Merge branch 'akpm/master'

57 files changed, 260 insertions, 92 deletions

diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h
index 2dbdf59258d9..f9d4e6b6d4bd 100644
--- a/arch/alpha/include/uapi/asm/mman.h
+++ b/arch/alpha/include/uapi/asm/mman.h
@@ -32,6 +32,7 @@
 #define MAP_NONBLOCK	0x40000		/* do not block on IO */
 #define MAP_STACK	0x80000		/* give out an address that is best suited for process/thread stacks */
 #define MAP_HUGETLB	0x100000	/* create a huge page mapping */
+#define MAP_FIXED_NOREPLACE	0x200000/* MAP_FIXED which doesn't unmap underlying mapping */
 
 #define MS_ASYNC	1		/* sync memory asynchronously */
 #define MS_SYNC		2		/* synchronous memory sync */
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 496667703693..ed8fd0d19a3e 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -22,12 +22,6 @@
 #include <mach/memory.h>
 #endif
 
-/*
- * Allow for constants defined here to be used from assembly code
- * by prepending the UL suffix only with actual C code compilation.
- */
-#define UL(x) _AC(x, UL)
-
 /* PAGE_OFFSET - the virtual address of the start of the kernel image */
 #define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
 
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 50fa96a49792..49d99214f43c 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -29,12 +29,6 @@
 #include <asm/sizes.h>
 
 /*
- * Allow for constants defined here to be used from assembly code
- * by prepending the UL suffix only with actual C code compilation.
- */
-#define UL(x) _AC(x, UL)
-
-/*
  * Size of the PCI I/O space. This must remain a power of two so that
  * IO_SPACE_LIMIT acts as a mask for the low bits of I/O addresses.
  */
diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
index 606e02ca4b6c..3035ca499cd8 100644
--- a/arch/mips/include/uapi/asm/mman.h
+++ b/arch/mips/include/uapi/asm/mman.h
@@ -50,6 +50,7 @@
 #define MAP_NONBLOCK	0x20000		/* do not block on IO */
 #define MAP_STACK	0x40000		/* give out an address that is best suited for process/thread stacks */
 #define MAP_HUGETLB	0x80000		/* create a huge page mapping */
+#define MAP_FIXED_NOREPLACE 0x100000	/* MAP_FIXED which doesn't unmap underlying mapping */
 
 /*
  * Flags for msync
diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
index 08c821296294..9fc99ff82d38 100644
--- a/arch/parisc/include/uapi/asm/mman.h
+++ b/arch/parisc/include/uapi/asm/mman.h
@@ -28,6 +28,7 @@
 #define MAP_NONBLOCK	0x20000		/* do not block on IO */
 #define MAP_STACK	0x40000		/* give out an address that is best suited for process/thread stacks */
 #define MAP_HUGETLB	0x80000		/* create a huge page mapping */
+#define MAP_FIXED_NOREPLACE 0x100000	/* MAP_FIXED which doesn't unmap underlying mapping */
 
 #define MS_SYNC		1		/* synchronous memory sync */
 #define MS_ASYNC	2		/* sync memory asynchronously */
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index a6198d4f0f03..5ca3e22d0512 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -38,6 +38,7 @@
 #include <linux/suspend.h>
 #include <linux/memblock.h>
 #include <linux/gfp.h>
+#include <linux/kmemleak.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/iommu.h>
diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c
index c4dae27172b3..6243a7e537d0 100644
--- a/arch/powerpc/sysdev/msi_bitmap.c
+++ b/arch/powerpc/sysdev/msi_bitmap.c
@@ -10,6 +10,7 @@
 
 #include <linux/slab.h>
 #include <linux/kernel.h>
+#include <linux/kmemleak.h>
 #include <linux/bitmap.h>
 #include <linux/bootmem.h>
 #include <asm/msi_bitmap.h>
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index c7a627620e5e..8c867b43c8eb 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -15,7 +15,7 @@
 #include <linux/hardirq.h>
 #include <linux/log2.h>
 #include <linux/kprobes.h>
-#include <linux/slab.h>
+#include <linux/kmemleak.h>
 #include <linux/time.h>
 #include <linux/module.h>
 #include <linux/sched/signal.h>
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index a4a9fe1934e9..2f8f7d7dd9a8 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -27,7 +27,6 @@
 #include <linux/err.h>
 #include <linux/spinlock.h>
 #include <linux/kernel_stat.h>
-#include <linux/kmemleak.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/irqflags.h>
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index d66dde833f5e..713670e6d13d 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -22,7 +22,6 @@
 #include <linux/seq_file.h>
 #include <linux/ftrace.h>
 #include <linux/irq.h>
-#include <linux/kmemleak.h>
 
 #include <asm/ptrace.h>
 #include <asm/processor.h>
diff --git a/arch/sparc/lib/NG4memset.S b/arch/sparc/lib/NG4memset.S
index f81ee5419e2c..d0c4d195fd40 100644
--- a/arch/sparc/lib/NG4memset.S
+++ b/arch/sparc/lib/NG4memset.S
@@ -14,14 +14,14 @@
 	.globl		NG4memset
 NG4memset:
 	andcc		%o1, 0xff, %o4
-	be,pt		%icc, 1f
+	be,pt		%xcc, 1f
 	 mov		%o2, %o1
 	sllx		%o4, 8, %g1
 	or		%g1, %o4, %o2
 	sllx		%o2, 16, %g1
 	or		%g1, %o2, %o2
 	sllx		%o2, 32, %g1
-	ba,pt		%icc, 1f
+	ba,pt		%xcc, 1f
 	 or		%g1, %o2, %o4
 	.size		NG4memset,.-NG4memset
 
