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

 *.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/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 */

arch/m68k/include/asm/mcf_pgtable.h

@@ -198,17 +198,9 @@ static inline int pmd_bad2(pmd_t *pmd) { return 0; }
 #define pmd_present(pmd) (!pmd_none2(&(pmd)))
 static inline void pmd_clear(pmd_t *pmdp) { pmd_val(*pmdp) = 0; }
 
-static inline int pgd_none(pgd_t pgd) { return 0; }
-static inline int pgd_bad(pgd_t pgd) { return 0; }
-static inline int pgd_present(pgd_t pgd) { return 1; }
-static inline void pgd_clear(pgd_t *pgdp) {}
-
 #define pte_ERROR(e) \
 	printk(KERN_ERR "%s:%d: bad pte %08lx.\n",	\
 	__FILE__, __LINE__, pte_val(e))
-#define pmd_ERROR(e) \
-	printk(KERN_ERR "%s:%d: bad pmd %08lx.\n",	\
-	__FILE__, __LINE__, pmd_val(e))
 #define pgd_ERROR(e) \
 	printk(KERN_ERR "%s:%d: bad pgd %08lx.\n",	\
 	__FILE__, __LINE__, pgd_val(e))
@@ -339,14 +331,6 @@ extern pgd_t kernel_pg_dir[PTRS_PER_PGD];
  */
 #define pgd_offset_k(address)	pgd_offset(&init_mm, address)
 
-/*
- * Find an entry in the second-level pagetable.
- */
-static inline pmd_t *pmd_offset(pgd_t *pgd, unsigned long address)
-{
-	return (pmd_t *) pgd;
-}
-
 /*
  * Find an entry in the third-level pagetable.
  */
@@ -360,12 +344,16 @@ static inline pmd_t *pmd_offset(pgd_t *pgd, unsigned long address)
 static inline void nocache_page(void *vaddr)
 {
 	pgd_t *dir;
+	p4d_t *p4dp;
+	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
 	unsigned long addr = (unsigned long) vaddr;
 
 	dir = pgd_offset_k(addr);
-	pmdp = pmd_offset(dir, addr);
+	p4dp = p4d_offset(dir, addr);
+	pudp = pud_offset(p4dp, addr);
+	pmdp = pmd_offset(pudp, addr);
 	ptep = pte_offset_kernel(pmdp, addr);
 	*ptep = pte_mknocache(*ptep);
 }
@@ -376,12 +364,16 @@ static inline void nocache_page(void *vaddr)
 static inline void cache_page(void *vaddr)
 {
 	pgd_t *dir;
+	p4d_t *p4dp;
+	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
 	unsigned long addr = (unsigned long) vaddr;
 
 	dir = pgd_offset_k(addr);
-	pmdp = pmd_offset(dir, addr);
+	p4dp = p4d_offset(dir, addr);
+	pudp = pud_offset(p4dp, addr);
+	pmdp = pmd_offset(pudp, addr);
 	ptep = pte_offset_kernel(pmdp, addr);
 	*ptep = pte_mkcache(*ptep);
 }

arch/m68k/include/asm/mmu_context.h

@@ -100,6 +100,8 @@ static inline void load_ksp_mmu(struct task_struct *task)
 	struct mm_struct *mm;
 	int asid;
 	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 	unsigned long mmuar;
@@ -127,7 +129,15 @@ static inline void load_ksp_mmu(struct task_struct *task)
 	if (pgd_none(*pgd))
 		goto bug;
 
-	pmd = pmd_offset(pgd, mmuar);
+	p4d = p4d_offset(pgd, mmuar);
+	if (p4d_none(*p4d))
+		goto bug;
+
+	pud = pud_offset(p4d, mmuar);
+	if (pud_none(*pud))
+		goto bug;
+
+	pmd = pmd_offset(pud, mmuar);
 	if (pmd_none(*pmd))
 		goto bug;
 

arch/m68k/include/asm/motorola_pgalloc.h

@@ -106,9 +106,9 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t page
 }
 #define pmd_pgtable(pmd) pmd_page(pmd)
 
-static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd)
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 {
-	pgd_set(pgd, pmd);
+	pud_set(pud, pmd);
 }
 
 #endif /* _MOTOROLA_PGALLOC_H */

arch/m68k/include/asm/motorola_pgtable.h

@@ -117,14 +117,14 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
 	}
 }
 
-static inline void pgd_set(pgd_t *pgdp, pmd_t *pmdp)
+static inline void pud_set(pud_t *pudp, pmd_t *pmdp)
 {
-	pgd_val(*pgdp) = _PAGE_TABLE | _PAGE_ACCESSED | __pa(pmdp);
+	pud_val(*pudp) = _PAGE_TABLE | _PAGE_ACCESSED | __pa(pmdp);
 }
 
 #define __pte_page(pte) ((unsigned long)__va(pte_val(pte) & PAGE_MASK))
 #define __pmd_page(pmd) ((unsigned long)__va(pmd_val(pmd) & _TABLE_MASK))
-#define __pgd_page(pgd) ((unsigned long)__va(pgd_val(pgd) & _TABLE_MASK))
+#define pud_page_vaddr(pud) ((unsigned long)__va(pud_val(pud) & _TABLE_MASK))
 
 
 #define pte_none(pte)		(!pte_val(pte))
@@ -147,11 +147,11 @@ static inline void pgd_set(pgd_t *pgdp, pmd_t *pmdp)
 #define pmd_page(pmd)		virt_to_page(__va(pmd_val(pmd)))
 
 
-#define pgd_none(pgd)		(!pgd_val(pgd))
-#define pgd_bad(pgd)		((pgd_val(pgd) & _DESCTYPE_MASK) != _PAGE_TABLE)
-#define pgd_present(pgd)	(pgd_val(pgd) & _PAGE_TABLE)
-#define pgd_clear(pgdp)		({ pgd_val(*pgdp) = 0; })
-#define pgd_page(pgd)		(mem_map + ((unsigned long)(__va(pgd_val(pgd)) - PAGE_OFFSET) >> PAGE_SHIFT))
+#define pud_none(pud)		(!pud_val(pud))
+#define pud_bad(pud)		((pud_val(pud) & _DESCTYPE_MASK) != _PAGE_TABLE)
+#define pud_present(pud)	(pud_val(pud) & _PAGE_TABLE)
+#define pud_clear(pudp)		({ pud_val(*pudp) = 0; })
+#define pud_page(pud)		(mem_map + ((unsigned long)(__va(pud_val(pud)) - PAGE_OFFSET) >> PAGE_SHIFT))
 
 #define pte_ERROR(e) \
 	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
@@ -209,9 +209,9 @@ static inline pgd_t *pgd_offset_k(unsigned long address)
 
 
 /* Find an entry in the second-level page table.. */
-static inline pmd_t *pmd_offset(pgd_t *dir, unsigned long address)
+static inline pmd_t *pmd_offset(pud_t *dir, unsigned long address)
 {
-	return (pmd_t *)__pgd_page(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PMD-1));
+	return (pmd_t *)pud_page_vaddr(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PMD-1));
 }
 
 /* Find an entry in the third-level page table.. */
@@ -239,11 +239,15 @@ static inline void nocache_page(void *vaddr)
 
 	if (CPU_IS_040_OR_060) {
 		pgd_t *dir;
+		p4d_t *p4dp;
+		pud_t *pudp;
 		pmd_t *pmdp;
 		pte_t *ptep;
 
 		dir = pgd_offset_k(addr);
-		pmdp = pmd_offset(dir, addr);
+		p4dp = p4d_offset(dir, addr);
+		pudp = pud_offset(p4dp, addr);
+		pmdp = pmd_offset(pudp, addr);
 		ptep = pte_offset_kernel(pmdp, addr);
 		*ptep = pte_mknocache(*ptep);
 	}
@@ -255,11 +259,15 @@ static inline void cache_page(void *vaddr)
 
 	if (CPU_IS_040_OR_060) {
 		pgd_t *dir;
+		p4d_t *p4dp;
+		pud_t *pudp;
 		pmd_t *pmdp;
 		pte_t *ptep;
 
 		dir = pgd_offset_k(addr);
-		pmdp = pmd_offset(dir, addr);
+		p4dp = p4d_offset(dir, addr);
+		pudp = pud_offset(p4dp, addr);
+		pmdp = pmd_offset(pudp, addr);
 		ptep = pte_offset_kernel(pmdp, addr);
 		*ptep = pte_mkcache(*ptep);
 	}

arch/m68k/include/asm/page.h

@@ -21,19 +21,22 @@
 /*
  * These are used to make use of C type-checking..
  */
-typedef struct { unsigned long pte; } pte_t;
+#if !defined(CONFIG_MMU) || CONFIG_PGTABLE_LEVELS == 3
 typedef struct { unsigned long pmd[16]; } pmd_t;
+#define pmd_val(x)	((&x)->pmd[0])
+#define __pmd(x)	((pmd_t) { { (x) }, })
+#endif
+
+typedef struct { unsigned long pte; } pte_t;
 typedef struct { unsigned long pgd; } pgd_t;
 typedef struct { unsigned long pgprot; } pgprot_t;
 typedef struct page *pgtable_t;
 
 #define pte_val(x)	((x).pte)
-#define pmd_val(x)	((&x)->pmd[0])
 #define pgd_val(x)	((x).pgd)
 #define pgprot_val(x)	((x).pgprot)
 
 #define __pte(x)	((pte_t) { (x) } )
-#define __pmd(x)	((pmd_t) { { (x) }, })
 #define __pgd(x)	((pgd_t) { (x) } )
 #define __pgprot(x)	((pgprot_t) { (x) } )
 

arch/m68k/include/asm/pgtable_mm.h

@@ -2,7 +2,12 @@
 #ifndef _M68K_PGTABLE_H
 #define _M68K_PGTABLE_H
 
-#include <asm-generic/4level-fixup.h>
+
+#if defined(CONFIG_SUN3) || defined(CONFIG_COLDFIRE)
+#include <asm-generic/pgtable-nopmd.h>
+#else
+#include <asm-generic/pgtable-nopud.h>
+#endif
 
 #include <asm/setup.h>
 
@@ -30,9 +35,7 @@
 
 
 /* PMD_SHIFT determines the size of the area a second-level page table can map */
-#ifdef CONFIG_SUN3
-#define PMD_SHIFT       17
-#else
+#if CONFIG_PGTABLE_LEVELS == 3
 #define PMD_SHIFT	22
 #endif
 #define PMD_SIZE	(1UL << PMD_SHIFT)

arch/m68k/include/asm/pgtable_no.h

@@ -2,7 +2,7 @@
 #ifndef _M68KNOMMU_PGTABLE_H
 #define _M68KNOMMU_PGTABLE_H
 
-#include <asm-generic/4level-fixup.h>
+#include <asm-generic/pgtable-nopud.h>
 
 /*
  * (C) Copyright 2000-2002, Greg Ungerer <gerg@snapgear.com>

arch/m68k/include/asm/sun3_pgalloc.h

@@ -17,8 +17,6 @@
 
 extern const char bad_pmd_string[];
 
-#define pmd_alloc_one(mm,address)       ({ BUG(); ((pmd_t *)2); })
-
 #define __pte_free_tlb(tlb,pte,addr)			\
 do {							\
 	pgtable_pte_page_dtor(pte);			\
@@ -41,7 +39,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t page
  * inside the pgd, so has no extra memory associated with it.
  */
 #define pmd_free(mm, x)			do { } while (0)
-#define __pmd_free_tlb(tlb, x, addr)	do { } while (0)
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
@@ -58,6 +55,4 @@ static inline pgd_t * pgd_alloc(struct mm_struct *mm)
      return new_pgd;
 }
 
-#define pgd_populate(mm, pmd, pte) BUG()
-
 #endif /* SUN3_PGALLOC_H */

arch/m68k/include/asm/sun3_pgtable.h

@@ -110,11 +110,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 
 #define pmd_set(pmdp,ptep) do {} while (0)
 
-static inline void pgd_set(pgd_t *pgdp, pmd_t *pmdp)
-{
-	pgd_val(*pgdp) = virt_to_phys(pmdp);
-}
-
 #define __pte_page(pte) \
 ((unsigned long) __va ((pte_val (pte) & SUN3_PAGE_PGNUM_MASK) << PAGE_SHIFT))
 #define __pmd_page(pmd) \
@@ -145,16 +140,9 @@ static inline int pmd_present2 (pmd_t *pmd) { return pmd_val (*pmd) & SUN3_PMD_V
 #define pmd_present(pmd) (!pmd_none2(&(pmd)))
 static inline void pmd_clear (pmd_t *pmdp) { pmd_val (*pmdp) = 0; }
 
-static inline int pgd_none (pgd_t pgd) { return 0; }
-static inline int pgd_bad (pgd_t pgd) { return 0; }
-static inline int pgd_present (pgd_t pgd) { return 1; }
-static inline void pgd_clear (pgd_t *pgdp) {}
-
 
 #define pte_ERROR(e) \
 	pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
-#define pmd_ERROR(e) \
-	pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
 #define pgd_ERROR(e) \
 	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 
@@ -194,12 +182,6 @@ extern pgd_t kernel_pg_dir[PTRS_PER_PGD];
 /* Find an entry in a kernel pagetable directory. */
 #define pgd_offset_k(address) pgd_offset(&init_mm, address)
 
-/* Find an entry in the second-level pagetable. */
-static inline pmd_t *pmd_offset (pgd_t *pgd, unsigned long address)
-{
-	return (pmd_t *) pgd;
-}
-
 /* Find an entry in the third-level pagetable. */
 #define pte_index(address) ((address >> PAGE_SHIFT) & (PTRS_PER_PTE-1))
 #define pte_offset_kernel(pmd, address) ((pte_t *) __pmd_page(*pmd) + pte_index(address))

arch/m68k/kernel/sys_m68k.c

@@ -465,6 +465,8 @@ sys_atomic_cmpxchg_32(unsigned long newval, int oldval, int d3, int d4, int d5,
 	for (;;) {
 		struct mm_struct *mm = current->mm;
 		pgd_t *pgd;
+		p4d_t *p4d;
+		pud_t *pud;
 		pmd_t *pmd;
 		pte_t *pte;
 		spinlock_t *ptl;
@@ -474,7 +476,13 @@ sys_atomic_cmpxchg_32(unsigned long newval, int oldval, int d3, int d4, int d5,
 		pgd = pgd_offset(mm, (unsigned long)mem);
 		if (!pgd_present(*pgd))
 			goto bad_access;
-		pmd = pmd_offset(pgd, (unsigned long)mem);
+		p4d = p4d_offset(pgd, (unsigned long)mem);
+		if (!p4d_present(*p4d))
+			goto bad_access;
+		pud = pud_offset(p4d, (unsigned long)mem);
+		if (!pud_present(*pud))
+			goto bad_access;
+		pmd = pmd_offset(pud, (unsigned long)mem);
 		if (!pmd_present(*pmd))
 			goto bad_access;
 		pte = pte_offset_map_lock(mm, pmd, (unsigned long)mem, &ptl);

arch/m68k/mm/init.c

@@ -130,8 +130,10 @@ static inline void init_pointer_tables(void)
 	/* insert pointer tables allocated so far into the tablelist */
 	init_pointer_table((unsigned long)kernel_pg_dir);
 	for (i = 0; i < PTRS_PER_PGD; i++) {
-		if (pgd_present(kernel_pg_dir[i]))
-			init_pointer_table(__pgd_page(kernel_pg_dir[i]));
+		pud_t *pud = (pud_t *)(&kernel_pg_dir[i]);
+
+		if (pud_present(*pud))
+			init_pointer_table(pgd_page_vaddr(kernel_pg_dir[i]));
 	}
 
