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, 5 insertions, 49 deletions

diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index 1b9f473c6369..c79912a6b196 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -36,9 +36,8 @@
  *   This means each only has 1 PGDIR_SIZE worth of kvaddr mappings, which means
  *   2M of kvaddr space for typical config (8K page and 11:8:13 traversal split)
  *
- * - fixmap anyhow needs a limited number of mappings. So 2M kvaddr == 256 PTE
- *   slots across NR_CPUS would be more than sufficient (generic code defines
- *   KM_TYPE_NR as 20).
+ * - The fixed KMAP slots for kmap_local/atomic() require KM_MAX_IDX slots per
+ *   CPU. So the number of CPUs sharing a single PTE page is limited.
  *
  * - pkmap being preemptible, in theory could do with more than 256 concurrent
  *   mappings. However, generic pkmap code: map_new_virtual(), doesn't traverse
@@ -47,48 +46,6 @@
  */
 
 extern pte_t * pkmap_page_table;
-static pte_t * fixmap_page_table;
-
-void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
-{
-	int idx, cpu_idx;
-	unsigned long vaddr;
-
-	cpu_idx = kmap_atomic_idx_push();
-	idx = cpu_idx + KM_TYPE_NR * smp_processor_id();
-	vaddr = FIXMAP_ADDR(idx);
-
-	set_pte_at(&init_mm, vaddr, fixmap_page_table + idx,
-		   mk_pte(page, prot));
-
-	return (void *)vaddr;
-}
-EXPORT_SYMBOL(kmap_atomic_high_prot);
-
-void kunmap_atomic_high(void *kv)
-{
-	unsigned long kvaddr = (unsigned long)kv;
-
-	if (kvaddr >= FIXMAP_BASE && kvaddr < (FIXMAP_BASE + FIXMAP_SIZE)) {
-
-		/*
-		 * Because preemption is disabled, this vaddr can be associated
-		 * with the current allocated index.
-		 * But in case of multiple live kmap_atomic(), it still relies on
-		 * callers to unmap in right order.
-		 */
-		int cpu_idx = kmap_atomic_idx();
-		int idx = cpu_idx + KM_TYPE_NR * smp_processor_id();
-
-		WARN_ON(kvaddr != FIXMAP_ADDR(idx));
-
-		pte_clear(&init_mm, kvaddr, fixmap_page_table + idx);
-		local_flush_tlb_kernel_range(kvaddr, kvaddr + PAGE_SIZE);
-
-		kmap_atomic_idx_pop();
-	}
-}
-EXPORT_SYMBOL(kunmap_atomic_high);
 
 static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr)
 {
@@ -108,10 +65,9 @@ void __init kmap_init(void)
 {
 	/* Due to recursive include hell, we can't do this in processor.h */
 	BUILD_BUG_ON(PAGE_OFFSET < (VMALLOC_END + FIXMAP_SIZE + PKMAP_SIZE));
+	BUILD_BUG_ON(LAST_PKMAP > PTRS_PER_PTE);
+	BUILD_BUG_ON(FIX_KMAP_SLOTS > PTRS_PER_PTE);
 
-	BUILD_BUG_ON(KM_TYPE_NR > PTRS_PER_PTE);
 	pkmap_page_table = alloc_kmap_pgtable(PKMAP_BASE);
-
-	BUILD_BUG_ON(LAST_PKMAP > PTRS_PER_PTE);
-	fixmap_page_table = alloc_kmap_pgtable(FIXMAP_BASE);
+	alloc_kmap_pgtable(FIXMAP_BASE);
 }