@@ -30,7 +30,7 @@ NG4memset:
 NG4bzero:
 	clr		%o4
 1:	cmp		%o1, 16
-	ble		%icc, .Ltiny
+	ble		%xcc, .Ltiny
 	 mov		%o0, %o3
 	sub		%g0, %o0, %g1
 	and		%g1, 0x7, %g1
@@ -38,7 +38,7 @@ NG4bzero:
 	 sub		%o1, %g1, %o1
 1:	stb		%o4, [%o0 + 0x00]
 	subcc		%g1, 1, %g1
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 1, %o0
 .Laligned8:
 	cmp		%o1, 64 + (64 - 8)
@@ -49,7 +49,7 @@ NG4bzero:
 	 sub		%o1, %g1, %o1
 1:	stx		%o4, [%o0 + 0x00]
 	subcc		%g1, 8, %g1
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x8, %o0
 .Laligned64:
 	andn		%o1, 64 - 1, %g1
@@ -59,30 +59,30 @@ NG4bzero:
 1:	stxa		%o4, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P
 	subcc		%g1, 0x40, %g1
 	stxa		%o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x40, %o0
 .Lpostloop:
 	cmp		%o1, 8
-	bl,pn		%icc, .Ltiny
+	bl,pn		%xcc, .Ltiny
 	 membar		#StoreStore|#StoreLoad
 .Lmedium:
 	andn		%o1, 0x7, %g1
 	sub		%o1, %g1, %o1
 1:	stx		%o4, [%o0 + 0x00]
 	subcc		%g1, 0x8, %g1
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x08, %o0
 	andcc		%o1, 0x4, %g1
-	be,pt		%icc, .Ltiny
+	be,pt		%xcc, .Ltiny
 	 sub		%o1, %g1, %o1
 	stw		%o4, [%o0 + 0x00]
 	add		%o0, 0x4, %o0
 .Ltiny:
 	cmp		%o1, 0
-	be,pn		%icc, .Lexit
+	be,pn		%xcc, .Lexit
 1:	 subcc		%o1, 1, %o1
 	stb		%o4, [%o0 + 0x00]
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 1, %o0
 .Lexit:
 	retl
@@ -100,8 +100,8 @@ NG4bzero:
 	stxa		%o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P
 	stxa		%o4, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P
 	stxa		%o4, [%o0 + %o5] ASI_BLK_INIT_QUAD_LDD_P
-	bne,pt		%icc, 1b
+	bne,pt		%xcc, 1b
 	 add		%o0, 0x30, %o0
-	ba,a,pt		%icc, .Lpostloop
+	ba,a,pt		%xcc, .Lpostloop
 	 nop
 	.size		NG4bzero,.-NG4bzero
diff --git a/arch/unicore32/include/asm/memory.h b/arch/unicore32/include/asm/memory.h
index 3bb0a29fd2d7..66bb9f6525c0 100644
--- a/arch/unicore32/include/asm/memory.h
+++ b/arch/unicore32/include/asm/memory.h
@@ -20,12 +20,6 @@
 #include <mach/memory.h>
 
 /*
- * Allow for constants defined here to be used from assembly code
- * by prepending the UL suffix only with actual C code compilation.
- */
-#define UL(x) _AC(x, UL)
-
-/*
  * PAGE_OFFSET - the virtual address of the start of the kernel image
  * TASK_SIZE - the maximum size of a user space task.
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 5ffa116ddb08..c06046e2d3ff 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -122,12 +122,14 @@ struct x86_init_pci {
  * @guest_late_init:		guest late init
  * @x2apic_available:		X2APIC detection
  * @init_mem_mapping:		setup early mappings during init_mem_mapping()
+ * @init_after_bootmem:		guest init after boot allocator is finished
  */
 struct x86_hyper_init {
 	void (*init_platform)(void);
 	void (*guest_late_init)(void);
 	bool (*x2apic_available)(void);
 	void (*init_mem_mapping)(void);
+	void (*init_after_bootmem)(void);
 };
 
 /**
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index df7ab02f959f..cb9c1fa2e2a8 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -6,7 +6,6 @@
 #include <linux/bootmem.h>
 #include <linux/gfp.h>
 #include <linux/pci.h>
-#include <linux/kmemleak.h>
 
 #include <asm/proto.h>
 #include <asm/dma.h>
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index aab817eb05cf..3215bffbf4d1 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -91,6 +91,7 @@ struct x86_init_ops x86_init __initdata = {
 		.guest_late_init	= x86_init_noop,
 		.x2apic_available	= bool_x86_init_noop,
 		.init_mem_mapping	= x86_init_noop,
+		.init_after_bootmem	= x86_init_noop,
 	},
 
 	.acpi = {
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 396e1f0151ac..8008db2bddb3 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -778,6 +778,7 @@ void __init mem_init(void)
 	free_all_bootmem();
 
 	after_bootmem = 1;
+	x86_init.hyper.init_after_bootmem();
 
 	mem_init_print_info(NULL);
 	printk(KERN_INFO "virtual kernel memory layout:\n"
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 332f6e25977a..8d60443dd900 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1189,6 +1189,7 @@ void __init mem_init(void)
 	/* this will put all memory onto the freelists */
 	free_all_bootmem();
 	after_bootmem = 1;
+	x86_init.hyper.init_after_bootmem();
 