 	/* insert also pointer table that we used to unmap the zero page */

arch/m68k/mm/kmap.c

@@ -63,18 +63,23 @@ static void __free_io_area(void *addr, unsigned long size)
 {
 	unsigned long virtaddr = (unsigned long)addr;
 	pgd_t *pgd_dir;
+	p4d_t *p4d_dir;
+	pud_t *pud_dir;
 	pmd_t *pmd_dir;
 	pte_t *pte_dir;
 
 	while ((long)size > 0) {
 		pgd_dir = pgd_offset_k(virtaddr);
-		if (pgd_bad(*pgd_dir)) {
-			printk("iounmap: bad pgd(%08lx)\n", pgd_val(*pgd_dir));
-			pgd_clear(pgd_dir);
+		p4d_dir = p4d_offset(pgd_dir, virtaddr);
+		pud_dir = pud_offset(p4d_dir, virtaddr);
+		if (pud_bad(*pud_dir)) {
+			printk("iounmap: bad pud(%08lx)\n", pud_val(*pud_dir));
+			pud_clear(pud_dir);
 			return;
 		}
-		pmd_dir = pmd_offset(pgd_dir, virtaddr);
+		pmd_dir = pmd_offset(pud_dir, virtaddr);
 
+#if CONFIG_PGTABLE_LEVELS == 3
 		if (CPU_IS_020_OR_030) {
 			int pmd_off = (virtaddr/PTRTREESIZE) & 15;
 			int pmd_type = pmd_dir->pmd[pmd_off] & _DESCTYPE_MASK;
@@ -87,6 +92,7 @@ static void __free_io_area(void *addr, unsigned long size)
 			} else if (pmd_type == 0)
 				continue;
 		}
+#endif
 
 		if (pmd_bad(*pmd_dir)) {
 			printk("iounmap: bad pmd (%08lx)\n", pmd_val(*pmd_dir));
@@ -159,6 +165,8 @@ void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cachefla
 	unsigned long virtaddr, retaddr;
 	long offset;
 	pgd_t *pgd_dir;
+	p4d_t *p4d_dir;
+	pud_t *pud_dir;
 	pmd_t *pmd_dir;
 	pte_t *pte_dir;
 
@@ -245,18 +253,23 @@ void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cachefla
 			printk ("\npa=%#lx va=%#lx ", physaddr, virtaddr);
 #endif
 		pgd_dir = pgd_offset_k(virtaddr);
-		pmd_dir = pmd_alloc(&init_mm, pgd_dir, virtaddr);
+		p4d_dir = p4d_offset(pgd_dir, virtaddr);
+		pud_dir = pud_offset(p4d_dir, virtaddr);
+		pmd_dir = pmd_alloc(&init_mm, pud_dir, virtaddr);
 		if (!pmd_dir) {
 			printk("ioremap: no mem for pmd_dir\n");
 			return NULL;
 		}
 
+#if CONFIG_PGTABLE_LEVELS == 3
 		if (CPU_IS_020_OR_030) {
 			pmd_dir->pmd[(virtaddr/PTRTREESIZE) & 15] = physaddr;
 			physaddr += PTRTREESIZE;
 			virtaddr += PTRTREESIZE;
 			size -= PTRTREESIZE;
-		} else {
+		} else
+#endif
+		{
 			pte_dir = pte_alloc_kernel(pmd_dir, virtaddr);
 			if (!pte_dir) {
 				printk("ioremap: no mem for pte_dir\n");
@@ -307,6 +320,8 @@ void kernel_set_cachemode(void *addr, unsigned long size, int cmode)
 {
 	unsigned long virtaddr = (unsigned long)addr;
 	pgd_t *pgd_dir;
+	p4d_t *p4d_dir;
+	pud_t *pud_dir;
 	pmd_t *pmd_dir;
 	pte_t *pte_dir;
 
@@ -341,13 +356,16 @@ void kernel_set_cachemode(void *addr, unsigned long size, int cmode)
 
 	while ((long)size > 0) {
 		pgd_dir = pgd_offset_k(virtaddr);
-		if (pgd_bad(*pgd_dir)) {
-			printk("iocachemode: bad pgd(%08lx)\n", pgd_val(*pgd_dir));
-			pgd_clear(pgd_dir);
+		p4d_dir = p4d_offset(pgd_dir, virtaddr);
+		pud_dir = pud_offset(p4d_dir, virtaddr);
+		if (pud_bad(*pud_dir)) {
+			printk("iocachemode: bad pud(%08lx)\n", pud_val(*pud_dir));
+			pud_clear(pud_dir);
 			return;
 		}
-		pmd_dir = pmd_offset(pgd_dir, virtaddr);
+		pmd_dir = pmd_offset(pud_dir, virtaddr);
 
+#if CONFIG_PGTABLE_LEVELS == 3
 		if (CPU_IS_020_OR_030) {
 			int pmd_off = (virtaddr/PTRTREESIZE) & 15;
 
@@ -359,6 +377,7 @@ void kernel_set_cachemode(void *addr, unsigned long size, int cmode)
 				continue;
 			}
 		}
+#endif
 
 		if (pmd_bad(*pmd_dir)) {
 			printk("iocachemode: bad pmd (%08lx)\n", pmd_val(*pmd_dir));

arch/m68k/mm/mcfmmu.c

@@ -92,6 +92,8 @@ int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word)
 	unsigned long flags, mmuar, mmutr;
 	struct mm_struct *mm;
 	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 	int asid;
@@ -113,7 +115,19 @@ int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word)
 		return -1;
 	}
 
-	pmd = pmd_offset(pgd, mmuar);
+	p4d = p4d_offset(pgd, mmuar);
+	if (p4d_none(*p4d)) {
+		local_irq_restore(flags);
+		return -1;
+	}
+
+	pud = pud_offset(p4d, mmuar);
+	if (pud_none(*pud)) {
+		local_irq_restore(flags);
+		return -1;
+	}
+
+	pmd = pmd_offset(pud, mmuar);
 	if (pmd_none(*pmd)) {
 		local_irq_restore(flags);
 		return -1;

arch/m68k/mm/motorola.c

@@ -82,9 +82,11 @@ static pmd_t * __init kernel_ptr_table(void)
 		 */
 		last = (unsigned long)kernel_pg_dir;
 		for (i = 0; i < PTRS_PER_PGD; i++) {
-			if (!pgd_present(kernel_pg_dir[i]))
+			pud_t *pud = (pud_t *)(&kernel_pg_dir[i]);
+
+			if (!pud_present(*pud))
 				continue;
-			pmd = __pgd_page(kernel_pg_dir[i]);
+			pmd = pgd_page_vaddr(kernel_pg_dir[i]);
 			if (pmd > last)
 				last = pmd;
 		}
@@ -118,6 +120,8 @@ static void __init map_node(int node)
 #define ROOTTREESIZE (32*1024*1024)
 	unsigned long physaddr, virtaddr, size;
 	pgd_t *pgd_dir;
+	p4d_t *p4d_dir;
+	pud_t *pud_dir;
 	pmd_t *pmd_dir;
 	pte_t *pte_dir;
 
@@ -149,14 +153,16 @@ static void __init map_node(int node)
 				continue;
 			}
 		}
-		if (!pgd_present(*pgd_dir)) {
+		p4d_dir = p4d_offset(pgd_dir, virtaddr);
+		pud_dir = pud_offset(p4d_dir, virtaddr);
+		if (!pud_present(*pud_dir)) {
 			pmd_dir = kernel_ptr_table();
 #ifdef DEBUG
 			printk ("[new pointer %p]", pmd_dir);
 #endif
-			pgd_set(pgd_dir, pmd_dir);
+			pud_set(pud_dir, pmd_dir);
 		} else
-			pmd_dir = pmd_offset(pgd_dir, virtaddr);
+			pmd_dir = pmd_offset(pud_dir, virtaddr);
 
 		if (CPU_IS_020_OR_030) {
 			if (virtaddr) {
@@ -304,4 +310,3 @@ void __init paging_init(void)
 			node_set_state(i, N_NORMAL_MEMORY);
 	}
 }
-

arch/m68k/sun3x/dvma.c

@@ -80,6 +80,8 @@ inline int dvma_map_cpu(unsigned long kaddr,
 			       unsigned long vaddr, int len)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
 	unsigned long end;
 	int ret = 0;
 
@@ -90,12 +92,14 @@ inline int dvma_map_cpu(unsigned long kaddr,
 
 	pr_debug("dvma: mapping kern %08lx to virt %08lx\n", kaddr, vaddr);
 	pgd = pgd_offset_k(vaddr);
+	p4d = p4d_offset(pgd, vaddr);
+	pud = pud_offset(p4d, vaddr);
 
 	do {
 		pmd_t *pmd;
 		unsigned long end2;
 
-		if((pmd = pmd_alloc(&init_mm, pgd, vaddr)) == NULL) {
+		if((pmd = pmd_alloc(&init_mm, pud, vaddr)) == NULL) {
 			ret = -ENOMEM;
 			goto out;
 		}
@@ -196,4 +200,3 @@ void dvma_unmap_iommu(unsigned long baddr, int len)
 	}
 
 }
-

arch/microblaze/include/asm/page.h

@@ -90,7 +90,6 @@ typedef struct { unsigned long	pte; }		pte_t;
 typedef struct { unsigned long	pgprot; }	pgprot_t;
 /* FIXME this can depend on linux kernel version */
 #   ifdef CONFIG_MMU
-typedef struct { unsigned long pmd; } pmd_t;
 typedef struct { unsigned long pgd; } pgd_t;
 #   else /* CONFIG_MMU */
 typedef struct { unsigned long	ste[64]; }	pmd_t;
@@ -103,7 +102,6 @@ typedef struct { p4d_t		pge[1]; }	pgd_t;
 # define pgprot_val(x)	((x).pgprot)
 
 #   ifdef CONFIG_MMU
-#   define pmd_val(x)      ((x).pmd)
 #   define pgd_val(x)      ((x).pgd)
 #   else  /* CONFIG_MMU */
 #   define pmd_val(x)	((x).ste[0])
@@ -112,7 +110,6 @@ typedef struct { p4d_t		pge[1]; }	pgd_t;
 #   endif  /* CONFIG_MMU */
 
 # define __pte(x)	((pte_t) { (x) })
-# define __pmd(x)	((pmd_t) { (x) })
 # define __pgd(x)	((pgd_t) { (x) })
 # define __pgprot(x)	((pgprot_t) { (x) })
 

arch/microblaze/include/asm/pgalloc.h

@@ -41,13 +41,6 @@ static inline void free_pgd(pgd_t *pgd)
 
 #define pmd_pgtable(pmd)	pmd_page(pmd)
 
-/*
- * We don't have any real pmd's, and this code never triggers because
- * the pgd will always be present..
- */
-#define pmd_alloc_one_fast(mm, address)	({ BUG(); ((pmd_t *)1); })
-#define pmd_alloc_one(mm, address)	({ BUG(); ((pmd_t *)2); })
-
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm);
 
 #define __pte_free_tlb(tlb, pte, addr)	pte_free((tlb)->mm, (pte))
@@ -58,15 +51,6 @@ extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm);
 #define pmd_populate_kernel(mm, pmd, pte) \
 		(pmd_val(*(pmd)) = (unsigned long) (pte))
 
-/*
- * We don't have any real pmd's, and this code never triggers because
- * the pgd will always be present..
- */
-#define pmd_alloc_one(mm, address)	({ BUG(); ((pmd_t *)2); })
-#define pmd_free(mm, x)			do { } while (0)
-#define __pmd_free_tlb(tlb, x, addr)	pmd_free((tlb)->mm, x)
-#define pgd_populate(mm, pmd, pte)	BUG()
-
 #endif /* CONFIG_MMU */
 
 #endif /* _ASM_MICROBLAZE_PGALLOC_H */

arch/microblaze/include/asm/pgtable.h

@@ -59,9 +59,7 @@ extern int mem_init_done;
 
 #else /* CONFIG_MMU */
 
-#include <asm-generic/4level-fixup.h>
-
-#define __PAGETABLE_PMD_FOLDED 1
+#include <asm-generic/pgtable-nopmd.h>
 
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
@@ -138,13 +136,8 @@ static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
  *
  */
 
-/* PMD_SHIFT determines the size of the area mapped by the PTE pages */
-#define PMD_SHIFT	(PAGE_SHIFT + PTE_SHIFT)
-#define PMD_SIZE	(1UL << PMD_SHIFT)
-#define PMD_MASK	(~(PMD_SIZE-1))
-
 /* PGDIR_SHIFT determines what a top-level page table entry can map */
-#define PGDIR_SHIFT	PMD_SHIFT
+#define PGDIR_SHIFT	(PAGE_SHIFT + PTE_SHIFT)
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
@@ -165,9 +158,6 @@ static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 #define pte_ERROR(e) \
 	printk(KERN_ERR "%s:%d: bad pte "PTE_FMT".\n", \
 		__FILE__, __LINE__, pte_val(e))
-#define pmd_ERROR(e) \
-	printk(KERN_ERR "%s:%d: bad pmd %08lx.\n", \
-		__FILE__, __LINE__, pmd_val(e))
 #define pgd_ERROR(e) \
 	printk(KERN_ERR "%s:%d: bad pgd %08lx.\n", \
 		__FILE__, __LINE__, pgd_val(e))
@@ -313,18 +303,6 @@ extern unsigned long empty_zero_page[1024];
 	__pte(((pte_basic_t)(pfn) << PFN_SHIFT_OFFSET) | pgprot_val(prot))
 
 #ifndef __ASSEMBLY__
-/*
- * The "pgd_xxx()" functions here are trivial for a folded two-level
- * setup: the pgd is never bad, and a pmd always exists (as it's folded
- * into the pgd entry)
- */
-static inline int pgd_none(pgd_t pgd)		{ return 0; }
-static inline int pgd_bad(pgd_t pgd)		{ return 0; }
-static inline int pgd_present(pgd_t pgd)	{ return 1; }
-#define pgd_clear(xp)				do { } while (0)
-#define pgd_page(pgd) \
-	((unsigned long) __va(pgd_val(pgd) & PAGE_MASK))
-
 /*
  * The following only work if pte_present() is true.
  * Undefined behaviour if not..
@@ -479,12 +457,6 @@ static inline void ptep_mkdirty(struct mm_struct *mm,
 #define pgd_index(address)	 ((address) >> PGDIR_SHIFT)
 #define pgd_offset(mm, address)	 ((mm)->pgd + pgd_index(address))
 
