int size);
 void invalidate_kernel_vmap_range(void *addr, int size);
-void flush_icache_range(unsigned long start, unsigned long end);
-void flush_icache_page(struct vm_area_struct *vma, struct page *page);
 #define flush_dcache_mmap_lock(mapping)   xa_lock_irq(&(mapping)->i_pages)
 #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&(mapping)->i_pages)
 
 #else
 #include <asm-generic/cacheflush.h>
+#undef flush_icache_range
+#undef flush_icache_page
+#undef flush_icache_user_range
+void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+	                     unsigned long addr, int len);
 #endif
 
 #endif /* __NDS32_CACHEFLUSH_H__ */
diff --git a/arch/nds32/include/asm/futex.h b/arch/nds32/include/asm/futex.h
index eab5e84bd991..cb6cb91cfdf8 100644
--- a/arch/nds32/include/asm/futex.h
+++ b/arch/nds32/include/asm/futex.h
@@ -16,7 +16,7 @@
 	"	.popsection\n"					\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"4:	move	%0, " err_reg "\n"			\
-	"	j	3b\n"					\
+	"	b	3b\n"					\
 	"	.popsection"
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
diff --git a/arch/nds32/kernel/setup.c b/arch/nds32/kernel/setup.c
index 2f5b2ccebe47..63a1a5ef5219 100644
--- a/arch/nds32/kernel/setup.c
+++ b/arch/nds32/kernel/setup.c
@@ -278,7 +278,8 @@ static void __init setup_memory(void)
 
 void __init setup_arch(char **cmdline_p)
 {
-	early_init_devtree( __dtb_start);
+	early_init_devtree(__atags_pointer ? \
+		phys_to_virt(__atags_pointer) : __dtb_start);
 
 	setup_cpuinfo();
 
diff --git a/arch/nds32/mm/cacheflush.c b/arch/nds32/mm/cacheflush.c
index ce8fd34497bf..254703653b6f 100644
--- a/arch/nds32/mm/cacheflush.c
+++ b/arch/nds32/mm/cacheflush.c
@@ -13,7 +13,39 @@
 
 extern struct cache_info L1_cache_info[2];
 
-#ifndef CONFIG_CPU_CACHE_ALIASING
+void flush_icache_range(unsigned long start, unsigned long end)
+{
+	unsigned long line_size, flags;
+	line_size = L1_cache_info[DCACHE].line_size;
+	start = start & ~(line_size - 1);
+	end = (end + line_size - 1) & ~(line_size - 1);
+	local_irq_save(flags);
+	cpu_cache_wbinval_range(start, end, 1);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_icache_range);
+
+void flush_icache_page(struct vm_area_struct *vma, struct page *page)
+{
+	unsigned long flags;
+	unsigned long kaddr;
+	local_irq_save(flags);
+	kaddr = (unsigned long)kmap_atomic(page);
+	cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC);
+	kunmap_atomic((void *)kaddr);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_icache_page);
+
+void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+	                     unsigned long addr, int len)
+{
+	unsigned long kaddr;
+	kaddr = (unsigned long)kmap_atomic(page) + (addr & ~PAGE_MASK);
+	flush_icache_range(kaddr, kaddr + len);
+	kunmap_atomic((void *)kaddr);
+}
+
 void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 		      pte_t * pte)
 {
@@ -35,19 +67,15 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 
 	if ((test_and_clear_bit(PG_dcache_dirty, &page->flags)) ||
 	    (vma->vm_flags & VM_EXEC)) {
-
-		if (!PageHighMem(page)) {
-			cpu_cache_wbinval_page((unsigned long)
-					       page_address(page),
-					       vma->vm_flags & VM_EXEC);
-		} else {
-			unsigned long kaddr = (unsigned long)kmap_atomic(page);
-			cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC);
-			kunmap_atomic((void *)kaddr);
-		}
+		unsigned long kaddr;
+		local_irq_save(flags);
+		kaddr = (unsigned long)kmap_atomic(page);
+		cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC);
+		kunmap_atomic((void *)kaddr);
+		local_irq_restore(flags);
 	}
 }
-#else
+#ifdef CONFIG_CPU_CACHE_ALIASING
 extern pte_t va_present(struct mm_struct *mm, unsigned long addr);
 
 static inline unsigned long aliasing(unsigned long addr, unsigned long page)
@@ -317,52 +345,4 @@ void invalidate_kernel_vmap_range(void *addr, int size)
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(invalidate_kernel_vmap_range);
-
-void flush_icache_range(unsigned long start, unsigned long end)
-{
-	unsigned long line_size, flags;
-	line_size = L1_cache_info[DCACHE].line_size;
-	start = start & ~(line_size - 1);
-	end = (end + line_size - 1) & ~(line_size - 1);
-	local_irq_save(flags);
-	cpu_cache_wbinval_range(start, end, 1);
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(flush_icache_range);
-
-void flush_icache_page(struct vm_area_struct *vma, struct page *page)
-{
-	unsigned long flags;
-	local_irq_save(flags);
-	cpu_cache_wbinval_page((unsigned long)page_address(page),
-			       vma->vm_flags & VM_EXEC);
-	local_irq_restore(flags);
-}
-
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
-		      pte_t * pte)
-{
-	struct page *page;
-	unsigned long flags;
-	unsigned long pfn = pte_pfn(*pte);
-
-	if (!pfn_valid(pfn))
-		return;
-
-	if (vma->vm_mm == current->active_mm) {
-		local_irq_save(flags);
-		__nds32__mtsr_dsb(addr, NDS32_SR_TLB_VPN);
-		__nds32__tlbop_rwr(*pte);
-		__nds32__isb();
-		local_irq_restore(flags);
-	}
-
-	page = pfn_to_page(pfn);
-	if (test_and_clear_bit(PG_dcache_dirty, &page->flags) ||
-	    (vma->vm_flags & VM_EXEC)) {
-		local_irq_save(flags);
-		cpu_dcache_wbinval_page((unsigned long)page_address(page));
-		local_irq_restore(flags);
-	}
-}
 #endif
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 2ea575cb3401..fb96206de317 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -243,6 +243,7 @@ endif
 cpu-as-$(CONFIG_4xx)		+= -Wa,-m405
 cpu-as-$(CONFIG_ALTIVEC)	+= $(call as-option,-Wa$(comma)-maltivec)
 cpu-as-$(CONFIG_E200)		+= -Wa,-me200
+cpu-as-$(CONFIG_E500)		+= -Wa,-me500
 cpu-as-$(CONFIG_PPC_BOOK3S_64)	+= -Wa,-mpower4
 cpu-as-$(CONFIG_PPC_E500MC)	+= $(call as-option,-Wa$(comma)-me500mc)
 