 	/*
 	 * Must be done after boot memory is put on freelist, because here we
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index d20763472920..486c0a34d00b 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -116,6 +116,8 @@ DEFINE_PER_CPU(unsigned long, xen_current_cr3);	 /* actual vcpu cr3 */
 
 static phys_addr_t xen_pt_base, xen_pt_size __initdata;
 
+static DEFINE_STATIC_KEY_FALSE(xen_struct_pages_ready);
+
 /*
  * Just beyond the highest usermode address.  STACK_TOP_MAX has a
  * redzone above it, so round it up to a PGD boundary.
@@ -155,11 +157,18 @@ void make_lowmem_page_readwrite(void *vaddr)
 }
 
 
+/*
+ * During early boot all page table pages are pinned, but we do not have struct
+ * pages, so return true until struct pages are ready.
+ */
 static bool xen_page_pinned(void *ptr)
 {
-	struct page *page = virt_to_page(ptr);
+	if (static_branch_likely(&xen_struct_pages_ready)) {
+		struct page *page = virt_to_page(ptr);
 
-	return PagePinned(page);
+		return PagePinned(page);
+	}
+	return true;
 }
 
 static void xen_extend_mmu_update(const struct mmu_update *update)
@@ -836,11 +845,6 @@ void xen_mm_pin_all(void)
 	spin_unlock(&pgd_lock);
 }
 
-/*
- * The init_mm pagetable is really pinned as soon as its created, but
- * that's before we have page structures to store the bits.  So do all
- * the book-keeping now.
- */
 static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
 				  enum pt_level level)
 {
@@ -848,8 +852,18 @@ static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
 	return 0;
 }
 
-static void __init xen_mark_init_mm_pinned(void)
+/*
+ * The init_mm pagetable is really pinned as soon as its created, but
+ * that's before we have page structures to store the bits.  So do all
+ * the book-keeping now once struct pages for allocated pages are
+ * initialized. This happens only after free_all_bootmem() is called.
+ */
+static void __init xen_after_bootmem(void)
 {
+	static_branch_enable(&xen_struct_pages_ready);
+#ifdef CONFIG_X86_64
+	SetPagePinned(virt_to_page(level3_user_vsyscall));
+#endif
 	xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP);
 }
 
@@ -1623,14 +1637,15 @@ static inline void __set_pfn_prot(unsigned long pfn, pgprot_t prot)
 static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
 				    unsigned level)
 {
-	bool pinned = PagePinned(virt_to_page(mm->pgd));
+	bool pinned = xen_page_pinned(mm->pgd);
 
 	trace_xen_mmu_alloc_ptpage(mm, pfn, level, pinned);
 
 	if (pinned) {
 		struct page *page = pfn_to_page(pfn);
 
-		SetPagePinned(page);
+		if (static_branch_likely(&xen_struct_pages_ready))
+			SetPagePinned(page);
 
 		if (!PageHighMem(page)) {
 			xen_mc_batch();
@@ -2364,9 +2379,7 @@ static void __init xen_post_allocator_init(void)
 
 #ifdef CONFIG_X86_64
 	pv_mmu_ops.write_cr3 = &xen_write_cr3;
-	SetPagePinned(virt_to_page(level3_user_vsyscall));
 #endif
-	xen_mark_init_mm_pinned();
 }
 
 static void xen_leave_lazy_mmu(void)
@@ -2450,6 +2463,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 void __init xen_init_mmu_ops(void)
 {
 	x86_init.paging.pagetable_init = xen_pagetable_init;
+	x86_init.hyper.init_after_bootmem = xen_after_bootmem;
 
 	pv_mmu_ops = xen_mmu_ops;
 
diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h
index 3e9d01ada81f..58f29a9d895d 100644
--- a/arch/xtensa/include/uapi/asm/mman.h
+++ b/arch/xtensa/include/uapi/asm/mman.h
@@ -57,6 +57,7 @@
 #define MAP_NONBLOCK	0x20000		/* do not block on IO */
 #define MAP_STACK	0x40000		/* give out an address that is best suited for process/thread stacks */
 #define MAP_HUGETLB	0x80000		/* create a huge page mapping */
+#define MAP_FIXED_NOREPLACE 0x100000	/* MAP_FIXED which doesn't unmap underlying mapping */
 #ifdef CONFIG_MMAP_ALLOW_UNINITIALIZED
 # define MAP_UNINITIALIZED 0x4000000	/* For anonymous mmap, memory could be
 					 * uninitialized */
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 210715f08cf6..85879cfec52f 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -17,6 +17,7 @@
 #include <linux/io.h>
 #include <linux/iommu.h>
 #include <linux/interrupt.h>
+#include <linux/kmemleak.h>
 #include <linux/list.h>
 #include <linux/of.h>
 #include <linux/of_iommu.h>
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index 1b1b77594897..a7c2a973784f 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -25,7 +25,6 @@
 #include <linux/io.h>
 #include <linux/iommu.h>
 #include <linux/iopoll.h>
-#include <linux/kmemleak.h>
 #include <linux/list.h>
 #include <linux/of_address.h>
 #include <linux/of_iommu.h>
diff --git a/drivers/media/platform/sti/delta/delta-ipc.c b/drivers/media/platform/sti/delta/delta-ipc.c
index a4603d573c34..bd1bbbeedec3 100644
--- a/drivers/media/platform/sti/delta/delta-ipc.c
+++ b/drivers/media/platform/sti/delta/delta-ipc.c
@@ -175,8 +175,8 @@ int delta_ipc_open(struct delta_ctx *pctx, const char *name,
 	msg.ipc_buf_size = ipc_buf_size;
 	msg.ipc_buf_paddr = ctx->ipc_buf->paddr;
 