-/* Find an entry in the second-level page table.. */
-static inline pmd_t *pmd_offset(pgd_t *dir, unsigned long address)
-{
-	return (pmd_t *) dir;
-}
-
 /* Find an entry in the third-level page table.. */
 #define pte_index(address)		\
 	(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))

arch/microblaze/kernel/signal.c

@@ -160,6 +160,9 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	int err = 0, sig = ksig->sig;
 	unsigned long address = 0;
 #ifdef CONFIG_MMU
+	pgd_t *pgdp;
+	p4d_t *p4dp;
+	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
 #endif
@@ -195,9 +198,10 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 
 	address = ((unsigned long)frame->tramp);
 #ifdef CONFIG_MMU
-	pmdp = pmd_offset(pud_offset(
-			pgd_offset(current->mm, address),
-					address), address);
+	pgdp = pgd_offset(current->mm, address);
+	p4dp = p4d_offset(pgdp, address);
+	pudp = pud_offset(p4dp, address);
+	pmdp = pmd_offset(pudp, address);
 
 	preempt_disable();
 	ptep = pte_offset_map(pmdp, address);

arch/microblaze/mm/init.c

@@ -53,8 +53,11 @@ EXPORT_SYMBOL(kmap_prot);
 
 static inline pte_t *virt_to_kpte(unsigned long vaddr)
 {
-	return pte_offset_kernel(pmd_offset(pgd_offset_k(vaddr),
-			vaddr), vaddr);
+	pgd_t *pgd = pgd_offset_k(vaddr);
+	p4d_t *p4d = p4d_offset(pgd, vaddr);
+	pud_t *pud = pud_offset(p4d, vaddr);
+
+	return pte_offset_kernel(pmd_offset(pud, vaddr), vaddr);
 }
 
 static void __init highmem_init(void)

arch/microblaze/mm/pgtable.c

@@ -134,11 +134,16 @@ EXPORT_SYMBOL(iounmap);
 
 int map_page(unsigned long va, phys_addr_t pa, int flags)
 {
+	p4d_t *p4d;
+	pud_t *pud;
 	pmd_t *pd;
 	pte_t *pg;
 	int err = -ENOMEM;
+
 	/* Use upper 10 bits of VA to index the first level map */
-	pd = pmd_offset(pgd_offset_k(va), va);
+	p4d = p4d_offset(pgd_offset_k(va), va);
+	pud = pud_offset(p4d, va);
+	pd = pmd_offset(pud, va);
 	/* Use middle 10 bits of VA to index the second-level map */
 	pg = pte_alloc_kernel(pd, va); /* from powerpc - pgtable.c */
 	/* pg = pte_alloc_kernel(&init_mm, pd, va); */
@@ -188,13 +193,17 @@ void __init mapin_ram(void)
 static int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep)
 {
 	pgd_t	*pgd;
+	p4d_t	*p4d;
+	pud_t	*pud;
 	pmd_t	*pmd;
 	pte_t	*pte;
 	int     retval = 0;
 
 	pgd = pgd_offset(mm, addr & PAGE_MASK);
 	if (pgd) {
-		pmd = pmd_offset(pgd, addr & PAGE_MASK);
+		p4d = p4d_offset(pgd, addr & PAGE_MASK);
+		pud = pud_offset(p4d, addr & PAGE_MASK);
+		pmd = pmd_offset(pud, addr & PAGE_MASK);
 		if (pmd_present(*pmd)) {
 			pte = pte_offset_kernel(pmd, addr & PAGE_MASK);
 			if (pte) {

arch/mips/include/uapi/asm/msgbuf.h

@@ -2,6 +2,7 @@
 #ifndef _ASM_MSGBUF_H
 #define _ASM_MSGBUF_H
 
+#include <asm/ipcbuf.h>
 
 /*
  * The msqid64_ds structure for the MIPS architecture.

arch/mips/include/uapi/asm/sembuf.h

@@ -2,6 +2,8 @@
 #ifndef _ASM_SEMBUF_H
 #define _ASM_SEMBUF_H
 
+#include <asm/ipcbuf.h>
+
 /*
  * The semid64_ds structure for the MIPS architecture.
  * Note extra padding because this structure is passed back and forth

arch/nds32/include/asm/page.h

@@ -41,17 +41,14 @@ void clear_page(void *page);
 void copy_page(void *to, void *from);
 
 typedef unsigned long pte_t;
-typedef unsigned long pmd_t;
 typedef unsigned long pgd_t;
 typedef unsigned long pgprot_t;
 
 #define pte_val(x)      (x)
-#define pmd_val(x)      (x)
 #define pgd_val(x)	(x)
 #define pgprot_val(x)   (x)
 
 #define __pte(x)        (x)
-#define __pmd(x)        (x)
 #define __pgd(x)        (x)
 #define __pgprot(x)     (x)
 

arch/nds32/include/asm/pgalloc.h

@@ -15,9 +15,6 @@
 /*
  * Since we have only two-level page tables, these are trivial
  */
-#define pmd_alloc_one(mm, addr)		({ BUG(); ((pmd_t *)2); })
-#define pmd_free(mm, pmd)			do { } while (0)
-#define pgd_populate(mm, pmd, pte)	BUG()
 #define pmd_pgtable(pmd) pmd_page(pmd)
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);

arch/nds32/include/asm/pgtable.h

@@ -4,8 +4,7 @@
 #ifndef _ASMNDS32_PGTABLE_H
 #define _ASMNDS32_PGTABLE_H
 
-#define __PAGETABLE_PMD_FOLDED 1
-#include <asm-generic/4level-fixup.h>
+#include <asm-generic/pgtable-nopmd.h>
 #include <linux/sizes.h>
 
 #include <asm/memory.h>
@@ -18,26 +17,20 @@
 #ifdef CONFIG_ANDES_PAGE_SIZE_4KB
 #define PGDIR_SHIFT      22
 #define PTRS_PER_PGD     1024
-#define PMD_SHIFT        22
-#define PTRS_PER_PMD     1
 #define PTRS_PER_PTE     1024
 #endif
 
 #ifdef CONFIG_ANDES_PAGE_SIZE_8KB
 #define PGDIR_SHIFT      24
 #define PTRS_PER_PGD     256
-#define PMD_SHIFT        24
-#define PTRS_PER_PMD     1
 #define PTRS_PER_PTE     2048
 #endif
 
 #ifndef __ASSEMBLY__
 extern void __pte_error(const char *file, int line, unsigned long val);
-extern void __pmd_error(const char *file, int line, unsigned long val);
 extern void __pgd_error(const char *file, int line, unsigned long val);
 
 #define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte_val(pte))
-#define pmd_ERROR(pmd)		__pmd_error(__FILE__, __LINE__, pmd_val(pmd))
 #define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd_val(pgd))
 #endif /* !__ASSEMBLY__ */
 
@@ -368,9 +361,6 @@ static inline pmd_t __mk_pmd(pte_t * ptep, unsigned long prot)
 /* to find an entry in a kernel page-table-directory */
 #define pgd_offset_k(addr)      pgd_offset(&init_mm, addr)
 
-/* Find an entry in the second-level page table.. */
-#define pmd_offset(dir, addr)	((pmd_t *)(dir))
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	const unsigned long mask = 0xfff;

arch/nds32/include/asm/tlb.h

@@ -7,6 +7,5 @@
 #include <asm-generic/tlb.h>
 
 #define __pte_free_tlb(tlb, pte, addr)	pte_free((tlb)->mm, pte)
-#define __pmd_free_tlb(tlb, pmd, addr)	pmd_free((tln)->mm, pmd)
 
 #endif

arch/nds32/kernel/pm.c

@@ -14,6 +14,7 @@ unsigned int *phy_addr_sp_tmp;
 static void nds32_suspend2ram(void)
 {
 	pgd_t *pgdv;
+	p4d_t *p4dv;
 	pud_t *pudv;
 	pmd_t *pmdv;
 	pte_t *ptev;
@@ -21,7 +22,8 @@ static void nds32_suspend2ram(void)
 	pgdv = (pgd_t *)__va((__nds32__mfsr(NDS32_SR_L1_PPTB) &
 		L1_PPTB_mskBASE)) + pgd_index((unsigned int)cpu_resume);
 
-	pudv = pud_offset(pgdv, (unsigned int)cpu_resume);
+	p4dv = p4d_offset(pgdv, (unsigned int)cpu_resume);
+	pudv = pud_offset(p4dv, (unsigned int)cpu_resume);
 	pmdv = pmd_offset(pudv, (unsigned int)cpu_resume);
 	ptev = pte_offset_map(pmdv, (unsigned int)cpu_resume);
 

arch/nds32/mm/fault.c

@@ -31,6 +31,8 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 	pr_alert("[%08lx] *pgd=%08lx", addr, pgd_val(*pgd));
 
 	do {
+		p4d_t *p4d;
+		pud_t *pud;
 		pmd_t *pmd;
 
 		if (pgd_none(*pgd))
@@ -41,7 +43,9 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 			break;
 		}
 
-		pmd = pmd_offset(pgd, addr);
+		p4d = p4d_offset(pgd, addr);
+		pud = pud_offset(p4d, addr);
+		pmd = pmd_offset(pud, addr);
 #if PTRS_PER_PMD != 1
 		pr_alert(", *pmd=%08lx", pmd_val(*pmd));
 #endif
@@ -359,6 +363,7 @@ void do_page_fault(unsigned long entry, unsigned long addr,
 
 		unsigned int index = pgd_index(addr);
 		pgd_t *pgd, *pgd_k;
+		p4d_t *p4d, *p4d_k;
 		pud_t *pud, *pud_k;
 		pmd_t *pmd, *pmd_k;
 		pte_t *pte_k;
@@ -369,8 +374,13 @@ void do_page_fault(unsigned long entry, unsigned long addr,
 		if (!pgd_present(*pgd_k))
 			goto no_context;
 
-		pud = pud_offset(pgd, addr);
-		pud_k = pud_offset(pgd_k, addr);
+		p4d = p4d_offset(pgd, addr);
+		p4d_k = p4d_offset(pgd_k, addr);
+		if (!p4d_present(*p4d_k))
+			goto no_context;
+
+		pud = pud_offset(p4d, addr);
+		pud_k = pud_offset(p4d_k, addr);
 		if (!pud_present(*pud_k))
 			goto no_context;
 

arch/nds32/mm/init.c

@@ -54,6 +54,7 @@ static void __init map_ram(void)
 {
 	unsigned long v, p, e;
 	pgd_t *pge;
+	p4d_t *p4e;
 	pud_t *pue;
 	pmd_t *pme;
 	pte_t *pte;
@@ -69,7 +70,8 @@ static void __init map_ram(void)
 
 	while (p < e) {
 		int j;
-		pue = pud_offset(pge, v);
+		p4e = p4d_offset(pge, v);
+		pue = pud_offset(p4e, v);
 		pme = pmd_offset(pue, v);
 
 		if ((u32) pue != (u32) pge || (u32) pme != (u32) pge) {
@@ -100,6 +102,7 @@ static void __init fixedrange_init(void)
 {
 	unsigned long vaddr;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 #ifdef CONFIG_HIGHMEM
@@ -111,7 +114,8 @@ static void __init fixedrange_init(void)
 	 */
 	vaddr = __fix_to_virt(__end_of_fixed_addresses - 1);
 	pgd = swapper_pg_dir + pgd_index(vaddr);
-	pud = pud_offset(pgd, vaddr);
+	p4d = p4d_offset(pgd, vaddr);
+	pud = pud_offset(p4d, vaddr);
 	pmd = pmd_offset(pud, vaddr);
 	fixmap_pmd_p = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 	if (!fixmap_pmd_p)
@@ -126,7 +130,8 @@ static void __init fixedrange_init(void)
 	vaddr = PKMAP_BASE;
 
 	pgd = swapper_pg_dir + pgd_index(vaddr);
-	pud = pud_offset(pgd, vaddr);
+	p4d = p4d_offset(pgd, vaddr);
+	pud = pud_offset(p4d, vaddr);
 	pmd = pmd_offset(pud, vaddr);
 	pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 	if (!pte)

arch/nds32/mm/mm-nds32.c

@@ -74,6 +74,8 @@ void setup_mm_for_reboot(char mode)
 {
 	unsigned long pmdval;
 	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
 	pmd_t *pmd;
 	int i;
 
@@ -84,7 +86,9 @@ void setup_mm_for_reboot(char mode)
 
 	for (i = 0; i < USER_PTRS_PER_PGD; i++) {
 		pmdval = (i << PGDIR_SHIFT);
-		pmd = pmd_offset(pgd + i, i << PGDIR_SHIFT);
+		p4d = p4d_offset(pgd, i << PGDIR_SHIFT);
+		pud = pud_offset(p4d, i << PGDIR_SHIFT);
+		pmd = pmd_offset(pud + i, i << PGDIR_SHIFT);
 		set_pmd(pmd, __pmd(pmdval));
 	}
 }

arch/nds32/mm/proc.c

@@ -16,10 +16,14 @@ extern struct cache_info L1_cache_info[2];
 
 int va_kernel_present(unsigned long addr)
 {
+	p4d_t *p4d;
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *ptep, pte;
 
-	pmd = pmd_offset(pgd_offset_k(addr), addr);
+	p4d = p4d_offset(pgd_offset_k(addr), addr);
+	pud = pud_offset(p4d, addr);
+	pmd = pmd_offset(pud, addr);
 	if (!pmd_none(*pmd)) {
 		ptep = pte_offset_map(pmd, addr);
 		pte = *ptep;
@@ -32,13 +36,16 @@ int va_kernel_present(unsigned long addr)
 pte_t va_present(struct mm_struct * mm, unsigned long addr)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *ptep, pte;
 
 	pgd = pgd_offset(mm, addr);
 	if (!pgd_none(*pgd)) {
-		pud = pud_offset(pgd, addr);
+		p4d = p4d_offset(pgd, addr);
+		if (!p4d_none(*p4d)) {
+			pud = pud_offset(p4d, addr);
 			if (!pud_none(*pud)) {
 				pmd = pmd_offset(pud, addr);
 				if (!pmd_none(*pmd)) {
@@ -49,6 +56,7 @@ pte_t va_present(struct mm_struct * mm, unsigned long addr)
 				}
 			}
 		}
+	}
 	return 0;
 
 }

arch/parisc/include/asm/page.h

@@ -42,48 +42,54 @@ typedef struct { unsigned long pte; } pte_t; /* either 32 or 64bit */
 
 /* NOTE: even on 64 bits, these entries are __u32 because we allocate
  * the pmd and pgd in ZONE_DMA (i.e. under 4GB) */
-typedef struct { __u32 pmd; } pmd_t;
 typedef struct { __u32 pgd; } pgd_t;
 typedef struct { unsigned long pgprot; } pgprot_t;
 
-#define pte_val(x)	((x).pte)
-/* These do not work lvalues, so make sure we don't use them as such. */
+#if CONFIG_PGTABLE_LEVELS == 3
+typedef struct { __u32 pmd; } pmd_t;
+#define __pmd(x)	((pmd_t) { (x) } )
+/* pXd_val() do not work as lvalues, so make sure we don't use them as such. */
 #define pmd_val(x)	((x).pmd + 0)
+#endif
+
+#define pte_val(x)	((x).pte)
 #define pgd_val(x)	((x).pgd + 0)
 #define pgprot_val(x)	((x).pgprot)
 
 #define __pte(x)	((pte_t) { (x) } )
-#define __pmd(x)	((pmd_t) { (x) } )
 #define __pgd(x)	((pgd_t) { (x) } )
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
-#define __pmd_val_set(x,n) (x).pmd = (n)
-#define __pgd_val_set(x,n) (x).pgd = (n)
-
 #else
 /*
  * .. while these make it easier on the compiler
  */
 typedef unsigned long pte_t;
+
+#if CONFIG_PGTABLE_LEVELS == 3
 typedef         __u32 pmd_t;
+#define pmd_val(x)      (x)
+#define __pmd(x)	(x)
+#endif
+
 typedef         __u32 pgd_t;
 typedef unsigned long pgprot_t;
 
 #define pte_val(x)      (x)
-#define pmd_val(x)      (x)
 #define pgd_val(x)      (x)
 #define pgprot_val(x)   (x)
 
 #define __pte(x)        (x)
-#define __pmd(x)	(x)
 #define __pgd(x)        (x)
 #define __pgprot(x)     (x)
 
-#define __pmd_val_set(x,n) (x) = (n)
-#define __pgd_val_set(x,n) (x) = (n)
-
 #endif /* STRICT_MM_TYPECHECKS */
 
+#define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval))
+#if CONFIG_PGTABLE_LEVELS == 3
+#define set_pud(pudptr, pudval) (*(pudptr) = (pudval))
+#endif
+
 typedef struct page *pgtable_t;
 
 typedef struct __physmem_range {

arch/parisc/include/asm/pgalloc.h

@@ -34,13 +34,13 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 		/* Populate first pmd with allocated memory.  We mark it
 		 * with PxD_FLAG_ATTACHED as a signal to the system that this
 		 * pmd entry may not be cleared. */
-		__pgd_val_set(*actual_pgd, (PxD_FLAG_PRESENT | 
+		set_pgd(actual_pgd, __pgd((PxD_FLAG_PRESENT |
 				        PxD_FLAG_VALID |
 					PxD_FLAG_ATTACHED)
-			+ (__u32)(__pa((unsigned long)pgd) >> PxD_VALUE_SHIFT));
+			+ (__u32)(__pa((unsigned long)pgd) >> PxD_VALUE_SHIFT)));
 		/* The first pmd entry also is marked with PxD_FLAG_ATTACHED as
 		 * a signal that this pmd may not be freed */
-		__pgd_val_set(*pgd, PxD_FLAG_ATTACHED);
+		set_pgd(pgd, __pgd(PxD_FLAG_ATTACHED));
 #endif
 	}
 	spin_lock_init(pgd_spinlock(actual_pgd));
@@ -59,10 +59,10 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 
 /* Three Level Page Table Support for pmd's */
 