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 896efa559996..b2f89b621b15 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -35,9 +35,9 @@ extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
 extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries);
 extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa);
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa);
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
 extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
 #endif
@@ -143,24 +143,33 @@ static inline void mm_context_remove_copro(struct mm_struct *mm)
 {
 	int c;
 
-	c = atomic_dec_if_positive(&mm->context.copros);
-
-	/* Detect imbalance between add and remove */
-	WARN_ON(c < 0);
-
 	/*
-	 * Need to broadcast a global flush of the full mm before
-	 * decrementing active_cpus count, as the next TLBI may be
-	 * local and the nMMU and/or PSL need to be cleaned up.
-	 * Should be rare enough so that it's acceptable.
+	 * When removing the last copro, we need to broadcast a global
+	 * flush of the full mm, as the next TLBI may be local and the
+	 * nMMU and/or PSL need to be cleaned up.
+	 *
+	 * Both the 'copros' and 'active_cpus' counts are looked at in
+	 * flush_all_mm() to determine the scope (local/global) of the
+	 * TLBIs, so we need to flush first before decrementing
+	 * 'copros'. If this API is used by several callers for the
+	 * same context, it can lead to over-flushing. It's hopefully
+	 * not common enough to be a problem.
 	 *
 	 * Skip on hash, as we don't know how to do the proper flush
 	 * for the time being. Invalidations will remain global if
-	 * used on hash.
+	 * used on hash. Note that we can't drop 'copros' either, as
+	 * it could make some invalidations local with no flush
+	 * in-between.
 	 */
-	if (c == 0 && radix_enabled()) {
+	if (radix_enabled()) {
 		flush_all_mm(mm);
-		dec_mm_active_cpus(mm);
+
+		c = atomic_dec_if_positive(&mm->context.copros);
+		/* Detect imbalance between add and remove */
+		WARN_ON(c < 0);
+
+		if (c == 0)
+			dec_mm_active_cpus(mm);
 	}
 }
 #else
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index e734f6e45abc..689306118b48 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -144,7 +144,9 @@ power9_restore_additional_sprs:
 	mtspr	SPRN_MMCR1, r4
 
 	ld	r3, STOP_MMCR2(r13)
+	ld	r4, PACA_SPRG_VDSO(r13)
 	mtspr	SPRN_MMCR2, r3
+	mtspr	SPRN_SPRG3, r4
 	blr
 
 /*
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index fe9733ffffaa..471aac313b89 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -42,6 +42,8 @@
 #include <asm/ppc-pci.h>
 #include <asm/eeh.h>
 
+#include "../../../drivers/pci/pci.h"
+
 /* hose_spinlock protects accesses to the the phb_bitmap. */
 static DEFINE_SPINLOCK(hose_spinlock);
 LIST_HEAD(hose_list);
@@ -1014,7 +1016,7 @@ void pcibios_setup_bus_devices(struct pci_bus *bus)
 		/* Cardbus can call us to add new devices to a bus, so ignore
 		 * those who are already fully discovered
 		 */
-		if (dev->is_added)
+		if (pci_dev_is_added(dev))
 			continue;
 
 		pcibios_setup_device(dev);
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index d066e37551ec..8c456fa691a5 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -449,7 +449,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 		/* This only handles v2 IOMMU type, v1 is handled via ioctl() */
 		return H_TOO_HARD;
 
-	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
+	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, tbl->it_page_shift, &hpa)))
 		return H_HARDWARE;
 
 	if (mm_iommu_mapped_inc(mem))
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 925fc316a104..5b298f5a1a14 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -279,7 +279,8 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 	if (!mem)
 		return H_TOO_HARD;
 
-	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
+	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift,
+			&hpa)))
 		return H_HARDWARE;
 
 	pua = (void *) vmalloc_to_phys(pua);
@@ -469,7 +470,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 
 		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
 		if (mem)
-			prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0;
+			prereg = mm_iommu_ua_to_hpa_rm(mem, ua,
+					IOMMU_PAGE_SHIFT_4K, &tces) == 0;
 	}
 
 	if (!prereg) {
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index abb43646927a..a4ca57612558 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -19,6 +19,7 @@
 #include <linux/hugetlb.h>
 #include <linux/swap.h>
 #include <asm/mmu_context.h>
+#include <asm/pte-walk.h>
 
 static DEFINE_MUTEX(mem_list_mutex);
 
@@ -27,6 +28,7 @@ struct mm_iommu_table_group_mem_t {
 	struct rcu_head rcu;
 	unsigned long used;
 	atomic64_t mapped;
+	unsigned int pageshift;
 	u64 ua;			/* userspace address */
 	u64 entries;		/* number of entries in hpas[] */
 	u64 *hpas;		/* vmalloc'ed */
@@ -125,6 +127,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 {
 	struct mm_iommu_table_group_mem_t *mem;
 	long i, j, ret = 0, locked_entries = 0;
+	unsigned int pageshift;
+	unsigned long flags;
 	struct page *page = NULL;
 
 	mutex_lock(&mem_list_mutex);
@@ -159,6 +163,12 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 		goto unlock_exit;
 	}
 