-	memcpy(msg.name, name, sizeof(msg.name));
-	msg.name[sizeof(msg.name) - 1] = 0;
+	memset(msg.name, 0, sizeof(msg.name));
+	strcpy(msg.name, name);
 
 	msg.param_size = param->size;
 	memcpy(ctx->ipc_buf->vaddr, param->data, msg.param_size);
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 1b1b78fdc138..5de96e020a24 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -35,6 +35,7 @@
 #include <linux/of_net.h>
 #include <linux/of_device.h>
 #include <linux/if_vlan.h>
+#include <linux/kmemleak.h>
 
 #include <linux/pinctrl/consumer.h>
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c
index 2437422625bf..57bb8f049e59 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.c
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.c
@@ -31,7 +31,6 @@
 #include "efuse.h"
 #include <linux/interrupt.h>
 #include <linux/export.h>
-#include <linux/kmemleak.h>
 #include <linux/module.h>
 
 MODULE_AUTHOR("lizhaoming	<chaoming_li@realsil.com.cn>");
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192c/fw_common.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192c/fw_common.c
index 015476e3f7e5..f3bff66e85d0 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192c/fw_common.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192c/fw_common.c
@@ -32,7 +32,6 @@
 #include "../rtl8192ce/def.h"
 #include "fw_common.h"
 #include <linux/export.h>
-#include <linux/kmemleak.h>
 
 static void _rtl92c_enable_fw_download(struct ieee80211_hw *hw, bool enable)
 {
diff --git a/drivers/staging/rtl8188eu/hal/fw.c b/drivers/staging/rtl8188eu/hal/fw.c
index 03d091bad13a..6b67b38a6a9f 100644
--- a/drivers/staging/rtl8188eu/hal/fw.c
+++ b/drivers/staging/rtl8188eu/hal/fw.c
@@ -30,7 +30,7 @@
 #include "rtl8188e_hal.h"
 
 #include <linux/firmware.h>
-#include <linux/kmemleak.h>
+#include <linux/slab.h>
 
 static void _rtl88e_enable_fw_download(struct adapter *adapt, bool enable)
 {
diff --git a/drivers/staging/rtlwifi/pci.c b/drivers/staging/rtlwifi/pci.c
index 70a64a5f564a..d56810eabde7 100644
--- a/drivers/staging/rtlwifi/pci.c
+++ b/drivers/staging/rtlwifi/pci.c
@@ -31,7 +31,6 @@
 #include "efuse.h"
 #include <linux/interrupt.h>
 #include <linux/export.h>
-#include <linux/kmemleak.h>
 #include <linux/module.h>
 
 MODULE_AUTHOR("lizhaoming	<chaoming_li@realsil.com.cn>");
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 71458f493cf8..21d464a29cf8 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -23,7 +23,6 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/hrtimer.h>
-#include <linux/kmemleak.h>
 #include <linux/dma-mapping.h>
 #include <xen/xen.h>
 
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 3edca6cb9a33..41e04183e4ce 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -377,6 +377,11 @@ static unsigned long elf_map(struct file *filep, unsigned long addr,
 	} else
 		map_addr = vm_mmap(filep, addr, size, prot, type, off);
 
+	if ((type & MAP_FIXED_NOREPLACE) && BAD_ADDR(map_addr))
+		pr_info("%d (%s): Uhuuh, elf segment at %p requested but the memory is mapped already\n",
+				task_pid_nr(current), current->comm,
+				(void *)addr);
+
 	return(map_addr);
 }
 
@@ -575,7 +580,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
 				elf_prot |= PROT_EXEC;
 			vaddr = eppnt->p_vaddr;
 			if (interp_elf_ex->e_type == ET_EXEC || load_addr_set)
-				elf_type |= MAP_FIXED;
+				elf_type |= MAP_FIXED_NOREPLACE;
 			else if (no_base && interp_elf_ex->e_type == ET_DYN)
 				load_addr = -vaddr;
 
@@ -890,7 +895,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	   the correct location in memory. */
 	for(i = 0, elf_ppnt = elf_phdata;
 	    i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
-		int elf_prot = 0, elf_flags;
+		int elf_prot = 0, elf_flags, elf_fixed = MAP_FIXED_NOREPLACE;
 		unsigned long k, vaddr;
 		unsigned long total_size = 0;
 
@@ -922,6 +927,13 @@ static int load_elf_binary(struct linux_binprm *bprm)
 					 */
 				}
 			}
+
+			/*
+			 * Some binaries have overlapping elf segments and then
+			 * we have to forcefully map over an existing mapping
+			 * e.g. over this newly established brk mapping.
+			 */
+			elf_fixed = MAP_FIXED;
 		}
 
 		if (elf_ppnt->p_flags & PF_R)
@@ -939,7 +951,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		 * the ET_DYN load_addr calculations, proceed normally.
 		 */
 		if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) {
-			elf_flags |= MAP_FIXED;
+			elf_flags |= elf_fixed;
 		} else if (loc->elf_ex.e_type == ET_DYN) {
 			/*
 			 * This logic is run once for the first LOAD Program
@@ -975,7 +987,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 				load_bias = ELF_ET_DYN_BASE;
 				if (current->flags & PF_RANDOMIZE)
 					load_bias += arch_mmap_rnd();
-				elf_flags |= MAP_FIXED;
+				elf_flags |= elf_fixed;
 			} else
 				load_bias = 0;
 
