Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:
 "A few little subsystems and a start of a lot of MM patches.

  Subsystems affected by this patch series: squashfs, ocfs2, parisc,
  vfs. With mm subsystems: slab-generic, slub, debug, pagecache, gup,
  swap, memcg, pagemap, memory-failure, vmalloc, kasan"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (128 commits)
  kasan: move kasan_report() into report.c
  mm/mm_init.c: report kasan-tag information stored in page->flags
  ubsan: entirely disable alignment checks under UBSAN_TRAP
  kasan: fix clang compilation warning due to stack protector
  x86/mm: remove vmalloc faulting
  mm: remove vmalloc_sync_(un)mappings()
  x86/mm/32: implement arch_sync_kernel_mappings()
  x86/mm/64: implement arch_sync_kernel_mappings()
  mm/ioremap: track which page-table levels were modified
  mm/vmalloc: track which page-table levels were modified
  mm: add functions to track page directory modifications
  s390: use __vmalloc_node in stack_alloc
  powerpc: use __vmalloc_node in alloc_vm_stack
  arm64: use __vmalloc_node in arch_alloc_vmap_stack
  mm: remove vmalloc_user_node_flags
  mm: switch the test_vmalloc module to use __vmalloc_node
  mm: remove __vmalloc_node_flags_caller
  mm: remove both instances of __vmalloc_node_flags
  mm: remove the prot argument to __vmalloc_node
  mm: remove the pgprot argument to __vmalloc
  ...

Documentation/admin-guide/cgroup-v2.rst

@@ -1329,6 +1329,10 @@ PAGE_SIZE multiple when read back.
 	  workingset_activate
 		Number of refaulted pages that were immediately activated
 
+	  workingset_restore
+		Number of restored pages which have been detected as an active
+		workingset before they got reclaimed.
+
 	  workingset_nodereclaim
 		Number of times a shadow node has been reclaimed
 
@@ -1370,6 +1374,22 @@ PAGE_SIZE multiple when read back.
 	The total amount of swap currently being used by the cgroup
 	and its descendants.
 
+  memory.swap.high
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "max".
+
+	Swap usage throttle limit.  If a cgroup's swap usage exceeds
+	this limit, all its further allocations will be throttled to
+	allow userspace to implement custom out-of-memory procedures.
+
+	This limit marks a point of no return for the cgroup. It is NOT
+	designed to manage the amount of swapping a workload does
+	during regular operation. Compare to memory.swap.max, which
+	prohibits swapping past a set amount, but lets the cgroup
+	continue unimpeded as long as other memory can be reclaimed.
+
+	Healthy workloads are not expected to reach this limit.
+
   memory.swap.max
 	A read-write single value file which exists on non-root
 	cgroups.  The default is "max".
@@ -1383,6 +1403,10 @@ PAGE_SIZE multiple when read back.
 	otherwise, a value change in this file generates a file
 	modified event.
 
+	  high
+		The number of times the cgroup's swap usage was over
+		the high threshold.
+
 	  max
 		The number of times the cgroup's swap usage was about
 		to go over the max boundary and swap allocation

Documentation/core-api/cachetlb.rst

@@ -213,7 +213,7 @@ Here are the routines, one by one:
 	there will be no entries in the cache for the kernel address
 	space for virtual addresses in the range 'start' to 'end-1'.
 
-	The first of these two routines is invoked after map_vm_area()
+	The first of these two routines is invoked after map_kernel_range()
 	has installed the page table entries.  The second is invoked
 	before unmap_kernel_range() deletes the page table entries.
 

Documentation/filesystems/locking.rst

@@ -239,6 +239,7 @@ prototypes::
 	int (*readpage)(struct file *, struct page *);
 	int (*writepages)(struct address_space *, struct writeback_control *);
 	int (*set_page_dirty)(struct page *page);
+	void (*readahead)(struct readahead_control *);
 	int (*readpages)(struct file *filp, struct address_space *mapping,
 			struct list_head *pages, unsigned nr_pages);
 	int (*write_begin)(struct file *, struct address_space *mapping,
@@ -271,7 +272,8 @@ writepage:		yes, unlocks (see below)
 readpage:		yes, unlocks
 writepages:
 set_page_dirty		no
-readpages:
+readahead:		yes, unlocks
+readpages:		no
 write_begin:		locks the page		 exclusive
 write_end:		yes, unlocks		 exclusive
 bmap:
@@ -295,6 +297,8 @@ the request handler (/dev/loop).
 ->readpage() unlocks the page, either synchronously or via I/O
 completion.
 