+	/*
+	 * For a starting point for a maximum page size calculation
+	 * we use @ua and @entries natural alignment to allow IOMMU pages
+	 * smaller than huge pages but still bigger than PAGE_SIZE.
+	 */
+	mem->pageshift = __ffs(ua | (entries << PAGE_SHIFT));
 	mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0])));
 	if (!mem->hpas) {
 		kfree(mem);
@@ -199,6 +209,23 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 			}
 		}
 populate:
+		pageshift = PAGE_SHIFT;
+		if (PageCompound(page)) {
+			pte_t *pte;
+			struct page *head = compound_head(page);
+			unsigned int compshift = compound_order(head);
+
+			local_irq_save(flags); /* disables as well */
+			pte = find_linux_pte(mm->pgd, ua, NULL, &pageshift);
+			local_irq_restore(flags);
+
+			/* Double check it is still the same pinned page */
+			if (pte && pte_page(*pte) == head &&
+					pageshift == compshift)
+				pageshift = max_t(unsigned int, pageshift,
+						PAGE_SHIFT);
+		}
+		mem->pageshift = min(mem->pageshift, pageshift);
 		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
 	}
 
@@ -349,7 +376,7 @@ struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 EXPORT_SYMBOL_GPL(mm_iommu_find);
 
 long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa)
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
 {
 	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
 	u64 *va = &mem->hpas[entry];
@@ -357,6 +384,9 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 	if (entry >= mem->entries)
 		return -EFAULT;
 
+	if (pageshift > mem->pageshift)
+		return -EFAULT;
+
 	*hpa = *va | (ua & ~PAGE_MASK);
 
 	return 0;
@@ -364,7 +394,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
 
 long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa)
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
 {
 	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
 	void *va = &mem->hpas[entry];
@@ -373,6 +403,9 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
 	if (entry >= mem->entries)
 		return -EFAULT;
 
+	if (pageshift > mem->pageshift)
+		return -EFAULT;
+
 	pa = (void *) vmalloc_to_phys(va);
 	if (!pa)
 		return -EFAULT;
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 380cbf9a40d9..c0a9bcd28356 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -286,6 +286,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		u64 imm64;
 		u8 *func;
 		u32 true_cond;
+		u32 tmp_idx;
 
 		/*
 		 * addrs[] maps a BPF bytecode address into a real offset from
@@ -637,11 +638,7 @@ emit_clear:
 		case BPF_STX | BPF_XADD | BPF_W:
 			/* Get EA into TMP_REG_1 */
 			PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
-			/* error if EA is not word-aligned */
-			PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x03);
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + 12);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
+			tmp_idx = ctx->idx * 4;
 			/* load value from memory into TMP_REG_2 */
 			PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
 			/* add value from src_reg into this */
@@ -649,32 +646,16 @@ emit_clear:
 			/* store result back */
 			PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
 			/* we're done if this succeeded */
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4));
-			/* otherwise, let's try once more */
-			PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
-			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
-			PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
-			/* exit if the store was not successful */
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_BCC(COND_NE, exit_addr);
+			PPC_BCC_SHORT(COND_NE, tmp_idx);
 			break;
 		/* *(u64 *)(dst + off) += src */
 		case BPF_STX | BPF_XADD | BPF_DW:
 			PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
-			/* error if EA is not doubleword-aligned */
-			PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x07);
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (3*4));
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
-			PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
-			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
-			PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4));
+			tmp_idx = ctx->idx * 4;
 			PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
 			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
 			PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_BCC(COND_NE, exit_addr);
+			PPC_BCC_SHORT(COND_NE, tmp_idx);
 			break;
 
 		/*
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 5bd0eb6681bc..70b2e1e0f23c 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -46,6 +46,7 @@
 
 #include "powernv.h"
 #include "pci.h"
+#include "../../../../drivers/pci/pci.h"
 
 #define PNV_IODA1_M64_NUM	16	/* Number of M64 BARs	*/
 #define PNV_IODA1_M64_SEGS	8	/* Segments per M64 BAR	*/
@@ -3138,7 +3139,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
 	struct pci_dn *pdn;
 	int mul, total_vfs;
 
-	if (!pdev->is_physfn || pdev->is_added)
+	if (!pdev->is_physfn || pci_dev_is_added(pdev))
 		return;
 
 	pdn = pci_get_pdn(pdev);
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 139f0af6c3d9..8a4868a3964b 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -71,6 +71,7 @@
 #include <asm/security_features.h>
 
 #include "pseries.h"
+#include "../../../../drivers/pci/pci.h"
 
 int CMO_PrPSP = -1;
 int CMO_SecPSP = -1;
@@ -664,7 +665,7 @@ static void pseries_pci_fixup_iov_resources(struct pci_dev *pdev)
 	const int *indexes;
 	struct device_node *dn = pci_device_to_OF_node(pdev);
 
