Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "Most of the rest of MM and various other things. Some Kconfig rework
  still awaits merges of dependent trees from linux-next.

  Subsystems affected by this patch series: mm/hotfixes, mm/memcg,
  mm/vmstat, mm/thp, procfs, sysctl, misc, notifiers, core-kernel,
  bitops, lib, checkpatch, epoll, binfmt, init, rapidio, uaccess, kcov,
  ubsan, ipc, bitmap, mm/pagemap"

* akpm: (86 commits)
  mm: remove __ARCH_HAS_4LEVEL_HACK and include/asm-generic/4level-fixup.h
  um: add support for folded p4d page tables
  um: remove unused pxx_offset_proc() and addr_pte() functions
  sparc32: use pgtable-nopud instead of 4level-fixup
  parisc/hugetlb: use pgtable-nopXd instead of 4level-fixup
  parisc: use pgtable-nopXd instead of 4level-fixup
  nds32: use pgtable-nopmd instead of 4level-fixup
  microblaze: use pgtable-nopmd instead of 4level-fixup
  m68k: mm: use pgtable-nopXd instead of 4level-fixup
  m68k: nommu: use pgtable-nopud instead of 4level-fixup
  c6x: use pgtable-nopud instead of 4level-fixup
  arm: nommu: use pgtable-nopud instead of 4level-fixup
  alpha: use pgtable-nopud instead of 4level-fixup
  gpio: pca953x: tighten up indentation
  gpio: pca953x: convert to use bitmap API
  gpio: pca953x: use input from regs structure in pca953x_irq_pending()
  gpio: pca953x: remove redundant variable and check in IRQ handler
  lib/bitmap: introduce bitmap_replace() helper
  lib/test_bitmap: fix comment about this file
  lib/test_bitmap: move exp1 and exp2 upper for others to use
  ...

.gitattributes

@@ -1,2 +1,4 @@
 *.c   diff=cpp
 *.h   diff=cpp
+*.dtsi diff=dts
+*.dts  diff=dts

Documentation/core-api/genalloc.rst

@@ -129,7 +129,7 @@ writing of special-purpose memory allocators in the future.
    :functions: gen_pool_for_each_chunk
 
 .. kernel-doc:: lib/genalloc.c
-   :functions: addr_in_gen_pool
+   :functions: gen_pool_has_addr
 
 .. kernel-doc:: lib/genalloc.c
    :functions: gen_pool_avail

Documentation/dev-tools/kcov.rst

@@ -34,6 +34,7 @@ Profiling data will only become accessible once debugfs has been mounted::
 
 Coverage collection
 -------------------
+
 The following program demonstrates coverage collection from within a test
 program using kcov:
 
@@ -128,6 +129,7 @@ only need to enable coverage (disable happens automatically on thread end).
 
 Comparison operands collection
 ------------------------------
+
 Comparison operands collection is similar to coverage collection:
 
 .. code-block:: c
@@ -202,3 +204,130 @@ Comparison operands collection is similar to coverage collection:
 