+->readahead() unlocks the pages that I/O is attempted on like ->readpage().
+
 ->readpages() populates the pagecache with the passed pages and starts
 I/O against them.  They come unlocked upon I/O completion.
 

Documentation/filesystems/proc.rst

@@ -1043,8 +1043,8 @@ PageTables
               amount of memory dedicated to the lowest level of page
               tables.
 NFS_Unstable
-              NFS pages sent to the server, but not yet committed to stable
-	      storage
+              Always zero. Previous counted pages which had been written to
+              the server, but has not been committed to stable storage.
 Bounce
               Memory used for block device "bounce buffers"
 WritebackTmp

Documentation/filesystems/vfs.rst

@@ -706,6 +706,7 @@ cache in your filesystem.  The following members are defined:
 		int (*readpage)(struct file *, struct page *);
 		int (*writepages)(struct address_space *, struct writeback_control *);
 		int (*set_page_dirty)(struct page *page);
+		void (*readahead)(struct readahead_control *);
 		int (*readpages)(struct file *filp, struct address_space *mapping,
 				 struct list_head *pages, unsigned nr_pages);
 		int (*write_begin)(struct file *, struct address_space *mapping,
@@ -781,12 +782,26 @@ cache in your filesystem.  The following members are defined:
 	If defined, it should set the PageDirty flag, and the
 	PAGECACHE_TAG_DIRTY tag in the radix tree.
 
+``readahead``
+	Called by the VM to read pages associated with the address_space
+	object.  The pages are consecutive in the page cache and are
+	locked.  The implementation should decrement the page refcount
+	after starting I/O on each page.  Usually the page will be
+	unlocked by the I/O completion handler.  If the filesystem decides
+	to stop attempting I/O before reaching the end of the readahead
+	window, it can simply return.  The caller will decrement the page
+	refcount and unlock the remaining pages for you.  Set PageUptodate
+	if the I/O completes successfully.  Setting PageError on any page
+	will be ignored; simply unlock the page if an I/O error occurs.
+
 ``readpages``
 	called by the VM to read pages associated with the address_space
 	object.  This is essentially just a vector version of readpage.
 	Instead of just one page, several pages are requested.
 	readpages is only used for read-ahead, so read errors are
 	ignored.  If anything goes wrong, feel free to give up.
+	This interface is deprecated and will be removed by the end of
+	2020; implement readahead instead.
 
 ``write_begin``
 	Called by the generic buffered write code to ask the filesystem

Documentation/vm/slub.rst

@@ -49,7 +49,7 @@ Possible debug options are::
 	P		Poisoning (object and padding)
 	U		User tracking (free and alloc)
 	T		Trace (please only use on single slabs)
-	A		Toggle failslab filter mark for the cache
+	A		Enable failslab filter mark for the cache
 	O		Switch debugging off for caches that would have
 			caused higher minimum slab orders
 	-		Switch all debugging off (useful if the kernel is

arch/arm/configs/omap2plus_defconfig

@@ -81,7 +81,7 @@ CONFIG_PARTITION_ADVANCED=y
 CONFIG_BINFMT_MISC=y
 CONFIG_CMA=y
 CONFIG_ZSMALLOC=m
-CONFIG_PGTABLE_MAPPING=y
+CONFIG_ZSMALLOC_PGTABLE_MAPPING=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y

arch/arm64/include/asm/pgtable.h

@@ -407,6 +407,9 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 #define __pgprot_modify(prot,mask,bits) \
 	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
 
+#define pgprot_nx(prot) \
+	__pgprot_modify(prot, 0, PTE_PXN)
+
 /*
  * Mark the prot value as uncacheable and unbufferable.
  */

arch/arm64/include/asm/vmap_stack.h

@@ -19,10 +19,8 @@ static inline unsigned long *arch_alloc_vmap_stack(size_t stack_size, int node)
 {
 	BUILD_BUG_ON(!IS_ENABLED(CONFIG_VMAP_STACK));
 
-	return __vmalloc_node_range(stack_size, THREAD_ALIGN,
-				    VMALLOC_START, VMALLOC_END,
-				    THREADINFO_GFP, PAGE_KERNEL, 0, node,
-				    __builtin_return_address(0));
+	return __vmalloc_node(stack_size, THREAD_ALIGN, THREADINFO_GFP, node,
+			__builtin_return_address(0));
 }
 