-	if (!pdev->is_physfn || pdev->is_added)
+	if (!pdev->is_physfn || pci_dev_is_added(pdev))
 		return;
 	/*Firmware must support open sriov otherwise dont configure*/
 	indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL);
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 47166ad2a669..196978733e64 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2734,7 +2734,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr,
 {
 	int nr, dotted;
 	unsigned long first_adr;
-	unsigned long inst, last_inst = 0;
+	unsigned int inst, last_inst = 0;
 	unsigned char val[4];
 
 	dotted = 0;
@@ -2758,7 +2758,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr,
 		dotted = 0;
 		last_inst = inst;
 		if (praddr)
-			printf(REG"  %.8lx", adr, inst);
+			printf(REG"  %.8x", adr, inst);
 		printf("\t");
 		dump_func(inst, adr);
 		printf("\n");
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index e44bb2b2873e..8a1863d9ed53 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -140,7 +140,7 @@ config S390
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if FUTEX
-	select HAVE_GCC_PLUGINS
+	select HAVE_GCC_PLUGINS if BROKEN
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index ac67828da201..410b263ef5c8 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -13,6 +13,7 @@ generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += module.h
+generic-y += msi.h
 generic-y += preempt.h
 generic-y += rwsem.h
 generic-y += serial.h
diff --git a/arch/sparc/include/asm/msi.h b/arch/sparc/include/asm/msi.h
deleted file mode 100644
index 3c17c1074431..000000000000
--- a/arch/sparc/include/asm/msi.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * msi.h:  Defines specific to the MBus - Sbus - Interface.
- *
- * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
- * Copyright (C) 1996 Eddie C. Dost   (ecd@skynet.be)
- */
-
-#ifndef _SPARC_MSI_H
-#define _SPARC_MSI_H
-
-/*
- * Locations of MSI Registers.
- */
-#define MSI_MBUS_ARBEN	0xe0001008	/* MBus Arbiter Enable register */
-
-/*
- * Useful bits in the MSI Registers.
- */
-#define MSI_ASYNC_MODE  0x80000000	/* Operate the MSI asynchronously */
-
-
-static inline void msi_set_sync(void)
-{
-	__asm__ __volatile__ ("lda [%0] %1, %%g3\n\t"
-			      "andn %%g3, %2, %%g3\n\t"
-			      "sta %%g3, [%0] %1\n\t" : :
-			      "r" (MSI_MBUS_ARBEN),
-			      "i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3");
-}
-
-#endif /* !(_SPARC_MSI_H) */
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index 2ef8cfa9677e..f0eba72aa1ad 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -814,7 +814,7 @@ static void __init get_tick_patch(void)
 	}
 }
 
-static void init_tick_ops(struct sparc64_tick_ops *ops)
+static void __init init_tick_ops(struct sparc64_tick_ops *ops)
 {
 	unsigned long freq, quotient, tick;
 
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index 1d70c3f6d986..be9cb0065179 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -37,7 +37,6 @@
 #include <asm/mbus.h>
 #include <asm/page.h>
 #include <asm/asi.h>
-#include <asm/msi.h>
 #include <asm/smp.h>
 #include <asm/io.h>
 
@@ -116,6 +115,25 @@ static inline void srmmu_ctxd_set(ctxd_t *ctxp, pgd_t *pgdp)
 	set_pte((pte_t *)ctxp, pte);
 }
 
+/*
+ * Locations of MSI Registers.
+ */
+#define MSI_MBUS_ARBEN	0xe0001008	/* MBus Arbiter Enable register */
+
+/*
+ * Useful bits in the MSI Registers.
+ */
+#define MSI_ASYNC_MODE  0x80000000	/* Operate the MSI asynchronously */
+
+static void msi_set_sync(void)
+{
+	__asm__ __volatile__ ("lda [%0] %1, %%g3\n\t"
+			      "andn %%g3, %2, %%g3\n\t"
+			      "sta %%g3, [%0] %1\n\t" : :
+			      "r" (MSI_MBUS_ARBEN),
+			      "i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3");
+}
+
 void pmd_set(pmd_t *pmdp, pte_t *ptep)
 {
 	unsigned long ptp;	/* Physical address, shifted right by 4 */
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f1dbb4ee19d7..887d3a7bb646 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -63,7 +63,7 @@ config X86
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_REFCOUNT
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
-	select ARCH_HAS_UACCESS_MCSAFE		if X86_64
+	select ARCH_HAS_UACCESS_MCSAFE		if X86_64 && X86_MCE
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index fa42f895fdde..169c2feda14a 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -106,9 +106,13 @@ define cmd_check_data_rel
 	done
 endef
 
+# We need to run two commands under "if_changed", so merge them into a
+# single invocation.
+quiet_cmd_check-and-link-vmlinux = LD      $@
+      cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld)
+
 $(obj)/vmlinux: $(vmlinux-objs-y) FORCE
-	$(call if_changed,check_data_rel)
-	$(call if_changed,ld)
+	$(call if_changed,check-and-link-vmlinux)
 
 OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
 $(obj)/vmlinux.bin: vmlinux FORCE
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index 8c5107545251..9e2157371491 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -1,3 +1,4 @@
+#include <asm/e820/types.h>
 #include <asm/processor.h>
 #include "pgtable.h"
 #include "../string.h"
@@ -34,10 +35,62 @@ unsigned long *trampoline_32bit __section(.data);
 extern struct boot_params *boot_params;
 int cmdline_find_option_bool(const char *option);
 
+static unsigned long find_trampoline_placement(void)
+{
+	unsigned long bios_start, ebda_start;
+	unsigned long trampoline_start;
+	struct boot_e820_entry *entry;
+	int i;
+
+	/*
+	 * Find a suitable spot for the trampoline.
+	 * This code is based on reserve_bios_regions().
+	 */
+
+	ebda_start = *(unsigned short *)0x40e << 4;
+	bios_start = *(unsigned short *)0x413 << 10;
+
+	if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX)
+		bios_start = BIOS_START_MAX;
+
+	if (ebda_start > BIOS_START_MIN && ebda_start < bios_start)
+		bios_start = ebda_start;
+
+	bios_start = round_down(bios_start, PAGE_SIZE);
+
+	/* Find the first usable memory region under bios_start. */
+	for (i = boot_params->e820_entries - 1; i >= 0; i--) {
+		entry = &boot_params->e820_table[i];
+
+		/* Skip all entries above bios_start. */
+		if (bios_start <= entry->addr)
+			continue;
+
+		/* Skip non-RAM entries. */
+		if (entry->type != E820_TYPE_RAM)
+			continue;
+
+		/* Adjust bios_start to the end of the entry if needed. */
+		if (bios_start > entry->addr + entry->size)
+			bios_start = entry->addr + entry->size;
+
+		/* Keep bios_start page-aligned. */
+		bios_start = round_down(bios_start, PAGE_SIZE);
+
+		/* Skip the entry if it's too small. */
+		if (bios_start - TRAMPOLINE_32BIT_SIZE < entry->addr)
+			continue;
+
+		break;
+	}
+
+	/* Place the trampoline just below the end of low memory */
+	return bios_start - TRAMPOLINE_32BIT_SIZE;
+}
+
 struct paging_config paging_prepare(void *rmode)
 {
 	struct paging_config paging_config = {};
-	unsigned long bios_start, ebda_start;
 