-static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd)
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 {
-	__pgd_val_set(*pgd, (PxD_FLAG_PRESENT | PxD_FLAG_VALID) +
-		        (__u32)(__pa((unsigned long)pmd) >> PxD_VALUE_SHIFT));
+	set_pud(pud, __pud((PxD_FLAG_PRESENT | PxD_FLAG_VALID) +
+			(__u32)(__pa((unsigned long)pmd) >> PxD_VALUE_SHIFT)));
 }
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
@@ -88,19 +88,6 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 	free_pages((unsigned long)pmd, PMD_ORDER);
 }
 
-#else
-
-/* Two Level Page Table Support for pmd's */
-
-/*
- * allocating and freeing a pmd is trivial: the 1-entry pmd is
- * inside the pgd, so has no extra memory associated with it.
- */
-
-#define pmd_alloc_one(mm, addr)		({ BUG(); ((pmd_t *)2); })
-#define pmd_free(mm, x)			do { } while (0)
-#define pgd_populate(mm, pmd, pte)	BUG()
-
 #endif
 
 static inline void
@@ -110,14 +97,14 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
 	/* preserve the gateway marker if this is the beginning of
 	 * the permanent pmd */
 	if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
-		__pmd_val_set(*pmd, (PxD_FLAG_PRESENT |
+		set_pmd(pmd, __pmd((PxD_FLAG_PRESENT |
 				PxD_FLAG_VALID |
 				PxD_FLAG_ATTACHED)
-			+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT));
+			+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT)));
 	else
 #endif
-		__pmd_val_set(*pmd, (PxD_FLAG_PRESENT | PxD_FLAG_VALID) 
-			+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT));
+		set_pmd(pmd, __pmd((PxD_FLAG_PRESENT | PxD_FLAG_VALID)
+			+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT)));
 }
 
 #define pmd_populate(mm, pmd, pte_page) \

arch/parisc/include/asm/pgtable.h

@@ -3,7 +3,12 @@
 #define _PARISC_PGTABLE_H
 
 #include <asm/page.h>
-#include <asm-generic/4level-fixup.h>
+
+#if CONFIG_PGTABLE_LEVELS == 3
+#include <asm-generic/pgtable-nopud.h>
+#elif CONFIG_PGTABLE_LEVELS == 2
+#include <asm-generic/pgtable-nopmd.h>
+#endif
 
 #include <asm/fixmap.h>
 
@@ -101,8 +106,10 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 
 #define pte_ERROR(e) \
 	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
+#if CONFIG_PGTABLE_LEVELS == 3
 #define pmd_ERROR(e) \
 	printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, (unsigned long)pmd_val(e))
+#endif
 #define pgd_ERROR(e) \
 	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e))
 
@@ -132,19 +139,18 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 #define PTRS_PER_PTE    (1UL << BITS_PER_PTE)
 
 /* Definitions for 2nd level */
+#if CONFIG_PGTABLE_LEVELS == 3
 #define PMD_SHIFT       (PLD_SHIFT + BITS_PER_PTE)
 #define PMD_SIZE	(1UL << PMD_SHIFT)
 #define PMD_MASK	(~(PMD_SIZE-1))
-#if CONFIG_PGTABLE_LEVELS == 3
 #define BITS_PER_PMD	(PAGE_SHIFT + PMD_ORDER - BITS_PER_PMD_ENTRY)
+#define PTRS_PER_PMD    (1UL << BITS_PER_PMD)
 #else
-#define __PAGETABLE_PMD_FOLDED 1
 #define BITS_PER_PMD	0
 #endif
-#define PTRS_PER_PMD    (1UL << BITS_PER_PMD)
 
 /* Definitions for 1st level */
-#define PGDIR_SHIFT	(PMD_SHIFT + BITS_PER_PMD)
+#define PGDIR_SHIFT	(PLD_SHIFT + BITS_PER_PTE + BITS_PER_PMD)
 #if (PGDIR_SHIFT + PAGE_SHIFT + PGD_ORDER - BITS_PER_PGD_ENTRY) > BITS_PER_LONG
 #define BITS_PER_PGD	(BITS_PER_LONG - PGDIR_SHIFT)
 #else
@@ -317,6 +323,8 @@ extern unsigned long *empty_zero_page;
 
 #define pmd_flag(x)	(pmd_val(x) & PxD_FLAG_MASK)
 #define pmd_address(x)	((unsigned long)(pmd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
+#define pud_flag(x)	(pud_val(x) & PxD_FLAG_MASK)
+#define pud_address(x)	((unsigned long)(pud_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
 #define pgd_flag(x)	(pgd_val(x) & PxD_FLAG_MASK)
 #define pgd_address(x)	((unsigned long)(pgd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
 
@@ -334,42 +342,32 @@ static inline void pmd_clear(pmd_t *pmd) {
 	if (pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
 		/* This is the entry pointing to the permanent pmd
 		 * attached to the pgd; cannot clear it */
-		__pmd_val_set(*pmd, PxD_FLAG_ATTACHED);
+		set_pmd(pmd, __pmd(PxD_FLAG_ATTACHED));
 	else
 #endif
-		__pmd_val_set(*pmd,  0);
+		set_pmd(pmd,  __pmd(0));
 }
 
 
 
 #if CONFIG_PGTABLE_LEVELS == 3
-#define pgd_page_vaddr(pgd) ((unsigned long) __va(pgd_address(pgd)))
-#define pgd_page(pgd)	virt_to_page((void *)pgd_page_vaddr(pgd))
+#define pud_page_vaddr(pud) ((unsigned long) __va(pud_address(pud)))
+#define pud_page(pud)	virt_to_page((void *)pud_page_vaddr(pud))
 
 /* For 64 bit we have three level tables */
 
-#define pgd_none(x)     (!pgd_val(x))
-#define pgd_bad(x)      (!(pgd_flag(x) & PxD_FLAG_VALID))
-#define pgd_present(x)  (pgd_flag(x) & PxD_FLAG_PRESENT)
-static inline void pgd_clear(pgd_t *pgd) {
+#define pud_none(x)     (!pud_val(x))
+#define pud_bad(x)      (!(pud_flag(x) & PxD_FLAG_VALID))
+#define pud_present(x)  (pud_flag(x) & PxD_FLAG_PRESENT)
+static inline void pud_clear(pud_t *pud) {
 #if CONFIG_PGTABLE_LEVELS == 3
-	if(pgd_flag(*pgd) & PxD_FLAG_ATTACHED)
-		/* This is the permanent pmd attached to the pgd; cannot
+	if(pud_flag(*pud) & PxD_FLAG_ATTACHED)
+		/* This is the permanent pmd attached to the pud; cannot
 		 * free it */
 		return;
 #endif
-	__pgd_val_set(*pgd, 0);
+	set_pud(pud, __pud(0));
 }
-#else
-/*
- * The "pgd_xxx()" functions here are trivial for a folded two-level
- * setup: the pgd is never bad, and a pmd always exists (as it's folded
- * into the pgd entry)
- */
-static inline int pgd_none(pgd_t pgd)		{ return 0; }
-static inline int pgd_bad(pgd_t pgd)		{ return 0; }
-static inline int pgd_present(pgd_t pgd)	{ return 1; }
-static inline void pgd_clear(pgd_t * pgdp)	{ }
 #endif
 
 /*
@@ -452,7 +450,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 #if CONFIG_PGTABLE_LEVELS == 3
 #define pmd_index(addr)         (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
 #define pmd_offset(dir,address) \
-((pmd_t *) pgd_page_vaddr(*(dir)) + pmd_index(address))
+((pmd_t *) pud_page_vaddr(*(dir)) + pmd_index(address))
 #else
 #define pmd_offset(dir,addr) ((pmd_t *) dir)
 #endif

arch/parisc/include/asm/tlb.h

@@ -4,7 +4,9 @@
 
 #include <asm-generic/tlb.h>
 
+#if CONFIG_PGTABLE_LEVELS == 3
 #define __pmd_free_tlb(tlb, pmd, addr)	pmd_free((tlb)->mm, pmd)
+#endif
 #define __pte_free_tlb(tlb, pte, addr)	pte_free((tlb)->mm, pte)
 
 #endif

arch/parisc/include/uapi/asm/msgbuf.h

@@ -3,6 +3,7 @@
 #define _PARISC_MSGBUF_H
 
 #include <asm/bitsperlong.h>
+#include <asm/ipcbuf.h>
 
 /* 
  * The msqid64_ds structure for parisc architecture, copied from sparc.

arch/parisc/include/uapi/asm/sembuf.h

@@ -3,6 +3,7 @@
 #define _PARISC_SEMBUF_H
 
 #include <asm/bitsperlong.h>
+#include <asm/ipcbuf.h>
 
 /* 
  * The semid64_ds structure for parisc architecture.

arch/parisc/kernel/cache.c

@@ -534,13 +534,16 @@ static inline pte_t *get_ptep(pgd_t *pgd, unsigned long addr)
 	pte_t *ptep = NULL;
 
 	if (!pgd_none(*pgd)) {
-		pud_t *pud = pud_offset(pgd, addr);
+		p4d_t *p4d = p4d_offset(pgd, addr);
+		if (!p4d_none(*p4d)) {
+			pud_t *pud = pud_offset(p4d, addr);
 			if (!pud_none(*pud)) {
 				pmd_t *pmd = pmd_offset(pud, addr);
 				if (!pmd_none(*pmd))
 					ptep = pte_offset_map(pmd, addr);
 			}
 		}
+	}
 	return ptep;
 }
 

arch/parisc/kernel/pci-dma.c

@@ -133,9 +133,14 @@ static inline int map_uncached_pages(unsigned long vaddr, unsigned long size,
 
 	dir = pgd_offset_k(vaddr);
 	do {
+		p4d_t *p4d;
+		pud_t *pud;
 		pmd_t *pmd;
 
-		pmd = pmd_alloc(NULL, dir, vaddr);
+		p4d = p4d_offset(dir, vaddr);
+		pud = pud_offset(p4d, vaddr);
+		pmd = pmd_alloc(NULL, pud, vaddr);
+
 		if (!pmd)
 			return -ENOMEM;
 		if (map_pmd_uncached(pmd, vaddr, end - vaddr, &paddr))

arch/parisc/mm/fixmap.c

@@ -14,11 +14,13 @@ void notrace set_fixmap(enum fixed_addresses idx, phys_addr_t phys)
 {
 	unsigned long vaddr = __fix_to_virt(idx);
 	pgd_t *pgd = pgd_offset_k(vaddr);
-	pmd_t *pmd = pmd_offset(pgd, vaddr);
+	p4d_t *p4d = p4d_offset(pgd, vaddr);
+	pud_t *pud = pud_offset(p4d, vaddr);
+	pmd_t *pmd = pmd_offset(pud, vaddr);
 	pte_t *pte;
 
 	if (pmd_none(*pmd))
-		pmd = pmd_alloc(NULL, pgd, vaddr);
+		pmd = pmd_alloc(NULL, pud, vaddr);
 
 	pte = pte_offset_kernel(pmd, vaddr);
 	if (pte_none(*pte))
@@ -32,7 +34,9 @@ void notrace clear_fixmap(enum fixed_addresses idx)
 {
 	unsigned long vaddr = __fix_to_virt(idx);
 	pgd_t *pgd = pgd_offset_k(vaddr);
-	pmd_t *pmd = pmd_offset(pgd, vaddr);
+	p4d_t *p4d = p4d_offset(pgd, vaddr);
+	pud_t *pud = pud_offset(p4d, vaddr);
+	pmd_t *pmd = pmd_offset(pud, vaddr);
 	pte_t *pte = pte_offset_kernel(pmd, vaddr);
 
 	if (WARN_ON(pte_none(*pte)))

arch/parisc/mm/hugetlbpage.c

@@ -49,6 +49,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte = NULL;
@@ -61,7 +62,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 	addr &= HPAGE_MASK;
 
 	pgd = pgd_offset(mm, addr);
-	pud = pud_alloc(mm, pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	pud = pud_alloc(mm, p4d, addr);
 	if (pud) {
 		pmd = pmd_alloc(mm, pud, addr);
 		if (pmd)
@@ -74,6 +76,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte = NULL;
@@ -82,13 +85,16 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 
 	pgd = pgd_offset(mm, addr);
 	if (!pgd_none(*pgd)) {
-		pud = pud_offset(pgd, addr);
+		p4d = p4d_offset(pgd, addr);
+		if (!p4d_none(*p4d)) {
+			pud = pud_offset(p4d, addr);
 			if (!pud_none(*pud)) {
 				pmd = pmd_offset(pud, addr);
 				if (!pmd_none(*pmd))
 					pte = pte_offset_map(pmd, addr);
 			}
 		}
+	}
 	return pte;
 }
 

arch/powerpc/include/uapi/asm/msgbuf.h

@@ -2,6 +2,8 @@
 #ifndef _ASM_POWERPC_MSGBUF_H
 #define _ASM_POWERPC_MSGBUF_H
 
+#include <asm/ipcbuf.h>
+
 /*
  * The msqid64_ds structure for the PowerPC architecture.
  * Note extra padding because this structure is passed back and forth

arch/powerpc/include/uapi/asm/sembuf.h

@@ -2,6 +2,8 @@
 #ifndef _ASM_POWERPC_SEMBUF_H
 #define _ASM_POWERPC_SEMBUF_H
 
+#include <asm/ipcbuf.h>
+
 /*
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License

arch/s390/include/uapi/asm/ipcbuf.h

@@ -2,6 +2,8 @@
 #ifndef __S390_IPCBUF_H__
 #define __S390_IPCBUF_H__
 
+#include <linux/posix_types.h>
+
 /*
  * The user_ipc_perm structure for S/390 architecture.
  * Note extra padding because this structure is passed back and forth

arch/sparc/include/asm/pgalloc_32.h

@@ -26,14 +26,14 @@ static inline void free_pgd_fast(pgd_t *pgd)
 #define pgd_free(mm, pgd)	free_pgd_fast(pgd)
 #define pgd_alloc(mm)	get_pgd_fast()
 
-static inline void pgd_set(pgd_t * pgdp, pmd_t * pmdp)
+static inline void pud_set(pud_t * pudp, pmd_t * pmdp)
 {
 	unsigned long pa = __nocache_pa(pmdp);
 
-	set_pte((pte_t *)pgdp, __pte((SRMMU_ET_PTD | (pa >> 4))));
+	set_pte((pte_t *)pudp, __pte((SRMMU_ET_PTD | (pa >> 4))));
 }
 
-#define pgd_populate(MM, PGD, PMD)      pgd_set(PGD, PMD)
+#define pud_populate(MM, PGD, PMD)      pud_set(PGD, PMD)
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm,
 				   unsigned long address)

arch/sparc/include/asm/pgtable_32.h

@@ -12,7 +12,7 @@
 #include <linux/const.h>
 
 #ifndef __ASSEMBLY__
-#include <asm-generic/4level-fixup.h>
+#include <asm-generic/pgtable-nopud.h>
 
 #include <linux/spinlock.h>
 #include <linux/mm_types.h>
@@ -132,12 +132,12 @@ static inline struct page *pmd_page(pmd_t pmd)
 	return pfn_to_page((pmd_val(pmd) & SRMMU_PTD_PMASK) >> (PAGE_SHIFT-4));
 }
 
-static inline unsigned long pgd_page_vaddr(pgd_t pgd)
+static inline unsigned long pud_page_vaddr(pud_t pud)
 {
-	if (srmmu_device_memory(pgd_val(pgd))) {
+	if (srmmu_device_memory(pud_val(pud))) {
 		return ~0;
 	} else {
-		unsigned long v = pgd_val(pgd) & SRMMU_PTD_PMASK;
+		unsigned long v = pud_val(pud) & SRMMU_PTD_PMASK;
 		return (unsigned long)__nocache_va(v << 4);
 	}
 }
@@ -184,24 +184,24 @@ static inline void pmd_clear(pmd_t *pmdp)
 		set_pte((pte_t *)&pmdp->pmdv[i], __pte(0));
 }
 