 #endif /* __ASM_VMAP_STACK_H */

arch/arm64/mm/dump.c

@@ -252,7 +252,7 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr)
 }
 
 static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
-		      unsigned long val)
+		      u64 val)
 {
 	struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
 	static const char units[] = "KMGTPE";

arch/parisc/include/asm/pgtable.h

@@ -93,10 +93,8 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 
 #define set_pte_at(mm, addr, ptep, pteval)			\
 	do {							\
-		pte_t old_pte;					\
 		unsigned long flags;				\
 		spin_lock_irqsave(pgd_spinlock((mm)->pgd), flags);\
-		old_pte = *ptep;				\
 		set_pte(ptep, pteval);				\
 		purge_tlb_entries(mm, addr);			\
 		spin_unlock_irqrestore(pgd_spinlock((mm)->pgd), flags);\

arch/powerpc/include/asm/io.h

@@ -699,10 +699,6 @@ static inline void iosync(void)
  *
  * * iounmap undoes such a mapping and can be hooked
  *
- * * __ioremap_at (and the pending __iounmap_at) are low level functions to
- *   create hand-made mappings for use only by the PCI code and cannot
- *   currently be hooked. Must be page aligned.
- *
  * * __ioremap_caller is the same as above but takes an explicit caller
  *   reference rather than using __builtin_return_address(0)
  *
@@ -719,6 +715,8 @@ void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size);
 
 extern void iounmap(volatile void __iomem *addr);
 
+void __iomem *ioremap_phb(phys_addr_t paddr, unsigned long size);
+
 int early_ioremap_range(unsigned long ea, phys_addr_t pa,
 			unsigned long size, pgprot_t prot);
 void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
@@ -727,10 +725,6 @@ void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
 extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size,
 				      pgprot_t prot, void *caller);
 
-extern void __iomem * __ioremap_at(phys_addr_t pa, void *ea,
-				   unsigned long size, pgprot_t prot);
-extern void __iounmap_at(void *ea, unsigned long size);
-
 /*
  * When CONFIG_PPC_INDIRECT_PIO is set, we use the generic iomap implementation
  * which needs some additional definitions here. They basically allow PIO

arch/powerpc/include/asm/pci-bridge.h

@@ -66,7 +66,7 @@ struct pci_controller {
 
 	void __iomem *io_base_virt;
 #ifdef CONFIG_PPC64
-	void *io_base_alloc;
+	void __iomem *io_base_alloc;
 #endif
 	resource_size_t io_base_phys;
 	resource_size_t pci_io_size;

arch/powerpc/kernel/irq.c

@@ -748,9 +748,8 @@ void do_IRQ(struct pt_regs *regs)
 
 static void *__init alloc_vm_stack(void)
 {
-	return __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, VMALLOC_START,
-				    VMALLOC_END, THREADINFO_GFP, PAGE_KERNEL,
-				     0, NUMA_NO_NODE, (void*)_RET_IP_);
+	return __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, THREADINFO_GFP,
+			      NUMA_NO_NODE, (void *)_RET_IP_);
 }
 
 static void __init vmap_irqstack_init(void)

arch/powerpc/kernel/isa-bridge.c

@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/notifier.h>
+#include <linux/vmalloc.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -38,6 +39,22 @@ EXPORT_SYMBOL_GPL(isa_bridge_pcidev);
 #define ISA_SPACE_MASK 0x1
 #define ISA_SPACE_IO 0x1
 
+static void remap_isa_base(phys_addr_t pa, unsigned long size)
+{
+	WARN_ON_ONCE(ISA_IO_BASE & ~PAGE_MASK);
+	WARN_ON_ONCE(pa & ~PAGE_MASK);
+	WARN_ON_ONCE(size & ~PAGE_MASK);
+
+	if (slab_is_available()) {
+		if (ioremap_page_range(ISA_IO_BASE, ISA_IO_BASE + size, pa,
+				pgprot_noncached(PAGE_KERNEL)))
+			unmap_kernel_range(ISA_IO_BASE, size);
+	} else {
+		early_ioremap_range(ISA_IO_BASE, pa, size,
+				pgprot_noncached(PAGE_KERNEL));
+	}
+}
+
 static void pci_process_ISA_OF_ranges(struct device_node *isa_node,
 				      unsigned long phb_io_base_phys)
 {
@@ -105,15 +122,13 @@ static void pci_process_ISA_OF_ranges(struct device_node *isa_node,
 	if (size > 0x10000)
 		size = 0x10000;
 