 	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
 	boot_params = rmode;
@@ -61,23 +114,7 @@ struct paging_config paging_prepare(void *rmode)
 		paging_config.l5_required = 1;
 	}
 
-	/*
-	 * Find a suitable spot for the trampoline.
-	 * This code is based on reserve_bios_regions().
-	 */
-
-	ebda_start = *(unsigned short *)0x40e << 4;
-	bios_start = *(unsigned short *)0x413 << 10;
-
-	if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX)
-		bios_start = BIOS_START_MAX;
-
-	if (ebda_start > BIOS_START_MIN && ebda_start < bios_start)
-		bios_start = ebda_start;
-
-	/* Place the trampoline just below the end of low memory, aligned to 4k */
-	paging_config.trampoline_start = bios_start - TRAMPOLINE_32BIT_SIZE;
-	paging_config.trampoline_start = round_down(paging_config.trampoline_start, PAGE_SIZE);
+	paging_config.trampoline_start = find_trampoline_placement();
 
 	trampoline_32bit = (unsigned long *)paging_config.trampoline_start;
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 73a522d53b53..8ae7ffda8f98 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -981,7 +981,7 @@ ENTRY(\sym)
 
 	call	\do_sym
 
-	jmp	error_exit			/* %ebx: no swapgs flag */
+	jmp	error_exit
 	.endif
 END(\sym)
 .endm
@@ -1222,7 +1222,6 @@ END(paranoid_exit)
 
 /*
  * Save all registers in pt_regs, and switch GS if needed.
- * Return: EBX=0: came from user mode; EBX=1: otherwise
  */
 ENTRY(error_entry)
 	UNWIND_HINT_FUNC
@@ -1269,7 +1268,6 @@ ENTRY(error_entry)
 	 * for these here too.
 	 */
 .Lerror_kernelspace:
-	incl	%ebx
 	leaq	native_irq_return_iret(%rip), %rcx
 	cmpq	%rcx, RIP+8(%rsp)
 	je	.Lerror_bad_iret
@@ -1303,28 +1301,20 @@ ENTRY(error_entry)
 
 	/*
 	 * Pretend that the exception came from user mode: set up pt_regs
-	 * as if we faulted immediately after IRET and clear EBX so that
-	 * error_exit knows that we will be returning to user mode.
+	 * as if we faulted immediately after IRET.
 	 */
 	mov	%rsp, %rdi
 	call	fixup_bad_iret
 	mov	%rax, %rsp
-	decl	%ebx
 	jmp	.Lerror_entry_from_usermode_after_swapgs
 END(error_entry)
 
-
-/*
- * On entry, EBX is a "return to kernel mode" flag:
- *   1: already in kernel mode, don't need SWAPGS
- *   0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode
- */
 ENTRY(error_exit)
 	UNWIND_HINT_REGS
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
-	testl	%ebx, %ebx
-	jnz	retint_kernel
+	testb	$3, CS(%rsp)
+	jz	retint_kernel
 	jmp	retint_user
 END(error_exit)
 
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 4b98101209a1..d50bb4dc0650 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -579,7 +579,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 {
 	struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu);
 	struct perf_event *event = pcpu->event;
-	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event *hwc;
 	struct perf_sample_data data;
 	struct perf_raw_record raw;
 	struct pt_regs regs;
@@ -602,6 +602,10 @@ fail:
 		return 0;
 	}
 
+	if (WARN_ON_ONCE(!event))
+		goto fail;
+
+	hwc = &event->hw;
 	msr = hwc->config_base;
 	buf = ibs_data.regs;
 	rdmsrl(msr, *buf);
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 707b2a96e516..86f0c15dcc2d 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2997,6 +2997,9 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		}
 		if (x86_pmu.pebs_aliases)
 			x86_pmu.pebs_aliases(event);
+
+		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+			event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY;
 	}
 
 	if (needs_branch_stack(event)) {
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8a10a045b57b..8dbba77e0518 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -408,9 +408,11 @@ static int alloc_bts_buffer(int cpu)
 	ds->bts_buffer_base = (unsigned long) cea;
 	ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL);
 	ds->bts_index = ds->bts_buffer_base;
-	max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE);
-	ds->bts_absolute_maximum = ds->bts_buffer_base + max;
-	ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16);
+	max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
+	ds->bts_absolute_maximum = ds->bts_buffer_base +
+					max * BTS_RECORD_SIZE;
+	ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
+					(max / 16) * BTS_RECORD_SIZE;
 	return 0;
 }
 
@@ -1184,16 +1186,20 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	}
 
 	/*
+	 * We must however always use iregs for the unwinder to stay sane; the
+	 * record BP,SP,IP can point into thin air when the record is from a
+	 * previous PMI context or an (I)RET happend between the record and
+	 * PMI.
+	 */
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+		data->callchain = perf_callchain(event, iregs);
+
+	/*
 	 * We use the interrupt regs as a base because the PEBS record does not
 	 * contain a full regs set, specifically it seems to lack segment
 	 * descriptors, which get used by things like user_mode().
 	 *
 	 * In the simple case fix up only the IP for PERF_SAMPLE_IP.
-	 *
-	 * We must however always use BP,SP from iregs for the unwinder to stay
-	 * sane; the record BP,SP can point into thin air when the record is
-	 * from a previous PMI context or an (I)RET happend between the record
-	 * and PMI.
 	 */
 	*regs = *iregs;
 
