Merge tag 'core-mm-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull kmap updates from Thomas Gleixner:
 "The new preemtible kmap_local() implementation:

   - Consolidate all kmap_atomic() internals into a generic
     implementation which builds the base for the kmap_local() API and
     make the kmap_atomic() interface wrappers which handle the
     disabling/enabling of preemption and pagefaults.

   - Switch the storage from per-CPU to per task and provide scheduler
     support for clearing mapping when scheduling out and restoring them
     when scheduling back in.

   - Merge the migrate_disable/enable() code, which is also part of the
     scheduler pull request. This was required to make the kmap_local()
     interface available which does not disable preemption when a
     mapping is established. It has to disable migration instead to
     guarantee that the virtual address of the mapped slot is the same
     across preemption.

   - Provide better debug facilities: guard pages and enforced
     utilization of the mapping mechanics on 64bit systems when the
     architecture allows it.

   - Provide the new kmap_local() API which can now be used to cleanup
     the kmap_atomic() usage sites all over the place. Most of the usage
     sites do not require the implicit disabling of preemption and
     pagefaults so the penalty on 64bit and 32bit non-highmem systems is
     removed and quite some of the code can be simplified. A wholesale
     conversion is not possible because some usage depends on the
     implicit side effects and some need to be cleaned up because they
     work around these side effects.

     The migrate disable side effect is only effective on highmem
     systems and when enforced debugging is enabled. On 64bit and 32bit
     non-highmem systems the overhead is completely avoided"

* tag 'core-mm-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
  ARM: highmem: Fix cache_is_vivt() reference
  x86/crashdump/32: Simplify copy_oldmem_page()
  io-mapping: Provide iomap_local variant
  mm/highmem: Provide kmap_local*
  sched: highmem: Store local kmaps in task struct
  x86: Support kmap_local() forced debugging
  mm/highmem: Provide CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP
  mm/highmem: Provide and use CONFIG_DEBUG_KMAP_LOCAL
  microblaze/mm/highmem: Add dropped #ifdef back
  xtensa/mm/highmem: Make generic kmap_atomic() work correctly
  mm/highmem: Take kmap_high_get() properly into account
  highmem: High implementation details and document API
  Documentation/io-mapping: Remove outdated blurb
  io-mapping: Cleanup atomic iomap
  mm/highmem: Remove the old kmap_atomic cruft
  highmem: Get rid of kmap_types.h
  xtensa/mm/highmem: Switch to generic kmap atomic
  sparc/mm/highmem: Switch to generic kmap atomic
  powerpc/mm/highmem: Switch to generic kmap atomic
  nds32/mm/highmem: Switch to generic kmap atomic
  ...

1 files changed, 107 insertions, 187 deletions

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 14e6202ce47f..f597830f26b4 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -11,217 +11,137 @@
 
 #include <asm/cacheflush.h>
 
-#ifndef ARCH_HAS_FLUSH_ANON_PAGE
-static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr)
-{
-}
-#endif
+#include "highmem-internal.h"
 