@@ -1235,7 +1247,7 @@ static int load_elf_library(struct file *file)
 			(eppnt->p_filesz +
 			 ELF_PAGEOFFSET(eppnt->p_vaddr)),
 			PROT_READ | PROT_WRITE | PROT_EXEC,
-			MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE,
+			MAP_FIXED_NOREPLACE | MAP_PRIVATE | MAP_DENYWRITE,
 			(eppnt->p_offset -
 			 ELF_PAGEOFFSET(eppnt->p_vaddr)));
 	if (error != ELF_PAGESTART(eppnt->p_vaddr))
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 63a1ca4b9dee..eb5c41284649 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -384,8 +384,9 @@ out_err:
 
 static int __init dnotify_init(void)
 {
-	dnotify_struct_cache = KMEM_CACHE(dnotify_struct, SLAB_PANIC);
-	dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC);
+	dnotify_struct_cache = KMEM_CACHE(dnotify_struct,
+					  SLAB_PANIC|SLAB_ACCOUNT);
+	dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT);
 
 	dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops);
 	if (IS_ERR(dnotify_group))
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index d51e1bb781cf..cb6670bed289 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -157,14 +157,16 @@ struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group,
 	if (fanotify_is_perm_event(mask)) {
 		struct fanotify_perm_event_info *pevent;
 
-		pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp);
+		pevent = kmem_cache_alloc_memcg(fanotify_perm_event_cachep, gfp,
+						group->memcg);
 		if (!pevent)
 			return NULL;
 		event = &pevent->fae;
 		pevent->response = 0;
 		goto init;
 	}
-	event = kmem_cache_alloc(fanotify_event_cachep, gfp);
+	event = kmem_cache_alloc_memcg(fanotify_event_cachep, gfp,
+				       group->memcg);
 	if (!event)
 		return NULL;
 init: __maybe_unused
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 72e367822efb..6015bbaaa319 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -16,6 +16,7 @@
 #include <linux/uaccess.h>
 #include <linux/compat.h>
 #include <linux/sched/signal.h>
+#include <linux/memcontrol.h>
 
 #include <asm/ioctls.h>
 
@@ -756,6 +757,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 
 	group->fanotify_data.user = user;
 	atomic_inc(&user->fanotify_listeners);
+	group->memcg = get_mem_cgroup_from_mm(current->mm);
 
 	oevent = fanotify_alloc_event(group, NULL, FS_Q_OVERFLOW, NULL);
 	if (unlikely(!oevent)) {
@@ -951,7 +953,8 @@ COMPAT_SYSCALL_DEFINE6(fanotify_mark,
  */
 static int __init fanotify_user_setup(void)
 {
-	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, SLAB_PANIC);
+	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
+					 SLAB_PANIC|SLAB_ACCOUNT);
 	fanotify_event_cachep = KMEM_CACHE(fanotify_event_info, SLAB_PANIC);
 	if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) {
 		fanotify_perm_event_cachep =
diff --git a/fs/notify/group.c b/fs/notify/group.c
index b7a4b6a69efa..3e56459f4773 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -22,6 +22,7 @@
 #include <linux/srcu.h>
 #include <linux/rculist.h>
 #include <linux/wait.h>
+#include <linux/memcontrol.h>
 
 #include <linux/fsnotify_backend.h>
 #include "fsnotify.h"
@@ -36,6 +37,9 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group)
 	if (group->ops->free_group_priv)
 		group->ops->free_group_priv(group);
 
+	if (group->memcg)
+		mem_cgroup_put(group->memcg);
+
 	kfree(group);
 }
 
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 40dedb37a1f3..b184bff93d02 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -98,7 +98,7 @@ int inotify_handle_event(struct fsnotify_group *group,
 	i_mark = container_of(inode_mark, struct inotify_inode_mark,
 			      fsn_mark);
 
-	event = kmalloc(alloc_len, GFP_KERNEL);
+	event = kmalloc_memcg(alloc_len, GFP_KERNEL, group->memcg);
 	if (unlikely(!event)) {
 		/*
 		 * Treat lost event due to ENOMEM the same way as queue
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 8f17719842ec..d9e4b243c973 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -38,6 +38,7 @@
 #include <linux/uaccess.h>
 #include <linux/poll.h>
 #include <linux/wait.h>
+#include <linux/memcontrol.h>
 
 #include "inotify.h"
 #include "../fdinfo.h"
@@ -632,6 +633,7 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 	oevent->name_len = 0;
 
 	group->max_events = max_events;
+	group->memcg = get_mem_cgroup_from_mm(current->mm);
 
 	spin_lock_init(&group->inotify_data.idr_lock);
 	idr_init(&group->inotify_data.idr);
@@ -799,7 +801,8 @@ static int __init inotify_user_setup(void)
 
 	BUG_ON(hweight32(ALL_INOTIFY_BITS) != 21);
 
-	inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark, SLAB_PANIC);
+	inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark,
+					       SLAB_PANIC|SLAB_ACCOUNT);
 
 	inotify_max_queued_events = 16384;
 	init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128;
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 4cac4e1a72ff..8a856be25eea 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -1,11 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_BITOPS_H
 #define _LINUX_BITOPS_H
+#include <linux/const.h>
 #include <asm/types.h>
 