@@ -1212,15 +1218,8 @@ static void setup_pebs_sample_data(struct perf_event *event,
 		regs->si = pebs->si;
 		regs->di = pebs->di;
 
-		/*
-		 * Per the above; only set BP,SP if we don't need callchains.
-		 *
-		 * XXX: does this make sense?
-		 */
-		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
-			regs->bp = pebs->bp;
-			regs->sp = pebs->sp;
-		}
+		regs->bp = pebs->bp;
+		regs->sp = pebs->sp;
 
 #ifndef CONFIG_X86_32
 		regs->r8 = pebs->r8;
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index c9e1e0bef3c3..e17ab885b1e9 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -28,7 +28,7 @@
 #define UNCORE_PCI_DEV_TYPE(data)	((data >> 8) & 0xff)
 #define UNCORE_PCI_DEV_IDX(data)	(data & 0xff)
 #define UNCORE_EXTRA_PCI_DEV		0xff
-#define UNCORE_EXTRA_PCI_DEV_MAX	3
+#define UNCORE_EXTRA_PCI_DEV_MAX	4
 
 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
 
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 87dc0263a2e1..51d7c117e3c7 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1029,6 +1029,7 @@ void snbep_uncore_cpu_init(void)
 enum {
 	SNBEP_PCI_QPI_PORT0_FILTER,
 	SNBEP_PCI_QPI_PORT1_FILTER,
+	BDX_PCI_QPI_PORT2_FILTER,
 	HSWEP_PCI_PCU_3,
 };
 
@@ -3286,15 +3287,18 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = {
 	},
 	{ /* QPI Port 0 filter  */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT0_FILTER),
 	},
 	{ /* QPI Port 1 filter  */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT1_FILTER),
 	},
 	{ /* QPI Port 2 filter  */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   BDX_PCI_QPI_PORT2_FILTER),
 	},
 	{ /* PCU.3 (for Capability registers) */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0),
diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h
index c356098b6fb9..4d4015ddcf26 100644
--- a/arch/x86/include/asm/apm.h
+++ b/arch/x86/include/asm/apm.h
@@ -7,8 +7,6 @@
 #ifndef _ASM_X86_MACH_DEFAULT_APM_H
 #define _ASM_X86_MACH_DEFAULT_APM_H
 
-#include <asm/nospec-branch.h>
-
 #ifdef APM_ZERO_SEGS
 #	define APM_DO_ZERO_SEGS \
 		"pushl %%ds\n\t" \
@@ -34,7 +32,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
-	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -47,7 +44,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 		  "=S" (*esi)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
-	firmware_restrict_branch_speculation_end();
 }
 
 static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
@@ -60,7 +56,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
-	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -73,7 +68,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 		  "=S" (si)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
-	firmware_restrict_branch_speculation_end();
 	return error;
 }
 
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index 9ef5ee03d2d7..159622ee0674 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -43,7 +43,7 @@ asm    (".pushsection .text;"
 	"push  %rdx;"
 	"mov   $0x1,%eax;"
 	"xor   %edx,%edx;"
-	"lock cmpxchg %dl,(%rdi);"
+	LOCK_PREFIX "cmpxchg %dl,(%rdi);"
 	"cmp   $0x1,%al;"
 	"jne   .slowpath;"
 	"pop   %rdx;"
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 62acb613114b..a9d637bc301d 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -52,7 +52,12 @@ copy_to_user_mcsafe(void *to, const void *from, unsigned len)
 	unsigned long ret;
 
 	__uaccess_begin();
-	ret = memcpy_mcsafe(to, from, len);
+	/*
+	 * Note, __memcpy_mcsafe() is explicitly used since it can
+	 * handle exceptions / faults.  memcpy_mcsafe() may fall back to
+	 * memcpy() which lacks this handling.
+	 */
+	ret = __memcpy_mcsafe(to, from, len);
 	__uaccess_end();
 	return ret;
 }
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2aabd4cb0e3f..adbda5847b14 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -573,6 +573,9 @@ static u32 skx_deadline_rev(void)
 	case 0x04: return 0x02000014;
 	}
 
+	if (boot_cpu_data.x86_stepping > 4)
+		return 0;
+
 	return ~0U;
 }
 
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 5d0de79fdab0..ec00d1ff5098 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -240,6 +240,7 @@
 #include <asm/olpc.h>
 #include <asm/paravirt.h>
 #include <asm/reboot.h>
+#include <asm/nospec-branch.h>
 
 #if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT)
 extern int (*console_blank_hook)(int);
@@ -614,11 +615,13 @@ static long __apm_bios_call(void *_call)
 	gdt[0x40 / 8] = bad_bios_desc;
 
 	apm_irq_save(flags);
+	firmware_restrict_branch_speculation_start();
 	APM_DO_SAVE_SEGS;
 	apm_bios_call_asm(call->func, call->ebx, call->ecx,
 			  &call->eax, &call->ebx, &call->ecx, &call->edx,
 			  &call->esi);
 	APM_DO_RESTORE_SEGS;
+	firmware_restrict_branch_speculation_end();
 	apm_irq_restore(flags);
 	gdt[0x40 / 8] = save_desc_40;
 	put_cpu();
@@ -690,10 +693,12 @@ static long __apm_bios_call_simple(void *_call)
 	gdt[0x40 / 8] = bad_bios_desc;
 
 	apm_irq_save(flags);
+	firmware_restrict_branch_speculation_start();
 	APM_DO_SAVE_SEGS;
 	error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx,
 					 &call->eax);
 	APM_DO_RESTORE_SEGS;
+	firmware_restrict_branch_speculation_end();
 	apm_irq_restore(flags);
 	gdt[0x40 / 8] = save_desc_40;
 	put_cpu();
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index c102ad51025e..8c50754c09c1 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2165,9 +2165,6 @@ static ssize_t store_int_with_restart(struct device *s,
 	if (check_interval == old_check_interval)
 		return ret;
 
