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
  ...

2 files changed, 260 insertions, 15 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 390165ffbb0f..8c49d09da214 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -859,4 +859,7 @@ config ARCH_HAS_HUGEPD
 config MAPPING_DIRTY_HELPERS
         bool
 
+config KMAP_LOCAL
+	bool
+
 endmenu
diff --git a/mm/highmem.c b/mm/highmem.c
index 1352a27951e3..83f9660f168f 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -31,10 +31,6 @@
 #include <asm/tlbflush.h>
 #include <linux/vmalloc.h>
 
-#if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
-DEFINE_PER_CPU(int, __kmap_atomic_idx);
-#endif
-
 /*
  * Virtual_count is not a pure "count".
  *  0 means that it is not mapped, and has not been mapped
@@ -108,9 +104,7 @@ static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color)
 atomic_long_t _totalhigh_pages __read_mostly;
 EXPORT_SYMBOL(_totalhigh_pages);
 
-EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx);
-
-unsigned int nr_free_highpages (void)
+unsigned int __nr_free_highpages (void)
 {
 	struct zone *zone;
 	unsigned int pages = 0;
@@ -147,7 +141,7 @@ pte_t * pkmap_page_table;
 		do { spin_unlock(&kmap_lock); (void)(flags); } while (0)
 #endif
 
-struct page *kmap_to_page(void *vaddr)
+struct page *__kmap_to_page(void *vaddr)
 {
 	unsigned long addr = (unsigned long)vaddr;
 
@@ -158,7 +152,7 @@ struct page *kmap_to_page(void *vaddr)
 
 	return virt_to_page(addr);
 }
-EXPORT_SYMBOL(kmap_to_page);
+EXPORT_SYMBOL(__kmap_to_page);
 
 static void flush_all_zero_pkmaps(void)
 {
@@ -200,10 +194,7 @@ static void flush_all_zero_pkmaps(void)
 		flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
 }
 
