mm/mmu_gather.c

#include <linux/gfp.h>
#include <linux/highmem.h>
#include <linux/kernel.h>
#include <linux/mmdebug.h>
#include <linux/mm_types.h>
#include <linux/pagemap.h>
#include <linux/rcupdate.h>
#include <linux/smp.h>
#include <linux/swap.h>

#include <asm/pgalloc.h>
#include <asm/tlb.h>

#ifdef HAVE_GENERIC_MMU_GATHER

#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER

static bool tlb_next_batch(struct mmu_gather *tlb)
{
	struct mmu_gather_batch *batch;

	batch = tlb->active;
	if (batch->next) {
		tlb->active = batch->next;
		return true;
	}

	if (tlb->batch_count == MAX_GATHER_BATCH_COUNT)
		return false;

	batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
	if (!batch)
		return false;

	tlb->batch_count++;
	batch->next = NULL;
	batch->nr   = 0;
	batch->max  = MAX_GATHER_BATCH;

	tlb->active->next = batch;
	tlb->active = batch;

	return true;
}

static void tlb_batch_pages_flush(struct mmu_gather *tlb)
{
	struct mmu_gather_batch *batch;

	for (batch = &tlb->local; batch && batch->nr; batch = batch->next) {
		free_pages_and_swap_cache(batch->pages, batch->nr);
		batch->nr = 0;
	}
	tlb->active = &tlb->local;
}

static void tlb_batch_list_free(struct mmu_gather *tlb)
{
	struct mmu_gather_batch *batch, *next;

	for (batch = tlb->local.next; batch; batch = next) {
		next = batch->next;
		free_pages((unsigned long)batch, 0);
	}
	tlb->local.next = NULL;
}

bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size)
{
	struct mmu_gather_batch *batch;

	VM_BUG_ON(!tlb->end);

#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
	VM_WARN_ON(tlb->page_size != page_size);
#endif

	batch = tlb->active;
	/*
	 * Add the page and check if we are full. If so
	 * force a flush.
	 */
	batch->pages[batch->nr++] = page;
	if (batch->nr == batch->max) {
		if (!tlb_next_batch(tlb))
			return true;
		batch = tlb->active;
	}
	VM_BUG_ON_PAGE(batch->nr > batch->max, page);

	return false;
}

#endif /* HAVE_MMU_GATHER_NO_GATHER */

void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
				unsigned long start, unsigned long end)
{
	tlb->mm = mm;

	/* Is it from 0 to ~0? */
	tlb->fullmm     = !(start | (end+1));

#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
	tlb->need_flush_all = 0;
	tlb->local.next = NULL;
	tlb->local.nr   = 0;
	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
	tlb->active     = &tlb->local;
	tlb->batch_count = 0;
#endif

#ifdef CONFIG_HAVE_RCU_TABLE_FREE
	tlb->batch = NULL;
#endif
#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
	tlb->page_size = 0;
#endif

	__tlb_reset_range(tlb);
}

void tlb_flush_mmu_free(struct mmu_gather *tlb)
{
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
	tlb_table_flush(tlb);
#endif
#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
	tlb_batch_pages_flush(tlb);
#endif
}

void tlb_flush_mmu(struct mmu_gather *tlb)
{
	tlb_flush_mmu_tlbonly(tlb);
	tlb_flush_mmu_free(tlb);
}

/* tlb_finish_mmu
 *	Called at the end of the shootdown operation to free up any resources
 *	that were required.
 */
void arch_tlb_finish_mmu(struct mmu_gather *tlb,
		unsigned long start, unsigned long end, bool force)
{
	if (force) {
		__tlb_reset_range(tlb);
		__tlb_adjust_range(tlb, start, end - start);
	}

	tlb_flush_mmu(tlb);

	/* keep the page table cache within bounds */
	check_pgt_cache();
#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
	tlb_batch_list_free(tlb);
#endif
}

#endif /* HAVE_GENERIC_MMU_GATHER */

#ifdef CONFIG_HAVE_RCU_TABLE_FREE

/*
 * See the comment near struct mmu_table_batch.
 */

/*
 * If we want tlb_remove_table() to imply TLB invalidates.
 */
static inline void tlb_table_invalidate(struct mmu_gather *tlb)
{
#ifndef CONFIG_HAVE_RCU_TABLE_NO_INVALIDATE
	/*
	 * Invalidate page-table caches used by hardware walkers. Then we still
	 * need to RCU-sched wait while freeing the pages because software
	 * walkers can still be in-flight.
	 */
	tlb_flush_mmu_tlbonly(tlb);
#endif
}

static void tlb_remove_table_smp_sync(void *arg)
{
	/* Simply deliver the interrupt */
}

static void tlb_remove_table_one(void *table)
{
	/*
	 * This isn't an RCU grace period and hence the page-tables cannot be
	 * assumed to be actually RCU-freed.
	 *
	 * It is however sufficient for software page-table walkers that rely on
	 * IRQ disabling. See the comment near struct mmu_table_batch.
	 */
	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
	__tlb_remove_table(table);
}

static void tlb_remove_table_rcu(struct rcu_head *head)
{
	struct mmu_table_batch *batch;
	int i;

	batch = container_of(head, struct mmu_table_batch, rcu);

	for (i = 0; i < batch->nr; i++)
		__tlb_remove_table(batch->tables[i]);

	free_page((unsigned long)batch);
}

void tlb_table_flush(struct mmu_gather *tlb)
{
	struct mmu_table_batch **batch = &tlb->batch;

	if (*batch) {
		tlb_table_invalidate(tlb);
		call_rcu(&(*batch)->rcu, tlb_remove_table_rcu);
		*batch = NULL;
	}
}

void tlb_remove_table(struct mmu_gather *tlb, void *table)
{
	struct mmu_table_batch **batch = &tlb->batch;

	if (*batch == NULL) {
		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
		if (*batch == NULL) {
			tlb_table_invalidate(tlb);
			tlb_remove_table_one(table);
			return;
		}
		(*batch)->nr = 0;
	}

	(*batch)->tables[(*batch)->nr++] = table;
	if ((*batch)->nr == MAX_TABLE_BATCH)
		tlb_table_flush(tlb);
}

#endif /* CONFIG_HAVE_RCU_TABLE_FREE */

/**
 * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
 * @tlb: the mmu_gather structure to initialize
 * @mm: the mm_struct of the target address space
 * @start: start of the region that will be removed from the page-table
 * @end: end of the region that will be removed from the page-table
 *
 * Called to initialize an (on-stack) mmu_gather structure for page-table
 * tear-down from @mm. The @start and @end are set to 0 and -1
 * respectively when @mm is without users and we're going to destroy
 * the full address space (exit/execve).
 */
void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
			unsigned long start, unsigned long end)
{
	arch_tlb_gather_mmu(tlb, mm, start, end);
	inc_tlb_flush_pending(tlb->mm);
}

void tlb_finish_mmu(struct mmu_gather *tlb,
		unsigned long start, unsigned long end)
{
	/*
	 * If there are parallel threads are doing PTE changes on same range
	 * under non-exclusive lock(e.g., mmap_sem read-side) but defer TLB
	 * flush by batching, a thread has stable TLB entry can fail to flush
	 * the TLB by observing pte_none|!pte_dirty, for example so flush TLB
	 * forcefully if we detect parallel PTE batching threads.
	 */
	bool force = mm_tlb_flush_nested(tlb->mm);

	arch_tlb_finish_mmu(tlb, start, end, force);
	dec_tlb_flush_pending(tlb->mm);
}