 Note that the kcov modes (coverage collection or comparison operands) are
 mutually exclusive.
+
+Remote coverage collection
+--------------------------
+
+With KCOV_ENABLE coverage is collected only for syscalls that are issued
+from the current process. With KCOV_REMOTE_ENABLE it's possible to collect
+coverage for arbitrary parts of the kernel code, provided that those parts
+are annotated with kcov_remote_start()/kcov_remote_stop().
+
+This allows to collect coverage from two types of kernel background
+threads: the global ones, that are spawned during kernel boot in a limited
+number of instances (e.g. one USB hub_event() worker thread is spawned per
+USB HCD); and the local ones, that are spawned when a user interacts with
+some kernel interface (e.g. vhost workers).
+
+To enable collecting coverage from a global background thread, a unique
+global handle must be assigned and passed to the corresponding
+kcov_remote_start() call. Then a userspace process can pass a list of such
+handles to the KCOV_REMOTE_ENABLE ioctl in the handles array field of the
+kcov_remote_arg struct. This will attach the used kcov device to the code
+sections, that are referenced by those handles.
+
+Since there might be many local background threads spawned from different
+userspace processes, we can't use a single global handle per annotation.
+Instead, the userspace process passes a non-zero handle through the
+common_handle field of the kcov_remote_arg struct. This common handle gets
+saved to the kcov_handle field in the current task_struct and needs to be
+passed to the newly spawned threads via custom annotations. Those threads
+should in turn be annotated with kcov_remote_start()/kcov_remote_stop().
+
+Internally kcov stores handles as u64 integers. The top byte of a handle
+is used to denote the id of a subsystem that this handle belongs to, and
+the lower 4 bytes are used to denote the id of a thread instance within
+that subsystem. A reserved value 0 is used as a subsystem id for common
+handles as they don't belong to a particular subsystem. The bytes 4-7 are
+currently reserved and must be zero. In the future the number of bytes
+used for the subsystem or handle ids might be increased.
+
+When a particular userspace proccess collects coverage by via a common
+handle, kcov will collect coverage for each code section that is annotated
+to use the common handle obtained as kcov_handle from the current
+task_struct. However non common handles allow to collect coverage
+selectively from different subsystems.
+
+.. code-block:: c
+
+    struct kcov_remote_arg {
+	unsigned	trace_mode;
+	unsigned	area_size;
+	unsigned	num_handles;
+	uint64_t	common_handle;
+	uint64_t	handles[0];
+    };
+
+    #define KCOV_INIT_TRACE			_IOR('c', 1, unsigned long)
+    #define KCOV_DISABLE			_IO('c', 101)
+    #define KCOV_REMOTE_ENABLE		_IOW('c', 102, struct kcov_remote_arg)
+
+    #define COVER_SIZE	(64 << 10)
+
+    #define KCOV_TRACE_PC	0
+
+    #define KCOV_SUBSYSTEM_COMMON	(0x00ull << 56)
+    #define KCOV_SUBSYSTEM_USB	(0x01ull << 56)
+
+    #define KCOV_SUBSYSTEM_MASK	(0xffull << 56)
+    #define KCOV_INSTANCE_MASK	(0xffffffffull)
+
+    static inline __u64 kcov_remote_handle(__u64 subsys, __u64 inst)
+    {
+	if (subsys & ~KCOV_SUBSYSTEM_MASK || inst & ~KCOV_INSTANCE_MASK)
+		return 0;
+	return subsys | inst;
+    }
+
+    #define KCOV_COMMON_ID	0x42
+    #define KCOV_USB_BUS_NUM	1
+
+    int main(int argc, char **argv)
+    {
+	int fd;
+	unsigned long *cover, n, i;
+	struct kcov_remote_arg *arg;
+
+	fd = open("/sys/kernel/debug/kcov", O_RDWR);
+	if (fd == -1)
+		perror("open"), exit(1);
+	if (ioctl(fd, KCOV_INIT_TRACE, COVER_SIZE))
+		perror("ioctl"), exit(1);
+	cover = (unsigned long*)mmap(NULL, COVER_SIZE * sizeof(unsigned long),
+				     PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+	if ((void*)cover == MAP_FAILED)
+		perror("mmap"), exit(1);
+
+	/* Enable coverage collection via common handle and from USB bus #1. */
+	arg = calloc(1, sizeof(*arg) + sizeof(uint64_t));
+	if (!arg)
+		perror("calloc"), exit(1);
+	arg->trace_mode = KCOV_TRACE_PC;
+	arg->area_size = COVER_SIZE;
+	arg->num_handles = 1;
+	arg->common_handle = kcov_remote_handle(KCOV_SUBSYSTEM_COMMON,
+							KCOV_COMMON_ID);
+	arg->handles[0] = kcov_remote_handle(KCOV_SUBSYSTEM_USB,
+						KCOV_USB_BUS_NUM);
+	if (ioctl(fd, KCOV_REMOTE_ENABLE, arg))
+		perror("ioctl"), free(arg), exit(1);
+	free(arg);
+
+	/*
+	 * Here the user needs to trigger execution of a kernel code section
+	 * that is either annotated with the common handle, or to trigger some
+	 * activity on USB bus #1.
+	 */
+	sleep(2);
+
+	n = __atomic_load_n(&cover[0], __ATOMIC_RELAXED);
+	for (i = 0; i < n; i++)
+		printf("0x%lx\n", cover[i + 1]);
+	if (ioctl(fd, KCOV_DISABLE, 0))
+		perror("ioctl"), exit(1);
+	if (munmap(cover, COVER_SIZE * sizeof(unsigned long)))
+		perror("munmap"), exit(1);
+	if (close(fd))
+		perror("close"), exit(1);
+	return 0;
+    }