-#ifndef ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
-static inline void flush_kernel_dcache_page(struct page *page)
-{
-}
-static inline void flush_kernel_vmap_range(void *vaddr, int size)
-{
-}
-static inline void invalidate_kernel_vmap_range(void *vaddr, int size)
-{
-}
-#endif
-
-#include <asm/kmap_types.h>
-
-#ifdef CONFIG_HIGHMEM
-extern void *kmap_atomic_high_prot(struct page *page, pgprot_t prot);
-extern void kunmap_atomic_high(void *kvaddr);
-#include <asm/highmem.h>
-
-#ifndef ARCH_HAS_KMAP_FLUSH_TLB
-static inline void kmap_flush_tlb(unsigned long addr) { }
-#endif
-
-#ifndef kmap_prot
-#define kmap_prot PAGE_KERNEL
-#endif
-
-void *kmap_high(struct page *page);
-static inline void *kmap(struct page *page)
-{
-	void *addr;
-
-	might_sleep();
-	if (!PageHighMem(page))
-		addr = page_address(page);
-	else
-		addr = kmap_high(page);
-	kmap_flush_tlb((unsigned long)addr);
-	return addr;
-}
-
-void kunmap_high(struct page *page);
-
-static inline void kunmap(struct page *page)
-{
-	might_sleep();
-	if (!PageHighMem(page))
-		return;
-	kunmap_high(page);
-}
-
-/*
- * kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because
- * no global lock is needed and because the kmap code must perform a global TLB
- * invalidation when the kmap pool wraps.
+/**
+ * kmap - Map a page for long term usage
+ * @page:	Pointer to the page to be mapped
+ *
+ * Returns: The virtual address of the mapping
+ *
+ * Can only be invoked from preemptible task context because on 32bit
+ * systems with CONFIG_HIGHMEM enabled this function might sleep.
  *
- * However when holding an atomic kmap it is not legal to sleep, so atomic
- * kmaps are appropriate for short, tight code paths only.
+ * For systems with CONFIG_HIGHMEM=n and for pages in the low memory area
+ * this returns the virtual address of the direct kernel mapping.
  *
- * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap
- * gives a more generic (and caching) interface. But kmap_atomic can
- * be used in IRQ contexts, so in some (very limited) cases we need
- * it.
+ * The returned virtual address is globally visible and valid up to the
+ * point where it is unmapped via kunmap(). The pointer can be handed to
+ * other contexts.
+ *
+ * For highmem pages on 32bit systems this can be slow as the mapping space
+ * is limited and protected by a global lock. In case that there is no
+ * mapping slot available the function blocks until a slot is released via
+ * kunmap().
  */
-static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
-{
-	preempt_disable();
-	pagefault_disable();
-	if (!PageHighMem(page))
-		return page_address(page);
-	return kmap_atomic_high_prot(page, prot);
-}
-#define kmap_atomic(page)	kmap_atomic_prot(page, kmap_prot)
-
-/* declarations for linux/mm/highmem.c */
-unsigned int nr_free_highpages(void);
-extern atomic_long_t _totalhigh_pages;
-static inline unsigned long totalhigh_pages(void)
-{
-	return (unsigned long)atomic_long_read(&_totalhigh_pages);
-}
-
-static inline void totalhigh_pages_inc(void)
-{
-	atomic_long_inc(&_totalhigh_pages);
-}
-
-static inline void totalhigh_pages_dec(void)
-{
-	atomic_long_dec(&_totalhigh_pages);
-}
-
-static inline void totalhigh_pages_add(long count)
-{
-	atomic_long_add(count, &_totalhigh_pages);
-}
-
-static inline void totalhigh_pages_set(long val)
-{
-	atomic_long_set(&_totalhigh_pages, val);
-}
-
-void kmap_flush_unused(void);
+static inline void *kmap(struct page *page);
 
-struct page *kmap_to_page(void *addr);
-
-#else /* CONFIG_HIGHMEM */
+/**
+ * kunmap - Unmap the virtual address mapped by kmap()
+ * @addr:	Virtual address to be unmapped
+ *
+ * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of
+ * pages in the low memory area.
+ */
+static inline void kunmap(struct page *page);
 
-static inline unsigned int nr_free_highpages(void) { return 0; }
+/**
+ * kmap_to_page - Get the page for a kmap'ed address
+ * @addr:	The address to look up
+ *
+ * Returns: The page which is mapped to @addr.
+ */
+static inline struct page *kmap_to_page(void *addr);
 
-static inline struct page *kmap_to_page(void *addr)
-{
-	return virt_to_page(addr);
-}
+/**
+ * kmap_flush_unused - Flush all unused kmap mappings in order to
+ *		       remove stray mappings
+ */
+static inline void kmap_flush_unused(void);
 
-static inline unsigned long totalhigh_pages(void) { return 0UL; }
+/**
+ * kmap_local_page - Map a page for temporary usage
+ * @page:	Pointer to the page to be mapped
+ *
+ * Returns: The virtual address of the mapping
+ *
+ * Can be invoked from any context.
+ *
+ * Requires careful handling when nesting multiple mappings because the map
+ * management is stack based. The unmap has to be in the reverse order of
+ * the map operation:
+ *
+ * addr1 = kmap_local_page(page1);
+ * addr2 = kmap_local_page(page2);
+ * ...
+ * kunmap_local(addr2);
+ * kunmap_local(addr1);
+ *
+ * Unmapping addr1 before addr2 is invalid and causes malfunction.
+ *
+ * Contrary to kmap() mappings the mapping is only valid in the context of
+ * the caller and cannot be handed to other contexts.
+ *
+ * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the
+ * virtual address of the direct mapping. Only real highmem pages are
+ * temporarily mapped.
+ *
+ * While it is significantly faster than kmap() for the higmem case it
+ * comes with restrictions about the pointer validity. Only use when really
+ * necessary.
+ *
+ * On HIGHMEM enabled systems mapping a highmem page has the side effect of
+ * disabling migration in order to keep the virtual address stable across
+ * preemption. No caller of kmap_local_page() can rely on this side effect.
+ */
+static inline void *kmap_local_page(struct page *page);
 