 #ifdef	__KERNEL__
-#define BIT(nr)			(1UL << (nr))
-#define BIT_ULL(nr)		(1ULL << (nr))
 #define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
 #define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
 #define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
diff --git a/include/linux/const.h b/include/linux/const.h
new file mode 100644
index 000000000000..200892d8b0bf
--- /dev/null
+++ b/include/linux/const.h
@@ -0,0 +1,12 @@
+#ifndef _LINUX_CONST_H
+#define _LINUX_CONST_H
+
+#include <uapi/linux/const.h>
+
+#define UL(x)		(_UL(x))
+#define ULL(x)		(_ULL(x))
+
+#define BIT(x)		(_BITUL(x))
+#define BIT_ULL(x)	(_BITULL(x))
+
+#endif /* _LINUX_CONST_H */
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 9f1edb92c97e..81bd86dfa2cd 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -84,6 +84,8 @@ struct fsnotify_event_private_data;
 struct fsnotify_fname;
 struct fsnotify_iter_info;
 
+struct mem_cgroup;
+
 /*
  * Each group much define these ops.  The fsnotify infrastructure will call
  * these operations for each relevant group.
@@ -129,6 +131,8 @@ struct fsnotify_event {
  * everything will be cleaned up.
  */
 struct fsnotify_group {
+	const struct fsnotify_ops *ops;	/* how this group handles things */
+
 	/*
 	 * How the refcnt is used is up to each group.  When the refcnt hits 0
 	 * fsnotify will clean up all of the resources associated with this group.
@@ -139,8 +143,6 @@ struct fsnotify_group {
 	 */
 	refcount_t refcnt;		/* things with interest in this group */
 
-	const struct fsnotify_ops *ops;	/* how this group handles things */
-
 	/* needed to send notification to userspace */
 	spinlock_t notification_lock;		/* protect the notification_list */
 	struct list_head notification_list;	/* list of event_holder this group needs to send to userspace */
@@ -162,6 +164,8 @@ struct fsnotify_group {
 	atomic_t num_marks;		/* 1 for each mark and 1 for not being
 					 * past the point of no return when freeing
 					 * a group */
+	atomic_t user_waits;		/* Number of tasks waiting for user
+					 * response */
 	struct list_head marks_list;	/* all inode marks for this group */
 
 	struct fasync_struct *fsn_fa;    /* async notification */
@@ -169,8 +173,8 @@ struct fsnotify_group {
 	struct fsnotify_event *overflow_event;	/* Event we queue when the
 						 * notification list is too
 						 * full */
-	atomic_t user_waits;		/* Number of tasks waiting for user
-					 * response */
+
+	struct mem_cgroup *memcg;	/* memcg to charge allocations */
 
 	/* groups can define private fields here or use the void *private */
 	union {
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index c79cdf9f8138..4525b4404a9e 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -352,6 +352,8 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 	return css ? container_of(css, struct mem_cgroup, css) : NULL;
 }
 
+struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 	css_put(&memcg->css);
@@ -809,6 +811,11 @@ static inline bool task_in_mem_cgroup(struct task_struct *task,
 	return true;
 }
 
+static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
+{
+	return NULL;
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 }
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0b3f8921c8e1..7cc6b12b906c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1069,6 +1069,9 @@ struct task_struct {
 
 	/* Number of pages to reclaim on returning to userland: */
 	unsigned int			memcg_nr_pages_over_high;
+
+	/* Used by memcontrol for targeted memcg charge: */
+	struct mem_cgroup		*target_memcg;
 #endif
 
 #ifdef CONFIG_UPROBES
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 2c570cd934af..333f620a4634 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -206,6 +206,30 @@ static inline void memalloc_noreclaim_restore(unsigned int flags)
 	current->flags = (current->flags & ~PF_MEMALLOC) | flags;
 }
 
+#ifdef CONFIG_MEMCG
+static inline struct mem_cgroup *memalloc_memcg_save(struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *old_memcg = current->target_memcg;
+
+	current->target_memcg = memcg;
+	return old_memcg;
+}
+
+static inline void memalloc_memcg_restore(struct mem_cgroup *memcg)
+{
+	current->target_memcg = memcg;
+}
+#else
+static inline struct mem_cgroup *memalloc_memcg_save(struct mem_cgroup *memcg)
+{
+	return NULL;
+}
+
+static inline void memalloc_memcg_restore(struct mem_cgroup *memcg)
+{
+}
+#endif /* CONFIG_MEMCG */
+
 #ifdef CONFIG_MEMBARRIER
 enum {
 	MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY		= (1U << 0),
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 04402c637171..9ebe659bd4a5 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -15,6 +15,7 @@
 #include <linux/gfp.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
+#include <linux/sched/mm.h>
 
 
 /*
@@ -125,7 +126,6 @@
 #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \
 				(unsigned long)ZERO_SIZE_PTR)
 
-#include <linux/kmemleak.h>
 #include <linux/kasan.h>
 
 struct mem_cgroup;
@@ -375,6 +375,21 @@ static __always_inline void kfree_bulk(size_t size, void **p)
 	kmem_cache_free_bulk(NULL, size, p);
 }
 
+/*
+ * Calling kmem_cache_alloc_memcg implicitly assumes that the caller
+ * wants a __GFP_ACCOUNT allocation.
+ */
+static __always_inline void *kmem_cache_alloc_memcg(struct kmem_cache *cachep,
+						    gfp_t flags,
+						    struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *old_memcg = memalloc_memcg_save(memcg);
+	void *ptr = kmem_cache_alloc(cachep, flags | __GFP_ACCOUNT);
+
+	memalloc_memcg_restore(old_memcg);
+	return ptr;
+}
+
 #ifdef CONFIG_NUMA
 void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc;
 void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment __malloc;
@@ -390,6 +405,21 @@ static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t f
 }
 #endif
 