-	__ioremap_at(phb_io_base_phys, (void *)ISA_IO_BASE,
-		     size, pgprot_noncached(PAGE_KERNEL));
+	remap_isa_base(phb_io_base_phys, size);
 	return;
 
 inval_range:
 	printk(KERN_ERR "no ISA IO ranges or unexpected isa range, "
 	       "mapping 64k\n");
-	__ioremap_at(phb_io_base_phys, (void *)ISA_IO_BASE,
-		     0x10000, pgprot_noncached(PAGE_KERNEL));
+	remap_isa_base(phb_io_base_phys, 0x10000);
 }
 
 
@@ -248,8 +263,7 @@ void __init isa_bridge_init_non_pci(struct device_node *np)
 	 * and map it
 	 */
 	isa_io_base = ISA_IO_BASE;
-	__ioremap_at(pbase, (void *)ISA_IO_BASE,
-		     size, pgprot_noncached(PAGE_KERNEL));
+	remap_isa_base(pbase, size);
 
 	pr_debug("ISA: Non-PCI bridge is %pOF\n", np);
 }
@@ -297,7 +311,7 @@ static void isa_bridge_remove(void)
 	isa_bridge_pcidev = NULL;
 
 	/* Unmap the ISA area */
-	__iounmap_at((void *)ISA_IO_BASE, 0x10000);
+	unmap_kernel_range(ISA_IO_BASE, 0x10000);
 }
 
 /**

arch/powerpc/kernel/pci_64.c

@@ -109,23 +109,47 @@ int pcibios_unmap_io_space(struct pci_bus *bus)
 	/* Get the host bridge */
 	hose = pci_bus_to_host(bus);
 
-	/* Check if we have IOs allocated */
-	if (hose->io_base_alloc == NULL)
-		return 0;
-
 	pr_debug("IO unmapping for PHB %pOF\n", hose->dn);
 	pr_debug("  alloc=0x%p\n", hose->io_base_alloc);
 
-	/* This is a PHB, we fully unmap the IO area */
-	vunmap(hose->io_base_alloc);
-
+	iounmap(hose->io_base_alloc);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pcibios_unmap_io_space);
 
-static int pcibios_map_phb_io_space(struct pci_controller *hose)
+void __iomem *ioremap_phb(phys_addr_t paddr, unsigned long size)
 {
 	struct vm_struct *area;
+	unsigned long addr;
+
+	WARN_ON_ONCE(paddr & ~PAGE_MASK);
+	WARN_ON_ONCE(size & ~PAGE_MASK);
+
+	/*
+	 * Let's allocate some IO space for that guy. We don't pass VM_IOREMAP
+	 * because we don't care about alignment tricks that the core does in
+	 * that case.  Maybe we should due to stupid card with incomplete
+	 * address decoding but I'd rather not deal with those outside of the
+	 * reserved 64K legacy region.
+	 */
+	area = __get_vm_area_caller(size, 0, PHB_IO_BASE, PHB_IO_END,
+				    __builtin_return_address(0));
+	if (!area)
+		return NULL;
+
+	addr = (unsigned long)area->addr;
+	if (ioremap_page_range(addr, addr + size, paddr,
+			pgprot_noncached(PAGE_KERNEL))) {
+		unmap_kernel_range(addr, size);
+		return NULL;
+	}
+
+	return (void __iomem *)addr;
+}
+EXPORT_SYMBOL_GPL(ioremap_phb);
+
+static int pcibios_map_phb_io_space(struct pci_controller *hose)
+{
 	unsigned long phys_page;
 	unsigned long size_page;
 	unsigned long io_virt_offset;
@@ -146,12 +170,11 @@ static int pcibios_map_phb_io_space(struct pci_controller *hose)
 	 * with incomplete address decoding but I'd rather not deal with
 	 * those outside of the reserved 64K legacy region.
 	 */
-	area = __get_vm_area(size_page, 0, PHB_IO_BASE, PHB_IO_END);
-	if (area == NULL)
+	hose->io_base_alloc = ioremap_phb(phys_page, size_page);
+	if (!hose->io_base_alloc)
 		return -ENOMEM;
-	hose->io_base_alloc = area->addr;
-	hose->io_base_virt = (void __iomem *)(area->addr +
-					      hose->io_base_phys - phys_page);
+	hose->io_base_virt = hose->io_base_alloc +
+				hose->io_base_phys - phys_page;
 
 	pr_debug("IO mapping for PHB %pOF\n", hose->dn);
 	pr_debug("  phys=0x%016llx, virt=0x%p (alloc=0x%p)\n",
@@ -159,11 +182,6 @@ static int pcibios_map_phb_io_space(struct pci_controller *hose)
 	pr_debug("  size=0x%016llx (alloc=0x%016lx)\n",
 		 hose->pci_io_size, size_page);
 