-static inline int pgd_none(pgd_t pgd)          
+static inline int pud_none(pud_t pud)
 {
-	return !(pgd_val(pgd) & 0xFFFFFFF);
+	return !(pud_val(pud) & 0xFFFFFFF);
 }
 
-static inline int pgd_bad(pgd_t pgd)
+static inline int pud_bad(pud_t pud)
 {
-	return (pgd_val(pgd) & SRMMU_ET_MASK) != SRMMU_ET_PTD;
+	return (pud_val(pud) & SRMMU_ET_MASK) != SRMMU_ET_PTD;
 }
 
-static inline int pgd_present(pgd_t pgd)
+static inline int pud_present(pud_t pud)
 {
-	return ((pgd_val(pgd) & SRMMU_ET_MASK) == SRMMU_ET_PTD);
+	return ((pud_val(pud) & SRMMU_ET_MASK) == SRMMU_ET_PTD);
 }
 
-static inline void pgd_clear(pgd_t *pgdp)
+static inline void pud_clear(pud_t *pudp)
 {
-	set_pte((pte_t *)pgdp, __pte(0));
+	set_pte((pte_t *)pudp, __pte(0));
 }
 
 /*
@@ -319,9 +319,9 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 #define pgd_offset_k(address) pgd_offset(&init_mm, address)
 
 /* Find an entry in the second-level page table.. */
-static inline pmd_t *pmd_offset(pgd_t * dir, unsigned long address)
+static inline pmd_t *pmd_offset(pud_t * dir, unsigned long address)
 {
-	return (pmd_t *) pgd_page_vaddr(*dir) +
+	return (pmd_t *) pud_page_vaddr(*dir) +
 		((address >> PMD_SHIFT) & (PTRS_PER_PMD - 1));
 }
 

arch/sparc/include/uapi/asm/ipcbuf.h

@@ -2,6 +2,8 @@
 #ifndef __SPARC_IPCBUF_H
 #define __SPARC_IPCBUF_H
 
+#include <linux/posix_types.h>
+
 /*
  * The ipc64_perm structure for sparc/sparc64 architecture.
  * Note extra padding because this structure is passed back and forth

arch/sparc/include/uapi/asm/msgbuf.h

@@ -2,6 +2,8 @@
 #ifndef _SPARC_MSGBUF_H
 #define _SPARC_MSGBUF_H
 
+#include <asm/ipcbuf.h>
+
 /*
  * The msqid64_ds structure for sparc64 architecture.
  * Note extra padding because this structure is passed back and forth

arch/sparc/include/uapi/asm/sembuf.h

@@ -2,6 +2,8 @@
 #ifndef _SPARC_SEMBUF_H
 #define _SPARC_SEMBUF_H
 
+#include <asm/ipcbuf.h>
+
 /*
  * The semid64_ds structure for sparc architecture.
  * Note extra padding because this structure is passed back and forth

arch/sparc/mm/fault_32.c

@@ -351,6 +351,8 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 		 */
 		int offset = pgd_index(address);
 		pgd_t *pgd, *pgd_k;
+		p4d_t *p4d, *p4d_k;
+		pud_t *pud, *pud_k;
 		pmd_t *pmd, *pmd_k;
 
 		pgd = tsk->active_mm->pgd + offset;
@@ -363,8 +365,13 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 			return;
 		}
 
-		pmd = pmd_offset(pgd, address);
-		pmd_k = pmd_offset(pgd_k, address);
+		p4d = p4d_offset(pgd, address);
+		pud = pud_offset(p4d, address);
+		pmd = pmd_offset(pud, address);
+
+		p4d_k = p4d_offset(pgd_k, address);
+		pud_k = pud_offset(p4d_k, address);
+		pmd_k = pmd_offset(pud_k, address);
 
 		if (pmd_present(*pmd) || !pmd_present(*pmd_k))
 			goto bad_area_nosemaphore;

arch/sparc/mm/highmem.c

@@ -39,10 +39,14 @@ static pte_t *kmap_pte;
 void __init kmap_init(void)
 {
 	unsigned long address;
+	p4d_t *p4d;
+	pud_t *pud;
 	pmd_t *dir;
 
 	address = __fix_to_virt(FIX_KMAP_BEGIN);
-	dir = pmd_offset(pgd_offset_k(address), address);
+	p4d = p4d_offset(pgd_offset_k(address), address);
+	pud = pud_offset(p4d, address);
+	dir = pmd_offset(pud, address);
 
         /* cache the first kmap pte */
         kmap_pte = pte_offset_kernel(dir, address);

arch/sparc/mm/io-unit.c

@@ -239,12 +239,16 @@ static void *iounit_alloc(struct device *dev, size_t len,
 		page = va;
 		{
 			pgd_t *pgdp;
+			p4d_t *p4dp;
+			pud_t *pudp;
 			pmd_t *pmdp;
 			pte_t *ptep;
 			long i;
 
 			pgdp = pgd_offset(&init_mm, addr);
-			pmdp = pmd_offset(pgdp, addr);
+			p4dp = p4d_offset(pgdp, addr);
+			pudp = pud_offset(p4dp, addr);
+			pmdp = pmd_offset(pudp, addr);
 			ptep = pte_offset_map(pmdp, addr);
 
 			set_pte(ptep, mk_pte(virt_to_page(page), dvma_prot));

arch/sparc/mm/iommu.c

@@ -343,6 +343,8 @@ static void *sbus_iommu_alloc(struct device *dev, size_t len,
 		page = va;
 		{
 			pgd_t *pgdp;
+			p4d_t *p4dp;
+			pud_t *pudp;
 			pmd_t *pmdp;
 			pte_t *ptep;
 
@@ -354,7 +356,9 @@ static void *sbus_iommu_alloc(struct device *dev, size_t len,
 				__flush_page_to_ram(page);
 
 			pgdp = pgd_offset(&init_mm, addr);
-			pmdp = pmd_offset(pgdp, addr);
+			p4dp = p4d_offset(pgdp, addr);
+			pudp = pud_offset(p4dp, addr);
+			pmdp = pmd_offset(pudp, addr);
 			ptep = pte_offset_map(pmdp, addr);
 
 			set_pte(ptep, mk_pte(virt_to_page(page), dvma_prot));

arch/sparc/mm/srmmu.c

@@ -296,6 +296,8 @@ static void __init srmmu_nocache_init(void)
 	void *srmmu_nocache_bitmap;
 	unsigned int bitmap_bits;
 	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 	unsigned long paddr, vaddr;
@@ -329,6 +331,8 @@ static void __init srmmu_nocache_init(void)
 
 	while (vaddr < srmmu_nocache_end) {
 		pgd = pgd_offset_k(vaddr);
+		p4d = p4d_offset(__nocache_fix(pgd), vaddr);
+		pud = pud_offset(__nocache_fix(p4d), vaddr);
 		pmd = pmd_offset(__nocache_fix(pgd), vaddr);
 		pte = pte_offset_kernel(__nocache_fix(pmd), vaddr);
 
@@ -516,13 +520,17 @@ static inline void srmmu_mapioaddr(unsigned long physaddr,
 				   unsigned long virt_addr, int bus_type)
 {
 	pgd_t *pgdp;
+	p4d_t *p4dp;
+	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
 	unsigned long tmp;
 
 	physaddr &= PAGE_MASK;
 	pgdp = pgd_offset_k(virt_addr);
-	pmdp = pmd_offset(pgdp, virt_addr);
+	p4dp = p4d_offset(pgdp, virt_addr);
+	pudp = pud_offset(p4dp, virt_addr);
+	pmdp = pmd_offset(pudp, virt_addr);
 	ptep = pte_offset_kernel(pmdp, virt_addr);
 	tmp = (physaddr >> 4) | SRMMU_ET_PTE;
 
@@ -551,11 +559,16 @@ void srmmu_mapiorange(unsigned int bus, unsigned long xpa,
 static inline void srmmu_unmapioaddr(unsigned long virt_addr)
 {
 	pgd_t *pgdp;
+	p4d_t *p4dp;
+	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
 
+
 	pgdp = pgd_offset_k(virt_addr);
-	pmdp = pmd_offset(pgdp, virt_addr);
+	p4dp = p4d_offset(pgdp, virt_addr);
+	pudp = pud_offset(p4dp, virt_addr);
+	pmdp = pmd_offset(pudp, virt_addr);
 	ptep = pte_offset_kernel(pmdp, virt_addr);
 
 	/* No need to flush uncacheable page. */
@@ -693,20 +706,24 @@ static void __init srmmu_early_allocate_ptable_skeleton(unsigned long start,
 							unsigned long end)
 {
 	pgd_t *pgdp;
+	p4d_t *p4dp;
+	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
 
 	while (start < end) {
 		pgdp = pgd_offset_k(start);
-		if (pgd_none(*(pgd_t *)__nocache_fix(pgdp))) {
+		p4dp = p4d_offset(pgdp, start);
+		pudp = pud_offset(p4dp, start);
+		if (pud_none(*(pud_t *)__nocache_fix(pudp))) {
 			pmdp = __srmmu_get_nocache(
 			    SRMMU_PMD_TABLE_SIZE, SRMMU_PMD_TABLE_SIZE);
 			if (pmdp == NULL)
 				early_pgtable_allocfail("pmd");
 			memset(__nocache_fix(pmdp), 0, SRMMU_PMD_TABLE_SIZE);
-			pgd_set(__nocache_fix(pgdp), pmdp);
+			pud_set(__nocache_fix(pudp), pmdp);
 		}
-		pmdp = pmd_offset(__nocache_fix(pgdp), start);
+		pmdp = pmd_offset(__nocache_fix(pudp), start);
 		if (srmmu_pmd_none(*(pmd_t *)__nocache_fix(pmdp))) {
 			ptep = __srmmu_get_nocache(PTE_SIZE, PTE_SIZE);
 			if (ptep == NULL)
@@ -724,19 +741,23 @@ static void __init srmmu_allocate_ptable_skeleton(unsigned long start,
 						  unsigned long end)
 {
 	pgd_t *pgdp;
+	p4d_t *p4dp;
+	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
 
 	while (start < end) {
 		pgdp = pgd_offset_k(start);
-		if (pgd_none(*pgdp)) {
+		p4dp = p4d_offset(pgdp, start);
+		pudp = pud_offset(p4dp, start);
+		if (pud_none(*pudp)) {
 			pmdp = __srmmu_get_nocache(SRMMU_PMD_TABLE_SIZE, SRMMU_PMD_TABLE_SIZE);
 			if (pmdp == NULL)
 				early_pgtable_allocfail("pmd");
 			memset(pmdp, 0, SRMMU_PMD_TABLE_SIZE);
-			pgd_set(pgdp, pmdp);
+			pud_set((pud_t *)pgdp, pmdp);
 		}
-		pmdp = pmd_offset(pgdp, start);
+		pmdp = pmd_offset(pudp, start);
 		if (srmmu_pmd_none(*pmdp)) {
 			ptep = __srmmu_get_nocache(PTE_SIZE,
 							     PTE_SIZE);
@@ -779,6 +800,8 @@ static void __init srmmu_inherit_prom_mappings(unsigned long start,
 	unsigned long probed;
 	unsigned long addr;
 	pgd_t *pgdp;
+	p4d_t *p4dp;
+	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep;
 	int what; /* 0 = normal-pte, 1 = pmd-level pte, 2 = pgd-level pte */
@@ -810,18 +833,20 @@ static void __init srmmu_inherit_prom_mappings(unsigned long start,
 		}
 
 		pgdp = pgd_offset_k(start);
+		p4dp = p4d_offset(pgdp, start);
+		pudp = pud_offset(p4dp, start);
 		if (what == 2) {
 			*(pgd_t *)__nocache_fix(pgdp) = __pgd(probed);
 			start += SRMMU_PGDIR_SIZE;
 			continue;
 		}
-		if (pgd_none(*(pgd_t *)__nocache_fix(pgdp))) {
+		if (pud_none(*(pud_t *)__nocache_fix(pudp))) {
 			pmdp = __srmmu_get_nocache(SRMMU_PMD_TABLE_SIZE,
 						   SRMMU_PMD_TABLE_SIZE);
 			if (pmdp == NULL)
 				early_pgtable_allocfail("pmd");
 			memset(__nocache_fix(pmdp), 0, SRMMU_PMD_TABLE_SIZE);
-			pgd_set(__nocache_fix(pgdp), pmdp);
+			pud_set(__nocache_fix(pudp), pmdp);
 		}
 		pmdp = pmd_offset(__nocache_fix(pgdp), start);
 		if (srmmu_pmd_none(*(pmd_t *)__nocache_fix(pmdp))) {
@@ -906,6 +931,8 @@ void __init srmmu_paging_init(void)
 	phandle cpunode;
 	char node_str[128];
 	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 	unsigned long pages_avail;
@@ -967,7 +994,9 @@ void __init srmmu_paging_init(void)
 	srmmu_allocate_ptable_skeleton(PKMAP_BASE, PKMAP_END);
 
 	pgd = pgd_offset_k(PKMAP_BASE);
-	pmd = pmd_offset(pgd, PKMAP_BASE);
+	p4d = p4d_offset(pgd, PKMAP_BASE);
+	pud = pud_offset(p4d, PKMAP_BASE);
+	pmd = pmd_offset(pud, PKMAP_BASE);
 	pte = pte_offset_kernel(pmd, PKMAP_BASE);
 	pkmap_page_table = pte;
 

arch/um/include/asm/pgtable-2level.h

@@ -8,7 +8,6 @@
 #ifndef __UM_PGTABLE_2LEVEL_H
 #define __UM_PGTABLE_2LEVEL_H
 
-#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 
 /* PGDIR_SHIFT determines what a third-level page table entry can map */

arch/um/include/asm/pgtable-3level.h

@@ -7,7 +7,6 @@
 #ifndef __UM_PGTABLE_3LEVEL_H
 #define __UM_PGTABLE_3LEVEL_H
 
-#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 
 /* PGDIR_SHIFT determines what a third-level page table entry can map */

arch/um/include/asm/pgtable.h

@@ -106,6 +106,9 @@ extern unsigned long end_iomem;
 #define pud_newpage(x)  (pud_val(x) & _PAGE_NEWPAGE)
 #define pud_mkuptodate(x) (pud_val(x) &= ~_PAGE_NEWPAGE)
 
+#define p4d_newpage(x)  (p4d_val(x) & _PAGE_NEWPAGE)
+#define p4d_mkuptodate(x) (p4d_val(x) &= ~_PAGE_NEWPAGE)
+
 #define pmd_page(pmd) phys_to_page(pmd_val(pmd) & PAGE_MASK)
 
 #define pte_page(x) pfn_to_page(pte_pfn(x))

arch/um/kernel/mem.c

@@ -96,6 +96,7 @@ static void __init fixrange_init(unsigned long start, unsigned long end,
 				 pgd_t *pgd_base)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	int i, j;
@@ -107,7 +108,8 @@ static void __init fixrange_init(unsigned long start, unsigned long end,
 	pgd = pgd_base + i;
 
 	for ( ; (i < PTRS_PER_PGD) && (vaddr < end); pgd++, i++) {
-		pud = pud_offset(pgd, vaddr);
+		p4d = p4d_offset(pgd, vaddr);
+		pud = pud_offset(p4d, vaddr);
 		if (pud_none(*pud))
 			one_md_table_init(pud);
 		pmd = pmd_offset(pud, vaddr);
@@ -124,6 +126,7 @@ static void __init fixaddr_user_init( void)
 #ifdef CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA
 	long size = FIXADDR_USER_END - FIXADDR_USER_START;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -144,7 +147,8 @@ static void __init fixaddr_user_init( void)
 	for ( ; size > 0; size -= PAGE_SIZE, vaddr += PAGE_SIZE,
 		      p += PAGE_SIZE) {
 		pgd = swapper_pg_dir + pgd_index(vaddr);
-		pud = pud_offset(pgd, vaddr);
+		p4d = p4d_offset(pgd, vaddr);
+		pud = pud_offset(p4d, vaddr);
 		pmd = pmd_offset(pud, vaddr);
 		pte = pte_offset_kernel(pmd, vaddr);
 		pte_set_val(*pte, p, PAGE_READONLY);

arch/um/kernel/skas/mmu.c

@@ -19,15 +19,21 @@ static int init_stub_pte(struct mm_struct *mm, unsigned long proc,
 			 unsigned long kernel)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 
 	pgd = pgd_offset(mm, proc);
-	pud = pud_alloc(mm, pgd, proc);
-	if (!pud)
+
+	p4d = p4d_alloc(mm, pgd, proc);
+	if (!p4d)
 		goto out;
 