+/*
+ * Calling kmem_cache_alloc_node_memcg implicitly assumes that the caller
+ * wants a __GFP_ACCOUNT allocation.
+ */
+static __always_inline void *
+kmem_cache_alloc_node_memcg(struct kmem_cache *cachep, gfp_t flags, int node,
+			    struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *old_memcg = memalloc_memcg_save(memcg);
+	void *ptr = kmem_cache_alloc_node(cachep, flags | __GFP_ACCOUNT, node);
+
+	memalloc_memcg_restore(old_memcg);
+	return ptr;
+}
+
 #ifdef CONFIG_TRACING
 extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment __malloc;
 
@@ -519,6 +549,20 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags)
 }
 
 /*
+ * Calling kmalloc_memcg implicitly assumes that the caller wants a
+ * __GFP_ACCOUNT allocation.
+ */
+static __always_inline void *kmalloc_memcg(size_t size, gfp_t flags,
+					   struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *old_memcg = memalloc_memcg_save(memcg);
+	void *ptr = kmalloc(size, flags | __GFP_ACCOUNT);
+
+	memalloc_memcg_restore(old_memcg);
+	return ptr;
+}
+
+/*
  * Determine size used for the nth kmalloc cache.
  * return size or 0 if a kmalloc cache for that
  * size does not exist
@@ -555,6 +599,20 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 	return __kmalloc_node(size, flags, node);
 }
 
+/*
+ * Calling kmalloc_node_memcg implicitly assumes that the caller wants a
+ * __GFP_ACCOUNT allocation.
+ */
+static __always_inline void *
+kmalloc_node_memcg(size_t size, gfp_t flags, int node, struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *old_memcg = memalloc_memcg_save(memcg);
+	void *ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node);
+
+	memalloc_memcg_restore(old_memcg);
+	return ptr;
+}
+
 struct memcg_cache_array {
 	struct rcu_head rcu;
 	struct kmem_cache *entries[0];
diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index f8b134f5608f..e7ee32861d51 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -27,6 +27,9 @@
 # define MAP_UNINITIALIZED 0x0		/* Don't support this flag */
 #endif
 
+/* 0x0100 - 0x80000 flags are defined in asm-generic/mman.h */
+#define MAP_FIXED_NOREPLACE	0x100000	/* MAP_FIXED which doesn't unmap underlying mapping */
+
 /*
  * Flags for mlock
  */
diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h
index 92537757590a..5ed721ad5b19 100644
--- a/include/uapi/linux/const.h
+++ b/include/uapi/linux/const.h
@@ -1,8 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /* const.h: Macros for dealing with constants.  */
 
-#ifndef _LINUX_CONST_H
-#define _LINUX_CONST_H
+#ifndef _UAPI_LINUX_CONST_H
+#define _UAPI_LINUX_CONST_H
 
 /* Some constant macros are used in both assembler and
  * C code.  Therefore we cannot annotate them always with
@@ -22,7 +22,10 @@
 #define _AT(T,X)	((T)(X))
 #endif
 
-#define _BITUL(x)	(_AC(1,UL) << (x))
-#define _BITULL(x)	(_AC(1,ULL) << (x))
+#define _UL(x)		(_AC(x, UL))
+#define _ULL(x)		(_AC(x, ULL))
 
-#endif /* !(_LINUX_CONST_H) */
+#define _BITUL(x)	(_UL(1) << (x))
+#define _BITULL(x)	(_ULL(1) << (x))
+
+#endif /* _UAPI_LINUX_CONST_H */
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index d7f309f74dec..cff46bddf700 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -1611,8 +1611,10 @@ static int __init init_mqueue_fs(void)
 		goto out_filesystem;
 
 	m = kern_mount_data(&mqueue_fs_type, &init_ipc_ns);
-	if (IS_ERR(m))
+	if (IS_ERR(m)) {
+		error = PTR_ERR(m);
 		goto out_filesystem;
+	}
 	init_ipc_ns.mq_mnt = m;
 	return 0;
 
diff --git a/kernel/fork.c b/kernel/fork.c
index bdec8947d33f..abd9cae5639b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -833,6 +833,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->fail_nth = 0;
 #endif
 
+#ifdef CONFIG_MEMCG
+	tsk->target_memcg = NULL;
+#endif
 	return tsk;
 
 free_stack:
diff --git a/kernel/ucount.c b/kernel/ucount.c
index b4eeee03934f..f48d1b6376a4 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/cred.h>
 #include <linux/hash.h>
+#include <linux/kmemleak.h>
 #include <linux/user_namespace.h>
 
 #define UCOUNTS_HASHTABLE_BITS 10
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index 078a61480573..cee000ac54d8 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -21,6 +21,7 @@
 #include <linux/uaccess.h>
 #include <linux/delay.h>
 #include <linux/kthread.h>
+#include <linux/vmalloc.h>
 
 #define TEST_FIRMWARE_NAME	"test-firmware.bin"
 #define TEST_FIRMWARE_NUM_REQS	4
diff --git a/mm/cma.c b/mm/cma.c
index 646211d78f1e..aa40e6c7b042 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -35,6 +35,7 @@
 #include <linux/cma.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
+#include <linux/kmemleak.h>
 #include <trace/events/cma.h>
 