-	if (check_interval < 1)
-		check_interval = 1;
-
 	mutex_lock(&mce_sysfs_mutex);
 	mce_restart();
 	mutex_unlock(&mce_sysfs_mutex);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index bf8d1eb7fca3..3b8e7c13c614 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -138,6 +138,7 @@ static unsigned long kvm_get_tsc_khz(void)
 	src = &hv_clock[cpu].pvti;
 	tsc_khz = pvclock_tsc_khz(src);
 	put_cpu();
+	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
 	return tsc_khz;
 }
 
@@ -319,6 +320,8 @@ void __init kvmclock_init(void)
 	printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
 		msr_kvm_system_time, msr_kvm_wall_clock);
 
+	pvclock_set_pvti_cpu0_va(hv_clock);
+
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
 		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
 
@@ -366,14 +369,11 @@ int __init kvm_setup_vsyscall_timeinfo(void)
 	vcpu_time = &hv_clock[cpu].pvti;
 	flags = pvclock_read_flags(vcpu_time);
 
-	if (!(flags & PVCLOCK_TSC_STABLE_BIT)) {
-		put_cpu();
-		return 1;
-	}
-
-	pvclock_set_pvti_cpu0_va(hv_clock);
 	put_cpu();
 
+	if (!(flags & PVCLOCK_TSC_STABLE_BIT))
+		return 1;
+
 	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
 #endif
 	return 0;
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 92fd433c50b9..1bbec387d289 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -85,7 +85,7 @@ config KVM_AMD_SEV
 	def_bool y
 	bool "AMD Secure Encrypted Virtualization (SEV) support"
 	depends on KVM_AMD && X86_64
-	depends on CRYPTO_DEV_CCP && CRYPTO_DEV_CCP_DD && CRYPTO_DEV_SP_PSP
+	depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m)
 	---help---
 	Provides support for launching Encrypted VMs on AMD processors.
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d594690d8b95..6b8f11521c41 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -890,7 +890,7 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache,
 	if (cache->nobjs >= min)
 		return 0;
 	while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
-		page = (void *)__get_free_page(GFP_KERNEL);
+		page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
 		if (!page)
 			return -ENOMEM;
 		cache->objects[cache->nobjs++] = page;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1689f433f3a0..5d8e317c2b04 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2571,6 +2571,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 #ifdef CONFIG_X86_64
 	int cpu = raw_smp_processor_id();
+	unsigned long fs_base, kernel_gs_base;
 #endif
 	int i;
 
@@ -2586,12 +2587,20 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel;
 
 #ifdef CONFIG_X86_64
-	save_fsgs_for_kvm();
-	vmx->host_state.fs_sel = current->thread.fsindex;
-	vmx->host_state.gs_sel = current->thread.gsindex;
-#else
-	savesegment(fs, vmx->host_state.fs_sel);
-	savesegment(gs, vmx->host_state.gs_sel);
+	if (likely(is_64bit_mm(current->mm))) {
+		save_fsgs_for_kvm();
+		vmx->host_state.fs_sel = current->thread.fsindex;
+		vmx->host_state.gs_sel = current->thread.gsindex;
+		fs_base = current->thread.fsbase;
+		kernel_gs_base = current->thread.gsbase;
+	} else {
+#endif
+		savesegment(fs, vmx->host_state.fs_sel);
+		savesegment(gs, vmx->host_state.gs_sel);
+#ifdef CONFIG_X86_64
+		fs_base = read_msr(MSR_FS_BASE);
+		kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
+	}
 #endif
 	if (!(vmx->host_state.fs_sel & 7)) {
 		vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel);
@@ -2611,10 +2620,10 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	savesegment(ds, vmx->host_state.ds_sel);
 	savesegment(es, vmx->host_state.es_sel);
 
-	vmcs_writel(HOST_FS_BASE, current->thread.fsbase);
+	vmcs_writel(HOST_FS_BASE, fs_base);
 	vmcs_writel(HOST_GS_BASE, cpu_kernelmode_gs_base(cpu));
 
-	vmx->msr_host_kernel_gs_base = current->thread.gsbase;
+	vmx->msr_host_kernel_gs_base = kernel_gs_base;
 	if (is_long_mode(&vmx->vcpu))
 		wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
 #else
@@ -4322,11 +4331,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 	vmcs_conf->order = get_order(vmcs_conf->size);
 	vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff;
 
-	/* KVM supports Enlightened VMCS v1 only */
-	if (static_branch_unlikely(&enable_evmcs))
-		vmcs_conf->revision_id = KVM_EVMCS_VERSION;
-	else
-		vmcs_conf->revision_id = vmx_msr_low;
+	vmcs_conf->revision_id = vmx_msr_low;
 
 	vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
 	vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control;
@@ -4396,7 +4401,13 @@ static struct vmcs *alloc_vmcs_cpu(int cpu)
 		return NULL;
 	vmcs = page_address(pages);
 	memset(vmcs, 0, vmcs_config.size);
-	vmcs->revision_id = vmcs_config.revision_id; /* vmcs revision id */
+
+	/* KVM supports Enlightened VMCS v1 only */
+	if (static_branch_unlikely(&enable_evmcs))
+		vmcs->revision_id = KVM_EVMCS_VERSION;
+	else
+		vmcs->revision_id = vmcs_config.revision_id;
+
 	return vmcs;
 }
 
@@ -4564,6 +4575,19 @@ static __init int alloc_kvm_area(void)
 			return -ENOMEM;
 		}
 