+	pud = pud_alloc(mm, p4d, proc);
+	if (!pud)
+		goto out_pud;
+
 	pmd = pmd_alloc(mm, pud, proc);
 	if (!pmd)
 		goto out_pmd;
@@ -44,6 +50,8 @@ static int init_stub_pte(struct mm_struct *mm, unsigned long proc,
 	pmd_free(mm, pmd);
  out_pmd:
 	pud_free(mm, pud);
+ out_pud:
+	p4d_free(mm, p4d);
  out:
 	return -ENOMEM;
 }

arch/um/kernel/skas/uaccess.c

@@ -17,6 +17,7 @@
 pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -27,7 +28,11 @@ pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr)
 	if (!pgd_present(*pgd))
 		return NULL;
 
-	pud = pud_offset(pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	if (!p4d_present(*p4d))
+		return NULL;
+
+	pud = pud_offset(p4d, addr);
 	if (!pud_present(*pud))
 		return NULL;
 

arch/um/kernel/tlb.c

@@ -277,7 +277,7 @@ static inline int update_pmd_range(pud_t *pud, unsigned long addr,
 	return ret;
 }
 
-static inline int update_pud_range(pgd_t *pgd, unsigned long addr,
+static inline int update_pud_range(p4d_t *p4d, unsigned long addr,
 				   unsigned long end,
 				   struct host_vm_change *hvc)
 {
@@ -285,7 +285,7 @@ static inline int update_pud_range(pgd_t *pgd, unsigned long addr,
 	unsigned long next;
 	int ret = 0;
 
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (!pud_present(*pud)) {
@@ -299,6 +299,28 @@ static inline int update_pud_range(pgd_t *pgd, unsigned long addr,
 	return ret;
 }
 
+static inline int update_p4d_range(pgd_t *pgd, unsigned long addr,
+				   unsigned long end,
+				   struct host_vm_change *hvc)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	int ret = 0;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (!p4d_present(*p4d)) {
+			if (hvc->force || p4d_newpage(*p4d)) {
+				ret = add_munmap(addr, next - addr, hvc);
+				p4d_mkuptodate(*p4d);
+			}
+		} else
+			ret = update_pud_range(p4d, addr, next, hvc);
+	} while (p4d++, addr = next, ((addr < end) && !ret));
+	return ret;
+}
+
 void fix_range_common(struct mm_struct *mm, unsigned long start_addr,
 		      unsigned long end_addr, int force)
 {
@@ -316,8 +338,8 @@ void fix_range_common(struct mm_struct *mm, unsigned long start_addr,
 				ret = add_munmap(addr, next - addr, &hvc);
 				pgd_mkuptodate(*pgd);
 			}
-		}
-		else ret = update_pud_range(pgd, addr, next, &hvc);
+		} else
+			ret = update_p4d_range(pgd, addr, next, &hvc);
 	} while (pgd++, addr = next, ((addr < end_addr) && !ret));
 
 	if (!ret)
@@ -338,6 +360,7 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
 {
 	struct mm_struct *mm;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -364,7 +387,23 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
 			continue;
 		}
 
-		pud = pud_offset(pgd, addr);
+		p4d = p4d_offset(pgd, addr);
+		if (!p4d_present(*p4d)) {
+			last = ADD_ROUND(addr, P4D_SIZE);
+			if (last > end)
+				last = end;
+			if (p4d_newpage(*p4d)) {
+				updated = 1;
+				err = add_munmap(addr, last - addr, &hvc);
+				if (err < 0)
+					panic("munmap failed, errno = %d\n",
+					      -err);
+			}
+			addr = last;
+			continue;
+		}
+
+		pud = pud_offset(p4d, addr);
 		if (!pud_present(*pud)) {
 			last = ADD_ROUND(addr, PUD_SIZE);
 			if (last > end)
@@ -424,6 +463,7 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end)
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long address)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -437,7 +477,11 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long address)
 	if (!pgd_present(*pgd))
 		goto kill;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (!p4d_present(*p4d))
+		goto kill;
+
+	pud = pud_offset(p4d, address);
 	if (!pud_present(*pud))
 		goto kill;
 
@@ -490,35 +534,6 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long address)
 	force_sig(SIGKILL);
 }
 
-pgd_t *pgd_offset_proc(struct mm_struct *mm, unsigned long address)
-{
-	return pgd_offset(mm, address);
-}
-
-pud_t *pud_offset_proc(pgd_t *pgd, unsigned long address)
-{
-	return pud_offset(pgd, address);
-}
-
-pmd_t *pmd_offset_proc(pud_t *pud, unsigned long address)
-{
-	return pmd_offset(pud, address);
-}
-
-pte_t *pte_offset_proc(pmd_t *pmd, unsigned long address)
-{
-	return pte_offset_kernel(pmd, address);
-}
-
-pte_t *addr_pte(struct task_struct *task, unsigned long addr)
-{
-	pgd_t *pgd = pgd_offset(task->mm, addr);
-	pud_t *pud = pud_offset(pgd, addr);
-	pmd_t *pmd = pmd_offset(pud, addr);
-
-	return pte_offset_map(pmd, addr);
-}
-
 void flush_tlb_all(void)
 {
 	/*

arch/um/kernel/trap.c

@@ -28,6 +28,7 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -104,7 +105,8 @@ int handle_page_fault(unsigned long address, unsigned long ip,
 		}
 
 		pgd = pgd_offset(mm, address);
-		pud = pud_offset(pgd, address);
+		p4d = p4d_offset(pgd, address);
+		pud = pud_offset(p4d, address);
 		pmd = pmd_offset(pud, address);
 		pte = pte_offset_kernel(pmd, address);
 	} while (!pte_present(*pte));

arch/x86/include/uapi/asm/msgbuf.h

@@ -5,6 +5,9 @@
 #if !defined(__x86_64__) || !defined(__ILP32__)
 #include <asm-generic/msgbuf.h>
 #else
+
+#include <asm/ipcbuf.h>
+
 /*
  * The msqid64_ds structure for x86 architecture with x32 ABI.
  *

arch/x86/include/uapi/asm/sembuf.h

@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_SEMBUF_H
 #define _ASM_X86_SEMBUF_H
 
+#include <asm/ipcbuf.h>
+
 /*
  * The semid64_ds structure for x86 architecture.
  * Note extra padding because this structure is passed back and forth

arch/xtensa/include/uapi/asm/ipcbuf.h

@@ -12,6 +12,8 @@
 #ifndef _XTENSA_IPCBUF_H
 #define _XTENSA_IPCBUF_H
 
+#include <linux/posix_types.h>
+
 /*
  * Pad space is left for:
  * - 32-bit mode_t and seq

arch/xtensa/include/uapi/asm/msgbuf.h

@@ -17,6 +17,8 @@
 #ifndef _XTENSA_MSGBUF_H
 #define _XTENSA_MSGBUF_H
 
+#include <asm/ipcbuf.h>
+
 struct msqid64_ds {
 	struct ipc64_perm msg_perm;
 #ifdef __XTENSA_EB__

arch/xtensa/include/uapi/asm/sembuf.h

@@ -22,6 +22,7 @@
 #define _XTENSA_SEMBUF_H
 
 #include <asm/byteorder.h>
+#include <asm/ipcbuf.h>
 
 struct semid64_ds {
 	struct ipc64_perm sem_perm;		/* permissions .. see ipc.h */

drivers/auxdisplay/charlcd.c

@@ -287,31 +287,6 @@ static int charlcd_init_display(struct charlcd *lcd)
 	return 0;
 }
 
-/*
- * Parses an unsigned integer from a string, until a non-digit character
- * is found. The empty string is not accepted. No overflow checks are done.
- *
- * Returns whether the parsing was successful. Only in that case
- * the output parameters are written to.
- *
- * TODO: If the kernel adds an inplace version of kstrtoul(), this function
- * could be easily replaced by that.
- */
-static bool parse_n(const char *s, unsigned long *res, const char **next_s)
-{
-	if (!isdigit(*s))
-		return false;
-
-	*res = 0;
-	while (isdigit(*s)) {
-		*res = *res * 10 + (*s - '0');
-		++s;
-	}
-
-	*next_s = s;
-	return true;
-}
-
 /*
  * Parses a movement command of the form "(.*);", where the group can be
  * any number of subcommands of the form "(x|y)[0-9]+".
@@ -336,6 +311,7 @@ static bool parse_xy(const char *s, unsigned long *x, unsigned long *y)
 {
 	unsigned long new_x = *x;
 	unsigned long new_y = *y;
+	char *p;
 
 	for (;;) {
 		if (!*s)
@@ -345,11 +321,15 @@ static bool parse_xy(const char *s, unsigned long *x, unsigned long *y)
 			break;
 
 		if (*s == 'x') {
-			if (!parse_n(s + 1, &new_x, &s))
+			new_x = simple_strtoul(s + 1, &p, 10);
+			if (p == s + 1)
 				return false;
+			s = p;
 		} else if (*s == 'y') {
-			if (!parse_n(s + 1, &new_y, &s))
+			new_y = simple_strtoul(s + 1, &p, 10);
+			if (p == s + 1)
 				return false;
+			s = p;
 		} else {
 			return false;
 		}

drivers/base/node.c

@@ -496,20 +496,17 @@ static ssize_t node_read_vmstat(struct device *dev,
 	int n = 0;
 
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
-		n += sprintf(buf+n, "%s %lu\n", vmstat_text[i],
+		n += sprintf(buf+n, "%s %lu\n", zone_stat_name(i),
 			     sum_zone_node_page_state(nid, i));
 
 #ifdef CONFIG_NUMA
 	for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++)
-		n += sprintf(buf+n, "%s %lu\n",
-			     vmstat_text[i + NR_VM_ZONE_STAT_ITEMS],
+		n += sprintf(buf+n, "%s %lu\n", numa_stat_name(i),
 			     sum_zone_numa_state(nid, i));
 #endif
 
 	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
-		n += sprintf(buf+n, "%s %lu\n",
-			     vmstat_text[i + NR_VM_ZONE_STAT_ITEMS +
-			     NR_VM_NUMA_STAT_ITEMS],
+		n += sprintf(buf+n, "%s %lu\n", node_stat_name(i),
 			     node_page_state(pgdat, i));
 
 	return n;

drivers/gpio/gpio-104-dio-48e.c

@@ -178,46 +178,25 @@ static int dio48e_gpio_get(struct gpio_chip *chip, unsigned offset)
 	return !!(port_state & mask);
 }
 
+static const size_t ports[] = { 0, 1, 2, 4, 5, 6 };
+
 static int dio48e_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask,
 	unsigned long *bits)
 {
 	struct dio48e_gpio *const dio48egpio = gpiochip_get_data(chip);
-	size_t i;
-	static const size_t ports[] = { 0, 1, 2, 4, 5, 6 };
-	const unsigned int gpio_reg_size = 8;
-	unsigned int bits_offset;
-	size_t word_index;
-	unsigned int word_offset;
-	unsigned long word_mask;
-	const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
+	unsigned long offset;
+	unsigned long gpio_mask;
+	unsigned int port_addr;
 	unsigned long port_state;
 
 	/* clear bits array to a clean slate */
 	bitmap_zero(bits, chip->ngpio);
 
-	/* get bits are evaluated a gpio port register at a time */
-	for (i = 0; i < ARRAY_SIZE(ports); i++) {
-		/* gpio offset in bits array */
-		bits_offset = i * gpio_reg_size;
-
-		/* word index for bits array */
-		word_index = BIT_WORD(bits_offset);
-
-		/* gpio offset within current word of bits array */
-		word_offset = bits_offset % BITS_PER_LONG;
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		port_addr = dio48egpio->base + ports[offset / 8];
+		port_state = inb(port_addr) & gpio_mask;
 
-		/* mask of get bits for current gpio within current word */
-		word_mask = mask[word_index] & (port_mask << word_offset);
-		if (!word_mask) {
-			/* no get bits in this port so skip to next one */
-			continue;
-		}
-
-		/* read bits from current gpio port */
-		port_state = inb(dio48egpio->base + ports[i]);
-
-		/* store acquired bits at respective bits array offset */
-		bits[word_index] |= (port_state << word_offset) & word_mask;
+		bitmap_set_value8(bits, port_state, offset);
 	}
 
 	return 0;
@@ -247,37 +226,27 @@ static void dio48e_gpio_set_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct dio48e_gpio *const dio48egpio = gpiochip_get_data(chip);
-	unsigned int i;
-	const unsigned int gpio_reg_size = 8;
-	unsigned int port;
-	unsigned int out_port;
-	unsigned int bitmask;
+	unsigned long offset;
+	unsigned long gpio_mask;
+	size_t index;
+	unsigned int port_addr;
+	unsigned long bitmask;
 	unsigned long flags;
 
-	/* set bits are evaluated a gpio register size at a time */
-	for (i = 0; i < chip->ngpio; i += gpio_reg_size) {
-		/* no more set bits in this mask word; skip to the next word */
-		if (!mask[BIT_WORD(i)]) {
-			i = (BIT_WORD(i) + 1) * BITS_PER_LONG - gpio_reg_size;
-			continue;
-		}
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		index = offset / 8;
+		port_addr = dio48egpio->base + ports[index];
 
-		port = i / gpio_reg_size;
-		out_port = (port > 2) ? port + 1 : port;
-		bitmask = mask[BIT_WORD(i)] & bits[BIT_WORD(i)];
+		bitmask = bitmap_get_value8(bits, offset) & gpio_mask;
 
 		raw_spin_lock_irqsave(&dio48egpio->lock, flags);
 
 		/* update output state data and set device gpio register */
-		dio48egpio->out_state[port] &= ~mask[BIT_WORD(i)];
-		dio48egpio->out_state[port] |= bitmask;
-		outb(dio48egpio->out_state[port], dio48egpio->base + out_port);
+		dio48egpio->out_state[index] &= ~gpio_mask;
+		dio48egpio->out_state[index] |= bitmask;
+		outb(dio48egpio->out_state[index], port_addr);
 
 		raw_spin_unlock_irqrestore(&dio48egpio->lock, flags);
-
-		/* prepare for next gpio register set */
-		mask[BIT_WORD(i)] >>= gpio_reg_size;
-		bits[BIT_WORD(i)] >>= gpio_reg_size;
 	}
 }
 

drivers/gpio/gpio-104-idi-48.c

@@ -85,42 +85,20 @@ static int idi_48_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask,
 	unsigned long *bits)
 {
 	struct idi_48_gpio *const idi48gpio = gpiochip_get_data(chip);
-	size_t i;
+	unsigned long offset;
+	unsigned long gpio_mask;
 	static const size_t ports[] = { 0, 1, 2, 4, 5, 6 };
-	const unsigned int gpio_reg_size = 8;
-	unsigned int bits_offset;
-	size_t word_index;
-	unsigned int word_offset;
-	unsigned long word_mask;
-	const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
+	unsigned int port_addr;
 	unsigned long port_state;
 
 	/* clear bits array to a clean slate */
 	bitmap_zero(bits, chip->ngpio);
 