-	/* Establish the mapping */
-	if (__ioremap_at(phys_page, area->addr, size_page,
-			 pgprot_noncached(PAGE_KERNEL)) == NULL)
-		return -ENOMEM;
-
 	/* Fixup hose IO resource */
 	io_virt_offset = pcibios_io_space_offset(hose);
 	hose->io_resource.start += io_virt_offset;

arch/powerpc/mm/ioremap_64.c

@@ -4,56 +4,6 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 
-/**
- * Low level function to establish the page tables for an IO mapping
- */
-void __iomem *__ioremap_at(phys_addr_t pa, void *ea, unsigned long size, pgprot_t prot)
-{
-	int ret;
-	unsigned long va = (unsigned long)ea;
-
-	/* We don't support the 4K PFN hack with ioremap */
-	if (pgprot_val(prot) & H_PAGE_4K_PFN)
-		return NULL;
-
-	if ((ea + size) >= (void *)IOREMAP_END) {
-		pr_warn("Outside the supported range\n");
-		return NULL;
-	}
-
-	WARN_ON(pa & ~PAGE_MASK);
-	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
-	WARN_ON(size & ~PAGE_MASK);
-
-	if (slab_is_available()) {
-		ret = ioremap_page_range(va, va + size, pa, prot);
-		if (ret)
-			unmap_kernel_range(va, size);
-	} else {
-		ret = early_ioremap_range(va, pa, size, prot);
-	}
-
-	if (ret)
-		return NULL;
-
-	return (void __iomem *)ea;
-}
-EXPORT_SYMBOL(__ioremap_at);
-
-/**
- * Low level function to tear down the page tables for an IO mapping. This is
- * used for mappings that are manipulated manually, like partial unmapping of
- * PCI IOs or ISA space.
- */
-void __iounmap_at(void *ea, unsigned long size)
-{
-	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
-	WARN_ON(size & ~PAGE_MASK);
-
-	unmap_kernel_range((unsigned long)ea, size);
-}
-EXPORT_SYMBOL(__iounmap_at);
-
 void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size,
 			       pgprot_t prot, void *caller)
 {

arch/riscv/include/asm/pgtable.h

@@ -473,9 +473,9 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 #define PAGE_SHARED		__pgprot(0)
 #define PAGE_KERNEL		__pgprot(0)
 #define swapper_pg_dir		NULL
+#define TASK_SIZE		0xffffffffUL
 #define VMALLOC_START		0
-
-#define TASK_SIZE 0xffffffffUL
+#define VMALLOC_END		TASK_SIZE
 
 static inline void __kernel_map_pages(struct page *page, int numpages, int enable) {}
 

arch/riscv/mm/ptdump.c

@@ -204,7 +204,7 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr)
 }
 
 static void note_page(struct ptdump_state *pt_st, unsigned long addr,
-		      int level, unsigned long val)
+		      int level, u64 val)
 {
 	struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
 	u64 pa = PFN_PHYS(pte_pfn(__pte(val)));

arch/s390/kernel/setup.c

@@ -305,12 +305,9 @@ void *restart_stack __section(.data);
 unsigned long stack_alloc(void)
 {
 #ifdef CONFIG_VMAP_STACK
-	return (unsigned long)
-		__vmalloc_node_range(THREAD_SIZE, THREAD_SIZE,
-				     VMALLOC_START, VMALLOC_END,
-				     THREADINFO_GFP,
-				     PAGE_KERNEL, 0, NUMA_NO_NODE,
-				     __builtin_return_address(0));
+	return (unsigned long)__vmalloc_node(THREAD_SIZE, THREAD_SIZE,
+			THREADINFO_GFP, NUMA_NO_NODE,
+			__builtin_return_address(0));
 #else
 	return __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER);
 #endif