+		/*
+		 * When eVMCS is enabled, alloc_vmcs_cpu() sets
+		 * vmcs->revision_id to KVM_EVMCS_VERSION instead of
+		 * revision_id reported by MSR_IA32_VMX_BASIC.
+		 *
+		 * However, even though not explictly documented by
+		 * TLFS, VMXArea passed as VMXON argument should
+		 * still be marked with revision_id reported by
+		 * physical CPU.
+		 */
+		if (static_branch_unlikely(&enable_evmcs))
+			vmcs->revision_id = vmcs_config.revision_id;
+
 		per_cpu(vmxarea, cpu) = vmcs;
 	}
 	return 0;
@@ -7869,6 +7893,8 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 		     HRTIMER_MODE_REL_PINNED);
 	vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
 
+	vmx->nested.vpid02 = allocate_vpid();
+
 	vmx->nested.vmxon = true;
 	return 0;
 
@@ -8456,21 +8482,20 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 /* Emulate the VMPTRST instruction */
 static int handle_vmptrst(struct kvm_vcpu *vcpu)
 {
-	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	gva_t vmcs_gva;
+	unsigned long exit_qual = vmcs_readl(EXIT_QUALIFICATION);
+	u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr;
 	struct x86_exception e;
+	gva_t gva;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (get_vmx_mem_address(vcpu, exit_qualification,
-			vmx_instruction_info, true, &vmcs_gva))
+	if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, &gva))
 		return 1;
 	/* *_system ok, nested_vmx_check_permission has verified cpl=0 */
-	if (kvm_write_guest_virt_system(vcpu, vmcs_gva,
-					(void *)&to_vmx(vcpu)->nested.current_vmptr,
-					sizeof(u64), &e)) {
+	if (kvm_write_guest_virt_system(vcpu, gva, (void *)&current_vmptr,
+					sizeof(gpa_t), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
@@ -10346,11 +10371,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 			goto free_vmcs;
 	}
 
-	if (nested) {
+	if (nested)
 		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
 					   kvm_vcpu_apicv_active(&vmx->vcpu));
-		vmx->nested.vpid02 = allocate_vpid();
-	}
 
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
@@ -10367,7 +10390,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	return &vmx->vcpu;
 
 free_vmcs:
-	free_vpid(vmx->nested.vpid02);
 	free_loaded_vmcs(vmx->loaded_vmcs);
 free_msrs:
 	kfree(vmx->guest_msrs);
@@ -11753,7 +11775,6 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	u32 msr_entry_idx;
 	u32 exit_qual;
 	int r;
 
@@ -11775,10 +11796,10 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu)
 	nested_get_vmcs12_pages(vcpu, vmcs12);
 
 	r = EXIT_REASON_MSR_LOAD_FAIL;
-	msr_entry_idx = nested_vmx_load_msr(vcpu,
-					    vmcs12->vm_entry_msr_load_addr,
-					    vmcs12->vm_entry_msr_load_count);
-	if (msr_entry_idx)
+	exit_qual = nested_vmx_load_msr(vcpu,
+					vmcs12->vm_entry_msr_load_addr,
+					vmcs12->vm_entry_msr_load_count);
+	if (exit_qual)
 		goto fail;
 
 	/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0046aa70205a..2b812b3c5088 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1097,6 +1097,7 @@ static u32 msr_based_features[] = {
 
 	MSR_F10H_DECFG,
 	MSR_IA32_UCODE_REV,
+	MSR_IA32_ARCH_CAPABILITIES,
 };
 
 static unsigned int num_msr_based_features;
@@ -1105,7 +1106,8 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
 {
 	switch (msr->index) {
 	case MSR_IA32_UCODE_REV:
-		rdmsrl(msr->index, msr->data);
+	case MSR_IA32_ARCH_CAPABILITIES:
+		rdmsrl_safe(msr->index, &msr->data);
 		break;
 	default:
 		if (kvm_x86_ops->get_msr_feature(msr))
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 55799873ebe5..8f6cc71e0848 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -1441,8 +1441,8 @@ static void emit_prologue(u8 **pprog, u32 stack_depth)
 
 	/* sub esp,STACK_SIZE */
 	EMIT2_off32(0x81, 0xEC, STACK_SIZE);
-	/* sub ebp,SCRATCH_SIZE+4+12*/
-	EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 16);
+	/* sub ebp,SCRATCH_SIZE+12*/
+	EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 12);
 	/* xor ebx,ebx */
 	EMIT2(0x31, add_2reg(0xC0, IA32_EBX, IA32_EBX));
 
@@ -1475,8 +1475,8 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth)
 	/* mov edx,dword ptr [ebp+off]*/
 	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r0[1]));
 
-	/* add ebp,SCRATCH_SIZE+4+12*/
-	EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 16);
+	/* add ebp,SCRATCH_SIZE+12*/
+	EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 12);
 
 	/* mov ebx,dword ptr [ebp-12]*/
 	EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), -12);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 77873ce700ae..5f2eb3231607 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -417,7 +417,7 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va)
 	if (!(md->attribute & EFI_MEMORY_WB))
 		flags |= _PAGE_PCD;
 
-	if (sev_active())
+	if (sev_active() && md->type != EFI_MEMORY_MAPPED_IO)
 		flags |= _PAGE_ENC;
 
 	pfn = md->phys_addr >> PAGE_SHIFT;
diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c
index 744afdc18cf3..56c44d865f7b 100644
--- a/arch/x86/um/mem_32.c
+++ b/arch/x86/um/mem_32.c
@@ -16,7 +16,7 @@ static int __init gate_vma_init(void)
 	if (!FIXADDR_USER_START)
 		return 0;
 
-	gate_vma.vm_mm = NULL;
+	vma_init(&gate_vma, NULL);
 	gate_vma.vm_start = FIXADDR_USER_START;
 	gate_vma.vm_end = FIXADDR_USER_END;
 	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;