-	/* get bits are evaluated a gpio port register at a time */
-	for (i = 0; i < ARRAY_SIZE(ports); i++) {
-		/* gpio offset in bits array */
-		bits_offset = i * gpio_reg_size;
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		port_addr = idi48gpio->base + ports[offset / 8];
+		port_state = inb(port_addr) & gpio_mask;
 
-		/* word index for bits array */
-		word_index = BIT_WORD(bits_offset);
-
-		/* gpio offset within current word of bits array */
-		word_offset = bits_offset % BITS_PER_LONG;
-
-		/* mask of get bits for current gpio within current word */
-		word_mask = mask[word_index] & (port_mask << word_offset);
-		if (!word_mask) {
-			/* no get bits in this port so skip to next one */
-			continue;
-		}
-
-		/* read bits from current gpio port */
-		port_state = inb(idi48gpio->base + ports[i]);
-
-		/* store acquired bits at respective bits array offset */
-		bits[word_index] |= (port_state << word_offset) & word_mask;
+		bitmap_set_value8(bits, port_state, offset);
 	}
 
 	return 0;

drivers/gpio/gpio-74x164.c

@@ -6,6 +6,7 @@
  *  Copyright (C) 2010 Miguel Gaio <miguel.gaio@efixo.com>
  */
 
+#include <linux/bitops.h>
 #include <linux/gpio/consumer.h>
 #include <linux/gpio/driver.h>
 #include <linux/module.h>
@@ -72,20 +73,18 @@ static void gen_74x164_set_multiple(struct gpio_chip *gc, unsigned long *mask,
 				    unsigned long *bits)
 {
 	struct gen_74x164_chip *chip = gpiochip_get_data(gc);
-	unsigned int i, idx, shift;
-	u8 bank, bankmask;
+	unsigned long offset;
+	unsigned long bankmask;
+	size_t bank;
+	unsigned long bitmask;
 
 	mutex_lock(&chip->lock);
-	for (i = 0, bank = chip->registers - 1; i < chip->registers;
-	     i++, bank--) {
-		idx = i / sizeof(*mask);
-		shift = i % sizeof(*mask) * BITS_PER_BYTE;
-		bankmask = mask[idx] >> shift;
-		if (!bankmask)
-			continue;
+	for_each_set_clump8(offset, bankmask, mask, chip->registers * 8) {
+		bank = chip->registers - 1 - offset / 8;
+		bitmask = bitmap_get_value8(bits, offset) & bankmask;
 
 		chip->buffer[bank] &= ~bankmask;
-		chip->buffer[bank] |= bankmask & (bits[idx] >> shift);
+		chip->buffer[bank] |= bitmask;
 	}
 	__gen_74x164_write_config(chip);
 	mutex_unlock(&chip->lock);

drivers/gpio/gpio-gpio-mm.c

@@ -167,46 +167,25 @@ static int gpiomm_gpio_get(struct gpio_chip *chip, unsigned int offset)
 	return !!(port_state & mask);
 }
 
+static const size_t ports[] = { 0, 1, 2, 4, 5, 6 };
+
 static int gpiomm_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask,
 	unsigned long *bits)
 {
 	struct gpiomm_gpio *const gpiommgpio = gpiochip_get_data(chip);
-	size_t i;
-	static const size_t ports[] = { 0, 1, 2, 4, 5, 6 };
-	const unsigned int gpio_reg_size = 8;
-	unsigned int bits_offset;
-	size_t word_index;
-	unsigned int word_offset;
-	unsigned long word_mask;
-	const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
+	unsigned long offset;
+	unsigned long gpio_mask;
+	unsigned int port_addr;
 	unsigned long port_state;
 
 	/* clear bits array to a clean slate */
 	bitmap_zero(bits, chip->ngpio);
 
-	/* get bits are evaluated a gpio port register at a time */
-	for (i = 0; i < ARRAY_SIZE(ports); i++) {
-		/* gpio offset in bits array */
-		bits_offset = i * gpio_reg_size;
-
-		/* word index for bits array */
-		word_index = BIT_WORD(bits_offset);
-
-		/* gpio offset within current word of bits array */
-		word_offset = bits_offset % BITS_PER_LONG;
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		port_addr = gpiommgpio->base + ports[offset / 8];
+		port_state = inb(port_addr) & gpio_mask;
 
-		/* mask of get bits for current gpio within current word */
-		word_mask = mask[word_index] & (port_mask << word_offset);
-		if (!word_mask) {
-			/* no get bits in this port so skip to next one */
-			continue;
-		}
-
-		/* read bits from current gpio port */
-		port_state = inb(gpiommgpio->base + ports[i]);
-
-		/* store acquired bits at respective bits array offset */
-		bits[word_index] |= (port_state << word_offset) & word_mask;
+		bitmap_set_value8(bits, port_state, offset);
 	}
 
 	return 0;
@@ -237,37 +216,27 @@ static void gpiomm_gpio_set_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct gpiomm_gpio *const gpiommgpio = gpiochip_get_data(chip);
-	unsigned int i;
-	const unsigned int gpio_reg_size = 8;
-	unsigned int port;
-	unsigned int out_port;
-	unsigned int bitmask;
+	unsigned long offset;
+	unsigned long gpio_mask;
+	size_t index;
+	unsigned int port_addr;
+	unsigned long bitmask;
 	unsigned long flags;
 
-	/* set bits are evaluated a gpio register size at a time */
-	for (i = 0; i < chip->ngpio; i += gpio_reg_size) {
-		/* no more set bits in this mask word; skip to the next word */
-		if (!mask[BIT_WORD(i)]) {
-			i = (BIT_WORD(i) + 1) * BITS_PER_LONG - gpio_reg_size;
-			continue;
-		}
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		index = offset / 8;
+		port_addr = gpiommgpio->base + ports[index];
 
-		port = i / gpio_reg_size;
-		out_port = (port > 2) ? port + 1 : port;
-		bitmask = mask[BIT_WORD(i)] & bits[BIT_WORD(i)];
+		bitmask = bitmap_get_value8(bits, offset) & gpio_mask;
 
 		spin_lock_irqsave(&gpiommgpio->lock, flags);
 
 		/* update output state data and set device gpio register */
-		gpiommgpio->out_state[port] &= ~mask[BIT_WORD(i)];
-		gpiommgpio->out_state[port] |= bitmask;
-		outb(gpiommgpio->out_state[port], gpiommgpio->base + out_port);
+		gpiommgpio->out_state[index] &= ~gpio_mask;
+		gpiommgpio->out_state[index] |= bitmask;
+		outb(gpiommgpio->out_state[index], port_addr);
 
 		spin_unlock_irqrestore(&gpiommgpio->lock, flags);
-
-		/* prepare for next gpio register set */
-		mask[BIT_WORD(i)] >>= gpio_reg_size;
-		bits[BIT_WORD(i)] >>= gpio_reg_size;
 	}
 }
 

drivers/gpio/gpio-max3191x.c

@@ -31,6 +31,7 @@
  */
 
 #include <linux/bitmap.h>
+#include <linux/bitops.h>
 #include <linux/crc8.h>
 #include <linux/gpio/consumer.h>
 #include <linux/gpio/driver.h>
@@ -232,16 +233,20 @@ static int max3191x_get_multiple(struct gpio_chip *gpio, unsigned long *mask,
 				 unsigned long *bits)
 {
 	struct max3191x_chip *max3191x = gpiochip_get_data(gpio);
-	int ret, bit = 0, wordlen = max3191x_wordlen(max3191x);
+	const unsigned int wordlen = max3191x_wordlen(max3191x);
+	int ret;
+	unsigned long bit;
+	unsigned long gpio_mask;
+	unsigned long in;
 
 	mutex_lock(&max3191x->lock);
 	ret = max3191x_readout_locked(max3191x);
 	if (ret)
 		goto out_unlock;
 
-	while ((bit = find_next_bit(mask, gpio->ngpio, bit)) != gpio->ngpio) {
+	bitmap_zero(bits, gpio->ngpio);
+	for_each_set_clump8(bit, gpio_mask, mask, gpio->ngpio) {
 		unsigned int chipnum = bit / MAX3191X_NGPIO;
-		unsigned long in, shift, index;
 
 		if (max3191x_chip_is_faulting(max3191x, chipnum)) {
 			ret = -EIO;
@@ -249,12 +254,8 @@ static int max3191x_get_multiple(struct gpio_chip *gpio, unsigned long *mask,
 		}
 
 		in = ((u8 *)max3191x->xfer.rx_buf)[chipnum * wordlen];
-		shift = round_down(bit % BITS_PER_LONG, MAX3191X_NGPIO);
-		index = bit / BITS_PER_LONG;
-		bits[index] &= ~(mask[index] & (0xff << shift));
-		bits[index] |= mask[index] & (in << shift); /* copy bits */
-
-		bit = (chipnum + 1) * MAX3191X_NGPIO; /* go to next chip */
+		in &= gpio_mask;
+		bitmap_set_value8(bits, in, bit);
 	}
 
 out_unlock:

drivers/gpio/gpio-pci-idio-16.c

@@ -100,45 +100,23 @@ static int idio_16_gpio_get_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct idio_16_gpio *const idio16gpio = gpiochip_get_data(chip);
-	size_t i;
-	const unsigned int gpio_reg_size = 8;
-	unsigned int bits_offset;
-	size_t word_index;
-	unsigned int word_offset;
-	unsigned long word_mask;
-	const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
-	unsigned long port_state;
+	unsigned long offset;
+	unsigned long gpio_mask;
 	void __iomem *ports[] = {
 		&idio16gpio->reg->out0_7, &idio16gpio->reg->out8_15,
 		&idio16gpio->reg->in0_7, &idio16gpio->reg->in8_15,
 	};
+	void __iomem *port_addr;
+	unsigned long port_state;
 
 	/* clear bits array to a clean slate */
 	bitmap_zero(bits, chip->ngpio);
 
-	/* get bits are evaluated a gpio port register at a time */
-	for (i = 0; i < ARRAY_SIZE(ports); i++) {
-		/* gpio offset in bits array */
-		bits_offset = i * gpio_reg_size;
-
-		/* word index for bits array */
-		word_index = BIT_WORD(bits_offset);
-
-		/* gpio offset within current word of bits array */
-		word_offset = bits_offset % BITS_PER_LONG;
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		port_addr = ports[offset / 8];
+		port_state = ioread8(port_addr) & gpio_mask;
 
-		/* mask of get bits for current gpio within current word */
-		word_mask = mask[word_index] & (port_mask << word_offset);
-		if (!word_mask) {
-			/* no get bits in this port so skip to next one */
-			continue;
-		}
-
-		/* read bits from current gpio port */
-		port_state = ioread8(ports[i]);
-
-		/* store acquired bits at respective bits array offset */
-		bits[word_index] |= (port_state << word_offset) & word_mask;
+		bitmap_set_value8(bits, port_state, offset);
 	}
 
 	return 0;
@@ -178,30 +156,31 @@ static void idio_16_gpio_set_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct idio_16_gpio *const idio16gpio = gpiochip_get_data(chip);
+	unsigned long offset;
+	unsigned long gpio_mask;
+	void __iomem *ports[] = {
+		&idio16gpio->reg->out0_7, &idio16gpio->reg->out8_15,
+	};
+	size_t index;
+	void __iomem *port_addr;
+	unsigned long bitmask;
 	unsigned long flags;
-	unsigned int out_state;
+	unsigned long out_state;
 
-	raw_spin_lock_irqsave(&idio16gpio->lock, flags);
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		index = offset / 8;
+		port_addr = ports[index];
 
-	/* process output lines 0-7 */
-	if (*mask & 0xFF) {
-		out_state = ioread8(&idio16gpio->reg->out0_7) & ~*mask;
-		out_state |= *mask & *bits;
-		iowrite8(out_state, &idio16gpio->reg->out0_7);
-	}
+		bitmask = bitmap_get_value8(bits, offset) & gpio_mask;
 
-	/* shift to next output line word */
-	*mask >>= 8;
+		raw_spin_lock_irqsave(&idio16gpio->lock, flags);
 
-	/* process output lines 8-15 */
-	if (*mask & 0xFF) {
-		*bits >>= 8;
-		out_state = ioread8(&idio16gpio->reg->out8_15) & ~*mask;
-		out_state |= *mask & *bits;
-		iowrite8(out_state, &idio16gpio->reg->out8_15);
-	}
+		out_state = ioread8(port_addr) & ~gpio_mask;
+		out_state |= bitmask;
+		iowrite8(out_state, port_addr);
 
 		raw_spin_unlock_irqrestore(&idio16gpio->lock, flags);
+	}
 }
 
 static void idio_16_irq_ack(struct irq_data *data)

drivers/gpio/gpio-pcie-idio-24.c

@@ -201,52 +201,34 @@ static int idio_24_gpio_get_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct idio_24_gpio *const idio24gpio = gpiochip_get_data(chip);
-	size_t i;
-	const unsigned int gpio_reg_size = 8;
-	unsigned int bits_offset;
-	size_t word_index;
-	unsigned int word_offset;
-	unsigned long word_mask;
-	const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
-	unsigned long port_state;
+	unsigned long offset;
+	unsigned long gpio_mask;
 	void __iomem *ports[] = {
 		&idio24gpio->reg->out0_7, &idio24gpio->reg->out8_15,
 		&idio24gpio->reg->out16_23, &idio24gpio->reg->in0_7,
 		&idio24gpio->reg->in8_15, &idio24gpio->reg->in16_23,
 	};
+	size_t index;
+	unsigned long port_state;
 	const unsigned long out_mode_mask = BIT(1);
 
 	/* clear bits array to a clean slate */
 	bitmap_zero(bits, chip->ngpio);
 
-	/* get bits are evaluated a gpio port register at a time */
-	for (i = 0; i < ARRAY_SIZE(ports) + 1; i++) {
-		/* gpio offset in bits array */
-		bits_offset = i * gpio_reg_size;
-
-		/* word index for bits array */
-		word_index = BIT_WORD(bits_offset);
-
-		/* gpio offset within current word of bits array */
-		word_offset = bits_offset % BITS_PER_LONG;
-
-		/* mask of get bits for current gpio within current word */
-		word_mask = mask[word_index] & (port_mask << word_offset);
-		if (!word_mask) {
-			/* no get bits in this port so skip to next one */
-			continue;
-		}
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		index = offset / 8;
 
 		/* read bits from current gpio port (port 6 is TTL GPIO) */
-		if (i < 6)
-			port_state = ioread8(ports[i]);
+		if (index < 6)
+			port_state = ioread8(ports[index]);
 		else if (ioread8(&idio24gpio->reg->ctl) & out_mode_mask)
 			port_state = ioread8(&idio24gpio->reg->ttl_out0_7);
 		else
 			port_state = ioread8(&idio24gpio->reg->ttl_in0_7);
 
-		/* store acquired bits at respective bits array offset */
-		bits[word_index] |= (port_state << word_offset) & word_mask;
+		port_state &= gpio_mask;
+
+		bitmap_set_value8(bits, port_state, offset);
 	}
 
 	return 0;
@@ -297,59 +279,48 @@ static void idio_24_gpio_set_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct idio_24_gpio *const idio24gpio = gpiochip_get_data(chip);
-	size_t i;
-	unsigned long bits_offset;
+	unsigned long offset;
 	unsigned long gpio_mask;
-	const unsigned int gpio_reg_size = 8;
-	const unsigned long port_mask = GENMASK(gpio_reg_size, 0);
-	unsigned long flags;
-	unsigned int out_state;
 	void __iomem *ports[] = {
 		&idio24gpio->reg->out0_7, &idio24gpio->reg->out8_15,
 		&idio24gpio->reg->out16_23
 	};
+	size_t index;
+	unsigned long bitmask;
+	unsigned long flags;
+	unsigned long out_state;
 	const unsigned long out_mode_mask = BIT(1);
-	const unsigned int ttl_offset = 48;
-	const size_t ttl_i = BIT_WORD(ttl_offset);
-	const unsigned int word_offset = ttl_offset % BITS_PER_LONG;
-	const unsigned long ttl_mask = (mask[ttl_i] >> word_offset) & port_mask;
-	const unsigned long ttl_bits = (bits[ttl_i] >> word_offset) & ttl_mask;
-
-	/* set bits are processed a gpio port register at a time */
-	for (i = 0; i < ARRAY_SIZE(ports); i++) {
-		/* gpio offset in bits array */
-		bits_offset = i * gpio_reg_size;
-
-		/* check if any set bits for current port */
-		gpio_mask = (*mask >> bits_offset) & port_mask;
-		if (!gpio_mask) {
-			/* no set bits for this port so move on to next port */
-			continue;
-		}
 