arch/Kconfig

@@ -72,19 +72,19 @@ config KPROBES
 	  If in doubt, say "N".
 
 config JUMP_LABEL
-       bool "Optimize very unlikely/likely branches"
-       depends on HAVE_ARCH_JUMP_LABEL
-       depends on CC_HAS_ASM_GOTO
-       help
-         This option enables a transparent branch optimization that
+	bool "Optimize very unlikely/likely branches"
+	depends on HAVE_ARCH_JUMP_LABEL
+	depends on CC_HAS_ASM_GOTO
+	help
+	 This option enables a transparent branch optimization that
 	 makes certain almost-always-true or almost-always-false branch
 	 conditions even cheaper to execute within the kernel.
 
 	 Certain performance-sensitive kernel code, such as trace points,
 	 scheduler functionality, networking code and KVM have such
 	 branches and include support for this optimization technique.
 
-         If it is detected that the compiler has support for "asm goto",
+	 If it is detected that the compiler has support for "asm goto",
 	 the kernel will compile such branches with just a nop
 	 instruction. When the condition flag is toggled to true, the
 	 nop will be converted to a jump instruction to execute the
@@ -151,8 +151,8 @@ config HAVE_EFFICIENT_UNALIGNED_ACCESS
 	  information on the topic of unaligned memory accesses.
 
 config ARCH_USE_BUILTIN_BSWAP
-       bool
-       help
+	bool
+	help
 	 Modern versions of GCC (since 4.4) have builtin functions
 	 for handling byte-swapping. Using these, instead of the old
 	 inline assembler that the architecture code provides in the
@@ -221,10 +221,10 @@ config HAVE_DMA_CONTIGUOUS
 	bool
 
 config GENERIC_SMP_IDLE_THREAD
-       bool
+	bool
 
 config GENERIC_IDLE_POLL_SETUP
-       bool
+	bool
 
 config ARCH_HAS_FORTIFY_SOURCE
 	bool
@@ -257,7 +257,7 @@ config ARCH_HAS_UNCACHED_SEGMENT
 
 # Select if arch init_task must go in the __init_task_data section
 config ARCH_TASK_STRUCT_ON_STACK
-       bool
+	bool
 
 # Select if arch has its private alloc_task_struct() function
 config ARCH_TASK_STRUCT_ALLOCATOR

arch/alpha/include/asm/mmzone.h

@@ -73,7 +73,6 @@ PLAT_NODE_DATA_LOCALNR(unsigned long p, int n)
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
 
 #define pmd_page(pmd)		(pfn_to_page(pmd_val(pmd) >> 32))
-#define pgd_page(pgd)		(pfn_to_page(pgd_val(pgd) >> 32))
 #define pte_pfn(pte)		(pte_val(pte) >> 32)
 