 #include "cma.h"
diff --git a/mm/memblock.c b/mm/memblock.c
index e0bc45ad6093..2965f530da23 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -17,6 +17,7 @@
 #include <linux/poison.h>
 #include <linux/pfn.h>
 #include <linux/debugfs.h>
+#include <linux/kmemleak.h>
 #include <linux/seq_file.h>
 #include <linux/memblock.h>
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index afdb35cf4d0e..3801ac1fcfbc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -678,7 +678,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 }
 EXPORT_SYMBOL(mem_cgroup_from_task);
 
-static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
+struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 {
 	struct mem_cgroup *memcg = NULL;
 
@@ -701,6 +701,15 @@ static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 	return memcg;
 }
 
+static struct mem_cgroup *get_mem_cgroup(struct mem_cgroup *memcg)
+{
+	rcu_read_lock();
+	if (!css_tryget_online(&memcg->css))
+		memcg = NULL;
+	rcu_read_unlock();
+	return memcg;
+}
+
 /**
  * mem_cgroup_iter - iterate over memory cgroup hierarchy
  * @root: hierarchy root
@@ -2248,7 +2257,7 @@ static inline bool memcg_kmem_bypass(void)
  */
 struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
 {
-	struct mem_cgroup *memcg;
+	struct mem_cgroup *memcg = NULL;
 	struct kmem_cache *memcg_cachep;
 	int kmemcg_id;
 
@@ -2260,7 +2269,10 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
 	if (current->memcg_kmem_skip_account)
 		return cachep;
 
-	memcg = get_mem_cgroup_from_mm(current->mm);
+	if (current->target_memcg)
+		memcg = get_mem_cgroup(current->target_memcg);
+	if (!memcg)
+		memcg = get_mem_cgroup_from_mm(current->mm);
 	kmemcg_id = READ_ONCE(memcg->kmemcg_id);
 	if (kmemcg_id < 0)
 		goto out;
@@ -2338,13 +2350,16 @@ int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
  */
 int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
 {
-	struct mem_cgroup *memcg;
+	struct mem_cgroup *memcg = NULL;
 	int ret = 0;
 
 	if (memcg_kmem_bypass())
 		return 0;
 
-	memcg = get_mem_cgroup_from_mm(current->mm);
+	if (current->target_memcg)
+		memcg = get_mem_cgroup(current->target_memcg);
+	if (!memcg)
+		memcg = get_mem_cgroup_from_mm(current->mm);
 	if (!mem_cgroup_is_root(memcg)) {
 		ret = memcg_kmem_charge_memcg(page, gfp, order, memcg);
 		if (!ret)
diff --git a/mm/mmap.c b/mm/mmap.c
index dd76ea3dd22e..faf85699f1a1 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1342,6 +1342,10 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 		if (!(file && path_noexec(&file->f_path)))
 			prot |= PROT_EXEC;
 
+	/* force arch specific MAP_FIXED handling in get_unmapped_area */
+	if (flags & MAP_FIXED_NOREPLACE)
+		flags |= MAP_FIXED;
+
 	if (!(flags & MAP_FIXED))
 		addr = round_hint_to_min(addr);
 
@@ -1365,6 +1369,13 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 	if (offset_in_page(addr))
 		return addr;
 
+	if (flags & MAP_FIXED_NOREPLACE) {
+		struct vm_area_struct *vma = find_vma(mm, addr);
+
+		if (vma && vma->vm_start <= addr)
+			return -EEXIST;
+	}
+
 	if (prot == PROT_EXEC) {
 		pkey = execute_only_pkey(mm);
 		if (pkey < 0)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 45e93727d5bf..c0f0b1b680c5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -46,7 +46,6 @@
 #include <linux/stop_machine.h>
 #include <linux/sort.h>
 #include <linux/pfn.h>
-#include <xen/xen.h>
 #include <linux/backing-dev.h>
 #include <linux/fault-inject.h>
 #include <linux/page-isolation.h>
@@ -317,9 +316,6 @@ static inline bool update_defer_init(pg_data_t *pgdat,
 	/* Always populate low zones for address-constrained allocations */
 	if (zone_end < pgdat_end_pfn(pgdat))
 		return true;
-	/* Xen PV domains need page structures early */
-	if (xen_pv_domain())
-		return true;
 	(*nr_initialised)++;
 	if ((*nr_initialised > pgdat->static_init_pgcnt) &&
 	    (pfn & (PAGES_PER_SECTION - 1)) == 0) {
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index d714f65782b7..3ab85a259de6 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -15,7 +15,6 @@
 #include <linux/vmalloc.h>
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <linux/kmemleak.h>
 
 #include <net/ip.h>
 #include <net/sock.h>
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d7431164b33e..e07ab924caa1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -108,7 +108,6 @@
 #include <net/rtnetlink.h>
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
-#include <linux/kmemleak.h>
 #endif
 #include <net/secure_seq.h>
 #include <net/ip_tunnels.h>
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 9c86d384a9b0..cf56ebdd9c45 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -23,7 +23,6 @@
 #include <linux/sysctl.h>
 #include <linux/audit.h>
 #include <linux/user_namespace.h>
-#include <linux/kmemleak.h>
 #include <net/sock.h>
 
 #include "include/apparmor.h"
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index fa728f662a6f..933623784ccd 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -18,6 +18,7 @@
 #include <linux/err.h>
 #include <linux/scatterlist.h>
 #include <linux/random.h>
+#include <linux/vmalloc.h>
 #include <keys/user-type.h>
 #include <keys/big_key-type.h>
 #include <crypto/aead.h>