-		raw_spin_lock_irqsave(&idio24gpio->lock, flags);
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		index = offset / 8;
 
-		/* process output lines */
-		out_state = ioread8(ports[i]) & ~gpio_mask;
-		out_state |= (*bits >> bits_offset) & gpio_mask;
-		iowrite8(out_state, ports[i]);
+		bitmask = bitmap_get_value8(bits, offset) & gpio_mask;
 
+		raw_spin_lock_irqsave(&idio24gpio->lock, flags);
+
+		/* read bits from current gpio port (port 6 is TTL GPIO) */
+		if (index < 6) {
+			out_state = ioread8(ports[index]);
+		} else if (ioread8(&idio24gpio->reg->ctl) & out_mode_mask) {
+			out_state = ioread8(&idio24gpio->reg->ttl_out0_7);
+		} else {
+			/* skip TTL GPIO if set for input */
 			raw_spin_unlock_irqrestore(&idio24gpio->lock, flags);
+			continue;
 		}
 
-	/* check if setting TTL lines and if they are in output mode */
-	if (!ttl_mask || !(ioread8(&idio24gpio->reg->ctl) & out_mode_mask))
-		return;
-
-	/* handle TTL output */
-	raw_spin_lock_irqsave(&idio24gpio->lock, flags);
+		/* set requested bit states */
+		out_state &= ~gpio_mask;
+		out_state |= bitmask;
 
-	/* process output lines */
-	out_state = ioread8(&idio24gpio->reg->ttl_out0_7) & ~ttl_mask;
-	out_state |= ttl_bits;
+		/* write bits for current gpio port (port 6 is TTL GPIO) */
+		if (index < 6)
+			iowrite8(out_state, ports[index]);
+		else
 			iowrite8(out_state, &idio24gpio->reg->ttl_out0_7);
 
 		raw_spin_unlock_irqrestore(&idio24gpio->lock, flags);
+	}
 }
 
 static void idio_24_irq_ack(struct irq_data *data)

drivers/gpio/gpio-pisosr.c

@@ -96,16 +96,16 @@ static int pisosr_gpio_get_multiple(struct gpio_chip *chip,
 				    unsigned long *mask, unsigned long *bits)
 {
 	struct pisosr_gpio *gpio = gpiochip_get_data(chip);
-	unsigned int nbytes = DIV_ROUND_UP(chip->ngpio, 8);
-	unsigned int i, j;
+	unsigned long offset;
+	unsigned long gpio_mask;
+	unsigned long buffer_state;
 
 	pisosr_gpio_refresh(gpio);
 
 	bitmap_zero(bits, chip->ngpio);
-	for (i = 0; i < nbytes; i++) {
-		j = i / sizeof(unsigned long);
-		bits[j] |= ((unsigned long) gpio->buffer[i])
-			   << (8 * (i % sizeof(unsigned long)));
+	for_each_set_clump8(offset, gpio_mask, mask, chip->ngpio) {
+		buffer_state = gpio->buffer[offset / 8] & gpio_mask;
+		bitmap_set_value8(bits, buffer_state, offset);
 	}
 
 	return 0;

drivers/gpio/gpio-uniphier.c

@@ -15,9 +15,6 @@
 #include <linux/spinlock.h>
 #include <dt-bindings/gpio/uniphier-gpio.h>
 
-#define UNIPHIER_GPIO_BANK_MASK		\
-				GENMASK((UNIPHIER_GPIO_LINES_PER_BANK) - 1, 0)
-
 #define UNIPHIER_GPIO_IRQ_MAX_NUM	24
 
 #define UNIPHIER_GPIO_PORT_DATA		0x0	/* data */
@@ -150,15 +147,11 @@ static void uniphier_gpio_set(struct gpio_chip *chip,
 static void uniphier_gpio_set_multiple(struct gpio_chip *chip,
 				       unsigned long *mask, unsigned long *bits)
 {
-	unsigned int bank, shift, bank_mask, bank_bits;
-	int i;
+	unsigned long i, bank, bank_mask, bank_bits;
 
-	for (i = 0; i < chip->ngpio; i += UNIPHIER_GPIO_LINES_PER_BANK) {
+	for_each_set_clump8(i, bank_mask, mask, chip->ngpio) {
 		bank = i / UNIPHIER_GPIO_LINES_PER_BANK;
-		shift = i % BITS_PER_LONG;
-		bank_mask = (mask[BIT_WORD(i)] >> shift) &
-						UNIPHIER_GPIO_BANK_MASK;
-		bank_bits = bits[BIT_WORD(i)] >> shift;
+		bank_bits = bitmap_get_value8(bits, i);
 
 		uniphier_gpio_bank_write(chip, bank, UNIPHIER_GPIO_PORT_DATA,
 					 bank_mask, bank_bits);

drivers/gpio/gpio-ws16c48.c

@@ -129,42 +129,19 @@ static int ws16c48_gpio_get_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct ws16c48_gpio *const ws16c48gpio = gpiochip_get_data(chip);
-	const unsigned int gpio_reg_size = 8;
-	size_t i;
-	const size_t num_ports = chip->ngpio / gpio_reg_size;
-	unsigned int bits_offset;
-	size_t word_index;
-	unsigned int word_offset;
-	unsigned long word_mask;
-	const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
+	unsigned long offset;
+	unsigned long gpio_mask;
+	unsigned int port_addr;
 	unsigned long port_state;
 
 	/* clear bits array to a clean slate */
 	bitmap_zero(bits, chip->ngpio);
 
-	/* get bits are evaluated a gpio port register at a time */
-	for (i = 0; i < num_ports; i++) {
-		/* gpio offset in bits array */
-		bits_offset = i * gpio_reg_size;
+	for_each_set_clump8(offset, gpio_mask, mask, chip->ngpio) {
+		port_addr = ws16c48gpio->base + offset / 8;
+		port_state = inb(port_addr) & gpio_mask;
 
-		/* word index for bits array */
-		word_index = BIT_WORD(bits_offset);
-
-		/* gpio offset within current word of bits array */
-		word_offset = bits_offset % BITS_PER_LONG;
-
-		/* mask of get bits for current gpio within current word */
-		word_mask = mask[word_index] & (port_mask << word_offset);
-		if (!word_mask) {
-			/* no get bits in this port so skip to next one */
-			continue;
-		}
-
-		/* read bits from current gpio port */
-		port_state = inb(ws16c48gpio->base + i);
-
-		/* store acquired bits at respective bits array offset */
-		bits[word_index] |= (port_state << word_offset) & word_mask;
+		bitmap_set_value8(bits, port_state, offset);
 	}
 
 	return 0;
@@ -198,39 +175,29 @@ static void ws16c48_gpio_set_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct ws16c48_gpio *const ws16c48gpio = gpiochip_get_data(chip);
-	unsigned int i;
-	const unsigned int gpio_reg_size = 8;
-	unsigned int port;
-	unsigned int iomask;
-	unsigned int bitmask;
+	unsigned long offset;
+	unsigned long gpio_mask;
+	size_t index;
+	unsigned int port_addr;
+	unsigned long bitmask;
 	unsigned long flags;
 
-	/* set bits are evaluated a gpio register size at a time */
-	for (i = 0; i < chip->ngpio; i += gpio_reg_size) {
-		/* no more set bits in this mask word; skip to the next word */
-		if (!mask[BIT_WORD(i)]) {
-			i = (BIT_WORD(i) + 1) * BITS_PER_LONG - gpio_reg_size;
-			continue;
-		}
-
-		port = i / gpio_reg_size;
+	for_each_set_clump8(offset, gpio_mask, mask, chip->ngpio) {
+		index = offset / 8;
+		port_addr = ws16c48gpio->base + index;
 
 		/* mask out GPIO configured for input */
-		iomask = mask[BIT_WORD(i)] & ~ws16c48gpio->io_state[port];
-		bitmask = iomask & bits[BIT_WORD(i)];
+		gpio_mask &= ~ws16c48gpio->io_state[index];
+		bitmask = bitmap_get_value8(bits, offset) & gpio_mask;
 
 		raw_spin_lock_irqsave(&ws16c48gpio->lock, flags);
 
 		/* update output state data and set device gpio register */
-		ws16c48gpio->out_state[port] &= ~iomask;
-		ws16c48gpio->out_state[port] |= bitmask;
-		outb(ws16c48gpio->out_state[port], ws16c48gpio->base + port);
+		ws16c48gpio->out_state[index] &= ~gpio_mask;
+		ws16c48gpio->out_state[index] |= bitmask;
+		outb(ws16c48gpio->out_state[index], port_addr);
 
 		raw_spin_unlock_irqrestore(&ws16c48gpio->lock, flags);
-
-		/* prepare for next gpio register set */
-		mask[BIT_WORD(i)] >>= gpio_reg_size;
-		bits[BIT_WORD(i)] >>= gpio_reg_size;
 	}
 }
 

drivers/gpu/drm/drm_property.c

@@ -561,7 +561,7 @@ drm_property_create_blob(struct drm_device *dev, size_t length,
 	struct drm_property_blob *blob;
 	int ret;
 
-	if (!length || length > ULONG_MAX - sizeof(struct drm_property_blob))
+	if (!length || length > INT_MAX - sizeof(struct drm_property_blob))
 		return ERR_PTR(-EINVAL);
 
 	blob = kvzalloc(sizeof(struct drm_property_blob)+length, GFP_KERNEL);

drivers/misc/sram-exec.c

@@ -96,7 +96,7 @@ void *sram_exec_copy(struct gen_pool *pool, void *dst, void *src,
 	if (!part)
 		return NULL;
 
-	if (!addr_in_gen_pool(pool, (unsigned long)dst, size))
+	if (!gen_pool_has_addr(pool, (unsigned long)dst, size))
 		return NULL;
 
 	base = (unsigned long)part->base;

drivers/rapidio/rio-access.c

@@ -9,6 +9,8 @@
 #include <linux/rio.h>
 #include <linux/module.h>
 
+#include <linux/rio_drv.h>
+
 /*
  *  Wrappers for all RIO configuration access functions.  They just check
  *  alignment and call the low-level functions pointed to by rio_mport->ops.

drivers/rapidio/rio-driver.c

@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/rio.h>
 #include <linux/rio_ids.h>
+#include <linux/rio_drv.h>
 
 #include "rio.h"
 

drivers/thermal/intel/intel_soc_dts_iosf.c

@@ -6,6 +6,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
@@ -103,6 +104,7 @@ static int update_trip_temp(struct intel_soc_dts_sensor_entry *dts,
 	int status;
 	u32 temp_out;
 	u32 out;
+	unsigned long update_ptps;
 	u32 store_ptps;
 	u32 store_ptmc;
 	u32 store_te_out;
@@ -120,8 +122,10 @@ static int update_trip_temp(struct intel_soc_dts_sensor_entry *dts,
 	if (status)
 		return status;
 
-	out = (store_ptps & ~(0xFF << (thres_index * 8)));
-	out |= (temp_out & 0xFF) << (thres_index * 8);
+	update_ptps = store_ptps;
+	bitmap_set_value8(&update_ptps, temp_out & 0xFF, thres_index * 8);
+	out = update_ptps;
+
 	status = iosf_mbi_write(BT_MBI_UNIT_PMC, MBI_REG_WRITE,
 				SOC_DTS_OFFSET_PTPS, out);
 	if (status)
@@ -223,6 +227,7 @@ static int sys_get_curr_temp(struct thermal_zone_device *tzd,
 	u32 out;
 	struct intel_soc_dts_sensor_entry *dts;
 	struct intel_soc_dts_sensors *sensors;
+	unsigned long raw;
 
 	dts = tzd->devdata;
 	sensors = dts->sensors;
@@ -231,8 +236,8 @@ static int sys_get_curr_temp(struct thermal_zone_device *tzd,
 	if (status)
 		return status;
 
-	out = (out & dts->temp_mask) >> dts->temp_shift;
-	out -= SOC_DTS_TJMAX_ENCODING;
+	raw = out;
+	out = bitmap_get_value8(&raw, dts->id * 8) - SOC_DTS_TJMAX_ENCODING;
 	*temp = sensors->tj_max - out * 1000;
 
 	return 0;
@@ -280,11 +285,14 @@ static int add_dts_thermal_zone(int id, struct intel_soc_dts_sensor_entry *dts,
 				int read_only_trip_cnt)
 {
 	char name[10];
+	unsigned long trip;
 	int trip_count = 0;
 	int trip_mask = 0;
+	int writable_trip_cnt = 0;
+	unsigned long ptps;
 	u32 store_ptps;
+	unsigned long i;
 	int ret;
-	int i;
 
 	/* Store status to restor on exit */
 	ret = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ,
@@ -293,11 +301,10 @@ static int add_dts_thermal_zone(int id, struct intel_soc_dts_sensor_entry *dts,
 		goto err_ret;
 
 	dts->id = id;
-	dts->temp_mask = 0x00FF << (id * 8);
-	dts->temp_shift = id * 8;
 	if (notification_support) {
 		trip_count = min(SOC_MAX_DTS_TRIPS, trip_cnt);
-		trip_mask = BIT(trip_count - read_only_trip_cnt) - 1;
+		writable_trip_cnt = trip_count - read_only_trip_cnt;
+		trip_mask = GENMASK(writable_trip_cnt - 1, 0);
 	}
 
 	/* Check if the writable trip we provide is not used by BIOS */
@@ -306,11 +313,9 @@ static int add_dts_thermal_zone(int id, struct intel_soc_dts_sensor_entry *dts,
 	if (ret)
 		trip_mask = 0;
 	else {
-		for (i = 0; i < trip_count; ++i) {
-			if (trip_mask & BIT(i))
-				if (store_ptps & (0xff << (i * 8)))
-					trip_mask &= ~BIT(i);
-		}
+		ptps = store_ptps;
+		for_each_set_clump8(i, trip, &ptps, writable_trip_cnt * 8)
+			trip_mask &= ~BIT(i / 8);
 	}
 	dts->trip_mask = trip_mask;
 	dts->trip_count = trip_count;

drivers/thermal/intel/intel_soc_dts_iosf.h

@@ -24,8 +24,6 @@ struct intel_soc_dts_sensors;
 
 struct intel_soc_dts_sensor_entry {
 	int id;
-	u32 temp_mask;
-	u32 temp_shift;
 	u32 store_status;
 	u32 trip_mask;
 	u32 trip_count;

drivers/usb/core/hub.c

@@ -18,6 +18,7 @@
 #include <linux/sched/mm.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <linux/kcov.h>
 #include <linux/ioctl.h>
 #include <linux/usb.h>
 #include <linux/usbdevice_fs.h>
@@ -5484,6 +5485,8 @@ static void hub_event(struct work_struct *work)
 	hub_dev = hub->intfdev;
 	intf = to_usb_interface(hub_dev);
 
+	kcov_remote_start_usb((u64)hdev->bus->busnum);
+
 	dev_dbg(hub_dev, "state %d ports %d chg %04x evt %04x\n",
 			hdev->state, hdev->maxchild,
 			/* NOTE: expects max 15 ports... */
@@ -5590,6 +5593,8 @@ static void hub_event(struct work_struct *work)
 	/* Balance the stuff in kick_hub_wq() and allow autosuspend */
 	usb_autopm_put_interface(intf);
 	kref_put(&hub->kref, hub_release);
+
+	kcov_remote_stop();
 }
 
 static const struct usb_device_id hub_id_table[] = {