 #define mk_pte(page, pgprot)						     \

arch/alpha/include/asm/pgalloc.h

@@ -27,9 +27,9 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
 }
 
 static inline void
-pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd)
+pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 {
-	pgd_set(pgd, pmd);
+	pud_set(pud, pmd);
 }
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);

arch/alpha/include/asm/pgtable.h

@@ -2,7 +2,7 @@
 #ifndef _ALPHA_PGTABLE_H
 #define _ALPHA_PGTABLE_H
 
-#include <asm-generic/4level-fixup.h>
+#include <asm-generic/pgtable-nopud.h>
 
 /*
  * This file contains the functions and defines necessary to modify and use
@@ -226,8 +226,8 @@ extern inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 extern inline void pmd_set(pmd_t * pmdp, pte_t * ptep)
 { pmd_val(*pmdp) = _PAGE_TABLE | ((((unsigned long) ptep) - PAGE_OFFSET) << (32-PAGE_SHIFT)); }
 
-extern inline void pgd_set(pgd_t * pgdp, pmd_t * pmdp)
-{ pgd_val(*pgdp) = _PAGE_TABLE | ((((unsigned long) pmdp) - PAGE_OFFSET) << (32-PAGE_SHIFT)); }
+extern inline void pud_set(pud_t * pudp, pmd_t * pmdp)
+{ pud_val(*pudp) = _PAGE_TABLE | ((((unsigned long) pmdp) - PAGE_OFFSET) << (32-PAGE_SHIFT)); }
 
 
 extern inline unsigned long
@@ -238,11 +238,11 @@ pmd_page_vaddr(pmd_t pmd)
 
 #ifndef CONFIG_DISCONTIGMEM
 #define pmd_page(pmd)	(mem_map + ((pmd_val(pmd) & _PFN_MASK) >> 32))
-#define pgd_page(pgd)	(mem_map + ((pgd_val(pgd) & _PFN_MASK) >> 32))
+#define pud_page(pud)	(mem_map + ((pud_val(pud) & _PFN_MASK) >> 32))
 #endif
 
-extern inline unsigned long pgd_page_vaddr(pgd_t pgd)
-{ return PAGE_OFFSET + ((pgd_val(pgd) & _PFN_MASK) >> (32-PAGE_SHIFT)); }
+extern inline unsigned long pud_page_vaddr(pud_t pgd)
+{ return PAGE_OFFSET + ((pud_val(pgd) & _PFN_MASK) >> (32-PAGE_SHIFT)); }
 
 extern inline int pte_none(pte_t pte)		{ return !pte_val(pte); }
 extern inline int pte_present(pte_t pte)	{ return pte_val(pte) & _PAGE_VALID; }
@@ -256,10 +256,10 @@ extern inline int pmd_bad(pmd_t pmd)		{ return (pmd_val(pmd) & ~_PFN_MASK) != _P
 extern inline int pmd_present(pmd_t pmd)	{ return pmd_val(pmd) & _PAGE_VALID; }
 extern inline void pmd_clear(pmd_t * pmdp)	{ pmd_val(*pmdp) = 0; }
 
-extern inline int pgd_none(pgd_t pgd)		{ return !pgd_val(pgd); }
-extern inline int pgd_bad(pgd_t pgd)		{ return (pgd_val(pgd) & ~_PFN_MASK) != _PAGE_TABLE; }
-extern inline int pgd_present(pgd_t pgd)	{ return pgd_val(pgd) & _PAGE_VALID; }
-extern inline void pgd_clear(pgd_t * pgdp)	{ pgd_val(*pgdp) = 0; }
+extern inline int pud_none(pud_t pud)		{ return !pud_val(pud); }
+extern inline int pud_bad(pud_t pud)		{ return (pud_val(pud) & ~_PFN_MASK) != _PAGE_TABLE; }
+extern inline int pud_present(pud_t pud)	{ return pud_val(pud) & _PAGE_VALID; }
+extern inline void pud_clear(pud_t * pudp)	{ pud_val(*pudp) = 0; }
 
 /*
  * The following only work if pte_present() is true.
@@ -301,9 +301,9 @@ extern inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
  */
 