-static inline void *kmap(struct page *page)
-{
-	might_sleep();
-	return page_address(page);
-}
+/**
+ * kmap_atomic - Atomically map a page for temporary usage - Deprecated!
+ * @page:	Pointer to the page to be mapped
+ *
+ * Returns: The virtual address of the mapping
+ *
+ * Effectively a wrapper around kmap_local_page() which disables pagefaults
+ * and preemption.
+ *
+ * Do not use in new code. Use kmap_local_page() instead.
+ */
+static inline void *kmap_atomic(struct page *page);
 
-static inline void kunmap_high(struct page *page)
-{
-}
+/**
+ * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic()
+ * @addr:	Virtual address to be unmapped
+ *
+ * Counterpart to kmap_atomic().
+ *
+ * Effectively a wrapper around kunmap_local() which additionally undoes
+ * the side effects of kmap_atomic(), i.e. reenabling pagefaults and
+ * preemption.
+ */
 
-static inline void kunmap(struct page *page)
-{
-#ifdef ARCH_HAS_FLUSH_ON_KUNMAP
-	kunmap_flush_on_unmap(page_address(page));
-#endif
-}
+/* Highmem related interfaces for management code */
+static inline unsigned int nr_free_highpages(void);
+static inline unsigned long totalhigh_pages(void);
 
-static inline void *kmap_atomic(struct page *page)
+#ifndef ARCH_HAS_FLUSH_ANON_PAGE
+static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr)
 {
-	preempt_disable();
-	pagefault_disable();
-	return page_address(page);
 }
-#define kmap_atomic_prot(page, prot)	kmap_atomic(page)
-
-static inline void kunmap_atomic_high(void *addr)
-{
-	/*
-	 * Mostly nothing to do in the CONFIG_HIGHMEM=n case as kunmap_atomic()
-	 * handles re-enabling faults + preemption
-	 */
-#ifdef ARCH_HAS_FLUSH_ON_KUNMAP
-	kunmap_flush_on_unmap(addr);
 #endif
-}
-
-#define kmap_atomic_pfn(pfn)	kmap_atomic(pfn_to_page(pfn))
-
-#define kmap_flush_unused()	do {} while(0)
-
-#endif /* CONFIG_HIGHMEM */
-
-#if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
-
-DECLARE_PER_CPU(int, __kmap_atomic_idx);
 
-static inline int kmap_atomic_idx_push(void)
+#ifndef ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
+static inline void flush_kernel_dcache_page(struct page *page)
 {
-	int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1;
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-	WARN_ON_ONCE(in_irq() && !irqs_disabled());
-	BUG_ON(idx >= KM_TYPE_NR);
-#endif
-	return idx;
 }
-
-static inline int kmap_atomic_idx(void)
+static inline void flush_kernel_vmap_range(void *vaddr, int size)
 {
-	return __this_cpu_read(__kmap_atomic_idx) - 1;
 }
-
-static inline void kmap_atomic_idx_pop(void)
+static inline void invalidate_kernel_vmap_range(void *vaddr, int size)
 {
-#ifdef CONFIG_DEBUG_HIGHMEM
-	int idx = __this_cpu_dec_return(__kmap_atomic_idx);
-
-	BUG_ON(idx < 0);
-#else
-	__this_cpu_dec(__kmap_atomic_idx);
-#endif
 }
-
 #endif
 
-/*
- * Prevent people trying to call kunmap_atomic() as if it were kunmap()
- * kunmap_atomic() should get the return value of kmap_atomic, not the page.
- */
-#define kunmap_atomic(addr)                                     \
-do {                                                            \
-	BUILD_BUG_ON(__same_type((addr), struct page *));       \
-	kunmap_atomic_high(addr);                                  \
-	pagefault_enable();                                     \
-	preempt_enable();                                       \
-} while (0)
-
-
 /* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */
 #ifndef clear_user_highpage
 static inline void clear_user_highpage(struct page *page, unsigned long vaddr)