-/**
- * kmap_flush_unused - flush all unused kmap mappings in order to remove stray mappings
- */
-void kmap_flush_unused(void)
+void __kmap_flush_unused(void)
 {
 	lock_kmap();
 	flush_all_zero_pkmaps();
@@ -367,9 +358,260 @@ void kunmap_high(struct page *page)
 	if (need_wakeup)
 		wake_up(pkmap_map_wait);
 }
-
 EXPORT_SYMBOL(kunmap_high);
-#endif	/* CONFIG_HIGHMEM */
+#endif /* CONFIG_HIGHMEM */
+
+#ifdef CONFIG_KMAP_LOCAL
+
+#include <asm/kmap_size.h>
+
+/*
+ * With DEBUG_KMAP_LOCAL the stack depth is doubled and every second
+ * slot is unused which acts as a guard page
+ */
+#ifdef CONFIG_DEBUG_KMAP_LOCAL
+# define KM_INCR	2
+#else
+# define KM_INCR	1
+#endif
+
+static inline int kmap_local_idx_push(void)
+{
+	WARN_ON_ONCE(in_irq() && !irqs_disabled());
+	current->kmap_ctrl.idx += KM_INCR;
+	BUG_ON(current->kmap_ctrl.idx >= KM_MAX_IDX);
+	return current->kmap_ctrl.idx - 1;
+}
+
+static inline int kmap_local_idx(void)
+{
+	return current->kmap_ctrl.idx - 1;
+}
+
+static inline void kmap_local_idx_pop(void)
+{
+	current->kmap_ctrl.idx -= KM_INCR;
+	BUG_ON(current->kmap_ctrl.idx < 0);
+}
+
+#ifndef arch_kmap_local_post_map
+# define arch_kmap_local_post_map(vaddr, pteval)	do { } while (0)
+#endif
+
+#ifndef arch_kmap_local_pre_unmap
+# define arch_kmap_local_pre_unmap(vaddr)		do { } while (0)
+#endif
+
+#ifndef arch_kmap_local_post_unmap
+# define arch_kmap_local_post_unmap(vaddr)		do { } while (0)
+#endif
+
+#ifndef arch_kmap_local_map_idx
+#define arch_kmap_local_map_idx(idx, pfn)	kmap_local_calc_idx(idx)
+#endif
+
+#ifndef arch_kmap_local_unmap_idx
+#define arch_kmap_local_unmap_idx(idx, vaddr)	kmap_local_calc_idx(idx)
+#endif
+
+#ifndef arch_kmap_local_high_get
+static inline void *arch_kmap_local_high_get(struct page *page)
+{
+	return NULL;
+}
+#endif
+
+/* Unmap a local mapping which was obtained by kmap_high_get() */
+static inline bool kmap_high_unmap_local(unsigned long vaddr)
+{
+#ifdef ARCH_NEEDS_KMAP_HIGH_GET
+	if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) {
+		kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
+		return true;
+	}
+#endif
+	return false;
+}
+
+static inline int kmap_local_calc_idx(int idx)
+{
+	return idx + KM_MAX_IDX * smp_processor_id();
+}
+
+static pte_t *__kmap_pte;
+
+static pte_t *kmap_get_pte(void)
+{
+	if (!__kmap_pte)
+		__kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
+	return __kmap_pte;
+}
+
+void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
+{
+	pte_t pteval, *kmap_pte = kmap_get_pte();
+	unsigned long vaddr;
+	int idx;
+
+	/*
+	 * Disable migration so resulting virtual address is stable
+	 * accross preemption.
+	 */
+	migrate_disable();
+	preempt_disable();
+	idx = arch_kmap_local_map_idx(kmap_local_idx_push(), pfn);
+	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+	BUG_ON(!pte_none(*(kmap_pte - idx)));
+	pteval = pfn_pte(pfn, prot);
+	set_pte_at(&init_mm, vaddr, kmap_pte - idx, pteval);
+	arch_kmap_local_post_map(vaddr, pteval);
+	current->kmap_ctrl.pteval[kmap_local_idx()] = pteval;
+	preempt_enable();
+
+	return (void *)vaddr;
+}
+EXPORT_SYMBOL_GPL(__kmap_local_pfn_prot);
+
+void *__kmap_local_page_prot(struct page *page, pgprot_t prot)
+{
+	void *kmap;
+
+	/*
+	 * To broaden the usage of the actual kmap_local() machinery always map
+	 * pages when debugging is enabled and the architecture has no problems
+	 * with alias mappings.
+	 */
+	if (!IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) && !PageHighMem(page))
+		return page_address(page);
+
+	/* Try kmap_high_get() if architecture has it enabled */
+	kmap = arch_kmap_local_high_get(page);
+	if (kmap)
+		return kmap;
+
+	return __kmap_local_pfn_prot(page_to_pfn(page), prot);
+}
+EXPORT_SYMBOL(__kmap_local_page_prot);
+
+void kunmap_local_indexed(void *vaddr)
+{
+	unsigned long addr = (unsigned long) vaddr & PAGE_MASK;
+	pte_t *kmap_pte = kmap_get_pte();
+	int idx;
+
+	if (addr < __fix_to_virt(FIX_KMAP_END) ||
+	    addr > __fix_to_virt(FIX_KMAP_BEGIN)) {
+		if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP)) {
+			/* This _should_ never happen! See above. */
+			WARN_ON_ONCE(1);
+			return;
+		}
+		/*
+		 * Handle mappings which were obtained by kmap_high_get()
+		 * first as the virtual address of such mappings is below
+		 * PAGE_OFFSET. Warn for all other addresses which are in
+		 * the user space part of the virtual address space.
+		 */
+		if (!kmap_high_unmap_local(addr))
+			WARN_ON_ONCE(addr < PAGE_OFFSET);
+		return;
+	}
+
+	preempt_disable();
+	idx = arch_kmap_local_unmap_idx(kmap_local_idx(), addr);
+	WARN_ON_ONCE(addr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
+
+	arch_kmap_local_pre_unmap(addr);
+	pte_clear(&init_mm, addr, kmap_pte - idx);
+	arch_kmap_local_post_unmap(addr);
+	current->kmap_ctrl.pteval[kmap_local_idx()] = __pte(0);
+	kmap_local_idx_pop();
+	preempt_enable();
+	migrate_enable();
+}
+EXPORT_SYMBOL(kunmap_local_indexed);
+
+/*
+ * Invoked before switch_to(). This is safe even when during or after
+ * clearing the maps an interrupt which needs a kmap_local happens because
+ * the task::kmap_ctrl.idx is not modified by the unmapping code so a
+ * nested kmap_local will use the next unused index and restore the index
+ * on unmap. The already cleared kmaps of the outgoing task are irrelevant
+ * because the interrupt context does not know about them. The same applies
+ * when scheduling back in for an interrupt which happens before the
+ * restore is complete.
+ */
+void __kmap_local_sched_out(void)
+{
+	struct task_struct *tsk = current;
+	pte_t *kmap_pte = kmap_get_pte();
+	int i;
+
+	/* Clear kmaps */
+	for (i = 0; i < tsk->kmap_ctrl.idx; i++) {
+		pte_t pteval = tsk->kmap_ctrl.pteval[i];
+		unsigned long addr;
+		int idx;
+
+		/* With debug all even slots are unmapped and act as guard */
+		if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) {
+			WARN_ON_ONCE(!pte_none(pteval));
+			continue;
+		}
+		if (WARN_ON_ONCE(pte_none(pteval)))
+			continue;
+
+		/*
+		 * This is a horrible hack for XTENSA to calculate the
+		 * coloured PTE index. Uses the PFN encoded into the pteval
+		 * and the map index calculation because the actual mapped
+		 * virtual address is not stored in task::kmap_ctrl.
+		 * For any sane architecture this is optimized out.
+		 */
+		idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
+
+		addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+		arch_kmap_local_pre_unmap(addr);
+		pte_clear(&init_mm, addr, kmap_pte - idx);
+		arch_kmap_local_post_unmap(addr);
+	}
+}
+
+void __kmap_local_sched_in(void)
+{
+	struct task_struct *tsk = current;
+	pte_t *kmap_pte = kmap_get_pte();
+	int i;
+
+	/* Restore kmaps */
+	for (i = 0; i < tsk->kmap_ctrl.idx; i++) {
+		pte_t pteval = tsk->kmap_ctrl.pteval[i];
+		unsigned long addr;
+		int idx;
+
+		/* With debug all even slots are unmapped and act as guard */
+		if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) {
+			WARN_ON_ONCE(!pte_none(pteval));
+			continue;
+		}
+		if (WARN_ON_ONCE(pte_none(pteval)))
+			continue;
+
+		/* See comment in __kmap_local_sched_out() */
+		idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
+		addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+		set_pte_at(&init_mm, addr, kmap_pte - idx, pteval);
+		arch_kmap_local_post_map(addr, pteval);
+	}
+}
+
+void kmap_local_fork(struct task_struct *tsk)
+{
+	if (WARN_ON_ONCE(tsk->kmap_ctrl.idx))
+		memset(&tsk->kmap_ctrl, 0, sizeof(tsk->kmap_ctrl));
+}
+
+#endif
 
 #if defined(HASHED_PAGE_VIRTUAL)