 /* Find an entry in the second-level page table.. */
-extern inline pmd_t * pmd_offset(pgd_t * dir, unsigned long address)
+extern inline pmd_t * pmd_offset(pud_t * dir, unsigned long address)
 {
-	pmd_t *ret = (pmd_t *) pgd_page_vaddr(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1));
+	pmd_t *ret = (pmd_t *) pud_page_vaddr(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1));
 	smp_read_barrier_depends(); /* see above */
 	return ret;
 }

arch/alpha/mm/init.c

@@ -146,6 +146,8 @@ callback_init(void * kernel_end)
 {
 	struct crb_struct * crb;
 	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
 	pmd_t *pmd;
 	void *two_pages;
 
@@ -184,8 +186,10 @@ callback_init(void * kernel_end)
 	memset(two_pages, 0, 2*PAGE_SIZE);
 
 	pgd = pgd_offset_k(VMALLOC_START);
-	pgd_set(pgd, (pmd_t *)two_pages);
-	pmd = pmd_offset(pgd, VMALLOC_START);
+	p4d = p4d_offset(pgd, VMALLOC_START);
+	pud = pud_offset(p4d, VMALLOC_START);
+	pud_set(pud, (pmd_t *)two_pages);
+	pmd = pmd_offset(pud, VMALLOC_START);
 	pmd_set(pmd, (pte_t *)(two_pages + PAGE_SIZE));
 
 	if (alpha_using_srm) {
@@ -214,9 +218,9 @@ callback_init(void * kernel_end)
 				/* Newer consoles (especially on larger
 				   systems) may require more pages of
 				   PTEs. Grab additional pages as needed. */
-				if (pmd != pmd_offset(pgd, vaddr)) {
+				if (pmd != pmd_offset(pud, vaddr)) {
 					memset(kernel_end, 0, PAGE_SIZE);
-					pmd = pmd_offset(pgd, vaddr);
+					pmd = pmd_offset(pud, vaddr);
 					pmd_set(pmd, (pte_t *)kernel_end);
 					kernel_end += PAGE_SIZE;
 				}

arch/arm/include/asm/pgtable.h

@@ -12,7 +12,7 @@
 
 #ifndef CONFIG_MMU
 
-#include <asm-generic/4level-fixup.h>
+#include <asm-generic/pgtable-nopud.h>
 #include <asm/pgtable-nommu.h>
 
 #else

arch/arm/mm/dma-mapping.c

@@ -529,7 +529,7 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page)
 
 static bool __in_atomic_pool(void *start, size_t size)
 {
-	return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
+	return gen_pool_has_addr(atomic_pool, (unsigned long)start, size);
 }
 
 static int __free_from_pool(void *start, size_t size)

arch/c6x/include/asm/pgtable.h

@@ -8,7 +8,7 @@
 #ifndef _ASM_C6X_PGTABLE_H
 #define _ASM_C6X_PGTABLE_H
 
-#include <asm-generic/4level-fixup.h>
+#include <asm-generic/pgtable-nopud.h>
 
 #include <asm/setup.h>
 #include <asm/page.h>

arch/m68k/include/asm/mcf_pgalloc.h

@@ -28,9 +28,6 @@ extern inline pmd_t *pmd_alloc_kernel(pgd_t *pgd, unsigned long address)
 	return (pmd_t *) pgd;
 }
 
-#define pmd_alloc_one_fast(mm, address) ({ BUG(); ((pmd_t *)1); })
-#define pmd_alloc_one(mm, address)      ({ BUG(); ((pmd_t *)2); })
-
 #define pmd_populate(mm, pmd, page) (pmd_val(*pmd) = \
 	(unsigned long)(page_address(page)))
 
@@ -45,8 +42,6 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page,
 	__free_page(page);
 }
 
-#define __pmd_free_tlb(tlb, pmd, address) do { } while (0)
-
 static inline struct page *pte_alloc_one(struct mm_struct *mm)
 {
 	struct page *page = alloc_pages(GFP_DMA, 0);
@@ -100,6 +95,4 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 	return new_pgd;
 }
 
-#define pgd_populate(mm, pmd, pte) BUG()
-
 #endif /* M68K_MCF_PGALLOC_H */